Working With A Manufacturer - What's a BOM?

So you've got a great idea and you want to bring it to market, but you don't know the first thing about hiring a manufacturer and working with them to get your product assembled? We are here to help. This is the first in a series of articles that we'll be writing that will help people learn how to work with us to get their product assembled. 

So, what's a BOM? Well, you probably already know what a BOM is (Bill of Materials) but what are we specifically looking for from a BOM.  

There are 3 vital pieces of information.   

1. Reference Designator - this will be the location of your component. Something like R1 for resistors or U1 for IC's.  You begin with a prefix and then assign them a unique number. Here are the common prefixes

• Capactiors "C"
• Connectors "J"
• Diodes "D"
• Displays "DISP"
• Ferrite Beads "FB"
• IC's "U"
• Inductors "L"
• LED's "LED"
• Modules "U"
• Oscillators (Crystals) "Y" or "X"
• Resistors "R"
• Resistor Networks "RN"
• Switches "SW"
• Test Points "TP"
• Transformers "T"
• Transistors "Q"

2. Manufacturer's Part Number - we'll need to know what part to put in the location you've specified. And what we are looking for is a specific manufacture's part number. Saying "100k ohm resistor" isn't quite enough information. Think for a second how many pieces of information need to be specified for just a resistor. Value, tolerance, size, wattage, composition, temperature coefficienct, and operating temperature. And that's just for resistors! It's just too much information than we'd like to decide for you.  But an excellent resource is the Common Parts Library which WAi helped assemble in partnership with Octopart. We regularly keep these parts in stock and find them to be readily available and inexpensive compared to their alternatives.

3. Quantity - this is helpful for purchasing purposes. If you used a 1K resistor in 90 different locations, we'd rather not count those locations one by one to determine how many of that part number to buy. The quantity column will also help us double check our work. If we program our equipment and it tells us that there are 89 locations and you have a quantity of 90 specified, that will send up a red flag that there might be an issue.  

There's plenty more information that some of our customers put in their BOM that are useful but inessential. 

4. Line Items - this is handy for communicating back and forth. If we mention "There's a typo on line item 16" you'll know exactly where to look at your BOM for the issue.  

5. Descriptions - Descriptions are really helpful. Internally, we use Digikey's descriptions as much as possible because it's formatted nicely and has all of the pertinent information. We can also use the description to make sure that your manufacturer's part number is correct. If your description says that it should be a 4.7k resistor and when we look up the manufacturer's part number and find that it's a 47k resistor, we can check with you to make sure you've chosen the correct part number. You'd be surprised how many mistakes we catch with this technique. 

6. Datasheets - it's pretty useful to have a hyperlink to datasheets for components. Sometimes manufacturer's don't publicly release their datasheets (I'm looking at you Broadcom!) So if you provide us a link to datasheets it helps us speed up the process of programming your board. But don't stress about it. It's not necessary.  

7. Hardware Details - providing a nice full description of a piece of off the shelf hardware is great. If you give us a part number from McMaster-Carr for a hex nut, that's great. But a good full description of the nut is even more valuable. Is it stainless steel, or galvanized? Is it 3/16", how many turns per inch, etc. When we have a nice full description we can confidently buy these parts from an alternative manufacturer. I love McMaster-Carr (seriously. I love McMaster-Carr) but they're expensive. And we can find hardware for far less money from other suppliers. 

When you're done, here's what a BOM will more or less look like. They're generally formatted in a table that can be parsed by Excel or another spreadsheet program. CSV files and tab separated files work great too. We'd honestly prefer them over a proprietary format like Excel or OpenOffice.

Example of a BOM (Bill Of Materials)

BOM's are vital. Will live and die by our customer's BOM. If you have any questions we'd love to hear from you. You can email me at cdenney@worthingtonassembly.com or give us a call at (413) 397-8260.  

A Visit To Mycronic To Learn About The My600 Jet Printer

When Tim Cook announced the pricing for the Apple Watch Edition he didn't say $9,999. He said $10,000. Because when you get to this kind of price point, you specify your price in "thousands of dollars" not just "dollars". 

Such is the world of capital equipment. Equipment pricing is measured in "tens-of-thousands"  of dollars. So when you evaluate equipment like this, you don't take it lightly. But for this one, I can't help but gush...

---

Concept

The My600 is an absolutely breathtaking piece of engineering. The people who designed this thing (in Sweden) deserve to have their names written in the engineering hall of fame (if such an institution exists). I didn't fully appreciate this until I watched this machine in action. Just look at this thing run.

This is the real speed of the machine. I absolutely swear it is not sped up. It is printing up to 600 dots every second. It does this on the fly. Meaning that it does not stop moving to deposit a dot. It automatically calculate the trajectory of the dot based on the vertical speed of the dot and the horizontal speed of the head. Think of a plane dropping a bomb on a target. The plane needs to drop the bomb sometimes miles before it sees the target, depending on the speed and elevation of the plane. 

The My600 uses the same physics as calculating when to drop a bomb

This is how it goes so fast. It doesn't need to stop movement in order to deposit solder. Think of how many calculations this thing needs to make every second in order to actually land this dot exactly where it belongs, with incredible accuracy. Here's a picture of a 0.5mm pitch QFN.  

0.5mm Pitch QFN

I took this picture through one optic of a microscope. Look at the video again. This entire component is probably less than 200 dots so the My600 can print this entire footprint in a fraction of a second.  

Home plating is possible too. Looks at R67

You can see how the individual dots create a line for the individual leads of the QFN. There are three dots that make up each line. The accuracy here is so impressive considering the speed of this machine. You can add more paste to that center ground pad. If you look closely you can see that there's a via in the center of the pad that would pull solder paste down into it. If the via pulled too much solder paste, you could just add extra. You can't do anything like this with a stencil. The stencil is just one thickness so you have to hope the engineer designed things with that in mind and didn't make the via too large.

---

Hardware

It all starts with a 4,000 lb granite composite frame. That's right. This whole machine is made from a rock. Not steel.  

4,000 pound granite composite frame. Anywhere you see gray or black paint, that is granite

The machine needs this ultra heavy, rigid frame for stability. At Mycronic they have this machine sitting on a poured concrete floor. While the machine was running, you could feel the vibration in your feet. I can only imagine what this machine would do to a steel frame.  

To the granite frame they add this cantilevered beam. It just floats in the air, affixed to only one side of the machine. Unlike 99% of all circuit board production equipment in this world that use a gantry mounted head (affixed to two sides of the machine), Mycronic chose to mount their head on this ultra light weight carbon fiber cantilevered support beam. 

Ultra light carbon fiber cantilever beam. Notice it's affixed to only one side.

I'm told that this carbon fiber beam is the second most expensive item on the whole machine. Only the granite frame is more expansive. And it shows. Just think of how straight this thing needs to be. Any sort of flex or bow would completely throw off the accuracy of the machine. Imagine if you have the dispense head at the far end of the beam and you whip the head in the Y direction at 3G's. What do you think that would do to the beam? It would want to bow like a golf club. And yet it doesn't. The My600 maintains a 33 micron (a micron is a millionth of a meter) accuracy at 1.33 Cpk. 

Copper power cables

Notice those huge copper cables on the side and floating above the beam? This is how power gets transferred to the dispense head and its various controls. Most machines would just use a simple ribbon cable to transfer power. But with this machine, because the head is experiencing up to 3G's of force, a typical ribbon cable simply would not hold up. So Mycronic designed these special cables to transfer power to the head while withstanding these ridiculous forces. Take a look at the video again and notice how much that cable is bouncing. That's deliberate. If it was too rigid, it could fail early. Designing it to be flexible gives it greater longevity. 

Linear motors drive this beast. See those rounded rectangular blocks? Those are the magnets that are used to help propel the beam. You'll also notice smaller rounded rectangular blocks on the beam itself. Those are the magnets used to help propel the head. They work on the same principal as some roller coasters you may have been on before. 

Linear motors

In order to cool all of this, the previous generation machine (the My500) used an offline chiller with a hose plumbed into the machine to keep the head cool. But the engineers at Mycronic came up with a way simpler solution. It's called a "vortex tube". Compressed air goes in, hot air escapes through an exhaust on one end, and cold air is directed to its destination out the other end. Absolutely amazing.

Finally, there's the actual dispense head, which gets mounted to this carbon fiber beam and is driven by the linear motors.

Dispense head holding a tube of solder paste.  

This I'm told was the most complicated engineering challenge the team faced. It seems simple, but as with most things that seem simple I'm sure it's incredibly complicated. Basically, pneumatic pressure pushes a plunger down, keeping the pump full of solder. The pump then controls a very precise amount of pressure to feed the piezo which actually releases the solder paste. The piezo is capable of 600Hz but averages out to about 300Hz. That's the buzzing sound you hear in the video.  

Port where the actual solder paste is released.  

To put the above image into perspective, that hole is about 0.33mm in diameter.  By comparison, an 0201 capacitor is a 0.6mm x 0.3mm rectangle. 

Opposite side of the port, showing the shaft of the pump.  

---

Software

The ultimate goal for all of this is to be able to deposit solder very precisely, but only where you want it. How do you define where you want it? Software.

My600 programming software.  

The programming of this machine is ridiculously easy and fast. You import one file, specify which locations are SMT, and then the software does the rest. I programmed one side of the BeagleBoy myself in less than 5 minutes, with almost no training whatsoever.  It was so easy and simple, that that's really all I have to say about the user interfacing software. I'm sure Mycronic spent a ridiculous amount of time on the backend software that controls everything. But for the user, there's really not much they need to do.

---

Benefits

There are things you can do with a jet printer that simply are not possible with a stencil. One of the challenges of using stencils is that you can only deposit one volume of paste across the whole assembly (there are stepped stencils but I won't get into them here). Your paste is only as thick as the stencil you've used. So your QFN's and 0402's have just the right amount of solder paste, but your 1206's and large inductors are starved for solder paste. Not an issue with a jet printer.

 For instance if you have a part that should have a greater volume of paste, you can program the machine to add extra paste at that location. And best of all, it will remember that type of part so that the next time it sees a part like that again, it will use the same profile as before. 

Slide from the Mycronic brochure

One of the biggest issues we have here is mixing complicated USB or SD card connectors on the same board with a very fine pitch QFN. You have to optimize your stencil around the QFN otherwise you'll have terrible yields. So oftentimes with USB connectors we have to manually add a dot of paste using a dispenser that's held by hand. The volume of paste that gets applied by this method is extremely variable, not to mention very time consuming. With a jet printer you can tell the machine to just make the paste a little thicker in one location and your issues are gone.

Then there are things that a jet printer can do that is not just difficult with a stencil, it's simply impossible. Like a 3D cavity in the board.

Try doing this with a stencil

Something like this would never have even been tried before jet printing. You'd have to add the paste by hand. A stencil could not simply reach in and apply paste here. 

How about PoP (Package-on-Package or Part-on-Part) components. Today when we get an order for assemblies with PoP components, we need to create the PoP component ahead of time using a special carrier. But with a jet printer, you just place the part, run it through the printer again, and then build your whole assembly.

Package-on-package with virtually no stacking limit

Or how about when you build a board but then only realize afterward that you stencil was clogged and didn't get any paste on a few pads. Now you have all of the components already populated all around the board. You can't put it back in a stencil printer. Your only choice would be to add paste by hand. Not an issue with a jet printer.

Pre-mounted components are not an issue

Pin-in-paste has been a thing for many many years. But in order to do it right, you really needed to design your product to make it work. Typically, only OEM's could do this because the designer and the manufacturer were either the same person or at least working in the same office. But we don't have that luxury. So when we get surface mount components with thru-hole pins (like USB ports and HDMI connectors) we have to add the solder by hand after they've gone through the SMT process. You can cut apertures in your stencil for those pins but it's never quite enough solder paste. With a jet printer you can just keep adding more and more paste to that area until you find the correct ratio that results in a perfect solder joint.

High quality pin-in-paste is a reality

One of the other great challenges we have with our stencil printer today is that we can only run one job at a time. If we have a high volume job setup, we can't really slide in a single-piece order without wasting a lot of time. The stencil needs to be removed, the blades either need to be cleaned or swapped, the conveyor adjusted, support pins moved, etc. There's a lot involved in changing over a stencil printer. If you're exceptionally fast at it, you can probably do it in about 10 minutes if everything goes well. But with a jet printer, you simply load a different program, the conveyor adjusts automatically, and you print the other board. So not only can you fit that single-piece board into the process, but you can even be running two jobs at the same time and just switch back and forth between them seamlessly. 

Which reminds me of another awesome feature. There's no need for support pins on this machine. The very first thing the machine does is map out the height of the PCB. If there is any bow or twisting of the PCB it's compensated for by this process. Take a look at the beginning of this video. You'll first see the board transferred into the machine on the conveyor, then a camera will locate the fiducials and then you will see a red laser shining on the board. This is the measurement process.

The machine does this mapping process the first time it runs a PCB. This is a thorough mapping process. Every PCB after this (of the same batch) it will perform a much shorter mapping process before printing. This helps keep the machine very precise, but also eliminate the need for support pins which are extremely important in a stencil printing process. When a squeegee blade presses down on the stencil, if the board underneath it is not well supported you will get a large gap and it will result in a terrible print. With this height mapping process it can compensate for a significant amount of warpage. 

Speaking of warpage, a jet printer can also compensate for any shrink or stretch of a PCB, the same way a pick and place machine can compensate for shrink and stretch. When a machine locates a PCB it uses 3 fiducials. The 1st fiducial locates the board in the X and Y dimension. The 2nd fiducial tells the machine how much the PCB is rotated. The 3rd fiducial tells the machine how much the board is stretched or shrunk from the board house. With a stencil this is simply impossible. You just line up the PCB as close as you can and hope for the best. You're not going to stretch your stencil at all. This is normally not an issue, but if you were to run a very large board with very fine pitch components, it could become a real issue. A jet printer could simply compensate for this with math and be done with it.

You also save a ton of solder paste with this machine. A typical stencil printing operation, with a lot of changeover, results in well over 50% solder paste being wasted to the cleaning process. But with a jet printer, all the paste that's wasted is during purge and calibration. There is no cleaning process. No blades to wipe solder paste off of. No stencil to keep clean. Some My600 customers are reporting 98.5% utilization. Last year we spent $4545.80 on solder paste. And we likely through away over $2,000 worth of it. That's not nothing.

---

Decisions

There is no question that this technology is the way of the future. But remember the opening paragraph? All these benefits don't come cheap. Mycronic knows what they have here and they know it's great. Time to put my negotiator hat on.

Production Begins on the BeagleBoy Gaming Cape for BeagleBone

Just shot a quick video to share the progress of the BeagleBoy Gaming Cape for the BeagleBone.

Also, here are pictures of the top side and the bottom side of the boards. This picture is just of the SMT portion of the assembly, before the thru-hole parts get populated. 

BeagleBoy Top Side SMT

BeagleBoy Bottom Side SMT

Best Way To Export XY Data From Eagle

A customer of ours recently wrote a great blog post about how he exports XY data from Eagle. He was new to the process and upon investigating found that it wasn't as easy as you might expect. Go check out his post here if you'd like to find an easy way to do this yourself.

Mention in The Boston Globe

We got a nice mention on the front page of the Sunday edition of The Boston Globe this weekend. The piece, written by Jon Christian, was all about our New England Factory Tours group that we organize on Meetup. We'll be hosting another group tour here shortly. Check out the tours page to see upcoming events.

PCB Design - Minimum Silkscreen Parameters

Just a quick note today about silkscreen and how to make a success of it. Bigger silkscreen is easier to manufacture so if you can get away with larger characters and wider lines, go for it. The team here will appreciate you saving their vision too (microscopes are expensive).

But if you have a small product and still want silkscreen there are some parameters you might find useful. There are two ways to put silkscreen onto a PCB. A conventional squeegee and screen, or the more expensive automated computer controlled inkjet printer. 

Squeegee and Screen: Font Size 30 mil x 30 mil, with a 6 mil draw (line width)

Inkjet Printer: Font Size 20 mil x 30 mil, with a 5 mil draw (line width)

Remember,  these are minimums, so you're still pushing the process. If you design a little larger then your silkscreen will fit comfortably within the process window.

I hope you find that useful. As always, if you have any questions, please feel free to get in touch. My email address is cdenney@worthingtonassembly.com and our phone number is (413) 397-8260.

We Have A New Website

It had recently come to our attention that our website was a bit... long in the tooth. So we spent some time over the holiday break to update our website.

The short story is, we have a fresh new look and the layout is much simpler and should load much faster.

The long story is that we were formerly hosted on HostGator and used Wordpress as our content management system. This worked ok, and was SUPER cheap, but there's so much management with Wordpress. We would get so much spam that we had to turn off our commenting system. Plus, in order to get things to render properly in all browsers we had to constantly edit the code that displays the page. The worst part is that whenever we had to perform an update to the theme (which was quite often) we'd have to re-edit the code every time. Eventually, we just got tired of dealing with it and let it languish. And something as important as a website should not be neglected. 

I've been hearing ads for Squarespace for years. They even had a commercial for the 2014 Super Bowl. I had avoided trying it because I didn't want to learn something new. But after playing with it for just 30 minutes, I felt like an expert. The software is really impressive and the mobile app for putting together blog posts is really slick. So we decided to switch over to Squarespace for hosting our website and we're pleased with the results. If you haven't checked it out head on over to www.worthingtonassembly.com and take a look.

For those of you who subscribed to the blog via email, nothing should change except the delivery system of the email. You'll be getting the emails from MailChimp now and the format should look a little different. For those of you that subscribed via RSS, you will need to update your RSS URL. I'm just not technically astute enough to know how to automatically do this. And if you're reading this, you're presumably interested enough to want to resubscribe manually. The new URL is http://www.worthingtonassembly.com/blog/?format=rss

Thank you all for reading this blog and if you ever have any questions, please don't hesitate to get in touch.

Octopart's Common Parts Library

Today Octopart announced what I think is a really valuable tool. The Common Parts Library We worked with Sam and Janine over at Octopart and helped them identify popular, and more importantly, readily available parts to build a common parts library. This will be a library of components that are known to be well stocked at distributors and perhaps even your contract manufacturer (like us). What will make this library particularly valuable is when you're designing a new product and you just need to find a basic resistor, cap, LED, oscillator, or some other such part to perform a simple task, without diving into the complicated filter engines of large distributors.

Just browsing the library makes me want to design a new board. I hope you find it valuable and let us know if you think anything is missing.

Tessel Manufacturing

Here's a video we put together to show the Tessel being manufactured at our site in South Deerfield, MA. http://youtu.be/KiD3BK56GrI

Cloud Based Circuit Board Assembly

We are so excited to finally be able to announce that WAi and CircuitHub have partnered together to change the way circuit boards get assembled.

The short version is, you can head over to CircuitHub.com and have your BOM, PCB, and Assembly quoted instantly via CircuitHub's app. CircuitHub handles all of the ordering and logistics for you and boards just arrive at your door. But it goes much much deeper than that.

Here's the long version...

The path to this type of service is littered with the remains of countless hours and effort to make buying assembled PCB's easier. Assembly is expensive, there's a lot of duplicated effort, and you really need to have experience with the whole process in order to get what you expect. Finding trusted partners (like WAi) is not easy. So for years people have been trying to make it easier and less expensive.

CircuitHub's idea is simple. Use your own EDA tool, upload your files, and choose specific manufacturers for each of your parts. From there they take advantage of the community they're building to standardize their component library and buy in bulk, then pass the savings onto their customers.

Let's take an example of a typical circuit board we see here. Your BOM for a single piece is about $20. Now you need to buy circuit boards. Well you only need 10 so that'll probably run you about $300. Then you need to get them assembled. Your assembly house has a ton of work they need to do in order to prepare to build your assembly. So you're looking at about $500 for the assembly plus a $300 stencil. So to get just 10 boards assembled, you're going to be out $1,300.

One of the advantages that large companies have over small companies is that they can support their own in house manufacturing and not rely on contract manufacturers like ourselves. When you have a dedicated engineering team, they can stick to a standard component library and then the business can buy those components in large quantities and save a lot of money. In contract manufacturing, you need to buy very small quantities because every engineer is using a different part. So we need to purchase exactly the right part for you that you specified. Using CircuitHub's "Part Rank" the community decides which parts should be used. When all of the designers are using the same 10K resistor or Atmel chip, we can buy 10,000 of them instead of just 6 for your project alone. To give you an idea of the cost savings we're talking about, for a run of the mill MCU like the ATMEGA32U4-AUR we would have to buy each chip at about $7.00. If we could buy 10,000 because everybody is using them, then we could pay about $3.50. That's half. Now multiply that kind of cost savings across your entire BOM. Now you're getting an idea of just how much money we can save here.

So now we've reduced the cost of your BOM from $20 to $10. Over 10 boards, that's a $100 savings.

Now to buy your boards. Well you're just a small guy. You don't buy a whole lot so the board house is going to have to put in extra effort to manage your build. So you're going to pay a premium rate. But with CircuitHub, since they're buying for the whole community, they'll have purchasing power and leverage that the little guy can only dream of.

Assembly is where a huge cost comes in. Stencils are expensive, programming the machines, setting up the feeders, profiling your assembly for the reflow oven, I could go on. This is where CircuitHub truly shines.

They've fully integrated their software into our systems. They have the ability to read our inventory levels, set up automated purchasing, automatically push programs directly into our pick and place machines, auto generate purchase orders and define production sequences. All of these things today are done manually, by a person sitting at their desk and parsing the information supplied to them to figure out what is required to assemble your circuit board. These tools should significantly reduce costs and we fully expect that CircuitHub will be able to beat our own internal pricing on most orders because of these efficiencies.

Not only that, but when the community settles around a fixed number of components, these components can have feeders dedicated to them. So we only have to plug the feeder into the machine and say "Go!" For small prototype runs of about 10 pieces, easily 25% of the cost is simply loading feeders with the components needed for each job.

Yield can be improved as well. We've seen easily over 20 different footprints for an 0603 resistor. That is crazy. Each footprint has its own characteristics in the reflow oven and not all of them work well. It's not uncommon to get a great deal of "tombstone" or "head-in-pillow" defects from a poor footprint. But if you use CircuitHub's footprint, then you know that we've seen it before and we can guarantee a high yield with that footprint.

I cannot tell you how excited we are to be a part of this and I can't wait for this awesome community of engineers and developers to start making cool products that we can all enjoy at an affordable price.

- Chris Denney, CTO

Video: The Machine to Build the Machines

Fascinating video of how the original NeXT Cube's circuit board was made. It's actually a fairly good explanation of how SMT manufacturing is still done today. It is a little different (and much faster) but all the basics are there. What's so interesting to me is how far ahead of their time these manufacturing engineers were. They had 3-dimensional solder paste inspection in the 80's. That's amazing. 3D SPI has mostly been considered a modern technology. The NeXT engineers were truly ahead of their time. I would love to talk to whomever was responsible for this assembly line someday.

Selective Soldering Tips: Using the Machine for Rework

Ok, I confess. Sometimes we do make mistakes. As much as I hate to admit it, it does happen. For example, we've seen headers not fully seated to the board. They're a little bit crooked or one edge is touching the PCB, while the other edge is so far up in the air that you can't even see the pin protruding through the other side of the board. Other times, you have an edge connector that needs to protrude through a cover panel and there's no room for play. The connector must be perfectly flat and perfectly square. If you find yourself in this situation, your selective soldering machine can be your best friend. Warning! On some machines, you may be required to bypass security features. Please consult your manufacturer before bypassing anything designed to protect you from a dangerous machine.

If your connector is larger than the size of your nozzle, you'll need to program the machine to "walk" back and forth over the pins of the connector, as seen in the image above. There's a limit to how long of a connector you could reasonably rework using this method. But we've been able to fix 2" long connectors on 4 layer boards. The key was to make sure the nozzle could dwell a little bit on the pins that were connected to ground.

Every connector is different. Some connectors will become damaged with its much exposure to heat. The plastics just are not designed to handle it. For these connectors, we find it's best to just remove the entire connector and insert a brand new one. Other connectors however hold up well under the heat and you'll be able to apply slight pressure with your hand to push them back through the board. Be careful however, as a lot of times pushing the pins down will also push the solder down, and you'll have no top side filet.

Make sure to preheat the board. You don't want to hit this cold board with a bunch of molten solder. The thermal shock could shorten the lifetime of the assembly. So make sure it's nice and hot before you begin.

Link: The Hardware Revolution Is Upon Us And Why It Matters

Link: The Hardware Revolution Is Upon Us And Why It Matters Excellent article from venture capitalist firm True Ventures. We're seeing more and more investment in small businesses that are trying out new hardware ideas. Finally the venture capitalist world is waking up to this. There's so much I could say about this but True Ventures has already said it so well.

Selective Soldering Tips: Touching Surface Mount Components

This is just one article in a series of articles discussing tips and tricks for using a selective soldering machine. Here at Worthington Assembly Inc. we have a selective soldering machine manufactured by RPS Automation. Our particular model is a 2010 Rhythm model. These article are written by the same person who's used this machine every day for years. One of the beautiful things about selective soldering machines (vs. wave soldering machines) is that you can easily route around surface mount components that are mounted on the bottom side of the board. But it's not always that easy. For example, what happens when the board designer ran out of room and had to put surface mount components right next to the thru-hole components?

Well, believe it or not, you can actually safely make contact with surface mount components, so long as you reflow only one side of the component at a time. This requires that the design of the board has the surface mount components perpendicular to the plated thru-holes.

As you can see in the image above, the path of the nozzle crosses right over 9 surface mount components. The area where the nozzle makes contact with the component will reflow the solder that was deposited from solder paste, but the opposite side of the component will remain solid and hold the component in place. This can definitely make you a little nervous the first time you try it, but I assure you that component will stay put.

It would be a good idea to let your board designers know about this. Many designers would like to use every square centimeter of their board, and letting them know that they can put surface mount components very close to their plated thru-holes, so long as they are perpendicular to the holes, will certainly make them happy.

As always, if you have any questions, feel free to give me a call at (413) 624-6879 or send me an email at cdenney@worthingtonassembly.com.

WAi - Best Practices

I'd like to announce that we've added a new section to our website called "Best Practices".

Over the years, customers have asked us how they can best design their boards so that they're as simple for WAi to build as possible. A lot of the questions revolve around how our automated systems handle the circuit boards during the assembly process. So the first document we put together is called "WAi Board Design - Best Practices for Automated Handling" which can be found here. 

We'll try to update this page whenever we find customers asking us the same questions regularly. If you have a question about how best to design your board, please get in touch. We're happy to help.

The Top 10 Myths About Selecting a Contract Manufacturing Partner

Ron Keith (CEO) of Riverwood Solutions wrote a nice article for Industry Week discussing myths about selecting a contract manufacturing partner. 

I generally don't care for "top ten" lists, but I understand their appeal. Regardless, Ron seems to have his wits about him and makes many sound points. I particularly appreciated this sentence.

Effectively working with contract manufacturing is a fairly complex business relationship that must function well across a number of functional areas.

Link: How to Do On-Shoring Right

How to Do On-Shoring Right Great article discussing Avigilon's domestic manufacturing. Interesting that they're manufacturing in Canada when they're a US company, but I'm sure they have their reasons. Either way, it's obvious that manufacturing in North America can be done effectively and cheaply.

Design for Manufacturability (DFM): Use Surface Mount Components (SMT) - Part 3 of Many

This is just one article in a series of articles discussing design for manufacturability for electronic assemblies. As a contract manufacturer we see every possible design decision you can imagine. We know what works, and we know what doesn't. We're happy to look at your assembly for any manufacturability concerns, whether we're building the assembly or not. Remember, rule number 1 of DFM for electronic assemblies

"Whenever possible, use surface mount components instead of thru-hole components."

In my first article discussing the importance of using SMT components instead of thru-hole components I mentioned that there are exceptions. The most obvious and important exception is any component that is going to experience a lot of external force. Generally, these are any type of connector where the user will be plugging and unplugging cables often. The amount of force that these connectors experience can be pretty light. But what happens is, overtime, all of those forces stack up and cause the solder joints to weaken. Eventually, those solder joints, or the copper pads that they're connected to, will fracture and you will be left with a broken product.

But connector designers have become wise to this. A lot of modern SMT connectors are coming with tooling pins that are inserted into the board, without solder, or massive leads that are soldered to equally massive copper pads, that can help direct some of the brunt of the force away from the fragile solder joints and copper pads.

IMG_0949 - Version 2

As you can see in this picture, there are is a huge contact area on the edges of these D-Sub connectors. These connectors are rated for over 400 cycles. It is very rare for any connector to see that many cycles (except for cell phone connectors which may see as many as 1,000 cycles in its lifetime and they still use SMT connectors). This component was placed automatically with a machine and soldered the same way as all of the other surface mount components on this board. This takes far less time for us than any thru-hole equivalent, and ultimately saved our customer a lot of money.

So, even when it seems like a thru-hole component is absolutely necessary, please consider the alternative. It may save you a lot of money too.

As always, if you have any questions, feel free to send me an email at cdenney@worthingtonassembly.com or follow me on Twitter @WAssembly.

Design for Manufacturability (DFM): Use Surface Mount Components (SMT) - Part 2 of Many

This is just one article in a series of articles discussing design for manufacturability for electronic assemblies. As a contract manufacturer we see every possible design decision you can imagine. We know what works, and we know what doesn't. We're happy to look at your assembly for any manufacturability concerns, whether we're building the assembly or not. Remember, rule number 1 of DFM for electronic assemblies

"Whenever possible, use surface mount components instead of thru-hole components."

The number one reason we tend to hear here at Worthington Assembly, about why designers don't want to design their boards with SMT components is that if the designer needs to remove components himself then SMT components are too difficult to work with. This also happens to be the worst reason in my opinion for choosing thru-hole components. SMT components are actually far easier to work on with just a soldering iron than thru-hole components. When a thru-hole component is well soldered, you're going to have a really hard time remove it with just a soldering iron. You have to heat up one leg, grab it with a pair of pliers, pull the lead through the hole, and pray that you don't damage the barrel while doing it. Then you need to do the same to the other side. SMT components however, are quite simple to remove with a soldering iron. We call it the old "blob of solder" removal method. Take your soldering iron, take your solder wire, blob a whole bunch of it on the tip of the iron, set that blob onto of your SMT resistor and then just lift up. The surface tension from the solder will cause the SMT resistor to come right up with the tip of the soldering iron. It could not be any easier.

IMG_0959

Now, there's another reason designers may choose thru-hole components instead of SMT components that is related to what we just discussed. This is the thought that it's easier to assemble a thru-hole board by hand than it is to assemble an SMT board by hand. This can be true. Sometimes it is easier to procure material and handle that material than it is to handle the same SMT material. If you're building just one board, and only one board forever, then this is probably ok. DFM shouldn't even be considered in that case. But if you expect to sell even a few dozen pieces of your design (or millions!) then you will definitely want to start with an SMT design from the beginning. And I think you will be surprised. With the right tools, like a tweezer soldering iron, SMT components can be soldered really easily.

As always, if you have any questions, feel free to send me an email at cdenney@worthingtonassembly.com or follow me on Twitter @WAssembly.

Design for Manufacturability (DFM): Use Surface Mount Components (SMT) - Part 1 of Many

This is just one article in a series of articles discussing design for manufacturability for electronic assemblies. As a contract manufacturer we see every possible design decision you can imagine. We know what works, and we know what doesn't. We're happy to look at your assembly for any manufacturability concerns, whether we're building the assembly or not. Surface Mount Technology (SMT). The single greatest thing to happen to the manufacturability of electronics since the printed circuit board itself. Rule number 1 of DFM for electronic assemblies

"Whenever possible, use surface mount components instead of thru-hole components."

There are exceptions of course, but generally speaking surface mount components are almost always easier to assemble than thru-hole components. Primarily, this is because of the equipment that most electronics manufacturers employ. Even if your contract manufacturer has fully automated thru-hole equipment, it's likely still easier for them to assemble your design using surface mount components than it is thru-hole components. Today, the fastest SMT machines can pick and place components as fast as 120,000 times per hour. The fastest thru-hole machines still pale in comparison at 26,000 components per hour, and thats only for axial components. Radials are even slower to assemble at 22,000 components per hour.

Surface Mount Example

Remember, time is money when it comes to assembly work. Your manufacturer is charging you for their time. So if he can assemble your board at 120,000 CPH instead of 22,000 CPH, he's going to be able to deliver your product sooner and you'll be saving money.

But placing/inserting the components is only half the battle. You still need to solder it. With surface mount components, all of the soldering is done automatically using solder paste and a reflow oven. Thru-hole components need to either be wave soldered (if designed properly), selectively soldered (if designed poorly), or *gasp* hand soldered (when you really just didn't even think about manufacturability). Talk about taking a long time. Thru-hole soldering is not as easy as it might seem. Yeah one or two joints here or there can be pretty easy. But to solder thousands of solder joints by hand, consistently, year after year, takes a special person with a lot of skill and experience. And those people don't come cheap. Machines on the other hand, while the initial investment is high, are very cheap compared to a competent soldering technician. Time is money.

As always, if you have any questions, feel free to send me an email at cdenney@worthingtonassembly.com or follow me on Twitter @WAssembly.