Machine Vision 101
The following article presents some things to consider when purchasing a vision system. Whether you buy from us, or you buy from a competitor, these are some thoughts to consider. Technical aspects of vision system integration can involve confusing jargon (i.e. CCD vs. CMOS, Line Scan vs. Area Scan, or GigE vs. Camera Link vs. FireWire). Begin by asking yourself these simple questions:
- What type of inspection/defect are you trying to find?
- How can this enhance current business operations?
- What are the short and long term benefits of the solution?
- What are the potential limitations involved?
- Will this solution fit the business' needs?
Give yourself a plainspoken sense of capabilities, so you can determine if machine vision is right for your company, before diving into the details of an implementation. If you like to discuss these points further, call Artemis Vision at (303)832-1111 for a free consultation.
In-line vs. Off-line Inspections:
Do you need to inspect parts on the production line, or off-line at a measuring station?
In-line systems automate the plant by continually monitoring production, while off-line systems give QC teams another great tool to do their jobs more effectively. Off-line measurement generally have a cheaper price associated with the system since more standardized products exist, and there is less integration work needed. However, labor cost savings become less significant because employees still need to sample regularly.
"Off-the-shelf" Product vs. Custom System:
Off-the-shelf products are available for common vision inspections, such as, print and proof comparison, bar code scanner, etc. While a ready-to-use product may be the answer at time, an integrator has the capability to modify these products to fully serve the client's needs. Each situation can be unique and while there are so many options to consider, Artemis Vision can discuss talk through many of these to determine which solution would be best for you.
Flexibility for the Future
Products change, new product lines are added and others are removed. A vision system typically performs a precise inspection recipe for a specific product. Unless someone reprograms it, the system typically cannot inspect the new part. It knows a certain batch of features to verify and if those features change the part doesn't pass inspection because it doesn't look like the old part the system is supposed to recognize. If the new part passes the same system without modifying the inspection recipe it may be time to question the accuracy of the system if critical features of the part have been changed.
Buyers may initially spend $50k on a system, but find that additional changes may be required as products changes occur.If you make a product that tends to change from year-to-year, it is a good idea to include a support plan with your system. Artemis Vision can discuss options and how much support may be required over time, and ensure that costs are clear from the beginning. Although, some systems may not require any ongoing support, it is always important to discuss what happens after implementation.
Innovative manufacturers inherently create new products overtime that are not extensively tested for every issue at the time and despite our best efforts, new issues may arise. For example, tolerance on the calipers may change because of unforeseen interaction in cold climates with older disks. Vision systems can record every part and recall specific batches by serial codes, as needed. Depending on how much information we have from the point of sale, we may be able to call up the 50 customers whose caliper doesn't meet new tolerances instead of recalling all 500,000 units. Targeted recalls can avoid huge cost implications involved with changes, as well as, associated negative publicity.
|Avoid Waste:||Vision systems detect problems as they happen. If a critical diameter moves out of spec, the vision system is capable of catching and stopping that error in its tracks. This avoids any further waste being generated.|
Time wasted with scraps and production time can cost more than raw materials. Identifying problems immediately reduces downtime and saves the plant money. In some cases the vision system can correct the deviation from spec, automatically. For instance, if the diameter problem is because the mold is too hot, the system can talk to the cooling system and dial up coolant pressure, which will avoid shutdown.
|Repeatability:||Vision systems provide a consistent standard across plants, production lines, shifts and production cycles. Operators may be fatigued or make common mistakes and despite their best efforts, they may not apply the exact same standard every time. With multiple operators this this issue compounds itself and soon there may be significant variability.|
|Lower Labor Costs:||There are a variety of vision inspection methods, and additional steps that can be taken to generate significant labor savings.|
|Higher Quality:||Sampling can catch statistical deviations from spec, however a wholesome vision system can catch the intermittent defects sampling can miss. From samples we can estimate a process sigma and Cpk and conclude if defects will be rare enough. Vision systems do not add extra costs when checking every part, and can eliminate any defects found. For example, when trying to achieve six sigma status or 3.4 defects per million during a process, a vision system is capable of catching some portion of those 3.4 defects and improve quality. Furthermore, because we are inspecting all parts going out the door, we no longer have to worry quite as much about an excessively tight sigma that may add unnecessary cost. If the cost of a vision system plus some additional scrap parts are less than the cost of the stricter sigma, a manufacturer could save significant money and achieve the same level of quality.|
|Accountability:||Images from a vision system can easily be stored to keep extensive records. You may never use most of the images, but it can be very convenient for diagnostic purposes. What went wrong during the shift change yesterday? Why are parts jamming on the conveyor? A vision system gives management insight on the production line at any time.|
|Customer Satisfaction:||Whether you ever miss a spec or not, every manufacturer has tense conversations with clients who feel rightly or wrongly dissatisfied. The ability to show the client all the annotated images and measurements from the vision system can assist in changing the tone of the conversation. No longer does the client doubt that the parts were checked, and they can see extensive quality control processes took place. Having a documented, computer based system can quickly take the emotion out of those sometimes difficult situations and reviewing the records together can help determine how to solve the problem and achieve higher standards of customer satisfaction.|
|Live Production Data:||Vision systems can generate measurements on critical features for every part that comes off of a production line. A data set can provide endless opportunities for further analysis. Be sure to ask what your integrator can do with this data, as it can provide enormous payback and returns. In fact, analyzing a data set can uncover what was causing most of the defects in the first place.|
|Traceability:||If each part has a bar code/serial number or some other identifier, the image can be stored with its bar code number. Traceability can also provide positive return, and bring an enormous amount of accountability to a production line and provide the client with information on where the issue occurred and whose problem it was.|
|Financial:||Although machine vision systems were once considered an expensive addition, there are now cost-reduction methods to automate more affordably, that small and mid-sized companies can gain similar access to helpful vision solutions. Some tips that companies can refer to when trying to reduce costs on vision, include providing representative samples for feasibility testing, attaching bar codes to products, handling fixturing on-site, controlling ambient lighting and granting remote access.|
|Risk of Change:||While any change to an established process involves risk, vision systems can undoubtedly create more efficiency and accountability. Consider what symptoms are driving the change? Are defect rates too high? Do we need traceability? Do we currently have high labor costs from doing QC in house? Are waste costs mounting? Are customers demanding automated verification?|
|Limitations:||Vision systems provide inspections on critical features, but will not necessarily catch every defect. Non-visual problems will not caught, unless there is a specific visual manifestation of the part's weakness, i.e. a crack or a narrow critical dimension, etc. A vision system is capable of reading a bar code for programmed inspections, and consistently and repeatedly making those checks. The best candidate for vision systems are production processes where we can define some finite problems that are responsible for unnecessary costs.|
|Implementation:||After purchasing and implementation, operators must be aware that a vision system may not catch a new problem that has never been seen before, so they should always remain alert for new issues. Ultimately, deployment may have associated costs as training sessions will need to occur in order to ensure that the system is running effectively on the shop floor.|
Is Machine Vision right for us?