Factory Physics and Automation blog

Semiconductor manufacturing is a highly complex and dynamic industry that requires constant innovation and adaptation to meet the changing needs of customers. One of the biggest challenges in this industry is managing changes to the product mix, which can have a significant impact on the overall efficiency and effectiveness of the manufacturing process.

Product mix changes can occur for a variety of reasons, such as changes in market demand, new product introductions, and shifts in technology. These changes can have a ripple effect throughout the entire manufacturing process, impacting everything from sourcing and procurement, to production and logistics.

One of the major challenges of product mix changes is the need to quickly and efficiently re-configure the manufacturing process to accommodate the new products. This requires significant coordination and collaboration across multiple departments, including engineering, procurement, and production. Additionally, changes to the product mix may also require the use of new or different equipment, which can add further complexity to the process.

Another challenge is managing inventory and supply chain logistics. With changes in product mix, the demand for certain raw materials and components may fluctuate, requiring adjustments to inventory levels and procurement strategies. Additionally, changes in product mix can also impact shipping and delivery schedules, requiring careful coordination with customers and suppliers.

Overall, managing product mix changes in semiconductor manufacturing is a complex and dynamic process that requires a high degree of coordination and collaboration across multiple departments. It is important for companies in this industry to have a robust and flexible manufacturing process that can quickly adapt to changing product mix requirements, in order to remain competitive and meet the changing needs of customers.

---

O.k. – the text block above was generated by OpenAI’s ChatGPT.

I asked it (?) to “… write a short article about the complexity of product mix changes in semiconductor manufacturing …”

pretty impressive, especially because it took only about 10 seconds – the next text block was it’s second try:

Semiconductor manufacturing is a complex and constantly evolving industry, with a wide range of products that are produced using a variety of different processes and techniques. One of the most significant challenges faced by manufacturers in this industry is the complexity of product mix changes.

When a manufacturer wants to change the product mix of its semiconductors, it must consider a variety of factors, including the specific processes and techniques required to produce the new products, the availability of equipment and materials, and the costs and risks associated with the change.

One major challenge in changing the product mix is the need to retool and reconfigure manufacturing equipment. This can be a costly and time-consuming process, as manufacturers must purchase new equipment and train employees on how to use it. Additionally, the process of retooling can also lead to downtime and disruptions in production, which can have a significant impact on the bottom line.

Another major challenge is the need to secure and maintain a steady supply of materials, as well as the need to dispose of any remaining materials that are no longer needed. This can be a difficult and costly process, as manufacturers must navigate a complex supply chain and ensure that they have the necessary materials on hand to produce the new products.

Finally, manufacturers must also consider the costs and risks associated with changing the product mix. This can include the costs of retooling and reconfiguring equipment, as well as the potential loss of revenue if the new products do not sell as well as expected. Additionally, manufacturers must also be prepared to address any potential issues that may arise during the transition, such as quality control problems or supply chain disruptions.

Overall, changing the product mix in semiconductor manufacturing is a complex and challenging process that requires careful planning and execution. Manufacturers must weigh the costs and risks associated with the change against the potential benefits, and be prepared to address any issues that may arise during the transition.

---

I promise, the following contains only 100% of my own thoughts …

One of the more tricky aspects of optimizing factory performance is understanding the true impact caused by product mix changes. The key problem here is the level of complexity to:

• understand
• calculate and/or estimate
• drive actions to reduce the impact

Unfortunately there is no “one size fits all” rule to deal with this – other than:

The higher the product mix is in a FAB – the more likely there will be performance loss.

Almost 20 years ago I was confronted the 1st time with the problem of increasing product mix. I visited a factory which had recently gone from an almost mono culture FAB to a factory running now 10+ different products. FAB cycle times increased, output went down -all this at the same wafer starts level like the years before – and the management wanted to understand what is going on … (it seems that ChatGPT today has more “understanding” about this than the management 20 years ago)

Experienced factory physics practitioners will likely smile about this, but without a good understanding of the effects of changing product mix plan and actual results will very likely not be in sync.

Let’s try to dig into the topic a bit. First we need to define what do I mean with a product. In the real world there are various levels of differences between a product and another one. Unfortunately different companies have different naming conventions for that. I will use this definition: A product is different to another one, if at least one processing or metrology / test step is different.

For example: if the manufacturing of a wafer leads to the exact same chips at the end of the wafer FAB processing and just get a different frequency capability assigned after testing ( like CPU’s) I would not call them different products. As soon as there are steps with different recipes in the flow – these are 2 different products.

The size of the impact scales with the number of differences: If 2 products with 500 processing steps have a different recipe on 12 steps are much more similar to each other, than a product which has 100 out of the 500 steps different.

What are they key effects of the differences :

1. higher product mix will likely lead to smaller cascades on a process equipment since a recipe change might need additional setup times
2. different recipes at the same equipment will likely have a different number of qualified tools (in the planned world but especially on the FAB floor)
3. capacity planning no longer will work with simple static modeling approaches to reflect the real effective equipment and/or chamber dedication/availability
4. batch building at batch tools will either lead to smaller batch sizes or to longer batch formation times
5. higher number of products will likely increase the number of Litho reticles and therefore also increase reticle logistics and risk of “reticle not available when needed” scenarios
6. back up reticle sets are likely less available for products with smaller WIP in the line
7. small volume products tend to have higher metrology sampling rates (more often measured) since there is not enough “volume” statistics available
8. achieving very high on-time delivery percentage is harder for very small volume products (if 1 lot gets scrapped, is this 33% of the total WIP ?)
9. products with significantly different number of process steps (or mask layers) will likely create dynamic bottlenecks throughout the line due to different WIP arrival times
10. higher number of different recipes on a tool might cause higher re-qualification time needs, which can impact tool availability negatively
11. frequent changes in the product mix wafer starts will likely amplify the negative impacts of points 1. – 10.

---

How to deal with all of these complexities – especially if your FAB is going down the path of increasing product complexity ?
There are basically only 2 practical approaches to that:

A) – reduce general FAB loading and see what happens (with no guarantee what will be the outcome)

B) – invest in IE systems and experts to be able to quantify, calculate and plan for the expected effects

I have seen both in the real world, with B having significantly better chances to hit cycle time, output and on-time delivery goals.