The manufacturing industry is facing increasing volatility, uncertainty, complexity, and ambiguity, while still requiring high delivery reliability to meet customer demands. This is especially challenging for complex job shops in the semiconductor industry, where the manufacturing process is highly intricate, making it difficult to predict the consequences of changes. Although simulation has proven to be an effective tool for optimizing manufacturing processes, reference data sets and models often produce disparate and incomparable results. CoJoSim is introduced in this article as a reference model for semiconductor manufacturing, along with an associated reference implementation that accelerates the implementation and application of the reference model. CoJoSim can serve as a testbed and gold standard for other implementations. Using CoJoSim, different dispatching rules are evaluated to demonstrate an improvement of almost 15 percentage points in adherence to delivery dates compared to the reference. Findings emphasize the importance of optimizing setup time, particularly in products with high variance, as it significantly impacts adherence to delivery dates and throughput. Moving forward, future applications of CoJoSim will evaluate additional dispatching rules and use cases. Combining CoJoSim with dispatching methods that integrate manufacturing and supply networks to optimize production planning and control through reinforcement-learning-based agents is also planned. In conclusion, CoJoSim provides a reliable and effective tool for optimizing semiconductor manufacturing and can serve as a benchmark for future implementations.

This paper explores the application of a fingerprinting algorithm to the problem of load profile classification in manufacturing environments. Inspired by the Shazam algorithm, which is used for music recognition, we adapt the concept to classify energy consumption patterns in time series data by creating unique fingerprints for each product variant using locality-sensitive hashing (LSH). Our LSH-based classifier (LSHC) demonstrates its potential for efficient and accurate load profile classification, uniquely representing each product variant’s energy consumption pattern. One significant advantage of our method is that indexing just one time series sample per product variant is sufficient for recognizing the same product variant in future queries, similar to one-shot learning in machine learning. Experimental results show that LSHC performs exceptionally well in noise-free or slightly noisy environments, demonstrating robustness to deviations. LSHC is also highly flexible, allowing adjustments in window size, step size, and features based on the data type. However, we identify a potential limitation in the form of index blowup with large training sets, which can significantly increase querying time. While the LSHC meets key requirements such as speed, robustness, and flexibility, challenges with scalability remain. Future work will focus on addressing these scalability issues, extending the algorithm for clustering tasks, and developing methods for real-time identification of load profiles from continuous large time series.