A case-based expert support system for due-date assignment in a wafer fabrication factory

Owing to the complexity of wafer fabrication, the traditional human approach to assigning due-date is imprecise and very prone to failure, especially when the shop status is dynamically changing. Therefore, assigning a due date to each order becomes a challenge to the production planning and scheduling staff. Since most production orders are similar to those previously manufactured, the case based reasoning (CBR) approach provides a suitable means for solving the due-date assignment problem. This research proposes a CBR approach that employs the k-nearest neighbors concept with dynamic feature weights and non-linear similarity functions. The test results show that the proposed approach can more accurately predict order due dates than other approaches.     

Evolving fuzzy rules for due-date assignment problem in semiconductor manufacturing factory

This paper presents a fuzzy modeling method proposed by Wang and Mendel for generation of fuzzy rules using data generated from a simulated model that is built from a real factory located in Hsin-Chu science-based park of Taiwan, R.O.C. The fuzzy modeling method is further evolved by a genetic algorithm for due-date assignment problem in manufacturing. By using simulated data, the effectiveness of the proposed method is shown and compared with two other soft computing techniques: multi-layer perceptron neural networks and case-based reasoning. The comparative results indicate that the proposed method is consistently superior to the other two methods.     

Data based segmentation and summarization for sensor data in semiconductor manufacturing

In semiconductor manufacturing processes, sensor data are segmented and summarized in order to reduce storage space. This is conventionally done by segmenting the data based on predefined chamber step information and calculating statistics within the segments. However, segmentation via chamber steps often do not coincide with actual change points in data, which results in suboptimal summarization. This paper proposes a novel framework using abnormal difference and free knot spline with knot removal, to detect actual data change points and summarize on them. Preliminary experiments demonstrate that the proposed algorithm handles arbitrarily shaped data in a robust fashion and shows better performance than chamber step based segmentation and summarization. An evaluation metric based on linearity and parsimony is also proposed.     

An extended model for remaining time prediction in manufacturing systems using process mining

The ability to predict the remaining cycle-time in industrial environments is of major concern among production managers. An accurate prediction would enable managers to handle undesired situations with more control, thereby preventing future losses. However, making such predictions is no trivial task: there are many methods available to cope with this problem, including a recent research stream in process mining. Process mining provides tools for automated discovery of process models from event logs, and eventually, extend those models in driving predictions. In general, predictive models in process mining generally deals with business processes, and not directly with the industrial environment, which contains a full prism of particularities. In this paper we propose a hybrid predictive model based on transition-systems and statistical regression which is “product-oriented”, tailored to better predict online cycle-times on industrial environments. We propose a weight for each method, optimized by a linear programming model. We tested our new approach on an artificially created log that emulates an industrial environment, and on a real manufacture log. Results showed that our approach provides better accuracy measures for both test instances.     

Response time assessment in forest fire spread simulation: An integrated methodology for efficient exploitation of available prediction time

This work details a framework developed to shorten the time needed to perform fire spread predictions. The methodology presented relies on a two-stage prediction strategy which introduces a calibration stage in order to relieve the effects of uncertainty on simulator input parameters. Early assessment of the response time and quality of the results obtained constitute a key component in this method. This automatic and intelligent process of identification of lengthy simulations that slow down the course of the predictions presents a very high hit ratio. However, discarding certain simulations from the adjustment process (based on evolutionary algorithms) could lead to loss of accuracy in our predictions. A strong statistical study to analyze the impact of this action on our final predictions is reported. This study is based on a real fire which burnt 13,000 ha in the region of Catalonia (north-east of Spain) in the summer of 2012.