Real-time job shop scheduling method based on pca-xgboost-irf

Abstract

The invention discloses a PCA-XGBoost-IRF-based real-time scheduling method for a job shop, which includes step 1: standard data sample construction; step 2: sample data preprocessing, including abnormal value processing, category imbalance processing and Normalization processing and segmentation of the data set to meet the input requirements of decision-making model construction; Step 3: Perform feature engineering processing on the training set, including feature extraction, feature importance calculation and feature selection; Step 4: Based on improved random Forest decision-making model construction, including random forest model construction, improving the RF model to obtain the IRF model, and optimizing the hyperparameters of the IRF model based on grid search; Step 5: PCA-XGBoost-IRF decision-making model based on optimal parameters Training; Step 6: Use the decision model based on PCA-XGBoost-IRF to realize the real-time selection and decision-making of dynamic job shop scheduling rules. The invention provides a more reliable, robust and generalizable real-time scheduling method for intelligent scheduling research based on data drive.

Description

technical field [0001] The invention relates to the technical field of machine learning and job shop scheduling, in particular to a PCA-XGBoost-IRF-based real-time job shop scheduling method. Background technique [0002] With the rapid development of artificial intelligence, industrial Internet, and computer information technology, a new wave of industrial revolution is sweeping under the background of intelligent manufacturing. The Job-shop Scheduling Problem (JSP) is a typical NP problem with a strong engineering application background. As an intersecting research field, since Johnson established the first mathematical model for scheduling two machines in 1954, it has received extensive attention from experts in many intersecting fields such as computers and operations research. As the direct executor of manufacturing, the workshop carries a large number of production tasks, and is also the intersection of a large amount of real-time information. As the actual productio...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is: In order to overcome the problems of low practical operability, high calculation time cost and insufficient real-time response ability to workshop disturbances in the traditional job shop real-time scheduling method, the present invention provides a practically operable PCA-XGBoost-IRF-based real-time job shop scheduling method with high computational efficiency and real-time response to shop disturbances

Images