Production Feature Classification Method for Rubber Extrusion Molding Equipment Based on CART Decision Tree
Through the CART decision tree-based method, combined with data cleaning and feature engineering, the problem of insufficient flexibility and accuracy of traditional methods in industrial production is solved, and the subtle changes in production mode are captured and real-time adjustments are achieved, which improves the accuracy and adaptability of classification.
Patent Information
- Application Number
- CN202311120582.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-01
- Publication Date
- 2025-08-05
- Estimated Expiration
- 2043-09-01
AI Technical Summary
The existing time-series data classification methods are limited in flexibility and accuracy in industrial production, especially when processing data containing a large amount of noise and complex patterns. Traditional methods such as SVM, CNN and RNN are difficult to meet the real-time and accuracy requirements of industrial production.
Using a CART decision tree-based method, through data cleaning, standardization, critical timing data annotation, feature engineering and model training, combined with CFD numerical simulation, time domain and frequency domain features are extracted, and the stability and accuracy of the model are ensured through cross-validation, and deployed in a production environment for dynamic adjustment.
It realizes a comprehensive capture of subtle changes in production mode, ensures the accuracy and real-time classification, and meets the needs of industrial production.
Smart Images
Figure CN117077039B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a production feature classification method for rubber extrusion molding equipment based on a CART decision tree. Background Art
[0002] In industrial production, accurate data classification and processing are crucial to ensuring production quality and efficiency. For time series data, traditional classification methods such as support vector machines (SVM), convolutional neural networks (CNN), and recurrent neural networks (RNN) are not effective in processing data containing a lot of noise and complex patterns due to their model complexity and susceptibility to data noise.
[0003] While support vector machines (SVMs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs) have demonstrated excellent performance in many tasks, their model complexity and sensitivity to data noise limit their flexibility and accuracy when applied to scenarios tightly coupled with specific business logic. Furthermore, big data mining and algorithmic models in the industrial sector are rarely applied to specific verticals. To address this, we propose a production feature classification method for rubber extrusion equipment based on a CART decision tree. Summary of the Invention
[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides a production feature classification method for rubber extrusion molding equipment based on a CART decision tree.
[0005] The present invention provides the following technical solution: a production feature classification method for rubber extrusion molding equipment based on a CART decision tree, comprising the following steps:
[0006] S1. Data processing: Clean the production line equipment data in industrial scenarios, remove outliers, standardize and normalize the data, and analyze the data based on business knowledge;
[0007] S2. Key time series data annotation: Annotate key time periods based on actual production and business knowledge, and associate data with business knowledge;
[0008] S3. Feature Engineering: Utilize data analysis techniques and CFD numerical simulation to comprehensively capture production patterns, extract time and frequency domain features, and enhance data on physical property parameters through numerical simulation.
[0009] S4. Model training and validation: Use CART decision tree for feature training and cross-validation to ensure model stability and accuracy;
[0010] S5. Business model reasoning deployment: Work with the business department to ensure that the model is highly consistent with the key rules and logic in actual production, deploy the CART model in the production environment, and adjust the model based on feedback.
[0011] Compared with the prior art, the present invention has the following beneficial effects:
[0012] This CART decision tree-based production feature classification method for rubber extrusion molding equipment combines business knowledge with advanced data analysis and machine learning technologies to intelligently extract key features. Compared with traditional methods, we can more comprehensively capture subtle changes in production patterns. The model can be dynamically adjusted based on the latest production data to ensure classification accuracy and meet the real-time requirements of industrial production. The business integration strategy of data labeling, feature engineering and supervised learning makes the model more closely aligned with actual production needs. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] Figure 1 It is a structural schematic diagram of the present invention. DETAILED DESCRIPTION
[0014] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings of the embodiments of the present disclosure. In order to keep the following description of the embodiments of the present disclosure clear and concise, the present disclosure omits detailed descriptions of known functions and known components to avoid unnecessary confusion of the concepts of the present invention.
[0015] See also Figure 1 The production feature classification method of rubber extrusion molding equipment based on CART decision tree includes the following steps:
[0016] S1. Data processing: Clean the production line equipment data in industrial scenarios, remove outliers, standardize and normalize the data, and analyze the data based on business knowledge;
[0017] S2. Key time series data annotation: Annotate key time periods based on actual production and business knowledge, and associate data with business knowledge;
[0018] S3. Feature Engineering: Utilize data analysis techniques and CFD numerical simulation to comprehensively capture production patterns, extract time and frequency domain features, and enhance data on physical property parameters through numerical simulation.
[0019] S4. Model training and validation: Use CART decision tree for feature training and cross-validation to ensure model stability and accuracy;
[0020] S5. Business model reasoning deployment: Work with the business department to ensure that the model is highly consistent with the key rules and logic in actual production, deploy the CART model in the production environment, and adjust the model based on feedback.
[0021] The above embodiments are merely exemplary embodiments of the present invention and are not intended to limit the scope of the present invention. The scope of protection of the present invention is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present invention within the spirit and scope of protection of the present invention, and such modifications or equivalent substitutions shall also be deemed to fall within the scope of protection of the present invention.
Claims
1. A production feature classification method for rubber extrusion molding equipment based on a CART decision tree, characterized by: The following steps are involved: S1. Data processing: Clean the production line equipment data in industrial scenarios, remove outliers, standardize and normalize the data, and analyze the data based on business knowledge; S2. Key time series data annotation: Annotate key time periods based on actual production and business knowledge, and associate data with business knowledge; S3. Feature Engineering: Utilize data analysis techniques and CFD numerical simulation to comprehensively capture production patterns, extract time and frequency domain features, and enhance data on physical property parameters through numerical simulation. S4. Model training and validation: Use CART decision tree for feature training and cross-validation to ensure model stability and accuracy; S5. Business model reasoning deployment: Work with the business department to ensure that the model is highly consistent with the key rules and logic in actual production, deploy the CART model in the production environment, and adjust the model based on feedback.
Citation Information
Patent Citations
Interactive knowledge defining and processing method, system and device and readable medium
CN112861515A
Adaptive learning intelligent scheduling unified computing framework and system for industrial personalized customized production
WO2022099596A1