Heating ventilation air conditioning system fault detection method based on deep transfer learning and principal component analysis

By combining deep transfer learning and principal component analysis, problems such as data dependence and linear assumption limitation in HVAC system fault detection technology are solved, and fault detection effects with high accuracy, real-time and interpretability are achieved.

CN119669987AActive Publication Date: 2025-03-21ZHEJIANG UNIV +1
4 Cites 2 Cited by

Patent Information

Application Number
CN202510181271.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-19
Publication Date
2025-03-21
Estimated Expiration
2045-02-19

AI Technical Summary

Technical Problem

The existing HVAC system fault detection technology has problems such as data dependence, linear assumption limitations, insufficient real-time performance, poor multivariate data processing capabilities, insufficient generalization capabilities and insufficient interpretability.

Method used

Using a combination of deep transfer learning and principal component analysis, the pre-trained model is used to reduce the dependence on a large number of labeled data through transfer learning, combined with principal component analysis, improve the expression ability and interpretability of features, and enhance the detection ability of complex failure modes through the nonlinear mapping ability of deep learning models.

Benefits of technology

It realizes effective fault detection under data limitation, improves the accuracy and reliability of fault detection, enhances the detection ability of complex fault modes, is real-time and generalized, is suitable for various HVAC systems, and is interpretable.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a heating ventilation air conditioning system fault detection method based on deep transfer learning and principal component analysis. Comprising the following steps: respectively processing a source domain data set and a target domain data set by using a principal component analysis method to obtain a source domain feature data set and a target domain feature data set; after a deep learning model is constructed, the deep learning model is pre-trained by using a source domain feature data set, parameters of a convolutional neural network module of the pre-trained model are frozen, and a trained deep learning model is obtained by using a target domain feature data set; and receiving and processing sensing signal data to be predicted by using the trained deep learning model to obtain a fault detection result of the heating ventilation air conditioning system. According to the method, dependence on a large amount of labeled data is reduced, fault information can be fed back in time, and fault detection is accurate and reliable.
Need to check novelty before this filing date? Find Prior Art