Industrial equipment fault diagnosis system based on semi-supervised incremental learning
A technology of fault diagnosis system and industrial equipment, which is applied in the direction of test/monitoring control system, general control system, control/regulation system, etc. It can solve the problem of vicious operation of mechanical equipment system, lack of incremental update capability of model, and ineffective training of model and other issues to achieve high accuracy
Pending Publication Date: 2021-12-03
HOHAI UNIV
View PDF3 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In order to solve the existing technical problems, the present invention provides an industrial equipment fault diagnosis system based on semi-supervised incremental learning, which can solve the problems in the existing fault diagnosis system that the model lacks incremental update capability and the model cannot be used in the absence o
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
experiment example 1
[0108] The present embodiment employs a data set bearing disclosed Case Western Reserve University, the data contained in the data drive end bearing and the fan end, the bearing is divided into health, failure inner, outer fault, fault rolling four states.
[0109] Troubleshooting module process:
[0110] Data part (1) First, select the drive end bearing and the fan end of each fault category adding a known state sample database, and using the samples in the sample library of fault diagnosis model is initialized;
[0111] (2) fault diagnosis model data reading apparatus industrial monitoring, fault diagnosis, diagnosis results are given;
[0112] (3) some time after the system is running, the incremental update to update diagnosis fault diagnosis model incremental updates to ensure fault diagnosis model to adapt to changes in the data;
[0113] Fault diagnosis model (4) to continue the update is complete for fault diagnosis until the next update.
[0114] Semi-supervised tag modul...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an industrial equipment fault diagnosis system based on semi-supervised incremental learning. A fault diagnosis module reads equipment monitoring data, judges whether equipment is in a normal state or not according to the data, and judges the type of fault of the equipment if a fault occurs; a semi-supervised marking module firstly judges whether unknown fault category samples, namely unlabeled samples, exist in equipment monitoring data, marks false labels on all the unlabeled samples, and finally outputs samples with false labels to assist an incremental updating module in updating a fault diagnosis module; and the incremental updating module is used for incrementally updating the fault diagnosis module by using the false label sample output by the semi-supervised marking module. According to the system, in the case of data moment change and data label lack, it is ensured that the fault diagnosis model can be updated in time, effective training is performed under the condition of sample label lack, and the high fault diagnosis accuracy is kept.
Description
Technical field [0001] The present invention relates to an industrial equipment fault diagnosis system based on semi-supervision increment, belongs to the field of equipment fault diagnosis. Background technique [0002] In recent years, due to the continuous development of Internet of Things Technology and Industrial Automation, Industrial Internet Network is now widely used to monitor the actual industrial production environment. In the industrial manufacturing areas, industrial equipment failure will affect the overall performance of industrial systems, trigger equipment downtime, system malignant operation, etc., causing significant economic losses. Troubleshooting can determine the root cause of observed out-of-control status, which is critical to cancel or eliminating failures in the industrial process. [0003] During the operation of the industrial system, the equipment will gradually aggressive, and the working environment where the equipment is located, and multiple key...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G05B23/02
CPCG05B23/0262G05B2219/24065Y02P90/02
Inventor 孙宁王彬韩光洁
Owner HOHAI UNIV