Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Engine fault detection method, system, storage medium and equipment

A fault detection and engine technology, which is applied in the direction of engine testing, machine/structural component testing, measuring devices, etc., can solve the problems of parameter fitting error, difficulty in detecting unknown abnormal engine faults, and decline in diagnostic accuracy, and achieve strong adaptability performance, good fault diagnosis ability, and strong robustness

Active Publication Date: 2022-04-01
SHANDONG UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the actual diagnosis process, it is difficult to detect unknown abnormal faults of the engine using a linear classifier, and the construction process of a general Gaussian correlation model such as a Gaussian mixture model needs to estimate the model parameters by the expected maximum method. When the feature dimension increases, the parameters Fitting errors can easily lead to a decrease in diagnostic accuracy

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Engine fault detection method, system, storage medium and equipment
  • Engine fault detection method, system, storage medium and equipment
  • Engine fault detection method, system, storage medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] like Figure 1-5 As shown, the engine failure detection method includes the following steps:

[0047] Obtain the engine vibro-acoustic signal data, and intercept the continuous vibro-acoustic signal into equal-length and overlapping signal frames;

[0048] Obtain the frequency characteristics, Mel cepstral coefficient characteristics and difference characteristics of the vibroacoustic signal based on the signal frame;

[0049] According to the spectral features, Mel cepstral coefficient features and differential features, the multi-branch feature normal sub-model is constructed; each branch sub-model in the multi-branch feature normal sub-model is standardized to obtain samples for known fault type samples Score, the larger the value of the sample score, the more likely it belongs to this type of fault type, and vice versa, the less likely it belongs to this type of fault type;

[0050] Construct a hierarchical decision normal submodel based on sample scores;

[0051...

Embodiment 2

[0105] This embodiment provides a system for realizing the above detection method, including:

[0106] The data acquisition module is configured to: acquire engine vibro-acoustic signal data, intercept continuous vibro-acoustic signals into equal-length and overlapping signal frames; acquire frequency characteristics, Mel cepstral coefficient features and Differential features;

[0107] The model construction module is configured to: construct a multi-branch feature normal submodel according to the spectral feature, the Mel cepstral coefficient feature and the difference feature; standardize each branch sub-model in the multi-branch feature normal sub-model, and obtain Sample score for samples of known fault types; construct a hierarchical judgment normal submodel based on the sample score;

[0108] The judging module is configured to: for all fault types, use the multi-branch characteristic normal sub-model and the hierarchical normal sub-model to construct a multi-branch le...

Embodiment 3

[0111] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps in the engine failure detection method proposed in the first embodiment above are implemented.

[0112] In the engine fault detection method implemented in this embodiment, the working state and fault type of the engine in the actual engine inspection workshop environment can be accurately detected, and abnormal conditions can be reflected in time while almost no false detection occurs.

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

No PUM Login to View More

Abstract

The invention relates to an engine fault detection method, system, storage medium and equipment, comprising the following steps: obtaining the vibration-acoustic signal data of the engine for preprocessing, obtaining the frequency characteristics, Mel cepstrum coefficient characteristics and difference characteristics of the vibration-acoustic signal, and constructing multiple The characteristic normal sub-model is used to obtain the sample scores for samples of known fault types, and the hierarchical judgment normal sub-model is constructed based on the sample scores; the multi-branch characteristic normal sub-model and the hierarchical normal sub-model are used to construct multi-branch normal sub-models for all fault types. Branch-level normal anomaly detection model, the engine vibration and sound signal samples to be tested are sequentially input into various types of multi-branch-level normal anomaly detection models; when the sample is not within the set range of any known type, the corresponding The engine state is judged to be an unknown abnormal state. It can detect the working state and fault type of the engine under the detection link after the engine is manufactured, and reflect the abnormal situation without false detection.

Description

technical field [0001] The invention relates to the field of engine fault detection, in particular to an engine fault detection method, system, storage medium and equipment. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] As the main source of power for transportation vehicles, especially as the driving equipment for vehicles such as heavy-duty transport vehicles and ships, the health and operation status of the engine is related to the safety of people and property. The engine quality monitoring and fault repair process are very important to ensure the normal operation of the engine. In the engine quality inspection and maintenance workshop, the health status and operating status of the engine are generally judged by monitoring the engine speed and torque during engine operation, combined with the method of manually monitoring the engine...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G10L25/03G10L25/27G10L25/51G01M15/00
CPCG10L25/03G10L25/27G10L25/51G01M15/00
Inventor 常发亮蒋沁宇刘春生郇恒强赵子健
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com