CN113033625A - Industrial air conditioner fault diagnosis method based on neural network and integrated learning fusion - Google Patents
Industrial air conditioner fault diagnosis method based on neural network and integrated learning fusion Download PDFInfo
- Publication number
- CN113033625A CN113033625A CN202110253452.0A CN202110253452A CN113033625A CN 113033625 A CN113033625 A CN 113033625A CN 202110253452 A CN202110253452 A CN 202110253452A CN 113033625 A CN113033625 A CN 113033625A
- Authority
- CN
- China
- Prior art keywords
- fault diagnosis
- air conditioner
- industrial air
- neural network
- algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention provides an industrial air conditioner fault diagnosis method based on a neural network and an integrated learning algorithm. The method integrates various machine learning algorithms and is a fault diagnosis model with high accuracy. The neural network has an important function on analyzing time sequence data received by the industrial air conditioner in real time by learning a reasonable rule between automatic extraction output and output data. Therefore, an anomaly detection module based on a neural network algorithm is designed. The integration algorithm has the advantages of obviously avoiding overfitting, improving generalization capability and the like. Therefore, a fault diagnosis module based on an integrated learning algorithm is designed. Combining the abnormality detection model with the fault diagnosis model and introducing an attention mechanism to enable the detected abnormality to assist fault diagnosis to form an enhanced model which is more accurate than the basic model. The invention can carry out accurate fault diagnosis aiming at industrial air conditioner data.
Description
Technical Field
The invention relates to the field of internet and deep learning, in particular to an industrial air conditioner fault diagnosis method based on neural network and integrated learning fusion.
Background
An industrial air conditioner fault diagnosis method based on neural network and ensemble learning fusion is based on a neural network technology and an ensemble learning technology. The neural network algorithm LSTM realizes a mapping function from input to output, and mathematical theory proves that the neural network with three layers can approximate any nonlinear continuous function with any precision. The method is suitable for solving the problem of complex internal mechanism. The integrated learning algorithm LightGBM has the advantages of obviously avoiding overfitting, improving generalization capability and the like. The closest techniques to the present invention in recent years are:
(1) and predicting the failure of the integrated learning algorithm model based on the XGboost, wherein a failure diagnosis method based on XGboost algorithm feature extraction is also provided in New York and the like in recent years. The importance sequence of the input elements is generated by the XGboost algorithm, and the extracted time domain and time-frequency domain features are respectively input into a support vector machine so as to observe the accuracy of fault diagnosis. But the method itself is relatively weak to timing, making the method less than optimal in long-term data.
(2) Anomaly monitoring based on the LSTM model: the LSTM has wide application in anomaly monitoring, and can make anomaly monitoring judgment with better effect aiming at recent data memory and past stage data accumulation analysis. But the single monitoring method is less applicable in fault diagnosis.
In recent years, with the rapid advance of artificial intelligence technology, the connection between industrial scenes and intelligent technologies such as machine learning and big data is becoming more and more compact. And fusing the multi-algorithm models, combining or establishing a comprehensive model, acting on the sample data together, and finally obtaining a more accurate judgment effect through superposition calculation of a complex algorithm. The method can accurately diagnose the fault type by fusing a long-term and short-term memory neural network method and an integrated machine learning algorithm. The method improves the safety and reliability of the equipment by accurately diagnosing.
Disclosure of Invention
The industrial air conditioner aims to overcome the defects in the prior art and improve the safety and reliability of the industrial air conditioner in a real scene. The invention provides an industrial air conditioner fault diagnosis model based on a neural network and an integrated learning algorithm, wherein a long-term and short-term memory neural network method is adopted to monitor abnormal conditions of air conditioner sensor data received in real time and establish a real-time detection model; and analyzing and diagnosing the sensor data by adopting an integrated learning algorithm. And (5) interfering the diagnosis result by combining the abnormal signal to obtain an accurate diagnosis result.
The technical scheme of the invention is as follows:
1. the industrial air conditioner fault diagnosis method based on the neural network and the integrated learning algorithm is characterized in that an accurate fault diagnosis result is obtained by training and testing a data preprocessing module and an abnormality detection module and training and testing a fault diagnosis module aiming at industrial air conditioner data received in real time. The method comprises the following steps:
and (1) preprocessing the collected data of the industrial air conditioner sensor, and performing operations such as cleaning, noise reduction and the like. And a time sequence is formed for real-time reception format processing.
And (2) training the data processed in the step (1) by adopting an LSTM algorithm to obtain an anomaly detection model module based on a neural network.
And (3) training the data processed in the step (1) by adopting a lightGBM algorithm to obtain a fault diagnosis model module based on an integrated algorithm.
And (4) receiving industrial air conditioner data in real time, and processing the real-time data according to the processing method in the step (1). Inputting the abnormal signals into the abnormal detection module obtained by training in the step (2) and outputting abnormal detection signals.
And (5) analyzing the abnormal detection signal, inputting an analysis result into the fault diagnosis model obtained in the step (3), and assisting in fault diagnosis.
And (6) outputting a final fault diagnosis result.
The invention has the beneficial effects that:
(1) through the fusion of the LSTM abnormality detection method and the LightGBM fault diagnosis method, an accurate industrial air conditioner fault diagnosis method is constructed, so that the equipment safety is improved;
(2) the method enables the context vector and all sequence input information to construct 'connection' through an attention mechanism, and enhances the characteristic representation of related faults;
(3) the accuracy rate and the precision rate of the traditional fault diagnosis model are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flow chart of an industrial air conditioner fault diagnosis method based on neural network and ensemble learning fusion.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a flow chart of an industrial air conditioner fault diagnosis method based on a neural network and an integrated learning algorithm mainly includes five modules: the system comprises a data preprocessing module, an abnormality detection module, a fault diagnosis module, an abnormality information analysis module and an attention mechanism module.
The following describes in detail a specific flow of the industrial air conditioner fault diagnosis method based on the neural network and the ensemble learning algorithm with reference to fig. 1:
and (1) preprocessing the collected data of the industrial air conditioner sensor, and performing operations such as cleaning, noise reduction and the like. And a time sequence is formed for real-time reception format processing.
And (2) training the data processed in the step (1) by adopting an LSTM algorithm to obtain an anomaly detection model module based on a neural network.
And (3) training the data processed in the step (1) by adopting a lightGBM algorithm to obtain a fault diagnosis model module based on an integrated algorithm.
And (4) receiving industrial air conditioner data in real time, and processing the real-time data according to the processing method in the step (1). Inputting the abnormal signals into the abnormal detection module obtained by training in the step (2) and outputting abnormal detection signals.
And (5) analyzing the abnormal detection signal, inputting an analysis result into the fault diagnosis model obtained in the step (3), and assisting in fault diagnosis.
And (6) outputting a final fault diagnosis result.
The industrial air conditioner fault diagnosis method based on the neural network and the integrated learning algorithm forms an enhanced model by fusing a long and short term memory model in the neural network and the integrated learning algorithm in machine learning. The method is applied to data of industrial air conditioners in real scenes. The method can perform proper processing on the industrial air conditioner data received in real time to form a diagnosable time sequence and give an accurate fault diagnosis result. Accurate feedback and timely and effective maintenance direction are provided for the equipment. Thereby improving the durable safety and reliability of the equipment.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (1)
1. The industrial air conditioner fault diagnosis method based on the neural network and the integrated learning algorithm is characterized in that an accurate fault diagnosis result is obtained by training and testing a data preprocessing module and an abnormality detection module and training and testing a fault diagnosis module aiming at industrial air conditioner data received in real time. The method comprises the following steps:
and (1) preprocessing the collected data of the industrial air conditioner sensor, and performing operations such as cleaning, noise reduction and the like. And a time sequence is formed for real-time reception format processing.
And (2) training the data processed in the step (1) by adopting an LSTM algorithm to obtain an anomaly detection model module based on a neural network.
And (3) training the data processed in the step (1) by adopting a lightGBM algorithm to obtain a fault diagnosis model module based on an integrated algorithm.
And (4) receiving industrial air conditioner data in real time, and processing the real-time data according to the processing method in the step (1). Inputting the abnormal signals into the abnormal detection module obtained by training in the step (2) and outputting abnormal detection signals.
And (5) analyzing the abnormal detection signal, inputting an analysis result into the fault diagnosis model obtained in the step (3), and assisting in fault diagnosis.
And (6) outputting a final fault diagnosis result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110253452.0A CN113033625A (en) | 2021-03-05 | 2021-03-05 | Industrial air conditioner fault diagnosis method based on neural network and integrated learning fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110253452.0A CN113033625A (en) | 2021-03-05 | 2021-03-05 | Industrial air conditioner fault diagnosis method based on neural network and integrated learning fusion |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113033625A true CN113033625A (en) | 2021-06-25 |
Family
ID=76467068
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110253452.0A Pending CN113033625A (en) | 2021-03-05 | 2021-03-05 | Industrial air conditioner fault diagnosis method based on neural network and integrated learning fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113033625A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114893390A (en) * | 2022-07-15 | 2022-08-12 | 安徽云磬科技产业发展有限公司 | Pump equipment fault detection method based on attention and integrated learning mechanism |
CN115673596A (en) * | 2022-12-28 | 2023-02-03 | 苏芯物联技术(南京)有限公司 | Welding abnormity real-time diagnosis method based on Actor-Critic reinforcement learning model |
-
2021
- 2021-03-05 CN CN202110253452.0A patent/CN113033625A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114893390A (en) * | 2022-07-15 | 2022-08-12 | 安徽云磬科技产业发展有限公司 | Pump equipment fault detection method based on attention and integrated learning mechanism |
CN114893390B (en) * | 2022-07-15 | 2023-08-04 | 安徽云磬科技产业发展有限公司 | Pump equipment fault detection method based on attention and integrated learning mechanism |
CN115673596A (en) * | 2022-12-28 | 2023-02-03 | 苏芯物联技术(南京)有限公司 | Welding abnormity real-time diagnosis method based on Actor-Critic reinforcement learning model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111914883B (en) | Spindle bearing state evaluation method and device based on deep fusion network | |
CN111340238A (en) | Fault diagnosis method, device, equipment and storage medium of industrial system | |
CN111695598B (en) | Monitoring data abnormity diagnosis method based on generation countermeasure network | |
WO2019080367A1 (en) | Method for evaluating health status of mechanical device | |
CN113033625A (en) | Industrial air conditioner fault diagnosis method based on neural network and integrated learning fusion | |
CN113870260A (en) | Welding defect real-time detection method and system based on high-frequency time sequence data | |
CN111947928A (en) | Multi-source information fusion bearing fault prediction system and method | |
CN103671190A (en) | Intelligent early stage on-line fault diagnosis system of mine fan | |
CN108257365B (en) | Industrial alarm design method based on global uncertainty evidence dynamic fusion | |
CN111678699B (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
CN113305645A (en) | Numerical control machine tool cutter residual life prediction method based on mixed neural model | |
CN113177646B (en) | Power distribution equipment online monitoring method and system based on self-adaptive edge proxy | |
CN115824519B (en) | Comprehensive diagnosis method for valve leakage faults based on multi-sensor information fusion | |
CN110597235A (en) | Universal intelligent fault diagnosis method | |
CN112669879A (en) | Air conditioner indoor unit noise anomaly detection method based on time-frequency domain deep learning algorithm | |
CN115577860A (en) | Intelligent maintenance method and system for rail transit based on adaptive control | |
CN115470850A (en) | Water quality abnormal event recognition early warning method based on pipe network water quality time-space data | |
CN114893390A (en) | Pump equipment fault detection method based on attention and integrated learning mechanism | |
CN117422935B (en) | Motorcycle fault non-contact diagnosis method and system | |
CN113593605B (en) | Industrial audio fault monitoring system and method based on deep neural network | |
CN117216647A (en) | Predictive maintenance and fault diagnosis method and system for vehicle body welding equipment | |
CN115062867A (en) | Bearing fault prediction method based on Teager energy spectrum and improved CNN model | |
CN114330413A (en) | Fault type identification and positioning method for traction motor bearing | |
CN110287594B (en) | Aero-engine state diagnosis method based on neural network algorithm | |
CN111380687A (en) | Industrial motor bearing fault diagnosis method based on multi-local model decision fusion |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication |