CN108204892A - Roller set equipment fault detection method based on array-type flexible pressure sensor - Google Patents
Roller set equipment fault detection method based on array-type flexible pressure sensor Download PDFInfo
- Publication number
- CN108204892A CN108204892A CN201810070059.6A CN201810070059A CN108204892A CN 108204892 A CN108204892 A CN 108204892A CN 201810070059 A CN201810070059 A CN 201810070059A CN 108204892 A CN108204892 A CN 108204892A
- Authority
- CN
- China
- Prior art keywords
- data
- roller set
- fault
- array
- pressure sensor
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
-
- 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
- G06N3/047—Probabilistic or stochastic networks
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The present invention relates to a kind of roller set equipment fault detection methods based on array-type flexible pressure sensor, belong to fault diagnosis technology field, this method includes:S1:The pressure distribution data between roller set is acquired using array pressure sensor;S2:Using pressure distribution data as the fault data of roller set, then collected fault data is input in probabilistic neural network and is trained structure fault diagnosis model;S3:Real-time collected roller set fault data is input in fault diagnosis model and carries out fault diagnosis and judgement, obtains the malfunction of roller set.The present invention predicts failure using probabilistic neural network, avoids the local optimum of BP neural network, the defects of training time is long.So that the fault diagnosis of roller set has good improvement in real-time and accuracy rate.
Description
Technical field
The invention belongs to fault diagnosis technology fields, are related to a kind of roller set based on array-type flexible pressure sensor and set
Standby fault detection method.
Background technology
Roller set is common mechanical equipment in industrial production, such as film laminator, grinder.The detection of mechanical breakdown can be with
It show whether mechanical equipment breaks down by the analysis of the signals such as vibrations, the sound to mechanical equipment, but shakes harmony message
It is number unstable, easily interfered by extraneous factor.
Invention content
In view of this, the purpose of the present invention is to provide a kind of roller set equipment based on array-type flexible pressure sensor
Fault detection method obtains the pressure data between roller set using pressure sensor, by the analysis to pressure data, precisely
Roller set failure is judged.
In order to achieve the above objectives, the present invention provides following technical solution:
Roller set equipment fault detection method based on array-type flexible pressure sensor, this method include:
S1:The pressure distribution data between roller set is acquired using array pressure sensor;
S2:Using pressure distribution data as the fault data of roller set, then collected fault data is input to probability
Structure fault diagnosis model is trained in neural network;
S3:Real-time collected roller set fault data is input in fault diagnosis model and carries out fault diagnosis and sentences
It is disconnected, obtain the malfunction of roller set.
Further, step S1 is specifically included:
S101:Array pressure sensor is connect with data acquisition microcontroller, microcontroller is connected to computer;
S102:Open power supply, arrange parameter;
S103:Computer sends acquisition instructions to microcontroller;
S104:Microcontroller gathered data simultaneously carries out filtering and noise reduction, and send data to computer according to communication protocol;
S105:Computer check data simultaneously store, and continue to send acquisition instructions.
Further, pass through serial ports or USB connections between the microcontroller and the computer.
Further, step S2 is comprised the following steps:
S201:To the collected pressure distribution data of institute plus identifier, the fault category belonging to fault data is marked;
S202:Pressure distribution data is divided into training dataset and test data set, and by training dataset and test
Data set is converted into vector, is normalized;
S203:Smoothing factor is chosen, establishes Probabilistic Neural Network Fault Diagnosis model;
S204:Training dataset is input to Probabilistic Neural Network Fault Diagnosis model, is trained;
S205:It is tested using the trained fault diagnosis model of test data set pair;
S206:Step S202-S205 is repeated by the pressure distribution data of multi collect, adjusts probabilistic neural network
Smoothing factor, until the accuracy rate of fault diagnosis model is met the requirements.
Further, the fault category described in step S201 is respectively that roller is left-leaning, roller is normal, roller Right deviation, roller
On have foreign matter.
The beneficial effects of the present invention are:In data acquisition, the present invention passes through with utilizing vibrations and voice signal to machine
The method that tool failure is diagnosed is compared, and greatly reduces influence of the extraneous factor to the data precision;In algorithm process, this
Invention predicts failure using probabilistic neural network, avoids local optimum, training time length of BP neural network etc.
Defect.So that the fault diagnosis of roller set has good improvement in real-time and accuracy rate.
Description of the drawings
In order to make the purpose of the present invention, technical solution and advantageous effect clearer, the present invention provides drawings described below and carries out
Explanation:
Fig. 1 is data collecting system data interaction block diagram of the present invention;
Fig. 2 is four kinds of fault type schematic diagrames of roller set;
Fig. 3 is the pressure-plotting of four kinds of fault types of roller set;
Fig. 4 is the partial results of roller set fault detect;
Wherein reference numeral is:
1 is left-leaning for roller, and 2 is normal for roller, and 3 be roller Right deviation, and 4 is have foreign matter on roller, and 5 be legend, and 101 be roller
Group, 102 be array-type flexible pressure sensor, and 103 acquire microcontroller for data, and 104 be terminal.
Specific embodiment
Below in conjunction with attached drawing, the preferred embodiment of the present invention is described in detail.
Diagnosis detection is carried out to roller set failure using array-type flexible pressure sensor the present invention provides a kind of
Method is acquired the pressure distribution data between roller set by array-type flexible pressure sensor, is made with pressure distribution data
For the fault data of roller set, then collected fault data is input in probabilistic neural network and is trained structure failure and examines
Disconnected model, finally will real-time collected roller then to being tested using the fault diagnosis model that probabilistic neural network is built
Wheel group fault data, which is input in fault diagnosis model, carries out fault diagnosis and judgement, obtains the malfunction of roller set, realizes
The fault diagnosis of roller set.
Wherein, array-type flexible pressure sensor can be customized according to the needs of actual conditions.
Training and structure fault diagnosis model are included to the classification of fault data and to Probabilistic Neural Network Fault Diagnosis mould
The training of type.
In training and structure fault diagnosis model, roller set fault data is acquired first, is then added to data
Data set is divided into training dataset by upper identifier according to a certain percentage to mark the fault category belonging to fault data
And test data set.
Training Probabilistic Neural Network Fault Diagnosis model, vector is converted by training dataset and test data set respectively,
And it is normalized.Training dataset is input to Probabilistic Neural Network Fault Diagnosis model, model is trained, so
It is tested afterwards using the trained fault diagnosis model of test data set pair.Suitable probabilistic neural is chosen by test of many times
The smoothing factor of network so that the accuracy rate higher of fault diagnosis model.
Obtained fault diagnosis model is applied in real-time diagnosis system, realizes the fault diagnosis of roller set.
In practical applications, according to the size custom arrays formula pressure sensor of practical roller set, array pressure
Sensor perceives the pressure distribution between roller set, and array pressure sensor and data acquisition microcontroller are connect, microcontroller and
For computer by serial ports or USB connections, computer sends instruction control single chip computer acquisition pressure distribution data, microcontroller acquisition
Pressure distribution data between roller set, and denoising is filtered to collected data, then by data according to protocol format
Computer is transferred to, computer pre-processes data, and obtained data are input to trained fault diagnosis algorithm mould
Type carries out decision judgement to the fault type of roller set.Data interaction block diagram is as shown in Figure 1.
Step S1 is specifically included:
S101:Array pressure sensor is connect with data acquisition microcontroller, microcontroller is connected to computer, such as Fig. 1
It is shown;
S102:Open power supply, arrange parameter;
S103:Computer sends acquisition instructions to microcontroller;
S104:Microcontroller gathered data simultaneously carries out filtering and noise reduction, and send data to computer according to communication protocol;
S105:Computer check data simultaneously store, and continue to send acquisition instructions.
Fault category is respectively, and roller "Left"-deviationist 1, roller are normal 2, have foreign matter 4 on roller Right deviation 3, roller, such as Fig. 2 and Fig. 3
It is shown, wherein 5 be legend.
Failure decision specifically comprises the following steps:
1st, data set is read, and to every data that data are concentrated plus identifier, flag data fault category;
2nd, data set is divided into training dataset and test data set according to a certain percentage;
3rd, data set is converted into vector, and be normalized;
4th, appropriate smoothing factor is chosen, establishes probabilistic neural network;
5th, training dataset is inputted into neural network, training Probabilistic Neural Network Fault Diagnosis model;
6th, fault diagnosis model is tested;
7th, multiple test experiments are carried out, smoothing factor is adjusted, makes accuracy rate highest as far as possible;
8th, fault data is acquired, input fault diagnostic model carries out failure predication judgement;
9th, prediction result is obtained.
Wherein, the results are shown in Figure 4 for fractional prediction.
By using above-mentioned technical proposal, in data acquisition, the present invention passes through with utilizing vibrations and voice signal to machine
The method that tool failure is diagnosed is compared, and greatly reduces influence of the extraneous factor to the data precision;In algorithm process, this
Invention predicts failure using probabilistic neural network, avoids local optimum, training time length of BP neural network etc.
Defect.So that the fault diagnosis of roller set has good improvement in real-time and accuracy rate.
Finally illustrate, preferred embodiment above is only to illustrate the technical solution of invention and unrestricted, although passing through
Above preferred embodiment is described in detail the present invention, however, those skilled in the art should understand that, can be in shape
Various changes are made in formula and to it in details, without departing from claims of the present invention limited range.
Claims (5)
1. the roller set equipment fault detection method based on array-type flexible pressure sensor, it is characterised in that:This method includes:
S1:The pressure distribution data between roller set is acquired using array pressure sensor;
S2:Using pressure distribution data as the fault data of roller set, then collected fault data is input to probabilistic neural
Structure fault diagnosis model is trained in network;
S3:Real-time collected roller set fault data is input in fault diagnosis model and carries out fault diagnosis and judgement, is obtained
Go out the malfunction of roller set.
2. the roller set equipment fault detection method according to claim 1 based on array-type flexible pressure sensor,
It is characterized in that:Step S1 is specifically included:
S101:Array pressure sensor is connect with data acquisition microcontroller, microcontroller is connected to computer;
S102:Open power supply, arrange parameter;
S103:Computer sends acquisition instructions to microcontroller;
S104:Microcontroller gathered data simultaneously carries out filtering and noise reduction, and send data to computer according to communication protocol;
S105:Computer check data simultaneously store, and continue to send acquisition instructions.
3. the roller set equipment fault detection method according to claim 2 based on array-type flexible pressure sensor,
It is characterized in that:Pass through serial ports or USB connections between the microcontroller and the computer.
4. the roller set equipment fault detection method according to claim 2 based on array-type flexible pressure sensor,
It is characterized in that:Step S2 is comprised the following steps:
S201:To the collected pressure distribution data of institute plus identifier, the fault category belonging to fault data is marked;
S202:Pressure distribution data is divided into training dataset and test data set, and by training dataset and test data
Collection is converted into vector, is normalized;
S203:Smoothing factor is chosen, establishes Probabilistic Neural Network Fault Diagnosis model;
S204:Training dataset is input to Probabilistic Neural Network Fault Diagnosis model, is trained;
S205:It is tested using the trained fault diagnosis model of test data set pair;
S206:Step S202-S205 is repeated by the pressure distribution data of multi collect, adjusts the flat of probabilistic neural network
The sliding factor, until the accuracy rate of fault diagnosis model is met the requirements.
5. the roller set equipment fault detection method according to claim 4 based on array-type flexible pressure sensor,
It is characterized in that:Fault category described in step S201 is respectively that roller is left-leaning, roller is normal, there have on roller Right deviation, roller to be different
Object.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810070059.6A CN108204892B (en) | 2018-01-24 | 2018-01-24 | Roller set equipment fault detection method based on flexible array type pressure sensor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810070059.6A CN108204892B (en) | 2018-01-24 | 2018-01-24 | Roller set equipment fault detection method based on flexible array type pressure sensor |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108204892A true CN108204892A (en) | 2018-06-26 |
CN108204892B CN108204892B (en) | 2020-02-07 |
Family
ID=62606387
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810070059.6A Active CN108204892B (en) | 2018-01-24 | 2018-01-24 | Roller set equipment fault detection method based on flexible array type pressure sensor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108204892B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108995225A (en) * | 2018-07-04 | 2018-12-14 | 合肥欧语自动化有限公司 | A kind of automation rolling device |
CN113392936A (en) * | 2021-07-09 | 2021-09-14 | 四川英创力电子科技股份有限公司 | Oven fault diagnosis method based on machine learning |
CN115329493A (en) * | 2022-08-17 | 2022-11-11 | 兰州理工大学 | Impeller mechanical fault detection method based on centrifugal pump digital twin model |
WO2023143190A1 (en) * | 2022-01-28 | 2023-08-03 | International Business Machines Corporation | Unsupervised anomaly detection of industrial dynamic systems with contrastive latent density learning |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN203719796U (en) * | 2014-02-28 | 2014-07-16 | 厦门乃尔电子有限公司 | Pressure sensor flexible package structure for multipoint measurement |
CN105976021A (en) * | 2016-05-24 | 2016-09-28 | 北京工业大学 | Fault diagnosis method for roller assembly of belt conveyor |
CN106546362A (en) * | 2016-10-27 | 2017-03-29 | 中国科学院重庆绿色智能技术研究院 | A kind of capacitance pressure transducer, based on Graphene |
CN106680616A (en) * | 2016-10-27 | 2017-05-17 | 北京智芯微电子科技有限公司 | Fault detection terminal of power distribution network and system thereof |
CN107505548A (en) * | 2017-08-29 | 2017-12-22 | 华北电力大学(保定) | A kind of type local-discharge ultrasonic localization method based on flexible array sensor |
-
2018
- 2018-01-24 CN CN201810070059.6A patent/CN108204892B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN203719796U (en) * | 2014-02-28 | 2014-07-16 | 厦门乃尔电子有限公司 | Pressure sensor flexible package structure for multipoint measurement |
CN105976021A (en) * | 2016-05-24 | 2016-09-28 | 北京工业大学 | Fault diagnosis method for roller assembly of belt conveyor |
CN106546362A (en) * | 2016-10-27 | 2017-03-29 | 中国科学院重庆绿色智能技术研究院 | A kind of capacitance pressure transducer, based on Graphene |
CN106680616A (en) * | 2016-10-27 | 2017-05-17 | 北京智芯微电子科技有限公司 | Fault detection terminal of power distribution network and system thereof |
CN107505548A (en) * | 2017-08-29 | 2017-12-22 | 华北电力大学(保定) | A kind of type local-discharge ultrasonic localization method based on flexible array sensor |
Non-Patent Citations (1)
Title |
---|
梁晴晴等: "基于概率神经网络的离心式制冷机故障诊断", 《暖通空调》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108995225A (en) * | 2018-07-04 | 2018-12-14 | 合肥欧语自动化有限公司 | A kind of automation rolling device |
CN113392936A (en) * | 2021-07-09 | 2021-09-14 | 四川英创力电子科技股份有限公司 | Oven fault diagnosis method based on machine learning |
CN113392936B (en) * | 2021-07-09 | 2022-09-02 | 四川英创力电子科技股份有限公司 | Oven fault diagnosis method based on machine learning |
WO2023143190A1 (en) * | 2022-01-28 | 2023-08-03 | International Business Machines Corporation | Unsupervised anomaly detection of industrial dynamic systems with contrastive latent density learning |
CN115329493A (en) * | 2022-08-17 | 2022-11-11 | 兰州理工大学 | Impeller mechanical fault detection method based on centrifugal pump digital twin model |
CN115329493B (en) * | 2022-08-17 | 2023-07-14 | 兰州理工大学 | Impeller machinery fault detection method based on digital twin model of centrifugal pump |
Also Published As
Publication number | Publication date |
---|---|
CN108204892B (en) | 2020-02-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108204892A (en) | Roller set equipment fault detection method based on array-type flexible pressure sensor | |
CN107345857A (en) | A kind of electro spindle condition monitoring and failure diagnosis system and its monitoring, diagnosing method | |
CN103235098A (en) | On-line ground water quality monitoring system | |
CN109102189A (en) | A kind of electrical equipment is health management system arranged and method | |
CN102926983A (en) | State inspection system for compressor unit | |
CN109670584A (en) | A kind of fault diagnosis method and system based on big data | |
CN102607641A (en) | Cluster anomaly detection method of combustion gas turbine | |
CN109800894A (en) | One kind is based on deep learning discovery metering automation pipeline stall diagnostic method and diagnostic system | |
CN107064236A (en) | A kind of on-line checking electrodialysis plant intermediate ion exchanges the device and method of fouling membrane | |
Ou et al. | Deep transfer residual variational autoencoder with multi-sensors fusion for tool condition monitoring in impeller machining | |
CN109598309B (en) | Detection system and monitoring method of metal packaging punching machine | |
CN203274900U (en) | Dynamic on-line weighing state monitoring system | |
CN113092044B (en) | Rotary machine fault diagnosis method based on weighted level visible graph | |
CN117404767B (en) | Intelligent perception-based filter differential pressure safety monitoring method and system | |
CN116977708A (en) | Bearing intelligent diagnosis method and system based on self-adaptive aggregation visual view | |
CN103199623A (en) | Transformer substation state monitoring system | |
CN116448234A (en) | Power transformer running state voiceprint monitoring method and system | |
CN115339484A (en) | Long-distance passive sensing rail transit health monitoring system and method | |
CN206670841U (en) | A kind of composite plane load-carrying construction stress real-time monitoring system | |
KR102357754B1 (en) | A fault diagnosis system for smart factory using artifical intelligence | |
CN113807431A (en) | Intelligent spindle state evaluation method and system based on multi-source information fusion | |
CN104991547A (en) | Multi-fault diagnosis method driven by practical fault symptom data | |
CN117198458B (en) | Drug screening device fault prediction system based on Internet of things | |
CN115060495A (en) | Intelligent bearing edge diagnosis method and system based on deep interpolation network | |
CN103220335A (en) | River water quality monitoring system based on internet of things |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |