CN110243589B - Fuzzy fault diagnosis method and system for scraper speed reducer - Google Patents
Fuzzy fault diagnosis method and system for scraper speed reducer Download PDFInfo
- Publication number
- CN110243589B CN110243589B CN201910510555.3A CN201910510555A CN110243589B CN 110243589 B CN110243589 B CN 110243589B CN 201910510555 A CN201910510555 A CN 201910510555A CN 110243589 B CN110243589 B CN 110243589B
- Authority
- CN
- China
- Prior art keywords
- fault
- speed reducer
- fuzzy
- scraper speed
- scraper
- 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.)
- Active
Links
Images
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
- G01M13/02—Gearings; Transmission mechanisms
-
- 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
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/028—Acoustic or vibration analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
Abstract
The invention relates to a fuzzy fault diagnosis method and a system for a scraper speed reducer, wherein the method comprises the following steps: step 1, constructing a fuzzy relation matrix based on fault reasons and fault symptoms based on a scraper speed reducer fault case and related knowledge; step 2, constructing a weight matrix based on a rough set based on a scraper speed reducer fault case and related knowledge; step 3, combining the weight matrix and the fuzzy relation matrix to construct a new fuzzy relation matrix; step 4, fuzzifying monitoring parameters of the scraper speed reducer acquired by the multiple sensors to obtain a multi-source fuzzy input vector; and 5, obtaining a fault diagnosis result of the scraper speed reducer by solving the fuzzy matrix and fuzzy judgment based on the new fuzzy relation matrix and the multi-source fuzzy input vector. The method diagnoses the health state of the scraper speed reducer based on the rough set and the fuzzy reasoning, improves the accuracy and efficiency of diagnosis, and ensures the operation reliability of the scraper speed reducer.
Description
Technical Field
The invention belongs to the technical field of coal machine fault diagnosis, and particularly relates to a fuzzy fault diagnosis method and system for a scraper speed reducer.
Background
The scraper speed reducer is one of the most important vulnerable parts in coal mine production activities, and the running state of the scraper speed reducer determines whether the coal mine production activities can be smoothly carried out. The working condition of the scraper speed reducer is severe, the mapping relation between the fault and the symptom is complex, maintenance workers mainly judge the fault of the scraper speed reducer according to experience, so that the fault diagnosis accuracy of the scraper speed reducer is closely related to professional knowledge and practical experience of the maintenance workers, the fault can be found only when major problems occur in many cases, and the fault diagnosis accuracy rate and efficiency are low. With the acceleration of the rhythm of coal mine production, the maintenance mode depending on experience and regular maintenance can not meet the requirement of coal mine production.
With the proposal and wide application of advanced coal mining technical concepts such as intelligent coal mines, unmanned working faces and the like, a state perception system is initially established for monitoring and diagnosing the health state of the scraper speed reducer. The state parameters of the scraper speed reducer, such as vibration, bearing temperature, lubricating oil liquid level, lubricating oil quality, cooling water temperature, cooling water flow and the like, are used for describing the health state of the scraper speed reducer. However, the functions of these state parameters other than vibration in health monitoring and fault diagnosis of the blade reducer are limited to an over-value alarm, and no effective correlation analysis between the parameters is formed, and the cause of the fault cannot be accurately identified. Meanwhile, only by analyzing vibration parameters, the diagnosis of faults of parts such as a bearing, a gear, a coupling and the like of the scraper speed reducer can be realized, and the analysis of faults such as high temperature, lubrication deterioration and the like of the scraper speed reducer cannot be realized, so that the installation of sensors such as temperature, oil quality, flow and the like also loses the due significance.
Disclosure of Invention
The invention aims to provide a fuzzy fault diagnosis method and a fuzzy fault diagnosis system for a scraper speed reducer, which are used for diagnosing the health state of the scraper speed reducer based on rough set and fuzzy reasoning so as to improve the accuracy and efficiency of diagnosis and ensure the operational reliability of the scraper speed reducer.
The invention provides a fuzzy fault diagnosis method for a scraper speed reducer, which comprises the following steps:
step 1, constructing a fuzzy relation matrix based on fault reasons and fault symptoms based on a scraper speed reducer fault case and related knowledge;
step 2, constructing a weight matrix based on a rough set based on a scraper speed reducer fault case and related knowledge;
step 3, combining the weight matrix and the fuzzy relation matrix to construct a new fuzzy relation matrix;
step 4, fuzzifying monitoring parameters of the scraper speed reducer acquired by the multiple sensors to obtain a multi-source fuzzy input vector;
and 5, obtaining a fault diagnosis result of the scraper speed reducer by solving the fuzzy matrix and fuzzy judgment based on the new fuzzy relation matrix and the multi-source fuzzy input vector.
Further, in the step 1, the fault reasons include any one or more of a coupling fault between the motor and the scraper reducer, a coupling fault between the scraper reducer and the sprocket, a bolt loosening fault of the scraper reducer, a fault of an input shaft support bearing of the scraper reducer, a fault of an input shaft gear of the scraper reducer, a fault of an output shaft support bearing of the scraper reducer, a fault of an output shaft gear of the scraper reducer, emulsification of lubricating oil, leakage of lubricating oil of the scraper reducer, insufficient lubricating oil of the scraper reducer, leakage of cooling water of the scraper reducer and blockage of cooling water of the scraper reducer.
Further, the fault sign in step 1 includes any one or more of temperature of an input shaft of the scraper reducer, vibration of the input shaft of the scraper reducer, temperature of an output shaft of the scraper reducer, vibration of the output shaft of the scraper reducer, lubricating oil level of the scraper reducer, oil quality of lubricating oil of the scraper reducer, temperature of cooling water and pressure of the cooling water.
Further, the step 1 comprises:
counting fault cases and related knowledge of the scraper speed reducer by adopting a fuzzy statistical method, and establishing a fuzzy relation table of fault reasons and fault symptoms of the scraper speed reducer;
and constructing a fuzzy relation matrix according to the fuzzy relation table.
Further, the step 2 comprises:
extracting the characteristics of the fault cases and related knowledge of the scraper speed reducer by adopting a rough set method, and establishing a fault reason and fault symptom information table;
performing knowledge extraction and attribute reduction on the established fault reason and fault symptom information table to obtain optimal attribute reduction, and removing redundancy and conflict in the information table;
and setting the weight value of the condition attribute in the optimal attribute reduction to be 1 (except for the condition attribute value of 0), and setting the weight values of other condition attributes to be 0 to obtain a weight matrix.
Further, in step 3, the weight matrix and the fuzzy relation matrix are combined according to the following formula:
R＝R1+α·R2；
in the formula, R is a new fuzzy relation matrix; r1Is a fuzzy relation matrix; r2Is a weight matrix; an alpha weight coefficient.
Further, the step 4 comprises:
according to the characteristics of the acquisition parameters of different sensors, selecting a membership function matched with the characteristics to perform parameter fuzzification; and the half-rising trapezoidal membership function is adopted for the monitoring parameters with the upper limit value, and the half-falling trapezoidal membership function is adopted for the monitoring parameters with the lower limit value.
Further, the fuzzy matrix in step 5 is represented as:
wherein Y is a fuzzy matrix; x is a multi-source fuzzy input vector; and R is a new fuzzy relation matrix.
The invention also provides a fuzzy fault diagnosis system of the scraper speed reducer, which comprises:
the knowledge base module is used for constructing a fuzzy relation matrix based on fault reasons and fault symptoms based on a scraper speed reducer fault case and related knowledge, constructing a weight matrix based on a rough set based on the scraper speed reducer fault case and the related knowledge, and combining the weight matrix and the fuzzy relation matrix to construct a new fuzzy relation matrix;
the parameter fuzzification processing module is used for fuzzifying monitoring parameters of the scraper speed reducer acquired by the multiple sensors to obtain a multi-source fuzzy input vector;
and the fault diagnosis module is used for obtaining a fault diagnosis result of the scraper speed reducer by solving the fuzzy matrix and fuzzy judgment based on the new fuzzy relation matrix and the multi-source fuzzy input vector.
Further, the knowledge base module adopts a rough set method to extract the characteristics of the fault cases and the related knowledge of the scraper speed reducer and establish a fault reason and fault symptom information table;
performing knowledge extraction and attribute reduction on the established fault reason and fault symptom information table to obtain optimal attribute reduction, and removing redundancy and conflict in the information table; and
and setting the weight value of the condition attribute in the optimal attribute reduction to be 1 (except for the condition attribute value of 0), and setting the weight values of other condition attributes to be 0 to obtain a weight matrix.
By means of the scheme, the health state of the scraper speed reducer is diagnosed based on the rough set and the fuzzy reasoning through the scraper speed reducer fuzzy fault diagnosis method and system, the diagnosis accuracy and efficiency are improved, and the operation reliability of the scraper speed reducer is guaranteed.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical solutions of the present invention more clearly understood and to implement them in accordance with the contents of the description, the following detailed description is given with reference to the preferred embodiments of the present invention and the accompanying drawings.
Drawings
FIG. 1 is a flow chart of a fuzzy fault diagnosis method for a scraper speed reducer according to the invention;
FIG. 2 is a block diagram of the fuzzy fault diagnosis system of the scraper speed reducer of the present invention;
fig. 3 is a flow chart of an embodiment of fault diagnosis using the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Referring to fig. 1, the present embodiment provides a fuzzy fault diagnosis method for a blade reducer, including:
step S1, constructing a fuzzy relation matrix based on fault reasons and fault symptoms based on the fault cases of the scraper speed reducer and related knowledge (such as expert knowledge);
s2, constructing a weight matrix based on a rough set based on the fault case and the related knowledge of the scraper reducer;
step S3, merging the weight matrix and the fuzzy relation matrix to construct a new fuzzy relation matrix;
step S4, fuzzifying monitoring parameters of the scraper speed reducer acquired by multiple sensors to obtain a multi-source fuzzy input vector;
and step S5, obtaining a fault diagnosis result of the scraper speed reducer by solving the fuzzy matrix and fuzzy judgment based on the new fuzzy relation matrix and the multi-source fuzzy input vector.
According to the fuzzy fault diagnosis method for the scraper speed reducer, the health state of the scraper speed reducer is diagnosed based on the rough set and the fuzzy reasoning, so that the accuracy and efficiency of diagnosis are improved, and the operation reliability of the scraper speed reducer is guaranteed.
In this embodiment, the failure cause in step S1 includes any one or more of a coupling failure between the motor and the reduction flight, a coupling failure between the reduction flight and the sprocket, a bolt loosening failure of the reduction flight, a failure of a support bearing of an input shaft of the reduction flight, a failure of a gear of an input shaft of the reduction flight, a failure of a support bearing of an output shaft of the reduction flight, a failure of a gear of an output shaft of the reduction flight, emulsification of lubricating oil, leakage of lubricating oil of the reduction flight, shortage of lubricating oil of the reduction flight, leakage of cooling water of the reduction flight, and blockage of cooling water of the.
In the present embodiment, the fault sign in step S1 includes any one or more of a reduction flight input shaft temperature, reduction flight input shaft vibration, reduction flight output shaft temperature, reduction flight output shaft vibration, reduction flight lubricant oil level, reduction flight lubricant oil quality, cooling water temperature, and cooling water pressure.
In this embodiment, step 1 includes:
counting fault cases and related knowledge of the scraper speed reducer by adopting a fuzzy statistical method, and establishing a fuzzy relation table of fault reasons and fault symptoms of the scraper speed reducer;
and constructing a fuzzy relation matrix according to the fuzzy relation table.
In this embodiment, the step S2 includes:
extracting the characteristics of the fault cases and related knowledge of the scraper speed reducer by adopting a rough set method, and establishing a fault reason and fault symptom information table;
performing knowledge extraction and attribute reduction on the established fault reason and fault symptom information table to obtain optimal attribute reduction, and removing redundancy and conflict in the information table;
and setting the weight value of the condition attribute in the optimal attribute reduction to be 1 (except for the condition attribute value of 0), and setting the weight values of other condition attributes to be 0 to obtain a weight matrix.
In this embodiment, in step S3, the weight matrix and the fuzzy relation matrix are combined according to the following formula:
R＝R1+α·R2；
in the formula, R is a new fuzzy relation matrix; r1Is a fuzzy relation matrix; r2Is a weight matrix; an alpha weight coefficient.
In the present embodiment, step S4 includes:
according to the characteristics of the acquisition parameters of different sensors, selecting a membership function matched with the characteristics to perform parameter fuzzification; and the half-rising trapezoidal membership function is adopted for the monitoring parameters with the upper limit value, and the half-falling trapezoidal membership function is adopted for the monitoring parameters with the lower limit value.
In the present embodiment, the fuzzy matrix in step S5 is represented as:
wherein Y is a fuzzy matrix; x is a multi-source fuzzy input vector; and R is a new fuzzy relation matrix.
Referring to fig. 2, the present embodiment also provides a fuzzy fault diagnosis system of a speed reducer scraper for performing the fault diagnosis method, including:
the knowledge base module 10 is used for constructing a fuzzy relation matrix based on fault reasons and fault symptoms based on the fault cases and related knowledge of the scraper reducer, constructing a weight matrix based on a rough set based on the fault cases and related knowledge of the scraper reducer, combining the weight matrix and the fuzzy relation matrix and constructing a new fuzzy relation matrix;
the parameter fuzzification processing module 20 is used for fuzzifying monitoring parameters of the scraper speed reducer acquired by the multiple sensors to obtain a multi-source fuzzy input vector;
and the fault diagnosis module 30 is used for obtaining a fault diagnosis result of the scraper speed reducer by solving the fuzzy matrix and fuzzy judgment based on the new fuzzy relation matrix and the multi-source fuzzy input vector.
The fuzzy fault diagnosis system for the scraper speed reducer diagnoses the health state of the scraper speed reducer based on the rough set and the fuzzy reasoning, improves the accuracy and efficiency of diagnosis, and ensures the operational reliability of the scraper speed reducer.
In this embodiment, the knowledge base module 10 adopts a fuzzy statistical method to perform statistics on the scraper speed reducer fault cases and related knowledge, and establishes a fuzzy relation table between the scraper speed reducer fault reasons and fault symptoms; and constructing a fuzzy relation matrix according to the fuzzy relation table.
In the embodiment, the knowledge base module 10 adopts a rough set method to perform feature extraction on the fault case and the related knowledge of the scraper speed reducer, and establishes a fault reason and fault symptom information table;
performing knowledge extraction and attribute reduction on the established fault reason and fault symptom information table to obtain optimal attribute reduction, and removing redundancy and conflict in the information table; and
and setting the weight value of the condition attribute in the optimal attribute reduction to be 1 (except for the condition attribute value of 0), and setting the weight values of other condition attributes to be 0 to obtain a weight matrix.
In this embodiment, the knowledge base module 10 combines the weight matrix and the fuzzy relation matrix according to the following formula:
R＝R1+α·R2；
in the formula, R is a new fuzzy relation matrix; r1As a fuzzy relationA matrix; r2Is a weight matrix; an alpha weight coefficient.
In this embodiment, the parameter fuzzification processing module 20 selects a membership function matched with the characteristics of the acquired parameters of different sensors to perform parameter fuzzification; and the half-rising trapezoidal membership function is adopted for the monitoring parameters with the upper limit value, and the half-falling trapezoidal membership function is adopted for the monitoring parameters with the lower limit value.
In the present embodiment, the fault diagnosis module 30 obtains the fault diagnosis result of the speed reducer by solving the following fuzzy matrix and fuzzy evaluation.
Wherein Y is a fuzzy matrix; x is a multi-source fuzzy input vector; and R is a new fuzzy relation matrix.
Referring to fig. 3, in an embodiment, the process of diagnosing the speed reducer fault by applying the fuzzy fault diagnosis method includes:
1) and acquiring running state monitoring data and related measuring point information of the scraper speed reducer. The related measuring point information comprises: measuring point type and measuring point position. The operation state monitoring signals comprise vibration signals, temperature signals, pressure signals, flow signals and the like.
2) And acquiring a fault case and related knowledge (expert knowledge) of the on-site scraper speed reducer.
3) According to a fuzzy statistical method, the obtained fault cases and knowledge are counted to form a fuzzy relation table of fault reasons and fault symptoms of the fuzzy scraper reducer, and the fuzzy relation table is shown in a table 1.
TABLE 1 fuzzy relation matrix of drag reduction unit
Note: failure of the coupler 1, namely abrasion of a coupler pin; failure of the coupler 1 2, namely breakage of a coupler pin; gear 1-input shaft gear; bearing 1-input shaft bearing; gear 2-output shaft gear; bearing 2-output shaft bearing;
4) establishing a fuzzy relation matrix R according to the fuzzy relation table1。
5) And (3) extracting the characteristics of the obtained fault cases and knowledge by adopting a rough set method, and establishing a scraper speed reducer fault reason and fault symptom information table as shown in a table 2.
TABLE 2 SCRAPER REDUCER FAULT PROGRAM AND FAULT PROGRAM INFORMATION TABLE
Note: 0-substantially unchanged; 1-increase or decrease; 2-very large or very small.
And (3) carrying out knowledge extraction and attribute reduction on the established information table to obtain the optimal attribute reduction { c1, c2, c3, c4 and c5}, namely 5 attributes of input shaft temperature, input shaft vibration, output shaft temperature, output shaft vibration, lubricating oil temperature and the like.
6) Setting the weight value of the condition attribute in the optimal attribute reduction to be 1 (except for the attribute value of 0), setting the weight values of other condition attributes to be 0, and transposing the obtained weight matrix to obtain a weight matrix R for keeping the weight matrix consistent with the fuzzy relation matrix2。
7) Will obscure the relationship matrix R1And a weight matrix R2And merging to obtain a new fuzzy relation matrix R, wherein a merging formula is as follows:
R＝R1+α·R2；
wherein: the weight coefficient α is 0.3.
The results are as follows:
8) and fuzzifying the acquired monitoring data (parameters) of the running state of the scraper speed reducer to obtain a fuzzy input vector X.
The monitoring parameters with the upper limit value adopt a half-raised trapezoidal membership function, and the expression is as follows:
the monitoring parameters with the lower limit value adopt a halved trapezoid membership function, and the expression is as follows:
wherein: a-yellow early warning value;
b-red warning value.
TABLE 3 scraper blade speed reducer multisource input parameter measurement
According to the fuzzy input vector obtained by the method:
X＝[0.33 0.83 0.36 0.33 0 0 0 0 0 0 0 0 0]
9) solving a fuzzy matrix:
Y＝[0.53 0 0.3 0 0.28 0.32 0.32 0.2 0.2 0 0 0 0 0.2]
10) operator adopting fuzzy evaluation model
A diagnosis is made.
The fault reason of the scraper speed reducer can be diagnosed according to the fuzzy evaluation operator as follows: and the coupler between the motor and the speed reducer has a fault. The actual proof that the diagnosis conclusion is consistent with the actual fault reason, the conclusion is correct.
The invention fully utilizes the information acquired by the multiple sensors to diagnose the health state of the scraper speed reducer, and simultaneously integrates the field experience, case accumulation and expert knowledge into the fault diagnosis of the scraper speed reducer to form a fault diagnosis expert system suitable for the scraper speed reducer, thereby improving the utilization rate of various monitoring resources, ensuring the running reliability of the scraper speed reducer and having very important significance for the application of the intelligent and unmanned technology of the coal mine. The method specifically comprises the following technical effects:
1. fusion diagnosis of multisource sensor data of the scraper speed reducer is realized. The state monitoring data of the scraper speed reducer is fully utilized to realize the diagnosis and analysis of the health state of the scraper speed reducer, so that the monitoring and diagnosis result of the scraper speed reducer is not limited to threshold alarm.
2. And the fault case data collected on site is processed by adopting a rough set method, so that redundancy and conflict in information are removed. According to the optimal attribute reduction, the leading signs of the fault representation of the scraper speed reducer are established, the weight of the scraper speed reducer is enhanced, and the diagnosis result is more accurate.
3. The fuzzy fault diagnosis method is adopted, the description of site on fault symptoms is met, the site fault case information can be deeply excavated, the fuzzy relation matrix between the fault reasons and the fault symptoms of the scraper speed reducer is established, and the diagnosis efficiency and accuracy of the system are improved.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, it should be noted that, for those skilled in the art, many modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (4)
1. A fuzzy fault diagnosis method for a scraper speed reducer is characterized by comprising the following steps:
step 1, constructing a fuzzy relation matrix based on fault reasons and fault symptoms based on a scraper speed reducer fault case and related knowledge, and comprising the following steps:
counting fault cases and related knowledge of the scraper speed reducer by adopting a fuzzy statistical method, and establishing a fuzzy relation table of fault reasons and fault symptoms of the scraper speed reducer;
constructing a fuzzy relation matrix according to the fuzzy relation table;
step 2, constructing a weight matrix based on a rough set based on the fault case and the related knowledge of the scraper reducer, and comprising the following steps:
extracting the characteristics of the fault cases and related knowledge of the scraper speed reducer by adopting a rough set method, and establishing a fault reason and fault symptom information table;
performing knowledge extraction and attribute reduction on the established fault reason and fault symptom information table to obtain optimal attribute reduction, and removing redundancy and conflict in the information table;
setting the weight value of the condition attribute in the optimal attribute reduction to be 1, wherein the weight values of other condition attributes are set to be 0 except for the condition attribute value of 0, and obtaining a weight matrix;
step 3, combining the weight matrix and the fuzzy relation matrix to construct a new fuzzy relation matrix; the weight matrix and the fuzzy relation matrix are merged according to the following formula:
R＝R1+α·R2；
in the formula, R is a new fuzzy relation matrix; r1Is a fuzzy relation matrix; r2Is a weight matrix; an alpha weight coefficient;
step 4, fuzzifying monitoring parameters of the scraper speed reducer acquired by the multiple sensors to obtain a multi-source fuzzy input vector, and the method comprises the following steps:
according to the characteristics of the acquisition parameters of different sensors, selecting a membership function matched with the characteristics to perform parameter fuzzification; the monitoring parameters with the upper limit value adopt a half-rising trapezoidal membership function, and the monitoring parameters with the lower limit value adopt a half-falling trapezoidal membership function;
step 5, obtaining a fault diagnosis result of the scraper speed reducer by solving a fuzzy matrix and fuzzy judgment based on the new fuzzy relation matrix and the multi-source fuzzy input vector; the blur matrix is represented as:
wherein Y is a fuzzy matrix; x is a multi-source fuzzy input vector; and R is a new fuzzy relation matrix.
2. The fuzzy fault diagnosis method for the scraper speed reducer according to claim 1, wherein the fault causes in step 1 include any one or more of a coupling fault between a motor and the scraper speed reducer, a coupling fault between the scraper speed reducer and a sprocket, a bolt loosening fault of the scraper speed reducer, a fault of an input shaft support bearing of the scraper speed reducer, a fault of an input shaft gear of the scraper speed reducer, a fault of an output shaft support bearing of the scraper speed reducer, a fault of an output shaft gear of the scraper speed reducer, emulsification of lubricating oil, leakage of lubricating oil of the scraper speed reducer, insufficient lubricating oil of the scraper speed reducer, leakage of cooling water of the scraper speed reducer, and blockage of cooling water of the scraper.
3. The fuzzy fault diagnosis method for the scraper speed reducer as claimed in claim 2, wherein the fault symptoms in step 1 comprise any one or more of temperature of the scraper speed reducer input shaft, vibration of the scraper speed reducer input shaft, temperature of the scraper speed reducer output shaft, vibration of the scraper speed reducer output shaft, oil level of the scraper speed reducer lubricating oil, oil quality of the scraper speed reducer lubricating oil, temperature of the cooling water and pressure of the cooling water.
4. A fuzzy fault diagnosis system of a scraper speed reducer is characterized by comprising:
the knowledge base module is used for constructing a fuzzy relation matrix based on fault reasons and fault symptoms based on a scraper speed reducer fault case and related knowledge, constructing a weight matrix based on a rough set based on the scraper speed reducer fault case and the related knowledge, and combining the weight matrix and the fuzzy relation matrix to construct a new fuzzy relation matrix; the knowledge base module adopts a rough set method to carry out feature extraction on the scraper speed reducer fault case and related knowledge, and establishes a fault reason and fault symptom information table; performing knowledge extraction and attribute reduction on the established fault reason and fault symptom information table to obtain optimal attribute reduction, and removing redundancy and conflict in the information table; setting the weight value of the condition attribute in the optimal attribute reduction to be 1, wherein the weight values of other condition attributes are set to be 0 except for the condition attribute value of 0, and obtaining a weight matrix;
the parameter fuzzification processing module is used for fuzzifying monitoring parameters of the scraper speed reducer acquired by the multiple sensors to obtain a multi-source fuzzy input vector;
and the fault diagnosis module is used for obtaining a fault diagnosis result of the scraper speed reducer by solving the fuzzy matrix and fuzzy judgment based on the new fuzzy relation matrix and the multi-source fuzzy input vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910510555.3A CN110243589B (en) | 2019-06-13 | 2019-06-13 | Fuzzy fault diagnosis method and system for scraper speed reducer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910510555.3A CN110243589B (en) | 2019-06-13 | 2019-06-13 | Fuzzy fault diagnosis method and system for scraper speed reducer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110243589A CN110243589A (en) | 2019-09-17 |
| CN110243589B true CN110243589B (en) | 2021-03-05 |
Family
ID=67886888
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910510555.3A Active CN110243589B (en) | 2019-06-13 | 2019-06-13 | Fuzzy fault diagnosis method and system for scraper speed reducer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110243589B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103033359A (en) * | 2012-12-19 | 2013-04-10 | 西安交通大学 | Wind turbine generator main gear fault diagnosis method of multi-feature multilevel comprehensive judgment |
| CN105858126B (en) * | 2016-05-17 | 2018-04-24 | 中国矿业大学 | A kind of scraper conveyer chain fault diagnosis system and method |
| CN108510146A (en) * | 2017-12-28 | 2018-09-07 | 国家安全生产监督管理总局通信信息中心 | Safety of Coal Mine Production method for prewarning risk and system |
| CN208824743U (en) * | 2018-08-06 | 2019-05-07 | 金川集团股份有限公司 | A kind of flotation float skimming device for strip type groove |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8341108B2 (en) * | 2009-06-09 | 2012-12-25 | Microsoft Corporation | Kind classification through emergent semantic analysis |
-
2019
- 2019-06-13 CN CN201910510555.3A patent/CN110243589B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103033359A (en) * | 2012-12-19 | 2013-04-10 | 西安交通大学 | Wind turbine generator main gear fault diagnosis method of multi-feature multilevel comprehensive judgment |
| CN105858126B (en) * | 2016-05-17 | 2018-04-24 | 中国矿业大学 | A kind of scraper conveyer chain fault diagnosis system and method |
| CN108510146A (en) * | 2017-12-28 | 2018-09-07 | 国家安全生产监督管理总局通信信息中心 | Safety of Coal Mine Production method for prewarning risk and system |
| CN208824743U (en) * | 2018-08-06 | 2019-05-07 | 金川集团股份有限公司 | A kind of flotation float skimming device for strip type groove |
Non-Patent Citations (1)
| Title |
|---|
| "摊铺机刮板输料装置故障分析";陈建华;《工程机械文摘》;20071231(第2期);第62-63页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110243589A (en) | 2019-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101819411B (en) | GPU-based equipment fault early-warning and diagnosis method for improving weighted association rules | |
| CN111043023B (en) | Fracturing pump on-line monitoring and fault diagnosis system | |
| CN106649727B (en) | Database construction method for fault detection of unmanned aerial vehicle flight control system | |
| CN109989740B (en) | Coal measure stratum drilling intelligent identification system and method based on multi-source information fusion | |
| CN100468263C (en) | Continuous miner remote real-time failure forecast and diagnosis method and device | |
| CN102707037B (en) | On-line monitoring system for diesel lubrication oil | |
| CN107797537A (en) | A kind of prognostic and health management method applied to automatic production line | |
| CN106197996A (en) | Offshore crane Fault Diagnosis of Gear Case device and method based on multivariate data | |
| CN109236267A (en) | A kind of drilling machine remote monitoring system | |
| CN103180793A (en) | Anomaly diagnostic device and industrial machine | |
| CN108266178A (en) | A kind of sucker rod pump monitoring of working condition method based on rich information indicator card and DBN | |
| CN109405889B (en) | System and method for predicting fault of working arm reducer of heading machine | |
| CN116186946B (en) | Hydraulic system fault diagnosis method and system based on diagnosis model | |
| CN208456598U (en) | Shield owner's hydraulic monitoring system | |
| CN115526515A (en) | Safety monitoring system of gate for water conservancy and hydropower | |
| CN107025355A (en) | A kind of ship fault diagnosis method and system based on fuzzy nearness | |
| CN116658246A (en) | Coal mine water damage monitoring and early warning system and method | |
| CN113155443B (en) | Lubricating oil state monitoring and fault diagnosis system and method for reducer of coal mining machine | |
| CN110243589B (en) | Fuzzy fault diagnosis method and system for scraper speed reducer | |
| CN103760845B (en) | Monitoring method and system and rotary drilling rig | |
| CN107727392B (en) | State index evaluation and optimization method based on signal detection and ROC analysis | |
| CN116628544A (en) | Fault diagnosis method based on hydraulic winch state on-line monitoring | |
| CN115898848A (en) | Monitoring method and monitoring system of plunger pump | |
| CN115630284A (en) | Air compressor fault analysis and service life prediction system considering service period | |
| CN115326393A (en) | Wind turbine generator bearing pair fault diagnosis method based on temperature information |
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 |