CN109635879B - Coal mining machine fault diagnosis system with optimal parameters - Google Patents
Coal mining machine fault diagnosis system with optimal parameters Download PDFInfo
- Publication number
- CN109635879B CN109635879B CN201910015750.9A CN201910015750A CN109635879B CN 109635879 B CN109635879 B CN 109635879B CN 201910015750 A CN201910015750 A CN 201910015750A CN 109635879 B CN109635879 B CN 109635879B
- Authority
- CN
- China
- Prior art keywords
- particles
- max
- fault
- particle
- fault diagnosis
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 49
- 239000003245 coal Substances 0.000 title claims abstract description 34
- 238000005065 mining Methods 0.000 title claims abstract description 28
- 230000000739 chaotic effect Effects 0.000 claims abstract description 20
- 238000013507 mapping Methods 0.000 claims abstract description 17
- 238000005457 optimization Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 10
- 239000002245 particle Substances 0.000 claims description 65
- 101100129500 Caenorhabditis elegans max-2 gene Proteins 0.000 claims description 12
- 101100083446 Danio rerio plekhh1 gene Proteins 0.000 claims description 12
- 208000024891 symptom Diseases 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 9
- 239000000498 cooling water Substances 0.000 claims description 6
- 239000007788 liquid Substances 0.000 claims description 6
- 230000001502 supplementing effect Effects 0.000 claims description 6
- 239000013585 weight reducing agent Substances 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 5
- 238000001816 cooling Methods 0.000 claims description 3
- 230000009191 jumping Effects 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims 2
- 230000000153 supplemental effect Effects 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000012706 support-vector machine Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21C—MINING OR QUARRYING
- E21C35/00—Details of, or accessories for, machines for slitting or completely freeing the mineral from the seam, not provided for in groups E21C25/00 - E21C33/00, E21C37/00 or E21C39/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mining & Mineral Resources (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mechanical Engineering (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a coal mining machine fault diagnosis system with optimal parameters. The method overcomes the defects that the prior fault diagnosis method of the coal mining machine can not classify the characteristic information well and has low diagnosis accuracy, measures nine fault sign data of the coal mining machine, carries out fault diagnosis on the fault sign data by utilizing a gradient lifting tree GBDT to obtain the fault reason, and has high diagnosis accuracy; the optimal GBDT parameters are searched by an intelligent optimization algorithm, chaotic mapping is adopted to help optimizing, the optimal GBDT parameters are determined, and the diagnosis accuracy of the coal mining machine fault diagnosis system is further improved.
Description
Technical Field
The invention relates to the field of coal mine production, in particular to a coal mining machine fault diagnosis system with optimal parameters.
Background
China is a large energy consumption country, and with the development of national economy, the demand for energy is more and more great. In recent years, coal mining is gradually mechanized, a plurality of large and complex mechanized devices are emerged, the labor productivity is improved, the coal yield is increased, and serious vicious accidents are reduced. Among them, coal mining machines are widely concerned by people as core equipment in coal production. However, due to the complex and severe working environment, the load changes greatly, some key parts are easy to overload and generate abnormity in the production work, and the self composition structure is complex, so the cause of the fault is also complex. Once the coal mining machine fails, the coal mine is stopped, and the whole coal mine production system is broken down and great manpower and financial resources are wasted. Therefore, the faults of the coal mining machine are prevented and reduced, and the faults are accurately judged and timely eliminated after the faults occur, so that the method has important significance for exerting the efficiency of the coal mining machine and increasing the coal yield.
At present, a plurality of fault diagnosis methods exist, and with the development of data mining technology, artificial neural networks, support vector machines and the like are widely used fault classification methods. The artificial neural network has a limit on the generalization capability of the result and is easy to fall into local minimum; the support vector machine has good generalization capability on clear data, but the problem of multi-classification is not easy to solve by using the support vector machine. Therefore, the artificial neural network and the support vector machine are respectively used for fault diagnosis of the coal mining machine, and the characteristic information cannot be well classified.
Disclosure of Invention
In order to overcome the defect that the existing fault diagnosis method of the coal mining machine cannot well classify the characteristic information, the invention aims to provide a fault diagnosis system with optimal parameters.
The purpose of the invention is realized by the following technical scheme: a coal mining machine fault diagnosis system with optimal parameters is composed of a sensing module, a fault diagnosis module and a diagnosis result display instrument. The connection mode of each part is as follows: the sensing module measures all fault symptom data of the coal mining machine and transmits the data to the fault diagnosis module; and the fault diagnosis module intelligently identifies the fault reason according to the fault symptom data and transmits the result to the diagnosis result display instrument for displaying.
Wherein the sensing module measures fault symptom data X = (X1, X2, X3.., X9) of the shearer and transmits the data to the fault diagnosis module. Wherein: x1 represents the oil supplementing pressure when the coal mining machine is in no load; x2 represents the oil supplementing pressure when the coal mining machine is loaded; x3 represents auxiliary system pressure; x4 represents the difference between the total liquid inlet flow rate and the total liquid return flow rate of the hydraulic motor; x5 represents rocker arm lift time; x6 represents motor current; x7 represents the motor temperature; x8 represents cooling water pressure; and X9 represents the cooling water flow rate. The set of causes of failure is Y = (Y1, Y2, Y3., Y7), where Y1 represents a main pump failure; y2 represents a failure of the oil replenishing pump; y3 represents an oil filter failure; y4 represents an auxiliary pump failure; y5 represents a hydraulic motor failure; y6 represents motor overload; y7 indicates a cooling system failure. Each fault symptom data X = (X1, X2, X3., X9) corresponds to one or more fault causes of seven fault causes Y1 to Y7.
Further, the fault diagnosis module uses the gradient lifting tree GBDT as a classifier and optimizes two parameters n _ estimators and learning _ rate of the GBDT by using an optimization algorithm, wherein n _ estimators represents the number of the largest weak learners and learning _ rate represents a weight reduction coefficient of each weak learner. The optimization steps are as follows:
(1) The maximum number of weak learners n _ estimators and the weight reduction factor for each weak learner learning, learning _ rate, are optimization objectives. Randomly initializing N particles, wherein the initial position of each particle is p i (0)＝(p i1 (0)，p i2 (0) I =1,2, N, setting p min1 ≤p i1 ≤p max1 ，p min2 ≤p i2 ≤p max2 Initial velocity v i (0)＝(v i1 (0)，v i2 (0))，v min1 ≤v i1 ≤v max1 ，v min2 ≤v i2 ≤v max2 Current iteration t =0, maximum iteration t max Where the indices min and max represent the minimum and maximum values of the corresponding variables, respectively. Set the range of N to [10,100 ]]，p min1 ＝10，p max1 ＝10 2 ，p min2 ＝10 -4 ，p max2 ＝1，v min1 ＝1，v max1 ＝50，v min2 ＝10 -4 ，v max2 ＝0.05，t max In the range of [10,100 ]]。
(2) The current position p of each particle i (t)＝(p i1 (t)，p i2 (t)) the parameters of the GBDT classifier are set as the values of the parameters n _ estimators and learning _ rate. The input of the classifier is X = (X1, X2, X3., X9), and the output is the corresponding cause of the fault. Dividing all samples with complete input and output pairs into a training set and a test set, inputting the training set into a GBDT classifier for training, and calculating the classification accuracy rate fit of the test set i (t) of (d). Memory fit worst (t)＝min j∈{1，...，N} fit j (t)，fit best (t)＝max j∈{1，...，N} fit j And (t) respectively representing the highest classification accuracy and the lowest classification accuracy in all the particles of the iteration.
(3) When t is greater than or equal to 1, if fit i (t)＜fit i (t-1), then the position p of the current particle is determined i (t) performing chaotic mapping according to the following formula:
p″ i (t)＝4p′ i (t)(1-p′ i (t)) (2)
wherein p' i (t) and p ″) i (t) is an intermediate variable in the chaotic mapping process,
the position of the particle after chaotic mapping. Because some particles are subjected to chaotic mapping and some particles are not subjected to chaotic mapping, for subsequent unified representation, the chaotic mapping-performed particles are asserted to be/or>
p i (t) represents the current position of the particle. And (5) repeating the step (2) and then jumping to the step (4).
(4) Acceleration a of each particle i (t) is obtained by:
wherein rand j Is [0,1 ]]Random number between, m i (t) represents the absolute mass of particle i, M i (t) denotes the relative mass of particle i, G (t) denotes the gravitational parameter as a function of the number of iterations, R ij Denotes the distance between particle i and particle j, F ij (t) represents the force of particle j on particle i, and ε is a very small constant, typically 10 -10 ，F i (t) represents the sum of the forces of all other particles on particle i, a i (t) represents the acceleration of the particle i.
(5) Velocity v of the renewed particle i And position p i ：
v i (t+1)＝rand i ×v i (t)+a i (t) (11)
p i (t+1)＝p i (t)+v i (t+1) (12)
Wherein rand i Is [0,1 ]]A random number in between.
(6) The number of iterations t = t +1. Repeating steps (2) to (5) with the updated velocity and position until t = t is satisfied max The iteration is stopped. And after the iteration is finished, recording the positions of the particles which enable the classification accuracy of the test set to be highest, and determining the positions as GBDT classifier parameters n _ estimators and learning _ rateThe value of (c). And training the GBDT classifier under the parameter setting to obtain a final fault diagnosis model.
And further, inputting data X = (X1, X2, X3.., X9) measured by a sensing module with unknown classification results into the final fault diagnosis model obtained in the step (6), analyzing to obtain a specific fault reason, and transmitting the result to a diagnosis result display instrument for displaying.
The invention has the following beneficial effects: the method measures nine fault symptom data of the coal mining machine, utilizes the gradient lifting tree GBDT to carry out fault diagnosis on the fault symptom data to obtain fault reasons, and has high diagnosis accuracy; the optimal GBDT parameters are searched by an intelligent optimization algorithm, chaotic mapping is adopted to help optimizing, the optimal GBDT parameters are determined, and the diagnosis accuracy of the coal mining machine fault diagnosis system is further improved.
Drawings
Fig. 1 is a schematic structural view of the present invention.
FIG. 2 is a flow chart of parameter optimization in the fault diagnosis module of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings.
Referring to fig. 1, the coal mining machine fault diagnosis system with optimal parameters comprises a sensing module 2, a fault diagnosis module 3 and a diagnosis result display instrument 6. The connection mode of each part is as follows: the sensing module 2 measures nine fault symptom data of the coal mining machine 1 and transmits the data to the fault diagnosis module 3; the fault diagnosis module 3 intelligently identifies the fault reason according to the fault symptom data and transmits the result to the diagnosis result display instrument 6 for displaying.
The sensing module 2 measures fault symptom data X = (X1, X2, X3,.., X9) of the coal mining machine, and transmits the data to the fault diagnosis module 3. Wherein: x1 represents the oil supplementing pressure when the coal mining machine is in no load; x2 represents the oil supplementing pressure when the coal mining machine is loaded; x3 represents auxiliary system pressure; x4 represents the difference between the total liquid inlet flow rate and the total liquid return flow rate of the hydraulic motor; x5 represents rocker arm lift time; x6 represents motor current; x7 represents the motor temperature; x8 represents cooling water pressure; x9 represents cooling water flow. The set of causes of failure is Y = (Y1, Y2, Y3., Y7), where Y1 represents a main pump failure; y2 represents a failure of the oil replenishing pump; y3 represents an oil filter failure; y4 represents an auxiliary pump failure; y5 represents a hydraulic motor failure; y6 represents motor overload; y7 indicates a cooling system failure. Each fault symptom data X = (X1, X2, X3., X9) corresponds to one or more fault causes of seven fault causes Y1 to Y7.
Further, the diagnostic model of the fault diagnosis module 3 is a gradient-boosted tree GBDT classifier 5, and two parameters n _ estimators and learning _ rate of the GBDT classifier 5 are optimized by using the parameter intelligent optimization 4, where n _ estimators represents the maximum number of weak learners, and learning _ rate represents a weight reduction coefficient of each weak learner. Referring to fig. 2, the optimization steps are as follows:
(1) The maximum number of weak learners n _ estimators and the weight reduction coefficient learning _ rate of each weak learner are optimization objectives. Randomly initializing N particles, wherein the initial position of each particle is p i (0)＝(p i1 (0)，p i2 (0) I =1,2, N, setting p min1 ≤p i1 ≤p max1 ，p min2 ≤p i2 ≤p max2 Initial velocity v i (0)＝(v i1 (0)，v i2 (0))，v min1 ≤v i1 ≤v max1 ，v min2 ≤v i2 ≤v max2 Current iteration t =0, maximum iteration t max Where the indices min and max represent the minimum and maximum values of the corresponding variables, respectively. Set the range of N to [10,100 ]]，p min1 ＝10，p max1 ＝10 2 ，p min2 ＝10 -4 ，p max2 ＝1，v min1 ＝1，v max1 ＝50，v min2 ＝10 -4 ，v max2 ＝0.05，t max In the range of [10,100 ]]。
(2) The current position p of each particle i (t)＝(p i1 (t)，p i2 (t)) the parameters of the GBDT classifier 5 are set as the values of the parameters n _ estimators and learning _ rate. The GBDT classifier 5 has an input of X = (X1, X2, X3,.., X9) and an output of correspondenceThe cause of the failure of (2). Dividing all samples with complete input and output pairs into a training set and a test set, inputting the training set into a GBDT classifier 5 for training, and calculating the classification accuracy fit of the test set i (t) of (d). Memory of fit worst (t)＝min j∈{1，...，N} fit j (t)，fit best (t)＝max j∈{1，...，N} fit j And (t) respectively representing the highest classification accuracy and the lowest classification accuracy in all the particles of the iteration.
(3) When t is greater than or equal to 1, if fit i (t)＜fit i (t-1), then the position p of the current particle is determined i (t) performing chaotic mapping according to the following formula:
p″ i (t)＝4p′ i (t)(1-p′ i (t)) (2)
wherein p' i (t) and p ″) i (t) is an intermediate variable in the chaotic mapping process,
the position of the particle after chaotic mapping. Because some particles are subjected to chaotic mapping and some particles are not subjected to chaotic mapping, for subsequent unified representation, the chaotic mapping-performed particles are asserted to be/or>
p i (t) represents the current position of the particle. And (5) repeating the step (2) and then jumping to the step (4).
(4) Acceleration a of each particle i (t) is obtained by:
wherein rand j Is [0,1 ]]Random number between, m i (t)) represents the absolute mass of particle i, M i (t) denotes the relative mass of particle i, G (t) denotes the gravitational parameter as a function of the number of iterations, R ij Denotes the distance between particle i and particle j, F ij (t) represents the force of particle j on particle i, and ε is a very small constant, typically 10 -10 ，F i (t) represents the sum of the forces of all other particles on particle i, a i (t) represents the acceleration of the particle i.
(5) Velocity v of the renewed particle i And position p i ：
v i (t+1)＝rand i ×v i (t)+a i (t) (11)
p i (t+1)＝p i (t)+v i (t+1) (12)
Wherein rand i Is [0,1 ]]A random number in between.
(6) The number of iterations t = t + 1. Repeating steps (2) to (5) with the updated speed and position until t = t is satisfied max The iteration is stopped. After the iteration is finished, the positions of the particles which enable the test set to be classified with the highest accuracy are recorded and determined as the values of the parameters n _ estimators and learning _ rate of the GBDT classifier 5. And training the GBDT classifier 5 under the parameter setting to obtain a final fault diagnosis model.
Further, data X = (X1, X2, X3,. Once, X9) measured by the sensor module 2 with unknown classification results are input into the final fault diagnosis model obtained in step (6), a specific fault reason is obtained through analysis, and the result is transmitted to the diagnosis result display instrument 6 to be displayed.
The above-described embodiments are intended to illustrate rather than limit the invention, and any modifications and variations of the present invention are within the spirit and scope of the appended claims.
Claims (1)
1. The utility model provides an optimal coal-winning machine fault diagnosis system of parameter which characterized in that: the system comprises a sensing module, a fault diagnosis module and a diagnosis result display instrument;
the sensing module measures fault symptom data X = (X1, X2, X3, \8230;, X9) of the coal mining machine and transmits the data to the fault diagnosis module; wherein: x1 represents the oil supplementing pressure when the coal mining machine is in no load; x2 represents the oil supplementing pressure when the coal mining machine is loaded; x3 represents auxiliary system pressure; x4 represents the difference between the total liquid inlet flow rate and the total liquid return flow rate of the hydraulic motor; x5 represents rocker arm lift time; x6 represents a motor current; x7 represents the motor temperature; x8 represents cooling water pressure; x9 represents cooling water flow rate; the set of failure causes is Y = (Y1, Y2, Y3, \8230;, Y7), where Y1 represents a main pump failure; y2 represents a supplemental oil pump failure; y3 represents an oil filter failure; y4 represents an auxiliary pump failure; y5 represents a hydraulic motor failure; y6 represents motor overload; y7 represents a cooling system failure; each fault symptom data X = (X1, X2, X3, \8230;, X9) corresponds to one or more fault causes among seven fault causes Y1 to Y7;
the fault diagnosis module uses a gradient lifting tree GBDT as a classifier and optimizes two parameters n _ estimators and learning _ rate of the GBDT by using an optimization algorithm, wherein n _ estimators represent the number of the largest weak learners, and learning _ rate represents a weight reduction coefficient of each weak learner; the optimization steps are as follows:
(1) The maximum number n _ estimators of the weak learners and the weight reduction coefficient learning _ rate of each weak learner are optimization targets; randomly initializing N particles, wherein the initial position of each particle isp i (0)=(p i1 (0), p i2 (0)), i=1,2, \8230n, settingp min1 ≤p i1 ≤p max1 ，p min2 ≤p i2 ≤p max2 At an initial speed ofv i (0)=(v i1 (0), v i2 (0)), v min1 ≤v i1 ≤v max1 ，v min2 ≤v i2 ≤v max2 Current iterationt=0, maximum iteration oft max Wherein the subscriptminAndmaxrespectively representing the minimum value and the maximum value of the corresponding variable; setting the range of N to [10,100]，p min1 =10，p max1 =10 2 ，p min2 =10 -4 ，p max2 =1，v min1 =1，v max1 =50，v min2 =10 -4 ，v max2 =0.05，t max Has a range of [10,100 ]]；
(2) The current position of each particlep i (t)=(p i1 (t), p i2 (t) To set the parameters of the GBDT classifier as the values of the parameters n _ estimators and learning _ rate; the input of the classifier is X = (X1, X2, X3, \8230;, X9), and the output is the corresponding failure sourceThus; dividing all samples with complete input and output pairs into a training set and a test set, inputting the training set into a GBDT classifier for training, and calculating the classification accuracy of the test setfit i (t) (ii) a Memory of fit worst (t)=min j∈{1,…,N} fit j (t), fit best (t)=max j∈{1,…,N} fit j (t) respectively representing the highest classification accuracy and the lowest classification accuracy in all the particles of the iteration;
(3) When t is greater than or equal to 1, iffit i (t)< fit i (t-1), then the position of the current particle is determinedp i (t) Chaotic mapping is performed according to the following formula:
wherein, p' i (t) and p' i (t) is an intermediate variable in the chaotic mapping process, p * i (t) is the position of the particle after chaotic mapping; because some particles are subjected to chaotic mapping and some particles are not subjected to chaotic mapping, for subsequent uniform representation, the chaotic mapping-performed particles are expressed by p i (t)=p * i (t)，p i (t) represents a current position of the particle; repeating the step (2), and then jumping to the step (4);
(4) Acceleration of each particlea i (t) Obtained by:
wherein the content of the first and second substances,rand j is [0,1 ]]Random number of m between i (t) represents particlesiThe absolute mass of the sensor,M i (t) Representing particlesiG (t) represents a gravitational parameter that varies with the number of iterations,
representing particlesiAnd particlesjIn conjunction with a distance of->
Representing particlesjTo particlesiThe force of (e) is a very small constant, taken as 10 -10 ，F i (t) denotes all other pairs of particlesiThe sum of the forces of (a) and (b),a i (t) Representative particleiAcceleration of (2);
(5) Velocity v of the renewed particle i And position p i ：
Wherein the content of the first and second substances,rand i is [0,1 ]]A random number in between;
(6) Number of iterationst=t+1; repeating steps (2) to (5) with the updated speed and position until satisfiedt=t max Stopping iteration; after iteration is finished, recording the positions of the particles which enable the classification accuracy of the test set to be highest, and determining the positions as the values of parameters n _ estimators and learning _ rate of the GBDT classifier; training a GBDT classifier under the parameter setting to obtain a final fault diagnosis model;
and (4) inputting data X = (X1, X2, X3, \ 8230;, X9) obtained by measuring the sensor module with unknown classification results into the final fault diagnosis model obtained in the step (6), analyzing to obtain specific fault reasons, and transmitting the results to a diagnosis result display instrument for displaying.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910015750.9A CN109635879B (en) | 2019-01-08 | 2019-01-08 | Coal mining machine fault diagnosis system with optimal parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910015750.9A CN109635879B (en) | 2019-01-08 | 2019-01-08 | Coal mining machine fault diagnosis system with optimal parameters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109635879A CN109635879A (en) | 2019-04-16 |
| CN109635879B true CN109635879B (en) | 2023-04-07 |
Family
ID=66060235
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910015750.9A Active CN109635879B (en) | 2019-01-08 | 2019-01-08 | Coal mining machine fault diagnosis system with optimal parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109635879B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110286728A (en) * | 2019-06-27 | 2019-09-27 | 联想(北京)有限公司 | Radiator monitoring method, device and electronic equipment |
| CN111191354A (en) * | 2019-12-18 | 2020-05-22 | 北京航天智造科技发展有限公司 | GBDT-based boiler modeling method and device |
| CN111553380B (en) * | 2020-03-22 | 2023-05-26 | 中润普达(十堰)大数据中心有限公司 | Auxiliary diagnosis system for automobile fault symptoms and application method thereof |
| CN111208427B (en) * | 2020-04-23 | 2020-07-24 | 湖南中车时代通信信号有限公司 | Traction motor fault diagnosis method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102536234A (en) * | 2010-12-31 | 2012-07-04 | 上海派芬自动控制技术有限公司 | Electric control system of thin-seam electric traction coal mining machine |
| CN204331743U (en) * | 2014-11-13 | 2015-05-13 | 中国矿业大学(北京) | A kind of coal-rock detection system based on image frequency domain feature extraction and Classification and Identification |
| CN108764305A (en) * | 2018-05-14 | 2018-11-06 | 浙江大学 | A kind of improved colony intelligence machine learning fault diagnosis system |
| CN108985380A (en) * | 2018-07-25 | 2018-12-11 | 西南交通大学 | A kind of goat fault recognition method based on clustering ensemble |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046279B (en) * | 2015-08-07 | 2018-05-15 | 合肥工业大学 | A kind of analog circuit fault method for classifying modes |
-
2019
- 2019-01-08 CN CN201910015750.9A patent/CN109635879B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102536234A (en) * | 2010-12-31 | 2012-07-04 | 上海派芬自动控制技术有限公司 | Electric control system of thin-seam electric traction coal mining machine |
| CN204331743U (en) * | 2014-11-13 | 2015-05-13 | 中国矿业大学(北京) | A kind of coal-rock detection system based on image frequency domain feature extraction and Classification and Identification |
| CN108764305A (en) * | 2018-05-14 | 2018-11-06 | 浙江大学 | A kind of improved colony intelligence machine learning fault diagnosis system |
| CN108985380A (en) * | 2018-07-25 | 2018-12-11 | 西南交通大学 | A kind of goat fault recognition method based on clustering ensemble |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109635879A (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109635879B (en) | Coal mining machine fault diagnosis system with optimal parameters | |
| CN109272123B (en) | Sucker-rod pump working condition early warning method based on convolution-circulation neural network | |
| CN111460728B (en) | Method and device for predicting residual life of industrial equipment, storage medium and equipment | |
| CN113723010B (en) | Bridge damage early warning method based on LSTM temperature-displacement correlation model | |
| CN106769032B (en) | A kind of prediction technique of pivoting support service life | |
| CN106053067A (en) | Bearing fault diagnosis method based on quantum genetic algorithm optimized support vector machine | |
| CN104777418B (en) | A kind of analog-circuit fault diagnosis method based on depth Boltzmann machine | |
| CN113128338B (en) | Intelligent diagnosis method for printer roller faults under small sample | |
| CN101630376A (en) | Soft-sensing modeling method and soft meter of multi-model neural network in biological fermentation process | |
| CN110110768A (en) | Fault Diagnosis of Roller Bearings based on Concurrent Feature study and multi-categorizer | |
| CN115654381A (en) | Water supply pipeline leakage detection method based on graph neural network | |
| CN113157732A (en) | Underground scraper fault diagnosis method based on PSO-BP neural network | |
| CN112664185A (en) | Indicator diagram-based rod-pumped well working condition prediction method | |
| CN112507479A (en) | Oil drilling machine health state assessment method based on manifold learning and softmax | |
| CN113408190A (en) | Bayes-LSTM model-based surrounding rock deformation prediction method during construction of highway tunnel | |
| CN116720079A (en) | Wind driven generator fault mode identification method and system based on multi-feature fusion | |
| CN115753102A (en) | Bearing fault diagnosis method based on multi-scale residual error sub-domain adaptation | |
| CN113570111B (en) | Bridge health state on-chip monitoring method based on lightweight network | |
| CN115641495A (en) | Abnormal oil pumping well detection method based on convolutional neural network | |
| CN115841580A (en) | Method for predicting residual service life of bearing based on mark distribution | |
| CN114970365A (en) | Bearing residual life prediction model based on anti-migration learning | |
| CN109826626B (en) | Intelligent coal mining machine cutting mode recognition system | |
| Zhu et al. | Full reproduction of surface dynamometer card based on periodic electric current data | |
| CN108763728B (en) | Mechanical fault diagnosis method using parallel deep neural network hierarchical feature extraction | |
| CN112418267A (en) | Motor fault diagnosis method based on multi-scale visual and deep learning |
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 |