CN109871864B - Coal mining machine cutting mode recognition system with strong robustness improved group intelligent optimization - Google Patents
Coal mining machine cutting mode recognition system with strong robustness improved group intelligent optimization Download PDFInfo
- Publication number
- CN109871864B CN109871864B CN201910015757.0A CN201910015757A CN109871864B CN 109871864 B CN109871864 B CN 109871864B CN 201910015757 A CN201910015757 A CN 201910015757A CN 109871864 B CN109871864 B CN 109871864B
- Authority
- CN
- China
- Prior art keywords
- coal mining
- mining machine
- cutting mode
- model
- module
- 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.)
- Expired - Fee Related
Links
Images
Abstract
The invention discloses a coal mining machine cutting mode identification system for strong robustness improved group intelligent optimization, which comprises a data preprocessing module, a coal mining machine cutting mode identification model modeling module, an improved optimizing module, a coal mining machine cutting mode identification module and an online correction module. The invention realizes the recognition of the cutting mode of the coal mining machine, adopts the machine learning algorithm to establish the cutting mode recognition model of the coal mining machine in the cutting mode recognition system of the coal mining machine with strong robustness improved group intelligent optimization, can correct the modeling algorithm on line, has strong robustness, can automatically optimize parameters, is not easy to fall into local optimization in the optimization process, and can realize the high-efficiency and high-accuracy recognition of the cutting mode of the coal mining machine even in complex or strange environments.
Description
Technical Field
The invention relates to the field of coal cutter cutting pattern recognition, in particular to a coal cutter cutting pattern recognition system for strong robustness improved group intelligent optimization.
Background
Modern coal mining is gradually mechanized, a coal mining machine is used as a main component of comprehensive mechanized coal mining complete equipment, the production efficiency is improved, the coal yield is increased, and major vicious accidents are reduced.
The cutting mode of the coal mining machine is mainly identified by a coal rock interface identification method at present so as to solve the problems of automatic cutting and self-adaptive control of the coal mining machine, but the current identification technology of the cutting mode of the coal mining machine has low accuracy and poor adaptability, and is difficult to meet the requirements on the accuracy, reliability and adaptability of the identification of the cutting mode of the coal mining machine. Therefore, the cutting mode recognition system with strong robustness, high accuracy and high automation level has important practical significance.
Disclosure of Invention
Aiming at the problems of poor working environment and serious safety of the coal mining machine, lower intellectualization and automation level and poor adaptability of the current coal mining machine, the invention aims to provide a cutting mode recognition system of the coal mining machine with strong robustness and improved swarm intelligence optimization.
The purpose of the invention is realized by the following technical scheme: the system comprises a data preprocessing module, a coal mining machine cutting pattern recognition model modeling module, an improved optimizing module, a coal mining machine cutting pattern recognition module and an online correction module. The system comprises an on-site data acquisition sensor, a database, a strong robust improved group intelligent optimization coal mining machine cutting mode identification system and a display module which are sequentially connected, wherein the on-site data acquisition sensor acquires information such as voltage, current and rotating speed of a motor of a coal mining machine and stores the information of the coal mining machine into the database, the database comprises historical coal mining machine data and cutting mode labels corresponding to the historical coal mining machine data, and the labels are set into 6 cutting modes according to different loads caused by coal seams and rock strata on the coal mining machine: the database provides required data for a strong robust improved group intelligent optimization coal mining machine cutting mode identification system.
Further, the data preprocessing module is used for preprocessing the data of the coal mining machine and comprises the following steps:
1) extracting a coal mining machine signal from a database, wherein the coal mining machine signal is characterized by xiD, d is a characteristic dimension, respectively representing a plurality of information collected by the sensor, the more detailed the information collection is, the more beneficial the model is to be built, but at least includingMotor voltage, current, speed;
2) the normalized feature is obtained by processing the feature as followsWherein xminIs xiMinimum value of (1), xmaxIs xiMaximum value of (d):
further, the modeling module of the cutting pattern recognition model of the coal mining machine is used for establishing the cutting pattern recognition model of the coal mining machine, and the following processes are adopted to complete the modeling:
1) extracting n from a databasesData X of coal mining machinesAnd corresponding cutting mode label YsAs a training set, n is extractedvData X of coal mining machinevAnd corresponding cutting mode label YvAs a test set;
2) initializing RF algorithm parameters, wherein the maximum random characteristic number M is d, the number of subsamples, namely the number N of the sub decision trees is 100, and performing RF model training by adopting the training set obtained above to obtain a coal mining machine cutting mode identification model:
Y=h(X) (12)
further, the improved optimization module adopts a novel chaos modified particle swarm algorithm to optimize the RF parameter M, N. The method is completed by adopting the following steps:
1) randomly generating the speed and position of the 1 st generation initial particles, namely the initial solution;
vjk(1)=U×(vmax-vmin)+vmin vmin≤v≤vmax (13)
rjk(1)=U×(rmax-rmin)+rmin rmin≤r≤rmax (14)
where j 1, 2, m, m 100 is the group size, k 1, 2 each correspond to a parameter M, N, v to be optimizedjk(1) And rjk(1) Respectively representing the velocity and position of the kth component of the jth particle in the 1 st generation, U being [0, 1 ]]Uniformly distributed random numbers.
2) Calculating the fitness f of the jth particlej:
WhereinRespectively representing the true value and the calculated value, namely the predicted value.
3) Update inertia weight coefficient μ (t):
wherein mumax0.9 is the upper limit value of μminLower limit value of μ, t 0.2max150 is the maximum number of iterations.
4) Updating the speed and position of the particles to generate new groups;
wherein the content of the first and second substances,andis [0, 1 ]]A random number in between; pj best、GbestRespectively, the historical optimal solution of the jth particle and the optimal solution of the entire cluster.
5) Judging whether the global optimal solution is unchanged or reaches the maximum iteration number t for five continuous iterationsmax150. If so, outputting the global optimal particles and the optimal solution represented by the global optimal particles, and ending the iteration. Otherwise proceed toAnd (5) one step.
6) Determining whether the evolution of the particle has stagnated to avoid precocity according to:
wherein, delta2Is the group fitness variance, H2Is the early-maturing threshold value of the plant,is the average of all particle fitness.
If the condition is not met, directly returning to 2) to continue executing; otherwise, the first 20% of the optimal fitness in the current generation is reserved, and the rest 80% of particles are reconstructed according to the chaos thought and then continue:
wherein r ismin、rmaxRepresenting the minimum and maximum values of r, respectively.
7) And repeating the steps, substituting the obtained optimal parameters into a modeling module of the cutting mode recognition model of the coal mining machine, testing the model on a test set, and selecting the model with the highest accuracy as the optimal model.
Further, the coal mining machine cutting pattern recognition module performs real-time cutting pattern recognition on newly acquired coal mining machine data by using the trained optimal coal mining machine cutting pattern recognition model. The method is completed by adopting the following steps:
1) for newly acquired coal mining machine data xnewIs subjected to normalization processing to obtain
2) Carrying out cutting mode recognition on the coal mining machine data by using the optimized optimal recognition model of the improved optimizing module:
wherein h isoptIn order to optimize the optimal model after the optimization,is the identified cutting pattern.
Further, the online correction module corrects the model in real time. Because the current model only contains data covered in the training set and the working environment of the coal mining machine is complex, if the newly acquired data is greatly deviated from the data in the database, the identification accuracy of the model on the data is reduced, namely the model is mismatched, and therefore in order to improve the robustness of the model and the adaptability to the new environment, a model correction module is introduced, so that the identification accuracy of the cutting mode of the coal mining machine is further improved, and finally the cutting mode identification model of the coal mining machine with strong robustness and improved swarm intelligence optimization is obtained. The online correction strategy is completed by adopting the following processes:
1) the real value of the cutting mode of the coal mining machine identified by the coal mining machine data acquired at the moment tau can be obtained at the future moment tau + n, so that the accuracy of model identification can be judged. Adding the coal mining machine data with the recognition error into a training set as singular sample points;
2) and the improved optimizing module is used for optimizing the RF parameters on line again to obtain a new optimal coal cutter cutting mode identification model so as to solve the problem of model mismatch in a complex or strange environment and further improve the accuracy of model identification.
Further, the display module outputs and displays the cutting mode obtained by the cutting mode identification module of the coal mining machine through a display screen.
The technical conception of the invention is as follows: the invention uses the machine learning algorithm to establish the cutting mode recognition model of the coal mining machine from the cutting mode database of the coal mining machine, carries out cutting mode recognition on the coal mining machine data collected in real time, introduces an improved parameter optimization method to obtain better optimization effect, and simultaneously carries out online correction on the model to improve the adaptability, thereby establishing the strong robust improved group intelligent optimization coal mining machine cutting mode recognition system.
The invention has the following beneficial effects: 1. a machine learning algorithm is used for establishing a cutting mode identification model of the coal mining machine, and collected data of the coal mining machine can be processed in real time so as to automatically identify the current cutting mode of the coal mining machine; 2. the parameters are automatically optimized through an improved particle optimization algorithm, the optimization effect is good, and the identification accuracy is high; 3. the method has the advantages that the model is corrected on line in real time, so that the recognition model can be automatically adapted in complex and strange environments, the model is strong in robustness and high in adaptability, and meanwhile, the accuracy of cutting mode recognition is improved.
Drawings
FIG. 1 is a hardware connection diagram of a robust enhanced group intelligence optimized shearer cutting pattern recognition system;
FIG. 2 is a functional block diagram of a robust enhanced group intelligence optimized shearer cutting pattern recognition system;
FIG. 3 is a flow chart of a group intelligent optimization algorithm using chaos thought modification;
FIG. 4 is a flow chart of an online correction strategy.
Detailed Description
The invention is further illustrated below with reference to the figures and examples:
referring to fig. 1 and 2, an on-site data acquisition sensor 1, a database 2, a strong robust improved group intelligent optimized coal mining machine cutting mode identification system 3 and a display module 4 are connected in sequence, wherein the strong robust improved group intelligent optimized coal mining machine cutting mode identification system 3 comprises a data preprocessing module 5, a coal mining machine cutting mode identification model modeling module 6, a coal mining machine cutting mode identification module 7, an improved optimizing module 8 and an online correction module 9. The field data acquisition sensor 1 acquires the voltage, current and rotating speed information of a motor of the coal mining machine, and stores the information of the coal mining machine into the database 2, the database 2 comprises historical coal mining machine data and cutting mode labels corresponding to the historical coal mining machine data, and the labels are set into 6 cutting modes according to the difference of loads caused by coal seams and rock strata on the coal mining machine: the database 2 provides required data for the coal mining machine cutting mode identification system 3 with strong robustness improved group intelligent optimization.
The data preprocessing module 5 is used for preprocessing the data of the coal mining machine and is completed by adopting the following processes:
1) extracting a shearer signal from the database 2, which is characterized by xiD, d is a characteristic dimension which respectively represents a plurality of kinds of information collected by the sensor, and the more detailed information collection is more beneficial to model establishment, but at least comprises motor voltage, current and rotating speed;
2) the normalized feature is obtained by processing the feature as followsWherein xminIs xiMinimum value of (1), xmaxIs xiMaximum value of (d):
the modeling module 6 of the cutting pattern recognition model of the coal mining machine is used for establishing the cutting pattern recognition model of the coal mining machine and comprises the following steps:
1) extracting n from database 2sData X of coal mining machinesAnd corresponding cutting mode label YsAs a training set, n is extractedvData X of coal mining machinevAnd corresponding cutting mode label YvAs a test set;
2) initializing RF algorithm parameters, wherein the maximum random characteristic number M is d, the number of subsamples, namely the number N of the sub decision trees is 100, and performing RF model training by adopting the training set obtained above to obtain a coal mining machine cutting mode identification model:
Y=h(X) (22)
the improved optimization module 8 adopts a novel chaos modified particle swarm algorithm to optimize the RF parameter M, N. The optimization algorithm flow is shown in fig. 3, and the specific steps are as follows:
1) randomly generating the speed and position of the 1 st generation initial particles, namely the initial solution;
vjk(1)=U×(vmax-vmin)+vmin vmin≤v≤vmax (23)
rjk(1)=U×(rmax-rmin)+rmin rmin≤r≤rmax (24)
where j 1, 2, m, m 100 is the group size, k 1, 2 each correspond to a parameter M, N, v to be optimizedjk(1) And rjk(1) Respectively representing the velocity and position of the kth component of the jth particle in the 1 st generation, U being [0, 1 ]]Uniformly distributed random numbers.
2) Calculating the fitness f of the jth particlej:
WhereinRespectively representing the true value and the calculated value, namely the predicted value.
3) Update inertia weight coefficient μ (t):
wherein mumax0.9 is the upper limit value of μminLower limit value of μ, t 0.2max150 is the maximum number of iterations.
4) Updating the speed and position of the particles to generate new groups;
wherein the content of the first and second substances,andis [0, 1 ]]A random number in between; pj best、GbestRespectively, the historical optimal solution of the jth particle and the optimal solution of the entire cluster.
5) Judging whether the global optimal solution is unchanged or reaches the maximum iteration number t for five continuous iterationsmax150. If so, outputting the global optimal particles and the optimal solution represented by the global optimal particles, and ending the iteration. Otherwise, the next step is carried out.
6) Determining whether the evolution of the particle has stagnated to avoid precocity according to:
wherein, delta2Is the group fitness variance, H2Is the early-maturing threshold value of the plant,is the average of all particle fitness.
If the condition is not met, directly returning to 2) to continue executing; otherwise, the first 20% of the optimal fitness in the current generation is reserved, and the rest 80% of particles are reconstructed according to the chaos thought and then continue:
wherein r ismin、rmaxRepresenting the minimum and maximum values of r, respectively.
7) And repeating the steps, substituting the obtained optimal parameters into the modeling module 6 of the cutting pattern recognition model of the coal mining machine, testing the model on a test set, and selecting the model with the highest accuracy as the optimal model.
Further, the coal mining machine cutting pattern recognition module 7 performs real-time cutting pattern recognition on the newly acquired coal mining machine data by using the trained optimal coal mining machine cutting pattern recognition model. The method is completed by adopting the following steps:
1) for newly acquired coal mining machine data xnewIs subjected to normalization processing to obtain
2) And (3) carrying out cutting mode recognition on the coal mining machine data by using the optimized optimal recognition model of the improved optimizing module 8:
The online modification module 9 performs real-time modification on the model. Because the current model only contains data covered in the training set and the working environment of the coal mining machine is complex, if the newly acquired data is greatly deviated from the data in the database 2, the identification accuracy of the model on the data is reduced, namely the model is mismatched, and therefore in order to improve the robustness of the model and the adaptability to the new environment, a model correction module is introduced, so that the identification accuracy of the cutting mode of the coal mining machine is further improved, and finally the cutting mode identification model of the coal mining machine with strong robustness and improved swarm intelligence optimization is obtained. The flow of the online correction strategy is shown in fig. 4, and is completed by adopting the following processes:
1) the real value of the cutting mode of the coal mining machine identified by the coal mining machine data acquired at the moment tau can be obtained at the future moment tau + n, so that the accuracy of model identification can be judged. Adding the coal mining machine data with the recognition error into a training set as singular sample points;
2) and the improved optimizing module 8 is utilized to optimize the RF parameters on line again to obtain a new optimal coal cutter cutting mode identification model so as to solve the problem of model mismatch in a complex or strange environment and further improve the accuracy of model identification.
The display module 4 outputs and displays the cutting mode obtained by the coal mining machine cutting mode recognition module 7 through a display screen.
The above-described embodiments are intended to illustrate rather than to limit the invention, and any modifications and variations of the present invention are within the spirit of the invention and the scope of the appended claims.
Claims (1)
1. The coal mining machine cutting mode recognition system with the strong robustness improved group intelligent optimization is characterized in that: the system comprises a data preprocessing module, a modeling module of a cutting mode identification model of a coal mining machine, an improved optimizing module, a cutting mode identification module of the coal mining machine and an online correction module;
the data preprocessing module is used for preprocessing the data of the coal mining machine and is completed by adopting the following processes:
(1.1) extracting a shearer signal from the database, which is characterized by xiD, d is a characteristic dimension;
(1.2) obtaining normalized characteristics by subjecting the characteristics to the following processingWherein xminIs xiMinimum value of (1), xmaxIs xiMaximum value of (d):
the modeling module of the cutting mode identification model of the coal mining machine is used for establishing the cutting mode identification model of the coal mining machine and comprises the following steps:
(2.1) extracting n from the databasesData X of coal mining machinesAnd corresponding cutting mode label YsAs a training set, n is extractedvData X of coal mining machinevAnd corresponding cutting mode label YvAs a test set;
(2.2) initializing random forest algorithm parameters, wherein the maximum random feature number M is d, the number of subsamples, namely the number N of the sub decision trees is 100, and performing random forest model training by using the training set obtained above to obtain a cutting mode recognition model of the coal mining machine:
Y=h(X); (2)
the improved optimizing module adopts a novel chaotically modified particle swarm algorithm to optimize random forest algorithm parameters M, N; the method is completed by adopting the following steps:
(3.1) randomly generating the speed and the position of the 1 st generation of initial particles, namely the initial solution;
vjk(1)=U×(vmax-vmin)+vmin vmin≤v≤vmax (3)
rjk(1)=U×(rmax-rmin)+rmin rmin≤r≤rmax (4)
where j 1, 2, m, m 100 is the group size, k 1, 2 each correspond to a parameter M, N, v to be optimizedjk(1) And rjk(1) Respectively representing the velocity and position of the kth component of the jth particle in the 1 st generation, U being [0, 1 ]]Random numbers uniformly distributed among them;
(3.2) calculating the fitness f of the jth particlej:
(3.3) update inertia weight coefficient μ (t):
wherein mumax0.9 is the upper limit value of μminLower limit value of μ, t 0.2max150 is the maximum number of iterations;
(3.4) updating the speed and position of the particles to generate new populations;
wherein the content of the first and second substances,andis [0, 1 ]]A random number in between; pj best、GbestRespectively obtaining the historical optimal solution of the jth particle and the optimal solution of the whole group;
(3.5) judging whether the global optimal solution is unchanged or reaches the maximum iteration time t after five times of continuous iterationsmax150; if the global optimal particles are consistent with the optimal solution represented by the global optimal particles, outputting the global optimal particles and the optimal solution represented by the global optimal particles, and ending iteration; otherwise, carrying out the next step;
(3.6) determining whether the evolution of the particles has stagnated to avoid precocity according to:
wherein, delta2Is the group fitness variance, H2Is the early-maturing threshold value of the plant,is the average value of all particle fitness; if the condition is not met, directly returning to 0 to continue executing; otherwise, the first 20% of the optimal fitness in the current generation is reserved, and the rest 80% of particles are reconstructed according to the chaos thought and then continue:
wherein r ismin、rmaxRespectively represent the minimum value and the maximum value of r;
(3.7) repeating the steps, substituting the obtained optimal parameters into a modeling module of a cutting pattern recognition model of the coal mining machine, testing the model on a test set, and selecting the model with the highest accuracy as the optimal model;
the coal mining machine cutting mode recognition module carries out real-time cutting mode recognition on newly acquired coal mining machine data by using a trained optimal coal mining machine cutting mode recognition model; the method is completed by adopting the following steps:
And (4.2) carrying out cutting mode recognition on the coal mining machine data by using the optimized optimal recognition model of the improved optimizing module:
hoptin order to optimize the optimal model after the optimization,is the identified cutting pattern;
the online correction module corrects the model in real time; because the current model only contains data covered in the training set and the working environment of the coal mining machine is complex, if the newly acquired data is greatly deviated from the data in the database, the identification accuracy of the model on the data is reduced, namely the model is mismatched, and therefore, in order to improve the robustness of the model and the adaptability to the new environment, a model correction module is introduced, so that the identification accuracy of the cutting mode of the coal mining machine is further improved, and finally the cutting mode identification model of the coal mining machine with strong robustness and improved swarm intelligence optimization is obtained; the online correction strategy is completed by adopting the following processes:
(5.1) identifying the cutting mode of the coal mining machine by the coal mining machine data acquired at the moment tau, wherein the true value of the cutting mode can be obtained at the future tau + n moment, so that the accuracy of model identification can be judged; adding the coal mining machine data with the recognition error into a training set as singular sample points;
and (5.2) optimizing the random forest algorithm parameters online again by using the improved optimization searching module to obtain a new optimal coal mining machine cutting mode identification model so as to solve the problem of model mismatch in a complex or strange environment and further improve the accuracy of model identification.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910015757.0A CN109871864B (en) | 2019-01-08 | 2019-01-08 | Coal mining machine cutting mode recognition system with strong robustness improved group intelligent optimization |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910015757.0A CN109871864B (en) | 2019-01-08 | 2019-01-08 | Coal mining machine cutting mode recognition system with strong robustness improved group intelligent optimization |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109871864A CN109871864A (en) | 2019-06-11 |
CN109871864B true CN109871864B (en) | 2021-04-09 |
Family
ID=66917423
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910015757.0A Expired - Fee Related CN109871864B (en) | 2019-01-08 | 2019-01-08 | Coal mining machine cutting mode recognition system with strong robustness improved group intelligent optimization |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109871864B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110988803A (en) * | 2019-11-11 | 2020-04-10 | 浙江大学 | Radar radiation source individual identification system with high confidence degree dynamic adjustment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4981327A (en) * | 1989-06-09 | 1991-01-01 | Consolidation Coal Company | Method and apparatus for sensing coal-rock interface |
CN104695953A (en) * | 2015-02-15 | 2015-06-10 | 山东科技大学 | Coal cutter realizing automatic height adjustment of barrel and working method of coal cutter |
CN204436379U (en) * | 2015-02-15 | 2015-07-01 | 山东科技大学 | A kind of coal-winning machine realizing horizon control |
CN106198000A (en) * | 2016-07-11 | 2016-12-07 | 太原理工大学 | A kind of rocker arm of coal mining machine gear failure diagnosing method |
CN107013211A (en) * | 2017-06-06 | 2017-08-04 | 太原科技大学 | A kind of control method of coal mining machine roller automatic adjustment height |
CN107849919A (en) * | 2015-06-15 | 2018-03-27 | 乔伊·姆·特拉华公司 | System and method for monitoring longwell mine roof stability |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9103209B2 (en) * | 2014-03-25 | 2015-08-11 | Caterpillar Global Mining Llc | System for controlling speed of travel in a longwall shearer |
-
2019
- 2019-01-08 CN CN201910015757.0A patent/CN109871864B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4981327A (en) * | 1989-06-09 | 1991-01-01 | Consolidation Coal Company | Method and apparatus for sensing coal-rock interface |
CN104695953A (en) * | 2015-02-15 | 2015-06-10 | 山东科技大学 | Coal cutter realizing automatic height adjustment of barrel and working method of coal cutter |
CN204436379U (en) * | 2015-02-15 | 2015-07-01 | 山东科技大学 | A kind of coal-winning machine realizing horizon control |
CN107849919A (en) * | 2015-06-15 | 2018-03-27 | 乔伊·姆·特拉华公司 | System and method for monitoring longwell mine roof stability |
CN106198000A (en) * | 2016-07-11 | 2016-12-07 | 太原理工大学 | A kind of rocker arm of coal mining machine gear failure diagnosing method |
CN107013211A (en) * | 2017-06-06 | 2017-08-04 | 太原科技大学 | A kind of control method of coal mining machine roller automatic adjustment height |
Non-Patent Citations (1)
Title |
---|
采煤机摇臂振动信号分析及其截割模式识别方法研究;刘泽;《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》;20180315;第42-62页 * |
Also Published As
Publication number | Publication date |
---|---|
CN109871864A (en) | 2019-06-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109272123B (en) | Sucker-rod pump working condition early warning method based on convolution-circulation neural network | |
CN111680820B (en) | Distributed photovoltaic power station fault diagnosis method and device | |
CN110969194B (en) | Cable early fault positioning method based on improved convolutional neural network | |
CN112462736B (en) | Wind turbine generator fault diagnosis method based on data analysis | |
CN112183993B (en) | TBM (tunnel boring machine) tunneling control parameter intelligent prediction and optimization decision method | |
CN105652845A (en) | Fermentation process fault monitoring method based on just-in-time learning local model | |
CN109871864B (en) | Coal mining machine cutting mode recognition system with strong robustness improved group intelligent optimization | |
CN111507155A (en) | U-Net + + and UDA combined microseism effective signal first-arrival pickup method and device | |
CN115408925A (en) | Rock mass parameter prediction method and device for tunnel construction | |
CN115329853A (en) | Equipment parameter prediction and knowledge transfer method based on multi-source domain migration | |
CN108564601B (en) | Fruit identification tracking method and system based on deep learning algorithm | |
CN113569966B (en) | Coal-rock interface proportion identification and classification method based on GAF-deep learning | |
CN114839492A (en) | Method and device for identifying GIS partial discharge type based on MOBILE NETV3 | |
CN113255690B (en) | Composite insulator hydrophobicity detection method based on lightweight convolutional neural network | |
CN109886421B (en) | Swarm intelligence coal-winning machine cutting pattern recognition system based on ensemble learning | |
CN116012275A (en) | Downhole real-time processing device and method for while-drilling electric imaging data | |
CN112732541A (en) | Intelligent criterion mining system for fault diagnosis of complex equipment | |
CN115795369B (en) | Coal-rock interface identification method and device | |
CN111273352A (en) | Intelligent detection method and device for geological structure and electronic equipment | |
CN116560341A (en) | Industrial robot fault diagnosis model and fault diagnosis method | |
CN109657404B (en) | Automatic fault diagnosis system for coal mining machine based on chaos correction group intelligent optimization | |
CN109886420B (en) | Self-adaptive intelligent prediction system for cutting height of coal mining machine | |
CN109635880B (en) | Coal mining machine fault diagnosis system based on robust self-adaptive algorithm | |
CN114372640A (en) | Wind power prediction method based on fluctuation sequence classification correction | |
CN109902830B (en) | Coal mining machine cutting height prediction system based on chaos theory and integrated 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 | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210409 Termination date: 20220108 |