CN116226751B - A method, device and related components for intelligent assessment of health status of coal mining machine - Google Patents
A method, device and related components for intelligent assessment of health status of coal mining machine Download PDFInfo
- Publication number
- CN116226751B CN116226751B CN202310087191.9A CN202310087191A CN116226751B CN 116226751 B CN116226751 B CN 116226751B CN 202310087191 A CN202310087191 A CN 202310087191A CN 116226751 B CN116226751 B CN 116226751B
- Authority
- CN
- China
- Prior art keywords
- monitoring data
- mining machine
- coal mining
- time period
- health
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/048—Fuzzy inferencing
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21C—MINING OR QUARRYING
- E21C39/00—Devices for testing in situ the hardness or other properties of minerals, e.g. for giving information as to the selection of suitable mining tools
-
- 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
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Automation & Control Theory (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent assessment method and device for the health state of a coal mining machine and related components. The method comprises the steps of obtaining monitoring data of each target position of the coal mining machine in a plurality of adjacent time periods, carrying out dynamic cluster analysis on all the monitoring data corresponding to each time period by using a K-means algorithm, removing similar monitoring data based on a clustering result obtained by the dynamic cluster analysis, classifying the monitoring data with the similar monitoring data removed by using a pre-trained two-way long-short-term memory network model, outputting classification results, carrying out fuzzy comprehensive evaluation on all the classification results based on a preset coal mining machine health state evaluation rule, and calculating the coal mining machine health score of the current time period. The method is based on monitoring data of the coal mining machine in a continuous time period, and improves the rationality and accuracy of the health score of the coal mining machine in the current time period through bidirectional long-short period network model classification and fuzzy comprehensive evaluation.
Description
Technical Field
The invention relates to the technical field of equipment maintenance, in particular to an intelligent assessment method and device for the health state of a coal mining machine and related components.
Background
Along with the development of technologies such as big data, artificial intelligence and the like, the coal industry gradually advances into an intelligent era, wherein the coal intelligent equipment serving as an intelligent core of a coal mine needs to have good adaptability and reliability so as to improve the development efficiency and the intelligent level of the coal, and the evaluation, prediction and maintenance of the health state of the fully-mechanized coal mining equipment are guarantees of the intelligent development of the coal mine.
Under the actual application scene, the coal mining machine integrates the electromechanical liquid ring joint into a whole, takes on two tasks of coal cutting and coal loading, runs on a working surface with complex geological conditions and severe environment for a long time, accurately evaluates the health state of the working surface, and can provide basis for the maintenance of the coal mining machine so as to ensure the normal operation of equipment.
At present, the existing coal mining machine health state assessment method only focuses on the health state of the coal mining machine in the current period, namely, the health state of the coal mining machine is judged based on the health state monitoring data in the current period, so that the reliability of an assessment result is low.
Disclosure of Invention
The invention aims to provide an intelligent assessment method and device for the health state of a coal mining machine and related components, and aims to solve the problem that the accuracy degree of the existing assessment for the health state of the coal mining machine is low.
In order to solve the technical problems, the invention aims at providing an intelligent assessment method for the health state of a coal mining machine, which comprises the following steps:
Acquiring monitoring data of each target position of the coal mining machine in a plurality of adjacent time periods;
Performing dynamic cluster analysis on all the monitoring data corresponding to each time period by using a K-means algorithm, and removing similar monitoring data based on a clustering result obtained by the dynamic cluster analysis;
classifying the monitoring data after similar monitoring data are removed by utilizing a pre-trained two-way long-short-term memory network model, and outputting a classification result;
And carrying out fuzzy comprehensive evaluation by using all the classification results based on a preset coal cutter health state evaluation rule, and calculating the coal cutter health score in the current time period.
According to the technical scheme, firstly, monitoring data of a plurality of continuous time periods of the coal mining machine are collected, redundant data in all the monitoring data are removed, interference of similar monitoring data on health state assessment results is reduced, efficiency of health scoring result output is improved, monitoring data of all target positions in all the time periods are classified through a two-way long-short-period memory network model, probability of health state classification of each monitoring data is obtained, fuzzy comprehensive evaluation is finally carried out by the probability of health state classification, and health scoring of the coal mining machine is calculated.
Further, the dynamic cluster analysis is performed on all the monitoring data corresponding to each time period by using a K-means algorithm, including:
storing all the monitoring data in each time period in a data set in a state matrix mode, wherein the monitoring data of different target positions are located in different rows of the state matrix;
normalizing the state matrix according to the following formula:
Wherein s i represents the monitoring data after the normalization of the ith row, and x i represents the monitoring data of the ith row;
setting n initial clustering centers based on the normalized state matrix, and taking each row of monitoring data s of the state matrix as a sample respectively;
Carrying out iterative computation on the initial cluster center and a sample s, wherein if the following conditions are satisfied that I s-z j(m)||＜||s-zi (m) I, (i, j=1, 2,.., n and i not equal to j), s E f j (m), wherein z i (m) represents an ith cluster center in the m-th iteration, and f j (m) represents a cluster domain of the jth cluster center in the m-th iteration;
The new cluster center is calculated as:
Wherein N i is the number of samples in the i-th cluster domain f i (m);
After meeting the condition of z i(m+1)＝zi (m), all samples are clustered into n classes.
Through the technical scheme, all the monitoring data are clustered.
Further, the removing similar monitoring data based on the clustering result obtained by the dynamic clustering analysis includes:
the distance d (x, c) of each sample to the cluster center to which it belongs is calculated as follows:
d(x,c)=(x-c)[(x-c)]T;
The centroid c is the average value of all samples in the cluster domain;
And traversing all corresponding samples for each target clustering center, reserving the sample corresponding to the smallest d (x, c), taking the original monitoring data corresponding to the sample as target monitoring data, and deleting the original monitoring data corresponding to the rest samples.
Through the technical scheme, the similar monitoring data are removed, so that interference of the similar monitoring data on the health score is reduced, and meanwhile, the calculation efficiency of the health score is improved.
Further, the classifying the monitoring data after removing the similar monitoring data by using the pre-trained two-way long-short-term memory network model, and outputting a classification result, including:
and inputting the state matrix with the similar monitoring data removed into a sequence input layer in a pre-trained bidirectional long-short-term network model, sequentially passing through a first BiLSTM layer, a first discarding layer, a second BiLSTM layer, a second discarding layer, a full connection layer, a softmax function activation layer and a classification layer, and outputting a classification result vector.
Through the technical scheme, the two-way long-short-term memory network model is utilized to classify the rest monitoring data, and the corresponding health state classification probability is obtained.
Further, the classifying the monitoring data after removing the similar monitoring data by using the pre-trained two-way long-short-term memory network model, and before outputting the classification result, includes:
And optimizing target super parameters in the bidirectional long-short-term network model by using a particle swarm algorithm, wherein the target super parameters comprise the number of hidden units of a first BiLSTM layer, the discarding rate of a first discarding layer, the number of hidden units of a second BiLSTM layer, the discarding rate of a second discarding layer, an initial learning rate, a maximum iteration number and a small batch size.
According to the technical scheme, the super parameters of the bidirectional long-short-term network model are optimized by using the particle swarm algorithm, so that the classification accuracy of the bidirectional long-short-term network model is improved.
Further, the optimizing the target superparameter in the bidirectional long-short-term network model by using a particle swarm algorithm includes:
initializing the speed and the position of each particle in the population based on the value range [ h min,hmax ] of the target super-parameter, wherein the initial value is calculated according to the following formula:
h=rand*(hmax-hmin)+hmin;
The initial individual optimal position p best of the particles is taken as the fitness of the first particle in the particle group, wherein the fitness of the particles is calculated according to the following formula:
Wherein Y pred is the label of the BiLSTM network model classification and Y test is the label of the test set;
setting the global optimum position g best of the particle to min (p best);
Based on a preset updating rule, updating the position and speed of the particle, comparing the updated fitness of the particle with the fitness of the optimal position p best of the individual historical particle, and selecting the position corresponding to the smaller fitness as p best of the particle;
And continuously iterating until the maximum iteration step number t max of the particle swarm is reached, and taking the result obtained by optimizing as the corresponding value of the target super-parameter.
Further, the preset rule for evaluating the health state of the coal mining machine includes:
Determining monitoring data collected by the coal mining machine in each time period as a judgment factor, and obtaining a time period domain U based on all the judgment factors:
Dividing all the time period domains into q subsets according to time sequence, as follows:
Setting comment grade domains of each grade of the health condition of the coal mining machine as follows:
X= { State 1, state 2, state 3, state 4, state 5}
And carrying out fuzzy comprehensive evaluation by using all the classification results, and calculating the health score of the coal mining machine in the current time period, wherein the fuzzy comprehensive evaluation comprises the following steps:
Combining the classification result vectors corresponding to different time periods according to the time sequence to establish a fuzzy relation matrix;
Based on the time period domain and the comment level domain, an evaluation matrix R is obtained from the fuzzy relation matrix according to the following formula:
The first-order evaluation weight allocation vector a median (q) is set as follows:
The first-order evaluation weight allocation vector a res is set as follows:
Each element B in the first-order evaluation vector B is calculated as follows:
wherein a is an element in a first-level evaluation weight distribution vector, and R is an element in an evaluation matrix R;
The first order evaluation vector B is calculated as follows:
Wherein, Representing blurring operatorsA median (q) appears only in the calculation of B median (q), and the rest first-level evaluation vectors are calculated by a res;
calculating a single factor judgment matrix T of a time period domain U according to the following steps:
setting a secondary evaluation weight allocation vector as follows
The second-order evaluation vector is calculated as follows
The score vector S of each health state of the coal mining machine is calculated according to the following steps:
S=(0,25,50,75,100);
the health score of the shearer was calculated as follows:
in addition, the technical problem to be solved by the invention is to provide an intelligent assessment device for the health state of the coal mining machine, which comprises:
The acquisition unit is used for acquiring monitoring data of each target position of the coal mining machine in a plurality of adjacent time periods;
the removing unit is used for carrying out dynamic cluster analysis on all the monitoring data corresponding to each time period by using a K-means algorithm, and removing similar monitoring data based on a clustering result obtained by the dynamic cluster analysis;
The classification unit is used for classifying the monitoring data after the similar monitoring data are removed by utilizing a pre-trained two-way long-short-term memory network model to obtain a classification result;
and the scoring unit is used for carrying out fuzzy comprehensive evaluation by using all the classification results based on a preset coal cutter health state evaluation rule, and calculating the coal cutter health score in the current time period.
According to the technical scheme, firstly, monitoring data of a plurality of continuous time periods of the coal mining machine are collected, redundant data in all the monitoring data are removed, interference of similar monitoring data on health state assessment results is reduced, efficiency of health scoring result output is improved, monitoring data of all target positions in all the time periods are classified through a two-way long-short-period memory network model, probability of health state classification of each monitoring data is obtained, fuzzy comprehensive evaluation is finally carried out by the probability of health state classification, and health scoring of the coal mining machine is calculated.
In addition, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the intelligent assessment method for health status of a coal mining machine according to the first aspect when executing the computer program.
In addition, an embodiment of the present invention further provides a computer readable storage medium, where the computer readable storage medium stores a computer program, where the computer program when executed by a processor causes the processor to execute the intelligent assessment method for health status of a coal mining machine according to the first aspect.
The embodiment of the invention discloses an intelligent assessment method, device and related components for the health state of a coal cutter, wherein the method comprises the steps of obtaining monitoring data of each target position of the coal cutter in a plurality of adjacent time periods, carrying out dynamic cluster analysis on all the corresponding monitoring data in each time period by using a K-means algorithm, removing similar monitoring data based on a clustering result obtained by the dynamic cluster analysis, classifying the monitoring data with the similar monitoring data removed by using a pre-trained bidirectional long-short-term memory network model, outputting classification results, carrying out fuzzy comprehensive assessment on the basis of a preset coal cutter health state assessment rule by using all the classification results, and calculating the health score of the coal cutter in the current time period. The method is based on monitoring data of the coal mining machine in a continuous time period, and improves the rationality and accuracy of the health score of the coal mining machine in the current time period through bidirectional long-short period network model classification and fuzzy comprehensive evaluation.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an intelligent assessment method for the health status of a coal mining machine according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a two-way long-short-term memory network model in the intelligent assessment method for the health status of the coal mining machine according to the embodiment of the invention;
FIG. 3 is a schematic block diagram of an intelligent assessment device for the health status of a coal mining machine, which is provided by an embodiment of the invention;
fig. 4 is a schematic block diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Referring to fig. 1, fig. 1 is a flow chart of an intelligent assessment method for health status of a coal mining machine according to an embodiment of the invention, and as shown in fig. 1, the method includes steps S101 to S104.
S101, acquiring monitoring data of each target position of the coal mining machine in a plurality of adjacent time periods;
s102, performing dynamic cluster analysis on all the monitoring data corresponding to each time period by using a K-means algorithm, and removing similar monitoring data based on a clustering result obtained by the dynamic cluster analysis;
S103, classifying the monitoring data with the similar monitoring data removed by using a pre-trained two-way long-short-term memory network model, and outputting a classification result;
S104, based on a preset coal cutter health state evaluation rule, performing fuzzy comprehensive evaluation by using all the classification results, and calculating the coal cutter health score in the current time period.
In the embodiment, the existing health state evaluation method of the coal mining machine evaluates the health state of the current time zone of the coal mining machine only by collecting monitoring information of the current time zone of the coal mining machine, the method does not fully consider the characteristic that the health state change process of the coal mining machine has continuity in multiple time zones, namely the influence of the information of the multiple time zones on health scoring is ignored, so that the application collects monitoring data of the coal mining machine in each target position in the adjacent multiple time zones, utilizes a K-means algorithm to remove similar monitoring data in all collected monitoring data, reduces interference caused by a large number of similar monitoring data on the health scoring, improves scoring efficiency to a certain extent, reduces operation time, classifies the monitoring data after the similar monitoring data are removed by utilizing a pre-trained two-way long-short-term memory network model, obtains classification results, and finally carries out fuzzy comprehensive evaluation by using the classification results based on preset health state evaluation rules of the coal mining machine, and obtains the health scoring of the current time zone of the coal mining machine.
According to the assessment method, the influence of the running states of the coal mining machine in different periods on the health state of the coal mining machine is considered, the final score of the assessment is quantized, and the assessment result, namely the final health score, is more reasonable.
It should be appreciated that the shearer may acquire the above-described monitoring data via sensors or other monitoring devices, and the application will not be described in detail. In particular, the monitoring data of the present application includes, but is not limited to, traction motor temperature data, traction motor current data, traction motor vibration data, cutting motor temperature data, cutting motor current data, cutting motor vibration data, raise pump motor temperature data, raise pump motor current data, raise pump operating pressure data, crushing motor current data, crushing motor temperature data. In other words, each target location of the shearer includes, but is not limited to, a traction motor, a cutting motor, a hoist pump motor, a crushing motor.
In step S101, the monitoring data of each part of the coal mining machine is collected within one minute at a sampling frequency of 100Hz, in other words, each time period is 1 minute, and 6000 sampling point data (monitoring data) generated within one minute of each part of the coal mining machine can be collected, but in the actual evaluation process, the duration and sampling frequency of each time period can be other values, and the application is not limited.
In a specific embodiment, the "dynamic cluster analysis on all the monitoring data corresponding to each of the time periods by using a K-means algorithm" in the step S102 includes the following steps:
s10, storing all the corresponding monitoring data in each time period in a data set in a state matrix mode, wherein the monitoring data of different target positions are located in different rows of the state matrix;
In this embodiment, for example, all traction motor temperature data (6000) collected in the current time period (for example, within one minute) are arranged in the first row of the state matrix according to the collected time sequence, then all traction motor current data collected in the current time period are arranged in the second row of the state matrix according to the collected time sequence, and the like, so as to obtain the state matrix of the current time period, wherein each time period corresponds to one state matrix.
S11, normalizing the state matrix according to the following formula:
Wherein s i represents the monitoring data after the normalization of the ith row, and x i represents the monitoring data of the ith row;
In this embodiment, by performing normalization processing on the state matrix, the influence of the dimension between the monitor data can be eliminated.
S12, setting n initial clustering centers based on the normalized state matrix, and taking each row of monitoring data S of the state matrix as a sample respectively;
It should be noted that "n" in this step may also represent the number of samples remaining after removing the similar monitoring samples, in a specific embodiment, the number of samples s after normalization is set to k, and the initial cluster center is set to n, and the cluster analysis is performed by traversing n= (1, 2,..k-1), and the contour coefficient of the current cluster result is calculated after each cluster analysis to determine the value of n.
More specifically, the average distance d a(i),da (i) of the sample s i under the current cluster to other samples in the same cluster domain represents the dissimilarity in the cluster domain of the sample s i as follows:
Wherein N a is the number of samples in the same cluster domain as s i.
The average distance d bm (i) of the sample s i to all samples in the other cluster domain m is calculated as follows:
wherein N bm is the number of samples in other cluster domains m, and s mj is the number of samples in other cluster domains m.
If there are m cluster domains in addition to the cluster domain in which the sample s i is located, the dissimilarity between the cluster domains of the sample s i may be defined as d b (i):
d b(i)＝min{db1(i),db2(i),...,dbm (i) } calculating the contour coefficient c of the sample s i i
Wherein, the larger c i indicates that the clustering of the sample s i is more reasonable.
When the current initial clustering center is set as n, calculating a contour coefficient C n of a clustering result according to the following formula:
The larger C n shows that the clustering result is more reasonable.
The initial cluster center number n is set to be the initial cluster center number set when the cluster result profile coefficient C n is maximum, namely n corresponding to max { C n }.
For the convenience of understanding, the number of the normalized samples s is set to be 10, and the initial clustering centers should take 1,2 and perform clustering analysis after 9, namely, clustering once at n=2, clustering once at n=3, clustering once at n=4, clustering once at n=9.
Assuming n=4, the clustering yields 4 cluster domains, each with 5 samples, as shown in table 1 below:
TABLE 1
Calculating the average distance d a (1) from the sample s 1(sa1 under the current cluster to the other samples s a2,sa3,sa4,sa5 in the same cluster domain is as follows:
Calculate the average distance d b(1)、db(2)、db (3) of the sample s 1 to all samples in the other cluster domains B1, B2, B3:
The inter-cluster-domain dissimilarity d b (1) of sample s 1 is:
The profile factor c 1 of d b(1)＝min{db1(1),db2(1),db3(1)}s1 is:
Similarly, the profile factor c i, i.e., c 1,c2,...,c10, for each sample s i can be calculated.
The contour coefficient C 4 of the clustering result at the current n=4 is:
Similarly, the contour coefficient C n of the clustering result when n is other value, namely C 2,C3,...,C9, can be calculated. If max { C 1,C2,...,C9}＝C4, the initial cluster center number is set to 4.
S13, carrying out iterative computation on the initial clustering center and a sample S, wherein if the following conditions are satisfied that I S-z j(m)||＜||s-zi (m) I, (i, j=1, 2,.., n and i not equal to j), S E f j (m), wherein z i (m) represents an ith clustering center when the m iteration is carried out, and f j (m) represents a clustering domain of the jth clustering center when the m iteration is carried out;
it should be noted that "s" in the formula of this step represents each row of monitoring data s after normalization of the state matrix.
S14, calculating a new clustering center according to the following formula:
Wherein N i is the number of samples in the i-th cluster domain f i (m);
s15, after the condition of z i(m+1)＝zi (m) is met, all samples are clustered into n classes.
In this embodiment, after the condition of z i(m+1)＝zi (m) is satisfied, the algorithm converges, and n new cluster centers can be obtained finally.
In a specific embodiment, the step S102 of removing similar monitoring data based on the clustering result obtained by the dynamic clustering analysis includes the following steps:
S20, calculating the distance d (x, c) from each sample to the clustering center of the sample according to the following formula:
d(x,c)=(x-c)[(x-c)]T;
Wherein centroid c is the mean of the samples in the cluster domain, "[ (x-c) ] T" represents the transpose of the matrix for (x-c).
S21, traversing all corresponding samples for each target clustering center, reserving the sample corresponding to the smallest d (x, c), taking the original monitoring data corresponding to the sample as target monitoring data, and deleting the original monitoring data corresponding to the rest samples.
The embodiment of the application removes similar monitoring data as redundant data, can effectively improve the grading accuracy of the health state of the coal mining machine, and simultaneously improves the operation efficiency of each subsequent link.
Referring to fig. 2, in a specific embodiment, the step S103 includes the following steps:
s30, inputting the state matrix with the similar monitoring data removed into a sequence input layer in a pre-trained bidirectional long-short-term network model, sequentially passing through a first BiLSTM layer, a first discarding layer, a second BiLSTM layer, a second discarding layer, a full-connection layer, a softmax function activation layer and a classification layer, and outputting a classification result vector.
It should be noted that, the Long Short-Term Memory (LSTM) network is a special type of a recurrent neural network (RNN, recurrent Neural Network), which makes up a Short board for learning Long-Term information dependency relationship of the RNN, and is often suitable for processing time sequence data. BiLSTM is formed by combining a forward LSTM and a backward LSTM, overcomes the defect that the LSTM cannot encode back-to-front information, and can better discover the dependency relationship of bidirectional long-term information.
The bidirectional long-short-term memory network model is constructed by a sequence input layer (sequenceInputLayer), a first BiLSTM layer, a first discarding layer (dropoutLayer), a second BiLSTM layer, a second discarding layer (dropoutLayer), a full-connection layer (fullyConnectedLayer), a softmax function activation layer and a classification layer (classificationLayer), and specifically, n rows of state matrixes after similar monitoring data are removed are input into a pre-trained BiLSTM network model, wherein the input size of the input layer of the sequence input layer is set to n, the numbers of hidden units of the first BiLSTM layer and the second BiLSTM layer, the discarding rates of the first discarding layer and the second discarding layer are all calculated by a particle swarm algorithm when the network model is trained, the first BiLSTM layer outputs a complete sequence, the first discarding layer sets 0 according to the first discarding rate on input elements, the second BiLSTM layer outputs the last time step of the sequence, the second discarding layer sets 0 according to the second discarding rate on input elements, and the output size of the full-connection layer is set to 5 (the application sets 5 health levels: severe morbidity, general, sub-health, health), an abstract eigenvector z= (Z 1,z2,z3,z4,z5) with dimension 5 is output, and a softmax function (normalized exponential function) is applied to obtain the probability of multi-classification results:
Wherein, K is the number of the health state grades of the coal mining machine, z i represents the predicted value of the model for the sample belonging to the grade i;
Specifically, the classification result vector r= (R 1,r2,r3,r4,r5) output by the softmax function activation layer, where R n (n=1, 2,3,4, 5) represents the probability that the state matrix Q belongs to class n.
It should be noted that, training data used in the pre-training process of the two-way long-short-period memory network of the present application should be a state matrix formed by monitoring data of each target position and excluding similar monitoring data when the coal mining machine operates at different health state levels (i.e. the above 5 health levels), and the current health state level serial number is used as a label of the corresponding state matrix Q.
In a specific embodiment, before the step S103, the method includes the following steps:
And S40, optimizing target super parameters in the bidirectional long-short-period network model by using a particle swarm algorithm, wherein the target super parameters comprise the number of hidden units of a first BiLSTM layer, the discarding rate of a first discarding layer, the number of hidden units of a second BiLSTM layer, the discarding rate of the second discarding layer, an initial learning rate, a maximum iteration number and a small batch size (MiniBatchSize).
In this embodiment, the super parameters in BiLSTM network model are optimized by particle swarm optimization (PSO algorithm) to improve the classification accuracy of the model. It should be noted that, the actual performance of the BiLSTM network model is directly affected by the super-parameters, so that the PSO algorithm has better optimizing capability, and can quickly find out a proper super-parameter value through iterative optimizing calculation aiming at the complex deep learning network model.
In a specific embodiment, the step S40 includes the following steps:
S50, initializing the speed and the position of each particle in the population based on the value range [ h min,hmax ] of the target super-parameter, wherein the initial value is calculated according to the following formula:
h=rand*(hmax-hmin)+hmin;
in the present embodiment, rand represents a random value in the uniform distribution of the interval (0, 1);
s51, taking an initial individual optimal position p best of the particles as the fitness of the first particle in the particle group, wherein the fitness of the particles is calculated according to the following formula:
Wherein Y pred is the label of the bidirectional long-short-term network model classification, Y test is the label of the test set, Y pred＝＝Ytest is the label of judging whether the classified label is equal to the label of the test set, numel (Y test) is the label of calculating the number of the test set by using numel function, wherein the classified label is the preset 5 health grades of 1 (serious illness), 2 (illness), 3 (general), 4 (sub-health) and 5 (health).
S52, setting the global optimal position g best of the particle as min (p best);
S53, updating the position and the speed of the particle based on a preset updating rule, comparing the updated fitness of the particle with the fitness of the optimal position p best of the individual historical particle, and selecting the position corresponding to the smaller fitness as p best of the particle;
Through the comparison and replacement operation of step S53, particle positions that are both in accordance with the global optimum and the local optimum are found.
In the present embodiment, the specific steps of "updating the positions and velocities of all particles" in step S53 are as follows:
S531, updating the position of the particles according to the following formula:
Xi,j(t+1)＝Xi,j(t)+Vi,j(t+1);
Wherein, the population X= (X 1,X2,...,Xn) formed by n particles, the position of the ith particle represents a D-dimensional vector X i＝(Xi1,X2,...,XiD)T, and the speed of the ith particle represents a D-dimensional vector V i＝(Vi1,V2,...,ViD)T;
s91, updating the particle speed according to the following formula:
Wherein, c 1 and c 2 (both not less than 0) are acceleration constants, r 1 and r 2 are uniformly distributed random numbers and are both greater than 0 and less than 1, ω is an inertial weight coefficient, the position of the ith particle represents a D-dimensional vector X i＝(Xi1,X2,...,XiD)T, the speed of the ith particle represents a D-dimensional vector V i＝(Vi1,V2,...,ViD)T, the individual extremum is P i＝(Pi1,P2,...,PiD)T, and the global extremum is P g＝(Pg1,Pg2,...,PgD)T;
S532, calculating the inertia weight coefficient omega according to the following formula:
Wherein t represents the current iteration number, and t max represents the maximum iteration step number of the particle swarm.
In this embodiment, the maximum value ω max =1.2 of the inertia weight and the minimum value ω min =0.8 of the inertia weight.
And S54, taking the optimized result as the corresponding target super-parameter value after the iteration times reach the preset maximum iteration step number t max of the particle swarm.
It should be noted in advance that the fuzzy comprehensive evaluation method is a method for comprehensively evaluating things from a plurality of factors (indexes) by applying the principle of fuzzy relation synthesis. In a specific embodiment, the rule for evaluating the health status of the coal mining machine in step S104 includes the following steps:
s60, determining monitoring data acquired by the coal mining machine in each time period as judgment factors, and obtaining a time period domain U based on all the judgment factors:
In this embodiment, the monitoring data collected in the current time period of the coal mining machine, for example, in one minute, is recorded as "time i", the data of each j minutes before and after the "time i" are collected respectively, the number k=1+2j (k is an integer multiple of q) of all the time periods, and then all the collected monitoring data are determined as the judgment factors.
S61, dividing all the time slot domains into q subsets according to time sequence, wherein the q subsets are as follows:
q is an odd number not less than 3.
S62, setting comment level domains of all levels of the health condition of the coal mining machine as follows:
X= { State 1, state 2, state 3, state 4, state 5}
Specifically, the application divides the health state of the coal mining machine into a state 1, a state 2, a state 3, a state 4 and a state 5 according to the mapping relation between the health state grade and the health state of the coal mining machine shown in the table 2, and takes the state serial number as the label of the corresponding state matrix Q.
TABLE 2
The coal mining machine which is generally newly put into production is in a healthy state, namely a state 5 in the table 2.
In a specific embodiment, the step S104 includes the following steps:
s70, carrying out fuzzy comprehensive evaluation by using all the classification results, and calculating the health score of the coal mining machine in the current time period, wherein the method comprises the following steps:
S71, combining classification result vectors corresponding to different time periods according to time sequence to establish a fuzzy relation matrix, wherein the specific fuzzy relation matrix is shown in the following table 3, and r is more than or equal to 0 and less than or equal to 1
TABLE 3 Table 3
S72, based on the time period domain and the comment level domain, acquiring an evaluation matrix R from the fuzzy relation matrix according to the following formula:
It should be added that the "time i" is the current time period, and the health state of the coal mining machine in the current time period can be most reflected.
S73, setting a first-level evaluation weight distribution vector A median (q) according to the following steps:
Wherein the element in A median(q) at the medium (k/q) th position The elements at the rest positions areMedian represents the number of calculated medians.
S74, setting a first-level evaluation weight distribution vector A res according to the following steps:
Wherein A res has a length of k/q, and each element in the vector is
S75, calculating each element B in the first-level evaluation vector B according to the following formula:
wherein a is an element in a first-level evaluation weight distribution vector, and R is an element in an evaluation matrix R;
s76, calculating a first-level evaluation vector B according to the following formula:
wherein the symbols are Representing blurring operatorsA median(q) only appears in the calculation of B median(q), and the rest first-level evaluation vectors are all calculated by a res;
note that, the weighted average type blurring operator The weight of each factor is comprehensively considered, and the comprehensive consideration is reasonable, so that each element B in the first-level evaluation vector B is calculated by the operator:
S77, calculating a single factor judgment matrix T of a time period domain U according to the following formula:
S78, setting a secondary evaluation weight distribution vector according to the following mode
Wherein, In the element at the medium (q) th positionThe elements at the rest positions areMedian represents the number of calculated medians.
In the present embodiment, since the period in which the "time i" is located: the state of the coal mining machine in the current period can be reflected most, and then the secondary evaluation weight distribution vector is set according to the above
S79, calculating a second-level evaluation according to the following formula
Wherein the symbols areThe blurring operator M (, ·y) is represented.
S80, calculating score vectors S of all states of the coal mining machine according to the following steps:
S=(0,25,50,75,100);
Wherein the elements of each position of the score vector S in turn represent the score values of states 1 to 5.
S81, calculating to obtain the health score of the coal mining machine according to the following formula:
For ease of understanding, the present application records the current time period "time 5" of the shearer and collects data for 4 (j=4) minutes before and after "time 5", respectively, so the 9 (k=9) consecutive time periods are used to exemplify the shearer health score calculation:
the time period domain U is:
{ time 1, time 2, time 3, time 4, time 5, time 6, time 7, time 8, time 9}
Wherein time 5 is the current time period.
U is separated into 3 (q=3) subsets in time sequence:
The corresponding fuzzy relation matrix is as follows in table 4:
TABLE 4 Table 4
| State 1 | State 2 | State 3 | State 4 | State 5 | |
| Time 1 | r11 | r12 | r13 | r14 | r15 |
| Time 2 | r21 | r22 | r23 | r24 | r25 |
| Time 3 | r31 | r32 | r33 | r34 | r35 |
| Time 4 | r41 | r42 | r43 | r44 | r45 |
| Time 5 | r51 | r52 | r53 | r54 | r55 |
| Time 6 | r61 | r62 | r63 | r64 | r65 |
| Time 7 | r71 | r72 | r73 | r74 | r75 |
| Time 8 | r81 | r82 | r83 | r84 | r85 |
| Time 9 | r91 | r92 | r93 | r94 | r95 |
From U and X, the evaluation matrix R i (i=1, 2, 3) can be obtained as follows:
Setting a first-order evaluation weight allocation vector a median(q)(A2) as follows:
the first-level evaluation weight distribution vectors A res except for A 2 are all 3 in length, and each element in the vectors is
Each element B in the first-order evaluation vector B is calculated as follows:
Calculated as a first order evaluation vector B i (i=1, 2, 3):
The single factor judgment matrix T of U is:
setting a secondary evaluation weight allocation vector The method comprises the following steps:
The secondary evaluation was calculated as follows
Finally, the coal cutter health score is N:
The embodiment of the invention also provides an intelligent assessment device for the health state of the coal mining machine, which is used for executing any embodiment of the intelligent assessment method for the health state of the coal mining machine. Specifically, referring to fig. 3, fig. 3 is a schematic block diagram of an intelligent assessment device for health status of a coal mining machine according to an embodiment of the present invention.
As shown in fig. 3, the intelligent assessment device 200 for the health status of the coal mining machine includes:
an acquisition unit 201, configured to acquire monitoring data of each target position of the coal mining machine in a plurality of adjacent time periods;
the removing unit 202 is configured to perform dynamic cluster analysis on all the monitoring data corresponding to each time period by using a K-means algorithm, and remove similar monitoring data based on a clustering result obtained by the dynamic cluster analysis;
The classifying unit 203 is configured to classify all the remaining monitoring data by using a pre-trained bidirectional long-short-term memory network model, so as to obtain a classification result;
And the scoring unit 204 is used for carrying out fuzzy comprehensive evaluation by using all the classification results based on a preset coal cutter health state evaluation rule, and calculating the coal cutter health score in the current time period.
The method comprises the steps of collecting monitoring data of a coal mining machine in a plurality of continuous time periods, removing redundant data in all the monitoring data, reducing interference of similar monitoring data on health state evaluation results, improving efficiency of health grading result output, classifying the monitoring data of all target positions in all the time periods through a two-way long-short-period memory network model to obtain health state classification probability of each monitoring data, and finally carrying out fuzzy comprehensive evaluation by using the health state classification probability to calculate health grading of the coal mining machine.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus and units described above may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again.
The intelligent assessment device for the health status of the coal mining machine can be implemented in the form of a computer program which can be run on a computer device as shown in fig. 4.
Referring to fig. 4, fig. 4 is a schematic block diagram of a computer device according to an embodiment of the present invention. The computer device 1100 is a server, and the server may be a stand-alone server or a server cluster formed by a plurality of servers.
With reference to FIG. 4, the computer device 1100 includes a processor 1102, memory, and a network interface 1105 connected through a system bus 1101, wherein the memory may include a non-volatile storage medium 1103 and an internal memory 1104.
The non-volatile storage medium 1103 may store an operating system 11031 and computer programs 11032. The computer program 11032, when executed, causes the processor 1102 to perform a method for intelligently assessing the health of a shearer.
The processor 1102 is operable to provide computing and control capabilities to support the operation of the overall computer device 1100.
The internal memory 1104 provides an environment for the execution of a computer program 11032 in the non-volatile storage medium 1103, which computer program 11032, when executed by the processor 1102, causes the processor 1102 to perform the intelligent assessment method of shearer health.
The network interface 1105 is used for network communication such as providing transmission of data information, etc. It will be appreciated by those skilled in the art that the architecture shown in fig. 4 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting of the computer device 1100 to which the present inventive arrangements may be implemented, and that a particular computer device 1100 may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
Those skilled in the art will appreciate that the embodiment of the computer device shown in fig. 4 is not limiting of the specific construction of the computer device, and in other embodiments, the computer device may include more or less components than those shown, or certain components may be combined, or a different arrangement of components. For example, in some embodiments, the computer device may include only a memory and a processor, and in such embodiments, the structure and function of the memory and the processor are consistent with the embodiment shown in fig. 4, and will not be described again.
It should be appreciated that in an embodiment of the invention, the Processor 1102 may be a central processing unit (Central Processing Unit, CPU), the Processor 1102 may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL processors, DSPs), application SPECIFIC INTEGRATED Circuits (ASICs), off-the-shelf Programmable gate arrays (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In another embodiment of the invention, a computer-readable storage medium is provided. The computer readable storage medium may be a non-volatile computer readable storage medium. The computer readable storage medium stores a computer program, wherein the computer program realizes the intelligent assessment method of the health state of the coal mining machine according to the embodiment of the invention when being executed by a processor.
The storage medium is a physical, non-transitory storage medium, and may be, for example, a U-disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus, device and unit described above may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (8)
1. An intelligent assessment method for the health state of a coal mining machine is characterized by comprising the following steps:
Acquiring monitoring data of each target position of the coal mining machine in a plurality of adjacent time periods;
Performing dynamic cluster analysis on all the monitoring data corresponding to each time period by using a K-means algorithm, and removing similar monitoring data based on a clustering result obtained by the dynamic cluster analysis;
classifying the monitoring data after similar monitoring data are removed by utilizing a pre-trained two-way long-short-term memory network model, and outputting a classification result;
based on a preset coal cutter health state evaluation rule, carrying out fuzzy comprehensive evaluation by using all classification results, and calculating the coal cutter health score in the current time period;
The dynamic cluster analysis is carried out on all the monitoring data corresponding to each time period by using a K-means algorithm, and the dynamic cluster analysis comprises the following steps:
storing all the monitoring data in each time period in a data set in a state matrix mode, wherein the monitoring data of different target positions are located in different rows of the state matrix;
normalizing the state matrix according to the following formula:
Wherein s i represents the monitoring data after the normalization of the ith row, and x i represents the monitoring data of the ith row;
setting n initial clustering centers based on the normalized state matrix, and taking each row of monitoring data s of the state matrix as a sample respectively;
Performing iterative computation on the initial cluster center and a sample s, wherein if the following conditions are satisfied that (i, s-z j(m)‖<‖s-zi (m) |, (i, j=1, 2,.., n and i not equal to j), s epsilon f j (m), wherein z i (m) represents an ith cluster center in the m-th iteration, and f j (m) represents a cluster domain of the jth cluster center in the m-th iteration;
The new cluster center is calculated as:
Wherein N i is the number of samples in the i-th cluster domain f i (m);
after meeting the condition of z i(m+1)＝zi (m), all samples are clustered into n classes;
The method for removing similar monitoring data based on the clustering result obtained by dynamic cluster analysis comprises the following steps:
the distance d (x, c) of each sample to the cluster center to which it belongs is calculated as follows:
d(x,c)=(x-c)[(x-c)]T;
The centroid c is the average value of all samples in the cluster domain;
and traversing all corresponding samples for each target cluster center, reserving the sample corresponding to the smallest d (x, c), taking the original monitoring data corresponding to the sample as target monitoring data, and deleting the original monitoring data corresponding to the rest samples.
2. The intelligent assessment method of the health status of the coal mining machine according to claim 1, wherein the classifying the monitoring data from which similar monitoring data are removed by using a pre-trained bidirectional long-short-term memory network model, and outputting a classification result comprises:
and inputting the state matrix with the similar monitoring data removed into a sequence input layer in a pre-trained bidirectional long-short-term network model, sequentially passing through a first BiLSTM layer, a first discarding layer, a second BiLSTM layer, a second discarding layer, a full connection layer, a softmax function activation layer and a classification layer, and outputting a classification result vector.
3. The intelligent assessment method for health status of coal mining machine according to claim 2, wherein the classifying the monitoring data after removing similar monitoring data by using the pre-trained bidirectional long-short-term memory network model, and before outputting the classification result, comprises:
And optimizing target super parameters in the bidirectional long-short-term network model by using a particle swarm algorithm, wherein the target super parameters comprise the number of hidden units of a first BiLSTM layer, the discarding rate of a first discarding layer, the number of hidden units of a second BiLSTM layer, the discarding rate of a second discarding layer, an initial learning rate, a maximum iteration number and a small batch size.
4. The intelligent assessment method according to claim 3, wherein the optimizing the target super-parameters in the bidirectional long-short term network model by using a particle swarm algorithm comprises:
initializing the speed and the position of each particle in the population based on the value range [ h min,hmax ] of the target super-parameter, wherein the initial value is calculated according to the following formula:
h=rand*(hmax-hmin)+hmin;
The initial individual optimal position p best of the particles is taken as the fitness of the first particle in the particle group, wherein the fitness of the particles is calculated according to the following formula:
Wherein Y pred is a label of BiLSTM network model classification, Y test is a label of a test set, and the global optimal position g best of the particle is set to be min (p best);
Based on a preset updating rule, updating the position and speed of the particle, comparing the updated fitness of the particle with the fitness of the optimal position p best of the individual historical particle, and selecting the position corresponding to the smaller fitness as p best of the particle;
And continuously iterating until the maximum iteration step number t max of the particle swarm is reached, and taking the result obtained by optimizing as the corresponding value of the target super-parameter.
5. The intelligent assessment method of the health status of the coal mining machine according to claim 1, wherein the preset evaluation rule of the health status of the coal mining machine comprises:
Determining monitoring data collected by the coal mining machine in each time period as a judgment factor, and obtaining a time period domain U based on all the judgment factors:
Dividing all the time period domains into q subsets according to time sequence, as follows:
Setting comment grade domains of each grade of the health condition of the coal mining machine as follows:
X= { State 1, state 2, state 3, state 4, state 5}
And carrying out fuzzy comprehensive evaluation by using all the classification results, and calculating the health score of the coal mining machine in the current time period, wherein the fuzzy comprehensive evaluation comprises the following steps:
Combining the classification result vectors corresponding to different time periods according to the time sequence to establish a fuzzy relation matrix;
Based on the time period domain and the comment level domain, an evaluation matrix R is obtained from the fuzzy relation matrix according to the following formula:
The first-order evaluation weight allocation vector a median(q) is set as follows:
The first-order evaluation weight allocation vector a res is set as follows:
Each element B in the first-order evaluation vector B is calculated as follows:
wherein a is an element in a first-level evaluation weight distribution vector, and R is an element in an evaluation matrix R;
The first order evaluation vector B is calculated as follows:
Wherein "°" represents a blurring operator A median(q) only appears in the calculation of B median(q), and the rest first-level evaluation vectors are all calculated by a res;
calculating a single factor judgment matrix T of a time period domain U according to the following steps:
setting a secondary evaluation weight allocation vector as follows
The second-order evaluation vector is calculated as follows
Calculating score vectors S of each health state of the coal mining machine according to the following steps of S= (0,25,50,75,100);
the health score of the shearer was calculated as follows:
6. An intelligent assessment device for the health state of a coal mining machine is characterized by comprising:
The acquisition unit is used for acquiring monitoring data of each target position of the coal mining machine in a plurality of adjacent time periods;
the removing unit is used for carrying out dynamic cluster analysis on all the monitoring data corresponding to each time period by using a K-means algorithm, and removing similar monitoring data based on a clustering result obtained by the dynamic cluster analysis;
The classification unit is used for classifying the monitoring data after the similar monitoring data are removed by utilizing a pre-trained two-way long-short-term memory network model to obtain a classification result;
The scoring unit is used for carrying out fuzzy comprehensive evaluation by using all the classification results based on a preset coal cutter health state evaluation rule, and calculating the coal cutter health score in the current time period;
the removing unit is specifically configured to, when performing dynamic cluster analysis on all the monitoring data corresponding to each time period by using a K-means algorithm:
storing all the monitoring data in each time period in a data set in a state matrix mode, wherein the monitoring data of different target positions are located in different rows of the state matrix;
normalizing the state matrix according to the following formula:
Wherein s i represents the monitoring data after the normalization of the ith row, and x i represents the monitoring data of the ith row;
setting n initial clustering centers based on the normalized state matrix, and taking each row of monitoring data s of the state matrix as a sample respectively;
Carrying out iterative computation on the initial cluster center and a sample s, wherein if the following conditions are satisfied that I s-z j(m)||＜||s-zi (m) I, (i, j=1, 2,.., n and i not equal to j), s E f j (m), wherein z i (m) represents an ith cluster center in the m-th iteration, and f j (m) represents a cluster domain of the jth cluster center in the m-th iteration;
The new cluster center is calculated as:
Wherein N i is the number of samples in the i-th cluster domain f i (m);
after meeting the condition of z i(m+1)＝zi (m), all samples are clustered into n classes;
the removing unit is specifically configured to, when removing similar monitoring data based on a clustering result obtained by dynamic cluster analysis:
the distance d (x, c) of each sample to the cluster center to which it belongs is calculated as follows:
d(x,c)=(x-c)[(x-c)]T;
The centroid c is the average value of all samples in the cluster domain;
and traversing all corresponding samples for each target cluster center, reserving the sample corresponding to the smallest d (x, c), taking the original monitoring data corresponding to the sample as target monitoring data, and deleting the original monitoring data corresponding to the rest samples.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the intelligent assessment method of the health of a shearer as claimed in any one of claims 1 to 5 when the computer program is executed by the processor.
8. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, causes the processor to perform the intelligent assessment method of the health status of a coal mining machine according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310087191.9A CN116226751B (en) | 2023-01-31 | 2023-01-31 | A method, device and related components for intelligent assessment of health status of coal mining machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310087191.9A CN116226751B (en) | 2023-01-31 | 2023-01-31 | A method, device and related components for intelligent assessment of health status of coal mining machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116226751A CN116226751A (en) | 2023-06-06 |
| CN116226751B true CN116226751B (en) | 2024-12-03 |
Family
ID=86572503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310087191.9A Active CN116226751B (en) | 2023-01-31 | 2023-01-31 | A method, device and related components for intelligent assessment of health status of coal mining machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116226751B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580198A (en) * | 2020-12-03 | 2021-03-30 | 国网山西省电力公司晋城供电公司 | Improved optimization classification method for transformer state evaluation |
| CN114707431A (en) * | 2022-06-02 | 2022-07-05 | 广东工业大学 | Method, system and storage medium for predicting remaining service life of rotating multi-component |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103984788B (en) * | 2013-12-31 | 2017-10-10 | 中国矿业大学(北京) | A kind of coal entry anchor rod support automated intelligent design and optimization system |
| KR102045626B1 (en) * | 2017-10-13 | 2019-12-02 | 주식회사 포스코 | Apparatus and method for evaluating conditions of equipment |
| CN113705882B (en) * | 2021-08-25 | 2024-09-20 | 北京天玛智控科技股份有限公司 | Fault prediction method and device for coal mining machine |
| CN113988220B (en) * | 2021-11-25 | 2025-03-21 | 西安科技大学 | A method for evaluating the health status of coal mining machines |
| CN115471043A (en) * | 2022-08-09 | 2022-12-13 | 嘉善鑫海精密铸件有限公司 | Wax mould casting heat treatment equipment health state evaluation method based on integrated SAE-SOM |
-
2023
- 2023-01-31 CN CN202310087191.9A patent/CN116226751B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580198A (en) * | 2020-12-03 | 2021-03-30 | 国网山西省电力公司晋城供电公司 | Improved optimization classification method for transformer state evaluation |
| CN114707431A (en) * | 2022-06-02 | 2022-07-05 | 广东工业大学 | Method, system and storage medium for predicting remaining service life of rotating multi-component |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116226751A (en) | 2023-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111680446B (en) | Rolling bearing residual life prediction method based on improved multi-granularity cascade forest | |
| CN111242206B (en) | High-resolution ocean water temperature calculation method based on hierarchical clustering and random forests | |
| WO2024021246A1 (en) | Cross-device incremental bearing fault diagnosis method based on continuous learning | |
| CN106250442A (en) | The feature selection approach of a kind of network security data and system | |
| CN114036610A (en) | Penetration depth prediction method based on data enhancement | |
| CN112800115A (en) | Data processing method and data processing device | |
| CN112307410A (en) | Seawater temperature and salinity information time sequence prediction method based on shipborne CTD measurement data | |
| CN110968618A (en) | Method for mining quantitative association rule of welding parameters and application | |
| CN116681945B (en) | Small sample class increment recognition method based on reinforcement learning | |
| CN115587543A (en) | Tool Remaining Life Prediction Method and System Based on Federated Learning and LSTM | |
| CN110705631B (en) | SVM-based bulk cargo ship equipment state detection method | |
| CN117784615B (en) | Fire control system fault prediction method based on IMPA-RF | |
| CN118312723A (en) | A slope displacement prediction method and system based on monitoring data | |
| CN120449946B (en) | Self-adaptive hybrid precision quantization network generation method based on self-learning | |
| CN117976018A (en) | Method, device, computer equipment and storage medium for predicting optimal read voltage | |
| CN115292820B (en) | A method for predicting the remaining service life of urban rail train bearings | |
| Efendiyev et al. | Estimation of lost circulation rate using fuzzy clustering of geological objects by petrophysical properties | |
| CN116405368A (en) | A network fault diagnosis method and system under the condition of high-dimensional unbalanced data | |
| CN119758104B (en) | Battery performance attenuation test method, device and equipment for energy storage battery | |
| CN116226751B (en) | A method, device and related components for intelligent assessment of health status of coal mining machine | |
| CN120541629A (en) | A bearing fault diagnosis method and system based on MS-CNN-BO-SVM | |
| CN113191540A (en) | Construction method and device of industrial link manufacturing resources | |
| CN119105840A (en) | A method and device for allocating resources to a virtual machine | |
| CN116188834B (en) | Full-slice image classification method and device based on self-adaptive training model | |
| CN118410596A (en) | Rolling bearing life prediction method, system, equipment and medium |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An intelligent evaluation method for the health status of a coal mining machine, a device, and related components Granted publication date: 20241203 Pledgee: Industrial and Commercial Bank of China Taiyuan Branch|China Construction Bank Corporation Taiyuan Development Zone Branch Pledgor: SHANXI KEDA AUTOMATION CONTROL Co.,Ltd. Registration number: Y2025140000016 |