Health degree assessment method and device for mechanical equipment

By obtaining preset operating monitoring parameters of mechanical equipment, filtering target test data, and evaluating health using the Hidden Markov model, the problem of incomplete capture of single monitoring information is solved, and the accuracy of the assessment of the health of mechanical equipment is achieved. Convenience improves the reflection of equipment health status.

CN119004123APending Publication Date: 2024-11-22BEIJING GRIDSUM TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202310559271.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-17
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The prior art has the problem of incomplete capture of single monitoring information in the health assessment of mechanical equipment, and manual labeling methods are difficult to accurately reflect the health status of the equipment, resulting in the inability to accurately reflect the health status of the equipment.

Method used

By obtaining preset operation monitoring parameters of mechanical equipment, filtering target test data, and using the pre-trained hidden Markov model (HMM) to calculate the matching probability, assess the health of the equipment, reduce manual dependence, and conduct evaluation in combination with different indicators.

Benefits of technology

It improves the accuracy and convenience of the health assessment of mechanical equipment, reduces manual intervention, can more accurately reflect the health status of the equipment, reduces resource waste, and improves work efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119004123A_ABST
    Figure CN119004123A_ABST
Patent Text Reader

Abstract

The invention discloses a health degree assessment method and device for mechanical equipment, relates to the technical field of operation and maintenance of the mechanical equipment, and mainly aims to improve the accuracy and convenience of health degree assessment of different mechanical equipment on the basis of integrating different indexes. According to the main technical scheme, the method comprises the steps of obtaining test data based on preset operation monitoring parameters of to-be-evaluated mechanical equipment, wherein the test data is operation state data of the to-be-evaluated mechanical equipment; screening the test data by using a preset screening rule to obtain target test data; and based on the target test data, utilizing a preset trained HMM model to obtain a matching probability of the target test data and the preset trained HMM model, and obtaining the health degree of the to-be-evaluated mechanical equipment. The method is used for evaluating the health degree of the mechanical equipment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical equipment operation and maintenance, and in particular to a method and device for evaluating the health of mechanical equipment. Background Art

[0002] With the production and development of modern industry, the automation degree of mechanical equipment is getting higher and higher, which greatly improves the efficiency of industrial production. The equipment of an enterprise is the most basic guarantee for the enterprise to produce and make profits. However, since the equipment is often in a harsh working environment such as high temperature and high pressure, it is very likely to age, wear and tear, or even directly fail to work in almost uninterrupted operation, which brings great economic losses to the enterprise. Health is the quantified health of the equipment, which is a quantitative assessment of the health status of the equipment and can more accurately reflect the health status of the equipment. By collecting various signals in the operating status of mechanical equipment to evaluate the operating status and health level of the equipment and make appropriate maintenance decisions, it can reduce resource waste and improve work efficiency.

[0003] Currently, the method for evaluating equipment health is to manually label abnormal data and represent the health of the equipment based on single monitoring information of a single device.

[0004] However, since the above processing method is based on the single monitoring information of a single device to represent the health of the device, there is a problem that the single monitoring information does not capture comprehensive information. In addition, the manual labeling method not only makes it difficult to determine the label, but also makes it difficult to assess the health of the device, which ultimately leads to the inability to accurately reflect the health status of the device. Summary of the invention

[0005] In view of the above problems, the present invention provides a method and device for evaluating the health of mechanical equipment, the main purpose of which is to improve the accuracy and convenience of health evaluation of different mechanical equipment based on a comprehensive analysis of different indicators.

[0006] In order to solve the above technical problems, the present invention proposes the following solutions:

[0007] In a first aspect, the present invention provides a method for evaluating the health of mechanical equipment, the method comprising:

[0008] Acquiring test data based on preset operation monitoring parameters of the mechanical equipment to be evaluated, wherein the test data is operation status data of the mechanical equipment to be evaluated;

[0009] Filtering the test data using preset filtering rules to obtain target test data;

[0010] Based on the target test data, a preset trained HMM model is used to obtain a matching probability between the target test data and the preset trained HMM model, thereby obtaining the health of the mechanical equipment to be evaluated.

[0011] In a second aspect, the present invention provides a health assessment device for mechanical equipment, comprising:

[0012] An acquisition unit, configured to acquire test data based on preset operation monitoring parameters of the mechanical equipment to be evaluated, wherein the test data is operation status data of the mechanical equipment to be evaluated;

[0013] A screening unit, configured to screen the test data using a preset screening rule to obtain target test data,

[0014] The calculation unit is used to obtain the matching probability between the target test data and the preset trained HMM model based on the target test data, and obtain the health of the mechanical equipment to be evaluated.

[0015] In order to achieve the above-mentioned purpose, according to the third aspect of the present invention, a storage medium is provided, wherein the storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the health assessment method for mechanical equipment described in the first aspect.

[0016] In order to achieve the above-mentioned purpose, according to the fourth aspect of the present invention, there is provided an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, all or part of the steps of the health assessment device for mechanical equipment as described in the second aspect are implemented.

[0017] By means of the above technical scheme, the method and device for evaluating the health of mechanical equipment provided by the present invention is that the current method for evaluating the health of equipment is to use manual labeling for abnormal data, and to represent the health of the equipment based on the single monitoring information of a single device, which has the problem that the single monitoring information does not capture comprehensive information, and the manual labeling method is not only difficult to determine the label, but also difficult to assess the health of the equipment, which ultimately leads to the inability to accurately reflect the health of the equipment. To this end, the present invention obtains test data based on the preset operation monitoring parameters of the mechanical equipment to be evaluated, and the test data is the operating status data of the mechanical equipment to be evaluated; the test data is screened by using the preset screening rules to obtain the target test data; based on the target test data, the matching probability of the target test data and the preset trained HMM model is obtained by using the preset trained HMM model, and the health of the mechanical equipment to be evaluated is obtained. The present invention can reduce manual dependence on health evaluation of different mechanical equipment, and can also solve the problem that the single monitoring information captures incomplete information; by establishing a health evaluation model, the evaluation results of different indicators are integrated to give the final health evaluation of the mechanical equipment, thereby improving the accuracy and convenience of health evaluation of different mechanical equipment.

[0018] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0020] Figure 1 A flow chart of a method for evaluating the health of mechanical equipment provided by an embodiment of the present invention is shown;

[0021] Figure 2 Another flow chart of a method for evaluating the health of mechanical equipment provided by an embodiment of the present invention is shown;

[0022] Figure 3 A block diagram showing a composition of a device for assessing the health of mechanical equipment provided by an embodiment of the present invention;

[0023] Figure 4 A block diagram showing the composition of another device for assessing the health of mechanical equipment provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0025] The current method for evaluating the health of equipment is to manually label abnormal data, and to represent the health of the equipment based on the single monitoring information of a single device. There is a problem that the single monitoring information does not capture comprehensive information, and the manual labeling method is not only difficult to determine the label, but also difficult to assess the health of the equipment, which ultimately leads to the inability to accurately reflect the health of the equipment. In response to this problem, the inventors thought of selecting some typical indicators that best reflect the quality of the equipment status, deleting relatively minor indicators; and then establishing a health evaluation model, combining the evaluation results of different indicators, and giving the final health evaluation of the equipment.

[0026] To this end, an embodiment of the present invention provides a method for evaluating the health of mechanical equipment, by which the accuracy and convenience of evaluating the health of different mechanical equipment can be improved based on the comprehensive evaluation of different indicators. The specific execution steps are as follows: Figure 1 As shown, including:

[0027] 101. Obtain test data based on preset operating monitoring parameters of the mechanical equipment to be evaluated.

[0028] Among them, the test data is the operating status data of the mechanical equipment to be evaluated; the mechanical equipment to be evaluated refers to the mechanical equipment that needs to be evaluated for health; the preset operation monitoring parameters are selected based on the performance parameters involved in the operation of the mechanical equipment, and the selected performance parameters are capable of reflecting the performance of the mechanical equipment, such as: vibration, temperature, flow, pressure, etc., which are not specifically limited in this embodiment; the various sensors provided on the mechanical equipment are used to collect data corresponding to the preset operation monitoring parameters as test data for evaluating the health of the mechanical equipment. It should be noted that the test data includes good status data and bad status data.

[0029] 102. Filter the test data using preset filtering rules to obtain target test data.

[0030] Test data for evaluating the health of mechanical equipment can be obtained from step 101. This step requires selecting target test data from the test data. The target test data can be selected from the test data based on pre-set high-correlation feature fields and used as input data for the subsequent preset trained HMM model, which can improve the accuracy of the health of the mechanical equipment.

[0031] Among them, HMM (English full name: Hidden Markov Model, Chinese full name: Hidden Markov Model) is a statistical model, which is used to describe a Markov process with hidden unknown parameters. The difficulty is to determine the hidden parameters of the process from the observable parameters. These parameters are then used for further analysis, such as pattern recognition.

[0032] 103. Based on the target test data, the preset trained HMM model is used to obtain the matching probability between the target test data and the preset trained HMM model, and the health of the mechanical equipment to be evaluated is obtained.

[0033] From step 102, the target test data for the preset trained HMM model can be obtained, and the target test data of the preset trained HMM model is used as the input data of the preset trained HMM model. Then, executing the preset trained HMM model will obtain the matching probability between the target test data and the preset trained HMM model, for example: 80%; the matching probability is used as the health degree of the mechanical equipment, for example: according to the matching probability of 80%, the health degree is 0.8.

[0034] Based on the above Figure 1 It can be seen from the implementation of the embodiment that the present invention provides a method for health assessment of mechanical equipment. The present invention obtains test data based on preset operation monitoring parameters of the mechanical equipment to be assessed, and the test data is the operating status data of the mechanical equipment to be assessed; the test data is screened using preset screening rules to obtain target test data; based on the target test data, a preset trained HMM model is used to obtain the matching probability between the target test data and the preset trained HMM model. The present invention can implement health assessment of different mechanical equipment to reduce manual dependence, and can also solve the problem of incomplete information capture by single monitoring information; by establishing a health assessment model, the assessment results of different indicators are integrated to give the final health evaluation of the mechanical equipment, thereby improving the accuracy and convenience of health assessment of different mechanical equipment.

[0035] Furthermore, as a Figure 1 The embodiment shown in the figure is refined and expanded. The embodiment of the present invention also provides another method for evaluating the health of mechanical equipment, such as Figure 2 As shown, the specific steps are as follows:

[0036] 201. Collect training data based on preset operating monitoring parameters of the mechanical equipment to be evaluated.

[0037] The training data is data showing that the mechanical equipment to be evaluated is running well; the training data is selected for training the preset HMM model, so the training data is data taken when the mechanical equipment is running well. For example, various sensors are used to collect various operating monitoring parameters of mechanical equipment, and the commonly used performance parameters include vibration, temperature, flow, pressure, rotation speed, speed, frequency multiplication, phase, etc., hundreds of them. Data in good running state are collected as training data.

[0038] 202. Based on the training data, the data to be selected for features is obtained using preset data preprocessing rules.

[0039] The data to be feature selected does not contain data with missing values, constant columns, and outliers.

[0040] The training data can be obtained from step 201, and then it is identified whether there are data containing missing values, constant columns and outliers in the training data; when the data containing missing values ​​and the constant column are identified from the training data, the data containing missing values ​​and the constant column are directly deleted; when the outlier is identified from the training data, it is determined whether the data density of the training data meets the preset conditions; if the data density of the training data meets the preset conditions, the outlier is directly deleted; if the data density of the training data does not meet the preset conditions, the outlier is replaced by linear interpolation using the nearest valid data before and after the outlier. Among them, the preset condition can be that the data density of the training data remains within a certain interval value; the purpose of setting the preset condition is to ensure that the data density of the training data after removing the outlier still meets the requirements for training the preset HMM model, which is not specifically limited in this embodiment.

[0041] For example:

[0042] Remove all data and constant columns containing missing values ​​in the training data, and then remove outliers. The method of removing outliers is as follows: in order to cope with the characteristics of different parameters, three different outlier identification methods (Raida method, box plot method, 4D test method) are provided. The outliers identified by the above identification methods are directly removed by default. However, if the data density needs to be maintained, the outliers are replaced by linear interpolation using the nearest valid data before and after the outliers. The data after the above processing is used as the data to be selected as the feature

[0043] 203. Based on the data to be feature selected, a target feature vector is obtained using a preset feature screening rule.

[0044] Wherein, the target feature vector is a high-correlation feature field.

[0045] The data to be feature selected can be obtained from step 202, and then the Spearman correlation coefficient is used to perform feature selection on the target data to be feature selected to obtain the target feature vector, specifically: based on the target data to be feature selected, the Spearman correlation coefficient matrix is ​​calculated and the high-correlation feature field is obtained by the connectivity analysis method; the high-correlation feature field is determined as the target feature vector for training the preset HMM model; and the high-correlation feature field is saved for screening the test data.

[0046] 204. Based on the target feature vector, the preset HMM model is trained using the Baum-Welch algorithm to obtain a preset trained HMM model.

[0047] The target feature vector can be obtained from step 203, and then the selected feature vector is used to train the HMM using the Baum-Welch algorithm to obtain a model (the preset trained HMM model of the present invention). It should be noted that a complete HMM includes a Markov chain and a general random process, mainly including five elements, 2 state sets and 3 probability matrices:

[0048] (1) The number of states of the Markov chain is N, where the N states are x1, x2, ... x N , the observed value at time t is q t , then q t ∈(x1,x2,...x N );

[0049] (2) The number of observations in each state is M, and the M observations are y1, y2, ...y M , the observed value at time t is Q t , then Q t ∈(y1,y2,...y M );

[0050] (3) Initial probability distribution matrix π, let N probability distributions be π1, π2, ...π N , then π∈(π1,π2,...π N );

[0051] (4) State transfer matrix A, A = (a ij ) N×N , where the state transition probability is: a ij =P(q t+1 =, x j |q t =x i ), 1≤i, j≤N.

[0052] (5) Observation probability matrix B, B = (b jk ) N×M , where the observation probability is b jk =P(Q t =y k |q t =x j ), 1≤j≤N, 1≤k≤M;

[0053] The model of HMM is λ=(N,M,π,A,B, simplified to λ=(π,A,B). The present invention uses the Baum-Welch algorithm to train the HMM and uses the forward-backward algorithm to calculate the health corresponding to the test data.

[0054] 205. Acquire test data based on preset operation monitoring parameters of the mechanical equipment to be evaluated.

[0055] This step is combined with the description of step 101 in the above method, and the same contents are not repeated here.

[0056] Among them, the test data is the operating status data of the mechanical equipment to be evaluated; the test data is the same as the training data in that the corresponding preset operating monitoring parameters and collection methods are consistent, and the difference is that the test data can be data of good operation of the mechanical equipment, or data of poor preset HMM model; while the training data can only be data of good operation of the mechanical equipment.

[0057] 206. Filter the test data using preset filtering rules to obtain target test data.

[0058] This step is combined with the description of step 102 in the above method, and the same contents are not repeated here.

[0059] The test data can be obtained from step 205, and the saved high-correlation feature fields can be obtained from step 203 for screening the training data. A large amount of collected test data of good or bad running status of mechanical equipment is screened according to the high-correlation fields selected by the features to obtain target test data.

[0060] 207. Based on the target test data, a preset trained HMM model is used to obtain a matching probability between the target test data and the preset trained HMM model, and the health of the mechanical equipment to be evaluated is obtained.

[0061] This step is combined with the description of step 103 in the above method, and the same contents are not repeated here.

[0062] The target test data can be obtained from step 205, and then the target test data is input into the preset trained HMM model, and the forward-backward algorithm is used to obtain the matching probability between the target test data and the preset trained HMM model, and then the health degree is obtained. The health degree takes a value between 0 and 1. The closer it is to 1, the healthier it is, and vice versa.

[0063] Furthermore, based on the target test data, after obtaining the matching probability between the target test data and the preset trained HMM model using the preset trained HMM model and obtaining the health of the mechanical equipment to be evaluated, the method further includes: monitoring whether the health of the mechanical equipment to be evaluated meets the early warning conditions; when the health of the mechanical equipment to be evaluated does not meet the early warning conditions, triggering an alarm. For example, if the health is less than 0.8, an alarm condition will be triggered, and an alarm will be issued. The alarm method can be sound or a prompt box, which is not specifically limited in this embodiment.

[0064] Based on the above Figure 2 It can be seen from the implementation method that the present invention provides a health assessment method for mechanical equipment. The invention can perform health assessment on different mechanical equipment to reduce manual dependence and solve the problem of incomplete information capture by single monitoring information. The present invention mainly solves two key problems: one is the selection of evaluation indicators. Some typical indicators that best reflect the quality of the equipment status should be selected as much as possible, and relatively minor indicators should be deleted (feature extraction and selection are performed using the Pearson correlation coefficient); the second is to establish a health assessment model, integrate the evaluation results of different indicators, and give the final health evaluation of the equipment.

[0065] Furthermore, as a response to the above Figure 1 In order to realize the method shown in the figure, the embodiment of the present invention also provides a device for evaluating the health of mechanical equipment, which is used to evaluate the health of the mechanical equipment. Figure 1 The device embodiment corresponds to the aforementioned method embodiment. For ease of reading, this device embodiment will not repeat the details of the aforementioned method embodiment one by one, but it should be clear that the device in this embodiment can correspond to all the contents of the aforementioned method embodiment. Figure 3 As shown, the device comprises:

[0066] An acquisition unit 31 is used to acquire test data based on preset operation monitoring parameters of the mechanical equipment to be evaluated, wherein the test data is operation status data of the mechanical equipment to be evaluated;

[0067] A first screening unit 32, configured to screen the test data obtained from the acquisition unit 31 using a preset screening rule to obtain target test data;

[0068] The calculation unit 33 is used to obtain the matching probability between the target test data and the preset trained HMM model based on the target test data obtained from the screening unit 32, so as to obtain the health of the mechanical equipment to be evaluated.

[0069] Furthermore, as a response to the above Figure 2 In order to realize the method shown in the figure, the embodiment of the present invention also provides another device for evaluating the health of mechanical equipment, which is used to evaluate the health of the above-mentioned Figure 2 The device embodiment corresponds to the aforementioned method embodiment. For ease of reading, this device embodiment will not repeat the details of the aforementioned method embodiment one by one, but it should be clear that the device in this embodiment can correspond to all the contents of the aforementioned method embodiment. Figure 4 As shown, the device comprises:

[0070] An acquisition unit 31 is used to acquire test data based on preset operation monitoring parameters of the mechanical equipment to be evaluated, wherein the test data is operation status data of the mechanical equipment to be evaluated;

[0071] A first screening unit 32, configured to screen the test data obtained from the acquisition unit 31 using a preset screening rule to obtain target test data;

[0072] A calculation unit 33 is used to obtain the matching probability between the target test data and the preset trained HMM model obtained from the training unit 39 based on the target test data obtained from the screening unit 32, so as to obtain the health of the mechanical equipment to be evaluated;

[0073] A monitoring unit 34, used to monitor whether the health of the mechanical equipment to be evaluated obtained from the calculation unit 33 meets the warning condition;

[0074] The alarm unit 35 is used to trigger an alarm when the health status of the mechanical equipment to be evaluated obtained from the monitoring unit 34 does not meet the early warning condition.

[0075] A collection unit 36, configured to collect training data based on the preset operation monitoring parameters of the mechanical equipment to be evaluated, wherein the training data is data showing that the mechanical equipment to be evaluated operates well;

[0076] A feature selection unit 37 is used to obtain data to be selected based on the training data obtained from the acquisition unit 36 ​​by using a preset data preprocessing rule, wherein the data to be selected does not contain data with missing values, constant columns, and outliers;

[0077] A second screening unit 38 is used to obtain a target feature vector based on the data to be feature selected obtained from the feature selection unit 37 using a preset feature screening rule, wherein the target feature vector is a high-correlation feature field;

[0078] The training unit 39 is used to train a preset HMM model using a Baum-Welch algorithm based on the target feature vector obtained from the second screening unit 38 to obtain the preset trained HMM model.

[0079] Furthermore, the feature selection unit 37 includes:

[0080] An identification module 371 is used to identify whether there are data containing missing values, constant columns and outliers in the training data;

[0081] A first deleting module 372 is used for directly deleting the data containing missing values ​​and the constant column when the data containing missing values ​​and the constant column are identified from the training data obtained by the identifying module 371;

[0082] A judging module 373, configured to judge whether the data density of the training data meets a preset condition when the outlier is identified from the training data obtained by the identifying module 371;

[0083] A second deleting module 374, configured to directly delete outliers if the data density of the training data obtained from the judging module 373 meets a preset condition;

[0084] The replacement module 375 is used to replace the outlier by performing linear interpolation with the nearest valid data before and after the outlier if the data density of the training data obtained from the judgment module 373 does not meet the preset conditions.

[0085] Furthermore, the second screening unit 38 is further used for:

[0086] The Spearman correlation coefficient is used to perform feature selection on the target data to be feature selected to obtain the target feature vector.

[0087] Furthermore, the second screening unit 38 includes:

[0088] An acquisition module 381 is used to calculate the Spearman correlation coefficient matrix based on the target feature selection data and obtain the high correlation feature field using a connectivity analysis method;

[0089] A determination module 382, ​​configured to determine the high-correlation feature field obtained from the acquisition module 381 as the target feature vector for training the preset HMM model;

[0090] The saving module 383 is used to save the high-correlation feature field obtained from the acquisition module 381 for screening the test data.

[0091] Furthermore, the calculation unit 33 is also used for:

[0092] The target test data is input into the preset trained HMM model, and the matching probability between the target test data and the preset trained HMM model is obtained using a forward-backward algorithm.

[0093] Furthermore, an embodiment of the present invention further provides a processor, the processor is used to run a program, wherein the program executes the above Figure 1-2 The health assessment method for mechanical equipment described in .

[0094] Furthermore, an embodiment of the present invention further provides a storage medium, wherein the storage medium is used to store a computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the above Figure 1-2 The health assessment method for mechanical equipment described in .

[0095] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0096] It is understandable that the related features in the above methods and devices can be referenced to each other. In addition, the "first", "second" and the like in the above embodiments are used to distinguish the embodiments, but do not represent the advantages and disadvantages of the embodiments.

[0097] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0098] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0099] In addition, the memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0100] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0101] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0102] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0104] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0105] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0106] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0107] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0108] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0109] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for evaluating the health of mechanical equipment, characterized in that: The method comprises: Acquiring test data based on preset operation monitoring parameters of the mechanical equipment to be evaluated, wherein the test data is operation status data of the mechanical equipment to be evaluated; Filtering the test data using preset filtering rules to obtain target test data; Based on the target test data, a preset trained HMM model is used to obtain a matching probability between the target test data and the preset trained HMM model, thereby obtaining the health of the mechanical equipment to be evaluated.

2. The method according to claim 1, characterized in that Before obtaining the test data, the method further includes: Collecting training data based on the preset operation monitoring parameters of the mechanical equipment to be evaluated, wherein the training data is data of good operation of the mechanical equipment to be evaluated; Based on the training data, using preset data preprocessing rules to obtain data to be selected as features, wherein the data to be selected as features does not contain data with missing values, constant columns, and outliers; Based on the data to be feature selected, a target feature vector is obtained using a preset feature screening rule, wherein the target feature vector is a high-correlation feature field; Based on the target feature vector, the preset HMM model is trained using the Baum-Welch algorithm to obtain the preset trained HMM model.

3. The method according to claim 2, characterized in that The step of obtaining the data to be selected based on the training data by using a preset data preprocessing rule includes: Identify whether there are data containing missing values, constant columns and outliers in the training data; When the data containing missing values ​​and the constant column are identified from the training data, directly deleting the data containing missing values ​​and the constant column; When the outlier is identified from the training data, determining whether the data density of the training data meets a preset condition; If the data density of the training data meets the preset conditions, the outliers are directly deleted; If the data density of the training data does not meet the preset condition, the outlier is replaced by linear interpolation using the nearest valid data before and after the outlier.

4. The method according to claim 3, characterized in that The step of obtaining a target feature vector based on the data to be feature selected by using a preset feature screening rule includes: The Spearman correlation coefficient is used to perform feature selection on the target data to be feature selected to obtain the target feature vector.

5. The method according to claim 4, characterized in that The method of performing feature selection on the target data to be feature selected by using the Spearman correlation coefficient to obtain the target feature vector includes: Based on the target feature selection data, the Spearman correlation coefficient matrix is ​​calculated and the high correlation feature field is obtained by using the connectivity analysis method; Determine the high correlation feature field as the target feature vector for training the preset HMM model; The high-correlation feature fields are saved for use in screening the test data.

6. The method according to any one of claims 1 to 5, characterized in that: The method of obtaining the matching probability between the target test data and the preset trained HMM model based on the target test data by using the preset trained HMM model includes: The target test data is input into the preset trained HMM model, and the matching probability between the target test data and the preset trained HMM model is obtained using a forward-backward algorithm.

7. The method according to claim 6, characterized in that After obtaining the health of the mechanical equipment to be evaluated by using a preset health evaluation rule based on the matching probability between the target test data and the preset trained HMM model, the method further includes: Monitor whether the health of the mechanical equipment to be evaluated meets the early warning conditions; When the health of the mechanical equipment to be evaluated does not meet the early warning conditions, an alarm is triggered.

8. A device for evaluating the health of mechanical equipment, characterized in that: include: An acquisition unit, configured to acquire test data based on preset operation monitoring parameters of the mechanical equipment to be evaluated, wherein the test data is operation status data of the mechanical equipment to be evaluated; A screening unit, configured to screen the test data using a preset screening rule to obtain target test data; The calculation unit is used to obtain the matching probability between the target test data and the preset trained HMM model based on the target test data, and obtain the health of the mechanical equipment to be evaluated.

9. A storage medium comprising a stored program, characterized in that: When the program is running, the device where the storage medium is located is controlled to execute the health assessment method for mechanical equipment as described in any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the health assessment method for mechanical equipment as described in any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Method and device for predicting health degree of underground coal mine system based on hidden Markov

    CN112257745A