Operation and maintenance monitoring method and device based on machine learning, equipment and medium

Abstract

The invention provides an operation and maintenance monitoring method and device based on machine learning, equipment and a medium, and relates to the technical field of intelligent manufacturing diagnosis, and the method comprises the steps: obtaining a parameter standard operation value of each parameter of monitored equipment; acquiring real-time operation data of each parameter of the equipment; and according to the parameter standard operation value of each parameter and the real-time operation data, determining an abnormal parameter. The method is used for solving the problem that in the prior art, the abnormality diagnosis result is inaccurate, and then the efficiency and reliability of intelligent manufacturing are affected, the abnormality can be accurately found by comparing the parameter standard operation value and the real-time operation data, misjudgment caused by the occasional situation that the operation data are affected by other data is avoided, the production process is optimized, and the production efficiency is improved. And the production efficiency and reliability are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing diagnosis technology, and in particular to an operation and maintenance monitoring method, device, equipment and medium based on machine learning. Background Art

[0002] With the advancement of technology, the application of machine vision in intelligent manufacturing is becoming more and more extensive. Its development trends include higher resolution, faster processing speed, stronger intelligence level and better integration capability. Especially in the field of intelligent manufacturing, machine vision plays an irreplaceable role.

[0003] However, in the related technology, when the various parameters of equipment operation are monitored in real time, since the various parameters are interrelated, when the operating parameters are affected by other data and occasionally become abnormal, the abnormality may trigger an abnormal alarm, resulting in inaccurate abnormal diagnosis results, thereby affecting the efficiency and reliability of intelligent manufacturing. Summary of the invention

[0004] The present invention provides an operation and maintenance monitoring method, device, equipment and medium based on machine learning, which are used to solve the problem that the results of abnormal diagnosis in the prior art are inaccurate, thereby affecting the efficiency and reliability of intelligent manufacturing.

[0005] The present invention provides an operation and maintenance monitoring method based on machine learning, comprising the following steps.

[0006] Obtain the standard operating value of each parameter of the monitored equipment; Get real-time operating data of each parameter of the equipment; Determine abnormal parameters based on the parameter standard operating value and real-time operating data of each parameter.

[0007] According to an operation and maintenance monitoring method based on machine learning provided by the present invention, a parameter standard operating value of each parameter of a monitored device is obtained, including: Get the historical operating values ​​of each parameter of the equipment; Based on the historical operating values ​​of each parameter, a parameter standard operating value of each parameter is determined.

[0008] According to an operation and maintenance monitoring method based on machine learning provided by the present invention, the historical operation value of each parameter of the equipment is obtained, including: Within a preset period, obtain the historical operating value of each parameter and the operating time corresponding to each historical operating value; Based on the historical operating values ​​of each parameter, the standard operating value of each parameter is determined, including: The parameter standard operating value corresponding to each parameter is determined based on the historical operating value of each parameter and the operating time corresponding to the historical operating value.

[0009] According to an operation and maintenance monitoring method based on machine learning provided by the present invention, a parameter standard operation value corresponding to each parameter is determined according to the historical operation value of each parameter and the operation duration corresponding to the historical operation value, including: According to the historical operating value of each parameter and the operating time corresponding to the historical operating value, the historical operating value with an operating time greater than a preset time is determined as the first historical value; and the parameter standard operating value corresponding to each parameter is determined based on the first historical value.

[0010] According to an operation and maintenance monitoring method based on machine learning provided by the present invention, a parameter standard operation value corresponding to each parameter is determined based on a first historical value, including: Based on the first historical value, the parameter standard operating value corresponding to each parameter is determined by the following formula: ; Wherein, W is the discrete value of the first historical value, a is the number of values ​​of the first historical value, Ep is the mean of the first historical value, Er is any value in the first historical value, and satisfies a≥r≥1.

[0011] According to an operation and maintenance monitoring method based on machine learning provided by the present invention, abnormal parameters are determined according to the standard operating value and real-time operating data of each parameter, including: According to the parameter standard operating value corresponding to each parameter, draw and generate the parameter operating baseline corresponding to each parameter; Generate a real-time operation curve based on the real-time operation data of each parameter; Based on the real-time operation curve and the parameter operation baseline corresponding to each parameter, the abnormal parameters are determined.

[0012] According to an operation and maintenance monitoring method based on machine learning provided by the present invention, based on a real-time operation curve and a parameter operation baseline corresponding to each parameter, abnormal parameters are determined, including: Determine the deviation domain value of each parameter based on the real-time operation curve and the parameter operation baseline corresponding to each parameter; Parameters whose deviation threshold is greater than a preset value are determined as abnormal parameters.

[0013] The present invention also provides an operation and maintenance monitoring device based on machine learning, comprising the following modules: A first acquisition module is used to acquire a parameter standard operating value of each parameter of the monitored device; The second acquisition module is used to obtain real-time operating data of each parameter of the equipment; The determination module is used to determine abnormal parameters according to the parameter standard operation value and real-time operation data of each parameter.

[0014] According to an operation and maintenance monitoring device based on machine learning provided by the present invention, the first acquisition module is specifically used for: Get the historical operating values ​​of each parameter of the equipment; Based on the historical operating values ​​of each parameter, a parameter standard operating value of each parameter is determined.

[0015] According to an operation and maintenance monitoring device based on machine learning provided by the present invention, the first acquisition module is specifically used for: Within a preset period, obtain the historical operating value of each parameter and the operating time corresponding to each historical operating value; Based on the historical operating values ​​of each parameter, the standard operating value of each parameter is determined, including: The parameter standard operating value corresponding to each parameter is determined based on the historical operating value of each parameter and the operating time corresponding to the historical operating value.

[0016] According to an operation and maintenance monitoring device based on machine learning provided by the present invention, the first acquisition module is specifically used for: According to the historical operating value of each parameter and the operating time corresponding to the historical operating value, the historical operating value with an operating time greater than a preset time is determined as the first historical value; and the parameter standard operating value corresponding to each parameter is determined based on the first historical value.

[0017] According to an operation and maintenance monitoring device based on machine learning provided by the present invention, the first acquisition module is specifically used for: Based on the first historical value, the parameter standard operating value corresponding to each parameter is determined by the following formula: ; Wherein, W is the discrete value of the first historical value, a is the number of values ​​of the first historical value, Ep is the mean of the first historical value, Er is any value in the first historical value, and satisfies a≥r≥1.

[0018] According to an operation and maintenance monitoring device based on machine learning provided by the present invention, the determination module is specifically used for: According to the parameter standard operating value corresponding to each parameter, draw and generate the parameter operating baseline corresponding to each parameter; Generate a real-time operation curve based on the real-time operation data of each parameter; Based on the real-time operation curve and the parameter operation baseline corresponding to each parameter, the abnormal parameters are determined.

[0019] According to an operation and maintenance monitoring device based on machine learning provided by the present invention, the determination module is specifically used for: Determine the deviation domain value of each parameter based on the real-time operation curve and the parameter operation baseline corresponding to each parameter; Parameters whose deviation threshold is greater than a preset value are determined as abnormal parameters.

[0020] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described operation and maintenance monitoring methods based on machine learning.

[0021] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned operation and maintenance monitoring methods based on machine learning.

[0022] The operation and maintenance monitoring method based on machine learning provided by the present invention first obtains the standard operating value of each parameter of the monitored equipment, then obtains the real-time operating data of each parameter of the equipment, and finally determines the abnormal parameters according to the standard operating value of each parameter and the real-time operating data. It can accurately find the anomaly by comparing the standard operating value of the parameter and the real-time operating data, avoid misjudgment caused by the occasional influence of other data on the operating data, and thus optimize the production process and improve production efficiency and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 It is a flow chart of the operation and maintenance monitoring method based on machine learning provided by the present invention.

[0025] Figure 2 It is a schematic diagram of the principle of the deviation threshold provided by the present invention.

[0026] Figure 3 It is a structural schematic diagram of the operation and maintenance monitoring device based on machine learning provided by the present invention.

[0027] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] With the advancement of technology, the application of machine vision in intelligent manufacturing is becoming more and more extensive. Its development trends include higher resolution, faster processing speed, stronger intelligence level and better integration capability. Especially in the field of intelligent manufacturing, machine vision plays an irreplaceable role. Specific applications include product detection and classification, program control and optimization, and intelligent sorting. For example, by detecting and analyzing product appearance, size, shape and other features, machine vision can realize automatic detection, classification and statistics of products, avoid manual repetitive labor, and improve production efficiency. At the same time, machine vision can also help smart factories complete automatic detection links, and intelligently control the processing flow or optimize the operation status of the production line based on the detection data; However, in the related technology, when the various parameters of equipment operation are monitored in real time, since the various parameters are interrelated, when the operating parameters are affected by other data and occasionally become abnormal, the abnormality may trigger an abnormal alarm, resulting in inaccurate abnormal diagnosis results, thereby affecting the efficiency and reliability of intelligent manufacturing.

[0030] Therefore, there is an urgent need for an operation and maintenance monitoring method based on machine learning to solve the above problems.

[0031] Combine the following Figure 1-Figure 4 The present invention describes the operation and maintenance monitoring method, device, equipment and medium based on machine learning.

[0032] Figure 1 is one of the flow charts of the operation and maintenance monitoring method based on machine learning provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 101: Obtain the standard operating value of each parameter of the monitored equipment.

[0033] During the specific implementation, the standard operating value of the parameter corresponding to each parameter of the manufacturing equipment is obtained. Specifically, the historical operating data of each parameter of the manufacturing equipment is first obtained, and then the standard operating value of the parameter is determined based on the historical operating data. After obtaining the historical operating data of each parameter of the manufacturing equipment, the data can also be preprocessed. The historical operating data includes historical operating values ​​and the operating time corresponding to the historical operating values. The preprocessing operation includes cleaning data, removing noise and outliers, etc., to ensure the quality of the historical operating data and facilitate accurate analysis of the historical operating data at a later time. It should be noted that the various parameters include but are not limited to key parameters such as temperature, pressure, and vibration. The parameters obtained vary according to the type of manufacturing equipment, and the embodiments of the present invention do not limit this.

[0034] For any parameter, first obtain the historical operation value of the parameter within the preset period T days and the operation time corresponding to each historical operation value, then analyze the historical operation value and the operation time corresponding to each historical operation value, and obtain the parameter standard operation value corresponding to the parameter according to the analysis result. It should be noted that the value of the preset period T can be set according to the needs, and the embodiment of the present invention does not limit this. In this step, the historical operation values ​​of the parameter within the preset period T days are marked as Bi, where i refers to the number of historical operation values, and the operation time corresponding to each historical operation value is marked as Ci, i≥1, and then the historical operation values ​​Ea that meet the preset conditions are selected from each historical operation value, Ea is analyzed, and the parameter standard operation value F1 corresponding to the parameter is obtained according to the analysis result. The preset screening condition here is specifically: the historical operation value with a running time greater than the preset time t1 is retained and marked as the first historical value Ea, and the historical operation value with a running time less than or equal to the preset time t1 is deleted, where the specific value of the preset time t1 is 90 seconds.

[0035] Through the discrete value formula The discrete value W of the first historical value Ea is calculated, where a is the number of values ​​of the first historical value, Ep is the mean of the first historical value, and Er is any value in the first historical value. When W is less than or equal to the preset value Y1, the mean Ep of Ea is used as the parameter standard operating value F1 corresponding to the parameter; when W is greater than Y1, the corresponding Er values ​​are deleted in descending order according to |Er-Ep| until W is less than or equal to the preset value Y1, and the number of deleted Er is marked as b, Er is any value in Ea, and satisfies a≥r≥1.

[0036] When b / a>θ1, the average of the maximum and minimum values ​​in Ea is taken as the parameter standard operating value F1 corresponding to the parameter, that is, through the formula , obtain the parameter standard operating value F1 corresponding to the parameter, where E max is the maximum value in E, E min is the minimum value in Ea. When b / a≤θ1, the average value of the remaining Ea that has not been deleted is used as the parameter standard operating value F1 corresponding to the parameter, where Y is a preset value and θ1 is a preset proportional coefficient. The specific value can be set according to actual needs. The embodiment of the present invention does not limit this. In one example, θ1=0.682. The above method is performed for each parameter to finally obtain the parameter standard operating value Fj corresponding to each parameter of the manufacturing equipment, where j is the number of parameters corresponding to the manufacturing equipment, and j≥1.

[0037] In this step, the historical operating values ​​and parameter standard operating values ​​corresponding to each parameter of the manufacturing equipment can also be comprehensively analyzed, and the standard deviation values ​​corresponding to each parameter of the manufacturing equipment can be obtained according to the analysis results. Specifically, for any parameter, the historical operating values ​​Ea that meet the preset conditions are selected from the various historical operating values ​​of the parameter, and then the absolute value of the difference between each historical operating value Ea and the parameter standard operating value Fj corresponding to the parameter is calculated, and marked as Hj, that is, through Hj=|Ea-Fj|, Hj is averaged and the standard deviation value G1 corresponding to the parameter is obtained. The above method is performed for each parameter, and finally the standard deviation value Gj corresponding to each parameter of the manufacturing equipment is obtained.

[0038] Step 102: Acquire real-time operating data of each parameter of the device.

[0039] In specific implementation, various monitoring sensors are used to obtain the real-time operation data corresponding to each parameter of the manufacturing equipment in its corresponding monitoring period. For any parameter, the monitoring period of the parameter is marked as V1, and the real-time monitoring data of the parameter in the monitoring period V1 is obtained, as well as the monitoring time corresponding to each real-time monitoring value, that is, the time when the real-time monitoring value appears.

[0040] For the confirmation of the monitoring period, the total value of the operation time corresponding to the historical operation values ​​Ea of each parameter that meets the preset conditions is taken, and it is used as the monitoring period V1 corresponding to the target parameter. The above method is performed for each parameter to finally obtain the monitoring period Vj corresponding to each parameter of the manufacturing equipment.

[0041] By analyzing the historical operating values ​​corresponding to various parameters of the manufacturing equipment and the operating time corresponding to each historical operating value, the monitoring time corresponding to various parameters of the manufacturing equipment can be obtained, and then the various parameters of the manufacturing equipment can be accurately monitored, so as to improve the operation and maintenance effect of the intelligent manufacturing diagnosis platform.

[0042] Step 103: Determine abnormal parameters according to the standard operating value of each parameter and the real-time operating data.

[0043] In the specific implementation, the standard operating value of the parameter is first used to draw the parameter operating baseline corresponding to each parameter. At the same time, a real-time operating curve is generated according to the real-time operating data of each parameter. Finally, the abnormal parameters are determined based on the parameter operating baseline and the real-time operating curve.

[0044] Specifically, when drawing the parameter operation baseline, the standard operating values ​​of the parameters corresponding to each parameter of the manufacturing equipment are used as the vertical coordinate, and a horizontal straight line parallel to the horizontal coordinate line is drawn in the two-dimensional coordinate system to obtain the parameter operation baseline corresponding to each parameter of the manufacturing equipment.

[0045] When generating a real-time operation curve, step 102 is still used, and the real-time monitoring value of the parameter in the monitoring period V1 is marked as Rc, and each real-time monitoring value marked as Rc is obtained from the standard deviation value Gj, and the standard deviation value G1 of the parameter, and the absolute value of the difference Qc between them, that is, through Qc=|Rc-Qc|, where c is the number of real-time monitoring values ​​of the parameter in the monitoring period V1, c≥1; then the real-time monitoring value whose absolute value of the difference Qc is greater than the preset value Y2 is marked as Rb, where b is the number of real-time monitoring values ​​that satisfy Qc>Y2, c≥b≥1, and the specific value of Y2 can be set according to actual needs, and the embodiment of the present invention does not limit this. Then the monitoring time corresponding to each real-time monitoring value Rb of the parameter is marked as Jb, and the monitoring time Jb is used as the horizontal coordinate, and each real-time monitoring value Rb of the parameter is used as the vertical coordinate to draw the real-time operation curve corresponding to the parameter.

[0046] When determining abnormal parameters according to the parameter operation baseline and the real-time operation curve, the deviation domain value of each parameter is determined based on the real-time operation curve and the parameter operation baseline corresponding to each parameter, and then the parameter whose deviation threshold is greater than the preset value is determined as an abnormal parameter. Specifically, Figure 2 As shown in FIG. 1 , it is a schematic diagram of the principle of parameter operation baseline, real-time operation curve and deviation threshold. For any parameter, firstly, the total value of the horizontal axis length corresponding to the deviation between the real-time operation curve of the parameter and the corresponding parameter operation baseline in the monitoring period V1 is calculated, and it is marked as L1. Then, the vertical axis value corresponding to each deviation between the real-time operation curve and the corresponding parameter operation baseline in the monitoring period V1 is determined, and it is marked as K. f In this embodiment, K fPerform averaging to obtain its mean value Kp, and then calculate the deviation threshold Z1 corresponding to the parameter through the formula Z1=(L1×Kp) / 2, where f is the number of deviations between the real-time operation curve and its corresponding parameter operation baseline during the monitoring period, and f≥1. The above method is performed for each parameter, and finally the deviation threshold Zj corresponding to each parameter of the manufacturing equipment is obtained, and then the parameter corresponding to the deviation threshold Zj greater than the preset value Y3 is marked as an abnormal parameter. Y3 can be set according to actual needs, and the embodiment of the present invention does not limit this.

[0047] By using the method disclosed in the embodiment of the present invention, a comprehensive analysis is performed on the historical operating values ​​and the standard operating values ​​of the parameters corresponding to the various parameters of the manufacturing equipment, and the standard deviation values ​​corresponding to the various parameters of the manufacturing equipment are obtained according to the analysis results. According to the standard operating values ​​of the parameters corresponding to the various parameters of the manufacturing equipment, the parameter operating baselines corresponding to the various parameters of the manufacturing equipment are generated and drawn, and the deviation thresholds between the real-time operating curves of the various parameters of the manufacturing equipment and the corresponding parameter operating baselines are obtained. The deviation thresholds are analyzed to determine the abnormal parameters, so as to avoid the occasional abnormality of the operating data due to the influence of other data, which may cause misjudgment.

[0048] The operation and maintenance monitoring device based on machine learning provided by the present invention is described below. The operation and maintenance monitoring device based on machine learning described below and the operation and maintenance monitoring method based on machine learning described above can be referenced to each other.

[0049] like Figure 3 As shown, the operation and maintenance monitoring device 300 based on machine learning provided by the present invention includes the following modules: The first acquisition module 301 is used to obtain the parameter standard operation value of each parameter of the monitored device; The second acquisition module 302 is used to acquire real-time operation data of each parameter of the device; The determination module 303 is used to determine the abnormal parameter according to the parameter standard operation value and the real-time operation data of each parameter.

[0050] According to an operation and maintenance monitoring device based on machine learning provided by the present invention, the first acquisition module 301 is specifically used for: Get the historical operating values ​​of each parameter of the equipment; Based on the historical operating values ​​of each parameter, a parameter standard operating value of each parameter is determined.

[0051] According to an operation and maintenance monitoring device based on machine learning provided by the present invention, the first acquisition module 301 is specifically used for: Within a preset period, obtain the historical operating value of each parameter and the operating time corresponding to each historical operating value; Based on the historical operating values ​​of each parameter, the standard operating value of each parameter is determined, including: The parameter standard operating value corresponding to each parameter is determined based on the historical operating value of each parameter and the operating time corresponding to the historical operating value.

[0052] According to an operation and maintenance monitoring device based on machine learning provided by the present invention, the first acquisition module 301 is specifically used for: According to the historical operating value of each parameter and the operating time corresponding to the historical operating value, the historical operating value with an operating time greater than a preset time is determined as the first historical value; and the parameter standard operating value corresponding to each parameter is determined based on the first historical value.

[0053] According to an operation and maintenance monitoring device based on machine learning provided by the present invention, the first acquisition module 301 is specifically used for: Based on the first historical value, the parameter standard operating value corresponding to each parameter is determined by the following formula: ; Wherein, W is the discrete value of the first historical value, a is the number of values ​​of the first historical value, Ep is the mean of the first historical value, Er is any value in the first historical value, and satisfies a≥r≥1.

[0054] According to an operation and maintenance monitoring device based on machine learning provided by the present invention, the determination module 303 is specifically used for: According to the parameter standard operating value corresponding to each parameter, draw and generate the parameter operating baseline corresponding to each parameter; Generate a real-time operation curve based on the real-time operation data of each parameter; Based on the real-time operation curve and the parameter operation baseline corresponding to each parameter, the abnormal parameters are determined.

[0055] According to an operation and maintenance monitoring device based on machine learning provided by the present invention, the determination module 303 is specifically used for: Determine the deviation domain value of each parameter based on the real-time operation curve and the parameter operation baseline corresponding to each parameter; Parameters whose deviation threshold is greater than a preset value are determined as abnormal parameters.

[0056] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4As shown, the electronic device may include: a processor 410, a communications interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communications interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the operation and maintenance monitoring method based on machine learning, and the method includes: Obtain the standard operating value of each parameter of the monitored equipment; Get real-time operating data of each parameter of the equipment; Determine abnormal parameters based on the parameter standard operating value and real-time operating data of each parameter.

[0057] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0058] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can execute the operation and maintenance monitoring method based on machine learning provided by the above methods, the method comprising: Obtain the standard operating value of each parameter of the monitored equipment; Get real-time operating data of each parameter of the equipment; Determine abnormal parameters based on the parameter standard operating value and real-time operating data of each parameter.

[0059] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the operation and maintenance monitoring method based on machine learning provided by the above methods, the method comprising: Obtain the standard operating value of each parameter of the monitored equipment; Get real-time operating data of each parameter of the equipment; Determine abnormal parameters based on the parameter standard operating value and real-time operating data of each parameter.

[0060] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0061] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A machine learning-based operation and maintenance monitoring method, characterized in that: The method comprises: Obtain the standard operating value of each parameter of the monitored equipment; Acquire real-time operating data of each of the parameters of the device; Abnormal parameters are determined based on the parameter standard operating value and the real-time operating data of each parameter.

2. The operation and maintenance monitoring method based on machine learning according to claim 1, characterized in that: The step of obtaining the standard operating value of each parameter of the monitored device includes: Obtaining a historical operating value of each parameter of the device; Based on the historical operating value of each of the parameters, a parameter standard operating value of each of the parameters is determined.

3. The operation and maintenance monitoring method based on machine learning according to claim 2 is characterized in that: The obtaining of the historical operating value of each parameter of the device includes: Within a preset period, obtaining a historical operating value of each of the parameters and an operating time corresponding to each historical operating value; Then, determining the parameter standard operating value of each parameter based on the historical operating value of each parameter includes: According to the historical operating value of each parameter and the operating time corresponding to the historical operating value, the parameter standard operating value corresponding to each parameter is determined.

4. The operation and maintenance monitoring method based on machine learning according to claim 3 is characterized in that: Determining the parameter standard operation value corresponding to each parameter according to the historical operation value of each parameter and the operation duration corresponding to the historical operation value includes: According to the historical operating value of each parameter and the operating time corresponding to the historical operating value, the historical operating value whose operating time is greater than the preset time is determined as the first historical value; and the parameter standard operating value corresponding to each parameter is determined based on the first historical value.

5. The operation and maintenance monitoring method based on machine learning according to claim 4 is characterized in that: The determining, based on the first historical value, a parameter standard operating value corresponding to each of the parameters comprises: Based on the first historical value, the parameter standard operating value corresponding to each of the parameters is determined by the following formula: ； Wherein, W is the discrete value of the first historical value, a is the number of the first historical value, Ep is the mean of the first historical value, Er is any value in the first historical value, and satisfies a≥r≥1.

6. The operation and maintenance monitoring method based on machine learning according to claim 5, characterized in that: Determining abnormal parameters according to the parameter standard operating value and the real-time operating data of each parameter includes: According to the parameter standard operating value corresponding to each of the parameters, a parameter operating baseline corresponding to each of the parameters is drawn and generated; Generate a real-time operation curve according to the real-time operation data of each parameter; Abnormal parameters are determined based on the real-time operation curve and the parameter operation baseline corresponding to each of the parameters.

7. The operation and maintenance monitoring method based on machine learning according to claim 6, characterized in that: The determining of abnormal parameters based on the real-time operation curve and the parameter operation baseline corresponding to each parameter includes: Determine a deviation threshold value of each parameter based on the real-time operation curve and a parameter operation baseline corresponding to each parameter; The parameter whose deviation threshold is greater than a preset value is determined as an abnormal parameter.

8. An operation and maintenance monitoring device based on machine learning, characterized in that: include: A first acquisition module is used to acquire a parameter standard operating value of each parameter of the monitored device; A second acquisition module, used to acquire real-time operating data of each parameter of the device; A determination module is used to determine abnormal parameters according to the parameter standard operation value and the real-time operation data of each parameter.

9. 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 computer program, the operation and maintenance monitoring method based on machine learning as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the operation and maintenance monitoring method based on machine learning as described in any one of claims 1 to 7 is implemented.

Images