Equipment technology state evaluation method and system based on data driving

Abstract

The invention relates to the technical field of equipment technical state evaluation, in particular to an equipment technical state evaluation method and system based on data driving, and the method comprises the steps: S1, collecting equipment evaluation information; s2, processing the equipment evaluation information; s3, constructing an evaluation model according to the historical equipment evaluation information; s4, obtaining an evaluation level and a state parameter according to the evaluation model; s5, evaluating the evaluation level according to the actual state parameters every other sampling period; s6, performing distortion judgment on the evaluation level according to an evaluation result; s7, the evaluation level is optimized according to the distortion judgment result; step S8, adjusting the evaluation process according to the number of distortion times in the evaluation period; and S9, judging the adjustment effectiveness according to the adjusted distortion times, and correcting the evaluation model construction process according to a judgment result. The evaluation accuracy of the technical state of the equipment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment technical status evaluation, and in particular to a data-driven equipment technical status evaluation method and system. Background Art

[0002] Equipment technical status evaluation is to compare the technical capabilities, production capabilities, production efficiency and related technical quality standards of the equipment during use with the original given values ​​of the equipment, and use quantitative methods to reflect the degree of wear. This evaluation method can clearly show the current status of the equipment, so that managers can more accurately grasp the operating status of the equipment, so as to carry out targeted management and optimization, and help operation and maintenance personnel prevent equipment failures. Through regular inspection and evaluation of the equipment, abnormal phenomena and problems of the equipment can be discovered in time, and corresponding maintenance and care can be carried out to avoid production shutdowns and losses caused by equipment failures. Equipment technical status evaluation is of great significance for improving equipment management level, preventing equipment failures, determining reasonable maintenance plans, improving equipment efficiency and performance, and reducing production costs. Enterprises should attach importance to the evaluation of equipment technical status, strengthen the management and maintenance of equipment technical status, improve equipment reliability and production efficiency, and thus continuously improve the competitiveness of enterprises.

[0003] Chinese Patent Publication No.: CN115600350A discloses a data-driven dynamic risk assessment method, which belongs to the technical field of equipment status risk assessment. This method can be used to adjust parameters through a real-time dynamic risk assessment model according to the dynamic changes of the equipment to achieve a data-driven dynamic risk assessment technology; through this technology, the failure risk of the equipment and the probability of failure can be more accurately predicted, and the risk of the equipment can be estimated based on data. Compared with traditional RBI technology, it has an evaluation standard that is more in line with my country's equipment risk, and formulates reasonable and effective response measures in the form of an expert group. Especially for the petrochemical industry, timely discovery of failure risks can avoid oil or fuel leakage and reduce the occurrence of accidents. This scheme mainly evaluates the risks of petrochemical equipment in a dynamic process, does not conduct an overall evaluation of the technical status of the equipment, and does not evaluate and optimize the evaluation results. The evaluation accuracy of the technical status of the equipment is low. Summary of the invention

[0004] To this end, the present invention provides a data-driven equipment technical status evaluation method and system to overcome the problem of low accuracy in the evaluation of equipment technical status in the prior art.

[0005] To achieve the above objectives, on the one hand, the present invention provides a data-driven equipment technical status evaluation method, comprising:

[0006] Step S1, collecting data on equipment sensor information and equipment operation logs to obtain equipment evaluation information;

[0007] Step S2, processing the equipment evaluation information;

[0008] Step S3, constructing an evaluation model based on historical equipment evaluation information;

[0009] Step S4, obtaining evaluation level and state parameters according to the evaluation model;

[0010] Step S5, evaluating the evaluation level according to the actual state parameters every other sampling period;

[0011] Step S6, making a distortion judgment on the evaluation level according to the evaluation result;

[0012] Step S7, optimizing the evaluation level according to the distortion judgment result;

[0013] Step S8, adjusting the evaluation process according to the number of distortions within the evaluation period;

[0014] Step S9, judging the effectiveness of the adjustment according to the number of distortions after adjustment, and correcting the evaluation model building process according to the judgment result.

[0015] Furthermore, in the step S2, when processing the device evaluation information, the format of the device evaluation information is unified, the device evaluation information is time-aligned, and the data after the format is unified and time-aligned is supplemented.

[0016] Furthermore, in step S3, when constructing the evaluation model, 70% of the historical equipment evaluation information is randomly divided into a model training set, and 30% is randomly divided into a model test set. The model training set is input into the neural network model to train the neural network model, and the model test set is input into the trained neural network model for testing. When the accuracy of the test result reaches the preset accuracy, the neural network model is output as an evaluation model.

[0017] Furthermore, in step S4, the equipment evaluation information collected in real time is input into the evaluation model, and the evaluation level and state parameters are output.

[0018] Furthermore, in step S5, the actual state parameter is obtained every other sampling period, and the actual state parameter is compared with the state parameter, and the evaluation level is evaluated according to the comparison result, wherein:

[0019] When the actual state parameter is better than the state parameter, the evaluation level is evaluated as a low evaluation;

[0020] When the actual state parameter is consistent with the state parameter, the evaluation level is evaluated as an accurate evaluation;

[0021] When the actual state parameter is lower than the state parameter, the evaluation level is evaluated as a high evaluation.

[0022] Furthermore, in step S6, when performing distortion judgment, the state parameter difference R is obtained, and the state parameter difference R is compared with the preset state parameter difference R0, and the evaluation level is subjected to distortion judgment according to the comparison result, wherein:

[0023] When R≤R0, it is determined that the evaluation level is not distorted;

[0024] When R>R0, it is determined that the evaluation level is distorted.

[0025] Furthermore, in step S7, when optimizing the evaluation level, the evaluation level is optimized according to the distortion judgment result, wherein:

[0026] When the evaluation level is not distorted, the evaluation level is not optimized;

[0027] When the evaluation level is distorted, the evaluation level corresponding to the actual state parameter is obtained, and the evaluation level is optimized to the evaluation level corresponding to the actual state parameter.

[0028] Furthermore, in step S8, when the evaluation process is adjusted, the number of distortions n in the evaluation period is compared with the preset number of distortions n0, and the adjustment of the evaluation process is judged according to the comparison result, wherein:

[0029] When n≤n0, no adjustment is made to the evaluation process;

[0030] When n>n0, the evaluation process is adjusted, and the adjustment coefficient s is set, 0.89<s<0.97, and the preset state parameter difference R0 is adjusted according to the adjustment coefficient s. The adjusted preset state parameter difference is Rs0, and Rs0=s×R0 is set.

[0031] Furthermore, in step S9, when judging the effectiveness of the adjustment, the adjusted distortion times na are compared with the preset distortion times n0, and the effectiveness of the adjustment is judged according to the comparison result, wherein:

[0032] When na≤1.3×n0, the adjustment is determined to be effective;

[0033] When na>1.3×n0, the adjustment is judged to be invalid, and the evaluation model construction process is corrected. The equipment evaluation information corresponding to the evaluation level distortion is used as the model construction correction training set, and the evaluation model is trained according to the model construction correction training set.

[0034] On the other hand, the present invention also provides a data-driven equipment technical status evaluation system, comprising:

[0035] The data collection module is used to collect equipment sensor information and equipment operation logs to obtain equipment evaluation information;

[0036] An information processing module, used for processing equipment evaluation information;

[0037] A model building module, used to build an evaluation model based on historical equipment evaluation information;

[0038] Equipment evaluation module, used to obtain evaluation level and status parameters according to the evaluation model;

[0039] The result evaluation module is used to evaluate the evaluation level according to the actual state parameters every sampling period;

[0040] A distortion judgment module, used to make a distortion judgment on the evaluation level according to the evaluation result;

[0041] An evaluation optimization module, used to optimize the evaluation level according to the distortion judgment result;

[0042] An evaluation adjustment module, used to adjust the evaluation process according to the number of distortions within the evaluation cycle;

[0043] The model correction module is used to judge the effectiveness of the adjustment according to the number of distortions after adjustment, and to correct the evaluation model construction process according to the judgment result.

[0044] Compared with the prior art, the beneficial effects of the present invention are that the method collects data on the equipment sensor information and the equipment operation log through step S1 to obtain equipment evaluation information in a convenient collection manner, the method processes the equipment evaluation information through step S2 to facilitate subsequent evaluation of the equipment technical status according to the equipment evaluation information, the method constructs an evaluation model through step S3, and obtains the evaluation level and status parameters according to the evaluation model through step S4 to evaluate the equipment technical status in real time, thereby improving the equipment technical status evaluation efficiency, and the method evaluates the evaluation level according to the actual status parameters through step S5 to ensure The method improves the accuracy of the technical status evaluation results of the faulty equipment. The method judges the distortion of the evaluation level through step S6 to identify the distorted equipment technical status evaluation results. The method optimizes the evaluation level through step S7 to optimize the distorted equipment technical status evaluation results. The method adjusts the evaluation process through step S8 to adjust the evaluation intensity according to the number of distortions within the evaluation cycle. The method judges the effectiveness of the adjustment through step S9 to correct the evaluation model construction process according to the adjusted distortion number, thereby improving the accuracy of the evaluation model output results and further improving the evaluation accuracy of the equipment technical status. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 Schematic diagram of the process of the equipment technical status evaluation method based on data-driven in this embodiment;

[0046] Figure 2 Schematic diagram of the structure of the equipment technical status evaluation system based on data drive in this embodiment. DETAILED DESCRIPTION

[0047] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0048] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0049] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0050] See also Figure 1 As shown, it is a flow chart of the data-driven equipment technical status evaluation method of this embodiment, and the method includes:

[0051] Step S1, collecting data on equipment sensor information and equipment operation logs to obtain equipment evaluation information;

[0052] Step S2, processing the equipment evaluation information;

[0053] Step S3, constructing an evaluation model based on historical equipment evaluation information;

[0054] Step S4, obtaining evaluation level and state parameters according to the evaluation model;

[0055] Step S5, evaluating the evaluation level according to the actual state parameters every other sampling period;

[0056] Step S6, making a distortion judgment on the evaluation level according to the evaluation result;

[0057] Step S7, optimizing the evaluation level according to the distortion judgment result;

[0058] Step S8, adjusting the evaluation process according to the number of distortions within the evaluation period;

[0059] Step S9, judging the effectiveness of the adjustment according to the number of distortions after adjustment, and correcting the evaluation model building process according to the judgment result.

[0060] Specifically, the method is set in the equipment technical status evaluation system, and through the analysis and processing of the sensor information and equipment operation log collected by the Internet of Things technology, the real-time evaluation of the equipment technical status is realized according to the data with convenient collection method, the efficiency of the equipment technical status evaluation is improved, and the evaluation results are evaluated and optimized to further improve the evaluation accuracy of the equipment technical status. The method collects data from the equipment sensor information and the equipment operation log in step S1 to obtain the equipment evaluation information in a convenient collection manner. The method processes the equipment evaluation information in step S2 to facilitate the subsequent evaluation of the equipment technical status according to the equipment evaluation information. The method constructs an evaluation model in step S3, and obtains the evaluation level and status parameters according to the evaluation model in step S4 to evaluate the equipment technical status in real time. The method evaluates the technical status of the equipment, thereby improving the efficiency of the equipment technical status evaluation. The method evaluates the evaluation level according to the actual status parameters through step S5 to ensure the accuracy of the equipment technical status evaluation results. The method judges the distortion of the evaluation level through step S6 to identify the distorted equipment technical status evaluation results. The method optimizes the evaluation level through step S7 to optimize the distorted equipment technical status evaluation results. The method adjusts the evaluation process through step S8 to adjust the evaluation intensity according to the number of distortions within the evaluation cycle. The method judges the effectiveness of the adjustment through step S9 to correct the evaluation model construction process according to the adjusted distortion number, thereby improving the accuracy of the evaluation model output results and further improving the evaluation accuracy of the equipment technical status.

[0061] Specifically, in step S1, the device sensor information refers to the device operation information collected by the sensor set according to the working characteristics of the device. This embodiment does not limit the specific content of the device sensor information. Technical personnel in this field can freely set it according to actual conditions, and only need to meet the requirements for reflecting the technical status of the equipment. For example, when the device is a lathe, the sensor is installed on the shaft to collect the shaft speed and shaft temperature, and the collected information is used as the device sensor information. The device operation log refers to a document of information such as the device operation status, operating conditions, abnormal events, maintenance activities, etc. that occurs during the operation of the device and is recorded by the built-in system of the device. This embodiment does not limit the collection method of the device operation log. Technical personnel in this field can freely set it according to actual conditions, such as setting it to collect the device operation log by accessing the database where the device system log is stored.

[0062] Specifically, in step S2, when processing the device evaluation information, the format of the device evaluation information is unified, the device evaluation information is time-aligned, and the data after format unification and time alignment is supplemented.

[0063] It can be understood that the present embodiment does not limit the format unification method, and those skilled in the art can freely set it according to actual conditions, and only need to meet the unified requirements for data formats. For example, a preset format of device sensor information and device operation log can be set, and information of the device sensor information and device operation log can be intercepted according to the preset format, and the intercepted information can be used as device evaluation information after the format is unified. The present embodiment does not limit the time alignment method, and those skilled in the art can freely set it according to actual conditions, and only need to meet the processing requirements for data at the same time. For example, it can be set by obtaining the timestamp of the device sensor information and the device operation log, and the device sensor information and the device operation log with the same timestamp are used as a group of data. The present embodiment does not limit the data filling method, and those skilled in the art can freely set it according to actual conditions, and only need to meet the identification and supplement requirements for missing data. For example, it can be set to identify missing data for a group of data according to the preset format, and the position where there is no data in the preset format is used as missing data, and the device sensor information and the device operation log are re-intercepted to supplement the missing data.

[0064] Specifically, through step S2, the format of the equipment evaluation information is unified, time-aligned and gap-filled, so as to facilitate the evaluation of the equipment technical status based on the processed information and improve the accuracy of the equipment technical evaluation.

[0065] Specifically, in step S3, when constructing the evaluation model, 70% of the historical equipment evaluation information is randomly divided into a model training set, and 30% is randomly divided into a model test set. The model training set is input into the neural network model to train the neural network model, and the model test set is input into the trained neural network model for testing. When the accuracy of the test result reaches the preset accuracy, the neural network model is output as an evaluation model.

[0066] Specifically, the historical equipment evaluation information refers to the historical equipment sensor information, the historical equipment operation log and the corresponding evaluation level and state parameters. The evaluation level refers to the equipment technical status evaluation level obtained by evaluating the historical equipment sensor information and the historical equipment operation log. The state parameters refer to the state parameters that the equipment should have obtained by evaluating the historical equipment sensor information and the historical equipment operation log, including equipment accuracy, equipment performance and equipment response speed. This embodiment does not specifically limit the parameter content setting of the neural network model. Those skilled in the art can freely set it according to actual conditions, and only need to meet the requirements for model construction. For example, the neural network model can be set to a convolutional neural network model, and the loss function is a cross entropy function. The accuracy of the test result refers to the ratio of the amount of data whose output evaluation level and state parameters are consistent with the evaluation level and state parameters of the training set to the total amount of data in the training set when the test set is input into the trained neural network model for testing. This embodiment does not specifically limit the value of the preset accuracy rate. Those skilled in the art can freely set it according to actual conditions, and only need to meet the requirements for evaluation model construction. For example, the preset accuracy rate can be set to 95%.

[0067] Specifically, in step S4, the equipment evaluation information collected in real time is input into the evaluation model, and the evaluation level and state parameters are output.

[0068] Specifically, in step S5, the actual state parameter is obtained every other sampling period, and the actual state parameter is compared with the state parameter, and the evaluation level is evaluated according to the comparison result, wherein:

[0069] When the actual state parameter is better than the state parameter, the evaluation level is evaluated as a low evaluation;

[0070] When the actual state parameter is consistent with the state parameter, the evaluation level is evaluated as an accurate evaluation;

[0071] When the actual state parameter is lower than the state parameter, the evaluation level is evaluated as a high evaluation.

[0072] Specifically, the sampling period refers to the preset value of the interval period for sampling and evaluating the evaluation level. This embodiment does not limit the value of the sampling period, and those skilled in the art can freely set it according to actual conditions. However, it should be noted that the sampling period is smaller than the evaluation period, and the value of the evaluation period is more than ten times the sampling period. For example, the sampling period can be set to 1 day. The actual state parameters refer to the state parameters obtained by actually testing and measuring the equipment, such as equipment accuracy, equipment performance, and equipment response speed. This embodiment does not limit the method for obtaining the actual state parameters, and those skilled in the art can freely set it according to actual conditions. For example, the actual state parameters can be measured through experiments. The actual state parameters are better than the state parameters, which means that the actual state parameters are better than the numerical values ​​of the state parameters. For example, the equipment accuracy in the actual state parameters is 0.01, while the state parameters The device precision is 0.1, then the actual state parameter is better than the state parameter. The actual state parameter is lower than the state parameter means that the actual state parameter is worse than the state parameter in numerical value. For example, if the device precision in the actual state parameter is 0.1, and the device precision in the state parameter is 0.01, then the actual state parameter is worse than the state parameter in numerical value. This embodiment does not limit the comparison method between the actual state parameter and the state parameter. Those skilled in the art can freely set it according to actual conditions, as long as the evaluation requirements for the evaluation level are met. For example, it can be set that when comparing the device response speed v1 in the actual state parameter with the device response speed v2 in the state parameter, when v1<v2, it is determined that the actual state parameter is better than the state parameter, when v1=v2, it is determined that the actual state parameter is consistent with the state parameter, and when v1>v2, it is determined that the actual state parameter is lower than the state parameter.

[0073] Specifically, sampling evaluation is performed through step S5 to periodically monitor the evaluation model to ensure the accuracy of the evaluation model and to ensure that the evaluation model is authentic and accurate when outputting the evaluation level based on the real-time and conveniently collected data.

[0074] Specifically, in step S6, when performing distortion judgment, the state parameter difference R is obtained, and the state parameter difference R is compared with the preset state parameter difference R0, and the evaluation level is subjected to distortion judgment according to the comparison result, wherein:

[0075] When R≤R0, it is determined that the evaluation level is not distorted;

[0076] When R>R0, it is determined that the evaluation level is distorted.

[0077] Specifically, the state parameter difference refers to the numerical difference between the actual state parameter and the state parameter. This embodiment does not specifically limit the calculation process of the state parameter difference. Those skilled in the art can freely set it according to actual conditions. For example, the device response speed can be specified as the calculation parameter of the state parameter difference, and the device response speed v1 in the actual state parameter is subtracted from the device response speed v2 in the state parameter, and the obtained difference is used as the state parameter difference R. The preset state parameter difference refers to the preset value of the state parameter difference that reflects the distortion of the evaluation level. For example, when the device response speed is specified as the calculation parameter of the state parameter difference, the preset state parameter difference R0 can be set to 3s / time.

[0078] Specifically, in step S7, when optimizing the evaluation level, the evaluation level is optimized according to the distortion judgment result, wherein:

[0079] When the evaluation level is not distorted, the evaluation level is not optimized;

[0080] When the evaluation level is distorted, the evaluation level corresponding to the actual state parameter is obtained, and the evaluation level is optimized to the evaluation level corresponding to the actual state parameter.

[0081] Specifically, the evaluation level corresponding to the actual state parameter refers to the evaluation level set according to the actual state parameter. This embodiment does not limit the setting method of the correspondence between the actual state parameter and the evaluation level. Technical personnel in this field can freely set it according to actual conditions. It only needs to meet the need to set the evaluation level according to the actual state parameters. For example, the corresponding evaluation level of the equipment accuracy of 0.1 can be set to level 3, the corresponding evaluation level of the equipment accuracy of 0.01 can be set to level 2, and the corresponding evaluation level of the equipment accuracy of 0.001 can be set to level 1.

[0082] Specifically, in step S8, when adjusting the evaluation process, the number of distortions n in the evaluation period is compared with the preset number of distortions n0, and the adjustment of the evaluation process is judged according to the comparison result, wherein:

[0083] When n≤n0, no adjustment is made to the evaluation process;

[0084] When n>n0, the evaluation process is adjusted, and the adjustment coefficient s is set, 0.89<s<0.97, and the preset state parameter difference R0 is adjusted according to the adjustment coefficient s. The adjusted preset state parameter difference is Rs0, and Rs0=s×R0 is set.

[0085] Specifically, the number of distortions within the evaluation cycle refers to the number of times the evaluation level is distorted within the evaluation cycle, and the preset number of distortions refers to a preset value reflecting the number of distortions that need to be adjusted during the evaluation process, such as the preset number of distortions can be set to 3 times.

[0086] Specifically, the preset state parameter difference R0 is adjusted according to the adjustment coefficient s in step S8 to improve the evaluation accuracy requirement, thereby increasing the recognition strength of the distortion situation.

[0087] Specifically, in step S9, when judging the effectiveness of the adjustment, the adjusted distortion times na are compared with the preset distortion times n0, and the effectiveness of the adjustment is judged according to the comparison result, wherein:

[0088] When na≤1.3×n0, the adjustment is determined to be effective;

[0089] When na>1.3×n0, the adjustment is judged to be invalid, and the evaluation model construction process is corrected. The equipment evaluation information corresponding to the evaluation level distortion is used as the model construction correction training set, and the evaluation model is trained according to the model construction correction training set.

[0090] Specifically, the number of distortions after adjustment refers to the number of times the evaluation level is distorted within the evaluation cycle after the evaluation process is adjusted.

[0091] See also Figure 2 As shown, it is a structural schematic diagram of the equipment technical status evaluation system based on data drive in this embodiment, and the system includes:

[0092] The data collection module is used to collect equipment sensor information and equipment operation logs to obtain equipment evaluation information;

[0093] An information processing module, used for processing equipment evaluation information;

[0094] A model building module, used to build an evaluation model based on historical equipment evaluation information;

[0095] Equipment evaluation module, used to obtain evaluation level and status parameters according to the evaluation model;

[0096] The result evaluation module is used to evaluate the evaluation level according to the actual state parameters every sampling period;

[0097] A distortion judgment module, used to make a distortion judgment on the evaluation level according to the evaluation result;

[0098] An evaluation optimization module, used to optimize the evaluation level according to the distortion judgment result;

[0099] An evaluation adjustment module, used to adjust the evaluation process according to the number of distortions within the evaluation cycle;

[0100] The model correction module is used to judge the effectiveness of the adjustment according to the number of distortions after adjustment, and to correct the evaluation model construction process according to the judgment result.

[0101] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A data-driven equipment technical status evaluation method, characterized in that: include: Step S1, collecting data on equipment sensor information and equipment operation logs to obtain equipment evaluation information; Step S2, processing the equipment evaluation information; Step S3, constructing an evaluation model based on historical equipment evaluation information; Step S4, obtaining evaluation level and status parameters according to the evaluation model; Step S5, evaluating the evaluation level according to the actual state parameters every other sampling period; Step S6, judging the evaluation level according to the evaluation result; Step S7, optimizing the evaluation level according to the distortion judgment result; Step S8, adjusting the evaluation process according to the number of distortions within the evaluation period; Step S9, judging the effectiveness of the adjustment according to the number of distortions after the adjustment, and correcting the evaluation model building process according to the judgment result.

2. The data-driven equipment technical status evaluation method according to claim 1 is characterized in that: In the step S2, when processing the device evaluation information, the format of the device evaluation information is unified, the device evaluation information is time-aligned, and the data after the format is unified and time-aligned is supplemented.

3. The data-driven equipment technical status evaluation method according to claim 1 is characterized in that: In step S3, when constructing the evaluation model, 70% of the historical equipment evaluation information is randomly divided into a model training set, and 30% is randomly divided into a model test set. The model training set is input into the neural network model to train the neural network model, and the model test set is input into the trained neural network model for testing. When the accuracy of the test result reaches the preset accuracy, the neural network model is output as an evaluation model.

4. The data-driven equipment technical status evaluation method according to claim 3 is characterized in that: In step S4, the equipment evaluation information collected in real time is input into the evaluation model, and the evaluation level and state parameters are output.

5. The data-driven equipment technical status evaluation method according to claim 4 is characterized in that: In step S5, the actual state parameter is obtained every other sampling period, and the actual state parameter is compared with the state parameter, and the evaluation level is evaluated according to the comparison result, wherein: When the actual state parameter is better than the state parameter, the evaluation level is evaluated as a low evaluation; When the actual state parameter is consistent with the state parameter, the evaluation level is evaluated as an accurate evaluation; When the actual state parameter is lower than the state parameter, the evaluation level is evaluated as a high evaluation.

6. The data-driven equipment technical status evaluation method according to claim 5 is characterized in that: In step S6, when performing distortion judgment, the state parameter difference R is obtained, and the state parameter difference R is compared with the preset state parameter difference R0, and the evaluation level is subjected to distortion judgment according to the comparison result, wherein: When R≤R0, it is determined that the evaluation level is not distorted; When R>R0, it is determined that the evaluation level is distorted.

7. The data-driven equipment technical status evaluation method according to claim 6 is characterized in that: In step S7, when optimizing the evaluation level, the evaluation level is optimized according to the distortion judgment result, wherein: When the evaluation level is not distorted, the evaluation level is not optimized; When the evaluation level is distorted, the evaluation level corresponding to the actual state parameter is obtained, and the evaluation level is optimized to the evaluation level corresponding to the actual state parameter.

8. The data-driven equipment technical status evaluation method according to claim 7 is characterized in that: In step S8, when adjusting the evaluation process, the number of distortions n in the evaluation period is compared with the preset number of distortions n0, and the adjustment of the evaluation process is judged according to the comparison result, wherein: When n≤n0, no adjustment is made to the evaluation process; When n>n0, the evaluation process is adjusted, and the adjustment coefficient s is set, 0.89<s<0.97, and the preset state parameter difference R0 is adjusted according to the adjustment coefficient s. The adjusted preset state parameter difference is Rs0, and Rs0=s×R0 is set.

9. The data-driven equipment technical status evaluation method according to claim 8 is characterized in that: In step S9, when judging the effectiveness of the adjustment, the adjusted distortion times na are compared with the preset distortion times n0, and the effectiveness of the adjustment is judged according to the comparison result, wherein: When na≤1.3×n0, the adjustment is determined to be effective; When na>1.3×n0, the adjustment is judged to be invalid, and the evaluation model construction process is corrected. The equipment evaluation information corresponding to the evaluation level distortion is used as the model construction correction training set, and the evaluation model is trained according to the model construction correction training set.

10. A system applied to the data-driven equipment technical status evaluation method according to any one of claims 1 to 9, characterized in that: include: The data collection module is used to collect equipment sensor information and equipment operation logs to obtain equipment evaluation information; An information processing module, used for processing equipment evaluation information; A model building module, used to build an evaluation model based on historical equipment evaluation information; Equipment evaluation module, used to obtain evaluation level and status parameters according to the evaluation model; The result evaluation module is used to evaluate the evaluation level according to the actual state parameters every sampling period; A distortion judgment module, used to make a distortion judgment on the evaluation level according to the evaluation result; An evaluation optimization module, used to optimize the evaluation level according to the distortion judgment result; An evaluation adjustment module, used to adjust the evaluation process according to the number of distortions within the evaluation cycle; The model correction module is used to judge the effectiveness of the adjustment according to the number of distortions after adjustment, and to correct the evaluation model construction process according to the judgment result.

Images