A metering device health state evaluation method, system and terminal

Abstract

The application relates to a metering equipment health state evaluation method and system and a terminal, and relates to the technical field of equipment health evaluation.The metering equipment information and current operation data of a pre-designed metering equipment are acquired; the current operation data is preprocessed to determine denoised operation data; historical operation data is acquired according to the metering equipment information and the denoised operation data; a preset health evaluation algorithm model is trained and updated according to the historical operation data, and the denoised operation data is input into the trained and updated health evaluation algorithm model for analysis to generate an equipment health index; the equipment health index is evaluated to determine the equipment health state; the equipment health state is uploaded to a preset master station, and early warning is performed according to the equipment health state and preset early warning information.The application has the effect of improving the operation and maintenance efficiency of metering equipment.

Description

Technical Field

[0001] This application relates to the technical field of equipment health assessment, and in particular to a method, system and terminal for assessing the health status of metering equipment. Background Technology

[0002] Equipment health assessment refers to the process of determining the health status of equipment by real-time monitoring of operating parameters such as current, voltage, and temperature during equipment operation, and by analyzing and diagnosing the data.

[0003] In related technologies, when assessing the health status of equipment, intelligent monitoring terminals are typically used to monitor operating parameters such as current, voltage, and temperature in real time, and upload the raw data to the main station. The health status of the equipment is then determined through further analysis and diagnosis by the backend system or by human intervention.

[0004] Regarding the aforementioned technologies, when assessing the health status of metering equipment, since the intelligent monitoring terminal only has data acquisition and uploading functions, the data needs to be further analyzed and diagnosed by the backend system or by personnel when uploading the data to the main station. This results in problems such as high data processing latency and delayed early warning response, leading to low maintenance efficiency of metering equipment and room for improvement. Summary of the Invention

[0005] To improve the operation and maintenance efficiency of metering equipment, this application provides a method, system, and terminal for assessing the health status of metering equipment.

[0006] Firstly, this application provides a method for assessing the health status of metering equipment, employing the following technical solution:

[0007] 1. A method for assessing the health status of metering equipment, comprising:

[0008] Obtain metering equipment information and current operating data of preset metering equipment;

[0009] Perform data preprocessing on the current running data to determine the noise reduction running data;

[0010] Historical operating data is obtained based on metering equipment information and noise reduction operation data;

[0011] The preset health assessment algorithm model is trained and updated based on historical operating data, and the denoised operating data is input into the trained and updated health assessment algorithm model for analysis to generate the equipment health index.

[0012] Assess equipment health indices to determine the equipment's health status;

[0013] The device health status is uploaded to the preset master station, and warnings are issued based on the device health status and preset warning information.

[0014] 2. Optionally, the steps for obtaining historical operating data based on metering equipment information and noise reduction operating data include:

[0015] Retrieve historical information from the database;

[0016] Based on the metering equipment information, search the historical information in the database to determine if there is information on the same type of equipment;

[0017] If it exists, then the same type of running data of the same type of device information in the database historical information will be identified as historical running data;

[0018] If not found, compare the historical database information with the metering equipment information to determine similar equipment information and reference equipment information;

[0019] Based on information about similar devices, search and identify similar operational data in the historical information of the database;

[0020] The denoised running data is extracted in time series to generate a running data sequence;

[0021] Deviation analysis is performed on the operational data sequence and information from similar devices to determine historical data deviations;

[0022] The reference equipment information is calibrated based on the deviation of historical data to determine the historical operating data.

[0023] 3. Optionally, the steps of comparing historical database information with metering equipment information to determine similar equipment information and reference equipment information include:

[0024] Information is extracted from historical database information and metering equipment information to determine the equipment operating environment and historical operating environment;

[0025] The similarity between the equipment's operating environment and its historical operating environment is compared to determine the environmental similarity.

[0026] Determine whether the environmental similarity is greater than a preset environmental similarity threshold;

[0027] If it is greater than that, then the historical database information corresponding to the historical operating environment is determined as usable historical information;

[0028] If it is not greater than, then the historical database information corresponding to the historical operating environment will be removed;

[0029] Analyze available historical information and metering equipment information to identify similar equipment and reference equipment.

[0030] 4. Optionally, the steps of analyzing available historical information and metering equipment information to determine similar equipment information and reference equipment information include:

[0031] Information is extracted from available historical information and metering equipment information to determine current core component information, historical core component information, current collaborative logic information, and historical collaborative logic information;

[0032] The similarity between current core component information and historical core component information is compared to determine the similarity of core components;

[0033] The similarity between the current collaborative logic information and the historical collaborative logic information is compared to determine the similarity of the logic information;

[0034] The similarity of core components and the similarity of logical information are weighted according to the preset component similarity ratio and the preset logical similarity ratio to determine the total historical similarity.

[0035] Available historical information with a total historical similarity greater than a preset total similarity threshold is identified as reference device information;

[0036] The available historical information with the highest total historical similarity is identified as similar device information.

[0037] 5. Optionally, the step of performing deviation analysis on the operating data sequence and information on similar equipment to determine historical data deviation includes:

[0038] Obtain the equipment temperature sequence, equipment load sequence, historical temperature sequence, and historical load sequence;

[0039] The deviations of the equipment temperature sequence, equipment load sequence, historical temperature sequence, and historical load sequence are weighted according to the preset load rate weight and the preset operating temperature weight to determine the operating condition similarity.

[0040] Determine whether the similarity of working conditions is less than the preset threshold for similarity of working conditions;

[0041] If it is less than, then similar operating data corresponding to the historical temperature sequence and historical load sequence will be removed;

[0042] If it is not less than, then the similar operating data corresponding to the historical temperature sequence and the historical load sequence are determined as operating data under the same working conditions;

[0043] Analyze operating data and operating data sequences under the same working conditions to determine the historical sequence in the same dimension;

[0044] Analyze the historical sequence and the running data sequence in the same dimension to determine the deviation of the historical data.

[0045] 6. Optionally, the steps of analyzing operating data and operating data sequences under the same operating conditions to determine the historical sequence of the same dimension include:

[0046] Obtain the time series of the same operating conditions and the running time series of the running data series;

[0047] Compare time series under the same operating conditions with running time series to determine covered time points, uncovered time points, and covered data points;

[0048] Determine the left and right adjacent time points in the same operating condition time series based on the uncovered time points;

[0049] Determine the left and right adjacent operating data based on the left and right adjacent time points in the same operating condition operating data;

[0050] Input the left adjacent time point, right adjacent time point, left adjacent running data, right adjacent running data, and uncovered time point into the preset linear interpolation model to determine the interpolation running data;

[0051] The coverage point data and interpolated running data are combined according to the running time series to determine the same-dimensional historical sequence.

[0052] 7. The steps for analyzing historical data sequences and running data sequences of the same dimension to determine historical data bias include:

[0053] Input the same-dimensional historical sequence and running data sequence into the preset least squares coefficient model to determine the polynomial fitting coefficients;

[0054] Input the running data sequence, polynomial fitting coefficients, and same-dimensional historical sequence into the preset polynomial fitting model to determine the deviation of the fitting data;

[0055] The deviations of the fitted data are arranged chronologically to determine the deviations of historical data.

[0056] Secondly, this application provides a health status assessment system for metering equipment, which adopts the following technical solution:

[0057] A health status assessment system for metering equipment, comprising:

[0058] The acquisition module is used to acquire metering equipment information, current operating data, and historical operating data;

[0059] A memory for storing a program for a method of assessing the health status of a metering device as described in any of the preceding claims;

[0060] The processor and the program in the memory can be loaded and executed by the processor to implement a method for assessing the health status of a metering device as described in any of the above.

[0061] Thirdly, this application provides a smart terminal, which adopts the following technical solution:

[0062] A smart terminal includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in any of the preceding claims for assessing the health status of a metering device.

[0063] In summary, this application includes at least one of the following beneficial technical effects:

[0064] 1. By preprocessing the current operating data, denoised operating data is obtained to ensure the validity of the operating data. Historical operating data is obtained based on the metering equipment information and the denoised operating data. The health assessment algorithm model is trained and updated based on the historical operating data. The denoised operating data is then input into the trained and updated health assessment algorithm model for analysis to generate the equipment health index. This ensures that the health assessment algorithm model is updated in real time, thereby improving the model's prediction accuracy. After determining the equipment health index, the equipment health index is converted into equipment health status according to the evaluation criteria. The equipment health status is then uploaded to the main station, and warnings are issued based on the corresponding warning information. This allows for real-time collection and evaluation of the equipment health status, thereby improving the operation and maintenance efficiency of metering equipment.

[0065] 2. By searching the historical database based on the metering equipment information, it is determined whether there is similar equipment. If so, it means that the health status assessment model can be updated using the historical operating data of similar equipment in the historical database. If not, it means that there is no operating data for the current type of equipment in the historical database. Therefore, by comparing the historical database information with the metering equipment information, similar equipment information is identified. Then, similar operating data is determined based on the similar equipment information. Finally, the reference equipment information is calibrated based on the deviation between the similar operating data and the operating data sequence to determine the historical operating data. Thus, the equipment health assessment model is updated based on the operating data of similar equipment, thereby improving the accuracy of the model.

[0066] 3. By comparing the time series under the same operating conditions with the running time series, the covered time points in the running time series that are covered by the running time series under the same operating conditions and the uncovered time points that are not covered by the running time series under the same operating conditions are determined. Then, the values ​​at the uncovered time points are supplemented by linear interpolation, so that the data is aligned with the running data series, thereby ensuring the accuracy of historical data deviation. Attached Figure Description

[0067] Figure 1 This is a flowchart of a method for assessing the health status of metering equipment according to an embodiment of this application.

[0068] Figure 2 This is a flowchart illustrating the process of obtaining historical operating data based on metering equipment information and noise reduction operating data in an embodiment of this application.

[0069] Figure 3This is a flowchart in this application embodiment that compares historical database information with metering equipment information to determine similar equipment information and reference equipment information.

[0070] Figure 4 This is a flowchart illustrating the analysis of available historical information and metering equipment information in this application embodiment to determine similar equipment information and reference equipment information.

[0071] Figure 5 This is a flowchart in this application embodiment that performs deviation analysis on the running data sequence and similar device information to determine the historical data deviation.

[0072] Figure 6 This is a flowchart in this application embodiment of analyzing operating data and operating data sequences under the same working conditions to determine the same-dimensional historical sequence.

[0073] Figure 7 This is a flowchart in this application embodiment that analyzes the same-dimensional historical sequence and the running data sequence to determine the historical data deviation. Detailed Implementation

[0074] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figures 1 to 7 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0075] This application discloses a method, system, and terminal for assessing the health status of metering equipment. Specifically, it discloses a processing terminal and a metering device, which are connected for communication to achieve data interaction and control. The processing terminal obtains metering equipment information and current operating data, performs data preprocessing on the current operating data to obtain denoised operating data, thereby ensuring the validity of the operating data. Historical operating data is obtained based on the metering equipment information and denoised operating data. The health assessment algorithm model is trained and updated based on the historical operating data, and the denoised operating data is input into the trained and updated health assessment algorithm model for analysis to generate an equipment health index. This ensures that the health assessment algorithm model is updated in real time, thereby improving the model's prediction accuracy. After determining the equipment health index, the equipment health index is converted into an equipment health status according to the assessment criteria. The equipment health status is then uploaded to the main station, and warnings are issued based on corresponding warning information.

[0076] Reference Figure 1 This application discloses a method for assessing the health status of metering equipment, comprising the following steps:

[0077] Step S100: Obtain the metering equipment information and current operating data of the preset metering equipment.

[0078] Measuring equipment refers to equipment that measures relevant data and converts the measured data into relevant quantitative measurement data results.

[0079] Metering equipment information refers to the basic attribute information of metering equipment, including equipment model, rated parameters and component composition, which is determined by the processing terminal by accessing the equipment information database of the metering equipment.

[0080] Current operating data refers to the full-cycle operating data of the metering equipment, including operating parameters such as current, voltage, and temperature. It is determined by the processing terminal by directly retrieving monitoring data from various sensors such as current, voltage, and temperature built into the metering equipment.

[0081] Step S101: Perform data preprocessing on the current running data to determine the noise reduction running data.

[0082] Denoising operation data refers to the metering equipment operation data after noise reduction processing. The data is determined by the processing terminal through extreme value elimination and smoothing filtering algorithms to denoise the current operation data, thereby improving the accuracy of the operation data, improving the efficiency of equipment health status assessment, and providing data support for the subsequent determination of equipment health index.

[0083] Step S102: Obtain historical operating data based on metering equipment information and noise reduction operation data.

[0084] Historical operating data refers to the operating data stored in the system for equipment of the same model or similar structure and operating conditions as the current measuring equipment to be tested. This data is determined by the processing terminal through analysis of the measuring equipment information and the denoised operating data. Specific analysis steps are detailed below. Figure 2 The steps in the process.

[0085] Step S103: Train and update the preset health assessment algorithm model based on historical operating data, and input the denoised operating data into the trained and updated health assessment algorithm model for analysis to generate the equipment health index.

[0086] Among them, the health assessment algorithm model refers to a model based on deep learning algorithms such as neural networks and degradation models. After the model is initially trained based on the equipment operation data, it is then trained and updated based on the operation data of similar or related equipment in the database to achieve the analysis of the denoised operation data and generate the equipment health index.

[0087] Equipment health index refers to a quantitative indicator of equipment health status. The processing terminal first inputs historical operating data into the health assessment algorithm model to train and update the model, thereby improving the accuracy of the assessment model. Then, the denoised operating data is input into the trained and updated health assessment algorithm model to realize real-time detection of equipment health index, thereby improving equipment operation and maintenance efficiency.

[0088] Step S104: Assess the equipment health index to determine the equipment health status.

[0089] Among them, equipment health status refers to the health status of the equipment, including normal status, fault status, etc. The processing terminal determines the equipment health status by analyzing the equipment health index and determining the health status range of the equipment health index.

[0090] Step S105: Upload the device health status to the preset master station, and issue an alert based on the device health status and preset alert information.

[0091] The main station refers to the core control and data management center of the entire monitoring system, which is responsible for receiving, storing, and analyzing the health status of the metering equipment.

[0092] Warning information refers to the information provided when equipment shows signs of potential malfunction and requires maintenance or repair by operators. Different warning information is provided for different types of malfunctions, and is delivered to operators in the form of voice signals or flashing signals.

[0093] Once the health status of the equipment is determined, the health status information is uploaded to the main station, which then sends the equipment health status to the display terminal. When the equipment health status is in a fault warning state or other pending state, the operator is given a real-time warning based on the warning information corresponding to the status, thereby improving the efficiency of equipment operation and maintenance.

[0094] Reference Figure 2 The steps for obtaining historical operating data based on metering equipment information and noise reduction operation data include:

[0095] Step S200: Obtain historical information from the database.

[0096] Among them, the database historical information refers to the basic equipment information of all devices stored in the database, as well as the historical operation information associated with the device model, which is determined by the processing terminal by directly retrieving the historical stored data in the database.

[0097] Step S201: Search the historical information in the database based on the metering equipment information to determine whether there is information on the same type of equipment.

[0098] Among them, the information on equipment of the same type refers to the basic attribute information of equipment of the same type as the metering equipment to be evaluated. The processing terminal determines this information by searching the historical information in the database based on the equipment type in the metering equipment information.

[0099] By processing the terminal to determine whether there is information on the same type of equipment with the same model as the metering equipment in the historical information of the database, the historical operating data can be determined based on the same type of equipment, thereby improving the accuracy of the health assessment model, and thus improving the accuracy of the health assessment of the metering equipment and improving the equipment operation and maintenance efficiency.

[0100] Step S2011: If it exists, then determine the same type of running data of the same type of device information in the database historical information as historical running data.

[0101] If the processing terminal determines that there is information about the same type of equipment in the historical information of the database, it indicates that there is a similar type of equipment in the historical database. Therefore, the same type of operating data is directly identified as historical operating data, and the health status of the current equipment is evaluated based on the operating data of the same type of equipment, thereby improving the accuracy of the health status evaluation of the metering equipment.

[0102] Similar operating data refers to the historical operating data of equipment with the same model as the metering equipment during operation, as well as the health assessment results corresponding to each historical operating data.

[0103] Step S2012: If not found, compare the historical database information with the metering equipment information to determine similar equipment information and reference equipment information.

[0104] If the processing terminal determines that there is no information on the same type of equipment in the historical information database, it indicates that there is no historical operating data for equipment with the same model as the metering equipment in the historical database. Therefore, by comparing the historical database information with the metering equipment information, similar equipment information and reference equipment information are determined, providing data support for the subsequent determination of historical operating data.

[0105] Similar equipment information refers to the basic equipment information of equipment that has similar operating conditions to the metering equipment and whose collaborative logic and core components have the highest similarity to the metering equipment. This information is determined by the processing terminal by comparing historical database information with the metering equipment information. Specific analysis steps are detailed below. Figure 3 The steps in the process.

[0106] Reference equipment information refers to historical operating data of equipment with a high degree of similarity to the metering equipment in terms of operating environment, core components, and collaborative logic. This information is determined by the processing terminal by comparing historical database information with the metering equipment information. The specific analysis steps refer to this information. Figure 3 The steps in this process provide data support for the subsequent determination of historical operational data.

[0107] Step S202: Based on the information of similar devices, search and determine similar operating data in the historical information of the database.

[0108] Among them, similar operating data refers to the operating data of the equipment corresponding to similar equipment information. The operating data is arranged in chronological order of relative operating time, and records data such as temperature and current during the operation of similar equipment, as well as the health status assessment results after data analysis. This provides data support for subsequent updates to the health equipment assessment model. The processing terminal determines the corresponding model of equipment by searching for the operating data of the equipment in the historical information of the database through similar equipment information.

[0109] Step S203: Perform time-series extraction on the denoised running data to generate a running data sequence.

[0110] Among them, the running data sequence refers to the metering equipment running data arranged according to the relative running time sequence. The processing terminal extracts and arranges the denoised running data according to the time sequence based on the relative running time sequence of the metering equipment, with the initial running time as 0.

[0111] Step S204: Perform deviation analysis on the running data sequence and similar equipment information to determine historical data deviation.

[0112] Historical data deviation refers to the discrepancy between the operating data of similar equipment and the actual operating data of the current metering equipment. This deviation is determined by the processing terminal through deviation analysis of the operating data sequence and information on similar equipment. Specific analysis steps are detailed below. Figure 5 The steps in the process.

[0113] Step S205: Calibrate the reference equipment information based on the historical data deviation to determine the historical operating data.

[0114] In this process, after determining the historical data deviation, the reference equipment information is calibrated based on the historical data deviation to determine the historical operating data, thereby improving the accuracy of the historical operating data and thus improving the efficiency of the health assessment of the metering equipment.

[0115] The historical operating data is consistent with the historical operating data in step S102. The processing terminal determines the same type of operating data as historical operating data when the same type of equipment information exists in the historical information of the database. When the same type of equipment information does not exist in the historical information of the database, the historical database is compared with the metering equipment information to determine similar equipment information and reference equipment information. The similar equipment information is then analyzed to determine the difference between the operating data of similar equipment and the current metering equipment. The reference equipment information is then corrected according to the difference to determine the historical operating information, thereby improving the accuracy of the health status assessment of the metering equipment.

[0116] Reference Figure 3The steps for comparing historical database information with metering equipment information to determine similar equipment information and reference equipment information include:

[0117] Step S300: Extract information from historical database information and metering equipment information to determine the equipment operating environment and historical operating environment.

[0118] Among them, the equipment operating environment refers to the operating environment of the metering equipment, including data such as ambient temperature, humidity, and dust level that are directly related to the operation of the equipment. This data is collected in real time by the processing terminal through the connection of the built-in or external environmental sensors of the equipment, or determined by receiving real-time environmental signals output by the equipment control unit.

[0119] Historical operating environment refers to the operating environment of the device in the database. It is determined by the processing terminal by retrieving historical environment collection records and associated operating logs from the database, combined with the device's unique identifier.

[0120] Step S301: Compare the similarity between the equipment operating environment and the historical operating environment to determine the environmental similarity.

[0121] Among them, environmental similarity refers to the similarity between the operating environment of the metering equipment and the operating environment of the equipment in the database. It is determined by the processing terminal through synchronously acquiring the current operating environment data of the equipment and retrieving the historical operating environment data in the database, and using cosine similarity or Euclidean distance algorithms to calculate the degree of matching between the two sets of multi-dimensional environmental parameters.

[0122] Step S302: Determine whether the environmental similarity is greater than the preset environmental similarity threshold.

[0123] Among them, the environmental similarity threshold refers to the lowest threshold of environmental similarity, which is used to identify equipment with a high degree of similarity between the operating environment and the metering equipment. It is manually set or dynamically adjusted by the operator in combination with the equipment operating characteristics, historical fault data and actual production needs.

[0124] By processing the terminal to determine whether the environmental similarity is greater than the environmental similarity threshold, historical operating data that highly matches the current operating environment is selected, providing a reliable reference for the accurate calculation of subsequent historical data deviations and the correction of reference equipment data, thereby improving the accuracy of metering equipment health assessment.

[0125] Step S3021: If it is greater than, then the historical database information corresponding to the historical operating environment is determined as usable historical information.

[0126] If the processing terminal determines that the environmental similarity between the current device and the current metering device is greater than the environmental similarity threshold, it indicates that the current operating environment is similar to the historical operating environment of the device. This eliminates the interference of environmental differences on the device's operating data. Therefore, the historical database information corresponding to the historical operating environment can reflect the operating characteristics of the device under the same external conditions, thus identifying it as usable historical information. This ensures the accuracy of subsequent historical data correction and provides accurate data support for the health assessment of metering devices.

[0127] Available historical information refers to equipment information whose operating environment is similar to that of the metering equipment. The processing terminal determines the equipment information by searching the historical database for the equipment corresponding to the historical operating environment after determining that the operating environment of the equipment is similar to that of the current metering equipment.

[0128] Step S3022: If it is not greater than, then remove the historical database information corresponding to the historical operating environment.

[0129] If the processing terminal determines that the environmental similarity between the current device and the current metering device is less than the environmental similarity threshold, it indicates that the current operating environment is not similar to the historical operating environment of the device and has no reference value. Therefore, the historical database information corresponding to the historical operating environment is removed to eliminate invalid interference caused by environmental differences, thereby avoiding the distortion of deviation calculation caused by environmental mismatch data and providing accurate and reliable data support for the health assessment of metering equipment.

[0130] Step S303: Analyze the available historical information and metering equipment information to determine similar equipment information and reference equipment information.

[0131] After determining the available historical information and metering equipment information, this information is analyzed to identify similar and reference equipment, providing data support for subsequent determination of historical operating data. Specific analysis steps are detailed below. Figure 4 The steps in the process.

[0132] Reference Figure 4 The steps for analyzing available historical information and metering equipment information to determine similar equipment information and reference equipment information include:

[0133] Step S400: Extract information from available historical information and metering equipment information to determine current core component information, historical core component information, current collaborative logic information, and historical collaborative logic information.

[0134] Among them, the current core component information refers to the core component information of the metering equipment to be evaluated, including the model specifications and rated operating parameters of the core components, which is determined by the processing terminal by extracting the metering equipment component information from the metering equipment information.

[0135] Historical component information refers to the core component information of the equipment corresponding to the available historical information, which is determined by the processing terminal by extracting the equipment component information from the available historical information.

[0136] The current collaborative logic information refers to the linkage logic between the core components and functional modules of the metering equipment to be evaluated. It is determined by the processing terminal through information extraction of linkage logic information from the metering equipment information.

[0137] Historical collaborative logic information refers to the linkage logic between core components and functional modules of the device corresponding to the available historical information, which is determined by the processing terminal through information extraction of linkage logic information in the available historical information.

[0138] Step S401: Compare the current core component information with the historical core component information to determine the similarity of the core components.

[0139] Among them, core component similarity refers to the degree of similarity between core components of devices. The processing terminal extracts multi-dimensional key information of current and historical core components, such as model specification matching degree, rated parameter deviation rate and cumulative runtime difference ratio, calculates the similarity score of each dimension, and obtains a comprehensive similarity value through dynamic weighted fusion to determine the similarity, which provides data support for subsequent determination of historical similarity.

[0140] Step S402: Compare the current collaborative logic information and the historical collaborative logic information to determine the similarity of the logic information.

[0141] Among them, logical information similarity refers to the degree of similarity of the collaborative logic between devices. It is determined by the processing terminal by extracting key feature dimensions of the current and historical collaborative logic, such as timing allocation instruction features and load allocation power features, and then calculating similarity scores for each dimension according to the feature matching degree algorithm and then weighted and fused.

[0142] Step S403: Weight the similarity of core components and the similarity of logical information according to the preset component similarity ratio and the preset logical similarity ratio to determine the total historical similarity.

[0143] Among them, the component similarity ratio refers to the proportion of the influence of the core component similarity on the total similarity between the core component similarity and the historical total similarity. It is determined by the operator in combination with the type of metering equipment, the critical influence of the core component on the overall performance of the equipment, and the proportion of the core component's contribution to failure in historical failure data.

[0144] The logical similarity ratio refers to the proportion of the influence of logical information similarity on the total similarity between core component similarity and historical total similarity. It is determined by the operator in combination with the type of metering equipment, the critical influence of logical information on the overall performance of the equipment, and the proportion of logical information's contribution to failure in historical failure data.

[0145] Historical total similarity refers to the overall similarity between the metering device and the device corresponding to the available historical information. The processing terminal weights the non-identical similarity and logical similarity according to the component similarity ratio and the logical similarity ratio, and then sums the weighted data to determine the total similarity. This weighted fusion of the two key similarity information based on the weights improves the accuracy of historical total similarity and enhances the efficiency of equipment operation and maintenance.

[0146] Step S404: Useful historical information with a total historical similarity greater than a preset total similarity threshold is identified as reference device information.

[0147] The total similarity threshold refers to the lowest historical total similarity standard value of the reference device, which is determined by the operator based on the application scenario of the metering device, the accuracy requirements of the health assessment, and feedback from the assessment data of similar historical devices.

[0148] The reference device information is consistent with the reference device information in step S2012. The processing terminal filters the available historical information according to the total similarity threshold, retains the available historical information with a total historical similarity greater than the total similarity threshold, and determines the retained available historical information as the reference device information.

[0149] Step S405: The available historical information with the highest total historical similarity is identified as similar device information.

[0150] The similar device information is consistent with the similar device information in step S2012. The processing terminal compares the historical total similarity, determines the maximum historical total similarity, and then determines the available historical information of all devices of the same model corresponding to the historical total similarity as similar device information.

[0151] Reference Figure 5 The steps for performing deviation analysis on operational data sequences and information from similar devices to determine historical data deviations include:

[0152] Step S500: Obtain the device temperature sequence, device load sequence, historical temperature sequence, and historical load sequence.

[0153] The equipment temperature sequence refers to the set of time-series temperature data of the current metering equipment being evaluated during its operating period. It is determined by the processing terminal by collecting real-time feedback signals from the equipment's temperature sensors and sorting them by timestamp.

[0154] The equipment load sequence refers to the set of load time-series data of the metering equipment to be evaluated during the current operating period. It is determined by the processing terminal by reading the real-time load parameters output by the equipment controller and integrating them in chronological order.

[0155] Historical temperature sequence refers to the set of temperature time series data of all devices of the same model corresponding to similar device information during the matching operation period. It is determined by the processing terminal by retrieving the associated historical temperature acquisition records in the database and filtering them according to the time dimension.

[0156] Historical load sequence refers to the set of load time sequence data of all devices of the same model corresponding to similar device information during the matching runtime period. It is determined by the processing terminal by querying the historical load logs stored in the database and combining them with the time range.

[0157] Step S501: Weight the deviations of the equipment temperature sequence, equipment load sequence, historical temperature sequence, and historical load sequence according to the preset load rate weight and the preset operating temperature weight to determine the operating condition similarity.

[0158] Among them, the load rate weight refers to the weight value of the degree of influence of the deviation between the equipment load sequence and the historical load sequence on the similarity of the working conditions. It is determined by the operator in combination with the load characteristics of the equipment and the load influence ratio of historical working condition data.

[0159] Operating temperature weight refers to the weight value of the degree of influence of the deviation between the equipment temperature series and the historical temperature series on the similarity of operating conditions. It is determined by the operator based on the equipment's sensitivity to temperature and the contribution ratio of temperature factors in historical failures.

[0160] Operating condition similarity refers to the degree of similarity between the operating conditions of all similar equipment of the same model and the current measuring equipment to be evaluated. It is determined by the processing terminal by first calculating the deviation values ​​between the equipment temperature sequence and the historical temperature sequence, and the deviation values ​​between the equipment load sequence and the historical load sequence, and then weighting the two types of deviation values ​​with operating condition temperature weight and load rate weight respectively, and finally normalizing the weighted deviation values.

[0161] Step S502: Determine whether the working condition similarity is less than the preset working condition similarity threshold.

[0162] Among them, the operating condition similarity threshold refers to the minimum limit of operating condition similarity, which is manually set or dynamically adjusted by the operator based on the operating condition sensitivity characteristics of the metering equipment, the accuracy requirements of health assessment for operating condition matching, the feedback of assessment results under similar historical operating conditions, and the industry's operating condition similarity judgment standards.

[0163] By processing the terminal to determine whether the operating condition similarity is less than the operating condition similarity threshold, the device with a high degree of operating condition similarity to the metering equipment is identified among all devices of the same model corresponding to similar operating data. This eliminates the influence of data with large operating condition differences on historical data deviations and improves the accuracy of health assessment of metering equipment.

[0164] Step S5021: If it is less than, then similar operating data corresponding to the historical temperature sequence and historical load sequence are removed.

[0165] If the processing terminal determines that the operating condition similarity is less than the operating condition similarity threshold, it indicates that the operating condition of the device is not very similar to that of the metering device. Therefore, the similar operating data corresponding to the historical temperature sequence and historical load sequence are removed, thereby eliminating the influence of devices with large operating condition differences on the deviation of historical data and improving the accuracy of historical data deviation.

[0166] Step S5022: If it is not less than, then the similar operating data corresponding to the historical temperature sequence and the historical load sequence are determined as operating data under the same operating conditions.

[0167] If the processing terminal determines that the operating condition similarity is not less than the operating condition similarity threshold, it indicates that the operating condition of the device is highly similar to that of the metering device. Therefore, the similar operating data corresponding to the historical temperature sequence and the historical load sequence are determined as operating data under the same operating condition, providing data support for the subsequent determination of historical data deviation.

[0168] Step S503: Analyze the operating data and operating data sequence under the same working conditions to determine the historical sequence in the same dimension.

[0169] Among them, the same-dimensional historical sequence refers to a historical data sequence that is consistent with the dimension of the running data sequence and is time-aligned. The processing terminal first extracts the dimensional features of the current running data sequence, then selects historical sequences with completely matching dimensional features from the available historical data after three rounds of filtering based on environmental similarity, total historical similarity, and operating condition similarity. Finally, missing data is filled in through linear interpolation, and precise time alignment is achieved based on timestamp calibration. For specific analysis steps, refer to [reference needed]. Figure 6 The steps in the process.

[0170] Step S504: Analyze the same-dimensional historical sequence and running data sequence to determine the historical data deviation.

[0171] Historical data deviation refers to the discrepancy between the operating data of similar equipment and the operating data of metering equipment. It is used to correct the reference equipment data, thereby improving the accuracy of historical operating data. This deviation is determined by the processing terminal through analysis of the same-dimensional historical sequence and the operating data sequence. Specific analysis steps are detailed below. Figure 7 The steps in the process.

[0172] Reference Figure 6 The steps for analyzing operating data and operating data sequences under the same working conditions to determine historical sequences in the same dimension include:

[0173] Step S600: Obtain the time series of the same operating conditions and the running time series of the running data series.

[0174] Among them, the same working condition time series refers to the relative time series of operating data under the same working condition. It is determined by the processing terminal by extracting the time period data of the same working condition operating data, marking the timestamp with the equipment start time as the zero point, and then sorting and integrating them in chronological order.

[0175] The operating time series refers to the relative time series of the operating data of metering equipment. It is determined by the processing terminal by extracting the time period data of the operating data series, marking the timestamp with the start time of the metering equipment as the zero point, and then sorting and integrating them in chronological order.

[0176] Step S601: Compare the time series under the same operating conditions with the running time series to determine the covered time points, uncovered time points, and covered point data.

[0177] The coverage time point refers to the time point in the running time series that coincides with the time series under the same operating conditions. The processing terminal determines the point where the time points are consistent by comparing the time series under the same operating conditions with the running time series.

[0178] Uncovered time points refer to time points in the running time series that do not coincide with time series under the same operating conditions, i.e., time points not covered by time series under the same operating conditions. After determining the covered time points, the processing terminal will determine the remaining time points in the running time series as uncovered time points.

[0179] Coverage point data refers to the operational data corresponding to the time point of coverage in the same operating condition data. It is determined by the processing terminal after determining the coverage time point, based on the search results of the same operating condition data.

[0180] Step S602: Determine the left and right adjacent time points in the same working condition time series based on the uncovered time points.

[0181] Among them, the left adjacent time point refers to the effective feature time point that is located to the left of the coverage time point and is closest to it in the same working condition time series. It is determined by the processing terminal by first locating the timestamp of the target coverage time point, and then selecting the time point in the same working condition time series that is smaller than the timestamp of the coverage time point and is closest to the timestamp of the coverage time point.

[0182] The right adjacent time point refers to the effective feature time point that is located to the right of the covered time point and is closest to it in the same working condition time series. It is determined by the processing terminal by first locating the timestamp of the target covered time point, and then selecting the time point in the same working condition time series that is greater than the timestamp of the covered time point and is closest to the timestamp of the covered time point. This provides data support for the subsequent determination of the same dimension historical series through linear interpolation.

[0183] Step S603: Determine the left adjacent running data and the right adjacent running data in the same operating condition running data based on the left adjacent time point and the right adjacent time point.

[0184] Among them, the left adjacent operating data refers to the operating data value corresponding to the left adjacent time point in the same operating condition operating data. It is determined by the processing terminal after determining the left adjacent time point, and then finding the operating data value at the point where the left adjacent time point is located in the same operating condition operating data.

[0185] The right adjacent operating data refers to the operating data value corresponding to the right neighboring time point in the same operating condition operating data. It is determined by the processing terminal after determining the right adjacent time point, and then searching for the operating data value at the point where the right adjacent time point is located in the same operating condition operating data.

[0186] Step S604: Input the left adjacent time point, right adjacent time point, left adjacent running data, right adjacent running data, and uncovered time point into the preset linear interpolation model to determine the interpolation running data.

[0187] Among them, the linear interpolation model refers to a mathematical model that estimates the value of running data at any uncovered time point between two known data points by constructing a linear function based on the running data of two known data points.

[0188] Interpolated running data refers to the running data values ​​at uncovered time points calculated by a linear interpolation model. This data is determined by the processing terminal by inputting the left adjacent time point, right adjacent time point, left adjacent running data, right adjacent running data, and uncovered time point into a preset linear interpolation model. The specific calculation formula is as follows:

[0189] .

[0190] In the formula, To interpolate the running data, For the left adjacent running data, For the right adjacent running data, For the uncovered time points, The left adjacent time point, For the right adjacent time point, linear interpolation is performed on the left adjacent and right adjacent operating data using the above formula to determine the interpolated operating data at the uncovered point between the two points. This constructs a complete and continuous time series set of operating data under the same working condition, eliminates the data breakage problem caused by uncovered time points, and ensures that the data sequence can fully reflect the complete operating status of the equipment under the target working condition, thereby improving the accuracy of the health assessment of the metering equipment and the reliability of the data support.

[0191] Step S605: Combine the coverage point data and interpolation running data according to the running time series to determine the same-dimensional historical sequence.

[0192] Among them, the same dimension historical sequence is consistent with the same dimension historical sequence in step S503. It is determined by the processing terminal after determining the coverage point data and interpolation running data, and then arranging and merging the coverage point data and interpolation running data according to the running time sequence.

[0193] Reference Figure 7 The steps for analyzing historical data sequences and running data sequences of the same dimension to determine historical data bias include:

[0194] Step S700: Input the same-dimensional historical sequence and running data sequence into the preset least squares coefficient model to determine the polynomial fitting coefficients.

[0195] The least squares coefficient model refers to the mathematical model that uses the least squares principle to solve for the optimal polynomial coefficients by minimizing the sum of squared fitting errors between the historical sequence and the running data sequence of the same dimension. It is used to quantify the nonlinear mapping relationship between two sets of sequences.

[0196] The polynomial fitting coefficients refer to the coefficients used to construct the polynomial fitting function between the historical sequence and the running data sequence of the same dimension. They are calculated and determined by the processing terminal by inputting the historical sequence and the running data sequence of the same dimension into the least squares coefficient model. The specific calculation formula is as follows:

[0197] .

[0198] In the formula, These are the polynomial fitting coefficients. As a historical sequence of the same dimension, To run the data sequence, the optimal polynomial coefficients that minimize the sum of squared fitting errors are solved using the above formula. This establishes a nonlinear quantitative relationship model between the historical sequence and the current running data sequence of the same dimension, providing a mathematical basis for subsequent calculation of the nonlinear deviation between the two sets of sequences and improving the accuracy of health assessment of metrology equipment.

[0199] Step S701: Input the running data sequence, polynomial fitting coefficients, and same-dimensional historical sequence into the preset polynomial fitting model to determine the fitting data deviation.

[0200] Among them, the polynomial fitting model refers to a mathematical model built on polynomial fitting coefficients, which is used to predict corresponding running data based on the same-dimensional historical sequence. Its core is to map the nonlinear relationship between the same-dimensional historical sequence and the running data sequence through a polynomial function, so as to provide a fitting benchmark for calculating the deviation between the two.

[0201] Fitting bias refers to the fitting deviation between each running data point in the same-dimensional historical sequence and its corresponding running data sequence. It is determined by the processing terminal by inputting the polynomial fitting coefficients and the same-dimensional historical sequence into the polynomial fitting model. The specific calculation formula is as follows:

[0202] .

[0203] In the formula, Let be the deviation of the i-th fitted data. For the i-th running data sequence, The fitting coefficients are those of the nth polynomial. For the i-th historical sequence of the same dimension, the fitting deviation between the historical sequence of the same dimension and the running data sequence is calculated point by point using the above formula, thereby quantifying the local differences between the two sets of sequences under the nonlinear mapping relationship and providing data support for the subsequent determination of historical running data.

[0204] Step S702: Arrange the deviations of the fitted data in time sequence to determine the deviations of historical data.

[0205] Among them, the historical data deviation is consistent with the historical data deviation in step S504. After the processing terminal determines the fitted data deviation, the fitted data deviation is integrated into a deviation sequence that corresponds one-to-one with the running data sequence according to the deviation order.

[0206] Based on the same inventive concept, embodiments of this application provide a health status assessment system for metering equipment, including:

[0207] The acquisition module is used to acquire metering equipment information, current operating data, historical operating data, database historical information, equipment temperature sequence, equipment load sequence, historical temperature sequence, historical load sequence, time series under the same operating conditions, and operating time series.

[0208] A memory for storing a program for assessing the health status of a metering device;

[0209] The processor can load and execute programs in memory to implement a method for assessing the health status of metering equipment.

[0210] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0211] Based on the same inventive concept, embodiments of this application provide a smart terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded and executed by the processor to perform a method for assessing the health status of a metering device.

[0212] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0213] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A method of metrology equipment health state assessment, characterized by, The method comprises the following steps: obtaining metering equipment information and current operation data of a pre-designed metering equipment; performing data preprocessing on the current operation data to determine denoised operation data; obtaining historical operation data according to the metering equipment information and the denoised operation data; training and updating a preset health assessment algorithm model according to the historical operation data, and inputting the denoised operation data into the trained and updated health assessment algorithm model for analysis to generate an equipment health index; evaluating the equipment health index to determine an equipment health state; uploading the equipment health state to a preset master station and performing early warning according to the equipment health state and preset early warning information; the step of obtaining historical operation data according to the metering equipment information and the denoised operation data comprises the following steps: obtaining database historical information; searching for same-type equipment information in the database historical information according to the metering equipment information to determine whether same-type equipment information exists; if same-type equipment information exists, determining same-type operation data of the same-type equipment information in the database historical information as the historical operation data; if same-type equipment information does not exist, comparing the historical database information with the metering equipment information to determine similar equipment information and reference equipment information; searching for similar operation data in the database historical information according to the similar equipment information; performing time sequence extraction on the denoised operation data to generate an operation data sequence; performing deviation analysis on the operation data sequence and the similar equipment information to determine a historical data deviation; calibrating the reference equipment information according to the historical data deviation to determine the historical operation data; the step of performing deviation analysis on the operation data sequence and the similar equipment information to determine a historical data deviation comprises the following steps: obtaining an equipment temperature sequence, an equipment load sequence, a historical temperature sequence and a historical load sequence; weighting deviations of the equipment temperature sequence, the equipment load sequence, the historical temperature sequence and the historical load sequence according to preset load rate weights and preset working condition temperature weights to determine a working condition similarity; determining whether the working condition similarity is less than a preset working condition similarity threshold; if the working condition similarity is less than the preset working condition similarity threshold, the similar operation data corresponding to the historical temperature sequence and the historical load sequence is removed; if the working condition similarity is not less than the preset working condition similarity threshold, the similar operation data corresponding to the historical temperature sequence and the historical load sequence is determined as same-working-condition operation data; performing analysis on the same-working-condition operation data and the operation data sequence to determine a same-dimension historical sequence; performing analysis on the same-dimension historical sequence and the operation data sequence to determine a historical data deviation; the step of performing analysis on the same-dimension historical sequence and the operation data sequence to determine a historical data deviation comprises the following steps: inputting the same-dimension historical sequence and the operation data sequence into a preset least square coefficient model to determine a polynomial fitting coefficient; inputting the operation data sequence, the polynomial fitting coefficient and the same-dimension historical sequence into a preset polynomial fitting model to determine a fitting data deviation; performing time sequence arrangement on the fitting data deviation to determine a historical data deviation.

2. The method of claim 1, wherein, the step of comparing the historical database information with the metering equipment information to determine similar equipment information and reference equipment information comprises the following steps: performing information extraction on the historical database information and the metering equipment information to determine an equipment running environment and a historical running environment; performing similarity comparison on the equipment running environment and the historical running environment to determine an environment similarity; determining whether the environment similarity is greater than a preset environment similarity threshold value; if greater, determining the historical database information corresponding to the historical running environment as available historical information; if not greater, excluding the historical database information corresponding to the historical running environment; analyzing the available historical information and the metering device information to determine similar device information and reference device information.

3. The method of claim 2, wherein, The step of analyzing the available historical information and the metering device information to determine similar device information and reference device information comprises: extracting information from the available historical information and the metering device information to determine current core component information, historical core component information, current collaborative logic information, and historical collaborative logic information; comparing the current core component information and the historical core component information to determine core component similarity; comparing the current collaborative logic information and the historical collaborative logic information to determine logic information similarity; weighting the core component similarity and the logic information similarity according to a preset component similarity proportion and a preset logic similarity proportion to determine a total historical similarity; determining available historical information with a total historical similarity greater than a preset total similarity threshold value as reference device information; determining available historical information corresponding to the greatest total historical similarity as similar device information.

4. The method of claim 1, wherein, The step of analyzing the same-condition running data and the running data sequence to determine a same-dimension historical sequence comprises: obtaining a same-condition time sequence of the same-condition running data and a running time sequence of the running data sequence; comparing the same-condition time sequence and the running time sequence to determine covered time points, uncovered time points, and covered point data; determining a left adjacent time point and a right adjacent time point in the same-condition time sequence according to the uncovered time points; determining left adjacent running data and right adjacent running data in the same-condition running data according to the left adjacent time point and the right adjacent time point; inputting the left adjacent time point, the right adjacent time point, the left adjacent running data, the right adjacent running data, and the uncovered time points into a preset linear interpolation model to determine interpolation running data; combining the covered point data and the interpolation running data according to the running time sequence to determine the same-dimension historical sequence.

5. A metrology equipment health state assessment system, characterized by, comprises: an acquisition module for acquiring metering device information, current running data, and historical running data; a memory for storing a program of a metering device health state evaluation method according to any one of claims 1 to 4; a processor, the program in the memory being loadable and executable by the processor to implement a metering device health state evaluation method according to any one of claims 1 to 4.

6. A smart terminal, characterized by comprises a memory and a processor, the memory storing a computer program loadable and executable by the processor to implement a metering device health state evaluation method according to any one of claims 1 to 4.

Images