Facility maintenance management system

Abstract

To provide an equipment maintenance management system for realizing effective maintenance to equipment, and for improving the aging property of material demand, and for strongly guaranteeing the safe and stable operation of the equipment.SOLUTION: The equipment maintenance management system includes a data acquisition module for acquiring a monitoring record of an operating state of a target equipment, a state analysis module for generating a fault alarm report based on the monitoring record of the operating state of the equipment, an equipment maintenance module for combining the fault alarm record with an equipment inspection and maintenance ledger of the target equipment to generate an equipment maintenance record, and a spare part management module for dynamically adjusting a material purchase plan based on the equipment maintenance record. The fault alarm report generated by performing the state inspection and analysis of the target equipment is combined with the equipment inspection and maintenance ledger to implement that the target maintenance personnel is performing precise maintenance work on the target equipment, and the equipment maintenance record is generated to dynamically adjust the material purchasing plan.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to the technical field of power plant equipment repair management, and more particularly to an equipment maintenance management system. [Background technology]

[0002] In recent years, with the rapid development of the national economy, the demand for electricity has continued to increase, and the scale of power plants has expanded rapidly. As a result, "chain reactions" caused by defects and failures in power plant equipment have become frequent, causing production interruptions at power plants and significantly impacting the orderly development of society. Therefore, accurate management and maintenance of power plant equipment has become an important research topic. However, currently known equipment maintenance methods are unable to accurately inspect the equipment for external defects and operational failures, and are unable to perform in-depth analysis of defects or accurately locate the defect locations.

[0003] Therefore, the present invention provides an equipment maintenance management system, which effectively combines real-time monitoring of equipment status, in-depth analysis of defects and failures, and accurate maintenance and spare parts management, thereby strongly guaranteeing the safe and stable operation of equipment. Summary of the Invention [Problem to be solved by the invention]

[0004] The present invention provides an equipment maintenance management system that combines a fault alarm report generated by performing status detection and analysis of the target equipment with an equipment inspection and maintenance ledger, confirms that the target maintenance personnel are performing precise maintenance work on the target equipment, generates an equipment maintenance record, and makes dynamic adjustments to the material purchasing plan, thereby achieving effective maintenance of the equipment while improving the timeliness of material demand and strongly guaranteeing the safe and stable operation of the equipment. [Means for solving the problem]

[0005] The present invention provides an equipment maintenance management system, which includes:

[0006] a data acquisition module for monitoring the operation status of the target equipment in real time and generating a monitoring record of the equipment operation status; a condition analysis module for recognizing defects and failures of the target equipment based on the monitoring record of the equipment operating state, and generating a fault alarm record for the target equipment when a defect or failure exists in the target equipment; an equipment maintenance module for combining the fault alarm record with the equipment inspection and maintenance ledger of the target equipment, performing maintenance work on the target equipment by the target maintenance personnel, and generating an equipment maintenance record; A spare parts management module that determines predicted spare parts consumption data based on equipment maintenance records and dynamically adjusts material purchasing plans.

[0007] Preferably, the data acquisition module includes:

[0008] Using a preset monitoring device attached to a preset monitoring point, monitor the operating status of the target equipment in real time and obtain first operating status data; a data collection unit that acquires basic equipment information of the target equipment from an equipment information database, and compiles and organizes the acquired first operating status data to obtain a monitoring record of the equipment operating status;

[0009] Preferably, the basic equipment information includes equipment name, equipment department, equipment code, equipment type, shipping date, technical parameters, responsible person, installation location, spare part information, etc.

[0010] Preferably, the condition analysis module includes:

[0011] a data processing unit for performing data preprocessing on the first status data to obtain target image data and target operating status data; a fault inspection unit for performing defect inspection on the current target equipment using an external inspection block, and for performing fault inspection, analysis and prediction on the current target equipment using an internal inspection block; an external inspection block for performing an external defect inspection on the current target equipment based on the target image data, and generating a defect analysis table when a defect exists, and transmitting the same to the report generating unit; Perform a fault check on the current target equipment based on the target operating state data, and generate fault analysis data when a fault is detected, and transmit the data to a report generating unit; Otherwise, an internal inspection block for performing fault prediction on the current target equipment, generating fault prediction data and transferring it to the report generation unit; A report generating unit for receiving the defect analysis table, the failure analysis data and the failure prediction data, summarizing and organizing them with the basic equipment information of the current target equipment, generating a failure alarm report and transmitting it to the equipment repair module.

[0012] Preferably, the external inspection block includes:

[0013] Based on a preset amount of historical equipment defect reports extracted from an equipment maintenance database, a training data set is constructed to train a neural network to obtain a defect identification model; The normal image data in the target image data is sharpened using the CGAN algorithm to obtain the target image; inputting the target image into the defect identification model to perform defect identification, and determining a first defect location and a first defect type of the current target equipment; predicting a first defect risk value of the first defect portion based on past maintenance data extracted from an equipment maintenance database; The formula for calculating the first defect risk value is as follows: JPEG2026028209000002.jpg9143Here, Q i is the i-th first defect site X ij is the j-th set risk assessment amount of the i-th first defect part, where the set risk assessment amount is the ratio of the number of past maintenances, the frequency of patrol inspections, the average maintenance time, and the risk of the defect type. δij is the weight of the influence of the jth set risk assessment amount of the ith first defect part on the risk assessment of the first defect part. constructing a first defect table based on the first defect location, the first defect type, and the first defect risk value; performing a defect diagnosis on the thermal image data in the target image data to obtain a second defect portion and a defect portion identification temperature; obtaining a second defect risk value of the second defect location based on a difference between the defect location identification temperature and a correspondingly set temperature threshold; constructing a second defect table based on the second defect location, the defect location identification temperature, and the second defect risk value; For defect sites that simultaneously exist in the first defect table and the second defect table, calculate the sum of the corresponding first defect value and second defect value, and output it as a defect threat value; A first defect risk value that exists only in the first defect table and does not exist in the first defect location in the second defect table is defined as the defect threat value of the first defect location; A second defect risk value that exists only in the second defect table and does not exist in the second defect location in the first defect table is defined as the defect threat value of the second defect location; Determine the threat level of all primary and secondary defect areas based on the defect threat value; All currently detected defect sites are sorted in descending order of defect threat value, and a defect analysis table is created by combining the acquired defect type, defect site identification temperature, and threat grade, and transferred to the report generation unit.

[0014] Preferably, the internal check block includes:

[0015] Performing feature extraction on the target operating state data using a spectrum analysis method to obtain important state feature values; The important condition feature value is used as an input side of a condition inspection model constructed based on a random forest algorithm, and a condition inspection result of the current target equipment is output; If a fault is detected as a result of the current state inspection of the target equipment, select a reference operation state quantity whose state value does not belong to the corresponding state threshold range from the target operation state data based on the state threshold range; a fault identification sub-block for jointly analyzing the reference operating state quantity and the set state-fault related ranking table to obtain fault related results and output them as fault analysis data; If no fault is found as a result of the current status inspection of the target equipment, the target operating status data is input into a pre-constructed status prediction model to obtain a prediction result of the status quantity at the next time; If there is a target operating state quantity whose predicted result of the state quantity does not belong to the corresponding state threshold range, a prediction correction of the state quantity is performed for the target operating state quantity, and the predicted result of the state quantity is updated; The calculation formula for the corrected predicted state value is as follows: JPEG2026028209000003.jpg24145where, JPEG2026028209000004.jpg7142 is the predicted state value after correction of the kth target operating state quantity E k is the predicted value of the original state quantity at the next time of the kth target operating state quantity E kmax is the upper limit of the state threshold of the kth operational state quantity E kmin is the lower limit of the state threshold of the kth operational state quantity f is a preset correction coefficient a state prediction sub-block for inputting the predicted results of the state quantities into a state prediction model and obtaining the predicted results of the state quantities at the next time; Using a fault identification sub-block, a fault diagnosis is performed on the prediction results of the state quantity within a preset time period repeatedly acquired by the state prediction sub-block, and a fault prediction result is obtained at each preset time; Based on the failure prediction results, the preset time when the failure occurs and the corresponding failure item are obtained, and a failure prediction table is constructed in chronological order; constructing a state quantity prediction change curve for each target operational state quantity using the prediction results of the state quantities within a preset time period; Analyzing the state quantity prediction change curve to obtain the predicted change trend of each target operating state quantity; A change analysis sub-block for outputting the acquired failure prediction table, the predicted change curve of the state quantity of each target operating state quantity, and the predicted change trend as failure prediction data.

[0016] Preferably, the equipment maintenance module includes:

[0017] a personnel selection unit for acquiring selectable maintenance personnel using the list acquisition block, and selecting the selectable maintenance personnel acquired using the selection block to acquire a target maintenance personnel; a list acquisition block for acquiring the equipment name and department of the equipment to be repaired based on the received fault alarm report, and selecting corresponding selectable maintenance personnel from the equipment maintenance information database; A selection block for acquiring the work status and defect / fault handling records of all selectable maintenance personnel, and combining and analyzing the received defect threat level, fault-related results, and fault prediction table to select and acquire target maintenance personnel; a maintenance unit for acquiring an equipment inspection and maintenance ledger of the target equipment and transferring it together with the fault alarm report to a target maintenance person, so as to perform accurate maintenance on the target equipment and generate an equipment maintenance record;

[0018] Preferably, the spare parts management module includes:

[0019] Obtaining inspection spare part consumption data and maintenance spare part consumption data for the target equipment based on the equipment maintenance record; a forecast consumption unit that generates forecast consumption data for spare parts by associating existing spare part inventory information, undelivered spare part information, inspection spare part consumption data, and maintenance spare part consumption data; An adjustment unit that uses the predicted wear data of the spare parts to make dynamic adjustments to the material procurement plan. [Effects of the Invention]

[0020] Compared with the prior art, the present application has the following advantageous effects:

[0021] By combining the fault alarm report generated through the condition detection analysis of the target equipment with the equipment inspection and maintenance ledger, it is possible to confirm that the target maintenance personnel are performing precise maintenance work on the target equipment, and by generating an equipment maintenance record and making dynamic adjustments to the material purchasing plan, it is possible to achieve effective maintenance of the equipment while improving the timeliness of material demand, and further strongly guarantee the safe and stable operation of the equipment.

[0022] Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention may be realized and obtained by the structure particularly pointed out in the description and drawings.

[0023] The technical solution of the present invention will be described in more detail below in conjunction with the drawings and embodiments. [Brief explanation of the drawings]

[0024] The drawings are provided for a further understanding of the invention, constitute a part of the specification, and together with the examples of the invention are used to explain the invention and are not intended to limit the invention.

[0025] [Figure 1] 1 is a configuration diagram of an equipment maintenance management system according to an embodiment of the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0026] Hereinafter, preferred embodiments of the present invention will be described in conjunction with the drawings. It should be understood that the preferred embodiments described herein are used to explain and interpret the present invention, and are not intended to limit the present invention.

[0027] An embodiment of the present invention provides an equipment maintenance management system, which, as shown in FIG. 1, includes:

[0028] a data acquisition module for monitoring the operation status of the target equipment in real time and generating a monitoring record of the equipment operation status; a condition analysis module for recognizing defects and failures of the target equipment based on the monitoring record of the equipment operating state, and generating a fault alarm record for the target equipment when a defect or failure exists in the target equipment; an equipment maintenance module for combining the fault alarm record with the equipment inspection and maintenance ledger of the target equipment, performing maintenance work on the target equipment by the target maintenance personnel, and generating an equipment maintenance record; A spare parts management module that determines predicted spare parts consumption data based on equipment maintenance records and dynamically adjusts material purchasing plans.

[0029] In this embodiment, the target equipment refers to equipment whose status is monitored in real time to ensure production efficiency and production safety, such as a power plant equipment generator, fan, feedwater pump, etc. The equipment operating status monitoring record is a compilation of the basic equipment information of the target equipment and the acquired first operating status data, among which the basic equipment information includes the equipment name, the equipment department, equipment code, equipment type, shipping date, technical parameters, responsible person, installation location, spare part information, etc.

[0030] In this embodiment, the first operating status data is composed of video data obtained by real-time detection using a preset inspection device installed at a preset monitoring point, and real-time operating status data of the equipment, where the preset monitoring point is set in advance, and the preset inspection device includes a data collection device, an infrared thermal imaging camera, and an ordinary camera.

[0031] In this embodiment, the fault warning report is a report generated by collating and organizing the defect analysis table, the fault analysis data, the fault prediction data, and the basic equipment information of the current target equipment, among which the defect analysis table is composed of the defect location, the defect type, the defect location identification temperature, and the threat level.

[0032] In this embodiment, the fault analysis data refers to the fault-related results, i.e., fault items related to the reference operating state quantities obtained based on the set state-fault related ranking table, where the set state-fault related ranking table is established using the correlation between the state quantities and the faults previously determined by the grayscale correlation analysis method. The reference operating state quantity refers to the state numerical value in the target operating state data of the target equipment not belonging to the operating state quantity in the corresponding state threshold range when it is determined that the current target equipment has a fault using the state inspection model. The fault items are composed of the fault location and the fault type.

[0033] In this embodiment, the failure prediction data includes a failure prediction table, a predicted change curve of each target operating state quantity, and a predicted change trend. The failure prediction table is configured by arranging the predicted fault occurrence time and fault name in chronological order, and the predicted change trend includes an upward and downward trend.

[0034] In this embodiment, the status inspection model is a model for inspecting the operating status of the target equipment obtained by combining the frequency domain feature values ​​of the equipment's past operating status data as training data with random forest algorithm training.

[0035] In this example, the equipment inspection and maintenance ledger consists of equipment inspection records and technical documents, among which the equipment inspection records include the inspection start date, end date, pre-repair status, inspection contents, post-inspection status and maintenance personnel, etc., and the technical documents include the inspection file pack, inspection procedure card, etc. The target maintenance personnel refers to the maintenance personnel who is best suited to handle the current defects and breakdowns of the target equipment.

[0036] In this embodiment, the equipment maintenance record is composed of basic equipment information and maintenance information, of which the basic equipment information includes equipment name, department to which the equipment belongs, equipment code, equipment type, delivery date, technical parameters, responsible person, installation location, and spare part information, etc., and the maintenance information includes maintenance time, maintenance nature, maintenance content, maintenance personnel and maintenance time, inspection spare part consumption data, and maintenance spare part consumption data, of which the maintenance nature can be divided into two types: repair and routine maintenance.

[0037] In this embodiment, the predicted spare part consumption data refers to the predicted spare part consumption quantities, names, and specifications of the predicted spare parts that are expected to be consumed, which are obtained by correlating and analyzing existing spare part inventory information, information on undelivered spare parts, consumption data on inspected spare parts, and consumption data on maintenance spare parts. The material purchasing plan is a demand plan extracted by the material demand department according to the actual situation, and contains detailed information such as the names, specifications, quantities, and prices of the required materials.

[0038] The above technical solution combines the fault alarm report generated by performing the status inspection analysis on the target equipment with the equipment inspection and maintenance ledger, thereby ensuring that the target maintenance personnel are performing precise maintenance work on the target equipment, and generates an equipment maintenance record to dynamically adjust the material purchasing plan, thereby achieving effective maintenance of the equipment and improving the timeliness of material demand, and further ensuring the safe and stable operation of the equipment.

[0039] The present invention provides an equipment maintenance management system, wherein the data acquisition module includes:

[0040] Using a preset monitoring device attached to a preset monitoring point, monitor the operating status of the target equipment in real time and obtain first operating status data; a data collection unit that acquires basic equipment information of the target equipment from an equipment information database, and compiles and organizes the acquired first operating status data to obtain a monitoring record of the equipment operating status;

[0041] In this embodiment, the target equipment refers to equipment such as a power plant equipment generator, fan, and water supply pump, the status of which is monitored in real time to ensure production efficiency and production safety.

[0042] In this embodiment, the first operating status data is composed of video data obtained by real-time inspection using a preset inspection device installed at a preset monitoring point and real-time operating status data of the equipment, where the preset monitoring point is set in advance, the preset inspection device includes a data collection device, an infrared thermal imaging camera and an ordinary camera, and the equipment information database is composed of basic information of the equipment.

[0043] In this embodiment, the equipment operation status monitoring record is a record that compiles and organizes the basic equipment information of the target equipment and the acquired first operation status data, among which the basic equipment information includes the equipment name, the department to which the equipment belongs, the equipment code, the equipment type, the shipping date, the technical parameters, the person in charge, the installation location, and the spare part information.

[0044] The above technical solution has the advantageous effect of collecting and organizing the first operating status data obtained by monitoring the operating status of the target equipment in real time using a preset inspection device installed at a preset monitoring point together with the basic equipment information of the target equipment to obtain a monitoring record of the equipment operating status, thereby providing data support for subsequent equipment maintenance.

[0045] An embodiment of the present invention provides an equipment maintenance management system, wherein the condition analysis module includes:

[0046] a data processing unit for performing data preprocessing on the first status data to obtain target image data and target operating status data; a fault inspection unit for performing defect inspection on the current target equipment using an external inspection block, and for performing fault inspection, analysis and prediction on the current target equipment using an internal inspection block; an external inspection block for performing an external defect inspection on the current target equipment based on the target image data, and generating a defect analysis table when a defect exists, and transmitting the same to the report generating unit; Perform a fault check on the current target equipment based on the target operating state data, and generate fault analysis data when a fault is detected, and transmit the data to a report generating unit; Otherwise, an internal inspection block for performing fault prediction on the current target equipment, generating fault prediction data, and transferring the data to the report generation unit; A report generating unit for receiving the defect analysis table, the failure analysis data and the failure prediction data, summarizing and organizing them with the basic equipment information of the current target equipment, generating a failure alarm report and transmitting it to the equipment repair module.

[0047] In this embodiment, the first operating status data is composed of video data obtained by real-time detection using a preset inspection device installed at a preset monitoring point, and real-time operating status data of the equipment, where the preset monitoring point is set in advance, and the preset inspection device includes a data collection device, an infrared thermal imaging camera, and an ordinary camera.

[0048] In this embodiment, the target image data is a target image obtained by extracting and denoising video data collected using a conventional camera or an infrared thermal imaging camera, and includes conventional images and thermal images. The target operating status data is data obtained by filling in missing values ​​in real-time operating status data of the target equipment collected in real time using a data collection device and then normalizing the data.

[0049] In this embodiment, the defect analysis table is composed of defect location, defect type, defect location identification temperature, and threat level, and the failure analysis data is the failure-related result, that is, the failure item related to the reference operating state quantity obtained based on the set state-failure relationship ranking table, where the set state-failure relationship ranking table is established using the correlation between the state quantity and the failure previously determined by the grayscale correlation analysis method. The reference operating state quantity means that when it is determined that the current target equipment has a fault using the state inspection model, the state numerical value in the target operating state data of the target equipment does not belong to the operating state quantity of the corresponding state threshold range.

[0050] In this embodiment, the failure prediction data is composed of a failure prediction table and a predicted change trend of each target operating state quantity, of which the failure prediction table is composed of a chronological order of the predicted failure occurrence time and failure name, and the predicted change trend includes rising and falling. The basic equipment information includes the equipment name, the department to which the equipment belongs, the equipment code, the equipment type, the shipping date, the technical parameters, the person in charge, the installation location, and spare part information, etc. The failure alarm report is generated by combining and organizing the defect analysis table, the failure analysis data, and the failure prediction data with the basic equipment information of the current target equipment.

[0051] The above technical solution uses video data and operating status data obtained based on the target equipment monitored in real time after data preprocessing to perform defect inspection, fault identification and prediction, generate fault alarm reports, realize in-depth analysis of defects and faults, provide important information for equipment maintenance, and thereby have the advantageous effect of improving the efficiency and accuracy of equipment maintenance.

[0052] An embodiment of the present invention provides an equipment maintenance management system, in which the external inspection block includes:

[0053] Based on a preset amount of historical equipment defect reports extracted from an equipment maintenance database, a training data set is constructed to train a neural network to obtain a defect identification model; The normal image data in the target image data is sharpened using the CGAN algorithm to obtain the target image; inputting the target image into the defect identification model to perform defect identification, and determining a first defect location and a first defect type of the current target equipment; predicting a first defect risk value of the first defect portion based on past maintenance data extracted from an equipment maintenance database; The formula for calculating the first defect risk value is as follows: JPEG2026028209000005.jpg9143where, Q i is the i-th first defect site X ij is the jth set risk assessment value of the i-th first defect part, where the set risk assessment value is the ratio of the number of past maintenances, the frequency of patrol inspections, the average maintenance time, and the risk of defect type. δ ij is the weight of the influence of the jth set risk assessment amount of the ith first defect part on the risk assessment of the first defect part. constructing a first defect table based on the first defect location, the first defect type, and the first defect risk value; performing a defect diagnosis on the thermal image data in the target image data to obtain a second defect portion and a defect portion identification temperature; obtaining a second defect risk value of the second defect location based on a difference between the defect location identification temperature and a correspondingly set temperature threshold; constructing a second defect table based on the second defect location, the defect location identification temperature, and the second defect risk value; For defect sites that simultaneously exist in the first defect table and the second defect table, calculate the sum of the corresponding first defect value and second defect value, and output it as a defect threat value; A first defect risk value that exists only in the first defect table and does not exist in the first defect location in the second defect table is defined as the defect threat value of the first defect location; A second defect risk value that exists only in the second defect table and does not exist in the second defect location in the first defect table is defined as the defect threat value of the second defect location; Determine the threat level of all primary and secondary defect areas based on the defect threat value; All currently detected defect sites are sorted in descending order of defect threat value, and a defect analysis table is created by combining the acquired defect type, defect site identification temperature, and threat grade, and transferred to the report generation unit.

[0054] In this embodiment, the defect identification model is a model obtained by training a neural network using a training data set constructed based on past equipment defect reports that extract preset quantities from an equipment maintenance database, and is used to identify defects in collected images of the equipment; The procedure for establishing training data is as follows:

[0055] 1. Extract past equipment defect image data from the acquired past equipment defect reports and perform preliminary defect category marking. 2. After category marking, sort out the past equipment defect images, and select the image data with only one type of defect and clear defect characteristics as the first image. 3. The first image is subjected to extension processes such as inversion, local occlusion, and cut to obtain a training dataset.

[0056] In this embodiment, the target image is an image obtained by sharpening a normal image using the CGAN algorithm, and the first defect portion is a defect portion obtained by inputting the normal image after sharpening into a defect identification model, such as an insulator or a box door. The first defect type includes breakage, deformation, corrosion, etc. The past maintenance data is data extracted from an equipment maintenance database, such as the name of the equipment that has been maintained, the maintenance portion, the maintenance frequency, and the maintenance time length.

[0057] In this embodiment, the first defect risk value is used to characterize the processing urgency of the current first defect site, and the first defect table is composed of the first defect site, the first defect type and the first defect risk value.

[0058] In this example, the thermal imaging data is an image obtained by extracting video data collected by an infrared thermal imaging camera and then performing noise reduction processing. The second defect region is a region obtained by dividing the thermal image into rows, evaluating it based on the HSV color model, and then segmenting it using a threshold segmentation technique. The defect region identification temperature is the temperature at the second defect region, and the set temperature threshold is a preset value.

[0059] In this embodiment, the second defect table is composed of a second defect location, a defect location identification temperature, and a second defect risk value, of which the second defect risk value is obtained by calculating the difference between the corresponding defect location identification temperature of the second defect location and a set temperature threshold, and is used to characterize the urgency of treating the current second defect location. The defect threat value is used to characterize the degree of threat that the defect location poses to the safe operation of the current target equipment, and the threat grades are divided into four: general threat, moderate threat, major threat, and serious threat. The defect analysis table is composed of a defect location, a defect type, a defect location identification temperature, and a threat grade.

[0060] The above technical solution uses image processing technology to detect external defects in normal images and thermal images, respectively, and generate a defect analysis table, thereby providing accurate recognition of external defects in equipment and reliable defect analysis data for future maintenance, which has the advantageous effect of helping to improve the maintenance efficiency and reliability of equipment.

[0061] An embodiment of the present invention provides an equipment maintenance management system, wherein the internal inspection block includes:

[0062] Performing feature extraction on the target operating state data using a spectrum analysis method to obtain important state feature values; The important condition feature value is used as an input side of a condition inspection model constructed based on a random forest algorithm, and a condition inspection result of the current target equipment is output; If a fault is detected as a result of the current state inspection of the target equipment, select a reference operation state quantity whose state value does not belong to the corresponding state threshold range from the target operation state data based on the state threshold range; a fault identification sub-block for jointly analyzing the reference operating state quantity and the set state-fault related ranking table to obtain fault related results and output them as fault analysis data; If no fault is found as a result of the current status inspection of the target equipment, the target operating status data is input into a pre-constructed status prediction model to obtain a prediction result of the status quantity at the next time; If there is a target operating state quantity whose predicted result of the state quantity does not belong to the corresponding state threshold range, a prediction correction of the state quantity is performed for the target operating state quantity, and the predicted result of the state quantity is updated; The calculation formula for the corrected predicted state value is as follows: JPEG2026028209000006.jpg24145where, JPEG2026028209000007.jpg7142 is the predicted state value after correction of the kth target operating state quantity E k is the predicted value of the original state quantity at the next time of the kth target operating state quantity E kmax is the upper limit of the state threshold of the kth operational state quantity E kmin is the lower limit of the state threshold of the kth operational state quantity f is a preset correction coefficient a state prediction sub-block for inputting the predicted results of the state quantities into a state prediction model and obtaining the predicted results of the state quantities at the next time; Using a fault identification sub-block, a fault diagnosis is performed on the prediction results of the state quantity within a preset time period repeatedly acquired by the state prediction sub-block, and a fault prediction result is obtained at each preset time; Based on the failure prediction results, the preset time when the failure occurs and the corresponding failure item are obtained, and a failure prediction table is constructed in chronological order; constructing a state quantity prediction change curve for each target operational state quantity using the prediction results of the state quantities within a preset time period; Analyzing the state quantity prediction change curve to obtain the predicted change trend of each target operating state quantity; A change analysis sub-block for outputting the acquired failure prediction table, the predicted change curve of the state quantity of each target operating state quantity, and the predicted change trend as failure prediction data.

[0063] In this embodiment, the target operating status data is data obtained by filling in missing values ​​in real-time equipment operating status data of the target equipment collected in real time using a data collection device and then normalizing the data. The spectrum analysis method is a method of converting the time domain signal of the target operating status data into the frequency domain. The important status feature value is obtained by extracting status frequency domain features from the target operating status data using the spectrum analysis method.

[0064] In this embodiment, the condition inspection model is a model for detecting the operating state of the target equipment obtained by combining the frequency domain feature values ​​of the equipment's past operating state data as training data with random forest algorithm training, and the condition inspection result has two results: the presence or absence of a fault.

[0065] In this embodiment, the state threshold range is a predetermined numerical range of an operating state quantity, among which the operating state quantities include voltage, current, power, etc., and the reference operating state quantity is an operating state quantity whose state numerical value does not fall outside the corresponding state threshold range.

[0066] In this embodiment, the setting state-failure association ranking table is created using the association between the state quantity and the failure, which has been previously determined by the grayscale association analysis method, and the failure association result is a failure item related to the reference operating state quantity determined based on the setting state-failure association ranking table.

[0067] In this embodiment, the state prediction model is a model used to predict state quantities at future times, obtained by training an LSTM neural model using preset amounts of important past state data extracted from the equipment operation database as input values.

[0068] In this embodiment, the prediction result of the state quantity is the predicted state quantity at the next time when the current operating state data is input to the state prediction model and output, the failure prediction result is the failure item obtained by performing failure identification based on the prediction result of the state quantity, and the preset time is the time when a failure occurs within a preset time period.

[0069] In this embodiment, the fault prediction table is a table created in chronological order of preset times when faults occur and corresponding fault items, among which the fault items consist of fault names and fault types, and the state quantity prediction change curves are created using the prediction results of the state quantities within a preset time period, and the predicted change trends include two trends: upward and downward. The fault prediction data includes the fault prediction table, the state quantity prediction change curves and predicted change trends of each target operating state quantity.

[0070] The above technical solution combines the spectrum analysis method and the random forest algorithm to perform fault detection on the current operating state of the target equipment, and if there is no fault in the current target equipment, builds a state prediction model to analyze the change trend of the operating state of the target equipment, thereby realizing effective monitoring and control of the equipment state and further having the advantageous effect of strongly guaranteeing the safe and stable operation of the equipment.

[0071] An embodiment of the present invention provides an equipment maintenance management system, wherein the equipment maintenance module includes:

[0072] a personnel selection unit for acquiring selectable maintenance personnel using the list acquisition block, and selecting the selectable maintenance personnel acquired using the selection block to acquire a target maintenance personnel; a list acquisition block for acquiring the equipment name and department of the equipment to be repaired based on the received fault alarm report, and selecting corresponding selectable maintenance personnel from the equipment maintenance information database; A selection block for acquiring the work status and defect / fault handling records of all selectable maintenance personnel, and combining and analyzing the received defect threat level, fault-related results, and fault prediction table to select and acquire target maintenance personnel; The maintenance unit acquires the equipment inspection and maintenance ledger of the target equipment, transfers it together with the fault alarm report to the target maintenance personnel, performs accurate maintenance on the target equipment, and generates an equipment maintenance record.

[0073] In this embodiment, the fault alarm report is generated by collating the defect analysis table, fault analysis data, and fault prediction data with the basic equipment information of the current target equipment. The equipment to be repaired refers to the equipment for which a fault alarm record is generated and sent to the equipment repair module. The equipment maintenance database is composed of equipment maintenance data, and includes equipment maintenance parameter information such as the name of the maintained equipment, the department to which the equipment belongs, the maintenance location, the maintenance frequency, and the maintenance personnel number, defect and fault handling record, etc.

[0074] In this embodiment, selectable maintenance personnel are selected from the equipment maintenance database according to the equipment name of the equipment to be repaired and the department to which the equipment belongs, and there are two work states: not working and working.

[0075] In this embodiment, the equipment inspection and maintenance ledger is composed of equipment inspection records and technical documents, of which the equipment inspection records include the inspection start date, end date, pre-repair status, inspection contents, post-repair status and maintenance personnel, etc. The technical documents include the inspection file pack, inspection procedure card, etc. The target maintenance personnel refers to the maintenance personnel who is best suited to handle the current defects and breakdowns of the target equipment.

[0076] The above technical solution has the advantageous effect of combining and analyzing the fault alarm report and the equipment inspection and maintenance ledger to select maintenance personnel to accurately inspect and repair the defects and faults currently existing in the target equipment, thereby realizing effective maintenance of the equipment and contributing to the safe and stable operation of the equipment.

[0077] An embodiment of the present invention provides an equipment maintenance management system, wherein the spare parts management module includes:

[0078] Obtaining inspection spare part consumption data and maintenance spare part consumption data for the target equipment based on the equipment maintenance record; a forecast consumption unit that generates forecast consumption data for spare parts by associating existing spare part inventory information, undelivered spare part information, inspection spare part consumption data, and maintenance spare part consumption data; An adjustment unit that uses the predicted wear data of the spare parts to make dynamic adjustments to the material procurement plan.

[0079] In this embodiment, the equipment maintenance record is composed of basic information of the equipment and maintenance information, of which the basic information of the equipment includes the equipment name, the department to which the equipment belongs, the equipment code, the equipment type, the shipping date, the technical parameters, the person in charge, the installation location and the spare part information, etc., and the maintenance information includes the maintenance time, the maintenance nature, the maintenance content, the maintenance staff, the maintenance time, the inspection spare part consumption data and the maintenance spare part consumption data, of which the maintenance nature is divided into two types: repair and daily maintenance.

[0080] In this embodiment, the inspection spare part consumption data is the number, specifications, and names of spare parts used in equipment repairs, the maintenance spare part consumption data is the number, specifications, and names of spare parts used in equipment maintenance, and the undelivered spare part information is the number, specifications, and names of purchased spare parts that have not yet been received.

[0081] In this embodiment, the predicted spare part consumption data is the predicted quantity of spare parts to be consumed, the names of the spare parts to be consumed, and the specifications of the spare parts to be consumed, which are obtained by correlating and analyzing existing spare part inventory information, information on spare parts that have not yet arrived, consumption data on inspected spare parts, and consumption data on maintenance spare parts. The material purchasing plan is a demand plan extracted by the material demand department according to the actual situation, and contains detailed information such as the names, specifications, quantities, and prices of the required materials.

[0082] The above technical solution has the advantageous effects of ensuring the timeliness of material demand, increasing the flexibility of equipment spare parts management, and strongly guaranteeing equipment maintenance by determining predicted spare parts consumption data based on equipment maintenance records and making dynamic adjustments to material purchasing plans.

[0083] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention also intends to include these modifications and variations.

Claims

1. 1. An equipment maintenance management system, comprising: a data acquisition module for monitoring the operation status of the target equipment in real time and generating a monitoring record of the equipment operation status; a condition analysis module for recognizing defects and failures of the target equipment based on the monitoring record of the equipment operating state, and generating a fault alarm record for the target equipment when a defect or failure exists in the target equipment; an equipment maintenance module for combining the fault alarm record with the equipment inspection and maintenance ledger of the target equipment, performing maintenance work on the target equipment by the target maintenance personnel, and generating an equipment maintenance record; A spare parts management module for determining predicted spare parts consumption data based on equipment maintenance records and dynamically adjusting material purchasing plans; Wherein, the status analysis module includes: a data processing unit for performing data pre-processing on the first status data to obtain target image data and target operating status data; a fault inspection unit for performing defect inspection on the current target equipment using an external inspection block, and for performing fault inspection, analysis and prediction on the current target equipment using an internal inspection block; an external inspection block for performing an external defect inspection on the current target equipment based on the target image data, and generating a defect analysis table when a defect exists, and transmitting the same to the report generating unit; Perform a fault check on the current target equipment based on the target operating state data, and generate fault analysis data when a fault is detected, and transmit the data to a report generating unit; Otherwise, an internal inspection block for performing fault prediction on the current target equipment, generating fault prediction data and transferring it to the report generation unit; a report generating unit for receiving the defect analysis table, the failure analysis data and the failure prediction data, and collating and organizing them with the basic equipment information of the current target equipment, generating a fault alarm report, and transmitting it to the equipment repair module; Wherein, the external inspection block includes: Based on a preset amount of historical equipment defect reports extracted from an equipment maintenance database, a training data set is constructed to train a neural network to obtain a defect identification model; The normal image data in the target image data is sharpened using a CGAN algorithm to obtain a target image; inputting the target image into the defect identification model to perform defect identification, and determining a first defect location and a first defect type of the current target equipment; predicting a first defect risk value of the first defect portion based on past maintenance data extracted from an equipment maintenance database; The calculation formula for the first defect risk value is as follows: Here, Q ｉ is the i-th first defect site X ij is the j-th set risk assessment amount of the i-th first defect portion, where the set risk assessment amount is the ratio of the number of past maintenances, the frequency of patrol inspections, the average maintenance time, and the risk of the defect type. δij is the weight of the influence of the jth set risk assessment amount of the i-th first defect portion on the risk assessment of the first defect portion. constructing a first defect table based on the first defect location, the first defect type, and the first defect risk value; performing a defect diagnosis on the thermal image data in the target image data to obtain a second defect portion and a defect portion identification temperature; obtaining a second defect risk value of the second defect location based on a difference between the defect location identification temperature and a correspondingly set temperature threshold value; constructing a second defect table based on the second defect location, the defect location identification temperature, and the second defect risk value; For defect locations that simultaneously exist in the first defect table and the second defect table, calculate the sum of the corresponding first defect value and second defect value, and output it as a defect threat value; a first defect risk value that exists only in the first defect table and does not exist in the first defect location in the second defect table is set as the defect threat value of the first defect location; a second defect risk value that exists only in the second defect table and does not exist in the second defect location in the first defect table is defined as the defect threat value of the second defect location; determining a threat level for all first and second defect locations based on the defect threat value; Sort all currently detected defect locations in descending order of defect threat value, combine the acquired defect type, defect location identification temperature, and threat grade to create a defect analysis table, and transfer it to a report generation unit; Wherein, the internal inspection block includes: Performing feature extraction on the target operating state data using a spectrum analysis method to obtain important state feature values; The important condition feature value is used as an input side of a condition inspection model constructed based on a random forest algorithm, and a condition inspection result of the current target equipment is output; If a fault is detected as a result of the current state inspection of the target equipment, select a reference operation state quantity whose state value does not belong to the corresponding state threshold range from the target operation state data based on the state threshold range; a fault identification sub-block for jointly analyzing the reference operating state quantity and the set state-fault related ranking table to obtain fault related results and output them as fault analysis data; If no fault is found as a result of the current status inspection of the target equipment, the target operating status data is input into a pre-constructed status prediction model to obtain a prediction result of the status quantity at the next time; If there is a target operating state quantity whose predicted result of the state quantity does not belong to the corresponding state threshold range, a prediction correction of the state quantity is performed for the target operating state quantity, and the predicted result of the state quantity is updated; The calculation formula for the corrected predicted state value is as follows: where: is the predicted state value after correction of the kth target operating state quantity E k is the predicted value of the original state quantity at the next time of the kth target operating state quantity E kmax is the upper limit of the state threshold of the kth operational state quantity E kmin is the lower limit of the state threshold of the kth operational state quantity f is a preset correction coefficient a state prediction sub-block for inputting the predicted results of the state quantities into a state prediction model and obtaining the predicted results of the state quantities at the next time; Using a fault identification sub-block, a fault diagnosis is performed on the prediction results of the state quantity within a preset time period repeatedly acquired by the state prediction sub-block, and a fault prediction result is obtained at each preset time; Based on the failure prediction results, the preset time when the failure occurs and the corresponding failure item are obtained, and a failure prediction table is constructed in chronological order; constructing a state quantity prediction change curve for each target operational state quantity using the prediction results of the state quantities within a preset time period; Analyzing the state quantity prediction change curve to obtain the predicted change trend of each target operating state quantity; a change analysis sub-block for outputting the acquired failure prediction table, the state quantity prediction change curve and the predicted change trend of each target operating state quantity as failure prediction data.

2. The data acquisition module includes: Using a preset monitoring device attached to a preset monitoring point, monitor the operating status of the target equipment in real time and obtain first operating status data; 2. The equipment maintenance management system according to claim 1, characterized in that the data collection unit acquires basic equipment information of the target equipment from an equipment information database, and compiles and organizes the acquired first operating status data to obtain a monitoring record of the equipment operating status.

3. The equipment maintenance management system according to claim 2, characterized in that the basic equipment information includes the equipment name, the department to which the equipment belongs, the equipment code, the equipment type, the shipping date, the technical parameters, the person in charge, the installation location, and the spare part information.

4. The equipment maintenance module includes: a personnel selection unit for acquiring selectable maintenance personnel using the list acquisition block, and selecting the selectable maintenance personnel acquired using the selection block to acquire a target maintenance personnel; a list acquisition block for acquiring the equipment name and department of the equipment to be repaired based on the received fault alarm report, and selecting corresponding selectable maintenance personnel from the equipment maintenance information database; A selection block for acquiring the work status and defect / fault handling records of all selectable maintenance personnel, and combining and analyzing the received defect threat level, fault-related results, and fault prediction table to select and acquire target maintenance personnel; 2. The equipment maintenance management system according to claim 1, characterized in that the maintenance unit acquires an equipment inspection and maintenance ledger for the target equipment, transfers it together with the fault alarm report to the target maintenance personnel, performs accurate maintenance on the target equipment, and generates an equipment maintenance record.

5. The spare parts management module includes: Obtaining inspection spare part consumption data and maintenance spare part consumption data for the target equipment based on the equipment maintenance record; a forecast consumption unit that generates forecast consumption data for spare parts by associating existing spare part inventory information, undelivered spare part information, inspection spare part consumption data, and maintenance spare part consumption data; 2. The facility maintenance management system according to claim 1, further comprising an adjustment unit that dynamically adjusts a material procurement plan using the predicted consumption data of the spare parts.

Images