Fault prediction-based intelligent operation and maintenance method and system for dual-system evaporative condenser

Abstract

The invention belongs to the technical field of condenser intelligent control, and discloses a fault prediction-based intelligent operation and maintenance method and system for a dual-system evaporative condenser, and the method comprises the steps: extracting and integrating detection data with timestamps from a plurality of label detection devices, carrying out the longitudinal and transverse analysis, and obtaining the information of a single device and a process device; an abnormal dynamic chart is extracted from the process equipment information, and an equipment abnormal matrix is generated and input into the main prediction unit for fault prediction; the results exceeding the co-occurrence threshold value are subjected to secondary verification through the standby prediction unit, and if the results are consistent, a fault is confirmed; the double verification mechanism and the dynamic anomaly detection capability significantly improve the accuracy and operation and maintenance efficiency of fault prediction, and the method is suitable for a scene with a high reliability requirement; and finally, based on the fault probability prediction trend, generating an operation and maintenance task and intervening in advance to realize intelligent operation and maintenance.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control of condensers. More specifically, the present invention relates to an intelligent operation and maintenance method and system for a dual-system evaporative condenser based on fault prediction. Background Art

[0002] Evaporative condensers are widely used in refrigeration, air conditioning, and industrial cooling systems. Their operating status directly affects the energy efficiency and stability of the system. Traditional operation and maintenance methods usually rely on regular maintenance or repair after a fault. Among them, regular maintenance may be excessive or insufficient and cannot accurately match the actual status of the equipment. Repair after a fault may lead to downtime and production losses; both lack early warning of potential faults; For example, Chinese Patent Publication No.: CN118860787A discloses an intelligent fault prediction method, device, equipment, medium, and product for operation and maintenance. It preprocesses operation and maintenance data and extracts key target fault features, solving problems such as the lack of fault prediction and intelligent warning capabilities. However, there are still the following problems: 1. The current fault prediction model has no inspection function for data missing or data delay. When there is a problem with the prediction result, it is impossible to determine whether it is an analysis result or a model fault; when a fault occurs in the equipment, the fault location cannot be obtained in time.

[0003] 2. Directly obtain the operating status of the equipment, and the collected data is overall packaged in the memory. A large amount of data increases the analysis difficulty and analysis time. In addition, the equipment itself is not analyzed. When a fault occurs, it is necessary to check the equipment faults one by one, with low efficiency.

[0004] In view of this, the present application proposes an intelligent operation and maintenance method and system for a dual-system evaporative condenser based on fault prediction. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention proposes an intelligent operation and maintenance method and system for a dual-system evaporative condenser based on fault prediction, which is used for fault prediction and operation and maintenance of the evaporative condenser to ensure the stable operation of the server cooling system.

[0006] In a first aspect, the present invention provides an intelligent operation and maintenance method for a dual-system evaporative condenser based on fault prediction, which is applied to a server and includes the following steps: Extract detection data from multiple independently operating tag detection devices, and integrate the detection data according to the location information to generate detection encapsulated data with a timestamp; Conduct vertical analysis on the target device nodes based on the encapsulation time node to obtain single-device information; conduct horizontal analysis on the single-device information of all target device nodes based on the working operation logic to obtain process device information; extract abnormal dynamic charts from the process device information; Extract the device anomaly matrix from the anomaly dynamic chart, send the device anomaly matrix to the fault prediction model corresponding to the main prediction unit to predict the device fault probability and the predicted fault location, and perform secondary verification on the data with the device fault probability exceeding the co-occurrence threshold through the fault prediction model corresponding to the backup prediction unit; if the results of the main prediction unit and the backup prediction unit are consistent, it is confirmed that the device where the location tag information is located has a fault; Predict the device fault trend based on the device fault probability to obtain the pending operation and maintenance tasks, and perform operation and maintenance intervention on the possible faults of the device in advance according to the pending operation and maintenance tasks.

[0007] As a preferred technical solution of the first aspect of the present invention, the marking logic of the tag detection device is as follows: Divide the fault types of the evaporative condenser based on the fault database, and determine the target device nodes based on the fault types. The target device nodes include the location tag information and the detection data; Build a local schematic map based on the location tag information; the local schematic map includes at least one location tag information, and each location tag information corresponds to at least one sensor installation point; at least one sensor is installed at each sensor installation point, and each sensor collects detection data based on the sampling frequency and the reporting interval; Integrate the corresponding detection data at the target device node to obtain the detection encapsulated data with a timestamp, store the detection encapsulated data in the storage module corresponding to the fault database, and use the location tag information as the retrieval guide to associate the detection encapsulated data based on the location tag information; and update the detection encapsulated data in real time.

[0008] As a preferred technical solution of the first aspect of the present invention, the integration logic of the detection encapsulated data is as follows: Statistically analyze the sampling frequencies and reporting intervals of all tag detection devices, determine the encapsulation time period based on prior knowledge, and mark the timestamp at the end of the encapsulation time period as the encapsulation time node, Obtain the corresponding detection data based on the sampling frequency within the encapsulation time period, integrate the detection data of the same type to obtain the detection encapsulated data. The detection encapsulated data includes standard detection data and abnormal detection data; during the integration process, determine the detection safety threshold and the detection change threshold corresponding to the detection data with adjacent timestamps based on prior knowledge; If the detection data is within the detection safety threshold range and the floating range of adjacent detection data is within the detection change threshold range, then use the average value of the detection data corresponding to all timestamps as the standard detection data within the encapsulation time period; Otherwise, the detection data within the encapsulation time period is successively subdivided, and the adjacent detection data within the detection safety threshold range and with the floating range of adjacent detection data within the detection change threshold range is integrated to update the local detection data, and all the local monitoring data is integrated and marked as abnormal detection data in matrix form.

[0009] As a preferred technical solution of the first aspect of the present invention, the acquisition logic of the single device information is as follows: Taking the same location tag information as the retrieval guide, based on the retrieval guide, extract it into a plane coordinate system, use the detected encapsulated data as the ordinate, the time stamp as the abscissa, and different encapsulated time nodes as the unit time length, and use different marking symbols for different types of detected encapsulated data; Extract abnormal feature variables from the abnormal detection data, where the abnormal feature variables correspond to the change curvature per unit time length; count the abnormal frequency of the change curvature within the unit time length; Perform probability assignment based on the abnormal frequency to obtain an abnormal probability, statistically count the abnormal probabilities corresponding to all the location tag information of the target device node with the time stamp, represent the standard detection data with a specific value, and represent it in matrix form as single device information with a time stamp.

[0010] As a preferred technical solution of the first aspect of the present invention, the acquisition logic of the process device information is as follows: Based on the evaporative condenser, progress segmentation is performed according to the working process to form a transition stage, count the single device information of all target device nodes corresponding to the transition stage, determine the process progress time based on the time stamp of the single device information, establish a process plane coordinate system with the working process as the retrieval guide, use the standard detection data as the ordinate, and the time stamp as the abscissa; Analyze the transition stage in the historical database to obtain the estimated progress time interval and the estimated progress information interval; represent the estimated progress time interval and the estimated progress information interval in the process plane coordinate system; If the standard detection data of the real-time monitored evaporative condenser is consistent with the estimated progress information interval, it indicates that the current detection data is normal. If the time progress process is less than or equal to the expected progress process, it indicates that the current working process is normal. Update the current process progress time to the estimated progress time interval and update and store it in the historical storage database in real time; If the time progress process is greater than the expected progress process, it indicates that the current process progress is abnormal. Obtain the feedback information of the staff in real time; and mark the process plane coordinate system, and mark the marked process plane coordinate system as the process device information.

[0011] As a preferred technical solution of the first aspect of the present invention, feedback information of the staff is obtained in real time, and the feedback information includes defects that can be eliminated and defects that cannot be eliminated; If the feedback information is a defect that can be eliminated, the staff is prompted to perform defect elimination processing and the defect elimination timestamp is recorded; the standard detection data and the cause of abnormal fluctuations are stored in the fault database for updating the normal fluctuation detection range; If the feedback information is a defect that cannot be eliminated, the staff is prompted to pay attention and view it, and the equipment is shut down in time and waiting for maintenance.

[0012] As a preferred technical solution of the first aspect of the present invention, the acquisition logic of the abnormal dynamic chart is as follows: Taking the process plane coordinate system corresponding to the process equipment information as the X-axis and Y-axis, taking the process progress time as the X-axis, and the vertical coordinate detection package data in the single equipment information as the Y-axis, and the detection type corresponding to the detection package data in the single equipment information is marked as the Z-axis; Constructing an abnormal dynamic chart corresponding to the process equipment information based on the execution relationship between the process progress time and the corresponding work process, and the abnormal dynamic chart is presented in the form of an AND-OR tree on the basis of a three-dimensional table; Among them, the AND-OR tree includes a node set, an edge set and the attributes of the edges. The root node in the node set indicates the end of the work process, and each non-root node represents a refined work process in the work process.

[0013] As a preferred technical solution of the first aspect of the present invention, the fault prediction module includes a feature extraction module, a main prediction unit and a standby prediction unit, wherein: the machine learning algorithms used by the main prediction unit 320 and the standby prediction unit to train the fault prediction model are the same. The device abnormal matrix required by the machine learning algorithm is extracted through the feature extraction module, and the device fault probability is output based on the device abnormal matrix.

[0014] As a preferred technical solution of the first aspect of the present invention, the application logic of the fault prediction model: Taking the device abnormal matrix as the input factor and the device fault probability as the output factor, the device abnormal matrix is a set of abnormal feature variables. The device abnormal matrix is constructed according to the abnormal probability in the single device information, and the rough set theory is used to optimize the device abnormal matrix. Using the optimized device abnormal matrix, calculate the device fault probability through the asymmetric importance factor and the separation information, and intuitively display the fault distribution to facilitate the rapid positioning of the operation and maintenance personnel.

[0015] Second aspect, the present invention provides an intelligent operation and maintenance system for a dual-system evaporative condenser based on fault prediction. Based on the implementation of the first aspect, it is applied to a server, and the server includes a data acquisition module, a data analysis module, a fault prediction module, and a maintenance control module; each module is connected by wire or wireless; The data acquisition module extracts detection data from multiple independently operating tag detection devices, integrates the detection data according to the location information to generate detection encapsulated data with timestamps, and sends the detection encapsulated data to the data analysis module; The data analysis module conducts vertical analysis on the target device nodes based on the encapsulation time nodes to obtain single-device information; conducts horizontal analysis on the single-device information of all target device nodes based on the working operation logic to obtain process device information; extracts abnormal dynamic charts from the process device information; sends the abnormal dynamic charts to the fault prediction module; The fault prediction module extracts a device anomaly matrix from the abnormal dynamic charts, sends the device anomaly matrix to the fault prediction model corresponding to the main prediction unit to predict the device fault probability and the predicted fault location, and conducts secondary verification on the data with the device fault probability exceeding the co-occurrence threshold through the fault prediction model corresponding to the backup prediction unit; if the results of the main prediction unit and the backup prediction unit are consistent, it is confirmed that the device where the location tag information is located has a fault; sends the device with the confirmed fault to the maintenance control module; The maintenance control module predicts the device fault trend based on the device fault probability to obtain the pending operation and maintenance tasks, and conducts operation and maintenance intervention on the possible faults of the device in advance according to the pending operation and maintenance tasks.

[0016] Technical effects and advantages of the intelligent operation and maintenance method and system for the dual-system evaporative condenser based on fault prediction of the present invention: Through data integration, anomaly detection, fault prediction, and proactive operation and maintenance intervention, the present invention realizes the intelligent operation and maintenance of the evaporative condenser in the server; the dual verification mechanism and dynamic anomaly detection ability significantly improve the accuracy of fault prediction and operation and maintenance efficiency, and are applicable to scenarios with high reliability requirements. Description of the Drawings

[0017] Figure 1 It is a schematic diagram of the intelligent operation and maintenance system for the dual-system evaporative condenser of the present invention; Figure 2 It is a partial system framework diagram of the fault prediction module of the present invention; Figure 3 It is a flowchart of the intelligent operation and maintenance method for the dual-system evaporative condenser of the present invention. Detailed Embodiments

[0018] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0019] Embodiment 1 Please refer to Figure 1 As shown, the intelligent operation and maintenance system of the dual-system evaporative condenser based on fault prediction in this embodiment is applied to a server. The server includes a data acquisition module 100, a data analysis module 200, a fault prediction module 300, and a maintenance control module 400; each module is connected by wire or wirelessly. The data acquisition module 100 extracts detection data from multiple independently operating tag detection devices, integrates the detection data according to the location information to generate detection encapsulated data with timestamps, and sends the detection encapsulated data to the data analysis module 200. It should be noted that: This embodiment is for upgrading the use of existing equipment, and there is no need to transform the existing equipment. Only detection devices need to be deployed at key positions of the evaporative condenser. The detection devices are mainly sensors, which have the characteristics of high precision, low power consumption, and corrosion resistance to adapt to the operating environment of the evaporative condenser. Sensors that transmit data in real time ensure that the operation and maintenance system can timely obtain the equipment operation status. However, during the real-time transmission process, it cannot be guaranteed that each sensor can transmit data in real time. Once a detection device fails or there is an abnormal delay, and the detection data itself is incorrect, even if the analysis result is correct, its analysis logic is based on incorrect data and cannot be popularized. In addition, a large amount of overlapping data will only increase the data analysis and calculation intensity of the system and increase the system burden. Therefore, in this embodiment, we use detection encapsulated data, configure the detection data according to the sampling frequency, reporting interval, and working mode parameters of the sensors at the detection device site; encapsulate the configured data and mark it with a timestamp, and then transmit it through the wireless communication module.

[0020] The current purpose of setting the sensors is to issue an alarm during an abnormality to prompt maintenance personnel to perform maintenance; it shows that the current equipment itself is equipped with detection devices. In addition, when the equipment issues an alarm, on the one hand, it may be the result of a false alarm due to a detection device failure, and on the other hand, it may be that the equipment cannot work properly, seriously affecting the production process.

[0021] Exemplarily, the tag detection devices include a temperature sensor, a pressure sensor, a flowmeter, and a vibration sensor with deployment position tag information; the detection data includes temperature values, pressure values, flow values, and vibration frequency values.

[0022] Specifically, the marking logic of the tag detection device is as follows: Based on the fault database, the fault types of the evaporative condenser are classified, and the target device nodes are determined based on the fault types. The target device nodes include the position tag information and detection data; Based on the position tag information, a local schematic map is built; the local schematic map includes at least one position tag information, and each position tag information corresponds to at least one sensor installation point; at least one sensor is installed at each sensor installation point, and each sensor collects detection data based on the sampling frequency and reporting interval; Integrate the detection data corresponding to the target device nodes to obtain detection encapsulated data with timestamps, store the detection encapsulated data in the storage module corresponding to the fault database, and use the position tag information as the retrieval guide to associate the detection encapsulated data based on the position tag information; and update the detection encapsulated data in real time.

[0023] Specifically, the integration logic of the detection encapsulated data is as follows: Statistically analyze the sampling frequencies and reporting intervals of all tag detection devices, determine the encapsulation time period based on prior knowledge, and mark the timestamp at the end of the encapsulation time period as the encapsulation time node, Obtain the corresponding detection data based on the sampling frequency within the encapsulation time period, integrate the detection data of the same type to obtain detection encapsulated data, and the detection encapsulated data includes standard detection data and abnormal detection data; during the integration process, determine the detection safety threshold and detection change threshold corresponding to the detection data with adjacent timestamps based on prior knowledge; If the detection data is within the detection safety threshold range and the floating range of adjacent detection data is within the detection change threshold range, then take the average value of the detection data corresponding to all timestamps as the standard detection data within the encapsulation time period; Otherwise, subdivide the detection data within the encapsulation time period in sequence, integrate and update the local detection data for the adjacent detection data where the detection data is within the detection safety threshold range and the floating range of adjacent detection data is within the detection change threshold range, and integrate and mark all the local monitoring data in matrix form as abnormal detection data.

[0024] The data analysis module 200 performs a vertical analysis on the target device nodes based on the encapsulation time node to obtain single-device information; performs a horizontal analysis on the single-device information of all target device nodes based on the working operation logic to obtain process device information; extracts an abnormal dynamic chart from the process device information; and sends the abnormal dynamic chart to the fault prediction module 300; Specifically, the acquisition logic of the single-device information is as follows: Using the same location tag information as the retrieval guide, extract it into a plane coordinate system based on the retrieval guide. Use the detected encapsulated data as the ordinate, the timestamp as the abscissa, and different encapsulated time nodes as the unit time length. Use different marking symbols for different types of detected encapsulated data; Extract abnormal feature variables from the abnormal detection data. The abnormal feature variables correspond to the change curvature of the unit time length; count the abnormal frequency of the change curvature within the unit time length; Obtain the abnormal probability based on the abnormal frequency. Statistically count the abnormal probabilities corresponding to all the location tag information of the target device node with the timestamp. Represent the standard detection data with a specific value and characterize it in matrix form as single device information with a timestamp.

[0025] It should be noted that: here, it is possible to quickly determine whether the device is in an abnormal state through simple comparison, reducing false alarms and missed alarms. Then, the status information is characterized in matrix form and has a timestamp, which can provide detailed device operation history and status change trends for the operation and maintenance personnel. The operation and maintenance personnel can focus on dealing with the confirmed abnormal devices and avoid unnecessary inspections and maintenance of normal devices. In addition, the discrete data is sent to the fault prediction module 300 in matrix form, reducing the packet loss rate during the transmission process.

[0026] Further explanation, the acquisition logic of the process device information is as follows: Based on the evaporative condenser, form transition stages according to the work process, count the single device information of all target device nodes corresponding to the transition stages, determine the process progress time based on the timestamp of the single device information, establish a process plane coordinate system with the work process as the retrieval guide, use the standard detection data as the ordinate, and the timestamp as the abscissa; Exemplarily illustrate that the transition stages include the refrigerant condensation stage, the spray water circulation stage, the heat exchange stage, the air flow stage, the heat dissipation stage, and the water circulation stage; Analyze the transition stages in the historical database to obtain the estimated progress time interval and the estimated progress information interval; represent the estimated progress time interval and the estimated progress information interval in the process plane coordinate system; If the standard detection data of the evaporative condenser monitored in real time is consistent with the estimated progress information interval, it indicates that the current detection data is normal. If the time progress process is less than or equal to the expected progress process, it indicates that the current work process is normal. Update the current process progress time to the estimated progress time interval and update it in real time to the historical storage database; When the time progress process is greater than the expected progress process, it indicates that the current process progress is abnormal. Obtain the feedback information of the staff in real time, and mark the process plane coordinate system, and mark the marked process plane coordinate system as the process device information.

[0027] Furthermore, obtain the feedback information of the staff in real time. The feedback information includes defects that can be eliminated and defects that cannot be eliminated. If the feedback information is a defect that can be eliminated, prompt the staff to perform defect elimination processing and record the defect elimination timestamp. Store the standard detection data and the cause of abnormal fluctuations in the fault database for updating the detection safety threshold and the detection change threshold. If the feedback information is a defect that cannot be eliminated, prompt the staff to pay attention and check, and turn off the equipment in time and wait for maintenance.

[0028] Furthermore, the acquisition logic of the abnormal dynamic chart is as follows: Take the process plane coordinate system corresponding to the process device information as the X-axis and Y-axis, take the process progress time as the X-axis, and the vertical coordinates of each detection encapsulation data in the single device information as the Y-axis. The detection type corresponding to the detection encapsulation data in the single device information is marked as the Z-axis. Construct the abnormal dynamic chart corresponding to the process device information based on the execution relationship between the process progress time and the corresponding work process. The abnormal dynamic chart is presented in the form of an AND-OR tree based on a three-dimensional table. Among them, the AND-OR tree includes a node set, an edge set, and the attributes of the edges. The root node in the node set indicates the end of the work process, and each non-root node represents a refined work process in the work process.

[0029] The fault prediction module 300 extracts the device anomaly matrix from the abnormal dynamic chart, sends the device anomaly matrix to the main prediction unit corresponding to the fault prediction model to predict the device fault probability and the predicted fault location, and performs secondary verification on the data with the device fault probability exceeding the co-occurrence threshold through the corresponding fault prediction model of the standby prediction unit. If the results of the main prediction unit and the standby prediction unit are consistent, confirm that the device where the location tag information is located has a fault, and send the device with the confirmed fault to the maintenance control module 400.

[0030] Specifically, as Figure 2 shown, the fault prediction module 300 includes a feature extraction module 310, a main prediction unit 320, and a standby prediction unit 330, where: the machine learning algorithms used by the main prediction unit 320 and the standby prediction unit 330 to train the fault prediction model are the same. The device anomaly matrix required by the machine learning algorithm is extracted through the feature extraction module 310, and the device fault probability is output based on the device anomaly matrix.

[0031] Application logic of the fault prediction model: Using the device anomaly matrix as the input factor and the device fault probability as the output factor, the device anomaly matrix is a set of anomaly feature variables. The device anomaly matrix is constructed based on the anomaly probabilities in the single device information and optimized using rough set theory. Using the optimized device anomaly matrix, the device fault probability is calculated through the asymmetric importance factor and the separation information, and the fault distribution is visually displayed to facilitate the quick positioning by the operation and maintenance personnel.

[0032] The maintenance control module 400 predicts the device fault trend based on the device fault probability to obtain the pending operation and maintenance tasks, and performs operation and maintenance intervention on the possible faults of the device in advance according to the pending operation and maintenance tasks.

[0033] Embodiment 2 Based on Embodiment 1, this embodiment provides an exemplary illustration. The server uses an evaporative condenser for heat dissipation and performs intelligent operation and maintenance using the above method, where: Install multiple independent temperature sensors, humidity sensors, and pressure sensors on the evaporative condenser, and send the temperature, humidity, and pressure data with time stamps and location tags collected by the sensors to the server corresponding to the evaporative condenser.

[0034] Inside the server, analyze the historical data of each sensor and extract the standard detection data of each sensor. For example, analyze the temperature change trend of a certain temperature sensor in the past week.

[0035] Based on the working logic of the evaporative condenser, perform horizontal analysis on the data of all sensors to extract the operation status information of the entire condenser. For example, analyze the relationship between temperature, humidity, and pressure to determine whether the condenser is within the normal working range.

[0036] Based on the process device information, extract the abnormal dynamic chart. For example, it is found that the temperature of a certain temperature sensor rises sharply within a short time and exceeds the normal range; send the abnormal features to the main prediction unit, and use the fault prediction model to predict the device fault probability and location. For example, predict that the probability of a certain temperature sensor having a fault is 80%. If the fault probability of the main prediction unit exceeds the co-occurrence threshold (e.g., 80%), the data will be sent to the backup prediction unit for secondary verification. If the backup prediction unit also predicts an 80% fault probability for this sensor, it is confirmed that the sensor may have a fault.

[0037] Predict the equipment failure trend based on the equipment failure probability. For example, predict that the temperature sensor may completely fail within the next 24 hours. According to the prediction results, arrange maintenance personnel to replace the temperature sensor in advance to prevent the server from crashing due to overheating. Thus, potential failures of the evaporative condenser can be detected and handled in advance to ensure the stable operation of the server. This not only improves the reliability of the equipment but also reduces the downtime and maintenance costs caused by failures.

[0038] Embodiment 3 Please refer to Figure 3 As shown, for the parts not described in detail in this embodiment, refer to the description in Embodiment 1. Provide an intelligent operation and maintenance method for a dual-system evaporative condenser based on failure prediction, which is applied to a server and includes the following steps: Extract detection data from multiple independently operating tag detection devices, and integrate the detection data according to the location information to generate detection encapsulated data with timestamps. Conduct a vertical analysis on the target device nodes based on the encapsulation time node to obtain single-device information; conduct a horizontal analysis on the single-device information of all target device nodes based on the working operation logic to obtain process equipment information; extract an abnormal dynamic chart from the process equipment information. Extract an equipment anomaly matrix from the abnormal dynamic chart, send the equipment anomaly matrix to the failure prediction model corresponding to the main prediction unit to predict the equipment failure probability and the predicted failure location, and conduct secondary verification on the data with the equipment failure probability exceeding the co-occurrence threshold through the failure prediction model corresponding to the backup prediction unit; if the results of the main prediction unit and the backup prediction unit are consistent, confirm that the device where the location tag information is located has failed. Predict the equipment failure trend based on the equipment failure probability to obtain the operation and maintenance tasks to be processed, and conduct operation and maintenance intervention on the possible failures of the equipment in advance according to the operation and maintenance tasks to be processed.

[0039] As a preferred technical solution of the first aspect of the present invention, the tagging logic of the tag detection device is as follows: Divide the failure types of the evaporative condenser based on the failure database, and determine the target device nodes based on the failure types. The target device nodes include the location tag information and the detection data. Build a local schematic map based on the location tag information; the local schematic map includes at least one location tag information, and each location tag information corresponds to at least one sensor installation point; at least one sensor is installed at each sensor installation point, and each sensor collects detection data based on the sampling frequency and the reporting interval. Integrate the detection data corresponding to the target device node to obtain the detection encapsulated data with timestamps, store the detection encapsulated data in the storage module corresponding to the fault database, and use the location tag information as the retrieval guide to associate the detection encapsulated data based on the location tag information; and update the detection encapsulated data in real time.

[0040] The integration logic of the detection encapsulated data is as follows: Statistically analyze the sampling frequencies and reporting intervals of all tag detection devices, determine the encapsulation time period based on prior knowledge, and mark the timestamp at the end of the encapsulation time period as the encapsulation time node. Obtain the corresponding detection data based on the sampling frequency within the encapsulation time period, integrate the detection data of the same type to obtain the detection encapsulated data, and the detection encapsulated data includes standard detection data and abnormal detection data; during the integration process, determine the detection safety threshold and detection change threshold corresponding to the detection data with adjacent timestamps based on prior knowledge. If the detection data is within the detection safety threshold range and the floating range of adjacent detection data is within the detection change threshold range, then use the average value of the detection data corresponding to all timestamps as the standard detection data within the encapsulation time period. Otherwise, subdivide the detection data within the encapsulation time period in sequence, integrate and update the local detection data for the adjacent detection data where the detection data is within the detection safety threshold range and the floating range of adjacent detection data is within the detection change threshold range, and integrate and mark all the local monitoring data in matrix form as abnormal detection data.

[0041] The acquisition logic of the single device information is as follows: Using the same location tag information as the retrieval guide, extract it into a plane coordinate system based on the retrieval guide. Taking the detection encapsulated data as the ordinate, the timestamp as the abscissa, and different encapsulation time nodes as the unit time length, use different marking symbols for different types of detection encapsulated data. Extract the abnormal feature variables from the abnormal detection data, and the abnormal feature variables correspond to the change curvature per unit time length; statistically analyze the abnormal frequency of the change curvature within the unit time length. Obtain the abnormal probability through probability assignment based on the abnormal frequency, statistically analyze the abnormal probabilities corresponding to all the location tag information of the target device node with timestamps, represent the standard detection data with specific values, and characterize it in matrix form as the single device information with timestamps.

[0042] The acquisition logic of the process equipment information is as follows: The evaporative condenser is segmented according to the working process to form a transition stage. The single device information of all target device nodes corresponding to the transition stage is counted, and the process progress time is determined based on the timestamps of the single device information. A process plane coordinate system is established with the working process as the retrieval guide, with the standard detection data as the ordinate and the timestamp as the abscissa; Based on the historical database, the estimated progress time interval and the estimated progress information interval are obtained through analysis of the transition stage; the estimated progress time interval and the estimated progress information interval are represented in the process plane coordinate system; If the standard detection data of the evaporative condenser monitored in real time is consistent with the estimated progress information interval, it indicates that the current detection data is normal. If the time progress process is less than or equal to the expected progress process, it indicates that the current working process is normal. The current process progress time is updated to the estimated progress time interval and stored in the historical storage database in real time; If the time progress process is greater than the expected progress process, it indicates that the current process progress is abnormal, and the feedback information of the staff is obtained in real time; and the process plane coordinate system is marked, and the marked process plane coordinate system is marked as the process device information.

[0043] The feedback information of the staff is obtained in real time, and the feedback information includes defects that can be eliminated and defects that cannot be eliminated; If the feedback information is a defect that can be eliminated, the staff is prompted to perform defect elimination processing and the defect elimination timestamp is recorded; the standard detection data and the cause of abnormal fluctuations are stored in the fault database for updating the normal fluctuation detection interval; If the feedback information is a defect that cannot be eliminated, the staff is prompted to pay attention and view it, and the equipment is turned off in time and waiting for repair.

[0044] The acquisition logic of the abnormal dynamic chart is as follows: Taking the process plane coordinate system corresponding to the process device information as the X-axis and Y-axis, the process progress time is aligned with the X-axis, and each detected encapsulated data in the ordinate of the single device information is aligned with the Y-axis, and the detection type corresponding to the detected encapsulated data in the single device information is marked as the Z-axis; The execution relationship between the process progress time and the corresponding working process is constructed to form the abnormal dynamic chart corresponding to the process device information. The abnormal dynamic chart is presented in the form of an AND-OR tree based on a three-dimensional table; Among them, the AND-OR tree includes a node set, an edge set, and the attributes of the edges. The root node in the node set indicates the end of the working process, and each non-root node represents a refined working process in the working process.

[0045] The fault prediction module 300 includes a feature extraction module 310, a primary prediction unit 320, and a backup prediction unit 330, where: the machine learning algorithms used by the primary prediction unit 320 and the backup prediction unit 330 to train the fault prediction model are the same. The device anomaly matrix required by the machine learning algorithm is extracted by the feature extraction module 310, and the device fault probability is output based on the device anomaly matrix.

[0046] The application logic of the fault prediction model: Taking the device anomaly matrix as the input factor and the device fault probability as the output factor, the device anomaly matrix is a set of anomaly feature variables. The device anomaly matrix is constructed according to the anomaly probability in the single device information, and the rough set theory is used to optimize the device anomaly matrix. Using the optimized device anomaly matrix, the device fault probability is calculated through the asymmetric importance factor and the separation information, and the fault distribution is intuitively displayed to facilitate the quick positioning of the operation and maintenance personnel.

[0047] Embodiment 4 An electronic device according to an exemplary embodiment includes: a processor and a memory, where a computer program that can be called by the processor is stored in the memory; The processor executes the above-mentioned intelligent operation and maintenance method for a dual-system evaporative condenser based on fault prediction by calling the computer program stored in the memory.

[0048] The electronic device provided by the embodiments of the present application may have relatively large differences due to different configurations or performances, and can include one or more processors (Central Processing Units, CPUs) and one or more memories. Among them, at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the intelligent operation and maintenance method for a dual-system evaporative condenser based on fault prediction provided by the above-mentioned various method embodiments. The electronic device can also include other components for implementing the functions of the device. For example, the electronic device can also have components such as wired or wireless network interfaces and input / output interfaces for input / output. The embodiments of the present application will not be elaborated here.

[0049] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0050] It should be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0051] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0052] Those of ordinary skill in the art will appreciate that the units and algorithm steps of the examples described in connection with the embodiments disclosed in the present invention can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0053] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0054] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one way, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings, direct couplings, or communication connections shown or discussed with each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms.

[0055] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed over multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0056] In addition, in each embodiment of the present invention, each functional unit may be integrated in a processing unit, may exist separately as individual physical units, or two or more units may be integrated in one unit.

[0057] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0058] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent operation and maintenance method for a dual-system evaporative condenser based on fault prediction, which is applied to a server, is characterized in that, It includes the following steps: Extract detection data from multiple independently operating tag detection devices, and integrate the detection data according to the location information to generate detection encapsulated data with timestamps; Perform vertical analysis on the target device nodes based on the encapsulation time node to obtain single device information; Perform horizontal analysis on the single device information of all target device nodes based on the working operation logic to obtain process device information; Extract the abnormal dynamic chart from the process device information; Extract the device anomaly matrix from the abnormal dynamic chart, send the device anomaly matrix to the fault prediction model corresponding to the main prediction unit to predict the device fault probability and the predicted fault location, and perform secondary verification on the data with the device fault probability exceeding the co-occurrence threshold through the fault prediction model corresponding to the backup prediction unit; if the results of the main prediction unit and the backup prediction unit are consistent, it is confirmed that the device where the location tag information is located has a fault; Predict the device fault trend based on the device fault probability to obtain the maintenance tasks to be processed, and perform maintenance intervention on the possible faults of the device in advance according to the maintenance tasks to be processed.

2. The intelligent operation and maintenance method of the dual-system evaporative condenser based on fault prediction according to claim 1, characterized in that: The tagging logic of the tag detection device is: Classify the fault types of the evaporative condenser based on the fault database, and determine the target device nodes based on the fault types. The target device nodes include the location tag information and the detection data; Build a local schematic map based on the location tag information; the local schematic map includes at least one location tag information, and each location tag information corresponds to at least one sensor installation point; at least one sensor is installed at each sensor installation point, and each sensor collects detection data based on the sampling frequency and the reporting interval; Integrate the corresponding detection data at the target device node to obtain detection encapsulated data with timestamps, store the detection encapsulated data in the storage module corresponding to the fault database, and use the location tag information as the retrieval guide to associate the detection encapsulated data based on the location tag information; And update the detection encapsulated data in real time.

3. The intelligent operation and maintenance method of the dual-system evaporative condenser based on fault prediction according to claim 2, characterized in that: The integration logic of the detection encapsulated data is: Statistically analyze the sampling frequencies and reporting intervals of all tag detection devices, determine the encapsulation time period based on prior knowledge, and mark the timestamp at the end of the encapsulation time period as the encapsulation time node, Obtain the corresponding detection data based on the sampling frequency within the encapsulation time period, and integrate the detection data of the same type to obtain detection encapsulated data. The detection encapsulated data includes standard detection data and abnormal detection data; During the integration process, determine the detection safety threshold and the detection change threshold corresponding to the detection data with adjacent timestamps based on prior knowledge; If the detection data is within the detection safety threshold range and the floating range of adjacent detection data is within the detection change threshold range, then use the average value of the detection data corresponding to all timestamps as the standard detection data within the encapsulation time period; Otherwise, subdivide the detection data within the encapsulation time period in turn, integrate and update the local detection data for the adjacent detection data where the detection data is within the detection safety threshold range and the floating range of adjacent detection data is within the detection change threshold range, and integrate and mark all the local monitoring data in matrix form as abnormal detection data.

4. The intelligent operation and maintenance method of the dual-system evaporative condenser based on fault prediction according to claim 3, characterized in that: The acquisition logic of the single device information is: Using the same location tag information as the retrieval guide, extract it into a plane coordinate system based on the retrieval guide. Taking the detected encapsulated data as the ordinate, the timestamp as the abscissa, and different encapsulated time nodes as the unit time length, different marking symbols are used for different types of detected encapsulated data; Extract the abnormal feature variables from the abnormal detection data, where the abnormal feature variables correspond to the change curvature of the unit time length; Statistically count the abnormal frequency of the change curvature within the unit time length; Obtain the abnormal probability based on the abnormal frequency. Statistically count the abnormal probabilities corresponding to all the location tag information of the target device node with the timestamp. Represent the standard detection data with a specific value and characterize it in matrix form as single device information with a timestamp.

5. The intelligent operation and maintenance method of the dual-system evaporative condenser based on fault prediction according to claim 4, characterized in that: The acquisition logic of the process device information is as follows: Based on the evaporative condenser, form a transition stage by segmenting the progress according to the working process. Statistically count the single device information of all target device nodes corresponding to the transition stage. Determine the process progress time based on the timestamp of the single device information. Establish a process plane coordinate system with the working process as the retrieval guide, taking the standard detection data as the ordinate and the timestamp as the abscissa; Analyze the transition stage in the historical database to obtain the estimated progress time interval and the estimated progress information interval; Represent the estimated progress time interval and the estimated progress information interval in the process plane coordinate system; If the standard detection data of the evaporative condenser monitored in real time is consistent with the estimated progress information interval, it indicates that the current detection data is normal. If the time progress process is less than or equal to the expected progress process, it indicates that the current working process is normal. Update the current process progress time to the estimated progress time interval and update and store it in the historical storage database in real time; If the time progress process is greater than the expected progress process, it indicates that the current process progress is abnormal. Obtain the feedback information of the staff in real time; and mark the process plane coordinate system, and mark the marked process plane coordinate system as the process device information.

6. The intelligent operation and maintenance method of the dual-system evaporative condenser based on fault prediction according to claim 5, characterized in that: Obtain the feedback information of the staff in real time, and the feedback information includes defects that can be eliminated and defects that cannot be eliminated; If the feedback information is a defect that can be eliminated, prompt the staff to perform defect elimination processing and record the defect elimination timestamp; Store the standard detection data and the cause of abnormal fluctuations in the fault database for updating the normal fluctuation detection interval; If the feedback information is a defect that cannot be eliminated, prompt the staff to pay attention and check, and turn off the equipment in time and wait for maintenance.

7. The intelligent operation and maintenance method of the dual-system evaporative condenser based on fault prediction according to claim 6, characterized in that: The acquisition logic of the abnormal dynamic chart is as follows: Using the process plane coordinate system corresponding to the process device information as the X-axis and Y-axis, the process progress time is aligned with the X-axis, each detected encapsulated data in the ordinate of the single device information is aligned with the Y-axis, and the detection type corresponding to the detected encapsulated data in the single device information is marked as the Z-axis; Construct the abnormal dynamic chart corresponding to the process device information based on the execution relationship between the process progress time and the corresponding working process. The abnormal dynamic chart is presented in the form of an AND-OR tree based on a three-dimensional table; Among them, the AND-OR tree includes a node set, an edge set, and edge attributes. The root node in the node set indicates the end of the workflow, and each non-root node represents a refined workflow in the workflow.

8. The intelligent operation and maintenance method of the dual-system evaporative condenser based on fault prediction according to claim 7, characterized in that: The fault prediction module (300) includes a feature extraction module (310), a primary prediction unit (320), and a backup prediction unit (330), where: the machine learning algorithms used by the primary prediction unit (320) and the backup prediction unit (330) to train the fault prediction model are the same. The device anomaly matrix required by the machine learning algorithm is extracted through the feature extraction module (310), and the device fault probability is output based on the device anomaly matrix.

9. The intelligent operation and maintenance method of the dual-system evaporative condenser based on fault prediction according to claim 8, characterized in that: The application logic of the fault prediction model: Using the device anomaly matrix as the input factor and the device fault probability as the output factor, the device anomaly matrix is a set of anomaly feature variables. The device anomaly matrix is constructed according to the anomaly probability in the single device information, and the rough set theory is used to optimize the device anomaly matrix. Using the optimized device anomaly matrix, the device fault probability is calculated through the asymmetric importance factor and the separation information, and the fault distribution is intuitively displayed to facilitate the rapid positioning of the operation and maintenance personnel.

10. An intelligent operation and maintenance system for a dual-system evaporative condenser based on fault prediction, which is implemented based on the intelligent operation and maintenance method for a dual-system evaporative condenser based on fault prediction according to any one of claims 1-9, characterized in that: Applied to a server, the server includes a data acquisition module (100), a data analysis module (200), a fault prediction module (300), and a maintenance control module (400); each module is connected by wire or wirelessly; The data acquisition module (100) extracts detection data from multiple independently operating tag detection devices, integrates the detection data according to the location information to generate timestamped detection encapsulated data, and sends the detection encapsulated data to the data analysis module (200); The data analysis module (200) performs vertical analysis on the target device nodes based on the encapsulated time node to obtain single device information; Performs horizontal analysis on the single device information of all target device nodes based on the work operation logic to obtain process device information; extracts an anomaly dynamic chart from the process device information; sends the anomaly dynamic chart to the fault prediction module (300); The fault prediction module (300) extracts the device anomaly matrix from the anomaly dynamic chart, sends the device anomaly matrix to the corresponding fault prediction model of the primary prediction unit to predict the device fault probability and the predicted fault location, and performs secondary verification on the data with the device fault probability exceeding the co-occurrence threshold through the corresponding fault prediction model of the backup prediction unit; if the results of the primary prediction unit and the backup prediction unit are the same, it is confirmed that the device where the location tag information is located has a fault; sends the device with the confirmed fault to the maintenance control module (400); The maintenance control module (400) predicts the device fault trend based on the device fault probability to obtain the pending operation and maintenance tasks, and performs operation and maintenance intervention on the possible faults of the device in advance according to the pending operation and maintenance tasks.

Images