Fault prediction method and device for intelligent operation and maintenance system

Abstract

The invention discloses a fault prediction method and device for an intelligent operation and maintenance system, and relates to the technical field of fault prediction. The method comprises the following steps: receiving a prediction request sent by a user side, and determining first equipment according to the prediction request; determining preset first monitoring data according to a first model corresponding to the first equipment; judging whether the first monitoring data is consistent with preset first monitoring data or not; when the first monitoring data is inconsistent with preset first monitoring data, determining that the first equipment has a first fault; obtaining a target association degree between the first device and the second device; judging whether the target association degree is greater than or equal to a preset association degree; and if the target association degree is greater than or equal to the preset association degree, determining that the first equipment and the second equipment have fault states, and sending the fault states to the user side, so that a user corresponding to the user side checks the fault states. By implementing the technical scheme provided by the invention, the operation and maintenance personnel have enough time to repair, and unnecessary loss caused by fault expansion is avoided.

Description

Technical Field

[0001] The present application relates to the technical field of fault prediction, and in particular to a fault prediction method and device for an intelligent operation and maintenance system. Background Art

[0002] With the deepening of the industrial era, industrial enterprises are increasingly relying on various types of equipment to improve production efficiency. However, equipment failures are inevitable during operation, which not only reduce production efficiency, but may also cause serious safety accidents. Therefore, it is particularly important to monitor equipment failures, which can detect and handle abnormal conditions of equipment at an early stage, thereby effectively preventing major accidents.

[0003] At present, in order to implement equipment failure monitoring more effectively, industrial enterprises tend to adopt intelligent operation and maintenance systems. The core of intelligent operation and maintenance systems is to comprehensively use cutting-edge technologies such as big data, machine learning, and artificial intelligence to conduct in-depth mining and detailed analysis of the large amount of data generated during daily operation and maintenance, so as to accurately identify potential problems and failures during equipment operation. However, the current intelligent operation and maintenance system can only analyze the failure of a single device, and the analysis is mostly limited to passive response after the failure occurs, rather than early warning of potential failures, resulting in unnecessary losses due to untimely maintenance.

[0004] Therefore, there is an urgent need for a fault prediction method and device for an intelligent operation and maintenance system that can solve the above-mentioned technical problems. Summary of the invention

[0005] The present application provides a fault prediction method and device for an intelligent operation and maintenance system. The method solves the problem that the current intelligent operation and maintenance system can only analyze the fault of a single device and the analysis is mostly limited to passive response after the fault occurs. This allows operation and maintenance personnel to have enough time to intervene and repair, avoiding unnecessary losses caused by the expansion of the fault.

[0006] In the first aspect, the present application provides a fault prediction method for an intelligent operation and maintenance system, the method comprising: receiving a prediction request sent by a user terminal, determining a first device according to the prediction request, the first device being any one of a plurality of devices to be monitored; obtaining first monitoring data corresponding to the first device, the first monitoring data comprising operation data, electrical data, vibration data and environmental data; determining preset first monitoring data according to a first model corresponding to the first device; determining whether the first monitoring data is consistent with the preset first monitoring data; when the first monitoring data is inconsistent with the preset first monitoring data, determining that a first fault exists in the first device; obtaining a target correlation between the first device and the second device; determining whether the target correlation is greater than or equal to the preset correlation; if the target correlation is greater than or equal to the preset correlation, determining that both the first device and the second device are in a fault state, and sending the fault state to the user terminal so that the user corresponding to the user terminal can view the fault state.

[0007] By adopting the above technical solution, the prediction request sent by the user end is received, and any one of the multiple monitored devices (the first device) is actively monitored, and its first monitoring data is obtained in real time. The preset first monitoring data is determined according to the model of the first device. This is based on the known parameters when the device is operating normally. The first monitoring data obtained in real time is compared with the preset first monitoring data, and data anomalies can be found in time, so as to determine whether the first device has a fault. When the first device has a first fault, the correlation between the first device and the second device is also obtained. If the target correlation between the first device and the second device is greater than or equal to the preset correlation, it can be inferred that the second device may also have potential risks. This correlation analysis helps to identify potential chain failures and further improve the accuracy and comprehensiveness of fault warnings. It successfully solves the problem that the current intelligent operation and maintenance system can only analyze the faults of a single device and the analysis is mostly limited to passive response after the fault occurs. Once a fault or potential fault is detected, an early warning can be issued before the fault occurs or in the early stage, so that the operation and maintenance personnel have enough time to intervene and repair, avoiding unnecessary losses caused by the expansion of the fault.

[0008] Optionally, obtaining a target correlation between the first device and the second device specifically includes: obtaining a first monitoring value corresponding to the first device, the first monitoring value including a first temperature, a first pressure value, a first vibration value, a first current value, a first voltage value and a first speed value; obtaining a second monitoring value corresponding to the second device, the second monitoring value including a second temperature, a second pressure value, a second vibration value, a second current value, a second voltage value and a second speed value; using a preset formula to calculate the first monitoring value and the second monitoring value to obtain multiple correlation values; determining multiple weights based on the multiple correlation values, one correlation value corresponding to one weight; multiplying each correlation value with the weight corresponding to each correlation value to obtain multiple target values; adding the multiple target values ​​to obtain the target correlation.

[0009] By adopting the above technical solution, multiple monitoring values ​​(including temperature, pressure, vibration, current, voltage and speed, etc.) of the first device and the second device are obtained, and the operating status of the device can be comprehensively evaluated. The first monitoring value and the second monitoring value are calculated using a preset formula to obtain multiple correlation values, which reflect the correlation between the two devices in different parameters. Multiple weights are determined based on the multiple correlation values, and one correlation value corresponds to one weight. Each correlation value is multiplied by the corresponding weight to obtain multiple target values, and then these target values ​​are added to obtain the target correlation. This comprehensive evaluation method can comprehensively consider multiple parameters and the correlation between them, so as to obtain a comprehensive and objective correlation evaluation result.

[0010] Optionally, a preset formula is used to calculate the first monitoring value and the second monitoring value to obtain multiple correlation values, specifically including: obtaining a first parameter from the first monitoring value, the first parameter including a first temperature, a first pressure value, a first vibration value, a first current value, a first voltage value, and a first speed value; obtaining a second parameter from the second monitoring value, the second parameter including a second temperature, a second pressure value, a second vibration value, a second current value, a second voltage value, and a second speed value; using a preset formula to calculate the first parameter and the second parameter to obtain multiple correlation values, the preset formula is as follows: ; Among them, r represents the correlation value, n represents the maximum value corresponding to the number of observations, and t1 ij represents the jth first parameter in the first monitoring value of the first device at the i-th observation time; t2 ij represents the jth second parameter in the second monitoring value of the second device at the i-th observation time; T1 j represents the average value of the jth first parameter of n observations in the first device, T2 j Represents the average value of the j-th second parameter of n observation times in the second device.

[0011] By adopting the above technical solution, the calculated correlation value can timely discover potential related failures between devices, and realize comprehensive and dynamic monitoring and analysis of device status.

[0012] Optionally, after determining whether the target association is greater than or equal to a preset association, the method further includes: when the target association is less than the preset association, obtaining a target device set that has a connection relationship with the first device; determining whether there is a second device in the target device set; and when the second device does not exist in the target device set, confirming that the second device is not in a fault state.

[0013] By adopting the above technical solution, when the target correlation is less than the preset correlation, first obtain the target device set that has a connection relationship with the first device. Determine whether the second device exists in the target device set. If not, it means that the correlation between the second device and the first device is not strong, or the connection relationship between them may not be tight. In this case, it can be confirmed that the second device does not have the same fault state as the first device, thereby avoiding unnecessary inspection and maintenance of the second device. By accurately determining whether the second device exists in the target device set, the false alarm rate caused by inaccurate correlation calculation can be reduced.

[0014] Optionally, after determining whether the second device exists in the target device set, the method further includes: if the second device exists in the target device set, determining that both the first device and the second device are in a fault state.

[0015] By adopting the above technical solution, when the target device set includes the second device, it means that there is a strong correlation between the first device and the second device. If the first device has a fault, then the second device is likely to be affected and has the same fault state, so the second device is also judged as a fault state, which can improve the accuracy of fault judgment and reduce the possibility of missed judgment.

[0016] Optionally, after determining whether the first monitoring data is consistent with the preset first monitoring data, the method also includes: when the first monitoring data is consistent with the preset first monitoring data, obtaining a target image corresponding to the first device; processing the target image to obtain target feature data; comparing the target feature data with the preset feature data; when the target feature data is inconsistent with the preset feature data, determining that the first device is in a damage fault state, and obtaining a target temperature corresponding to the first device based on the damage fault state; if the target temperature is greater than the preset temperature, determining that the first device has an overheating fault.

[0017] By adopting the above technical solution, the first monitoring data is compared with the preset first monitoring data, so that the operating status of the first device can be monitored in real time. When the first monitoring data is consistent with the preset first monitoring data, the target image is obtained for further analysis, which realizes continuous monitoring of the device status. Once it is found that the target feature data is inconsistent with the preset feature data, it can be immediately determined that the device is in a damaged fault state, so that an early warning can be issued in time to avoid further development of the fault. After determining that the device is in a damaged fault state, the target temperature of the device is further obtained and compared with the preset temperature. If the target temperature is higher than the preset temperature, it can be determined that the device has an overheating fault, which helps to promptly discover and deal with equipment damage or safety accidents that may be caused by overheating.

[0018] Optionally, if the target correlation is greater than or equal to the preset correlation, then after determining that both the first device and the second device are in a fault state, the method also includes: obtaining second monitoring data corresponding to the second device; determining preset second monitoring data based on the second model, the second model being the device model corresponding to the second device; when the second monitoring data is inconsistent with the preset second monitoring data, confirming that the second device has a second fault; inputting the first fault and the second fault into a preset operation and maintenance database for query, obtaining operation and maintenance measures, generating an operation and maintenance evaluation report based on the operation and maintenance measures, and sending the operation and maintenance evaluation report to the user end so that the user can perform repairs based on the operation and maintenance evaluation report.

[0019] By adopting the above technical solution, the second monitoring data of the second device is obtained, and compared with the preset second monitoring data determined according to the device model (second model), it is possible to accurately detect whether the second device has a fault (second fault). This customized monitoring data comparison based on the device model improves the accuracy and pertinence of fault detection. Once it is confirmed that the second device has a fault, the first fault and the second fault are immediately entered into the preset operation and maintenance database for query. This rapid fault information integration and query helps the operation and maintenance team to quickly obtain the corresponding operation and maintenance measures, thereby achieving timely response and processing of faults, reducing the time for manual intervention and decision-making, and improving the efficiency of operation and maintenance work.

[0020] In a second aspect of the present application, a fault prediction device for an intelligent operation and maintenance system is provided, the device comprising a receiving unit, a processing unit and a determining unit; the receiving unit receives a prediction request sent by a user terminal, determines a first device according to the prediction request, and the first device is any one of a plurality of devices to be monitored; obtains first monitoring data corresponding to the first device, and the first monitoring data comprises operation data, electrical data, vibration data and environmental data; the processing unit determines preset first monitoring data according to a first model corresponding to the first device; determines whether the first monitoring data is consistent with the preset first monitoring data; when the first monitoring data is inconsistent with the preset first monitoring data, determines that a first fault exists in the first device; obtains a target correlation between the first device and the second device; determines whether the target correlation is greater than or equal to the preset correlation; the determining unit determines that both the first device and the second device are in a fault state if the target correlation is greater than or equal to the preset correlation, and sends the fault state to the user terminal so that the user corresponding to the user terminal can view the fault state.

[0021] Optionally, the receiving unit is used to obtain a first monitoring value corresponding to the first device, the first monitoring value including a first temperature, a first pressure value, a first vibration value, a first current value, a first voltage value and a first speed value; obtain a second monitoring value corresponding to the second device, the second monitoring value including a second temperature, a second pressure value, a second vibration value, a second current value, a second voltage value and a second speed value; the processing unit is used to calculate the first monitoring value and the second monitoring value using a preset formula to obtain multiple correlation values; determine multiple weights based on the multiple correlation values, one correlation value corresponding to one weight; multiply each correlation value by the weight corresponding to each correlation value to obtain multiple target values; add the multiple target values ​​to obtain a target correlation degree.

[0022] Optionally, the processing unit is used to obtain a first parameter from the first monitoring value, the first parameter including a first temperature, a first pressure value, a first vibration value, a first current value, a first voltage value, and a first speed value; obtain a second parameter from the second monitoring value, the second parameter including a second temperature, a second pressure value, a second vibration value, a second current value, a second voltage value, and a second speed value; calculate the first parameter and the second parameter using a preset formula to obtain multiple correlation values, the preset formula is as follows: ; Among them, r represents the correlation value, n represents the maximum value corresponding to the number of observations, and t1 ij represents the jth first parameter in the first monitoring value of the first device at the i-th observation time; t2 ij represents the jth second parameter in the second monitoring value of the second device at the i-th observation time; T1 j represents the average value of the jth first parameter of n observations in the first device, T2 jRepresents the average value of the j-th second parameter of n observation times in the second device.

[0023] Optionally, the receiving unit is used to obtain a set of target devices that are connected to the first device when the target correlation is less than a preset correlation; the processing unit is used to determine whether there is a second device in the target device set; and the determination unit is used to confirm that the second device is not in a fault state when the second device does not exist in the target device set.

[0024] Optionally, the determining unit is configured to determine that both the first device and the second device are in a fault state if the second device exists in the target device set.

[0025] Optionally, the receiving unit is used to obtain a target image corresponding to the first device when the first monitoring data is consistent with the preset first monitoring data; the processing unit is used to process the target image to obtain target feature data; and compare the target feature data with the preset feature data; the determination unit is used to determine that the first device is in a damage fault state when the target feature data is inconsistent with the preset feature data, and obtain a target temperature corresponding to the first device according to the damage fault state; if the target temperature is greater than the preset temperature, it is determined that the first device has an overheating fault.

[0026] Optionally, the receiving unit is used to obtain second monitoring data corresponding to the second device; the processing unit is used to determine preset second monitoring data based on the second model, where the second model is the device model corresponding to the second device; the determination unit is used to confirm that a second fault exists in the second device when the second monitoring data is inconsistent with the preset second monitoring data; the first fault and the second fault are input into a preset operation and maintenance database for query, to obtain operation and maintenance measures, to generate an operation and maintenance evaluation report based on the operation and maintenance measures, and to send the operation and maintenance evaluation report to the user end so that the user can perform maintenance according to the operation and maintenance evaluation report.

[0027] In a third aspect of the present application, an electronic device is provided, which includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory, so that an electronic device executes any one of the methods described above in the present application.

[0028] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any one of the above methods of the present application is executed.

[0029] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Receive the prediction request sent by the user end, actively monitor any one of the multiple devices to be monitored (the first device), and obtain its first monitoring data in real time. Determine the preset first monitoring data according to the model of the first device. This is based on the known parameters when the device is operating normally. Compare the first monitoring data obtained in real time with the preset first monitoring data, and timely find data anomalies, so as to determine whether the first device has a fault. When the first device has a first fault, the correlation between the first device and the second device is also obtained. If the target correlation between the first device and the second device is greater than or equal to the preset correlation, it can be inferred that the second device may also have potential risks. This correlation analysis helps to identify potential chain failures and further improve the accuracy and comprehensiveness of fault warnings. It successfully solves the problem that the current intelligent operation and maintenance system can only analyze the failure of a single device and the analysis is mostly limited to passive response after the failure occurs. Once a fault or potential fault is detected, an early warning can be issued before the fault occurs or in the early stage, so that the operation and maintenance personnel have enough time to intervene and repair, avoiding unnecessary losses caused by the expansion of the fault.

[0030] 2. Obtain the second monitoring data of the second device and compare it with the preset second monitoring data determined according to the device model (second model), so as to accurately detect whether the second device has a fault (second fault). This customized monitoring data comparison based on the device model improves the accuracy and pertinence of fault detection. Once it is confirmed that the second device has a fault, the first fault and the second fault are immediately entered into the preset operation and maintenance database for query. This rapid fault information integration and query helps the operation and maintenance team to quickly obtain the corresponding operation and maintenance measures, thereby achieving timely response and processing of faults, reducing the time for manual intervention and decision-making, and improving the efficiency of operation and maintenance work. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flowchart of a fault prediction method for an intelligent operation and maintenance system provided in an embodiment of the present application; Figure 2 It is a structural schematic diagram of a fault prediction device for an intelligent operation and maintenance system provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application.

[0032] Description of reference numerals: 201, receiving unit; 202, processing unit; 203, determining unit; 300, electronic device; 301, processor; 302, memory; 303, user interface; 304, network interface; 305, communication bus. DETAILED DESCRIPTION

[0033] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0034] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0035] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0036] With the deepening of the industrial era, industrial enterprises are increasingly relying on various types of equipment to improve production efficiency. However, equipment failures are inevitable during operation, which not only reduce production efficiency, but may also cause serious safety accidents. Therefore, it is particularly important to monitor equipment failures, which can detect and handle abnormal conditions of equipment at an early stage, thereby effectively preventing major accidents.

[0037] At present, in order to implement equipment failure monitoring more effectively, industrial enterprises tend to adopt intelligent operation and maintenance systems. The core of the intelligent operation and maintenance system is to comprehensively use cutting-edge technologies such as big data, machine learning, and artificial intelligence to conduct in-depth mining and fine analysis of the large amount of data generated during daily operation and maintenance, so as to accurately identify potential problems and failures during equipment operation. However, the current intelligent operation and maintenance system still relies on regular manual inspections to collect monitoring data. The collected monitoring data is then analyzed, and this analysis is mostly limited to passive response after the failure occurs, rather than early warning of potential failures, resulting in unnecessary losses due to untimely maintenance.

[0038] Therefore, how to solve the problem that the current intelligent operation and maintenance system relies on manual regular inspections and passive responses after failures. A fault prediction method for an intelligent operation and maintenance system provided in an embodiment of the present application is applied to a server. The server of the present application can be a platform that provides fault prediction services for the intelligent operation and maintenance system. Figure 1 is a flowchart of a fault prediction method for an intelligent operation and maintenance system provided in an embodiment of the present application, with reference to Figure 1 The method includes the following steps S101-S107.

[0039] S101: Receive a prediction request sent by a user terminal, and determine a first device according to the prediction request.

[0040] In the above S101, the user sends a prediction request to the server through the user terminal. The user refers to the staff responsible for the daily operation and maintenance of the equipment. The server receives the prediction request sent by the user terminal. After receiving the prediction request, it is necessary to parse the content of the prediction request and identify the prediction request therein. Extract device information from the parsed prediction request, including device ID, device name or device type, etc. According to the extracted device information, search and determine the first device among multiple devices to be monitored.

[0041] S102: Determine preset first monitoring data according to a first model corresponding to the first device.

[0042] In the above S102, after determining the first device, a connection is established with the first device through a communication protocol (such as Modbus, OPC UA, etc.). A sensor is installed at the first device in advance so that data can be collected from the first device through the sensor to obtain the first monitoring data. The first monitoring data includes operation data, electrical data, vibration data and environmental data. The operation data refers to the operation time, operation speed and load conditions; the electrical data refers to current, voltage, power and resistance. Vibration data refers to vibration amplitude, vibration frequency and vibration phase. Environmental data refers to the temperature, humidity, air pressure and light of the environment surrounding the first device. After obtaining the first monitoring data, the model information of the first device is obtained from the system database, and the corresponding preset first monitoring data is queried in the preset data standard library according to the device model. At this time, the preset first monitoring data refers to the threshold values ​​corresponding to various parameters when the first device is in normal operation. At this time, the preset first monitoring data includes preset operation data, preset electrical data, preset vibration data and preset environmental data.

[0043] S103: Determine whether the first monitoring data is consistent with the preset first monitoring data.

[0044] In the above S103, the collected first monitoring data is compared with the preset first monitoring data, and according to the comparison result, it is determined whether the first device is in a fault state.

[0045] S104: When the first monitoring data is inconsistent with the preset first monitoring data, it is determined that a first fault exists in the first device.

[0046] In the above S104, each data in the first monitoring data is compared with each data in the preset first monitoring data in turn. If a data in the first monitoring data is not within the range of the preset monitoring data, it can be assumed that the first monitoring data is inconsistent with the preset first monitoring data, and it can be determined that the first device has a fault. What kind of fault exists can be determined based on the inconsistent monitoring data, and no further explanation is given here. At this time, the first device can be marked as a fault state.

[0047] S105: Obtain a target association degree between the first device and the second device.

[0048] In the above S105, after determining that the first device has a fault, it is necessary to analyze other devices among the multiple devices to be monitored to analyze whether the fault of the first device will affect other devices, thereby identifying potential faults and giving early warnings in a timely manner. Since the multiple devices to be monitored are connected through a network, it is necessary to obtain the correlation between the first device and the other devices, and identify the potential faults of other devices based on the correlation.

[0049] In addition, obtaining the target correlation between the first device and the second device specifically includes: obtaining a first monitoring value corresponding to the first device, the first monitoring value including a first temperature, a first pressure value, a first vibration value, a first current value, a first voltage value and a first speed value; obtaining a second monitoring value corresponding to the second device, the second monitoring value including a second temperature, a second pressure value, a second vibration value, a second current value, a second voltage value and a second speed value; using a preset formula to calculate the first monitoring value and the second monitoring value to obtain a plurality of correlation values; determining a plurality of weights according to the plurality of correlation values, one correlation value corresponding to one weight; multiplying each correlation value by the weight corresponding to each correlation value to obtain a plurality of target values; adding the plurality of target values ​​to obtain the target correlation.

[0050] Specifically, a second device is selected from the devices to be monitored, and the second device is any device other than the first device among the multiple devices to be monitored. The first operating parameters corresponding to the first device can be obtained in real time by connecting the sensor of the first device. These first operating parameters include the first temperature, the first pressure value, the first vibration value, the first current value, the first voltage value and the first speed value. When collecting again, the operating parameters corresponding to the first device at different time points can be obtained, and these first operating parameters are recorded to obtain the first monitoring value, and each first monitoring value includes the operating parameters corresponding to the first device at different time points. Then, the second operating parameters are obtained by connecting the sensor of the second device. These second operating parameters include the second temperature, the second pressure value, the second vibration value, the second current value, the second voltage value and the second speed value. After the collection process, similar to the first device, the operating parameters corresponding to the second device at different time points are obtained. It is necessary to ensure that the time point corresponding to the acquisition of the operating parameters by the second device must be consistent with the time point of the first device, that is, at the same time point, the first device and the second device obtain their respective corresponding operating parameters and record them. For example, when monitoring the temperature of a device, the temperature of the first device and the second device at different time points are obtained. Five time points are selected for recording, namely time point 1, time point 2, time point 3, time point 4 and time point 5. At time point 1, the first temperature corresponding to the first device is 22°C, and the second temperature corresponding to the second device is 24°C; at time point 2, the first temperature corresponding to the first device is 23°C, and the second temperature corresponding to the second device is 25°C; at time point 3, the first temperature corresponding to the first device is 25°C, and the second temperature corresponding to the second device is 26°C; at time point 4, the first temperature corresponding to the first device is 27°C, and the second temperature corresponding to the second device is 28°C; at time point 5, the first temperature corresponding to the first device is 29°C, and the second temperature corresponding to the second device is 30°C; at this time, the first temperature of the first device at different time points is summarized to obtain the first temperature. Then, the second temperature of the second device at different time points is summarized to obtain the second temperature. Subsequently, the pressure, vibration, current and voltage are continuously monitored in the same manner as the temperature is monitored to obtain respective first pressure values ​​and second pressure values, etc. After obtaining the first monitoring value corresponding to the first device and the second monitoring value corresponding to the second device.

[0051] Further, the first monitoring value and the second monitoring value are calculated using a preset formula to obtain a plurality of correlation values, specifically including: obtaining a first parameter from the first monitoring value, the first parameter including a first temperature, a first pressure value, a first vibration value, a first current value, a first voltage value, and a first speed value; obtaining a second parameter from the second monitoring value, the second parameter including a second temperature, a second pressure value, a second vibration value, a second current value, a second voltage value, and a second speed value; calculating the first parameter and the second parameter using a preset formula to obtain a plurality of correlation values, the preset formula is as follows: ; Among them, r represents the correlation value, n represents the maximum value corresponding to the number of observations, and t1 ij represents the jth first parameter in the first monitoring value of the first device at the i-th observation time; t2 ij represents the jth second parameter in the second monitoring value of the second device at the i-th observation time; T1 j represents the average value of the jth first parameter of n observations in the first device, T2 j Represents the average value of the j-th second parameter of n observation times in the second device.

[0052] In the preset formula, n represents the total number of times a parameter (first parameter or second parameter) is obtained at different time points. One time point corresponds to one observation number, and one observation moment corresponds to one observation number. If the temperature at 5 time points is selected, n is 5. ij Indicates the jth first parameter in the first monitoring value of the first device at the i-th observation time. Since each first parameter includes multiple monitoring values, if j is 1, according to the sorting results of each parameter in the current first parameter, it is confirmed that the first parameter is the first temperature. When the first parameter is the first temperature, 5 monitoring values ​​of the first device at 5 time points are obtained, and one time point corresponds to one monitoring value. ij It indicates the jth second parameter in the second monitoring value of the second device at the i-th observation time. If j is 1, according to the sorting result of each parameter in the current second parameter, the second parameter is the second temperature. The first parameter and the second parameter are calculated, that is, the first temperature in the first device and the second temperature in the second device are correlated. When the correlation calculation is performed, it is necessary to ensure that the correlation calculation is performed between temperature and temperature, and the correlation calculation is performed between pressure and pressure. When j is 2, according to the sorting result of each parameter in the first parameter, the first parameter is the first pressure value, and according to the sorting result of each parameter in the second parameter, the second parameter is the second pressure value. T1 j represents the average value of the jth first parameter of n observations in the first device, T1 jIt can be understood as obtaining the average value of the jth first parameter of the first device at multiple time points. Since each first parameter contains multiple monitoring values, the multiple monitoring values ​​are superimposed to obtain the total monitoring value, and then divided by the number of monitoring values, which refers to the total number of multiple monitoring values, to obtain the average value of the first device. j represents the average value of the jth second parameter of n observations in the second device, T2 j It can be understood as obtaining the average value of the jth second parameter of the second device at multiple time points. Since each second parameter contains multiple second monitoring values, the multiple second monitoring values ​​are superimposed to obtain the second total monitoring value, and then divided by the second monitoring number, which refers to the total number of multiple second monitoring values, to obtain the average value of the second device. Calculate the multiple first temperature values ​​in the above first temperature, T1 of the first device j =(22+23+25+27+29) / 5=25.2, then calculate the second temperature value in the above second temperature, T2 of the second device j =(24+25+26+28+30) / 5=26.6.

[0053] Then start calculating the difference. For each observation time i and each parameter j, calculate t1 ij -T1 j and t2 ij -T2 j , and then calculate the numerator, for all observation times i and parameters j, calculate (t1 ij -T1 j )(t2 ij -T2 j ), and then calculate the denominator separately. If the numerator is 27 and the denominator is 26, then divide the numerator by the denominator to get the coherence value r. At this time, the coherence value represents the degree of correlation between the first device and the second device for the first first parameter and the second parameter. The first first parameter and the second parameter represent the temperature of the two devices. Repeat the above steps to calculate the other parameters in the first device and the second device to obtain the correlation value of each parameter. Then determine the weight according to the situation of each parameter, and assign the weight according to the importance of the monitoring value to the device status assessment. For example, if temperature is a key indicator for determining whether the device is overheated, a higher weight is given. The correlation value itself can be used as a basis for the weight, but it usually needs to be normalized or standardized to ensure that the sum of all weights is 1. Multiply each correlation value by its corresponding weight to obtain the target value. Add all the target values ​​to obtain the target correlation between the two devices.

[0054] For example, according to the above calculation method, the correlation calculation is performed on each parameter of the first device and the second device in turn to obtain multiple correlation values, and the weights of temperature, pressure, vibration, current, voltage, and speed can be assigned as 0.3, 0.2, 0.1, 0.15, 0.15, and 0.1 respectively. Then, each correlation value is multiplied by its weight, and then the sum is obtained to obtain the target correlation degree.

[0055] S106: Determine whether the target correlation is greater than or equal to a preset correlation.

[0056] In the above S106, after the target correlation between the first device and the second device is obtained by calculation, the calculated target correlation is compared with a preset correlation, where the preset correlation is a correlation set to determine whether the two devices will affect each other.

[0057] S107: If the target correlation is greater than or equal to the preset correlation, it is determined that both the first device and the second device are in a fault state, and the fault state is sent to the user terminal so that the user corresponding to the user terminal can view the fault state.

[0058] In the above S107, if the target correlation is greater than or equal to the preset correlation, it means that there is a strong correlation between the first device and the second device. When the first device fails, the second device will be affected by the failure of the first device, so it is determined that the second device is also in a fault state.

[0059] In addition, after determining that the second device is affected by the failure of the first device, it is necessary to monitor the operating data of the second device in real time to monitor the potential failure of the second device, which specifically includes: obtaining the second monitoring data corresponding to the second device; determining the preset second monitoring data according to the second model, the second model is the device model corresponding to the second device; when the second monitoring data is inconsistent with the preset second monitoring data, confirming that the second device has a second failure; inputting the first failure and the second failure into the preset operation and maintenance database for query, obtaining the operation and maintenance measures, and generating the operation and maintenance evaluation report according to the operation and maintenance measures, so as to send the operation and maintenance evaluation report to the user end. Specifically, sensors or other monitoring devices are deployed on the second device to monitor the operating status of the second device in real time. The sensors may include temperature sensors, pressure sensors, vibration sensors, etc., depending on the type of the second device and the parameters to be monitored. The second monitoring data of the second device is collected in real time by the sensors, and these data may include temperature, pressure, vibration amplitude, current, voltage, etc. The frequency and accuracy of data collection should be set according to the characteristics of the second device and the monitoring requirements. The collected second monitoring data is sent to the server to obtain the model information of the second device, which can usually be obtained through the device label, device manual or records in the device management system. According to the model of the second device, the corresponding preset second monitoring data is searched from the preset monitoring data table. The preset data is usually set according to the normal operating status of the device, the manufacturer's recommendations or industry standards. If the operating status or working environment of the second device changes, or the device is repaired or parts are replaced, the preset monitoring data may need to be updated. Compare the second monitoring data collected in real time with the preset second monitoring data. If the second monitoring data exceeds the preset range or threshold, or there is a significant inconsistency with the preset data, it is determined that the second device has a fault. The fault type may be determined based on the exceeded parameters and degree, such as overheating, overvoltage, excessive vibration, etc. A preset operation and maintenance database is established in advance, which contains information such as various equipment fault types, fault causes, operation and maintenance measures and solutions. The database can be constructed based on historical operation and maintenance data, manufacturer's recommendations, industry standards or expert experience. The type, description and related information of the first fault and the second fault are entered into the operation and maintenance database. Use the database query function to find the corresponding operation and maintenance measures and solutions based on the input fault information. Generate an operation and maintenance evaluation report based on the queried operation and maintenance measures and solutions. The report should include key information such as fault type, cause, recommended operation and maintenance measures, expected effect, implementation time, etc. Select an appropriate method to send the operation and maintenance assessment report to the user end, such as email, SMS notification, APP push, etc. Receive feedback from the user end on the operation and maintenance assessment report to understand the user's acceptance of the operation and maintenance measures and solutions and the implementation effect. Follow-up tracking and optimization can be carried out based on user feedback to improve operation and maintenance efficiency and equipment reliability.If the second monitoring data is consistent with the preset second monitoring data, the second device needs to be marked so as to subsequently monitor the marked device in real time.

[0060] Further, when the target correlation is less than the preset correlation, a target device set that has a connection relationship with the first device is obtained; whether the second device exists in the target device set is determined; when the second device does not exist in the target device set, it is confirmed that the second device does not have a fault state. Specifically, the correlation value calculated previously is used to evaluate the correlation between the first device and the current suspected faulty device (the second device). The preset correlation is a pre-set threshold used to determine whether the target correlation is high enough to confirm that there is a significant correlation between the first device and the suspected faulty device. The calculated target correlation is compared with the preset correlation. When the target correlation is less than the preset correlation, all devices that have a connection relationship with the first device need to be obtained to form a target device set. The connection relationship may be based on physical connections (such as wires, pipes, etc.), communication connections (such as networks, signals, etc.) or logical connections (such as program calls, data sharing, etc.), depending on the scenario requirements of the actual device. For each device in the target device set, its basic information (such as device type, model, location, etc.) and operating status information (such as temperature, pressure, vibration, current, voltage, speed, etc.) need to be collected. This information can be obtained through sensors, data acquisition systems or remote services, depending on the geographical location and communication conditions of the device. After obtaining the target device set, it is necessary to check whether the second device is included in it. This is achieved by comparing the unique identifier of the second device (such as device ID, MAC address, etc.) or fuzzy matching based on information such as device name and model. If the second device does not exist in the target device set, it can be preliminarily confirmed that the second device is not in the current suspected fault state. This means that the association between the second device and the first device is not enough to regard it as part of the faulty device, or the second device itself is not affected by the fault. It can effectively determine whether the second device is in a faulty state and provide strong support for subsequent troubleshooting and repair work. In addition, if the second device exists in the target device set, it is determined that both the first device and the second device are in a faulty state. In the constructed target device set, the second device has been confirmed to be included by comparing the device identifier, name or other relevant information. Since the second device is included in the target device set, it indicates that there is a certain degree of association between it and the first device. This association may be based on physical connection, communication connection, data sharing or logical dependency. Based on the fact that the target device set includes the second device and the correlation between the first device and the second device, it can be inferred that there may be a common failure mode or failure cause between the first device and the second device. It can be confirmed that both the first device and the second device are in a failure state, and it is predicted that the second device has a potential failure.

[0061] Furthermore, by real-time monitoring of the image corresponding to the first device, the image is analyzed to determine the type of fault in the device, specifically including: when the first monitoring data is consistent with the preset first monitoring data, the target image corresponding to the first device is obtained; the target image is processed to obtain target feature data; the target feature data is compared with the preset feature data; when the target feature data is inconsistent with the preset feature data, it is determined that the first device has a damage fault state, and the target temperature corresponding to the first device is obtained according to the damage fault state; if the target temperature is greater than the preset temperature, it is determined that the first device has an overheating fault. Specifically, the obtained first monitoring data is compared with the preset first monitoring data. The preset first monitoring data is a threshold or range set according to the normal operating state of the device. When the elevator monitoring data is consistent with the preset first monitoring data, it is preliminarily determined that the corresponding device has no fault, and at this time, it is necessary to obtain the image of the device for further analysis. Image acquisition devices such as cameras and infrared thermal imagers can be used to select appropriate image acquisition methods and parameters according to the actual situation of the device and monitoring requirements. The obtained target image is preprocessed, including denoising, enhancement, filtering and other operations to improve the quality and clarity of the image. According to the needs and goals of image processing, select appropriate image processing algorithms and tools, such as image filtering, edge detection, binarization, etc. In the preprocessed image, extract the feature data related to the target analysis. These feature data may include the texture, shape, color, brightness, etc. of the image. Traditional image processing methods, such as image filtering, edge detection, etc., can be used, or machine learning methods, such as support vector machines, decision trees, etc., or deep learning methods, such as convolutional neural networks (CNN), etc., can be used to extract feature data. Compare the extracted target feature data with the preset feature data. The preset feature data is set according to the normal operating state or known fault state of the equipment. According to the comparison result, determine whether the target feature data is consistent with the preset feature data. If they are consistent, it means that the equipment may be in a normal operating state; if they are inconsistent, it means that the equipment may have some kind of fault or abnormality. When the target feature data is inconsistent with the preset feature data, determine the damage fault state of the equipment. The fault state may include information such as the fault type and fault degree. According to the determined damage fault state, select a suitable temperature sensor or temperature measuring device to obtain the target temperature corresponding to the equipment. The target temperature may include the surface temperature and internal temperature of the equipment. You can use infrared thermometers, thermocouples, resistance thermometers and other temperature measuring devices. According to the actual situation of the equipment and the temperature measurement requirements, select the appropriate temperature measurement method and parameters. Compare the obtained target temperature with the preset temperature. The preset temperature is set according to the normal operation status of the equipment and the maximum allowable temperature. If the target temperature is greater than the preset temperature, it means that the equipment has an overheating fault. Overheating may cause the performance of the equipment to decline, shorten its life, or even damage it.According to the actual situation of the equipment and the cause of the overheating failure, take corresponding measures to repair and maintain to ensure the normal operation and safety of the equipment. If the target temperature is less than or equal to the preset temperature, it means that the first equipment does not have an overheating failure, and the first equipment is in normal operation.

[0062] The present application also provides a fault prediction device for an intelligent operation and maintenance system. Figure 2 is a schematic diagram of a fault prediction device for an intelligent operation and maintenance system provided in an embodiment of the present application, with reference to Figure 2 The device includes a receiving unit 201, a processing unit 202 and a determining unit 203.

[0063] The receiving unit 201 receives a prediction request sent by the user terminal, determines a first device according to the prediction request, and the first device is any one of multiple devices to be monitored; obtains first monitoring data corresponding to the first device, and the first monitoring data includes operation data, electrical data, vibration data and environmental data.

[0064] The processing unit 202 determines the preset first monitoring data according to the first model corresponding to the first device; determines whether the first monitoring data is consistent with the preset first monitoring data; when the first monitoring data is inconsistent with the preset first monitoring data, determines that the first device has a first fault; obtains the target correlation between the first device and the second device; and determines whether the target correlation is greater than or equal to the preset correlation.

[0065] The determination unit 203 determines that both the first device and the second device are in a fault state if the target correlation is greater than or equal to the preset correlation, and sends the fault state to the user terminal so that the user corresponding to the user terminal can view the fault state.

[0066] In a possible implementation, the receiving unit 201 is used to obtain a first monitoring value corresponding to a first device, the first monitoring value including a first temperature, a first pressure value, a first vibration value, a first current value, a first voltage value and a first speed value; obtain a second monitoring value corresponding to a second device, the second monitoring value including a second temperature, a second pressure value, a second vibration value, a second current value, a second voltage value and a second speed value; the processing unit 202 is used to calculate the first monitoring value and the second monitoring value using a preset formula to obtain multiple correlation values; determine multiple weights based on the multiple correlation values, one correlation value corresponding to one weight; multiply each correlation value by the weight corresponding to each correlation value to obtain multiple target values; add the multiple target values ​​to obtain a target correlation degree.

[0067] In a possible implementation, the processing unit 202 is used to obtain a first parameter from a first monitoring value, where the first parameter includes a first temperature, a first pressure value, a first vibration value, a first current value, a first voltage value, and a first speed value; obtain a second parameter from a second monitoring value, where the second parameter includes a second temperature, a second pressure value, a second vibration value, a second current value, a second voltage value, and a second speed value; and calculate the first parameter and the second parameter using a preset formula to obtain a plurality of correlation values, where the preset formula is as follows: ; Among them, r represents the correlation value, n represents the maximum value corresponding to the number of observations, and t1 ij represents the jth first parameter in the first monitoring value of the first device at the i-th observation time; t2 ij represents the jth second parameter in the second monitoring value of the second device at the i-th observation time; T1 j represents the average value of the jth first parameter of n observations in the first device, T2 j Represents the average value of the j-th second parameter of n observation times in the second device.

[0068] In one possible implementation, the receiving unit 201 is used to obtain a target device set that has a connection relationship with the first device when the target correlation degree is less than a preset correlation degree; the processing unit 202 is used to determine whether there is a second device in the target device set; and the determination unit 203 is used to confirm that the second device is not in a fault state when the second device does not exist in the target device set.

[0069] In a possible implementation manner, the determining unit 203 is configured to determine that both the first device and the second device are in a fault state if the second device exists in the target device set.

[0070] In a possible implementation, the receiving unit 201 is used to obtain a target image corresponding to the first device when the first monitoring data is consistent with the preset first monitoring data; the processing unit 202 is used to process the target image to obtain target feature data; and compare the target feature data with the preset feature data; the determination unit 203 is used to determine that the first device is in a damage fault state when the target feature data is inconsistent with the preset feature data, and obtain a target temperature corresponding to the first device according to the damage fault state; if the target temperature is greater than the preset temperature, it is determined that the first device has an overheating fault.

[0071] In a possible implementation, the receiving unit 201 is used to obtain second monitoring data corresponding to the second device; the processing unit 202 is used to determine preset second monitoring data based on the second model, where the second model is the device model corresponding to the second device; the determination unit 203 is used to confirm that the second device has a second fault when the second monitoring data is inconsistent with the preset second monitoring data; the first fault and the second fault are input into a preset operation and maintenance database for query to obtain operation and maintenance measures, an operation and maintenance evaluation report is generated based on the operation and maintenance measures, and the operation and maintenance evaluation report is sent to the user end so that the user can perform maintenance according to the operation and maintenance evaluation report.

[0072] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0073] The present application also discloses an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 302 , and at least one communication bus 305 .

[0074] The communication bus 305 is used to realize the connection and communication between these components.

[0075] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0076] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0077] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 302, and calling data stored in the memory 302. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application requests; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0078] Among them, the memory 302 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 302 includes a non-transitory computer-readable storage medium. The memory 302 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 302 may include a program storage area and a data storage area, wherein the program storage area. Instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. can be stored; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 302 can also be optionally at least one storage device located away from the aforementioned processor 301.

[0079] like Figure 3 As shown, the memory 302 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for fault prediction of the intelligent operation and maintenance system.

[0080] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 301 can be used to call the application program for fault prediction of the intelligent operation and maintenance system stored in the memory 302. When executed by one or more processors, the electronic device executes one or more methods described in the above embodiments.

[0081] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0082] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0083] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0084] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0086] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0087] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any variation, use or adaptive change of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure.

Claims

1. A fault prediction method for an intelligent operation and maintenance system, characterized in that: The method comprises: receiving a prediction request sent by a user terminal, and determining a first device according to the prediction request, where the first device is any one of a plurality of devices to be monitored; Acquire first monitoring data corresponding to the first device, the first monitoring data including operation data, electrical data, vibration data, and environmental data; Determine preset first monitoring data according to a first model corresponding to the first device; Determining whether the first monitoring data is consistent with the preset first monitoring data; When the first monitoring data is inconsistent with the preset first monitoring data, determining that a first fault exists in the first device; Acquire a target association degree between the first device and the second device; Determining whether the target correlation is greater than or equal to a preset correlation; If the target correlation is greater than or equal to the preset correlation, it is determined that both the first device and the second device are in a fault state, and the fault state is sent to the user terminal so that a user corresponding to the user terminal can view the fault state.

2. The method according to claim 1, characterized in that The obtaining of the target association degree between the first device and the second device specifically includes: Acquire a first monitoring value corresponding to the first device, the first monitoring value comprising a first temperature, a first pressure value, a first vibration value, a first current value, a first voltage value, and a first speed value; Acquire a second monitoring value corresponding to the second device, the second monitoring value comprising a second temperature, a second pressure value, a second vibration value, a second current value, a second voltage value, and a second speed value; Calculate the first monitoring value and the second monitoring value using a preset formula to obtain multiple correlation values; Determine a plurality of weights according to the plurality of correlation values, wherein one correlation value corresponds to one weight; Multiplying each of the correlation values ​​by a weight corresponding to each of the correlation values ​​to obtain a plurality of target values; A plurality of the target values ​​are added together to obtain the target correlation degree.

3. The method according to claim 2, characterized in that The using a preset formula to calculate the first monitoring value and the second monitoring value to obtain multiple correlation values ​​specifically includes: Acquire a first parameter from the first monitoring value, where the first parameter includes the first temperature, the first pressure value, the first vibration value, the first current value, the first voltage value, and the first speed value; Acquire a second parameter from the second monitoring value, where the second parameter includes the second temperature, the second pressure value, the second vibration value, the second current value, the second voltage value, and the second speed value; The first parameter and the second parameter are calculated using the preset formula to obtain a plurality of correlation values, and the preset formula is as follows: ; Where r represents the correlation value, n represents the maximum value corresponding to the number of observations, t1 ij represents the jth first parameter in the first monitoring value of the first device at the i-th observation time; t2 ij represents the jth second parameter in the second monitoring value of the second device at the i-th observation time; T1 j represents the average value of the jth first parameter of n observation times in the first device, T2 j Represents the average value of the j-th second parameter of n observation times in the second device.

4. The method according to claim 1, characterized in that: After determining whether the target correlation is greater than or equal to a preset correlation, the method further includes: When the target association degree is less than the preset association degree, acquiring a target device set having a connection relationship with the first device; Determine whether the second device exists in the target device set; When the second device does not exist in the target device, it is confirmed that the second device does not have the fault state.

5. The method according to claim 4, characterized in that After determining whether the second device exists in the target device set, the method further includes: If the second device exists in the target device set, it is determined that both the first device and the second device are in the fault state.

6. The method according to claim 1, characterized in that After determining whether the first monitoring data is consistent with the preset first monitoring data, the method further includes: When the first monitoring data is consistent with the preset first monitoring data, acquiring a target image corresponding to the first device; Processing the target image to obtain target feature data; Comparing the target characteristic data with preset characteristic data; When the target characteristic data is inconsistent with the preset characteristic data, it is determined that the first device is in a damage fault state, and a target temperature corresponding to the first device is obtained according to the damage fault state; If the target temperature is greater than a preset temperature, it is determined that the first device has an overheating fault.

7. The method according to claim 1, characterized in that After determining that both the first device and the second device are in a fault state if the target correlation is greater than or equal to the preset correlation, the method further includes: Acquire second monitoring data corresponding to the second device; Determine preset second monitoring data according to a second model, where the second model is a device model corresponding to the second device; When the second monitoring data is inconsistent with the preset second monitoring data, confirming that the second device has a second fault; The first fault and the second fault are input into a preset operation and maintenance database for query to obtain operation and maintenance measures, an operation and maintenance evaluation report is generated according to the operation and maintenance measures, and the operation and maintenance evaluation report is sent to the user end so that the user can perform maintenance according to the operation and maintenance evaluation report.

8. A fault prediction device for an intelligent operation and maintenance system, characterized in that: The device comprises a receiving unit (201), a processing unit (202) and a determining unit (203), The receiving unit (201) receives a prediction request sent by a user terminal, determines a first device according to the prediction request, and the first device is any one of a plurality of devices to be monitored; obtains first monitoring data corresponding to the first device, and the first monitoring data includes operation data, electrical data, vibration data, and environmental data; The processing unit (202) determines preset first monitoring data according to a first model corresponding to the first device; determines whether the first monitoring data is consistent with the preset first monitoring data; when the first monitoring data is inconsistent with the preset first monitoring data, determines that the first device has a first fault; obtains a target correlation between the first device and the second device; and determines whether the target correlation is greater than or equal to a preset correlation; The determination unit (203) determines that both the first device and the second device are in a fault state if the target correlation is greater than or equal to the preset correlation, and sends the fault state to the user terminal so that a user corresponding to the user terminal can view the fault state.

9. An electronic device, characterized in that: The electronic device (300) comprises a processor (301), a memory (302), a user interface (303) and a network interface (304), wherein the memory (302) is used to store instructions, the user interface (303) and the network interface (304) are used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (302) so that the electronic device (300) executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images