A method, device and medium for determining equipment status based on fault prediction

Abstract

The present application discloses a method, device and medium for determining the state of an equipment based on fault prediction, which not only obtains the real-time monitoring data of the target equipment, but also obtains the real-time monitoring data of the equipment associated with the target equipment, and considers more comprehensive factors. The root cause of the fault state is determined based on the knowledge graph, the actual posterior probability of all root causes is analyzed and the state of the target equipment is determined. Compared with directly determining the state of the target equipment based on monitoring data that can only reflect the appearance, the accuracy of determining the state of the equipment is improved, and the problem of delay between determining the state of the equipment based on the monitoring data and the actual state is effectively overcome. In addition, a time series prediction analysis is performed based on the actual posterior probability to obtain the predicted posterior probability within a preset time period in the future. The equipment state is determined based on the actual posterior probability and the predicted posterior probability of all root causes, which can provide insight into the equipment state earlier and serve as a warning.

Description

Technical Field

[0001] The present application relates to the technical field of fault information processing, and in particular to a method, apparatus, and medium for determining a device state based on fault prediction. Background Art

[0002] Currently, most large-scale industrial equipment has established online monitoring systems. Based on the monitoring data, the working status of the equipment can be understood, helping operation and maintenance managers to grasp the operating status of the equipment at any time, which is of great significance for ensuring equipment safety and normal production.

[0003] Since monitoring data is generally superficial, there may be many root causes of the superficial causes. Directly determining the equipment status based on monitoring data has low accuracy. In addition, there is often a large delay from the root cause of the fault to the superficial cause, resulting in a delay between directly determining the equipment status based on monitoring data and the actual situation.

[0004] Therefore, how to improve the accuracy of determining the device status and effectively overcome the delay between determining the device status directly based on monitoring data and the actual situation is an urgent problem that technicians in this field need to solve. Summary of the Invention

[0005] The purpose of this application is to provide a method, device and computer-readable storage medium for determining equipment status based on fault prediction, which is used to improve the accuracy of equipment status determination and effectively overcome the problem of delay between determining equipment status based on monitoring data and actual conditions.

[0006] To solve the above technical problems, the present application provides a method for determining device status based on fault prediction, comprising:

[0007] Acquire real-time monitoring data of a target device and its associated devices;

[0008] Calculating the current fault status of the target device and the associated device based on the real-time monitoring data;

[0009] Determine the root cause of the fault state according to the knowledge graph, and calculate the actual posterior probability of each root cause according to the fault state;

[0010] The actual posterior probabilities are sorted by time, and time series forecast analysis is performed to obtain a posterior probability change curve for each root cause within a future preset time period;

[0011] The predicted posterior probability within the future preset time period is obtained according to the posterior probability change curve, and the state of the target device is determined according to the actual posterior probabilities and the predicted posterior probabilities of all the root causes of the target device.

[0012] Preferably, determining the root cause of the fault state according to the knowledge graph and calculating the actual posterior probability of each root cause according to the fault state includes:

[0013] Determine, based on the knowledge graph, the root cause corresponding to the fault state and the state information fed back by the user;

[0014] According to the fault state and the state information, the actual posterior probability of each root cause is calculated using any one of a variable elimination algorithm, a clique tree propagation algorithm, a random sampling algorithm, and a variational method.

[0015] Preferably, after obtaining the posterior probability change curve of each root cause within a preset future time period, the method further includes:

[0016] The fault development trend is determined according to the time required for the posterior probability in the posterior probability change curve of each root cause to rise to a preset height.

[0017] Preferably, determining the state of the target device according to the actual a posteriori probabilities and the predicted a posteriori probabilities of all the root causes of the target device includes:

[0018] Calculating a weighted posterior probability of each of the root causes according to the actual posterior probability and the predicted posterior probability;

[0019] determining a priori probabilities for each of said root causes;

[0020] Calculating the occurrence probability gain of each of the root causes according to the prior probability and the weighted posterior probability;

[0021] Generate a fault root cause set according to all the root causes corresponding to the fault state and the state information fed back by the user;

[0022] Calculating the deviation of the target device state according to the root cause severity and the occurrence probability gain of all the root causes in the fault root cause set;

[0023] Calculating the health of the target device according to the deviation;

[0024] The status of the target device is determined according to the health level.

[0025] Preferably, determining the status of the target device according to the health level includes:

[0026] Comparing the health degree with a health grade table to determine the health grade of the device and a treatment recommendation to determine the status of the target device;

[0027] The health level table includes the corresponding relationship between health degree, health level and treatment suggestions, and the treatment suggestions include the need for immediate maintenance, attention to equipment operating status and normal operation.

[0028] Preferably, determining the root cause of the fault state according to the knowledge graph includes:

[0029] Constructing the knowledge graph based on historical data, expert experience data, and professional book data;

[0030] Determining the root cause of the fault state according to the knowledge graph;

[0031] The knowledge graph includes the logical relationships among equipment, monitoring data, status information, faults, and treatment measures.

[0032] Preferably, after determining the status of the target device, the method further includes:

[0033] If the target device is in an abnormal state, determining the root cause with a higher actual a posteriori probability;

[0034] The knowledge graph and the root cause with a higher actual posterior probability are used to perform fault analysis and determine fault handling measures.

[0035] The present application also provides a device for determining a device state based on fault prediction, comprising:

[0036] An acquisition module, configured to acquire real-time monitoring data of a target device and its associated devices;

[0037] A first calculation module, configured to calculate the current fault status of the target device and the associated device based on the real-time monitoring data;

[0038] A second calculation module is used to determine the root cause of the fault state according to the knowledge graph, and calculate the actual posterior probability of each root cause according to the fault state;

[0039] A prediction module is used to sort the actual posterior probabilities by time and perform time series prediction analysis to obtain a posterior probability change curve for each root cause within a future preset time period;

[0040] A determination module is configured to obtain a predicted posterior probability within the future preset time period according to the posterior probability change curve, and determine the state of the target device according to the actual posterior probabilities and the predicted posterior probabilities of all the root causes of the target device.

[0041] The present application also provides a device state determination apparatus based on fault prediction, comprising a memory for storing a computer program;

[0042] A processor is configured to implement the steps of the method for determining a device state based on fault prediction when executing the computer program.

[0043] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for determining the device state based on fault prediction are implemented.

[0044] The present application provides a method for determining the state of an equipment based on fault prediction, which not only obtains the real-time monitoring data of the target equipment, but also obtains the real-time monitoring data of the equipment associated with the target equipment, and considers more comprehensive factors. The root cause of the fault state is determined based on the knowledge graph, the actual posterior probability of all root causes is analyzed, and the state of the target equipment is determined. Compared with directly determining the state of the target equipment based on monitoring data that can only reflect the appearance, the accuracy of determining the state of the equipment is improved, and the problem of delay between determining the state of the equipment based on the monitoring data and the actual state is effectively overcome. In addition, a time series prediction analysis is performed based on the actual posterior probability to obtain the predicted posterior probability within a preset time period in the future. The equipment state is determined based on the actual posterior probability and the predicted posterior probability of all root causes, which can provide insight into the equipment state earlier and serve as a warning.

[0045] The device and medium provided in this application correspond to a device and method for determining the state of equipment based on fault prediction, and the effects are as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0047] Figure 1 A flowchart of a method for determining a device state based on fault prediction provided in an embodiment of the present application;

[0048] Figure 2 A Bayesian network diagram provided in an embodiment of the present application;

[0049] Figure 3 A structural diagram of a device for determining a device state based on fault prediction provided in an embodiment of the present application;

[0050] Figure 4 This is a structural diagram of another device for determining equipment status based on fault prediction provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0052] The core of this application is to provide a method, device and computer-readable storage medium for determining equipment status based on fault prediction.

[0053] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0054] Figure 1 This is a flow chart of a method for determining a device state based on fault prediction provided in an embodiment of the present application. Figure 1 As shown, the device status determination method includes:

[0055] S10: Acquire real-time monitoring data of the target device and its associated devices.

[0056] S11: Calculate the current fault status of the target device and associated devices based on the real-time monitoring data.

[0057] S12: Determine the root cause of the fault state based on the knowledge graph, and calculate the actual posterior probability of each root cause based on the fault state.

[0058] S13: Sort the actual posterior probabilities by time, and perform time series forecast analysis to obtain a posterior probability change curve for each root cause within a future preset time period.

[0059] S14: Obtain the predicted posterior probability within a future preset time period according to the posterior probability change curve, and determine the state of the target device according to the actual posterior probabilities and the predicted posterior probabilities of all root causes of the target device.

[0060] In step S10, the real-time monitoring data is real-time monitoring data regularly acquired from the online monitoring system. The embodiment of the present application acquires not only the real-time monitoring data of the target device, but also the real-time monitoring data of the devices associated with the target device.

[0061] In step S11, the current fault status of the target device and associated devices is calculated based on the real-time monitoring data. The embodiment of the present application does not specifically limit how to calculate the fault status and the number of fault states. For example, if the monitoring data is the bearing temperature c, the calculation formula for the fault state e corresponding to the fault of increased bearing temperature is as follows.

[0062]

[0063] In step S12, the knowledge graph can be an existing one or can be based on historical data, expert experience data, professional book data, etc., to model the equipment, monitoring data, status information, faults, treatment measures and the logical relationships between them to build a knowledge graph of the equipment. The actual posterior probability of each root cause is calculated. Specifically, a Bayesian network of the correlation between faults can be obtained based on the knowledge graph, such as Figure 2 As shown, Figure 2 In this embodiment of the present application, a Bayesian network diagram is provided. The two rightmost nodes, "Oil Level Rise 1" and "Bearing Temperature Rise 2," serve as evidence, with their fault state denoted as E. The three leftmost nodes, "Cooler Leakage 3," "Lubricant Aging 4," and "Cooling Water Interruption 5," serve as the root cause Q. The calculated actual posterior probability is P(Q|E=e). The actual posterior probability in this embodiment of the present application is calculated based on the fault state calculated from the real-time monitoring data acquired at each time. This embodiment of the present application does not specifically limit the number of actual posterior probabilities.

[0064] In step S13, the actual posterior probability of each root cause is arranged in chronological order and time series forecast analysis is performed. Available methods include but are not limited to simple averaging, sliding window averaging, exponential smoothing, differential integrated moving average autoregressive model, etc., to predict the posterior probability change curve within a preset time period in the future.

[0065] In step S14, a predicted posterior probability is obtained based on the posterior probability change curve. The predicted posterior probability is not calculated based on the fault state, but is predicted based on the existing actual posterior probability. This embodiment of the application does not specifically limit how to determine the state of the target device based on the actual posterior probability and the predicted posterior probability.

[0066] The embodiment of the present application provides a method for determining the state of an apparatus based on fault prediction, which not only obtains the real-time monitoring data of the target apparatus, but also obtains the real-time monitoring data of the apparatus associated with the target apparatus, and considers more comprehensive factors. The root cause of the fault state is determined based on the knowledge graph, the actual posterior probabilities of all root causes are analyzed, and the state of the target apparatus is determined. Compared with directly determining the state of the target apparatus based on monitoring data that can only reflect the appearance, the accuracy of determining the state of the apparatus is improved, and the problem of a delay between determining the state of the apparatus based on the monitoring data and the actual state is effectively overcome. In addition, a time series prediction analysis is performed based on the actual posterior probability to obtain the predicted posterior probability within a preset time period in the future. The apparatus state is determined based on the actual posterior probability and the predicted posterior probability of all root causes, which can provide insight into the apparatus state earlier and serve as a warning.

[0067] Based on the above embodiments, the embodiments of the present application determine the root cause of the fault state according to the knowledge graph, and calculate the actual posterior probability of each root cause according to the fault state, including: determining the root cause corresponding to the fault state and the status information fed back by the user according to the knowledge graph; according to the fault state and the status information, using any one of the variable elimination algorithm, clique tree propagation algorithm, random sampling algorithm, and variational method to calculate the actual posterior probability of each root cause.

[0068] The embodiment of the present application not only calculates the fault status based on the monitoring data, but also performs a comprehensive analysis based on other status information fed back by the user to determine all possible root causes, so the factors considered in the equipment status evaluation are more comprehensive.

[0069] Based on the above embodiment, after obtaining the posterior probability change curve of each root cause within a preset future time period, the embodiment of the present application further includes: determining the fault development trend based on the time required for the posterior probability in the posterior probability change curve of each root cause to rise to a preset height.

[0070] The embodiment of the present application does not specifically limit the preset height. The horizontal axis of the posterior probability change curve represents time, and the vertical axis represents the posterior probability. The posterior probability includes the actual posterior probability and the predicted posterior probability. The preset height can be the height of the posterior probability from 0 to 0.1. The fault development trend is determined based on the time required for the posterior probability to rise to the preset height. Specifically, if the time required for the actual posterior probability to reach the preset height in the most recent time is greater than 3 days, the development trend is stable. If it is from 8 hours to 3 days, the development trend is slowly deteriorating. If it is less than 8 hours, the development trend is rapidly deteriorating. The above is only a method for determining the fault development trend provided by the embodiment of the present application. In a specific real-time scenario, it can be determined according to the actual situation. The embodiment of the present application takes into account the fault development trend and can gain insight into the abnormality of the equipment status earlier.

[0071] Based on the above embodiments, the embodiments of the present application determine the state of the target device based on the actual posterior probability and the predicted posterior probability of all root causes of the target device, including: calculating the weighted posterior probability of each root cause based on the actual posterior probability and the predicted posterior probability; determining the prior probability of each root cause; calculating the occurrence probability gain of each root cause based on the prior probability and the weighted posterior probability; generating a fault root cause set based on all root causes corresponding to the fault state and the status information fed back by the user; calculating the deviation of the target device state based on the root cause severity and the occurrence probability gain of all root causes in the fault root cause set; calculating the health of the target device based on the deviation; and determining the state of the target device based on the health.

[0072] In the embodiment of the present application, the actual posterior probability and the predicted posterior probability are p i , weighting coefficient ρ (0<ρ<1), the calculation formula of weighted posterior probability p is

[0073] The prior probability is p0, and the calculation formula for the occurrence probability gain f is as follows.

[0074]

[0075] The set of fault root causes R is weighted according to the severity s of the root cause to calculate the deviation F of the equipment state. The calculation formula is:

[0076] The health level H of the target device is calculated based on the deviation F. The calculation formula is as follows.

[0077]

[0078] Based on the above embodiment, Table 1 is a health level table provided in the embodiment of the present application. The health level table includes health degree, health level, and treatment suggestions; treatment suggestions include the need for immediate maintenance, attention to equipment operating status, and normal operation. By comparing the health degree with the health table, the health level and treatment suggestions can be directly derived. If the health degree is 0.5, the health level is poor, and the treatment suggestion is the need for immediate maintenance. Determining the status of the target equipment based on the health table is more direct and also convenient for guiding maintenance personnel to quickly determine whether to perform maintenance.

[0079] Table 1 Health level table

[0080] Serial number Health Health Level Disposal suggestions 1 [0,0.6) Difference Immediate maintenance required 2 [0.6,0.9) middle Pay attention to the operating status of the equipment 3 [0.9,1] excellent Normal operation

[0081] Based on the above embodiments, after determining the status of the target device, the embodiments of the present application also include: if the target device is in an abnormal state, determining the root cause with a higher actual a posteriori probability; using the knowledge graph and the root cause with a higher actual a posteriori probability to perform fault analysis and determine the fault handling measures.

[0082] Since the knowledge graph includes equipment, monitoring data, status information, faults, treatment measures and the logical relationships between them, the fault status and status information can be determined based on the root cause with a higher posterior probability. Reasoning based on the knowledge graph can be performed to determine the fault treatment measures and propose maintenance plans for operation and maintenance personnel.

[0083] If the target device is in poor condition, possible faults and treatment measures will be given to help operation and maintenance personnel locate and treat the fault more quickly and restore the device status.

[0084] In the above embodiments, a method for determining a device state based on fault prediction is described in detail. This application also provides corresponding embodiments of an apparatus for determining a device state based on fault prediction. It should be noted that this application describes embodiments of the apparatus from two perspectives: one from a functional module perspective and the other from a hardware perspective.

[0085] Figure 3 This is a structural diagram of a device state determination device based on fault prediction provided in an embodiment of the present application, such as Figure 3 As shown, the device status determination device includes:

[0086] An acquisition module 10 is used to acquire real-time monitoring data of a target device and its associated devices;

[0087] A first calculation module 11 is used to calculate the current fault status of the target device and associated devices based on real-time monitoring data;

[0088] A second calculation module 12 is used to determine the root cause of the fault state based on the knowledge graph and calculate the actual posterior probability of each root cause based on the fault state;

[0089] The prediction module 13 is used to sort the actual posterior probabilities by time and perform time series prediction analysis to obtain a posterior probability change curve for each root cause within a preset future time period;

[0090] The determination module 14 is configured to obtain a predicted posterior probability within a preset future time period according to the posterior probability change curve, and determine the state of the target device according to the actual posterior probabilities and the predicted posterior probabilities of all root causes of the target device.

[0091] Based on the above embodiment, as a preferred embodiment, the second calculation module includes:

[0092] A first determining unit is configured to determine a root cause corresponding to the fault state and the state information fed back by the user based on the knowledge graph;

[0093] The first calculation unit is used to calculate the actual posterior probability of each root cause according to the fault state and state information by using any one of a variable elimination algorithm, a clique tree propagation algorithm, a random sampling algorithm, and a variational method.

[0094] Based on the above embodiment, as a preferred embodiment, it also includes:

[0095] The fault development trend determination module is used to determine the fault development trend according to the time required for the posterior probability in the posterior probability change curve of each root cause to rise to a preset height.

[0096] Based on the above embodiment, as a preferred embodiment, the determination module includes:

[0097] A second calculation unit is used to calculate the weighted posterior probability of each root cause according to the actual posterior probability and the predicted posterior probability;

[0098] a second determining unit, configured to determine a priori probability of each root cause;

[0099] a third calculation unit, configured to calculate an occurrence probability gain of each root cause according to the prior probability and the weighted posterior probability;

[0100] A generating unit, configured to generate a fault root cause set based on all root causes corresponding to the fault state and the state information fed back by the user;

[0101] a fourth calculation unit, configured to calculate a deviation of a target device state according to the root cause severity and the occurrence probability gain of all root causes in the fault root cause set;

[0102] a fifth calculation unit, configured to calculate the health of the target device according to the deviation;

[0103] The third determining unit is configured to determine the status of the target device according to the health level.

[0104] Based on the above embodiment, as a preferred embodiment, the third determining unit includes:

[0105] The comparison subunit is used to compare the health degree with the health level table to determine the health level of the equipment and the disposal recommendations to determine the status of the target equipment; wherein the health level table includes the correspondence between the health degree, health level and disposal recommendations, and the disposal recommendations include the need for immediate maintenance, attention to the equipment operating status and normal operation.

[0106] Based on the above embodiment, as a preferred embodiment, the second calculation module includes:

[0107] Construction unit, used to build a knowledge graph based on historical data, expert experience data and professional book data;

[0108] The fourth determination unit is used to determine the root cause of the fault state based on the knowledge graph; wherein the knowledge graph includes the logical relationship between equipment, monitoring data, status information, faults, and treatment measures.

[0109] Based on the above embodiment, as a preferred embodiment, it also includes:

[0110] The analysis module is used to determine the root cause with a higher actual a posteriori probability if the target device is in an abnormal state; use the knowledge graph and the root cause with a higher actual a posteriori probability to perform fault analysis and determine the fault handling measures.

[0111] Since the embodiments of the apparatus part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the apparatus part, and they will not be repeated here.

[0112] The embodiment of the present application provides a device for determining the state of an equipment based on fault prediction, which not only obtains the real-time monitoring data of the target equipment, but also obtains the real-time monitoring data of the equipment associated with the target equipment, and considers more comprehensive factors. The root cause of the fault state is determined based on the knowledge graph, the actual posterior probability of all root causes is analyzed, and the state of the target equipment is determined. Compared with directly determining the state of the target equipment based on monitoring data that can only reflect the appearance, the accuracy of determining the state of the equipment is improved, and the problem of delay between determining the state of the equipment based on the monitoring data and the actual state is effectively overcome. In addition, a time series prediction analysis is performed based on the actual posterior probability to obtain the predicted posterior probability within a preset time period in the future. The equipment state is determined based on the actual posterior probability and the predicted posterior probability of all root causes, which can provide insight into the equipment state earlier and serve as a warning.

[0113] Figure 4 This is a structural diagram of another device state determination device based on fault prediction provided in an embodiment of the present application, such as Figure 4 As shown, the device state determination apparatus based on fault prediction includes: a memory 20 for storing a computer program;

[0114] The processor 21 is configured to implement the steps of the method for determining a device state based on fault prediction in the above embodiment when executing a computer program.

[0115] The device state determination apparatus based on fault prediction provided in this embodiment may include, but is not limited to, a smart phone, a tablet computer, a laptop computer, or a desktop computer.

[0116] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0117] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include high-speed random access memory, and non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 20 is at least used to store the following computer program 201, wherein, after the computer program is loaded and executed by the processor 21, it can implement the relevant steps of the device state determination method based on fault prediction disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include but is not limited to monitoring data, actual posterior probability and predicted posterior probability, etc.

[0118] In some embodiments, the device for determining the state of an equipment based on fault prediction may further include a display screen 22 , an input and output interface 23 , a communication interface 24 , a power supply 25 , and a communication bus 26 .

[0119] Those skilled in the art will understand that Figure 4 The structure shown in the figure does not constitute a limitation on the device for determining the equipment state based on fault prediction, and may include more or fewer components than those shown in the figure.

[0120] An embodiment of the present application provides a device for determining a device state based on fault prediction, including a memory and a processor. When the processor executes a program stored in the memory, it can implement the following method: obtaining real-time monitoring data of a target device and its associated devices; calculating the current fault state of the target device and its associated devices based on the real-time monitoring data; determining the root cause of the fault state based on a knowledge graph, and calculating the actual posterior probability of each root cause based on the fault state; sorting the actual posterior probabilities by time, and performing time series prediction analysis to obtain a posterior probability change curve for each root cause within a future preset time period; obtaining a predicted posterior probability within a future preset time period based on the posterior probability change curve, and determining the state of the target device based on the actual posterior probabilities and predicted posterior probabilities of all root causes of the target device.

[0121] Finally, the present application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps described in the above method embodiment.

[0122] It is understandable that if the method in the above embodiment 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 storage medium. 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 storage medium and executes all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0123] The above is a detailed introduction to the method for determining the device state based on fault prediction provided by the present application. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of this application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of this application.

[0124] It should also be noted that, in this specification, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

Claims

1. A method for determining equipment status based on fault prediction, characterized in that: include: Acquire real-time monitoring data of a target device and its associated devices; Calculating the current fault status of the target device and the associated device based on the real-time monitoring data; Determine the root cause of the fault state according to the knowledge graph, and calculate the actual posterior probability of each root cause according to the fault state; The actual posterior probabilities are sorted by time, and time series forecast analysis is performed to obtain a posterior probability change curve for each root cause within a future preset time period; Obtaining a predicted posterior probability within the future preset time period according to the posterior probability change curve, and determining a state of the target device according to the actual posterior probabilities and the predicted posterior probabilities of all the root causes of the target device; The determining the state of the target device according to the actual a posteriori probabilities and the predicted a posteriori probabilities of all the root causes of the target device includes: Calculating a weighted posterior probability of each of the root causes according to the actual posterior probability and the predicted posterior probability; The formula for calculating the weighted posterior probability is: Among them, p is the weighted posterior probability, ρ is the weighting coefficient, and p i is the predicted posterior probability; determining a priori probabilities for each of said root causes; Calculating the occurrence probability gain of each of the root causes according to the prior probability and the weighted posterior probability; The calculation formula for the occurrence probability gain is: Among them, f is the occurrence probability gain, p0 is the prior probability, and p is the weighted posterior probability; Generate a fault root cause set according to all the root causes corresponding to the fault state and the state information fed back by the user; Calculating the deviation of the target device state according to the root cause severity and the occurrence probability gain of all the root causes in the fault root cause set; and calculating the health of the target device according to the deviation; determining a status of the target device according to the health; Determining the root cause of the fault state based on the knowledge graph and calculating the actual posterior probability of each root cause based on the fault state includes: Determine, based on the knowledge graph, the root cause corresponding to the fault state and the state information fed back by the user; Calculate the actual posterior probability of each root cause according to the fault state and the state information using any one of a variable elimination algorithm, a clique tree propagation algorithm, a random sampling algorithm, and a variational method; After obtaining the posterior probability change curve of each root cause within a preset future time period, the method further includes: The fault development trend is determined according to the time required for the posterior probability in the posterior probability change curve of each root cause to rise to a preset height.

2. The method for determining the device state based on fault prediction according to claim 1, characterized in that: Determining the state of the target device according to the health level includes: Comparing the health degree with a health grade table to determine the health grade of the device and a treatment recommendation to determine the status of the target device; The health level table includes the corresponding relationship between health degree, health level and treatment suggestions, and the treatment suggestions include the need for immediate maintenance, attention to equipment operating status and normal operation.

3. The method for determining the equipment status based on fault prediction according to claim 1, characterized in that: Determining the root cause of the fault state according to the knowledge graph includes: Constructing the knowledge graph based on historical data, expert experience data, and professional book data; Determining the root cause of the fault state according to the knowledge graph; The knowledge graph includes the logical relationships among equipment, monitoring data, status information, faults, and treatment measures.

4. The method for determining the equipment status based on fault prediction according to claim 1, characterized in that: After determining the state of the target device, the method further includes: If the target device is in an abnormal state, determining the root cause with a higher actual a posteriori probability; The knowledge graph and the root cause with a higher actual posterior probability are used to perform fault analysis and determine fault handling measures.

5. A device for determining equipment status based on fault prediction, characterized in that: include: An acquisition module, configured to acquire real-time monitoring data of a target device and its associated devices; A first calculation module, configured to calculate the current fault status of the target device and the associated device based on the real-time monitoring data; A second calculation module is used to determine the root cause of the fault state according to the knowledge graph, and calculate the actual posterior probability of each root cause according to the fault state; A prediction module is used to sort the actual posterior probabilities by time and perform time series prediction analysis to obtain a posterior probability change curve for each root cause within a future preset time period; a determination module, configured to obtain a predicted posterior probability within the future preset time period according to the posterior probability change curve, and determine the state of the target device according to the actual posterior probabilities and the predicted posterior probabilities of all the root causes of the target device; The modules to be determined include: A second calculation unit is used to calculate the weighted posterior probability of each root cause according to the actual posterior probability and the predicted posterior probability; The formula for calculating the weighted posterior probability is: Among them, p is the weighted posterior probability, ρ is the weighting coefficient, and p i is the predicted posterior probability; a second determining unit, configured to determine a priori probability of each root cause; a third calculation unit, configured to calculate an occurrence probability gain of each root cause according to the prior probability and the weighted posterior probability; The calculation formula for the occurrence probability gain is: Among them, f is the occurrence probability gain, p0 is the prior probability, and p is the weighted posterior probability; A generating unit, configured to generate a fault root cause set based on all root causes corresponding to the fault state and the state information fed back by the user; a fourth calculation unit, configured to calculate a deviation of a target device state according to the root cause severity and the occurrence probability gain of all root causes in the fault root cause set; a fifth calculation unit, configured to calculate the health of the target device according to the deviation; a third determining unit, configured to determine a state of the target device according to the health level; The second calculation module includes: A first determining unit is configured to determine a root cause corresponding to the fault state and the state information fed back by the user based on the knowledge graph; The first calculation unit is used to calculate the actual posterior probability of each root cause according to the fault state and state information using any one of a variable elimination algorithm, a clique tree propagation algorithm, a random sampling algorithm, and a variational method; The fault development trend determination module is used to determine the fault development trend according to the time required for the posterior probability in the posterior probability change curve of each root cause to rise to a preset height.

6. A device for determining equipment status based on fault prediction, characterized in that: including a memory for storing a computer program; A processor is configured to implement the steps of the method for determining a device state based on fault prediction according to any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for determining a device state based on fault prediction according to any one of claims 1 to 4.

Images