Fault positioning early warning method, system and equipment

Abstract

The invention provides a fault positioning early warning method, system and equipment, and relates to the technical field of fault detection, after fault correlation analysis is carried out on real-time equipment fault information to obtain a correlation equipment fault risk, primitive attribute mapping is carried out on the real-time equipment fault information and the correlation equipment fault risk, and primitive display information is output; and after the digital platform receives the primitive display information, updating the equipment state diagram according to the primitive display information to obtain a fault positioning early warning screen display. The technical problem that in the prior art, the equipment fault state and the equipment fault risk conduction condition are not visually displayed, so that equipment fault monitoring has a low equipment operation and maintenance guiding effect on operation and maintenance personnel is solved. Through primitive attribute mapping, the state and risk of the equipment fault are clearly and visually displayed, and the technical effect of assisting operation and maintenance personnel to quickly respond and effectively process the equipment fault is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault detection, and in particular to a fault location and early warning method, system and equipment. Background Art

[0002] With the rapid development of edge computing, the Internet of Things, and smart devices, equipment monitoring and fault warning systems are becoming increasingly widely used in various industries.

[0003] The current system generally has the problem of non-intuitive display. Equipment failures are usually presented through digital displays or static charts, which makes it difficult to effectively display the fault correlation and risk transmission between devices. Especially in the complex situation of multiple device failures, it is impossible to intuitively display the source of the failure and its impact on other devices. This lack of information display makes it impossible for operation and maintenance personnel to quickly locate the source of the failure, affecting response speed and decision-making efficiency.

[0004] In summary, the existing technology has the technical problem that the display of equipment failure status and equipment failure risk transmission is not intuitive, resulting in low equipment failure monitoring guidance effect for operation and maintenance personnel. Summary of the invention

[0005] The present invention provides a fault location and early warning method, system and device, which are used to solve the technical problem that the display of equipment fault status and equipment fault risk transmission in the prior art is not intuitive, resulting in low equipment fault monitoring guidance effect for operation and maintenance personnel.

[0006] In view of the above problems, the present invention provides a fault location and early warning method, system and device.

[0007] According to a first aspect of the present invention, a fault location and warning method is provided, the method comprising: when a device status monitoring center receives a first fault warning code, real-time device fault information is obtained by encoding and parsing the first fault warning code; the device status monitoring center obtains the associated device fault risk by performing fault correlation analysis on the real-time device fault information; the device status monitoring center performs primitive attribute mapping on the real-time device fault information and the associated device fault risk, and outputs primitive display information; interactively obtains functional dependencies of a target device cluster, and pre-builds a device status diagram on a digital platform according to the functional dependencies, wherein the target device cluster includes K functional devices, and the device status diagram includes K device primitives bound to the K functional device primitives; after the digital platform receives the primitive display information, it updates the device status diagram according to the primitive display information to obtain a fault location and warning screen display.

[0008] According to a second aspect of the present invention, a fault location and warning system is provided, the system comprising: an equipment fault parsing module, for obtaining real-time equipment fault information by performing code parsing on the first fault warning code when the equipment status monitoring center receives the first fault warning code; a fault correlation analysis module, for the equipment status monitoring center to obtain the associated equipment fault risk by performing fault correlation analysis on the real-time equipment fault information; a graphic element attribute mapping module, for the equipment status monitoring center to perform graphic element attribute mapping on the real-time equipment fault information and the associated equipment fault risk, and output graphic element display information; a graphic element binding execution module, for interactively obtaining the functional dependency of the target equipment cluster, and pre-building an equipment status diagram on a digital platform according to the functional dependency, wherein the target equipment cluster includes K functional equipment, and the equipment status diagram includes K equipment graphic elements bound to the K functional equipment graphic elements; a fault location and warning module, for updating the equipment status diagram according to the graphic element display information after the digital platform receives the graphic element display information, and obtaining a fault location and warning screen display.

[0009] According to a third aspect of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented: When the equipment status monitoring center receives the first fault warning code, the real-time equipment fault information is obtained by encoding and parsing the first fault warning code; the equipment status monitoring center obtains the associated equipment fault risk by performing fault correlation analysis on the real-time equipment fault information; the equipment status monitoring center performs primitive attribute mapping on the real-time equipment fault information and the associated equipment fault risk, and outputs primitive display information; the functional dependency relationship of the target equipment cluster is interactively obtained, and the equipment status diagram is pre-built on the digital platform according to the functional dependency relationship, wherein the target equipment cluster includes K functional equipment, and the equipment status diagram includes K equipment primitives bound to the K functional equipment primitives; after receiving the primitive display information, the digital platform updates the equipment status diagram according to the primitive display information to obtain a fault location warning screen display.

[0010] One or more technical solutions provided in the present invention have at least the following technical effects or advantages: The method provided by the embodiment of the present invention receives a first fault warning code through an equipment status monitoring center, obtains real-time equipment fault information by encoding and parsing the first fault warning code; the equipment status monitoring center obtains the associated equipment fault risk by performing fault association analysis on the real-time equipment fault information; the equipment status monitoring center performs primitive attribute mapping on the real-time equipment fault information and the associated equipment fault risk, and outputs primitive display information; interactively obtains the functional dependency of the target equipment cluster, and pre-builds an equipment status diagram on a digital platform according to the functional dependency, wherein the target equipment cluster includes K functional equipment, and the equipment status diagram includes K equipment primitives bound to the K functional equipment primitives; after receiving the primitive display information, the digital platform updates the equipment status diagram according to the primitive display information, and obtains a fault location warning screen display. Through primitive attribute mapping, the status and risk of equipment faults are clearly and intuitively displayed, achieving the technical effect of assisting operation and maintenance personnel to quickly respond to and effectively handle equipment faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic diagram of a fault location and early warning method provided by the present invention; Figure 2 A schematic diagram of a process for obtaining real-time equipment fault information in a fault location and early warning method provided by the present invention; Figure 3 A structural schematic diagram of a fault location and early warning system provided by the present invention.

[0012] Explanation of reference numerals: equipment fault analysis module 11 , fault correlation analysis module 12 , graphic element attribute mapping module 13 , graphic element binding execution module 14 , fault location warning module 15 . DETAILED DESCRIPTION

[0013] The present invention provides a fault location warning method, system and device, which are used to solve the technical problem that the display of equipment fault status and equipment fault risk transmission in the prior art is not intuitive, resulting in low equipment fault monitoring guidance for operation and maintenance personnel. Through primitive attribute mapping, the status and risk of equipment faults are clearly and intuitively displayed, achieving the technical effect of assisting operation and maintenance personnel to quickly respond to and effectively handle equipment faults.

[0014] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0015] Embodiment 1, as Figure 1 As shown, the present invention provides a fault location warning method, the method comprising: A100: When the equipment status monitoring center receives the first fault warning code, real-time equipment fault information is obtained by encoding and parsing the first fault warning code.

[0016] In one embodiment, Figure 2 As shown, when the equipment status monitoring center receives the first fault warning code, the real-time equipment fault information is obtained by coding and parsing the first fault warning code. The method step A100 provided by the present invention includes: A110: Configure K edge fault detection models on the K functional devices.

[0017] A120: Analyze the K real-time operation data of the K functional devices through the K edge fault detection models, and output K real-time device states.

[0018] A130: When the first real-time device state among the K real-time device states is a fault state, the first edge fault detection model performs encoding processing on the first functional device and the first real-time device state to generate the first fault warning code, wherein the first functional device is any functional device among the K functional devices.

[0019] A140: After receiving the first fault warning code, the equipment status monitoring center obtains the real-time equipment fault information by performing code analysis on the first fault warning code.

[0020] In one embodiment, K edge fault detection models are configured on the K functional devices, and step A110 of the method provided by the present invention includes: A111: Obtain the first historical fault information of the first functional device through local data call, wherein the first historical fault information includes multiple sample fault operation data, multiple sample fault types and multiple sample fault levels.

[0021] A112: Use the CNN network to pre-build a standard fault identification model, wherein the input data of the standard fault identification model is the equipment operation data, and the output result is the equipment fault type and equipment fault level.

[0022] A113: Use the first historical fault information as training data to optimize the parameters of the standard fault identification model to obtain a first fault identification unit.

[0023] A1141: Perform fault type aggregation on the multiple sample fault types to obtain multiple first fault types.

[0024] A1142: Use the multiple first fault types to traverse the multiple sample fault levels to obtain multiple groups of first fault levels.

[0025] A1143: Generate a fault classification level table using the multiple first fault types and multiple groups of first fault levels.

[0026] A1144: Obtain a fault classification coding table by encoding and configuring the fault classification level table.

[0027] A1145: Construct a first fault coding unit based on the first device code of the first functional device and the fault classification coding table.

[0028] A115: Complete the construction of the first edge fault detection model by cascading the first fault identification unit and the first fault encoding unit.

[0029] A116: Similarly, construct the K edge fault detection models of the K functional devices, and configure the K edge fault detection models at the K edge nodes of the K functional devices.

[0030] In this embodiment, first, an independent edge fault detection model is configured for each of the K functional devices in the target device cluster of the detection object, so as to realize localized fault detection on each functional device, so as to improve the response speed and accuracy of fault detection.

[0031] Since the edge fault detection model construction method of each functional device is similar, this embodiment takes the construction of the edge fault detection model of the first functional device as an example to elaborate on the technical solution in detail.

[0032] Specifically, first, first historical fault information of a first functional device is obtained through local data of the device (which may come from sensors, monitoring systems or logs on the device), and the first historical fault information includes multiple sample fault operation data (operation data of the device during the period when the fault occurs, such as temperature, pressure, current, vibration, etc.), multiple sample fault types (such as electrical fault, mechanical fault, communication fault, etc.) and multiple sample fault levels (the severity of the fault, such as minor fault, moderate fault, severe fault, etc.).

[0033] This embodiment is based on the characteristic that the CNN network is very effective in processing the time series data of the device (such as sensor data), and preferably the CNN network pre-builds a standard fault identification model, wherein the input of the standard fault identification model is the operation data of the device, that is, the historical fault operation data of the device obtained in step A111, and the output of the model is the fault type and fault level of the device, for example, determining whether the equipment fault is an electrical fault, a mechanical fault or a software fault, and assigning a level to the fault.

[0034] Multiple groups of sample fault operation data - sample fault types - multiple sample fault levels in the first historical fault information are used as training data, and the training data identifiers are divided into training set, test set and validation set in the ratio of 8:1:1 to adjust the parameters of the standard fault identification model (such as learning rate, number of network layers, filter size, etc.), so that the model can better identify the type and level of faults from the equipment operation data, and obtain the first fault identification unit adapted to accurately identify the faults of the first functional equipment.

[0035] Fault type aggregation is performed on the multiple sample fault types to aggregate the fault types in all historical data of the first functional device to obtain multiple first fault types, where the first fault types include but are not limited to electrical faults, mechanical faults, and software faults.

[0036] For each fault type, all possible fault levels are traversed to generate a set of fault levels, such as minor faults, medium faults, severe faults, and so on, and the multiple first fault types are used to traverse the multiple sample fault levels to obtain multiple sets of first fault levels.

[0037] The multiple first fault types and multiple groups of first fault levels are used to tabulate and generate a fault classification level table, wherein the fault classification level table records the mapping relationship between all possible fault types and fault levels of the first functional device.

[0038] By encoding and configuring the fault classification level table, each fault type and level combination is mapped to a unique code to obtain a fault classification coding table.

[0039] The first fault coding unit is constructed based on the first device code of the first functional device and the fault classification coding table, and the first fault coding unit is used to generate a fault coding array according to the fault type and fault level output by the first fault identification unit.

[0040] By connecting the output end of the first fault identification unit and the input end of the first fault coding unit, the construction of the first edge fault detection model is completed. The function of the first edge fault detection model is to detect equipment faults through real-time operation data, and generate fault codes according to the fault type and level to facilitate subsequent processing.

[0041] By analogy, the K edge fault detection models of the K functional devices are constructed, and the K edge fault detection models are configured at the K edge nodes of the K functional devices.

[0042] The K real-time operation data of the K functional devices are analyzed by the K fault identification units in the K edge fault detection models, and K real-time device states are output.

[0043] When the first real-time device state of a device (such as a first functional device) among the K real-time device states is a fault state, the first fault coding unit of the first edge fault detection model in the local edge node of the device (first functional device) in the fault state is activated, and the first fault coding unit is used to perform encoding processing on the first functional device and the first real-time device state to generate the first fault warning code, wherein the first functional device is any functional device among the K functional devices, and currently the first functional device is detected to have a device fault.

[0044] The first edge fault detection model sends the first fault warning code to the equipment status monitoring center. After receiving the first fault warning code, the equipment status monitoring center obtains the real-time equipment fault information by encoding and parsing the first fault warning code. Specifically, the real-time equipment fault information includes a first real-time fault type, a first real-time fault level and a unique equipment identifier for identifying the first functional device.

[0045] This embodiment achieves the technical effect of improving the timeliness and accuracy of fault detection by building edge nodes to monitor and judge the fault status of functional equipment. By using encoding to compress fault information (such as fault type, fault level, equipment status, etc.) into a concise format, the technical effect of improving the network transmission efficiency of fault information and reducing the burden of transmitted data volume is achieved.

[0046] A200: The equipment status monitoring center obtains the associated equipment failure risk by performing fault correlation analysis on the real-time equipment failure information.

[0047] In one embodiment, the device status monitoring center obtains the associated device failure risk by performing a failure correlation analysis on the real-time device failure information. Step A200 of the method provided by the present invention includes: A210: Obtain K historical fault information of the K functional devices through local data call.

[0048] A220: Collect fault time in the first historical fault information to obtain multiple sample fault times.

[0049] A230: After aligning the data of the K historical fault information, synchronously collect the data of the K historical fault information based on the multiple sample fault times to obtain multiple groups of equipment status information.

[0050] A240: Calculate the failure probability of K-1 functional devices according to the multiple groups of device status information to obtain a first group of failure transfer probabilities, wherein the first group of failure transfer probabilities includes K-1 failure transfer probabilities.

[0051] A250: Similarly, K groups of fault transfer probabilities are calculated based on the K historical fault information.

[0052] A260: Construct a fault transfer matrix according to the K functional devices and K groups of fault transfer probabilities, and update the fault transfer matrix to the device status monitoring center.

[0053] A270: The equipment status monitoring center loads the real-time equipment fault information into the fault transfer matrix to perform fault correlation analysis to obtain the associated equipment failure risk.

[0054] In one embodiment, the device status monitoring center loads the real-time device fault information into the fault transfer matrix to perform fault correlation analysis to obtain the associated device fault risk. Step A270 of the method provided by the present invention includes: A271: Analyze the real-time device fault information to obtain the first real-time fault type, the first real-time fault level and the first functional device.

[0055] A272: Input the first functional device into the fault transfer matrix to perform fault correlation analysis to obtain K-1 real-time fault probabilities.

[0056] A273: Calculate the fault frequency based on the K historical fault information to obtain K fault frequency coefficients.

[0057] A274: According to the first functional device, reverse screening is performed from the K fault frequency coefficients to obtain K-1 fault frequency coefficients.

[0058] A275: Perform weighted calculation on the K-1 real-time fault probabilities and the K-1 fault frequency coefficients to obtain K-1 updated fault probabilities.

[0059] A276: Use the K-1 updated fault probabilities to traverse the simulated fault level table to obtain K-1 simulated fault risk levels.

[0060] A277: Output K-1 simulated fault risk levels as the associated equipment failure risk.

[0061] Specifically, in this embodiment, the same method as that of obtaining the first historical fault data of the first functional device is adopted to obtain K historical fault information of the K functional devices through local data call. It should be understood that each historical fault information includes multiple sample fault operation data (operation data of the equipment during the period when the fault occurs, such as temperature, pressure, current, vibration, etc.), multiple sample fault types (such as electrical fault, mechanical fault, communication fault, etc.) and multiple sample fault levels (the severity of the fault, such as minor fault, medium fault, severe fault, etc.).

[0062] Fault time is collected in the first historical fault information to obtain the specific time point of each recorded fault and multiple sample fault times. The multiple sample fault times can help analyze the occurrence pattern of faults and the time relationship between equipment failures.

[0063] After data alignment is performed on the K historical fault information, synchronous data collection is performed on the K historical fault information with the multiple sample failure times as constraints to obtain multiple groups of device status information, each group of device status information includes K-1 device status information of K-1 functional devices, and each group of device status information is the device status information when the first functional device fails (including failure and non-fault states).

[0064] Use the synchronously collected device status information to analyze the probability relationship between the device failure status and the failure status of other devices. For a certain device (for example, device A), calculate the impact of its failure on other devices (device B, device C, etc.), that is, calculate the fault transfer probability. The fault transfer probability represents the possibility of device B or device C failing after device A fails, and generates the first set of fault transfer probabilities. Specifically, this set of fault transfer probabilities is K-1 fault transfer probabilities, that is, the failure probability of device B to device K when device A fails.

[0065] According to the previously calculated transfer probability method, the failure transfer probability of each device to other devices is calculated in turn, and finally K groups of failure transfer probabilities are obtained.

[0066] Each set of fault transfer probabilities represents the probability of other devices failing when one device fails. In this way, the system can fully understand the fault propagation chain between devices, that is, how faults propagate between multiple devices, and calculate the device failure risk based on the failure history of different devices.

[0067] The fault transfer matrix is ​​updated to the device status monitoring center, and the device status monitoring center uses the fault transfer matrix to predict the fault development trend.

[0068] Specifically, after decoding and obtaining the real-time device fault information, the device status monitoring center extracts and obtains the first real-time fault type, the first real-time fault level, and a device unique identifier for identifying the first functional device from the real-time device fault information.

[0069] The first functional device is input into the fault transfer matrix. The fault transfer matrix calculates the probability of failure of other associated devices (such as devices B, C, etc.) when the first functional device fails by mapping the fault type, and obtains K-1 real-time failure probabilities.

[0070] The frequency of equipment failure is calculated based on historical data to provide weights for failure risk assessment. Specifically, this embodiment calculates the failure frequency based on the K historical failure information to obtain K failure frequency coefficients. The failure frequency coefficient reflects the commonness of each equipment failure and is an important factor in assessing failure risk.

[0071] According to the first functional device, reverse screening is performed from the K fault frequency coefficients to obtain K-1 fault frequency coefficients of K-1 functional devices other than the first functional device, and weighted calculation is performed on the K-1 real-time fault probabilities and the K-1 fault frequency coefficients to obtain K-1 updated fault probabilities.

[0072] It should be understood that the fault risk level is generally related to the probability of equipment failure. The higher the probability, the more serious the fault risk level may be. Based on this, the present embodiment pre-constructs a fault level table.

[0073] The K-1 updated failure probabilities are used to find the corresponding failure risk level in the pre-constructed failure level table to obtain K-1 simulated failure risk levels. It should be understood that the simulated failure risk level is the risk level of each device that will be implicated and also fail when the failure of the first functional device actually occurs. The K-1 simulated failure risk levels are output as the failure risks of the associated devices.

[0074] This embodiment achieves the technical effect of accurately predicting the propagation of equipment failures and evaluating the failure risk status of associated equipment in real time, and indirectly achieves the technical effect of providing reliable reference information for subsequent display of failure graphics elements.

[0075] A300: The equipment status monitoring center performs graphic element attribute mapping on the real-time equipment failure information and the associated equipment failure risk, and outputs graphic element display information.

[0076] In one embodiment, the device status monitoring center performs graphic element attribute mapping on the real-time device failure information and the associated device failure risk, and outputs graphic element display information. Step A300 of the method provided by the present invention includes: A310: Preset K graphic element attribute definitions, wherein the graphic element attribute definitions include a fault color level sequence and a risk color level sequence.

[0077] A320: After the K graphic element attribute definitions call the first graphic element attribute definition of the first functional device, the first real-time fault level is used to traverse the first fault color level sequence of the first graphic element attribute definition to obtain the first real-time graphic element attribute.

[0078] A330: According to the first functional device, reversely call K-1 primitive attribute definitions in the K primitive attribute definitions.

[0079] A340: Use the K-1 simulated fault risk level mappings to traverse the K-1 risk color level sequences in the K-1 primitive attribute definitions to obtain K-1 associated primitive attributes.

[0080] A350: The first real-time primitive attribute and K-1 associated primitive attributes constitute the primitive display information.

[0081] In this embodiment, different attributes are set for the graphic element of each device, including color mapping of the fault state and color mapping of the risk state.

[0082] Specifically, the fault color level sequence is used to indicate the different levels of the equipment's own faults, with different colors corresponding to the fault levels from minor to major. For example, a minor fault may correspond to yellow, and a major fault may correspond to red. The risk color level sequence is used to indicate the fault risk level of the equipment affected by the faults of other equipment. When the equipment is affected by the faults of other equipment, the risk level of the equipment is determined by this color sequence. For example, low risk may correspond to green, and high risk may correspond to orange or red.

[0083] The colors of these two sequences are different. The fault color level sequence is determined based on the fault status of the device itself, while the risk color level sequence is the risk level of the device due to the impact of other device failures (i.e., simulated fault risk level).

[0084] Since the first functional device is a supply device that is actually in a faulty state, this implementation calls the first primitive attribute definition of the first functional device in the K primitive attribute definitions and only uses the first fault color level sequence in the first primitive attribute definition.

[0085] Specifically, the first real-time fault level is used to traverse the first fault color level sequence defined by the first graphic element attribute to obtain the first real-time graphic element attribute. For example, if the fault level of the first functional device is serious, the graphic element color may be set to red, indicating that the device is in a serious fault state.

[0086] According to the first functional device, K-1 graphic element attribute definitions of K-1 functional devices that are not in actual fault states are reversely called in the K graphic element attribute definitions, and only K-1 risk color level sequences in the K-1 graphic element attribute definitions are used.

[0087] According to the simulated failure risk level of each associated device, the corresponding risk color level sequence is traversed, and appropriate risk colors are selected for these devices to obtain K-1 associated graphic element attributes. For example, if the failure risk of device B is higher, the graphic element may be displayed in orange or red, indicating that the failure risk of device B is higher.

[0088] The first real-time primitive attribute and K-1 associated primitive attributes constitute the primitive display information, which is used to subsequently display the current status of all devices in the target device cluster in a graphical color change manner. In this way, operation and maintenance personnel can intuitively understand the health status of the device and the risk association between devices through the color and status of the primitive.

[0089] A400: Interactively obtain functional dependencies of a target device cluster, and pre-build a device status diagram on a digital platform based on the functional dependencies, wherein the target device cluster includes K functional devices, and the device status diagram includes K device primitives bound to the K functional device primitives.

[0090] Specifically, in this embodiment, by interacting with the system, the functional dependency relationship between the target device cluster (including K functional devices) is obtained. The functional dependency relationship refers to the mutual dependence between devices. For example, a device may rely on other devices to operate normally.

[0091] Based on the obtained functional dependencies, the device status diagram is pre-built on the digital platform. The device status diagram graphically displays the device status and the relationship between them.

[0092] Each primitive in the device state diagram represents a device, and the states of all K devices are displayed in the diagram through primitives (i.e., graphic elements). These device primitives are associated with each device through binding, showing their states and functional dependencies.

[0093] A500: After receiving the graphic element display information, the digital platform updates the equipment status diagram according to the graphic element display information to obtain a fault location warning screen display.

[0094] In one embodiment, after receiving the graphic element display information, the digital platform updates the device status diagram according to the graphic element display information to obtain a fault location warning screen display. Step A500 of the method provided by the present invention includes: A510: According to the mapping relationship between the K device primitives and the K functional devices, the attributes of the K device primitives are updated using the first real-time primitive attributes and K-1 associated primitive attributes to obtain an initial warning screen display.

[0095] A520: Locate the first device icon on the initial warning screen according to the first functional device, and display the first real-time fault type as text on the first device icon, complete the fault location of the initial warning screen, and generate the fault location warning screen.

[0096] Specifically, it should be understood that in this embodiment, a graphic element mapping relationship is established between K device graphic elements (ie, graphic elements representing each device) and K functional devices. In other words, each device graphic element corresponds to a specific device.

[0097] On this basis, the display attributes of each device primitive are updated by using the first real-time primitive attributes (such as fault level, color, etc.) and K-1 associated primitive attributes (which may be the fault risks of other devices related to the device). For example, the primitive of a faulty device may be displayed in red, while the primitives of the devices associated with it may be displayed in orange or yellow, indicating different fault risk levels.

[0098] After the attribute update of the equipment primitive is completed, an initial warning screen is generated, and the initial warning screen only displays the current status and risks of K functional equipment.

[0099] Furthermore, in the initial warning screen display, the corresponding device icon is located according to the first functional device (i.e., the device where the fault occurs), and the first real-time fault type (such as "electrical fault", "mechanical fault", etc.) is displayed as text on the first device icon, so as to complete the fault location of the initial warning screen display and generate the fault location warning screen display.

[0100] This embodiment achieves a clear and intuitive display of the status and risk of equipment failures through primitive attribute mapping, thereby achieving the technical effect of assisting operation and maintenance personnel to quickly respond to and effectively handle equipment failures.

[0101] Embodiment 2 is based on the same inventive concept as a fault location and early warning method in the above embodiment. Figure 3 As shown, the present invention provides a fault location warning system, wherein the system comprises: The equipment fault analysis module 11 is used to obtain real-time equipment fault information by performing code analysis on the first fault warning code when the equipment status monitoring center receives the first fault warning code.

[0102] The fault correlation analysis module 12 is used for the equipment status monitoring center to obtain the associated equipment failure risk by performing fault correlation analysis on the real-time equipment failure information.

[0103] The graphic element attribute mapping module 13 is used by the device status monitoring center to perform graphic element attribute mapping on the real-time device failure information and the associated device failure risk, and output graphic element display information.

[0104] The primitive binding execution module 14 is used to interactively obtain the functional dependencies of the target device cluster and pre-build a device state diagram on the digital platform according to the functional dependencies, wherein the target device cluster includes K functional devices, and the device state diagram includes K device primitives bound to the K functional device primitives.

[0105] The fault location warning module 15 is used for updating the equipment status diagram according to the graphic element display information after the digital platform receives the graphic element display information, so as to obtain the fault location warning screen display.

[0106] In one embodiment, the equipment fault analysis module 11 is further used for: K edge fault detection models are configured on the K functional devices; K real-time operation data of the K functional devices are analyzed by the K edge fault detection models, and K real-time device states are output; when the first real-time device state among the K real-time device states is a fault state, the first edge fault detection model performs encoding processing on the first functional device and the first real-time device state to generate the first fault warning code, wherein the first functional device is any functional device among the K functional devices; after receiving the first fault warning code, the device state monitoring center obtains the real-time device fault information by encoding and parsing the first fault warning code.

[0107] In one embodiment, the equipment fault analysis module 11 is further used for: The first historical fault information of the first functional device is obtained by calling local data, wherein the first historical fault information includes a plurality of sample fault operation data, a plurality of sample fault types and a plurality of sample fault levels; a standard fault identification model is pre-built by using a CNN network, wherein the input data of the standard fault identification model is the device operation data, and the output result is the device fault type and the device fault level; the first historical fault information is used as training data to perform parameter optimization of the standard fault identification model to obtain a first fault identification unit; the plurality of sample fault types are aggregated to obtain a plurality of first fault types; the plurality of first fault types are used to traverse The method comprises the steps of: going through the multiple sample fault levels to obtain multiple groups of first fault levels; using the multiple first fault types and the multiple groups of first fault levels to tabulate and generate a fault classification level table; encoding and configuring the fault classification level table to obtain a fault classification coding table; constructing a first fault coding unit based on the first device code of the first functional device and the fault classification coding table; completing the construction of the first edge fault detection model by cascading the first fault identification unit and the first fault coding unit; and so on, constructing the K edge fault detection models of the K functional devices, and configuring the K edge fault detection models on the K edge nodes of the K functional devices.

[0108] In one embodiment, the fault correlation analysis module 12 is further used for: Through local data call, K historical fault information of the K functional devices are obtained; fault time is collected on the first historical fault information to obtain multiple sample fault times; after data alignment of the K historical fault information, synchronous data collection is performed on the K historical fault information with the multiple sample fault times as constraints to obtain multiple groups of device status information; fault probabilities of K-1 functional devices are calculated based on the multiple groups of device status information to obtain a first group of fault transfer probabilities, wherein the first group of fault transfer probabilities includes K-1 fault transfer probabilities; and so on, K groups of fault transfer probabilities are calculated based on the K historical fault information; a fault transfer matrix is ​​constructed based on the K functional devices and the K groups of fault transfer probabilities, and the fault transfer matrix is ​​updated to the device status monitoring center; the device status monitoring center obtains the associated device failure risk by loading the real-time device fault information into the fault transfer matrix for fault correlation analysis.

[0109] In one embodiment, the fault correlation analysis module 12 is further used for: Parse the real-time device fault information to obtain a first real-time fault type, a first real-time fault level and the first functional device; input the first functional device into the fault transfer matrix for fault association analysis to obtain K-1 real-time fault probabilities; perform fault frequency calculation based on the K historical fault information to obtain K fault frequency coefficients; reversely screen the K fault frequency coefficients based on the first functional device to obtain K-1 fault frequency coefficients; perform weighted calculation on the K-1 real-time fault probabilities and the K-1 fault frequency coefficients to obtain K-1 updated fault probabilities; use the K-1 updated fault probabilities to traverse a simulated fault level table to obtain K-1 simulated fault risk levels; output the K-1 simulated fault risk levels as the associated device failure risk.

[0110] In one embodiment, the primitive attribute mapping module 13 is further used for: K primitive attribute definitions are preset, wherein the primitive attribute definitions include a fault color level sequence and a risk color level sequence; after the K primitive attribute definitions call the first primitive attribute definition of the first functional device, the first real-time fault level is used to traverse the first fault color level sequence of the first primitive attribute definition to obtain the first real-time primitive attribute; according to the first functional device, K-1 primitive attribute definitions are reversely called in the K primitive attribute definitions; the K-1 simulated fault risk level mappings are used to traverse the K-1 risk color level sequences in the K-1 primitive attribute definitions to obtain K-1 associated primitive attributes; the first real-time primitive attribute and K-1 associated primitive attributes constitute the primitive display information.

[0111] In one embodiment, the fault location warning module 15 is further used for: According to the mapping relationship between the K device primitives and the K functional device primitives, the attributes of the K device primitives are updated using the first real-time primitive attributes and K-1 associated primitive attributes to obtain an initial warning screen display; the first device primitive is located on the initial warning screen display according to the first functional device, and the first real-time fault type is displayed as text on the first device primitive to complete the fault location of the initial warning screen display and generate the fault location warning screen display.

[0112] Embodiment 3, based on the same inventive concept as a fault location and early warning method in the aforementioned embodiment 1, the present application provides an electronic device, which may be a server, comprising a processor, a memory and a network interface connected via a system bus, wherein the processor of the electronic device is used to provide computing and control capabilities, the memory of the electronic device comprises a non-volatile storage medium and an internal memory, the non-volatile storage medium stores an operating system, a computer program and a database, the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium, the database of the electronic device is used to store data, the network interface of the electronic device is used to communicate with an external terminal via a network connection, and the computer program is executed by the processor to implement a fault location and early warning method.

[0113] Any of the methods or steps described above may be stored as computer instructions or programs in various types of computer memories, and the computer instructions or programs may be recognized by various types of computer processors to implement any of the methods or steps described above.

[0114] Based on the above specific embodiments of the present invention, any improvements and modifications made to the present invention by those skilled in the art without departing from the principles of the present invention shall fall within the patent protection scope of the present invention.

Claims

1. A fault location early warning method, characterized in that: The method comprises: When the device status monitoring center receives the first fault warning code sent back by the first edge fault detection model, the real-time device fault information is obtained by encoding and parsing the first fault warning code, wherein the first edge fault detection model is configured in the first functional device; The equipment status monitoring center obtains the associated equipment failure risk by performing fault correlation analysis on the real-time equipment failure information; The equipment status monitoring center performs graphic element attribute mapping on the real-time equipment failure information and the associated equipment failure risk, and outputs graphic element display information; Interactively obtain functional dependencies of a target device cluster, and pre-build a device state diagram on a digital platform according to the functional dependencies, wherein the target device cluster includes K functional devices, and the device state diagram includes K device primitives bound to the K functional device primitives; After receiving the graphic element display information, the digital platform updates the equipment status diagram according to the graphic element display information to obtain a fault location warning screen display.

2. A fault location early warning method according to claim 1, characterized in that: When the device status monitoring center receives the first fault warning code sent back by the first edge fault detection model, real-time device fault information is obtained by encoding and parsing the first fault warning code. The method includes: Configure K edge fault detection models on the K functional devices; Analyze K real-time operation data of the K functional devices through the K edge fault detection models, and output K real-time device states; When a first real-time device state among the K real-time device states is a fault state, the first edge fault detection model performs encoding processing on the first functional device and the first real-time device state to generate the first fault warning code, wherein the first functional device is any functional device among the K functional devices; After receiving the first fault warning code, the equipment status monitoring center obtains the real-time equipment fault information by performing code analysis on the first fault warning code.

3. A fault location and early warning method as claimed in claim 2, characterized in that: K edge fault detection models are configured on the K functional devices, and the method includes: Obtaining first historical fault information of the first functional device by calling local data, wherein the first historical fault information includes a plurality of sample fault operation data, a plurality of sample fault types, and a plurality of sample fault levels; A standard fault identification model is pre-built using a CNN network, wherein the input data of the standard fault identification model is the equipment operation data, and the output result is the equipment fault type and equipment fault level; Using the first historical fault information as training data to perform parameter optimization on the standard fault identification model, to obtain a first fault identification unit; Performing fault type aggregation on the multiple sample fault types to obtain multiple first fault types; Using the multiple first fault types to traverse the multiple sample fault levels to obtain multiple groups of first fault levels; generating a fault classification level table by using the plurality of first fault types and the plurality of groups of first fault levels; Obtaining a fault classification coding table by encoding and configuring the fault classification level table; Constructing a first fault coding unit based on the first device code of the first functional device and the fault classification coding table; By cascading the first fault identification unit and the first fault encoding unit, the construction of the first edge fault detection model is completed; By analogy, the K edge fault detection models of the K functional devices are constructed, and the K edge fault detection models are configured at the K edge nodes of the K functional devices.

4. A fault location early warning method as claimed in claim 3, characterized in that: The device status monitoring center obtains the associated device failure risk by performing a failure correlation analysis on the real-time device failure information. The method includes: Obtaining K historical fault information of the K functional devices through local data calling; Collecting fault time from the first historical fault information to obtain multiple sample fault times; After aligning the data of the K historical fault information, synchronously collecting the data of the K historical fault information with the multiple sample fault times as constraints to obtain multiple groups of device status information; Calculate the failure probability of K-1 functional devices according to the multiple groups of device status information to obtain a first group of failure transfer probabilities, wherein the first group of failure transfer probabilities includes K-1 failure transfer probabilities; Similarly, K groups of fault transfer probabilities are calculated based on the K historical fault information; Constructing a fault transfer matrix according to the K functional devices and K groups of fault transfer probabilities, and updating the fault transfer matrix to the device status monitoring center; The equipment status monitoring center loads the real-time equipment failure information into the failure transfer matrix to perform failure correlation analysis to obtain the associated equipment failure risk.

5. A fault location and early warning method as claimed in claim 4, characterized in that: The device status monitoring center loads the real-time device fault information into the fault transfer matrix to perform fault correlation analysis to obtain the associated device fault risk. The method includes: Parsing the real-time device fault information to obtain a first real-time fault type, a first real-time fault level, and the first functional device; Inputting the first functional device into the fault transfer matrix to perform fault correlation analysis to obtain K-1 real-time fault probabilities; Calculating the fault frequency according to the K historical fault information to obtain K fault frequency coefficients; Reversely screening the K fault frequency coefficients to obtain K-1 fault frequency coefficients according to the first functional device; Performing weighted calculation on the K-1 real-time fault probabilities and the K-1 fault frequency coefficients to obtain K-1 updated fault probabilities; Using the K-1 updated fault probabilities to traverse the simulated fault level table, obtaining K-1 simulated fault risk levels; K-1 simulated fault risk levels are output as the associated equipment fault risks.

6. A fault location early warning method as claimed in claim 5, characterized in that: The device status monitoring center performs graphic element attribute mapping on the real-time device failure information and the associated device failure risk, and outputs graphic element display information, and the method includes: Preset K graphic element attribute definitions, wherein the graphic element attribute definitions include a fault color level sequence and a risk color level sequence; After the K graphic element attribute definitions call the first graphic element attribute definition of the first functional device, traverse the first fault color level sequence of the first graphic element attribute definition using the first real-time fault level to obtain the first real-time graphic element attribute; Reversely calling K-1 graphic element attribute definitions according to the first functional device in the K graphic element attribute definitions; Using the K-1 simulated fault risk level mappings to traverse the K-1 risk color level sequences in the K-1 primitive attribute definitions to obtain K-1 associated primitive attributes; The first real-time primitive attribute and K-1 associated primitive attributes constitute the primitive display information.

7. A fault location and early warning method as claimed in claim 6, characterized in that: After the digital platform receives the graphic element display information, it updates the device status diagram according to the graphic element display information to obtain a fault location warning screen display. The method further includes: According to the mapping relationship between the K device primitives and the K functional devices, the first real-time primitive attribute and K-1 associated primitive attributes are used to update the attributes of the K device primitives to obtain an initial warning screen display; The first device icon is located on the initial warning screen according to the first functional device, and the first real-time fault type is displayed as text on the first device icon, so as to complete the fault location of the initial warning screen and generate the fault location warning screen.

8. A fault location warning system, characterized in that: The steps for implementing the method according to any one of claims 1 to 7 include: An equipment fault analysis module, configured to obtain real-time equipment fault information by encoding and analyzing the first fault warning code when the equipment status monitoring center receives the first fault warning code returned by the first edge fault detection model, wherein the first edge fault detection model is configured in the first functional device; A fault correlation analysis module is used for the equipment status monitoring center to obtain the associated equipment failure risk by performing fault correlation analysis on the real-time equipment failure information; A graphic element attribute mapping module, used for the equipment status monitoring center to map the graphic element attributes of the real-time equipment failure information and the associated equipment failure risk, and output graphic element display information; A primitive binding execution module, used for interactively obtaining functional dependencies of a target device cluster, and pre-building a device state diagram on a digital platform according to the functional dependencies, wherein the target device cluster includes K functional devices, and the device state diagram includes K device primitives bound to the K functional device primitives; The fault location warning module is used for updating the equipment status diagram according to the graphic element display information after the digital platform receives the graphic element display information, so as to obtain the fault location warning screen display.

9. A fault location warning system as claimed in claim 8, characterized in that: The equipment fault analysis module is also used for: Configure K edge fault detection models on the K functional devices; Analyze K real-time operation data of the K functional devices through the K edge fault detection models, and output K real-time device states; When a first real-time device state among the K real-time device states is a fault state, the first edge fault detection model performs encoding processing on the first functional device and the first real-time device state to generate the first fault warning code, wherein the first functional device is any functional device among the K functional devices; After receiving the first fault warning code, the equipment status monitoring center obtains the real-time equipment fault information by performing code analysis on the first fault warning code.

10. A fault location warning system according to claim 9, characterized in that: The equipment fault analysis module is also used for: Obtaining first historical fault information of the first functional device by calling local data, wherein the first historical fault information includes a plurality of sample fault operation data, a plurality of sample fault types, and a plurality of sample fault levels; A standard fault identification model is pre-built using a CNN network, wherein the input data of the standard fault identification model is the equipment operation data, and the output result is the equipment fault type and equipment fault level; Using the first historical fault information as training data to perform parameter optimization on the standard fault identification model, to obtain a first fault identification unit; Performing fault type aggregation on the multiple sample fault types to obtain multiple first fault types; Using the multiple first fault types to traverse the multiple sample fault levels to obtain multiple groups of first fault levels; generating a fault classification level table by using the plurality of first fault types and the plurality of groups of first fault levels; Obtaining a fault classification coding table by encoding and configuring the fault classification level table; Constructing a first fault coding unit based on the first device code of the first functional device and the fault classification coding table; By cascading the first fault identification unit and the first fault encoding unit, the construction of the first edge fault detection model is completed; By analogy, the K edge fault detection models of the K functional devices are constructed, and the K edge fault detection models are configured at the K edge nodes of the K functional devices.

11. A fault location warning system according to claim 10, characterized in that: The fault correlation analysis module is also used for: Obtaining K historical fault information of the K functional devices through local data calling; Collecting fault time from the first historical fault information to obtain multiple sample fault times; After aligning the data of the K historical fault information, synchronously collecting the data of the K historical fault information with the multiple sample fault times as constraints to obtain multiple groups of device status information; Calculate the failure probability of K-1 functional devices according to the multiple groups of device status information to obtain a first group of failure transfer probabilities, wherein the first group of failure transfer probabilities includes K-1 failure transfer probabilities; Similarly, K groups of fault transfer probabilities are calculated based on the K historical fault information; Constructing a fault transfer matrix according to the K functional devices and K groups of fault transfer probabilities, and updating the fault transfer matrix to the device status monitoring center; The equipment status monitoring center loads the real-time equipment failure information into the failure transfer matrix to perform failure correlation analysis to obtain the associated equipment failure risk.

12. A fault location warning system according to claim 11, characterized in that: The fault correlation analysis module is also used for: Parsing the real-time device fault information to obtain a first real-time fault type, a first real-time fault level, and the first functional device; Inputting the first functional device into the fault transfer matrix to perform fault correlation analysis to obtain K-1 real-time fault probabilities; Calculating the fault frequency according to the K historical fault information to obtain K fault frequency coefficients; Reversely screening the K fault frequency coefficients to obtain K-1 fault frequency coefficients according to the first functional device; Performing weighted calculation on the K-1 real-time fault probabilities and the K-1 fault frequency coefficients to obtain K-1 updated fault probabilities; Using the K-1 updated fault probabilities to traverse the simulated fault level table, to obtain K-1 simulated fault risk levels; K-1 simulated fault risk levels are output as the associated equipment fault risks.

13. A fault location warning system according to claim 12, characterized in that: The primitive attribute mapping module is also used for: Preset K graphic element attribute definitions, wherein the graphic element attribute definitions include a fault color level sequence and a risk color level sequence; After the K graphic element attribute definitions call the first graphic element attribute definition of the first functional device, traverse the first fault color level sequence of the first graphic element attribute definition using the first real-time fault level to obtain the first real-time graphic element attribute; Reversely calling K-1 graphic element attribute definitions according to the first functional device in the K graphic element attribute definitions; Using the K-1 simulated fault risk level mappings to traverse the K-1 risk color level sequences in the K-1 primitive attribute definitions to obtain K-1 associated primitive attributes; The first real-time primitive attribute and K-1 associated primitive attributes constitute the primitive display information.

14. A fault location warning system according to claim 13, characterized in that: The fault location warning module is also used for: According to the mapping relationship between the K device primitives and the K functional devices, the first real-time primitive attribute and K-1 associated primitive attributes are used to update the attributes of the K device primitives to obtain an initial warning screen display; The first device icon is located on the initial warning screen according to the first functional device, and the first real-time fault type is displayed as text on the first device icon, so as to complete the fault location of the initial warning screen and generate the fault location warning screen.

15. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a fault location and early warning method described in any one of claims 1 to 7 are implemented.

Images