Fault backtracking system

Abstract

The invention provides a fault backtracking system, and relates to the technical field of fault identification, and the fault backtracking system comprises at least one side end embedded device and a cloud platform. The side end embedded equipment is used for collecting equipment fault data of fault equipment; the cloud platform comprises a message agent unit and a processing unit, and the message agent unit is used for receiving and storing equipment fault data sent by the edge end embedded equipment; and the processing unit is used for reading the equipment fault data from the message agent unit and carrying out fault analysis based on the equipment fault data to obtain a fault backtracking result, so that complete and accurate fault backtracking is realized, an accident occurrence process is restored, and a fault occurrence position is determined.

Description

Technical Field

[0001] The present application relates to the technical field of fault identification, and in particular to a fault backtracking system. Background Art

[0002] With the continuous expansion of the scale of energy storage systems and the increasing complexity of the structure of energy storage power stations, the safety and reliability of energy storage systems face huge challenges. As a place where high-intensity energy is concentrated, any accident in an energy storage power station may lead to serious consequences such as combustion, explosion, and grid fluctuations. In order to avoid similar situations, it is necessary to conduct a detailed analysis of energy storage power station accidents to find out the causes of the accidents and take preventive measures. Summary of the invention

[0003] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0004] To this end, the first objective of the present application is to propose a fault backtracing system to achieve detailed and accurate fault backtracing.

[0005] To achieve the above-mentioned purpose, the first embodiment of the present application proposes a fault backtracking system, the system comprising at least one edge embedded device and a cloud platform;

[0006] The edge embedded device is used to collect device fault data of the faulty device;

[0007] The cloud platform includes a message proxy unit and a processing unit, wherein the message proxy unit is used to receive and store the device fault data sent by the edge embedded device;

[0008] The processing unit is used to read the device fault data from the message proxy unit, and perform fault analysis based on the device fault data to obtain a fault backtracking result.

[0009] In some implementations, the edge embedded device further includes:

[0010] A backup unit, used to back up the collected equipment fault data to obtain at least two copies of the faulty equipment data;

[0011] The encryption unit is used to encrypt at least two copies of the faulty device data and obtain the encrypted device fault data for transmission.

[0012] In some implementations, the edge embedded device and the remote platform communicate through a message subscription and publishing mechanism to achieve transmission of device fault data.

[0013] In some implementations, the processing unit is further used to perform data filtering and data filling on the device fault data to obtain target fault data;

[0014] Knowledge extraction and knowledge integration are performed on the target fault data, and fault backtracing is performed based on the time mark to obtain a fault backtracing result, wherein the fault backtracing result includes one or more of the fault occurrence process, the fault location, and the fault impact range.

[0015] In some implementations, the processing unit is further used to obtain historical fault tracing results, and perform model training according to the historical fault tracing results to obtain a fault identification model;

[0016] Fault identification is performed on the operating data of the device to be tested based on the fault identification model to obtain a fault identification result.

[0017] In some implementations, in response to the fault identification result indicating that there is a fault risk, the processing unit issues a fault warning.

[0018] In some implementations, the processing unit is further used to extract decision rules according to the fault identification model, wherein the decision rules include fault identification rules of different data types;

[0019] The decision rule is sent to the edge embedded device.

[0020] In some implementations, the edge embedded device is further used to perform fault identification on the operating data of the device under test based on the decision rule;

[0021] In response to the operating data of the device under test satisfying any one of the decision rules, it is determined that the operating data of the device under test has a failure risk.

[0022] In some implementations, in response to determining that there is a risk of failure in the operating data of the device under test, the edge embedded device increases the frequency of collecting the operating data of the device under test and issues a failure warning.

[0023] In some implementations, the edge embedded device is externally connected to one or more sensor devices, and obtains environmental data of the faulty device based on the sensor devices;

[0024] The device-related data of the faulty device is collected based on the edge embedded device itself, and the device fault data of the faulty device is determined based on the device-related data and the environmental data.

[0025] A fault backtracing system provided by the present application includes an edge embedded device and a cloud platform. The edge embedded device is configured to comprehensively collect fault equipment data to provide an analysis basis for fault backtracing. The edge embedded device and the cloud platform are connected and communicated by wired or wireless means to achieve stable transmission and sending of fault data. The cloud platform includes a message proxy unit and a processing unit. The message proxy unit implements message proxy and storage. The processing unit obtains and analyzes the equipment fault data to achieve complete and accurate fault backtracing, restore the accident process, determine the location of the fault, and achieve a comprehensive review of the fault process.

[0026] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0028] Figure 1 A structural diagram of a fault backtracking system provided in an embodiment of the present application;

[0029] Figure 2 A structural diagram of another fault backtracking system provided in an embodiment of the present application;

[0030] Figure 3 It is a flow chart of a method for fault backtracking and fault monitoring provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0032] This application can be applied to the fault accident backtracking of energy storage power station scenarios. The backtracking analysis of fault accidents can record the operating parameters and status changes of various equipment in the energy storage power station before and after the accident, providing data support for accident analysis. At present, the power industry regulatory agency has formulated strict specifications and standards for the safe operation and accident management of power stations, prompting energy storage power station operators to establish a complete accident recall and analysis mechanism. The regulatory agency requires energy storage power stations to report accidents in a timely and accurate manner, and provide detailed accident cause analysis and improvement measures.

[0033] There are many types of power station equipment, including generators, transformers, circuit breakers and other large equipment. Failures of these equipment may cause power station accidents. Currently, there are many equipment manufacturers on the market, and their data structure points and communication protocols are not the same. Therefore, it is necessary to add a data collection system that supports multiple protocol logics to ensure that it can quickly adapt to the requirements of various manufacturers and reduce deployment costs. In non-operating states such as battery transportation and storage, there will also be problems of battery explosion due to external factors such as collision and extrusion. Therefore, it is necessary to monitor the battery module for a long time in a non-operating state. At the same time, when a fault occurs, it is often accompanied by a power outage and a disconnection from the network. Under these abnormal conditions, the accident recall system is also required to be able to operate normally for data processing and collection, and to be able to upload data in time after the fault is restored, trace back the logic of the fault, and generate an overall analysis of the accident.

[0034] A fault backtracking system according to an embodiment of the present application is described below with reference to the accompanying drawings.

[0035] Figure 1 This is a structural diagram of a fault tracing system provided in an embodiment of the present application. Figure 1 As shown, the fault tracing system includes at least one edge embedded device and a cloud platform.

[0036] Edge embedded devices are used to collect equipment failure data of faulty equipment.

[0037] In some implementations, edge embedded devices are embedded devices deployed in edge computing environments, which may include a self-contained power supply and a small inverter, capable of supporting 12-24V DC power supply, normal operation under 220V AC power supply and charging the self-contained power supply at the same time, and in the power-off state, the self-contained power supply uses silicon-carbon negative electrode technology, which can support the normal operation of the device for 24 hours and low-power operation for 48 hours.

[0038] In some implementations, the internal program of the edge embedded device can determine the current fault and power supply status, and adjust the internal working mode to ensure that the corresponding information data can be accurately collected when a fault occurs.

[0039] The cloud platform includes a message proxy unit and a processing unit. The message proxy unit is used to receive and store device fault data sent by edge embedded devices; the processing unit is used to read device fault data from the message proxy unit, and perform fault analysis based on the device fault data to obtain fault backtracing results.

[0040] Optionally, the edge embedded device and the cloud platform can be connected via a wired or wireless network to enable data transmission between the edge embedded device and the cloud platform.

[0041] In some implementations, the cloud platform is set up in the form of a server cluster, and a storage area network storage structure mode is used for data storage to improve data processing efficiency. In this embodiment, the cloud platform includes a message proxy unit and a processing unit. The message proxy unit is used to transmit messages between different applications. The message proxy acts as a central hub, receiving messages from publishers and distributing them to subscribers. The message proxy unit may include one or more data storage servers for receiving and storing equipment fault data.

[0042] The processing unit can act as a subscriber to read the equipment fault data from the message proxy unit, and perform feature extraction and analysis on the equipment fault data, thereby realizing fault backtracing and obtaining a fault backtracing result; optionally, the fault backtracing result may include information such as the cause of the fault and the location of the fault, so as to generate a reference record of the fault occurrence.

[0043] In some implementations, the fault backtracking results can also be visualized to more intuitively display fault information such as the cause of the fault and the location of the fault.

[0044] In this embodiment, a fault backtracing system is formed by edge embedded devices and a cloud platform. The edge embedded devices are configured to comprehensively collect the data of faulty devices to provide an analysis basis for fault backtracing. The edge embedded devices and the cloud platform are connected and communicated by wired or wireless means to achieve stable transmission and sending of fault data. The cloud platform includes a message proxy unit and a processing unit. The message proxy unit implements message proxy and storage. The processing unit obtains and analyzes the device fault data to achieve the fault backtracing process and visualizes the fault backtracing results to completely restore the accident process, determine the location of the fault, and achieve complete backtracing and comprehensive review of the fault process.

[0045] Based on the above embodiments, Figure 2 This is a structural diagram of another fault tracing system provided in an embodiment of the present application. Figure 2 As shown, the fault tracing system includes at least one edge embedded device and a cloud platform.

[0046] Edge embedded devices are used to collect equipment failure data of faulty equipment.

[0047] In some implementations, the edge embedded device is connected to one or more sensor devices, and obtains environmental data of the faulty device based on the sensor devices; the edge embedded device itself collects device-related data of the faulty device, and determines device fault data of the faulty device based on the device-related data and environmental data.

[0048] The cloud platform includes a message proxy unit and a processing unit. The message proxy unit is used to receive and store device fault data sent by edge embedded devices; the processing unit is used to read device fault data from the message proxy unit, and perform fault analysis based on the device fault data to obtain fault backtracing results.

[0049] Optionally, the edge embedded device can collect and integrate equipment-related data based on the Engine Management System (EMS). The environmental data can be external environmental data such as temperature, humidity, and pressure when a device fails, which can be measured according to corresponding temperature sensors, humidity sensors, and pressure sensors.

[0050] In some implementations, considering that the data point tables of EMS systems of different manufacturers are different and the sensor communication data protocols are also different, this embodiment can summarize the data, protocols and communication methods of the currently running sites, and add support for different communication methods such as International Electrotechnical Commission (IEC) 104, IEC 61850, Recommended Standard (RS) 485, RS232 and Input Output (IO), so as to meet the communication protocols of various manufacturers as much as possible, and greatly optimize the adaptation process of various devices through a modular program structure. Through configurable point correspondence and convergent data comparison rules, the rules of protocol, manufacturer and data analysis can be configurable, thereby achieving the purpose of instant communication, module change and protocol adaptation, and having extremely high flexibility and scalability.

[0051] In some implementations, based on the network port and wireless communication antenna of the edge embedded device, through remote tunnel deployment, users can remotely view the devices collected by the edge embedded device and independently decide to perform Over-The-Air Technology (OTA) upgrades, which can quickly iterate programs and update functions, further ensuring the stability of the fault tracing process.

[0052] In some implementations, the edge embedded device also includes a backup unit and an encryption unit. The backup unit is used to back up the collected device failure data to obtain at least two copies of the failed device data. Optionally, a disk array can be formed using multiple storage media in the edge embedded device to achieve redundant backup of the data. The collected data is written to at least two disks at the same time. When one disk fails, the other disk can still provide data access to ensure data availability.

[0053] It can be understood that the encryption unit is used to encrypt at least two copies of faulty device data, and the encrypted device fault data is transmitted, so that the data is stored in ciphertext form, following the confidentiality principle to ensure data security.

[0054] Optionally, the edge embedded device and the remote platform can communicate through a message subscription and publishing mechanism to achieve the transmission of equipment fault data; specifically, the open source stream processing platform kafka or the message queuing telemetry transport protocol (Message Queuing Telemetry Transport, MQTT) and other technologies can be used to establish a communication network architecture, for example, and Ethernet for communication, so that the communication between the edge embedded device and the cloud platform has the functional characteristics of loose coupling, flexibility and customizability, efficient message transmission, and enhanced system reliability, ensuring that the monitoring fault data can be sent stably, supporting flexible on-site configuration of various application scenarios, supporting wired network connection and wireless network configuration, achieving rapid adaptation, precise deployment, reducing debugging and maintenance costs, and improving efficiency.

[0055] It can be understood that the edge embedded device is the publisher and the cloud platform is the message agent and subscriber. For example, the message agent unit provides the message agent, and the processing unit subscribes to data as a subscriber. The edge embedded device collects equipment fault data and sends the equipment fault data to the message agent unit of the cloud platform. The cloud platform deploys different subscribers according to needs. The subscriber can be the cloud platform's own processing unit or other user devices, so as to pre-process the data according to the subscriber. The independent development and maintenance of the edge embedded devices and the cloud platform can be achieved, and new subscribers and publishers can be added at any time. It also supports multiple communication protocols such as MQTT and Kafka. The asynchronous communication mode and message buffering and forwarding of the message agent unit greatly increase the reliability of data transmission, ensuring that the data can be directly subscribed and processed once it is published. The processing unit can obtain and process the data at its own pace, and will not affect the collection and release of equipment fault data of the edge embedded device due to slow data processing speed.

[0056] In some implementations, the processing unit is also used to filter and fill in the equipment fault data to obtain target fault data; optionally, a rule-based filtering method can be used to extract key data such as electrical data, non-electrical data, and system operating status quantities according to equipment operating characteristics, deployed sensor parameters, and historical fault data information, and to supplement missing values ​​in the data, such as using mean filling or common value filling methods to supplement and configure missing values, thereby obtaining target fault data.

[0057] Furthermore, knowledge extraction and knowledge integration are performed on the target fault data, and fault backtracking is performed based on time tags to obtain fault backtracking results; optionally, the subject attributes in the fault occurrence can be structured through a knowledge extraction algorithm, so as to define the pattern of the relationship between each subject in the fault according to the power plant operation mode and architecture mode, so as to extract the cause of each subject fault, the influencer and relationship model that causes the fault; then the knowledge integration algorithm is used to align each entity with the subject attribute, define the logical relationship of the fault, integrate the relational logical influence data generated in the entire accident, confirm the link relationship of the fault, and perform fault backtracking based on the time tag, wherein the fault backtracking result includes one or more of the fault occurrence process, fault location and fault impact range, so as to be able to completely restore the accident process, determine the fault location and evaluate the accident impact range.

[0058] Optionally, to avoid the recurrence of similar accidents, the processing unit is also used to obtain historical fault backtracking results, and perform model training based on the historical fault backtracking results to obtain a fault identification model; based on the fault identification model, fault identification is performed on the operating data of the device under test to obtain a fault identification result, which can identify the occurrence of faults in advance when the device is not in operation; in some implementations, the historical fault backtracking results record at least data such as device system operating parameters, device operating status information, event sequence, timestamp, and fault occurrence results, and the device system operating parameters, device operating status information, event sequence, and timestamp are used as input parameters, and the fault occurrence results are used as decision-making guidelines, so as to train a fault identification model based on a long short-term memory network (Long Short-Term Memory, LSTM), perform fault identification on the operating data of the device under test based on the fault identification model, perform abstract analysis on the collected operating data, and perform collection comparison and reasoning based on the eigenvalues ​​to obtain a fault identification result of whether the device under test has a risk of failure.

[0059] In response to the fault identification result indicating the existence of a fault risk, the processing unit issues a fault warning to ensure timely warning of the occurrence of a fault; in some implementations, the possible cause of the fault can also be inferred, and a detailed fault explanation can be provided to maintenance personnel through an interpreter to ensure efficient handling of the fault.

[0060] In some implementations, the processing unit is also used to extract decision rules based on the fault identification model, and the decision rules include fault identification rules for different data types; optionally, the fault identification rules for different data types may be minimum threshold rules formulated for different data types, for example, the temperature cannot exceed the temperature threshold, and the pressure cannot exceed the pressure threshold, and based on the fault identification rules of each data type, it is determined whether the data of the corresponding data type satisfies the corresponding fault identification rules to determine whether the data has a risk of failure.

[0061] Optionally, the decision rules can be sent to the edge embedded device, and the edge embedded device is also used to perform fault identification on the operating data of the device under test based on the decision rules; that is, the operating data of the device under test is judged and identified according to the decision rules to determine whether the corresponding fault identification rules are met, thereby obtaining a fault identification result. In this way, in an offline state, fault pre-occurrence detection can be achieved through the edge embedded device, which reduces the amount of computation and resource usage compared to the identification of the fault identification model of the cloud platform.

[0062] In response to the operating data of the device under test satisfying any rule in the decision rules, it is determined that the operating data of the device under test has a failure risk; for example, if the temperature in the operating data of the device under test exceeds a temperature threshold, it is determined that the operating data of the device under test has a failure risk.

[0063] In response to determining that there is a fault risk in the operating data of the device under test, the edge embedded device increases the frequency of collecting the operating data of the device under test and issues a fault warning; that is, when a fault is detected, the frequency of data collection, storage and release is increased, and the user is pre-warned through the network, displaying the corresponding fault judgment rule logic to achieve accurate fault monitoring.

[0064] In this embodiment, the edge embedded device can be connected to one or more sensor devices to collect environmental data to improve the accuracy of fault tracing, and add multiple communication methods to meet the communication protocols of various manufacturers to ensure smooth data transmission. More comprehensive equipment fault data is formed based on device-related data and environmental data. The equipment fault data can also be backed up and encrypted in the edge embedded device to ensure data availability and data security; the equipment fault data is sent to the cloud platform, and the edge embedded device and the cloud platform communicate through a message subscription and publishing mechanism, so that the communication between the edge embedded device and the cloud platform has the functional characteristics of loose coupling, flexibility and customizability, efficient message transmission, and enhanced system reliability, ensuring that the monitoring fault data can be sent stably; the cloud After obtaining the equipment fault data, the processing unit in the end platform filters and fills the equipment fault data to improve the reliability of data analysis, extracts and integrates knowledge based on the pre-processed target fault data, and then traces the fault back according to the time mark to obtain the fault backtracking result; further, the fault identification model is trained based on the historical fault backtracking results, so that the fault identification model can identify faults of equipment operation data in a non-operating state or a real-time operating state, and determine whether there is a pre-fault situation. Decision rules can also be extracted based on the fault identification model and sent to the edge embedded device to ensure that the pre-fault identification can be completed based on the edge embedded device in the absence of a network, and timely early warning processing can be performed to achieve comprehensive and accurate fault monitoring.

[0065] Based on the above embodiments, Figure 3 It is a flow chart of a method for fault backtracing and fault monitoring provided by an embodiment of the present disclosure. When an accident occurs, fault data is collected and published through edge embedded devices. The cloud platform subscribes to the received fault data and restores the fault logic based on algorithms such as knowledge extraction and knowledge integration, and visualizes the fault backtracing results. After determining the fault backtracing results, a fault identification model can be constructed and trained, and fault detection of the operating data of the equipment under test is performed according to the fault identification model. Decision rules are extracted based on the fault identification model, and fault pre-occurrence identification can also be performed based on the decision rules. When the fault identification model or decision rule identifies the pre-occurrence of a fault, early warning processing is performed in a timely manner to ensure the complete process of the fault occurrence is traced back, and accurate identification of the pre-occurrence of the fault is performed to ensure the safe operation of the equipment.

[0066] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0067] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0068] The present application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, the present disclosure is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, the risk can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.

[0069] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0070] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0071] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0072] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0073] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0074] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0075] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0076] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A fault tracing system, characterized in that: The system includes at least one edge embedded device and a cloud platform; The edge embedded device is used to collect device fault data of the faulty device; The cloud platform includes a message proxy unit and a processing unit, wherein the message proxy unit is used to receive and store the device fault data sent by the edge embedded device; The processing unit is used to read the device fault data from the message proxy unit, and perform fault analysis based on the device fault data to obtain a fault backtracking result.

2. The system according to claim 1, characterized in that The edge embedded device also includes: A backup unit, used to back up the collected equipment fault data to obtain at least two copies of the faulty equipment data; The encryption unit is used to encrypt at least two copies of the faulty device data and obtain the encrypted device fault data for transmission.

3. The system according to claim 1 or 2, characterized in that: The edge embedded device and the remote platform communicate through a message subscription and publishing mechanism to achieve the transmission of device fault data.

4. The system according to claim 1, characterized in that The processing unit is also used to filter and fill the equipment fault data to obtain target fault data; Knowledge extraction and knowledge integration are performed on the target fault data, and fault backtracing is performed based on the time mark to obtain a fault backtracing result, wherein the fault backtracing result includes one or more of the fault occurrence process, the fault location, and the fault impact range.

5. The system according to claim 4, characterized in that The processing unit is also used to obtain historical fault tracing results, and perform model training according to the historical fault tracing results to obtain a fault identification model; Fault identification is performed on the operating data of the device to be tested based on the fault identification model to obtain a fault identification result.

6. The system according to claim 5, characterized in that In response to the fault identification result indicating that there is a fault risk, the processing unit issues a fault warning.

7. The system according to claim 5, characterized in that The processing unit is further used to extract decision rules according to the fault identification model, wherein the decision rules include fault identification rules of different data types; The decision rule is sent to the edge embedded device.

8. The system according to claim 7, characterized in that The edge embedded device is also used to perform fault identification on the operating data of the device under test based on the decision rule; In response to the operating data of the device under test satisfying any one of the decision rules, it is determined that the operating data of the device under test has a failure risk.

9. The system according to claim 8, characterized in that In response to determining that there is a fault risk in the operating data of the device under test, the edge embedded device increases the frequency of collecting the operating data of the device under test and issues a fault warning.

10. The system according to claim 1, characterized in that The edge embedded device is externally connected to one or more sensor devices, and obtains environmental data of the faulty device based on the sensor devices; The device-related data of the faulty device is collected based on the edge embedded device itself, and the device fault data of the faulty device is determined based on the device-related data and the environmental data.

Images