Fault prediction processing method, system and equipment of intelligent equipment and medium

Abstract

The invention relates to a fault prediction processing method and system for intelligent equipment, equipment and a medium. The method comprises the following steps: acquiring historical working data of the intelligent equipment; preprocessing the historical working data; constructing a fault prediction model based on the preprocessed historical working data; acquiring real-time working data of the intelligent equipment; preprocessing the real-time working data; inputting the preprocessed real-time working data into a fault prediction model for fault prediction; if the fault prediction model predicts that the intelligent equipment has a fault, identifying a fault type, and judging whether the corresponding real-time working data exceed threshold data or not based on the fault type; and if the corresponding real-time working data exceeds the threshold data, performing automatic processing on the intelligent equipment based on the identified fault type and the corresponding processing rule. According to the invention, false alarm can be avoided, automatic processing can be carried out without manual intervention, manual intervention is reduced, and the maintenance cost is reduced.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, system, device and medium for predicting and processing faults of intelligent devices. Background Art

[0002] With the advancement of technology, smart devices (such as smart cabinets, etc.) have developed rapidly due to their convenience and unmanned operation. However, smart devices also generally have the problem of insufficient stability. If a smart device fails, it is often discovered in time but maintenance cannot be carried out in time, thus affecting the normal use of the smart device.

[0003] In the field of intelligent equipment management, predictive maintenance is a key technology to reduce the failure rate and improve the efficiency of equipment operation. However, the existing fault prediction based only on fault prediction models has problems such as low prediction accuracy and frequent false alarms. In addition, when it is predicted that a smart device is about to fail, manual intervention is required to handle it, which results in more manual intervention and higher maintenance costs. Summary of the invention

[0004] Based on this, it is necessary to provide a fault prediction and processing method, system, device and medium for intelligent devices in response to the above technical problems.

[0005] In a first aspect, the present application provides a fault prediction processing method for an intelligent device, the fault prediction processing method for an intelligent device comprising:

[0006] Obtain historical working data of smart devices;

[0007] Preprocessing the historical work data;

[0008] Build a fault prediction model based on preprocessed historical working data;

[0009] Obtaining real-time working data of the smart device;

[0010] Preprocessing the real-time working data;

[0011] Inputting the preprocessed real-time working data into the fault prediction model for fault prediction;

[0012] If the fault prediction model predicts that the intelligent device has a fault, the fault type is identified, and based on the fault type, the corresponding real-time working data is determined to exceed the threshold data;

[0013] If the corresponding real-time working data exceeds the threshold data, the intelligent device is automatically processed based on the identified fault type and the corresponding processing rules to avoid the failure of the intelligent device.

[0014] Optionally, the historical work data includes time series data; and the preprocessing of the historical work data includes:

[0015] Cleaning the historical work data;

[0016] Normalize the cleaned historical work data;

[0017] The normalized historical work data is divided using sliding window technology;

[0018] Extract features from the divided historical work data;

[0019] Filter the extracted features.

[0020] Optionally, the historical working data includes historical working data of the smart device in a normal working state and historical working data of the smart device in a faulty state; and constructing a fault prediction model based on the preprocessed historical working data includes:

[0021] Fault marking of pre-processed historical working data;

[0022] Selecting an initial failure prediction model;

[0023] The initial fault prediction model is trained based on historical working data after fault annotation to obtain the fault prediction model.

[0024] Optionally, the inputting the preprocessed real-time working data into the fault prediction model for fault prediction includes: predicting the fault probability of the smart device failing based on the following formula:

[0025]

[0026] Where P(faultX) is the failure probability of the intelligent device under the given feature set X; β0 is the intercept term; β i is feature x i The coefficient of ; n is the number of features in the feature set X; i is an integer greater than or equal to 1 and less than or equal to N.

[0027] Optionally, after inputting the preprocessed real-time working data into the fault prediction model for fault prediction, the method further includes:

[0028] Generate a fault prediction report, the fault prediction including the fault probability of the smart device failing. If the fault probability is greater than a preset fault probability, it is predicted that the smart device fails. If the smart device is predicted to fail, the fault prediction report also includes the fault time and the fault type.

[0029] Optionally, if the corresponding real-time working data exceeds the threshold data, automatically processing the smart device based on the identified fault type and the corresponding processing rule to avoid the smart device from malfunctioning includes:

[0030] If the corresponding real-time working data exceeds the threshold data, a processing rule corresponding to the fault type is selected based on the identified fault type, and the processing rule includes: an execution condition of the processing operation and steps of the processing operation.

[0031] Optionally, the processing rules are encoded using a decision tree or expert system.

[0032] In a second aspect, the present application further provides a fault prediction and processing system for an intelligent device, the fault prediction and processing system for an intelligent device comprising:

[0033] A historical work data acquisition module is used to acquire historical work data of smart devices;

[0034] A first preprocessing module, used for preprocessing the historical working data;

[0035] A fault model building module is used to build a fault prediction model based on preprocessed historical working data;

[0036] A real-time working data acquisition module, used to acquire the real-time working data of the smart device;

[0037] A second preprocessing module, used for preprocessing the real-time working data, and inputting the preprocessed real-time working data into the fault prediction model for fault prediction;

[0038] An identification and judgment module, used to identify the fault type when the fault prediction model predicts that the intelligent device has a fault, and to judge whether the corresponding real-time working data exceeds the threshold data based on the fault type;

[0039] The automatic processing module is used to automatically process the intelligent device based on the identified fault type and the corresponding processing rules when the corresponding real-time working data exceeds the threshold data, so as to avoid the failure of the intelligent device.

[0040] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the fault prediction and processing method for an intelligent device described in any one of the first aspects above when executing the computer program.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the fault prediction and processing method for an intelligent device described in any one of the above-mentioned first aspects are implemented.

[0042] The fault prediction and processing method, system, device and medium of the above-mentioned intelligent device obtain the historical working data of the intelligent device; preprocess the historical working data; build a fault prediction model based on the preprocessed historical working data; obtain the real-time working data of the intelligent device; preprocess the real-time working data; input the preprocessed real-time working data into the fault prediction model for fault prediction; if the fault prediction model predicts that the intelligent device has a fault, identify the fault type, and determine whether the corresponding real-time working data exceeds the threshold data based on the fault type; if the corresponding real-time working data exceeds the threshold data, automatically process the intelligent device based on the identified fault type and the corresponding processing rules to avoid the failure of the intelligent device. After the fault prediction model predicts that the smart device has a fault, by adding the step of identifying the fault type and judging whether the corresponding real-time working data exceeds the threshold data based on the fault type, the accuracy of the fault prediction judgment can be ensured, thereby avoiding false alarms; at the same time, by setting a step of automatically processing the smart device based on the identified fault type and the corresponding processing rules when the corresponding real-time working data exceeds the threshold data to avoid the smart device from failing, when it is predicted that the smart device is about to fail, it can be automatically processed without human intervention, thereby reducing human intervention and lowering maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of a flow chart of a fault prediction and processing method for an intelligent device provided in one embodiment of the present application;

[0044] Figure 2 A structural block diagram of a fault prediction and processing system for an intelligent device provided in another embodiment of the present application;

[0045] Figure 3 This is a diagram of the internal structure of a computer device provided in yet another embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] In one embodiment, see Figure 1The present application provides a fault prediction and processing method for an intelligent device, and the fault prediction and processing method for an intelligent device may include the following steps: S10 to S17.

[0048] S10: Obtain historical working data of the smart device.

[0049] S11: Preprocessing the historical working data.

[0050] S12: Build a fault prediction model based on the preprocessed historical working data.

[0051] S13: Acquire real-time working data of the smart device.

[0052] S14: Preprocessing the real-time working data.

[0053] S15: Inputting the preprocessed real-time working data into the fault prediction model for fault prediction.

[0054] S16: If the fault prediction model predicts that the smart device has a fault, the fault type is identified, and based on the fault type, it is determined whether the corresponding real-time working data exceeds the threshold data.

[0055] S17: If the corresponding real-time working data exceeds the threshold data, the smart device is automatically processed based on the identified fault type and the corresponding processing rules to avoid the smart device from malfunctioning.

[0056] In the fault prediction and processing method for the intelligent device of the present application, by adding the step of identifying the fault type and judging whether the corresponding real-time working data exceeds the threshold data based on the fault type, the accuracy of the fault prediction judgment can be ensured, thereby avoiding false alarms; at the same time, by setting a step of automatically processing the intelligent device based on the identified fault type and the corresponding processing rules when the corresponding real-time working data exceeds the threshold data to avoid the failure of the intelligent device, when it is predicted that the intelligent device is about to fail, it can be automatically processed without human intervention, thereby reducing human intervention and lowering maintenance costs.

[0057] In step S10, refer to Figure 1 In step S10, historical working data of the smart device is obtained.

[0058] As an example, the operating data of the smart device can be collected by sensors and monitoring devices deployed on the smart device and saved as the historical operating data. The historical operating data may include but is not limited to temperature, voltage, current, and operation logs.

[0059] As an example, a distributed data acquisition system may be used to synchronize the working data collected at each monitoring point in real time; the collected working data may be stored in a designed data storage device as the historical working data to ensure the integrity and traceability of the historical working data.

[0060] In step S11, refer to Figure 1 In step S11, the historical working data is preprocessed.

[0061] As an example, the historical working data may include time series data, that is, when the collected working data is stored, it may be stored as time series data.

[0062] As an example, the historical working data may include historical working data of the smart device in a normal working state and historical working data of the smart device in a fault state.

[0063] As an example, step S11 may include the following steps: S111 to S115.

[0064] S111: Cleaning the historical work data.

[0065] S112: Normalize the cleaned historical work data.

[0066] S113: Use sliding window technology to divide the normalized historical work data.

[0067] S114: Extract features from the divided historical work data.

[0068] S115: Screening the extracted features.

[0069] Specifically, in step S111, the historical work data may be cleaned using, but not limited to, statistical methods and machine learning algorithms to remove outliers and duplicate data.

[0070] Specifically, in step S112, the influence of different dimensions on subsequent fault prediction model training can be eliminated through normalization processing.

[0071] Specifically, in step S113, a sliding window technique may be used to divide the normalized historical working data into data segments of fixed length to meet the input requirements of the subsequent fault prediction model.

[0072] Specifically, in step S114, features directly related to the performance of the smart device, such as mean value, variance or trend, etc., can be extracted from the divided historical working data based on neighborhood knowledge and data analysis results.

[0073] Specifically, in step S114, time series analysis technology may be used to extract periodic features, trend features, and seasonal features of the time series data (ie, the divided historical work data).

[0074] Specifically, in step S115, the features that contribute most to the fault prediction model may be screened out using, but not limited to, correlation analysis and information gain methods. The dimensions of the screened features may also be further reduced by algorithms such as stepwise regression or decision trees to avoid overfitting.

[0075] In step S12, refer to Figure 1 In step S12, a fault prediction model is constructed based on the preprocessed historical working data.

[0076] As an example, step S12 may include the following steps: S121 to S123.

[0077] S121: Fault marking is performed on the pre-processed historical working data.

[0078] S122: Select an initial fault prediction model.

[0079] S123: Training the initial fault prediction model based on the historical working data after fault annotation to obtain the fault prediction model.

[0080] Specifically, in step S121, expert knowledge and historical fault records can be combined to perform fault marking on the preprocessed historical working data to distinguish normal historical working data (historical working data in working state) and abnormal historical working data (historical working data in fault state).

[0081] Specifically, after the preprocessed historical working data is marked for fault, a time window may be created to ensure that the abnormal historical working data contains sufficient information before the fault.

[0082] Specifically, in step S122, a time series prediction model may be selected as the initial fault prediction model, such as a long short-term memory network (LSMT) model or a gated recurrent unit (GRU) model, etc.

[0083] Specifically, in step S123, the historical working data after fault marking can be divided into a training set, a verification set and a test set. The training set can be used to train the initial fault prediction model, the verification set can be used to verify the trained initial fault prediction model, and the test set can be used to test the initial fault prediction model after verification to obtain the fault prediction model.

[0084] In step S13, refer to Figure 1In step S13, real-time working data of the smart device is obtained.

[0085] As an example, the real-time operating data of the smart device may be collected by sensors and monitoring devices deployed on the smart device. The real-time operating data may include but is not limited to temperature, voltage, current, etc.

[0086] In step S14, refer to Figure 1 In step S14, the real-time working data is preprocessed.

[0087] As an example, the method for preprocessing the real-time working data may include: cleaning the real-time working data; normalizing the cleaned real-time working data; and extracting features from the normalized real-time working data.

[0088] In step S15, refer to Figure 1 In step S15, the preprocessed real-time working data is input into the fault prediction model for fault prediction.

[0089] As an example, the failure probability of the smart device failing may be predicted based on the following formula:

[0090]

[0091] Where P(faultX) is the failure probability of the intelligent device under the given feature set X; β0 is the intercept term; β i is feature x i The coefficient of ; n is the number of features in the feature set X; i is an integer greater than or equal to 1 and less than or equal to N.

[0092] As an example, after step S15, the following steps may also be included: generating a fault prediction report, wherein the fault prediction may include the fault probability of the smart device failing, and if the fault probability is greater than a preset fault probability, the smart device is predicted to fail; if the smart device is predicted to fail, the fault prediction report may also include the fault time and the fault type. The fault prediction report may be provided to maintenance personnel for reference, and the maintenance personnel may know whether the smart device will fail, the fault time, and the fault type through the fault prediction report.

[0093] In step S16, refer to Figure 1 In step S16, if the fault prediction model predicts that the intelligent device has a fault, the fault type is identified, and based on the fault type, it is determined whether the corresponding real-time working data exceeds the threshold data.

[0094] As an example, the fault type may be a fault type that can be automatically processed, such as abnormal temperature or current fluctuation.

[0095] As an example, the threshold data may be obtained based on analysis of historical fault data to ensure that fault signals can be captured sensitively while avoiding false alarms.

[0096] In one implementation, taking temperature abnormality as an example, the threshold data may be set to 75° C. When the temperature at the monitoring location corresponding to the smart device exceeds the threshold data, an automatic processing flow is triggered.

[0097] In step S17, refer to Figure 1 In step S17, if the corresponding real-time working data exceeds the threshold data, the smart device is automatically processed based on the identified fault type and the corresponding processing rules to avoid failure of the smart device.

[0098] As an example, if the corresponding real-time working data exceeds the threshold data, it is ultimately determined that the smart device is about to fail. At this time, based on the identified fault type, a processing rule corresponding to the identified fault type can be selected to automatically process the smart device.

[0099] As an example, the processing rule may include: execution conditions of the processing operation and steps of the processing operation. Specifically, taking the temperature abnormality of the monitoring position corresponding to the smart device as an example, the execution condition of the processing operation may be that the temperature of the monitoring position corresponding to the smart device is greater than a set threshold, such as 75°C; the steps of the processing operation may include: starting a cooling device to cool down the monitoring position with abnormal temperature.

[0100] It should be noted that the processing rules should be flexible and be able to adjust the processing strategy according to different fault types and the working status of the smart device.

[0101] As an example, the processing rules may be encoded using a decision tree or an expert system. Using a decision tree or an expert system to encode the processing rules can ensure that the system can automatically make decisions and execute corresponding processing operations.

[0102] In another embodiment, see Figure 2The present application also provides a fault prediction processing system for an intelligent device, which may include: a historical working data acquisition module 10, a first processing module 20, a fault model construction module 30, a real-time working data acquisition module 40, a second preprocessing module 50, an identification and judgment module 60 and an automatic processing module 70; wherein the historical working data acquisition module 10 is used to acquire the historical working data of the intelligent device; the first preprocessing module 20 is used to preprocess the historical working data; the fault model construction module 30 is used to construct a fault prediction model based on the preprocessed historical working data; the real-time working data acquisition module 40 is used to obtain the real-time working data of the smart device; the second preprocessing module 50 is used to preprocess the real-time working data, and input the preprocessed real-time working data into the fault prediction model for fault prediction; the identification and judgment module 60 is used to identify the fault type when the fault prediction model predicts that the smart device has a fault, and judge whether the corresponding real-time working data exceeds the threshold data based on the fault type; the automatic processing module 70 is used to automatically process the smart device based on the identified fault type and the corresponding processing rules when the corresponding real-time working data exceeds the threshold data, so as to avoid the smart device from failing.

[0103] As an example, the fault prediction processing system of the smart device can be used to perform the following steps: Figure 1 and the steps of the fault prediction and processing method for intelligent devices mentioned above; for the specific limitations of the fault prediction and processing system for intelligent devices, please refer to the limitations of the fault prediction and processing method for intelligent devices mentioned above, which will not be repeated here. Each module in the above-mentioned fault prediction and processing system for intelligent devices can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0104] As an example, the real-time working data acquisition module may be a part of the historical working data acquisition module, or may be a separate data acquisition device.

[0105] As an example, the fault prediction processing system of the smart device may further include an interface (not shown), which may be used for remote control by maintenance personnel, allowing maintenance personnel to remotely access the fault prediction processing system of the smart device through a secure link.

[0106] As an example, the interface may support multiple operations, such as restarting the smart device, adjusting parameters of the smart device, and diagnosing faults of the smart device, etc.

[0107] As an example, the interface may use a web service framework such as Flask or FastAPI to build a RESTful API.

[0108] As an example, the interface has an authentication and authorization mechanism to ensure that only authorized maintenance personnel can perform remote operations.

[0109] As an example, the fault prediction and processing system for the smart device may further include a recording module (not shown), which is used to record the automatic processing process and remote operation logs.

[0110] As an example, the interface may protect the security of data transmission through encrypted communication (such as HTTPS).

[0111] In one embodiment, the fault prediction processing system of the smart device detects that the temperature of a certain area of ​​the smart device exceeds the set threshold data of 75°C; the automatic processing module 70 automatically starts a cooling device (not shown) to perform a cooling process and notifies the maintenance personnel through the interface. The maintenance personnel can adjust the threshold data through the interface and monitor the cooling effect. The recording module records the automatic processing process and remote operation log to provide data support for subsequent analysis and optimization.

[0112] In another embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes 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 computer program in the non-volatile storage medium. The database of the computer device is used to store data such as deployment strategies. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it is implemented as follows Figure 1 And the fault prediction and processing method of the intelligent device described in the related embodiments.

[0113] In another embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it is implemented as follows Figure 1 The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0114] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0115] In another embodiment, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following is implemented: Figure 1 And the steps of the fault prediction and processing method of the intelligent device described in the related embodiments.

[0116] In another embodiment, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following Figure 1 And the steps of the fault prediction and processing method of the intelligent device described in the related embodiments.

[0117] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0118] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0119] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A fault prediction and processing method for an intelligent device, characterized in that: include: Obtain historical working data of smart devices; Preprocessing the historical work data; Build a fault prediction model based on preprocessed historical working data; Obtaining real-time working data of the smart device; Preprocessing the real-time working data; Inputting the preprocessed real-time working data into the fault prediction model for fault prediction; If the fault prediction model predicts that the intelligent device has a fault, the fault type is identified, and based on the fault type, the corresponding real-time working data is determined to exceed the threshold data; If the corresponding real-time working data exceeds the threshold data, the intelligent device is automatically processed based on the identified fault type and the corresponding processing rules to avoid the failure of the intelligent device.

2. The fault prediction and processing method for intelligent devices according to claim 1, characterized in that: The historical work data includes time series data; the preprocessing of the historical work data includes: Cleaning the historical work data; Normalize the cleaned historical work data; The normalized historical work data is divided using sliding window technology; Extract features from the divided historical work data; Filter the extracted features.

3. The fault prediction and processing method for intelligent devices according to claim 2, characterized in that: The historical working data includes historical working data of the smart device in a normal working state and historical working data of the smart device in a fault state; and constructing a fault prediction model based on the preprocessed historical working data includes: Fault marking of pre-processed historical working data; Selecting an initial failure prediction model; The initial fault prediction model is trained based on historical working data after fault annotation to obtain the fault prediction model.

4. The fault prediction and processing method for intelligent devices according to claim 1, characterized in that: The inputting the preprocessed real-time working data into the fault prediction model for fault prediction includes: predicting the fault probability of the smart device failing based on the following formula: Where P(faultX) is the failure probability of the intelligent device under the given feature set X; β0 is the intercept term; β i is feature x i The coefficient of ; n is the number of features in the feature set X; i is an integer greater than or equal to 1 and less than or equal to N.

5. The fault prediction and processing method for intelligent devices according to claim 1, characterized in that: After the pre-processed real-time working data is input into the fault prediction model for fault prediction, the method further includes: Generate a fault prediction report, the fault prediction including the fault probability of the smart device failing. If the fault probability is greater than a preset fault probability, the smart device is predicted to fail. If the smart device is predicted to fail, the fault prediction report also includes the fault time and the fault type.

6. The fault prediction and processing method for intelligent devices according to claim 1, characterized in that: If the corresponding real-time working data exceeds the threshold data, the intelligent device is automatically processed based on the identified fault type and the corresponding processing rule to avoid the fault of the intelligent device, including: If the corresponding real-time working data exceeds the threshold data, a processing rule corresponding to the fault type is selected based on the identified fault type, and the processing rule includes: an execution condition of the processing operation and steps of the processing operation.

7. The fault prediction and processing method for smart devices according to claim 1, characterized in that: The processing rules are coded using a decision tree or an expert system.

8. A fault prediction and processing system for intelligent equipment, characterized in that: include: A historical work data acquisition module is used to acquire historical work data of smart devices; A first preprocessing module, used for preprocessing the historical working data; A fault model building module is used to build a fault prediction model based on preprocessed historical working data; A real-time working data acquisition module, used to acquire the real-time working data of the smart device; A second preprocessing module, used for preprocessing the real-time working data, and inputting the preprocessed real-time working data into the fault prediction model for fault prediction; An identification and judgment module, used to identify the fault type when the fault prediction model predicts that the intelligent device has a fault, and to judge whether the corresponding real-time working data exceeds the threshold data based on the fault type; The automatic processing module is used to automatically process the intelligent device based on the identified fault type and the corresponding processing rules when the corresponding real-time working data exceeds the threshold data, so as to avoid the failure of the intelligent device.

9. A computer 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 the fault prediction processing method for an intelligent device according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the fault prediction processing method for an intelligent device according to any one of claims 1 to 7 are implemented.

Images