Method and device for determining fault probability of equipment, storage medium and electronic device

Abstract

The invention discloses a method and device for determining the fault probability of equipment, a storage medium and an electronic device, and the method comprises the steps: transmitting sensor data monitored by a monitoring node of the Internet of Things to an edge node of the Internet of Things, and determining a first fault prediction probability corresponding to the sensor data through the edge node, the monitoring node is used for monitoring target equipment of the Internet of Things; after the sensor data is stored in a data warehouse of a cloud platform, analyzing the stored data of the data warehouse by using a fusion analysis model to obtain a second fault prediction probability corresponding to the sensor data; and determining the fault probability of the target equipment according to a weighting result of the first fault prediction probability and the second fault prediction probability. By adopting the technical scheme, the technical problem that the fault condition of the equipment cannot be accurately judged is solved.

Description

Technical Field

[0001] The present application relates to the field of Internet of Things equipment maintenance, and specifically, to a method and device for determining the failure probability of a device, a storage medium, and an electronic device. Background Art

[0002] With the continuous development of intelligent manufacturing technology for industrial equipment, the number of industrial equipment is increasing, which also brings greater pressure to the fault diagnosis and maintenance of equipment. At present, it is usually necessary to rely on manual regular fault detection and equipment maintenance of equipment, but this method has some obvious limitations and defects. Due to the surge in the number of equipment, the labor cost required for maintenance has increased, and the traditional method of regular detection in the time dimension cannot judge the status of the equipment in real time, resulting in a waste of maintenance resources. In addition, equipment maintenance that is performed only after the equipment fails belongs to responsive maintenance, which lacks real-time monitoring and predictive analysis, and will seriously affect the maintenance efficiency of the equipment. Although there are currently methods for diagnosing equipment failures using equipment data, these methods do not conduct in-depth analysis of equipment data and cannot accurately determine the fault condition of the equipment. Therefore, in the related technology, there is a technical problem that the fault condition of the equipment cannot be accurately determined.

[0003] With regard to the technical problem in the related technology that the fault condition of the equipment cannot be accurately determined, no effective solution has been proposed so far.

[0004] Therefore, it is necessary to improve the related technology to overcome the above-mentioned defects in the related technology. Summary of the invention

[0005] The embodiments of the present application provide a method and apparatus for determining the failure probability of a device, a storage medium, and an electronic device, so as to at least solve the technical problem that the failure condition of the device cannot be accurately determined.

[0006] According to one aspect of an embodiment of the present application, a method for determining the failure probability of a device is provided, comprising: sending sensor data monitored by a monitoring node of an Internet of Things to an edge node of the Internet of Things, and determining a first failure prediction probability corresponding to the sensor data through the edge node, wherein the monitoring node is used to monitor a target device of the Internet of Things; after storing the sensor data in a data warehouse of a cloud platform, using a fusion analysis model to analyze the stored data in the data warehouse to obtain a second failure prediction probability corresponding to the sensor data; and determining the failure probability of the target device according to a weighted result of the first failure prediction probability and the second failure prediction probability.

[0007] In an exemplary embodiment, sensor data monitored by a monitoring node of an Internet of Things is sent to an edge node of the Internet of Things, and a first fault prediction probability corresponding to the sensor data is determined by the edge node, wherein the monitoring node is used to monitor a target device of the Internet of Things; after the sensor data is stored in a data warehouse of a cloud platform, a fusion analysis model is used to analyze the stored data in the data warehouse to obtain a second fault prediction probability corresponding to the sensor data; and the failure probability of the target device is determined based on a weighted result of the first fault prediction probability and the second fault prediction probability.

[0008] In an exemplary embodiment, determining a first fault prediction probability corresponding to the sensor data by the edge node includes: determining the first fault prediction probability corresponding to the sensor data by the edge node using a fault prediction model, including: integrating and processing the sensor data in the edge node to obtain initial data; preprocessing the initial data to obtain intermediate data; classifying the intermediate data according to equipment health indicators to obtain multiple groups of data, each group of data corresponding to an equipment health indicator; determining a data weight corresponding to each group of data according to a weight set for the equipment health indicator; determining each group of target data according to each group of data and the data weight corresponding to each group of data to obtain multiple groups of target data; inputting the multiple groups of target data into the fault prediction model to obtain the first fault prediction probability.

[0009] In an exemplary embodiment, the fusion analysis model includes at least a time series analysis sub-model and a neural network analysis sub-model, and the fusion analysis model is used to analyze the stored data in the data warehouse to obtain a second fault prediction probability corresponding to the sensor data, including: sending the stored data to the time series analysis sub-model and the neural network analysis sub-model respectively, obtaining a third fault prediction probability output by the time series analysis sub-model, and obtaining a fourth fault prediction probability output by the neural network analysis sub-model; and determining the second fault prediction probability according to a weighted result of the third fault prediction probability and the fourth fault prediction probability.

[0010] In an exemplary embodiment, the method also includes: storing the sensor data in a data warehouse of a cloud platform in the following manner: encrypting the sensor data using a key of an encryption algorithm to obtain an encryption result, and sending the encryption result to the cloud platform via a secure communication protocol; obtaining decrypted data obtained by the cloud platform using the key to decrypt the encryption result, and storing the decrypted data in the data warehouse, wherein the key has been pre-synchronized to the cloud platform.

[0011] In an exemplary embodiment, after determining the failure probability of the target device based on the weighted result of the first failure prediction probability and the second failure prediction probability, the method further includes: when it is determined that the failure probability is greater than a preset probability, determining that a fault exists in the target device, and generating prompt information for indicating that a fault exists in the target device; based on the prompt information, calling an equipment maintenance scheduling algorithm to generate a maintenance task for the target device; and sending the maintenance task to a target object to instruct the target object to perform the maintenance task.

[0012] In an exemplary embodiment, after determining the failure probability of the target device based on the weighted result of the first fault prediction probability and the second fault prediction probability, the method further includes: sending the sensor data to a back-end server; displaying the sensor data in a first display manner on a visualization interface connected to the back-end server, and displaying the target device and the failure probability in a second display manner on the visualization interface, wherein the network structure of the Internet of Things is already displayed on the visualization interface.

[0013] According to another aspect of an embodiment of the present application, a device for determining the failure probability of a device is also provided, including: a sending module, used to send sensor data monitored by a monitoring node of an Internet of Things to an edge node of the Internet of Things, and determine a first fault prediction probability corresponding to the sensor data through the edge node, wherein the monitoring node is used to monitor a target device of the Internet of Things; an obtaining module, used to analyze the stored data in the data warehouse using a fusion analysis model after storing the sensor data in a data warehouse of a cloud platform, to obtain a second fault prediction probability corresponding to the sensor data; and a determining module, used to determine the failure probability of the target device according to a weighted result of the first fault prediction probability and the second fault prediction probability.

[0014] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the method for determining the failure probability of the above-mentioned device when running.

[0015] According to another aspect of an embodiment of the present application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes a method for determining a failure probability of the device through the computer program.

[0016] According to another aspect of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0017] Through the present application, the sensor data monitored by the monitoring node of the Internet of Things is sent to the edge node of the Internet of Things, and the first fault prediction probability corresponding to the sensor data is determined by the edge node, wherein the monitoring node is used to monitor the target device of the Internet of Things; after the sensor data is stored in the data warehouse of the cloud platform, the stored data of the data warehouse is analyzed using a fusion analysis model to obtain the second fault prediction probability corresponding to the sensor data; the failure probability of the target device is determined according to the weighted result of the first failure prediction probability and the second failure prediction probability, which can solve the technical problem of being unable to accurately determine the fault condition of the device and improve the accuracy of judging the fault condition of the device. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] Figure 1 It is a hardware structure block diagram of a mobile terminal of a method for determining a failure probability of a device according to an embodiment of the present application;

[0021] Figure 2 is a flow chart of a method for determining a failure probability of a device according to an embodiment of the present application;

[0022] Figure 3 It is a structural block diagram of a device for determining the failure probability of a device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a method for determining a failure probability of a device according to an embodiment of the present application. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor (Central Processing Unit, MCU) or a programmable logic device (Field Programmable Gate Array, FPGA)) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0026] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for determining the probability of failure of the device in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0027] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0028] In this embodiment, a method for determining the failure probability of a device is provided. Figure 2 is a flow chart of a method for determining a failure probability of a device according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps:

[0029] Step S202: sending sensor data monitored by a monitoring node of the Internet of Things to an edge node of the Internet of Things, and determining a first fault prediction probability corresponding to the sensor data through the edge node, wherein the monitoring node is used to monitor a target device of the Internet of Things;

[0030] Among them, the Internet of Things (IoT) is a network concept composed of multiple networks such as the Internet, traditional telecommunication networks, and sensor networks, which allows objects to exchange information and communicate with each other.

[0031] A sensor network is arranged in the Internet of Things. Specifically, various types of sensors can be deployed at the key device nodes of the Internet of Things, such as temperature, pressure, vibration, current and other sensors. At the same time, wireless sensor network technology can also be used to achieve self-organizing communication between sensors. By using high-precision, low-power sensors, the status of the equipment can be judged based on the key performance of the facilities monitored in real time.

[0032] Step S204: after storing the sensor data in the data warehouse of the cloud platform, using the fusion analysis model to analyze the stored data in the data warehouse to obtain a second fault prediction probability corresponding to the sensor data;

[0033] Wherein, the data warehouse at least includes the sensor data.

[0034] Step S206: determining the failure probability of the target device according to a weighted result of the first failure prediction probability and the second failure prediction probability.

[0035] Through the above steps, the sensor data monitored by the monitoring node of the Internet of Things is sent to the edge node of the Internet of Things, and the first fault prediction probability corresponding to the sensor data is determined by the edge node, wherein the monitoring node is used to monitor the target device of the Internet of Things; after the sensor data is stored in the data warehouse of the cloud platform, the storage data of the data warehouse is analyzed using a fusion analysis model to obtain the second fault prediction probability corresponding to the sensor data; the failure probability of the target device is determined according to the weighted result of the first failure prediction probability and the second failure prediction probability, which can solve the technical problem of being unable to accurately determine the fault condition of the device and improve the accuracy of judging the fault condition of the device.

[0036] In an exemplary embodiment, the technical solution for determining the first fault prediction probability corresponding to the sensor data through the edge node in step S202 specifically includes: determining the first fault prediction probability corresponding to the sensor data through the edge node using a fault prediction model, including: integrating and processing the sensor data in the edge node to obtain initial data; preprocessing the initial data to obtain intermediate data; classifying the intermediate data according to equipment health indicators to obtain multiple groups of data, each group of data corresponding to an equipment health indicator; determining the data weight corresponding to each group of data according to the weight set for the equipment health indicator; determining each group of target data according to each group of data and the data weight corresponding to each group of data to obtain multiple groups of target data; inputting the multiple groups of target data into the fault prediction model to obtain the first fault prediction probability.

[0037] In the Internet of Things of this embodiment, edge computing processing is implemented by edge nodes, and sensor data can be preliminarily processed, so that fast data processing and anomaly detection can be performed directly near the monitoring node, that is, local decision-making can be achieved near the data source, reducing data transmission delays and the computing burden of the cloud platform. Local decisions, for example, automatically adjust device parameters to respond to detected abnormal conditions.

[0038] It can be understood that the fault prediction model is obtained by training with historical sensor data as input samples and fault results corresponding to the historical sensor data as output samples.

[0039] Optionally, time series analysis, support vector machine or other statistical methods may be used as an alternative model to the above fault prediction model.

[0040] Optionally, the data collected in real time by the sensors of the edge nodes can be subjected to preliminary signal conditioning and data aggregation, and data cleaning, denoising, normalization and other operations can be performed to achieve data preprocessing. The data can be analyzed in real time and preliminary anomaly detection can be performed to quickly identify the operating status of the equipment.

[0041] The above sensors may also include different types such as optical fiber sensors, electromagnetic sensors or ultrasonic sensors to adapt to different monitoring requirements and environmental conditions.

[0042] Edge Processing is a distributed computing architecture that extends data processing capabilities from central servers or the cloud to the edge of the network, that is, closer to the data source. This architecture is particularly suitable for the Internet of Things environment. The data source can be understood as a large amount of real-time data generated by smart devices or sensors.

[0043] Optionally, different edge computing architectures such as fog computing or dew computing can be used to achieve more decentralized computing resource allocation.

[0044] It should be noted that, in this embodiment, the process of fault prediction and health index evaluation can also be implemented, which is as follows: an anomaly detection algorithm is deployed on the edge node, and a fault prediction model is obtained through training.

[0045] For the fault prediction model, for example, it can be implemented based on univariate statistical analysis, cluster analysis, model-based methods, etc., and the health status and potential failure risks of the equipment can be evaluated by identifying abnormal patterns in the data in real time.

[0046] Furthermore, the fault prediction model can be integrated into the real-time monitoring system to issue an immediate warning once a potential fault is detected so that preventive measures can be taken.

[0047] Optionally, in this embodiment, a quantitative basis is provided for maintenance decisions by setting equipment health indicators. Specifically, a series of health indicators such as temperature stability, vibration amplitude, and pressure balance are defined to evaluate the health status of the facility. By further assigning weights to each health indicator, a weighted scoring system is constructed according to its importance to the overall health of the facility. According to the score of the health index, the health status of the facility is divided into different levels, such as excellent, good, general, poor, etc. The priority of maintenance work can also be determined according to the score of the health index. For example, facilities with poor health status are set to have a high priority so that facilities with poor health status are given priority.

[0048] In an exemplary embodiment, the fusion analysis model includes at least a time series analysis sub-model and a neural network analysis sub-model. The specific implementation process of using the fusion analysis model to analyze the stored data in the data warehouse in the above step S204 to obtain the second fault prediction probability corresponding to the sensor data may include: sending the stored data to the time series analysis sub-model and the neural network analysis sub-model respectively, obtaining the third fault prediction probability output by the time series analysis sub-model, and obtaining the fourth fault prediction probability output by the neural network analysis sub-model; determining the second fault prediction probability according to the weighted result of the third fault prediction probability and the fourth fault prediction probability.

[0049] In this embodiment, the stored data is mined, managed, and deeply analyzed through big data analysis technology to identify equipment operation modes and potential problems and protect data transmitted in the IoT network. At the same time, machine learning algorithms are applied to analyze historical and real-time data to achieve intelligent identification of fault prediction and maintenance needs.

[0050] Optionally, this embodiment can extract key features such as temperature peak, vibration frequency, pressure fluctuation, etc. that can reflect the operating status of the facility from the raw data collected by the sensor, and then use a variety of mathematical analysis methods to analyze the data, specifically: use time series analysis methods, such as the AutoRegressive Integrated Moving Average (ARIMA) model, to analyze the trend of data changes over time and predict future performance degradation. Or use machine learning algorithms such as Random Forest, Gradient Boosting Machine (GBM), Neural Networks, etc. to model and predict the status of the equipment. Or use deep learning techniques such as Convolutional Neural Networks (CNN) or Recurrent Neural Networks (RNN) to process complex data patterns and improve prediction accuracy. Alternatively, the prediction results of the above multiple methods can be combined to improve the accuracy of fault prediction through an integrated learning method.

[0051] Optionally, the above mathematical analysis method may also include other methods such as fuzzy logic or expert system to improve the accuracy and adaptability of data analysis.

[0052] In an exemplary embodiment, further, the sensor data can be stored in the data warehouse of the cloud platform in the following manner: encrypt the sensor data using the key of the encryption algorithm to obtain an encryption result, and send the encryption result to the cloud platform through a secure communication protocol; obtain decrypted data obtained by the cloud platform using the key to decrypt the encryption result, and store the decrypted data in the data warehouse, wherein the key has been pre-synchronized to the cloud platform.

[0053] Through this embodiment, by establishing a data warehouse on the cloud platform, the data lifecycle management can be performed to optimize storage efficiency. And the edge processed data is synchronized to the cloud through a secure communication protocol (such as MQTT, CoAP), and data encryption and secure transmission technology are used to perform data encryption and access control to protect system data security, implement data security and privacy protection measures, and ensure the security of system operation. Improve the security of data during transmission and protect the integrity of data and the privacy of users.

[0054] The communication protocol may also include, for example, ZigBee, Bluetooth LE, NB-IoT or dedicated industrial wireless communication standards to adapt to different transmission distances and bandwidth requirements.

[0055] Optionally, distributed database or blockchain technology can be used for data storage to improve the security and immutability of the data.

[0056] In an exemplary embodiment, after determining the failure probability of the target device based on the weighted result of the first failure prediction probability and the second failure prediction probability, further, when it is determined that the failure probability is greater than a preset probability, it is determined that a fault exists in the target device, and a prompt message is generated to indicate that a fault exists in the target device; based on the prompt message, a device maintenance scheduling algorithm is called to generate a maintenance task for the target device; and the maintenance task is sent to the target object to instruct the target object to perform the maintenance task.

[0057] The equipment maintenance scheduling algorithm may include but is not limited to a genetic algorithm, a simulated annealing algorithm or an ant colony algorithm. By using the scheduling maintenance algorithm to generate maintenance tasks, the efficiency of maintenance task scheduling may be improved.

[0058] The target object may be, for example, a person, or may be an automated maintenance device, which is not limited in the present application.

[0059] This embodiment proposes an active facility maintenance system under IoT, which adopts a predictive maintenance strategy to intervene before equipment failure. It aims to automatically schedule maintenance tasks according to the predicted failure probability and dynamically adjust maintenance tasks according to real-time data analysis to optimize resource allocation and maintenance processes by integrating advanced sensor networks, real-time data monitoring, predictive analysis and automated maintenance response. It can solve the problem of low maintenance efficiency in existing facility maintenance systems and provide a more efficient, intelligent and cost-effective maintenance solution.

[0060] Optionally, in one embodiment, maintenance tasks and work orders can be automatically generated based on the fault prediction results, and a maintenance scheduling algorithm can be applied to optimize resource allocation and task execution sequence, thereby achieving automated generation and scheduling of maintenance tasks.

[0061] Furthermore, maintenance can be carried out on-site or remotely using remote control or remote communication technologies such as 5G, which reduces manual intervention and the high maintenance costs caused by unexpected failures. It improves the efficiency of maintenance work while improving real-time monitoring and predictive analysis, thereby improving the reliability and safety of facilities.

[0062] In an exemplary embodiment, after determining the failure probability of the target device based on the weighted result of the first fault prediction probability and the second fault prediction probability, further, the sensor data is sent to a back-end server; the sensor data is displayed in a first display manner on a visualization interface connected to the back-end server, and the target device and the failure probability are displayed in a second display manner on the visualization interface, wherein the network structure of the Internet of Things is already displayed on the visualization interface.

[0063] This embodiment improves the ease of operation through an intuitive user interface, allowing non-technical users to easily manage and monitor the maintenance status of facilities, thereby improving the user experience. It can provide users with real-time monitoring, alarm notifications and maintenance logs, and also implements interactive fault diagnosis assistance to help users quickly locate problems.

[0064] Furthermore, user feedback, equipment maintenance information and equipment execution data can be collected to evaluate model performance. At the same time, feedback loops can be used to continuously optimize algorithms and maintenance processes to improve system adaptability and accuracy.

[0065] In terms of data, we implement end-to-end encryption and access control mechanisms to protect data security and user privacy. We also conduct regular system security audits and vulnerability scans to ensure the security of the system, thereby protecting data integrity and user privacy.

[0066] Through the above content, active maintenance of IoT devices can be achieved, fault prediction and health index evaluation can be carried out, the occurrence of unexpected failures can be reduced, the service life of facilities can be extended, resource waste can be reduced, the impact on the environment can be reduced, and the overall maintenance efficiency can be improved. It not only improves the intelligent level of maintenance, but also achieves multiple goals of cost-effectiveness, ease of operation and environmental friendliness.

[0067] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0068] In this embodiment, a device for determining the failure probability of a device is also provided, and the device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made are not repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0069] Figure 3 : is a structural block diagram of a device for determining a failure probability of a device according to an embodiment of the present application, the device comprising:

[0070] A sending module 32, configured to send sensor data monitored by a monitoring node of the Internet of Things to an edge node of the Internet of Things, and determine a first fault prediction probability corresponding to the sensor data through the edge node, wherein the monitoring node is used to monitor a target device of the Internet of Things;

[0071] An obtaining module 34 is used to analyze the stored data in the data warehouse of the cloud platform using a fusion analysis model after storing the sensor data in the data warehouse to obtain a second fault prediction probability corresponding to the sensor data;

[0072] The determination module 36 is used to determine the failure probability of the target device according to a weighted result of the first failure prediction probability and the second failure prediction probability.

[0073] Through the above-mentioned device, the sensor data monitored by the monitoring node of the Internet of Things is sent to the edge node of the Internet of Things, and the first fault prediction probability corresponding to the sensor data is determined by the edge node, wherein the monitoring node is used to monitor the target device of the Internet of Things; after the sensor data is stored in the data warehouse of the cloud platform, the stored data of the data warehouse is analyzed using a fusion analysis model to obtain the second fault prediction probability corresponding to the sensor data; the failure probability of the target device is determined according to the weighted result of the first failure prediction probability and the second failure prediction probability, which can solve the technical problem of being unable to accurately determine the fault condition of the device and improve the accuracy of judging the fault condition of the device.

[0074] In an exemplary embodiment, the sending module is also used to: determine the first fault prediction probability corresponding to the sensor data by using the fault prediction model through the edge node, including: integrating and processing the sensor data in the edge node to obtain initial data; preprocessing the initial data to obtain intermediate data; classifying the intermediate data according to equipment health indicators to obtain multiple groups of data, each group of data corresponds to an equipment health indicator; determining the data weight corresponding to each group of data according to the weight set for the equipment health indicator; determining each group of target data according to each group of data and the data weight corresponding to each group of data to obtain multiple groups of target data; inputting the multiple groups of target data into the fault prediction model to obtain the first fault prediction probability.

[0075] In an exemplary embodiment, the fusion analysis model includes at least a time series analysis sub-model and a neural network analysis sub-model, and the above-mentioned obtaining module is also used to: send the stored data to the time series analysis sub-model and the neural network analysis sub-model respectively, obtain the third fault prediction probability output by the time series analysis sub-model, and obtain the fourth fault prediction probability output by the neural network analysis sub-model; determine the second fault prediction probability according to the weighted result of the third fault prediction probability and the fourth fault prediction probability.

[0076] In an exemplary embodiment, the above-mentioned obtaining module is also used to: store the sensor data in the data warehouse of the cloud platform in the following manner: encrypt the sensor data using the key of the encryption algorithm to obtain the encryption result, and send the encryption result to the cloud platform through a secure communication protocol; obtain the decrypted data of the encryption result decrypted by the cloud platform using the key, and store the decrypted data in the data warehouse, wherein the key has been pre-synchronized to the cloud platform.

[0077] In an exemplary embodiment, the device for determining the failure probability of the above-mentioned equipment also includes a maintenance module, which is used to determine the failure probability of the target equipment based on the weighted result of the first fault prediction probability and the second fault prediction probability, and when it is determined that the failure probability is greater than a preset probability, determine that there is a fault in the target equipment and generate prompt information indicating that there is a fault in the target equipment; based on the prompt information, call an equipment maintenance scheduling algorithm to generate a maintenance task for the target equipment; and send the maintenance task to the target object to instruct the target object to perform the maintenance task.

[0078] In an exemplary embodiment, the device for determining the failure probability of the above-mentioned equipment also includes a display module, which is used to send the sensor data to a back-end server after determining the failure probability of the target device according to a weighted result of the first fault prediction probability and the second fault prediction probability; display the sensor data in a first display manner on a visual display interface connected to the back-end server, and display the target device and the failure probability in a second display manner on the visual display interface, wherein the network structure of the Internet of Things is already displayed on the visual display interface.

[0079] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0080] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0081] S1, sending sensor data monitored by a monitoring node of the Internet of Things to an edge node of the Internet of Things, and determining a first fault prediction probability corresponding to the sensor data through the edge node, wherein the monitoring node is used to monitor a target device of the Internet of Things;

[0082] S2, after storing the sensor data in a data warehouse of the cloud platform, using a fusion analysis model to analyze the stored data in the data warehouse to obtain a second fault prediction probability corresponding to the sensor data;

[0083] S3: Determine the failure probability of the target device according to a weighted result of the first failure prediction probability and the second failure prediction probability.

[0084] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0085] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0086] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0087] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0088] S1, sending sensor data monitored by a monitoring node of the Internet of Things to an edge node of the Internet of Things, and determining a first fault prediction probability corresponding to the sensor data through the edge node, wherein the monitoring node is used to monitor a target device of the Internet of Things;

[0089] S2, after storing the sensor data in a data warehouse of the cloud platform, using a fusion analysis model to analyze the stored data in the data warehouse to obtain a second fault prediction probability corresponding to the sensor data;

[0090] S3: Determine the failure probability of the target device according to a weighted result of the first failure prediction probability and the second failure prediction probability.

[0091] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0092] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0093] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0094] An embodiment of the present application also provides a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in any one of the above method embodiments.

[0095] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0096] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0097] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining the failure probability of a device, characterized in that: include: Sending sensor data monitored by a monitoring node of the Internet of Things to an edge node of the Internet of Things, and determining a first fault prediction probability corresponding to the sensor data through the edge node, wherein the monitoring node is used to monitor a target device of the Internet of Things; After storing the sensor data in a data warehouse of a cloud platform, using a fusion analysis model to analyze the stored data in the data warehouse to obtain a second fault prediction probability corresponding to the sensor data; The failure probability of the target device is determined according to a weighted result of the first failure prediction probability and the second failure prediction probability.

2. The method according to claim 1, characterized in that: Determining, by the edge node, a first fault prediction probability corresponding to the sensor data, comprising: Determining a first fault prediction probability corresponding to the sensor data by using a fault prediction model at the edge node includes: integrating and processing the sensor data in the edge node to obtain initial data; Preprocessing the initial data to obtain intermediate data; Classifying the intermediate data according to the equipment health indicators to obtain multiple groups of data, each group of data corresponding to one equipment health indicator; Determining a data weight corresponding to each set of data according to a weight set for the device health indicator; Determine each set of target data according to each set of data and the data weight corresponding to each set of data to obtain multiple sets of target data; The multiple groups of target data are input into the fault prediction model to obtain the first fault prediction probability.

3. The method according to claim 1, characterized in that The fusion analysis model includes at least a time series analysis sub-model and a neural network analysis sub-model. The fusion analysis model is used to analyze the stored data in the data warehouse to obtain a second fault prediction probability corresponding to the sensor data, including: Sending the stored data to the time series analysis sub-model and the neural network analysis sub-model respectively, obtaining a third fault prediction probability output by the time series analysis sub-model, and obtaining a fourth fault prediction probability output by the neural network analysis sub-model; The second fault prediction probability is determined according to a weighted result of the third fault prediction probability and the fourth fault prediction probability.

4. The method according to claim 1, characterized in that: The method further comprises: The sensor data is stored in the data warehouse of the cloud platform in the following ways: Encrypt the sensor data using a key of an encryption algorithm to obtain an encryption result, and send the encryption result to the cloud platform through a secure communication protocol; The decrypted data obtained by the cloud platform using the key to decrypt the encryption result is obtained, and the decrypted data is stored in the data warehouse, wherein the key has been pre-synchronized to the cloud platform.

5. The method according to claim 1, characterized in that After determining the failure probability of the target device according to a weighted result of the first failure prediction probability and the second failure prediction probability, the method further includes: In the case where it is determined that the failure probability is greater than a preset probability, determining that a failure exists in the target device, and generating prompt information indicating that a failure exists in the target device; Calling a device maintenance scheduling algorithm based on the prompt information to generate a maintenance task for the target device; The maintenance task is sent to a target object to instruct the target object to perform the maintenance task.

6. The method according to claim 1, characterized in that After determining the failure probability of the target device according to a weighted result of the first failure prediction probability and the second failure prediction probability, the method further includes: Sending the sensor data to a backend server; The sensor data is displayed in a first display manner on a visualization interface connected to the back-end server, and the target device and the failure probability are displayed in a second display manner on the visualization interface, wherein the network structure of the Internet of Things is already displayed on the visualization interface.

7. A device for determining the failure probability of a device, characterized in that: include: A sending module, used to send sensor data monitored by a monitoring node of the Internet of Things to an edge node of the Internet of Things, and determine a first fault prediction probability corresponding to the sensor data through the edge node, wherein the monitoring node is used to monitor a target device of the Internet of Things; An obtaining module is used to analyze the stored data in the data warehouse of the cloud platform using a fusion analysis model after storing the sensor data in the data warehouse to obtain a second fault prediction probability corresponding to the sensor data; A determination module is used to determine the failure probability of the target device according to a weighted result of the first failure prediction probability and the second failure prediction probability.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 6 when executed.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 6 through the computer program.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images