Gateway fault detection method, apparatus, and device, storage medium, and product

Abstract

The present application relates to the technical field of communications, and discloses a gateway fault detection method, apparatus, and device, a storage medium, and a computer program product. The method comprises: acquiring historical data of a gateway, and identifying an abnormal value in the historical data by means of a Gaussian mixture model; acquiring real-time data of the gateway, and identifying an abnormal pattern in the real-time data by means of a sliding window algorithm; and generating a fault detection result of the gateway on the basis of the abnormal value and the abnormal pattern. In the present application, a Gaussian mixture model is used for identifying an abnormal value in historical data, thereby improving the accuracy of gateway fault detection. In addition, in the present application, a sliding window algorithm is used for identifying an abnormal pattern in real-time data, thereby improving real-time performance of gateway fault detection.

Description

Gateway fault detection method, device, equipment, storage medium and product

[0001] Cross-reference to Related Applications

[0002] The present application is based on the Chinese patent application No.CN202411255381.8, filed on September 9, 2024, and claims the priority of the Chinese patent application No.CN202411255381.8, the whole content of which is incorporated herein by reference. TECHNICAL FIELD

[0003] The present application relates to the field of communication technology, in particular to a gateway fault detection method, device, equipment, storage medium and computer program product. BACKGROUND

[0004] In today's industrial era, Industrial Internet of Things (IIoT) is becoming an integral part of manufacturing and other industrial fields, which connects various machines and devices through the Internet, realizes real-time collection, exchange and analysis of data, and improves production efficiency, reduces cost and improves product quality. However, with the continuous expansion of industrial internet, how to effectively process and utilize massive device data, especially in the case of device failure, quickly and accurately diagnose and handle, has become an important challenge.

[0005] Fault detection is a key task in industrial internet of things gateway, which needs to accurately identify and respond to abnormal situations in devices or networks. Data often encounters missing or damaged problems in the process of collection and transmission, which is a major challenge for data-based decision-making process. With the continuous expansion of industrial internet of things system, data security problem becomes particularly important.

[0006] Traditional fault detection methods mainly rely on rule-based logic or simple statistical analysis. These methods may be sufficient for simple systems, but in complex industrial environments, due to large amount of data, complex environment and rapid change, these methods often fail to meet the requirements of real-time and accuracy. SUMMARY

[0007] The main purpose of the present application is to provide a gateway fault detection method, device, equipment, storage medium and computer program product, which aims to solve the technical problem that related gateway fault detection methods are difficult to meet the requirements of real-time and accuracy in complex industrial environments.

[0008] To achieve the above purpose, the present application provides a gateway fault detection method, which comprises:

[0009] acquire historical data of the gateway, identify abnormal values in the historical data through a Gaussian mixture model;

[0010] acquire real-time data of the gateway, identify abnormal patterns in the real-time data through a sliding window algorithm;

[0011] generate a fault detection result of the gateway according to the abnormal values and the abnormal patterns.

[0012] In addition, to achieve the above-mentioned purpose, the present application also provides a gateway fault detection device, which comprises:

[0013] an abnormal value identification module, configured to acquire historical data of the gateway, and identify abnormal values in the historical data through a Gaussian mixture model;

[0014] an abnormal pattern identification module, configured to acquire real-time data of the gateway, and identify abnormal patterns in the real-time data through a sliding window algorithm;

[0015] a detection result generation module, configured to generate a fault detection result of the gateway according to the abnormal values and the abnormal patterns.

[0016] In addition, to achieve the above-mentioned purpose, the present application also provides a gateway fault detection device, which comprises a memory, a processor, and a gateway fault detection program stored in the memory and executable on the processor, and the gateway fault detection program is configured to implement the gateway fault detection method as described above.

[0017] In addition, to achieve the above-mentioned purpose, the present application also provides a storage medium, which stores a gateway fault detection program, and the gateway fault detection program is executed by a processor to implement the gateway fault detection method as described above.

[0018] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which comprises a gateway fault detection program, and the gateway fault detection program is executed by a processor to implement the gateway fault detection method as described above. BRIEF DESCRIPTION OF DRAWINGS

[0019] The drawings incorporated into the specification and forming a part thereof, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application.

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the embodiments or the related art description will be briefly introduced. Obviously, those skilled in the art can obtain other drawings according to these drawings without any creative effort.

[0021] Fig. 1 is a flowchart of a first embodiment of the gateway fault detection method of the present application;

[0022] Fig. 2 is a flowchart of a second embodiment of the gateway fault detection method of the present application;

[0023] Fig. 3 is a flowchart of a third embodiment of the gateway fault detection method of the present application;

[0024] Fig. 4 is a flowchart of a fourth embodiment of the gateway fault detection method of the present application;

[0025] Fig. 5 is a block diagram of the gateway fault detection device of the present application;

[0026] Fig. 6 is a device structure diagram of the hardware operating environment involved in the gateway fault detection method of the present application.

[0027] The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings. DETAILED DESCRIPTION

[0028] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and do not limit the present application.

[0029] In order to better understand the technical solutions of the present application, the following will be described in detail in conjunction with the drawings and specific embodiments.

[0030] In today's industrial era, Industrial Internet of Things (IIoT) is becoming an indispensable part of manufacturing and other industrial fields, which connects various machines and devices through the Internet, realizes real-time collection, exchange and analysis of data, and improves production efficiency, reduces cost and improves product quality. However, with the continuous expansion of Industrial Internet of Things, how to effectively process and utilize massive device data, especially in the case of device failure, quickly and accurately diagnose and handle, has become an important challenge.

[0031] Fault detection is a key task in Industrial Internet of Things gateway, which needs to accurately identify and respond to abnormal situations in devices or networks. Data often encounters missing or damaged problems in the process of collection and transmission, which is a major challenge to data-based decision-making process. With the continuous expansion of Industrial Internet of Things system, data security problem becomes particularly important.

[0032] Traditional fault detection methods mainly rely on rule-based logic or simple statistical analysis. These methods may be effective in dealing with simple systems, but in complex industrial environments, due to large amounts of data, complex environment and rapid changes, these methods often fail to meet the requirements of real-time and accuracy.

[0033] Related industrial gateway fault detection methods use rule-based logic or simple statistical analysis, and only analyze historical fault data. Such methods may be effective when the system is simple, but when the data volume explodes, the environment is complex, the gateway data changes rapidly, and the data is missing, it will interfere with the analysis results. Therefore, these traditional methods often fail to meet the requirements of real-time and accuracy.

[0034] As related technology discloses an industrial Internet of Things gateway intelligent fault learning and processing method and system. The method counts the causes and solutions of historical faults and the execution times of the solutions. When the gateway fails, the cause of the failure is determined and the solution is found and executed according to the cause of the failure.

[0035] Related technology simply determines the fault type according to the process running before the device fails, and the solution is selected according to the execution times of the solutions. The logic is simple and depends on the completeness of historical data. At the same time, this method is only for the case after the gateway completely fails, and the real-time and timeliness of the industrial control system fault discovery cannot meet the requirements. At the same time, each solution is executed in turn to solve the problem, and the accuracy level of fault diagnosis cannot be guaranteed.

[0036] Therefore, in order to solve the above technical problems, the present application provides a solution, which comprises: acquiring historical data of the gateway, identifying abnormal values in the historical data through a Gaussian mixture model, acquiring real-time data of the gateway, identifying abnormal patterns in the real-time data through a sliding window algorithm, and generating a fault detection result of the gateway according to the abnormal values and the abnormal patterns. Since the Gaussian mixture model is used to identify abnormal values in the historical data, the accuracy of gateway fault detection is improved, and since the sliding window algorithm is used to identify abnormal patterns in the real-time data, the real-time performance of gateway fault detection is improved.

[0037] It should be noted that the execution subject of the present embodiment can be a gateway fault detection device with data processing, network communication and program running functions, such as a gateway control device, or other electronic devices capable of achieving the same or similar functions, which are not limited in the present embodiment.

[0038] Based on this, the embodiment of the present application provides a gateway fault detection method. Referring to FIG. 1, FIG. 1 is a flowchart of the first embodiment of the gateway fault detection method of the present application.

[0039] In this embodiment, the gateway fault detection method comprises:

[0040] Operation S10: Obtain historical data of the gateway, and identify abnormal values in the historical data by using a Gaussian mixture model.

[0041] It should be noted that the historical data includes but is not limited to historical running status, performance logs, error logs, hardware status, network status, etc. The frequency of gateway fault occurrence and the cause of the fault occurrence can be known according to the historical data of the gateway. The method for adaptively adjusting the data acquisition frequency and quality based on the historical network status and gateway performance can optimize the accuracy and efficiency of fault prediction.

[0042] When the gateway runs stably, the acquisition frequency is reduced to reduce the network burden; when potential problems are detected, the acquisition frequency is increased to monitor the gateway status in detail, and the acquisition strategy is dynamically adjusted according to the historical data and gateway performance indicators (such as CPU usage, memory occupation, network delay, etc.).

[0043] It can be understood that in this embodiment, the threshold can be determined by using the Gaussian mixture model to identify the abnormal points in the historical data. The Gaussian mixture model is a probability model, which assumes that all data points are generated by a mixture of a limited number of Gaussian distributions. Each Gaussian distribution represents a "group" or "component" in the data, and each component has its own mean and covariance. By learning these Gaussian components of the data, the Gaussian mixture model can be effectively used for clustering and anomaly point detection.

[0044] For ease of understanding, the following examples are given, but do not limit the present application. In an embodiment, for example, the data points can be divided into two clusters according to the CPU and memory usage. The two clusters may represent different operating states, one cluster may correspond to the gateway under normal workload, and the other cluster may correspond to high load or potential fault state. By further analyzing the characteristics of the two clusters, such as the center of the cluster or the distance between the data point and the center, an example threshold is defined, for example, if the probability of a data point is lower than a certain threshold, i.e. it is not likely to belong to the two known normal operation clusters, it can be marked as abnormal. Such abnormal points may indicate that the gateway is experiencing atypical load, or a fault may occur.

[0045] Further, in order to maintain the continuity and integrity of the historical data and improve the detection accuracy, the operation S10 comprises: obtaining the historical data of the gateway, detecting whether there is a missing value in the historical data; filling the missing value to obtain the filled historical data, and identifying abnormal values in the filled historical data by using a Gaussian mixture model.

[0046] It should be understood that in the present embodiment, the missing values in the historical data are filled in by an interpolation technique, which is used to fill in the missing values in the data for subsequent analysis and prediction. The missing values refer to the case of missing or lost data during monitoring due to various reasons. The interpolation technique estimates the missing values by using the pattern and trend of the existing data, thereby maintaining the continuity and integrity of the data.

[0047] In some embodiments, linear interpolation can be used to maintain the continuity and integrity of the data by assuming that the change between data is linear. For missing values, linear interpolation estimates the missing values according to the linear relationship between the known adjacent data points;

[0048] For ease of understanding, the following is illustrated by way of example, but does not limit the present application. In an embodiment, for example, CPU usage and memory usage are obtained. At some time points, due to monitoring device failure or communication problems, there may be some missing values in the data set, and interpolation techniques can be used to fill in these missing values for subsequent failure prediction and analysis. Linear interpolation can be used to fill in the missing values of CPU usage and memory usage. Assuming that the data set is as shown in Table 1:

[0049] Table 1

[0050] For the missing CPU usage and memory usage, linear interpolation can be used with the known adjacent data points. For example, the CPU usage on January 2, 2024 can be estimated by using linear interpolation of the CPU usage on January 1, 2024 and January 3, 2024. Similarly, the memory usage on January 4, 2024 can be estimated by using linear interpolation of the memory usage at adjacent time points. After completing the interpolation, the data set will become as shown in Table 2:

[0051] Table 2

[0052] In this way, the missing values are successfully filled in, and the continuity and integrity of the data are maintained for subsequent failure prediction and analysis.

[0053] Operation S20: Obtain real-time data of the gateway, and identify abnormal patterns in the real-time data by a sliding window algorithm.

[0054] It can be understood that the sliding window algorithm is a technique in time series data analysis, which is particularly suitable for real-time monitoring and analysis, such as monitoring of IIoT gateways. This algorithm identifies abnormal patterns by continuously calculating statistical properties of data within a fixed-size window that slides over the data stream. Using the sliding window algorithm to identify abnormal patterns in data, abnormal patterns can indicate impending failures.

[0055] It should be understood that in order to maintain the continuity and integrity of real-time data and improve identification accuracy, missing values in real-time data can also be filled in by interpolation techniques in this embodiment. The specific operation is the same as the filling operation of missing values in historical data, which will not be repeated here.

[0056] Operation S30: generating a failure detection result of the gateway according to the abnormal value and the abnormal pattern.

[0057] It can be understood that generating a failure detection result of the gateway according to the abnormal value and the abnormal pattern can be first marking the abnormal value and sending the first mark to the user terminal, and second marking the abnormal pattern and sending the second mark to the user terminal.

[0058] In this embodiment, after determining the abnormal value, the abnormal value is first marked and the first mark is sent to the user terminal. The user terminal can know the abnormal value, so as to determine the corresponding problem according to the abnormal value;

[0059] For example, abnormal CPU usage may indicate that the gateway is at risk of overload or resource exhaustion. For example, CPU usage consistently above a threshold may indicate that the gateway is facing performance issues; abnormal memory usage may indicate that the gateway has memory leaks or resource management problems; abnormal network traffic patterns, such as sudden increases or decreases in traffic, may indicate network problems or attacks; abnormal error log quantities may indicate that the gateway is encountering more abnormal situations, which may be an early indicator of failure; abnormal connection quantities may indicate that the gateway is facing resource exhaustion or network congestion problems.

[0060] In this embodiment, after determining the abnormal pattern, the abnormal pattern is second marked and the second mark is sent to the user terminal. The user terminal can know the abnormal pattern, so as to determine the corresponding problem according to the abnormal pattern.

[0061] This embodiment uses Gaussian mixture model to identify abnormal values in historical data, thereby improving the accuracy of gateway failure detection. And because this embodiment uses sliding window algorithm to identify abnormal patterns in real-time data, thereby improving the real-time performance of gateway failure detection.

[0062] Referring to Figure 2, which is a flowchart of the second embodiment of the gateway fault detection method of this application, a second embodiment of the gateway fault detection method of this application is proposed based on the first embodiment shown in Figure 1 above.

[0063] In the second embodiment, prior to operation S10, the following steps are also included:

[0064] Operation S01: Construct a Gaussian mixture model and set a probability density threshold based on the training dataset and the Gaussian mixture model.

[0065] It should be understood that a Gaussian mixture model is constructed by a weighted sum of multiple Gaussian distributions, and the mathematical formula can be expressed as:

[0066] In the formula, p(x) is the probability density function of data point x, k is the number of components in the model, and π K It is the mixing coefficient of the k-th component, satisfying π k ≥0 indicates the weight of each Gaussian distribution in the mixture, N(x|μ k ∑k) is μ k Let μ be the mean, Σk be a multidimensional Gaussian distribution of the covariance matrix, and μ be the mean. k ∑k is the mean vector of the k-th Gaussian distribution, and ∑k is the covariance matrix of the k-th Gaussian distribution.

[0067] For ease of understanding, the following examples are provided, but are not intended to limit the scope of this application. In one embodiment, it is assumed that K=2, meaning that two Gaussian distributions are used to model the normal operating state of the gateway.

[0068] Understandably, in this embodiment, historical monitoring data (CPU and memory usage) of the gateway is used as the training dataset to train the Gaussian Mixture Model (GMM) in order to set the probability density threshold.

[0069] Furthermore, in order to improve the accuracy of the probability density threshold, in this embodiment, the probability density threshold is set according to the probability density distribution of the training data in the training dataset, so that the probability density of most training data is higher than the probability density threshold. The operation S01 includes: inputting the training data in the training dataset into a Gaussian mixture model to calculate the probability density of the training data; statistically analyzing the probability density distribution of the training dataset based on the probability density of the training data; and setting the probability density threshold based on the probability density distribution.

[0070] It should be understood that the outlier identification is based on the probability density p(x) of the data point, if p(x) is lower than a predetermined threshold, which means that this data point is less likely to be generated by any of the Gaussian distributions of the current model, and thus can be considered as an outlier. The threshold can be determined based on the probability density distribution of the training data set, for example, a probability density threshold is selected such that the probability density of 99% of the training data points is higher than it.

[0071] Correspondingly, the operation S10 comprises:

[0072] Operation S101: Obtain historical data of the gateway, and calculate the probability density of the historical data based on the Gaussian mixture model.

[0073] Operation S102: Compare the probability density with the probability density threshold, and identify outliers in the historical data according to the comparison result.

[0074] For the sake of understanding, the following is illustrated by way of example, but does not limit the present application. In an embodiment, for each monitoring data point x, p(x) is calculated, and if p(x) < threshold, x is marked as an outlier.

[0075] Suppose in the gateway monitoring data, a data point x = [85%, 95%] is observed, representing the CPU and memory usage at a certain time point.

[0076] Calculate the probability density: For x, calculate its probability density p(x) generated by the trained GMM.

[0077] Outlier detection: If p(x) is lower than the threshold set based on the normal behavior data distribution, x is considered to represent an abnormal state, which may indicate that the gateway is encountering performance problems or other types of failures;

[0078] A Gaussian mixture model (GMM) is used to cluster a set of example data representing the CPU usage and memory usage of a gateway. Two Gaussian distributions are selected, which means that the model will try to cluster the data into two different components. The GMM successfully separates the data points into two clusters based on CPU and memory usage. The two clusters may represent different operating states, for example, one cluster may correspond to a gateway under normal workload, while the other cluster may correspond to a high load or potential failure state.

[0079] The embodiment pre-constructs a Gaussian mixture model, sets a probability density threshold based on a training data set and the Gaussian mixture model, calculates the probability density of the historical data based on the Gaussian mixture model, and determines outliers in the historical data by comparing the probability density with the probability density threshold, thereby improving the accuracy of outlier identification.

[0080] Referring to FIG. 3, FIG. 3 is a flowchart of a third embodiment of the gateway fault detection method of the present application. Based on the above embodiments, the third embodiment of the gateway fault detection method of the present application is proposed.

[0081] In the third embodiment, the operation S20 comprises:

[0082] Operation S201: Obtain real-time data of the gateway.

[0083] It should be understood that in this embodiment, the real-time data of the gateway is obtained, which can monitor the data flow in real time, process the real-time data through the stream processing framework, use the sliding window algorithm to count the data characteristics to determine whether it exceeds the threshold, so as to identify the abnormal patterns in the data.

[0084] Operation S202: Process the real-time data through the stream processing framework.

[0085] In this embodiment, the real-time data of the gateway is obtained, and a stream processing framework is constructed. The stream processing framework is a technology for processing continuous stream data. It allows real-time processing and analysis of monitoring data from the gateway, and immediately identifies potential faults or abnormal situations.

[0086] The stream processing framework needs to be able to access stream data from different data sources. These data sources can be sensor data from the gateway, log data, event data, etc. The data source access module is responsible for converting the data in these data sources into stream data for subsequent processing; the stream data processing module will process and analyze the data in real time. This may involve various operations such as data cleaning, feature extraction, anomaly detection, and model training, etc. The stream processing framework needs to be able to output the processing results to the appropriate destination. This may be storing the results to a database, sending to a message queue, real-time visualization, etc. The result output module is responsible for passing the processing results to the downstream system or user.

[0087] For example, real-time data such as CPU usage and memory usage is obtained from the gateway sensor, a series of data processing operations can be defined, such as filtering out outliers, calculating rolling averages, applying machine learning models for anomaly detection, etc. The history of each gateway's abnormal situation, the cumulative number of anomalies, etc. In the stream processing framework, a state backend can be used to manage these state information, and the processing results are output to the appropriate destination, such as writing abnormal situations to a database, sending alarm messages to the operation and maintenance team, real-time visualization of abnormal situations, etc.

[0088] Apache Flink can be used to monitor the CPU usage of the gateway in real time. If the CPU usage exceeds a certain threshold for a sustained period of time, it can be flagged as an anomaly and timely measures can be taken to address the issue to avoid the failure of the gateway. Apache Flink is a stream processing engine and distributed data processing framework that supports event-driven, real-time data stream processing and batch processing jobs, which can be used to build real-time data processing applications, including real-time analytics, data pipelines, and event-driven applications.

[0089] Operation S203: Identify abnormal patterns in the processed real-time data through a sliding window algorithm.

[0090] It can be understood that in this embodiment, the real-time data is identified through a predetermined algorithm, which can use a sliding window algorithm to identify real-time data, such as monitoring of industrial Internet of Things gateways. This algorithm slides a fixed-size window over the data stream, continuously calculating the statistical properties of the data within the window, thereby identifying abnormal patterns;

[0091] The size of the window is defined according to the type of anomaly to be detected and the characteristics of the data. The window size determines the sensitivity of the algorithm to changes in time series data; the window slides from the beginning of the time series data backwards, each move can be one time unit or multiple time units, depending on the application requirements of some embodiments; for the data within the window, calculate its statistical properties, such as mean, standard deviation, maximum, minimum, etc., to help identify abnormal patterns in the data, set a threshold or use a machine learning model to determine whether the data in the current window is abnormal. The threshold can be fixed or dynamically adjusted, for example, based on the historical statistical properties of the data within the window; once an anomaly is detected, appropriate measures are taken, such as issuing an alert, recording a log, etc. At the same time, the results of the anomaly detection can be used to adjust the threshold or optimize the model to improve the accuracy of future detection.

[0092] For example, using a 10-minute sliding window to analyze the time series data of CPU usage, considering the CPU usage data within the previous 10 minutes at each time point, and sliding the window forward every 1 minute to start analyzing the latest 10 minutes of data. For each window, calculate the mean, standard deviation, and maximum of the CPU usage. If the average CPU usage of a certain window exceeds 90%, or the standard deviation is abnormally high, it indicates that the CPU usage has unusual fluctuations, which may be a sign of performance problems or failure. At the same time, if the maximum value reaches 100% usage and this situation occurs in multiple consecutive windows, it further confirms that the system may have a problem. Once an abnormal pattern is detected, the system automatically alerts the maintenance team and records the time point and CPU usage at which the anomaly occurred for further analysis and processing.

[0093] The embodiment can monitor the data flow in real time by acquiring real-time data of the gateway, process the real-time data through a stream processing framework, and determine whether the threshold is exceeded by using a sliding window algorithm to count data characteristics, so as to accurately identify abnormal patterns in real-time data.

[0094] Referring to FIG. 4, FIG. 4 is a flowchart of a fourth embodiment of the gateway fault detection method of the present application. Based on the above embodiments, the fourth embodiment of the gateway fault detection method of the present application is proposed.

[0095] In the fourth embodiment, the operation S30 further includes:

[0096] Operation S210: Acquire the key corresponding to the industrial equipment hung under the gateway, and / or send an authorization request to the management terminal corresponding to the industrial equipment, and receive the authorization code fed back by the management terminal according to the authorization request.

[0097] Operation S220: Acquire the business data corresponding to the industrial equipment according to the key and / or the authorization code.

[0098] Correspondingly, the operation S30 includes:

[0099] Operation S30': Generate the fault detection result of the gateway according to the abnormal value, the abnormal pattern and the business data.

[0100] It should be understood that, in order to identify whether the data anomaly is caused by the gateway fault or the industrial equipment hung under the gateway, the business data of the industrial equipment hung under the gateway is also needed to generate the fault detection result in the embodiment. In order to improve the data security, the business data corresponding to the industrial equipment is acquired based on the key and / or the authorization code corresponding to the industrial equipment in the embodiment.

[0101] For the sake of understanding, the following examples are given, but the present application is not limited thereto. In an embodiment, the real-time data is encrypted, and the data access control mechanism based on the blockchain can ensure that only authorized users can access sensitive data, thereby further ensuring the security and privacy of the data. The corresponding key is generated after the real-time data is encrypted, and the encrypted real-time data is unlocked through the key, which can prevent the data from being stolen or tampered with during transmission.

[0102] For example, a highly secure encryption communication method can be used. Through a quantum key distribution protocol, the gateway and the data processing center can securely establish an encrypted channel, protect the security of the data during transmission, authenticate the data transmission, and ensure that only authorized devices or users can send data to the gateway, which can be achieved by using authentication mechanisms such as key-based authentication or digital certificates.

[0103] In this embodiment, the authorization code is sent to the user terminal, and the user needs to input the authorization code when accessing the gateway. After inputting the correct authorization code, the user can access the gateway and download or browse the encrypted data. The access control list is stored on the blockchain, recording which users have access to which data. Only users listed in the access control list can access sensitive data. The authorization code and the corresponding user are matched to ensure that the gateway data cannot be accessed without the authorization code.

[0104] For example, an industrial gateway is responsible for monitoring the status of equipment in a factory and collecting related data. Factory managers, engineers, and data analysts need to access this data for monitoring and analysis. Using a blockchain-based data access control mechanism, the factory can establish an access control list on the blockchain, recording the permissions of each user. Only users who have been authenticated and authorized can query data on the smart contract, while others cannot access it. At the same time, the security of the data is enhanced because advanced encryption techniques such as homomorphic encryption or quantum encryption are used during transmission and processing.

[0105] In this embodiment, the accessed data is backed up, and the stored data is backed up regularly to ensure the security of the backup data. In the event of data loss or damage, the data can be recovered in time to ensure the availability of the gateway.

[0106] This embodiment uses a Gaussian mixture model to continuously learn the threshold of the fault state, and takes into account the complexity of the industrial site, where data is prone to missing values. Therefore, interpolation techniques are used to fill in missing values to continuously improve the accuracy of threshold calculation and improve detection accuracy.

[0107] This embodiment addresses the problem of large amounts of industrial data and high real-time state monitoring of the gateway. The sliding window algorithm is used to dynamically adjust the window size based on actual conditions such as machine resource conditions, accuracy requirements, and real-time requirements, and machine learning methods are used to further determine whether there are anomalies in the data within the window.

[0108] This embodiment addresses the requirement for industrial data privacy. The blockchain-related technology is used to encrypt the data and strictly control the data-related permissions, while considering data risks and performing regular backups.

[0109] It should be noted that the above examples are only for understanding the present application and do not constitute a limitation on the gateway fault detection method of the present application, and more forms of simple transformation based on this technical concept are within the protection scope of the present application.

[0110] The present application also provides a gateway fault detection device, please refer to Figure 5, the gateway fault detection device comprises:

[0111] An outlier identification module 10 is configured to acquire historical data of a gateway and identify outliers in the historical data by using a Gaussian mixture model.

[0112] An anomaly pattern identification module 20 is configured to acquire real-time data of the gateway and identify anomaly patterns in the real-time data by using a sliding window algorithm.

[0113] A detection result generation module 30 is configured to generate a gateway fault detection result according to the outliers and the anomaly patterns.

[0114] The gateway fault detection device provided by the present application adopts the gateway fault detection method in the above embodiments, and can solve the technical problem that related gateway fault detection methods are difficult to meet the requirements of real-time and accuracy in complex industrial environments. Compared with related technologies, the gateway fault detection device provided by the present application has the same beneficial effects as the gateway fault detection method provided by the above embodiments, and other technical features in the gateway fault detection device are the same as the features disclosed in the above embodiments, which will not be repeated here.

[0115] The present application provides a gateway fault detection device, which comprises at least one processor and a memory connected with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the gateway fault detection method in the above embodiment one.

[0116] Reference is now made to FIG. 6, which shows a structural diagram of a gateway failure detection apparatus suitable for implementing embodiments of the present application. The gateway failure detection apparatus in embodiments of the present application can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDA (Personal Digital Assistant), PAD (Portable Application Description), PMP (Portable Media Player), car terminals (e.g., car navigation terminals), and the like, as well as fixed terminals such as digital TVs, desktop computers, and the like. The gateway failure detection apparatus shown in FIG. 6 is merely an example and should not impose any limitation on the functions and use range of embodiments of the present application.

[0117] As shown in FIG. 6, the gateway failure detection apparatus can include a processing device 1001 (e.g., a central processor, a graphic processor, etc.) that can perform various appropriate actions and processes according to programs stored in a ROM (Read Only Memory) 1002 or loaded from a storage device 1003 into a RAM (Random Access Memory) 1004. Various programs and data required for the operation of the gateway failure detection apparatus are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An I / O (Input / Output) interface 1006 is also connected to the bus. In general, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, and the like; output devices 1008 including, for example, an LCD (Liquid Crystal Display), a speaker, a vibrator, and the like; the storage device 1003 including, for example, a magnetic tape, a hard disk, and the like; and a communication device 1009. The communication device 1009 can allow the gateway failure detection apparatus to communicate wirelessly or wiredly with other devices to exchange data. Although the gateway failure detection apparatus having various systems is shown in the figure, it should be understood that all of the shown systems are not required to be implemented or provided. More or less systems can be alternatively implemented or provided.

[0118] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program codes for executing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network through a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiments disclosed in the present application are executed.

[0119] The gateway fault detection device provided by the present application adopts the gateway fault detection method in the above-mentioned embodiments, and can solve the technical problem that the related gateway fault detection methods are difficult to meet the requirements of real-time and accuracy in complex industrial environments. Compared with the related art, the beneficial effects of the gateway fault detection device provided by the present application are the same as those of the gateway fault detection method provided by the above-mentioned embodiments, and other technical features in the gateway fault detection device are the same as those disclosed in the previous embodiment method, which will not be repeated here.

[0120] It should be understood that parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0121] The above is only some embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0122] The present application provides a storage medium having computer readable program instructions (i.e. computer program) stored thereon, the computer readable program instructions being used to execute the gateway fault detection method in the above-mentioned embodiments.

[0123] The storage medium provided in the application may be, for example, a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination of the above. Other embodiments of the storage medium may include, but are not limited to, an electric connection with one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present embodiment, the storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the storage medium can be transmitted by any suitable medium, including but not limited to an electric wire, an optical cable, an RF (Radio Frequency), and the like, or any suitable combination of the above.

[0124] The storage medium described above may be included in the gateway fault detection device, or may exist separately and not be assembled into the gateway fault detection device.

[0125] The storage medium described above carries one or more programs, which, when executed by the gateway fault detection device, cause the gateway fault detection device to: acquire historical data of the gateway, identify abnormal values in the historical data by using a Gaussian mixture model, acquire real-time data of the gateway, identify abnormal patterns in the real-time data by using a sliding window algorithm, and generate a fault detection result of the gateway according to the abnormal values and the abnormal patterns.

[0126] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0127] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0128] The modules involved in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the module itself.

[0129] The storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e., computer programs) for executing the gateway fault detection method described above, and can solve the technical problem that the related gateway fault detection method is difficult to meet the requirements of real-time and accuracy in a complex industrial environment. Compared with the related art, the computer readable storage medium provided by the present application has the same beneficial effects as the gateway fault detection method provided by the above embodiments, and will not be described here.

[0130] The application also provides a computer program product comprising a computer program which, when executed by a processor, implements the gateway fault detection method as described above.

[0131] The computer program product provided by the application can solve the technical problem that the related gateway fault detection method is difficult to meet the requirements of real-time and accuracy in a complex industrial environment. Compared with the related art, the beneficial effects of the computer program product provided by the application are the same as those of the gateway fault detection method provided by the above-mentioned embodiments, which will not be repeated here.

[0132] The above only describes some embodiments of the application, and does not limit the patent scope of the application. Any equivalent structural transformation made by using the content of the specification and drawings, or direct / indirect application in other related technical fields under the technical concept of the application is included in the patent protection scope of the application.

Claims

1. A gateway fault detection method, wherein, The gateway fault detection method comprises: Obtaining historical data of the gateway, identifying abnormal values in the historical data through a Gaussian mixture model; Obtaining real-time data of the gateway, identifying abnormal patterns in the real-time data through a sliding window algorithm; Generating a fault detection result of the gateway according to the abnormal values and the abnormal patterns.

2. The gateway fault detection method of claim 1, wherein, Before the step of obtaining historical data of the gateway, identifying abnormal values in the historical data through a Gaussian mixture model, the method further comprises: Constructing a Gaussian mixture model, setting a probability density threshold according to a training data set and the Gaussian mixture model; Correspondingly, the step of obtaining historical data of the gateway, identifying abnormal values in the historical data through a Gaussian mixture model comprises: Obtaining historical data of the gateway, calculating the probability density of the historical data based on the Gaussian mixture model; Comparing the probability density with the probability density threshold, identifying abnormal values in the historical data according to the comparison result.

3. The gateway fault detection method of claim 2, wherein, The step of setting a threshold according to a training data set and the Gaussian mixture model comprises: Inputting training data in the training data set into the Gaussian mixture model to calculate the probability density of the training data; Statistically analyzing the probability density distribution of the training data set according to the probability density of the training data, setting a probability density threshold according to the probability density distribution.

4. The gateway fault detection method of any one of claims 1 to 3, wherein, The step of obtaining real-time data of the gateway, identifying abnormal patterns in the real-time data through a sliding window algorithm comprises: Obtaining real-time data of the gateway; Processing the real-time data through a stream processing framework; Identifying abnormal patterns in the processed real-time data through the sliding window algorithm.

5. The gateway fault detection method of claim 4, wherein, The step of identifying abnormal patterns in the processed real-time data through the sliding window algorithm comprises: Sliding a fixed-size window on the data stream of the processed real-time data, continuously calculating the statistical characteristics of the data in the window, setting a threshold or using a machine learning model to determine whether the data in the current window is abnormal; Wherein, the size of the window is defined according to the type of abnormality to be detected and the characteristics of the data, the size of the window determines the sensitivity of the sliding window algorithm to the change of time series data, and the threshold is fixed or dynamically adjusted.

6. The gateway fault detection method of claim 1, wherein, The step of obtaining real-time data of the gateway, identifying abnormal patterns in the real-time data through a sliding window algorithm further comprises: Using interpolation techniques to estimate missing values using existing data patterns and trends to fill in missing values in the real-time data.

7. The gateway fault detection method of any one of claims 1 to 3, wherein, Before the step of generating a fault detection result of the gateway according to the abnormal values and the abnormal patterns, the method further comprises: Obtaining a key corresponding to an industrial device hung under the gateway, and / or sending an authorization request to a management terminal corresponding to the industrial device, receiving an authorization code fed back by the management terminal according to the authorization request; Obtaining business data corresponding to the industrial device according to the key and / or the authorization code; Correspondingly, the step of generating a fault detection result of the gateway according to the abnormal values and the abnormal patterns comprises: Generating a fault detection result of the gateway according to the abnormal values, the abnormal patterns, and the business data.

8. The gateway fault detection method of any one of claims 1 to 3, wherein, The method comprises the following steps: The method comprises the following steps: The method comprises the following steps:

9. The gateway fault detection method of claim 8, wherein, The method comprises the following steps: The method comprises the following steps:

10. The gateway fault detection method of claim 1, wherein, The method comprises the following steps: The method comprises the following steps: The method further comprises the following steps:

11. The gateway fault detection method of claim 1, wherein, The method further comprises the following steps:

12. A gateway fault detection device, comprising: an abnormal value identification module configured to acquire historical data of a gateway and identify abnormal values in the historical data by using a Gaussian mixture model; an abnormal pattern identification module configured to acquire real-time data of the gateway and identify abnormal patterns in the real-time data by using a sliding window algorithm; a detection result generation module configured to generate a fault detection result of the gateway according to the abnormal values and the abnormal patterns. The gateway fault detection device comprises a memory, a processor, and a gateway fault detection program stored in the memory and executable on the processor, and when the gateway fault detection program is executed by the processor, the following functions are realized:

13. A gateway failure detection device, wherein, acquiring historical data of a gateway and identifying abnormal values in the historical data by using a Gaussian mixture model; acquiring real-time data of the gateway and identifying abnormal patterns in the real-time data by using a sliding window algorithm; generating a fault detection result of the gateway according to the abnormal values and the abnormal patterns. Before the step of acquiring historical data of a gateway and identifying abnormal values in the historical data by using a Gaussian mixture model, when the gateway fault detection program is executed by the processor, the following functions are realized:

14. The gateway failure detection device of claim 13, wherein, constructing a Gaussian mixture model, setting a probability density threshold value according to a training data set and the Gaussian mixture model; Accordingly, the step of acquiring historical data of a gateway and identifying abnormal values in the historical data by using a Gaussian mixture model comprises the following steps: acquiring historical data of a gateway, calculating a probability density of the historical data based on the Gaussian mixture model; comparing the probability density with the probability density threshold value, and identifying abnormal values in the historical data according to the comparison result. The step of setting a threshold value according to a training data set and the Gaussian mixture model comprises the following steps:

15. The gateway failure detection device of claim 13, wherein, inputting training data in the training data set into the Gaussian mixture model to calculate a probability density of the training data; statistically analyzing a probability density distribution of the training data set according to the probability density of the training data, and setting a probability density threshold value according to the probability density distribution. ​ 16. The gateway failure detection device of any of claims 13 to 15, wherein, The acquiring real-time data of the gateway, and identifying an abnormal pattern in the real-time data by a sliding window algorithm, comprises: acquiring real-time data of the gateway; processing the real-time data by a stream processing framework; identifying an abnormal pattern in the processed real-time data by a sliding window algorithm.

17. The gateway failure detection device of any of claims 13 to 15, wherein, Before the generating a fault detection result of the gateway according to the abnormal value and the abnormal pattern, the gateway fault detection program, when executed by the processor, further implements: acquiring a key corresponding to an industrial device hung under the gateway, and / or sending an authorization request to a management terminal corresponding to the industrial device, and receiving an authorization code fed back by the management terminal according to the authorization request; acquiring service data corresponding to the industrial device according to the key and / or the authorization code; Accordingly, the generating a fault detection result of the gateway according to the abnormal value and the abnormal pattern comprises: generating a fault detection result of the gateway according to the abnormal value, the abnormal pattern and the service data.

18. The gateway failure detection device of any of claims 13 to 15, wherein, The acquiring historical data of the gateway, and identifying an abnormal value in the historical data by a Gaussian mixture model, comprises: acquiring historical data of the gateway, and detecting whether there is a missing value in the historical data; filling the missing value to obtain filled historical data, and identifying an abnormal value in the filled historical data by a Gaussian mixture model.

19. A storage medium, wherein, The storage medium has a gateway fault detection program stored thereon, and the gateway fault detection program, when executed by the processor, implements the gateway fault detection method according to any one of claims 1 to 11.

20. A computer program product, comprising a gateway fault detection program, and the gateway fault detection program, when executed by the processor, implements the gateway fault detection method according to any one of claims 1 to 11.

Images