Real-time fault early warning method of special line asset equipment and related device

Abstract

The embodiment of the invention provides a real-time fault early warning method of special line asset equipment and a related device, which are applied to a real-time fault early warning system, and the method comprises the steps: obtaining first operation environment data, an operation image set and first equipment operation data when target special line asset equipment operates in a machine room; performing environment feature extraction on the operation images in the operation image set to obtain second operation environment data; performing environment data matrix construction according to the first operation environment data and the second operation environment data to obtain a first operation environment data matrix; constructing a second operation data matrix according to the first equipment operation data; splicing the first operation environment data matrix and the second operation data matrix to obtain a target operation data matrix; performing early warning analysis on the target special line asset equipment according to the target operation data matrix to obtain an early warning analysis result; and early warning prompt is performed according to the early warning analysis result, so that the accuracy of performing real-time fault early warning on the special line asset equipment is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a real-time fault warning method and related device for dedicated line asset equipment. Background Art

[0002] With the rapid development of information technology, dedicated line rooms play a vital role in various enterprises and units. The switches, routing equipment, etc. in the dedicated line room (such as dedicated line asset equipment) are key infrastructure to ensure the stable operation of dedicated line network lines. However, at present, the status monitoring and early warning of dedicated line asset equipment are mostly carried out through manual detection and manual early warning, which cannot provide real-time and timely feedback on the failure of dedicated line asset equipment. In addition, the operating status of the dedicated line asset equipment itself is also monitored and warned. Although automation has been achieved to a certain extent, due to its single monitoring indicator, it only focuses on the basic operating parameters of the equipment and cannot deeply analyze the performance of the equipment, potential fault hazards, and the impact of complex operating environments on the equipment. Therefore, the current fault warning method may make the fault warning process for dedicated line asset equipment less accurate. Summary of the invention

[0003] The embodiments of the present application provide a real-time fault warning method and related devices for dedicated line asset equipment, which can improve the accuracy of real-time fault warning for dedicated line asset equipment.

[0004] A first aspect of an embodiment of the present application provides a real-time fault warning method for a dedicated line asset device, the method comprising:

[0005] Acquire first operating environment data of the target dedicated line asset device when it is running in the computer room through the Internet of Things detection sensor, collect an operating image set of the target dedicated line asset device through the Internet of Things detection camera, and acquire first device operating data of the target dedicated line asset device;

[0006] Extracting environmental features from the operation images in the operation image set to obtain second operation environment data;

[0007] Constructing an environment data matrix according to the first operating environment data and the second operating environment data to obtain a first operating environment data matrix;

[0008] constructing a second operation data matrix according to the first device operation data;

[0009] Performing splicing processing on the first operating environment data matrix and the second operating data matrix to obtain a target operating data matrix;

[0010] Perform early warning analysis on the target dedicated line asset equipment according to the target operation data matrix to obtain early warning analysis results;

[0011] Issue early warning prompts based on the early warning analysis results.

[0012] In this example, the first operating environment data of the target dedicated line asset equipment when it is running in the computer room is obtained through the Internet of Things detection sensor, the operating image set of the target dedicated line asset equipment is collected through the Internet of Things detection camera, and the first device operating data of the target dedicated line asset equipment is obtained, so as to extract environmental features of the operating images in the operating image set to obtain the second operating environment data, and construct an environmental data matrix based on the first operating environment data and the second operating environment data to obtain the first operating environment data matrix, so as to further construct the second operating data matrix based on the first device operating data, thereby splicing the first operating environment data matrix and the second operating data matrix to obtain the target operating data matrix, and then perform early warning analysis on the target dedicated line asset equipment based on the target operating data matrix to obtain more accurate early warning analysis results, and make more accurate early warning prompts based on the early warning analysis results, thereby improving the accuracy of real-time fault early warning for dedicated line asset equipment.

[0013] A second aspect of an embodiment of the present application provides a real-time fault warning device for a dedicated line asset device, the device comprising:

[0014] A data acquisition unit is used to acquire first operating environment data of a target dedicated line asset device when it is running in a computer room through an Internet of Things detection sensor, collect an operating image set of the target dedicated line asset device through an Internet of Things detection camera, and acquire first device operating data of the target dedicated line asset device;

[0015] A feature extraction unit, used to extract environmental features from the operation images in the operation image set to obtain second operation environment data;

[0016] A first construction unit is used to construct an environment data matrix according to the first operating environment data and the second operating environment data to obtain a first operating environment data matrix;

[0017] A second construction unit, configured to construct a second operation data matrix according to the first device operation data;

[0018] A splicing processing unit, used for splicing the first operating environment data matrix and the second operating data matrix to obtain a target operating data matrix;

[0019] An early warning analysis unit is used to perform early warning analysis on target dedicated line asset equipment according to the target operation data matrix to obtain early warning analysis results;

[0020] The early warning prompt unit is used to issue early warning prompts based on the early warning analysis results.

[0021] A third aspect of an embodiment of the present application provides a terminal, comprising a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions and execute the step instructions as in the first aspect of the embodiment of the present application.

[0022] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiments of the present application.

[0023] A fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] 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, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 A structural schematic diagram of a real-time fault warning system is provided for an embodiment of the present application;

[0026] Figure 2 A flowchart of a real-time fault warning method for dedicated line asset equipment is provided for an embodiment of the present application;

[0027] Figure 3 A schematic diagram of the structure of a terminal provided in an embodiment of the present application;

[0028] Figure 4 A structural schematic diagram of a real-time fault warning device for dedicated line asset equipment is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions 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 are within the scope of protection of this application.

[0030] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0031] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0032] In order to better understand the real-time fault warning method for dedicated line asset equipment provided in the embodiment of the present application, the following first briefly introduces the scenario in which the real-time fault warning method for dedicated line asset equipment is applied. In a dedicated network line specially set up for a company, one or more dedicated line asset equipment is usually included, such as relay equipment, servers, switches, routers, etc. in the dedicated network line. Since the dedicated line asset equipment is related to the smoothness of the entire dedicated network line, it is necessary to accurately and in real time monitor and warn the status of the dedicated line asset equipment. The real-time fault warning method for dedicated line asset equipment provided in the present application can obtain the first operating environment data of the target dedicated line asset equipment when it is running in the computer room through the Internet of Things detection sensor, collect the operating image set of the target dedicated line asset equipment through the Internet of Things detection camera, and obtain the first device operating data of the target dedicated line asset equipment, so as to extract the environmental features of the operating images in the operating image set to obtain the second operating environment data, and construct an environmental data matrix based on the first operating environment data and the second operating environment data to obtain the first operating environment data matrix, so as to further construct the second operating data matrix based on the first device operating data, thereby splicing the first operating environment data matrix and the second operating data matrix to obtain the target operating data matrix, and then perform early warning analysis on the target dedicated line asset equipment according to the target operating data matrix to obtain more accurate early warning analysis results, and make more accurate early warning prompts based on the early warning analysis results, thereby improving the accuracy of real-time fault warning for dedicated line asset equipment.

[0033] The real-time fault warning method of dedicated line asset equipment is applied to the real-time fault warning system. Figure 1 Figure 2 shows a schematic diagram of the structure of a real-time fault warning system. Figure 1As shown, the real-time fault warning system includes: an Internet of Things detection sensor, an Internet of Things detection camera, and an Internet of Things master node, etc. It should be noted that the Internet of Things detection sensor, the Internet of Things detection camera, and the Internet of Things group node are networked to form an Internet of Things network. Among them, the Internet of Things detection sensor can be a device for collecting environmental or equipment-related data, which can perceive various parameters and changes in the physical world, such as temperature, humidity, pressure, vibration, etc. The Internet of Things detection sensor can transmit the collected data to the real-time fault warning system in real time through high-precision measurement and sensitive response; the Internet of Things detection camera can be a device for collecting environmental or equipment-related image data, which can provide clear real-time images and can also have intelligent analysis functions. For example, the Internet of Things detection camera can perform real-time detection of the appearance and operating status of the equipment, and through image recognition technology, determine whether there is abnormal wear, deformation, leakage, etc.; the Internet of Things master node can be used to receive data from the Internet of Things detection sensor and the Internet of Things detection camera, and summarize, process and analyze it. The Internet of Things master node can have strong data processing and communication capabilities, can quickly determine whether the data is abnormal, and issue an alarm in time when a fault sign is found. This application does not limit this.

[0034] See also Figure 2 , Figure 2 The present application provides a flowchart of a real-time fault warning method for dedicated line asset equipment. Figure 2 As shown, the method is applied to a real-time fault warning system, and the method includes:

[0035] S201: Acquire first operating environment data of a target dedicated line asset device when it is operating in a computer room through an Internet of Things detection sensor, collect an operating image set of the target dedicated line asset device through an Internet of Things detection camera, and acquire first device operating data of the target dedicated line asset device.

[0036] The target dedicated line asset device can be used to indicate the dedicated line asset device that needs to be detected by real-time fault warning. The first operating environment data can be used to indicate the operating environment data corresponding to the target dedicated line asset device detected by the Internet of Things detection sensor when it is running in the computer room. The operating environment data may include but is not limited to temperature, humidity, light intensity, wind speed, dust concentration, etc., and this application does not limit this.

[0037] The operation image set may include one or more operation images, which can be used to indicate the image data corresponding to the target dedicated line asset equipment when it is running in the computer room, which is collected by the Internet of Things detection camera. The first device operation data can be used to indicate the device operation data related to the target dedicated line asset equipment during operation. The device operation data may include but is not limited to device performance parameters, device status parameters, device energy consumption, working hours, number of uses, traffic data, fault and alarm information, etc., and this application does not limit this.

[0038] The real-time fault warning system can obtain the first device operation data corresponding to the target dedicated line asset equipment through the built-in monitoring system of the target dedicated line asset equipment, or the data acquisition card installed on the target dedicated line asset equipment, etc. This application does not impose any restrictions on this.

[0039] S202: Extract environmental features from the operation images in the operation image set to obtain second operation environment data.

[0040] The second operating environment data can be used to indicate the operating environment data obtained by extracting environmental features from each operating image in the operating image set. In other words, the second operating environment data is the operating environment data obtained by analyzing the image collected by the IoT detection camera, and is operating environment data from a different source than the first operating environment data directly obtained by the IoT detection sensor, and this application does not impose any restrictions on this.

[0041] It should be noted that the operating environment data obtained after analyzing the images collected by the Internet of Things detection camera may include but is not limited to equipment line data, line surface aging information, line surface damage information, air vent opening information, etc., and this application does not impose any restrictions on this.

[0042] S203: Construct an environment data matrix according to the first operating environment data and the second operating environment data to obtain a first operating environment data matrix.

[0043] The first operating environment data matrix can be used to indicate the operating environment data matrix obtained after the environment data matrix is ​​constructed by the first operating environment data and the second operating environment data. Optionally, the real-time fault warning system can first pre-process the first operating environment data and the second operating environment data, and then determine the dimension and structure of the matrix to be constructed, and then fill the processed data into the matrix according to a predetermined rule to construct the first operating environment data matrix, which is not limited in this application.

[0044] S204: Construct a second operation data matrix according to the first device operation data.

[0045] The second operation data matrix can be used to indicate the operation data matrix obtained after the operation data matrix is ​​constructed according to the operation data of the first device. Optionally, the real-time fault warning system can first organize and analyze the operation data of the first device to determine the structure and characteristics of the data; secondly, according to the characteristics of the data and the analysis requirements, the dimension and structure of the matrix to be constructed are determined, and then the analyzed and organized data are filled into the matrix according to the determined rules to construct the second operation data matrix, which is not limited in this application.

[0046] S205: Concatenate the first operating environment data matrix and the second operating data matrix to obtain a target operating data matrix.

[0047] The target operation data matrix can be used to indicate the operation data matrix obtained after the first operation environment data matrix and the second operation data matrix are spliced. The real-time fault warning system can use a more direct splicing function, such as the cat function, or use a fully connected layer or residual module in a deep learning model to achieve the splicing of the first operation environment data matrix and the second operation data matrix, and this application does not limit this.

[0048] Optionally, when constructing the first operating environment data matrix and the second operating data matrix, the real-time fault warning system can adjust the dimensions of the two matrices so that when the first operating environment data matrix and the second operating data matrix are spliced, the dimensions of the two matrices in the splicing direction can be matched, so that the splicing processing can be better performed to obtain a more comprehensive and integrated target operating data matrix containing different sources, which is conducive to obtaining more accurate warning analysis results based on the target operating data matrix in subsequent steps. The present application does not impose any restrictions on this.

[0049] S206: Perform early warning analysis on the target dedicated line asset equipment according to the target operation data matrix to obtain early warning analysis results.

[0050] The early warning analysis results can be used to indicate the early warning analysis results corresponding to the target dedicated line asset equipment after the early warning analysis is performed according to the target operation data matrix. Optionally, the real-time fault early warning system can comprehensively consider the relationship between multiple data indicators, use data analysis algorithms and models, and generate early warning analysis results based on the analysis results to clearly indicate whether there are abnormal conditions, possible fault types, and recommended countermeasures, thereby achieving the purpose of predicting whether the target dedicated line asset equipment may fail in the future and issuing early warnings.

[0051] S207: Providing early warning prompts based on the early warning analysis results.

[0052] The real-time fault warning system can provide different warning prompts based on the different warning analysis results. For example, for some key equipment, the real-time fault warning system can automatically take control actions such as emergency shutdown and switching to the backup system based on the warning results to prevent the fault from expanding. For some ordinary equipment, the real-time fault warning system can use sound and light alarms, display screen prompts, SMS notifications, email notifications, mobile application push, etc. to provide warning prompts to the corresponding management personnel as soon as possible, and this application does not limit this.

[0053] In this example, the first operating environment data of the target dedicated line asset equipment when it is running in the computer room is obtained through the Internet of Things detection sensor, the operating image set of the target dedicated line asset equipment is collected through the Internet of Things detection camera, and the first device operating data of the target dedicated line asset equipment is obtained, so as to extract environmental features of the operating images in the operating image set to obtain the second operating environment data, and construct an environmental data matrix based on the first operating environment data and the second operating environment data to obtain the first operating environment data matrix, so as to further construct the second operating data matrix based on the first device operating data, thereby splicing the first operating environment data matrix and the second operating data matrix to obtain the target operating data matrix, and then perform early warning analysis on the target dedicated line asset equipment based on the target operating data matrix to obtain more accurate early warning analysis results, and make more accurate early warning prompts based on the early warning analysis results, thereby improving the accuracy of real-time fault early warning for dedicated line asset equipment.

[0054] In a possible implementation, the real-time fault warning system constructs an environment data matrix according to the first operating environment data and the second operating environment data to obtain the first operating environment data matrix, which may include the following steps:

[0055] A1. Construct a first operation data vector according to the first operation environment data;

[0056] A2. Construct a second operation data vector according to the second operation environment data;

[0057] A3, concatenating the first operation data vector and the second operation data vector to obtain a reference operation environment data matrix;

[0058] A4. Perform fusion processing on the associated data in the reference operating environment data matrix to obtain a first operating environment data matrix.

[0059] Among them, the first operation data vector can be used to indicate the operation data vector constructed according to the first operation environment data. Optionally, taking the first operation environment data including temperature and dust concentration as an example, the real-time fault warning system can construct the first operation data vector according to the temperature and dust concentration collected at different sampling times; for example, a11 is the temperature value at the first sampling time, a12 is the temperature value at the second sampling time, b11 is the dust concentration at the first sampling time, and b12 is the dust concentration at the second sampling time, then the first operation data vector can be (a11, a12, b11, b12), and this application does not limit this.

[0060] Optionally, the above example takes the first operation data vector as the temperature value vector and the dust concentration vector spliced ​​together, which is not a limitation to the present application. It is understandable that the first operation data vector can also be obtained by splicing the temperature value vector and the dust concentration vector together, which is not limited to the present application.

[0061] It should be noted that the sampling moment may include multiple sampling moments, and the relevant data corresponding to the first sampling moment can be understood as historical sampling data, such as historical temperature values ​​and historical dust concentration values; the last sampling moment can be the current moment, and this application does not impose any restrictions on this.

[0062] The second operation data vector can be used to indicate the operation data vector constructed according to the second operation environment data. Optionally, taking the second operation environment data including line surface aging information and air vent opening information as an example, the real-time fault warning system can construct the second operation data vector according to the line surface aging information and air vent opening information collected at different sampling times; for example, c11 is the line surface aging information at the first sampling time, c12 is the line surface aging information at the second sampling time, d11 is the air vent opening information at the first sampling time, and d12 is the air vent opening information at the second sampling time, then the first operation data vector can be (c11, c12, d11, d12), and this application does not limit this.

[0063] The reference operating environment data matrix can be used to indicate the operating environment data matrix obtained after the first operating data vector and the second operating data vector are spliced. It is understandable that the real-time fault warning system can select a suitable splicing method according to the needs, such as a front-to-back splicing method or an upper-lower splicing method, to realize the process of splicing the first operating data vector and the second operating data vector, and this application does not limit this.

[0064] In the reference operating environment data matrix, there may be some data with correlation relationships. Therefore, the real-time fault warning system can further analyze and process the data with correlation relationships to obtain a first operating environment data matrix that can better reflect the operating environment status of the dedicated line asset equipment. For example, the temperature values ​​of different parts may affect each other, and the real-time fault warning system can further perform fusion processing to extract more valuable information; for example, different environmental data may affect each other, and the real-time fault warning system can further perform fusion processing to extract more valuable information. This application does not limit this.

[0065] Optionally, the real-time fault warning system may perform fusion processing by calculating an average value, a weighted average value, performing principal component analysis, etc. The real-time fault warning system may reduce redundant data and noise data by performing fusion processing on the associated data to obtain a first operating environment data matrix that better reflects the operating environment status of the equipment.

[0066] In this example, a first operating data vector is constructed based on the first operating environment data, and a second operating data vector is constructed based on the second operating environment data, so that the first operating data vector and the second operating data vector are further spliced ​​to obtain a reference operating environment data matrix, and the related data in the reference operating environment data matrix are fused to obtain a more comprehensive and integrated first operating environment data matrix.

[0067] In a possible implementation, the real-time fault warning system performs fusion processing on the associated data in the reference operating environment data matrix to obtain the first operating environment data matrix, which may include the following steps:

[0068] B1. Extracting related data from the reference operating environment data matrix to obtain k related data combinations;

[0069] B2. Perform association calculation on the k association data combinations to obtain association data vectors corresponding to the k association data combinations respectively;

[0070] B3, replacing the data corresponding to the associated data in the associated data combination with the k associated data vectors to obtain a reference operating environment data matrix after replacement;

[0071] B4, obtain the fusion coefficient vector;

[0072] B5. Assign coefficient weights to the replaced reference operating environment data matrix according to the fusion coefficient vector to obtain a first operating environment data matrix.

[0073] Among them, k associated data combinations can be used to indicate the mutually associated data combinations extracted from the reference operating environment data matrix. Optionally, k is a positive integer. Exemplarily, taking the temperature in the reference operating environment data matrix as being associated with the line surface aging information and the dust concentration as being associated with the air vent opening information as an example, the temperature and the line surface aging information can be one associated data combination, and the dust concentration and the air vent opening information can be one associated data combination, that is, the real-time fault warning system can extract 2 associated data combinations, and this application does not impose any limitation on this.

[0074] The associated data vector can be used to indicate the associated data vector obtained after the associated data combination is associated with the calculation. The real-time fault warning system can better reflect the relationship between the associated data in each associated data combination by performing a specific association calculation on each associated data combination. For example, the real-time fault warning system can use the relationship between temperature and line surface aging to calculate a new fused data, which can be used to characterize the association between temperature and line aging, and this application does not limit this.

[0075] The replaced reference operating environment data matrix can be used to indicate the reference operating environment data matrix obtained after replacing the data corresponding to the associated data in the associated data combination through the associated data vector. In other words, the real-time fault warning system can use the value of the calculated associated data vector to replace the value of the associated data combination in the reference operating environment data matrix, thereby obtaining a reference operating environment data matrix that has been preliminarily processed and replaced.

[0076] The fusion coefficient vector can be used to perform weighted processing on the data in the replaced reference operating environment data matrix. Optionally, the fusion coefficient vector can be a set of vectors set in advance, or a set of vectors calculated by a related algorithm (such as principal component analysis algorithm, hierarchical analysis algorithm, random forest regression algorithm, entropy weight method, etc.), and this application does not limit this.

[0077] After obtaining the fusion coefficient vector, the real-time fault warning system can multiply each fusion coefficient vector value in the fusion coefficient vector with the value of the corresponding associated data vector in the replaced reference operating environment data matrix to achieve weighted adjustment of the data in the replaced reference operating environment data matrix, thereby obtaining a first operating environment data matrix that can more accurately reflect the operating environment status of the dedicated line asset equipment, which is conducive to providing more valuable information for subsequent fault warning analysis.

[0078] In this example, by extracting associated data from the reference operating environment data matrix, k associated data combinations are obtained, and association calculations are performed on the k associated data combinations to obtain associated data vectors corresponding to the k associated data combinations, so that the k associated data vectors replace the data corresponding to the associated data in the associated data combinations to obtain the replaced reference operating environment data matrix, and obtain the fusion coefficient vector, and then assign coefficient weights to the replaced reference operating environment data matrix according to the fusion coefficient vector to obtain the first operating environment data matrix that can more accurately reflect the operating environment status of the dedicated line asset equipment, which is conducive to providing more valuable information for subsequent fault warning analysis.

[0079] In a possible implementation, the real-time fault warning system performs a warning analysis on the target dedicated line asset equipment according to the target operation data matrix to obtain a warning analysis result, which may include the following steps:

[0080] C1. Normalize the target operation data matrix to obtain a normalized target operation data matrix;

[0081] C2. Perform a warning score operation on each normalized target operation data in the normalized target operation data matrix to obtain a set of warning score values;

[0082] C3. Construct a scoring matrix according to the early warning score value set to obtain a first scoring matrix;

[0083] C4. Use the first scoring matrix to construct a risk scoring graph to obtain a first risk scoring graph;

[0084] C5. Obtain the risk score value at each sampling time from the first risk score graph to obtain a risk score value set;

[0085] C6. Determine the risk level based on the risk score value set, and determine the risk level as the warning analysis result.

[0086] The normalized target operation data matrix can be used to indicate the target operation data matrix obtained after the target operation data matrix is ​​normalized. The real-time fault warning system can normalize the data of different magnitudes into a standard range by normalizing the target operation data matrix, for example, mapping the data into the interval [0,1], so that subsequent operations can be more fair and accurate.

[0087] The early warning score value set may include one or more early warning score values, which may be used to indicate the score value obtained after performing an early warning score operation on each normalized target operation data in the normalized target operation data matrix. The real-time fault early warning system may assign score values ​​corresponding to different factors according to factors such as the degree of deviation and change trend between the normalized target operation data and the normal operation data, so as to finally obtain an early warning score value, which is not limited in this application.

[0088] The first scoring matrix can be used to indicate the scoring matrix obtained after the scoring matrix is ​​constructed according to the early warning scoring value set. It can be understood that the first scoring matrix can more systematically and comprehensively present the scoring conditions of each sampling moment and each data dimension.

[0089] The first risk score map can be used to indicate the risk score map obtained after the risk score map is constructed according to the first scoring matrix. Optionally, the real-time fault warning system can construct the risk score map at the sampling moment. When constructing the risk score map, the real-time fault warning system can obtain the risk score value corresponding to each sampling moment according to the first scoring matrix, and further perform weighted operations according to the operating conditions of the equipment at each sampling moment to comprehensively consider the impact of various factors, thereby obtaining a risk score map that can more accurately reflect the risk level at each sampling moment.

[0090] For example, if the operating power of the device is greater, the weighted value determined by the real-time fault warning system can be higher; if the operating power of the device is smaller, the weighted value determined by the real-time fault warning system can be smaller, etc., and this application does not limit this. Among them, the operating status of the device is explained by taking the operating power as an example, which does not constitute a limitation on this application. Optionally, the operating status of the device may include but is not limited to the operating power, data transmission rate, bandwidth occupancy, etc., and this application does not limit this.

[0091] The risk score value set may include one or more risk score values, which can be used to indicate the risk score value corresponding to each sampling moment in the first risk score graph. The risk level can be used to indicate the risk level determined according to the risk score value. It can be understood that the risk level can be pre-divided, such as low risk, medium risk, high risk, etc.; the real-time fault warning system can further determine the current risk level of the equipment by comparing the risk score value with the thresholds of different risk levels, so that the risk level can be used as a warning analysis result, and then the warning analysis result can be used in subsequent steps.

[0092] In this example, the target operation data matrix is ​​normalized to obtain a normalized target operation data matrix, and a warning scoring operation is performed on each normalized target operation data in the normalized target operation data matrix to obtain a warning scoring value set, so as to further construct a scoring matrix based on the warning scoring value set to obtain a first scoring matrix, and use the first scoring matrix to construct a risk scoring map to obtain a first risk scoring map, so that the risk score value at each sampling moment can be obtained from the first risk scoring map to obtain a risk scoring value set, and then a more accurate risk level can be determined based on the risk scoring value set, so as to determine the more accurate risk level as the warning analysis result.

[0093] In a possible implementation, after the real-time fault warning system issues a warning prompt according to the warning analysis result, it may further include the following steps:

[0094] D1. Accident handling information fed back by maintenance personnel after receiving early warning prompts;

[0095] D2. Calculate the accident handling completeness score based on the accident handling information and the current operation information of the target dedicated line asset equipment to obtain the accident handling completeness score value;

[0096] D3. Display the accident handling completeness score.

[0097] Among them, the accident handling information is the processing information fed back by the maintenance personnel in response to the warning prompt after receiving the warning prompt. When the real-time fault warning system issues a warning prompt, the maintenance personnel will handle the fault or abnormal situation. After the processing is completed, the maintenance personnel will feedback the relevant information of the processing process, such as the measures taken and the results of the processing, to the real-time fault warning system, so that the real-time fault warning system receives the accident handling information.

[0098] The accident handling completeness score value can be used to indicate the handling completeness score value obtained after the accident handling completeness score is calculated based on the accident handling information and the current operating information of the target dedicated line asset equipment. The scoring calculation process may consider multiple factors, such as whether the handling measures are aimed at the root cause of the warning, whether the operating parameters of the equipment are restored to the normal range after the treatment, whether the treatment is timely and effective, and whether the treatment is comprehensive, etc. This application does not limit this.

[0099] For example, assuming that for fault warning 1, the ideal handling method should include 1. replacing component A, 2. cleaning component B, 3. recalibrating parameter C; if the accident handling information fed back by the maintenance personnel only completed the replacement of component A and cleaning component B, but did not calibrate parameter C, and because of the lack of calibration parameter C, some of the equipment's operating parameters still do not meet normal standards, then the accident handling completeness score may be relatively low, and this application does not impose any restrictions on this.

[0100] The real-time fault warning system can further display the accident handling completeness score on the display interface. Optionally, the real-time fault warning system can present the accident handling completeness score in the form of numbers, charts or color markings, so that relevant managers can clearly understand the effect and quality of each accident handling. By displaying the accident handling completeness score, not only can the work of maintenance personnel be effectively supervised and evaluated, but also reference and improvement direction can be provided for subsequent fault handling.

[0101] In this example, by receiving the accident handling information fed back by the maintenance personnel after the early warning prompt, the accident handling completeness score can be calculated based on the accident handling information and the current operation information of the target dedicated line asset equipment to obtain the accident handling completeness score value, so as to display the accident handling completeness score value, and then clearly understand the effect and quality of each accident handling, so as to achieve better and more effective supervision and evaluation of the work of the maintenance personnel, which is conducive to providing reference and improvement direction for subsequent fault handling.

[0102] For the above embodiments, please refer to Figure 3 , Figure 3 A schematic diagram of the structure of a terminal provided in an embodiment of the present application, as shown in the figure, includes a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the program includes instructions for executing the following steps;

[0103] Acquire first operating environment data of the target dedicated line asset device when it is running in the computer room through the Internet of Things detection sensor, collect an operating image set of the target dedicated line asset device through the Internet of Things detection camera, and acquire first device operating data of the target dedicated line asset device;

[0104] Extracting environmental features from the operation images in the operation image set to obtain second operation environment data;

[0105] Constructing an environment data matrix according to the first operating environment data and the second operating environment data to obtain a first operating environment data matrix;

[0106] constructing a second operation data matrix according to the first device operation data;

[0107] Performing splicing processing on the first operating environment data matrix and the second operating data matrix to obtain a target operating data matrix;

[0108] Perform early warning analysis on the target dedicated line asset equipment according to the target operation data matrix to obtain early warning analysis results;

[0109] Issue early warning prompts based on the early warning analysis results.

[0110] In this example, the first operating environment data of the target dedicated line asset equipment when it is running in the computer room is obtained through the Internet of Things detection sensor, the operating image set of the target dedicated line asset equipment is collected through the Internet of Things detection camera, and the first device operating data of the target dedicated line asset equipment is obtained, so as to extract environmental features of the operating images in the operating image set to obtain the second operating environment data, and construct an environmental data matrix based on the first operating environment data and the second operating environment data to obtain the first operating environment data matrix, so as to further construct the second operating data matrix based on the first device operating data, thereby splicing the first operating environment data matrix and the second operating data matrix to obtain the target operating data matrix, and then perform early warning analysis on the target dedicated line asset equipment based on the target operating data matrix to obtain more accurate early warning analysis results, and make more accurate early warning prompts based on the early warning analysis results, thereby improving the accuracy of real-time fault early warning for dedicated line asset equipment.

[0111] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that in order to realize the above functions, the terminal includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0112] The embodiment of the present application can divide the terminal into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0113] In line with the above, see Figure 4 , Figure 4 The present application provides a schematic diagram of a real-time fault warning device for dedicated line asset equipment. Figure 4 As shown, the device comprises:

[0114] The data acquisition unit 101 is used to acquire first operating environment data of the target dedicated line asset device when it is running in the computer room through the Internet of Things detection sensor, collect an operating image set of the target dedicated line asset device through the Internet of Things detection camera, and acquire first device operating data of the target dedicated line asset device;

[0115] The feature extraction unit 102 is used to extract environmental features from the operation images in the operation image set to obtain second operation environment data;

[0116] A first construction unit 103 is used to construct an environment data matrix according to the first operating environment data and the second operating environment data to obtain a first operating environment data matrix;

[0117] A second construction unit 104 is used to construct a second operation data matrix according to the first device operation data;

[0118] A splicing processing unit 105 is used to splice the first operating environment data matrix and the second operating data matrix to obtain a target operating data matrix;

[0119] The early warning analysis unit 106 is used to perform early warning analysis on the target dedicated line asset equipment according to the target operation data matrix to obtain early warning analysis results;

[0120] The early warning prompt unit 107 is used to issue early warning prompts according to the early warning analysis results.

[0121] In a possible implementation, the first construction unit 103 is used to construct an environment data matrix according to the first operating environment data and the second operating environment data to obtain a first operating environment data matrix, specifically for:

[0122] Constructing a first operation data vector according to the first operation environment data;

[0123] Constructing a second operation data vector according to the second operation environment data;

[0124] The first operation data vector and the second operation data vector are concatenated to obtain a reference operation environment data matrix;

[0125] The associated data in the reference operating environment data matrix is ​​fused to obtain a first operating environment data matrix.

[0126] In a possible implementation, the first construction unit 103 is used to perform fusion processing on the associated data in the reference operating environment data matrix to obtain the first operating environment data matrix, specifically for:

[0127] Extracting associated data from the reference operating environment data matrix to obtain k associated data combinations;

[0128] Perform association calculation on k association data combinations to obtain association data vectors corresponding to the k association data combinations respectively;

[0129] The k associated data vectors are used to replace the data corresponding to the associated data in the associated data combination to obtain a reference operating environment data matrix after replacement;

[0130] Get the fusion coefficient vector;

[0131] The coefficient weights are assigned to the replaced reference operating environment data matrix according to the fusion coefficient vector to obtain a first operating environment data matrix.

[0132] In a possible implementation, the early warning analysis unit 106 is used to perform early warning analysis on the target dedicated line asset equipment according to the target operation data matrix to obtain early warning analysis results, which are specifically used to:

[0133] Normalizing the target operation data matrix to obtain a normalized target operation data matrix;

[0134] Performing a warning score operation on each normalized target operation data in the normalized target operation data matrix to obtain a warning score value set;

[0135] A scoring matrix is ​​constructed according to the early warning score value set to obtain a first scoring matrix;

[0136] The first scoring matrix is ​​used to construct a risk scoring graph to obtain a first risk scoring graph;

[0137] Obtaining the risk score value at each sampling moment from the first risk score graph to obtain a risk score value set;

[0138] The risk level is determined based on the risk score value set, and the risk level is determined as a warning analysis result.

[0139] In a possible implementation, the early warning analysis unit 106 is used, after issuing an early warning prompt according to the early warning analysis result, to further specifically:

[0140] Accident handling information fed back by maintenance personnel after receiving early warning prompts;

[0141] The accident handling completeness score is calculated based on the accident handling information and the current operation information of the target dedicated line asset equipment to obtain the accident handling completeness score value;

[0142] Displays the accident handling completeness score.

[0143] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any real-time fault warning method for dedicated line asset equipment recorded in the above method embodiments.

[0144] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program enables a computer to execute part or all of the steps of any real-time fault warning method for dedicated line asset equipment recorded in the above method embodiments.

[0145] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0146] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0147] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0148] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0149] In addition, the functional units in the various embodiments of the application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0150] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0151] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0152] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A real-time fault warning method for dedicated line asset equipment, characterized in that: Applied to a real-time fault warning system, the real-time fault warning system includes an Internet of Things detection sensor, an Internet of Things detection camera and an Internet of Things master node, the Internet of Things detection sensor, the Internet of Things detection camera and the Internet of Things group node are networked to form an Internet of Things network, and the method includes: Acquire the first operating environment data of the target dedicated line asset device when it is running in the computer room through the Internet of Things detection sensor, collect the operating image set of the target dedicated line asset device through the Internet of Things detection camera, and acquire the first device operating data of the target dedicated line asset device; Extracting environmental features from the operation images in the operation image set to obtain second operation environment data; Constructing an environment data matrix according to the first operating environment data and the second operating environment data to obtain a first operating environment data matrix; Constructing a second operation data matrix according to the first device operation data; Performing splicing processing on the first operating environment data matrix and the second operating data matrix to obtain a target operating data matrix; Performing early warning analysis on the target dedicated line asset equipment according to the target operation data matrix to obtain early warning analysis results; An early warning prompt is issued according to the early warning analysis result.

2. The real-time fault warning method for dedicated line asset equipment according to claim 1 is characterized in that: The step of constructing an environment data matrix according to the first operating environment data and the second operating environment data to obtain a first operating environment data matrix includes: Constructing a first operating data vector according to the first operating environment data; Constructing a second operation data vector according to the second operation environment data; The first operation data vector and the second operation data vector are concatenated to obtain a reference operation environment data matrix; The associated data in the reference operating environment data matrix is ​​fused to obtain the first operating environment data matrix.

3. The real-time fault warning method for dedicated line asset equipment according to claim 2, characterized in that: The fusing the associated data in the reference operating environment data matrix to obtain the first operating environment data matrix includes: Extracting associated data from the reference operating environment data matrix to obtain k associated data combinations; Performing association calculation on the k association data combinations to obtain association data vectors respectively corresponding to the k association data combinations; The k associated data vectors are used to replace the data corresponding to the associated data in the associated data combination to obtain a reference operating environment data matrix after replacement; Get the fusion coefficient vector; The coefficient weights are assigned to the replaced reference operating environment data matrix according to the fusion coefficient vector to obtain the first operating environment data matrix.

4. The real-time fault warning method for dedicated line asset equipment according to any one of claims 1 to 3, characterized in that: The step of performing early warning analysis on the target dedicated line asset equipment according to the target operation data matrix to obtain early warning analysis results includes: Normalizing the target operation data matrix to obtain a normalized target operation data matrix; Performing a warning scoring operation on each normalized target operation data in the normalized target operation data matrix to obtain a warning scoring value set; Constructing a scoring matrix according to the early warning scoring value set to obtain a first scoring matrix; Using the first scoring matrix to construct a risk scoring map to obtain a first risk scoring map; Acquire the risk score value at each sampling moment from the first risk score graph to obtain a risk score value set; A risk level is determined according to the risk score value set, and the risk level is determined as a warning analysis result.

5. The real-time fault warning method for dedicated line asset equipment according to claim 4 is characterized in that: After issuing an early warning prompt according to the early warning analysis result, the method further includes: Accident handling information fed back by maintenance personnel after receiving early warning prompts; Calculate the accident handling completeness score based on the accident handling information and the current operation information of the target dedicated line asset equipment to obtain an accident handling completeness score value; The accident handling completeness score is displayed.

6. A real-time fault warning device for dedicated line asset equipment, characterized in that: The device comprises: A data acquisition unit is used to acquire first operating environment data of a target dedicated line asset device when it is running in a computer room through an Internet of Things detection sensor, collect an operating image set of the target dedicated line asset device through an Internet of Things detection camera, and acquire first device operating data of the target dedicated line asset device; A feature extraction unit, configured to extract environmental features from the operation images in the operation image set to obtain second operation environment data; A first construction unit, configured to construct an environment data matrix according to the first operating environment data and the second operating environment data to obtain a first operating environment data matrix; A second construction unit, configured to construct a second operation data matrix according to the operation data of the first device; A splicing processing unit, used for splicing the first operating environment data matrix and the second operating data matrix to obtain a target operating data matrix; An early warning analysis unit, used to perform early warning analysis on the target dedicated line asset equipment according to the target operation data matrix to obtain an early warning analysis result; The early warning prompt unit is used to make early warning prompts according to the early warning analysis results.

7. The real-time fault warning device for dedicated line asset equipment according to claim 6, characterized in that: The first construction unit is used to construct an environment data matrix according to the first operating environment data and the second operating environment data to obtain a first operating environment data matrix, specifically for: Constructing a first operating data vector according to the first operating environment data; Constructing a second operation data vector according to the second operation environment data; The first operation data vector and the second operation data vector are concatenated to obtain a reference operation environment data matrix; The associated data in the reference operating environment data matrix is ​​fused to obtain the first operating environment data matrix.

8. The real-time fault warning device for dedicated line asset equipment according to claim 7, characterized in that: The first construction unit is used to perform fusion processing on the associated data in the reference operating environment data matrix to obtain the first operating environment data matrix, specifically for: Extracting associated data from the reference operating environment data matrix to obtain k associated data combinations; Performing association calculation on the k association data combinations to obtain association data vectors respectively corresponding to the k association data combinations; The k associated data vectors are used to replace the data corresponding to the associated data in the associated data combination to obtain a reference operating environment data matrix after replacement; Get the fusion coefficient vector; The coefficient weights are assigned to the replaced reference operating environment data matrix according to the fusion coefficient vector to obtain the first operating environment data matrix.

9. A terminal, characterized in that: The method comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute a method according to any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 5.

Images