Equipment fault early warning method and device, equipment and storage medium

Abstract

The invention discloses an equipment fault early warning method and device, equipment and a storage medium, relates to the technical field of equipment data processing, and discloses the following steps: obtaining operation data of target industrial equipment and associated data of each operation data; performing exception analysis according to the association degree between the operation data and the associated data to obtain exceptional data; performing graph correlation analysis on the abnormal data according to a preset fault graph to obtain a fault type correlation degree; determining an early warning level and a prediction fault type according to the fault type association degree; performing fault early warning on the target industrial equipment based on the early warning level and the predicted fault type; according to the method, various sensor data of industrial equipment are collected, abnormal data atlas analysis is carried out based on relevance of data when different faults occur in a fault atlas, a root fault reason is recognized, then the relevance degree of different fault types is quantified, the fault types are determined, and the early warning level is determined. The accuracy and efficiency of fault identification are improved, and equipment maintenance is carried out in advance based on potential fault problems.

Description

Technical Field

[0001] The present application relates to the technical field of equipment data processing, and in particular to equipment failure early warning methods, devices, equipment and storage media. Background Art

[0002] With the widespread application of IoT technology, modern industrial production is increasingly dependent on highly automated and intelligent equipment. These devices can generate a large amount of operating data, including but not limited to temperature, pressure, vibration, current and other parameters. Through IoT technology, these data can be collected in real time and transmitted to the central processing system, providing a rich data source for data analysis.

[0003] With the advancement of big data and artificial intelligence technology, enterprises are increasingly inclined to adopt data-driven methods to make decisions. Modern industrial production requires equipment to operate stably for a long time, and any unexpected downtime may lead to huge economic losses. Traditional preventive maintenance is usually based on fixed time intervals to check and maintain equipment, which is often not flexible enough and easily leads to waste of resources. In contrast, predictive maintenance focuses more on predicting potential failures by real-time monitoring of equipment status, so as to take measures before failures occur. For industrial equipment, this means that valuable information needs to be extracted from massive operating data to support maintenance decisions. However, during the equipment maintenance process in the factory, due to the large amount of equipment and data, and the complex types of failures, it is impossible to quickly and accurately identify possible equipment failures.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide an equipment fault warning method, device, equipment and storage medium, aiming to solve the technical problem that during the equipment maintenance process of the factory, due to the large amount of equipment data and the complex fault types, it is impossible to quickly and accurately identify the possible faults of the equipment.

[0006] To achieve the above purpose, the present application proposes a device failure early warning method, which includes: Acquire the operation data of the target industrial equipment and the associated data of each operation data; Performing anomaly analysis according to the correlation between the operating data and the correlation data to obtain abnormal data; Performing graph correlation analysis on the abnormal data according to a preset fault graph to obtain a fault type correlation degree; Determine the warning level and the predicted fault type according to the fault type correlation; A fault warning is performed on the target industrial equipment based on the warning level and the predicted fault type.

[0007] In one embodiment, performing graph correlation analysis on the abnormal data according to a preset fault graph to obtain a fault type correlation degree includes: identifying abnormal points among the abnormal data; Obtaining anomaly weights between various anomaly data based on the anomaly points; Determine preset fault data in a preset fault map according to the abnormal weight; The correlation degree of each fault type is determined according to the preset fault data.

[0008] In one embodiment, determining the preset fault data in the preset fault map according to the abnormal weight includes: Extracting abnormal features of the abnormal data, matching the abnormal features with preset fault data, and obtaining initial fault data; sorting the initial fault data according to the abnormal weights of the fault data to obtain reference fault data; The reference fault data whose weight is greater than a preset weight threshold in the reference fault data is used as preset fault data.

[0009] In one embodiment, determining the correlation of each fault type according to the preset fault data includes: Obtaining preset fault data associated with each fault type in the preset fault map; Obtaining the failure rate of each failure type according to the weight of the preset failure data; The correlation degree of each fault type is obtained according to the abnormal weights between the various abnormal data.

[0010] In one embodiment, obtaining the correlation degree of each fault type according to the abnormal weights between the various abnormal data includes: Get the weight threshold; Comparing the weight threshold with the abnormal weights of the various abnormal data to obtain a comparison result; Obtaining the number of connected nodes of each abnormal point according to the comparison result; The correlation degree of each fault type is obtained according to the number of connected nodes and the fault rate.

[0011] In one embodiment, after obtaining the correlation degree of each fault type according to the number of connected nodes and the fault rate, the method further includes: When the correlation degree is greater than or equal to the correlation degree threshold, the steps of determining the warning level and predicting the fault type according to the fault type correlation degree are performed; When the correlation degree is less than a correlation degree threshold, generating an abnormal signal according to the abnormal data, and performing an abnormal alarm based on the abnormal signal; Obtaining a reference abnormality type based on the abnormal alarm feedback from the user and generating an abnormality release signal; The preset fault map is updated according to the reference abnormality type and the abnormality release signal.

[0012] In one embodiment, determining the warning level and predicting the fault type according to the fault type correlation degree includes: The fault type with the largest fault type correlation is taken as the predicted fault type; Obtaining a data abnormality degree according to the abnormal data and a preset data standard value; A preset fault level table is matched with the data abnormality to obtain a warning level, wherein the preset fault level table includes one-to-one corresponding data abnormality and fault level.

[0013] In addition, to achieve the above purpose, the present application also proposes an equipment failure early warning device, the equipment failure early warning device comprising: A data acquisition module, used to acquire the operating data of the target industrial equipment and the associated data of each operating data; A fault analysis module, used for performing an abnormality analysis according to the correlation between the operation data and the correlation data to obtain abnormal data; The fault analysis module is further used to perform graph correlation analysis on the abnormal data according to a preset fault spectrum to obtain a fault type correlation degree; A fault warning module, used to determine the warning level and predict the fault type according to the fault type correlation; The fault warning module is used to provide fault warning for the target industrial equipment based on the warning level and the predicted fault type.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes an equipment failure warning device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the equipment failure warning method described above.

[0015] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the equipment failure warning method described above are implemented.

[0016] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the device failure warning method described above are implemented.

[0017] One or more technical solutions proposed in this application have at least the following technical effects: By collecting various sensor data of industrial equipment in real time and analyzing abnormal data maps based on the correlation between various data of the equipment according to the correlation between various data at different faults through fault maps, the root cause of the problem can be identified, thereby improving the accuracy and efficiency of diagnosis; and then quantifying the degree of correlation between different fault types, determining the fault type and the warning level, quickly and accurately identifying potential fault problems of equipment and taking preventive measures, and being able to send timely and effective alarms to operators to avoid serious equipment damage or production interruptions. BRIEF DESCRIPTION OF THE DRAWINGS

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

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

[0020] Figure 1 A flow chart of the first embodiment of the device failure warning method of the present application; Figure 2 A flow chart of the second embodiment of the device failure warning method of the present application; Figure 3 A schematic diagram of a preset fault spectrum provided in Embodiment 2 of the device fault warning method of this application; Figure 4 This is a schematic diagram of the module structure of the equipment failure warning device according to an embodiment of the present application; Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the device failure warning method in the embodiment of the present application. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0022] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of the embodiment of the present application is: obtaining the operating data of the target industrial equipment and the associated data of each operating data; performing anomaly analysis based on the correlation between the operating data and the associated data to obtain abnormal data; performing graph association analysis on the abnormal data based on a preset fault map to obtain the fault type correlation; determining the warning level and predicted fault type based on the fault type correlation; and performing fault warning on the target industrial equipment based on the warning level and predicted fault type.

[0024] In this embodiment, for the convenience of description, the following description is made by taking the device for identifying device failure and early warning as the execution subject.

[0025] As the existing technology is widely used in the Internet of Things, modern industrial production is increasingly dependent on highly automated and intelligent equipment. These devices can generate a large amount of operating data, including but not limited to temperature, pressure, vibration, current and other parameters. Through the Internet of Things technology, these data can be collected in real time and transmitted to the central processing system, providing a rich data source for data analysis.

[0026] With the advancement of big data and artificial intelligence technology, enterprises are increasingly inclined to adopt data-driven methods to make decisions. Modern industrial production requires equipment to operate stably for a long time, and any unexpected downtime may lead to huge economic losses. Traditional preventive maintenance is usually based on fixed time intervals to check and maintain equipment, which is often not flexible enough and easily leads to waste of resources. In contrast, predictive maintenance focuses more on predicting potential failures by real-time monitoring of equipment status, so as to take measures before failures occur. For industrial equipment, this means that valuable information needs to be extracted from massive operating data to support maintenance decisions. However, during the equipment maintenance process in the factory, due to the large amount of equipment and data, and the complex types of failures, it is impossible to quickly and accurately identify possible equipment failures.

[0027] The present application provides a solution, which collects various sensor data of industrial equipment, performs abnormal data map analysis based on the correlation of various data at different faults in the fault map, identifies the root cause of the fault, and then quantifies the degree of correlation between different fault types, determines the fault type and determines the warning level, improves the accuracy and efficiency of fault identification, and performs equipment maintenance in advance based on potential fault problems.

[0028] It can be seen from the above embodiments that the present application discloses an equipment fault warning method, device, equipment and storage medium, which relates to the field of equipment data processing technology, and discloses: obtaining the operating data of the target industrial equipment and the associated data of each operating data; performing an abnormal analysis based on the correlation between the operating data and the associated data to obtain abnormal data; performing a graph correlation analysis on the abnormal data according to a preset fault map to obtain the fault type correlation; determining the warning level and predicting the fault type according to the fault type correlation; performing fault warning on the target industrial equipment based on the warning level and the predicted fault type; by collecting various sensor data of industrial equipment, performing abnormal data map analysis based on the correlation of each data at different faults in the fault map, identifying the root cause of the fault, and then quantifying the correlation between different fault types, determining the fault type and determining the warning level, improving the accuracy and efficiency of fault identification and performing equipment maintenance in advance based on potential fault problems.

[0029] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a device failure warning device, etc. The following takes the device failure warning device as an example to illustrate this embodiment and the following embodiments.

[0030] Based on this, the present application embodiment provides a device failure warning method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the device failure warning method of the present application.

[0031] In this embodiment, the device failure early warning method includes steps S10 to S40: Step S10, acquiring the operating data of the target industrial equipment and the associated data of each operating data.

[0032] It is understandable that in order to achieve comprehensive monitoring and analysis of target industrial equipment, an effective method is needed to obtain its operating data and its related associated data. Specifically, it is to collect various data generated by the target industrial equipment during operation in real time through various sensors and monitoring equipment, such as temperature, pressure, speed, vibration, etc. These data can reflect the operating status and performance indicators of the equipment, which is of great significance for subsequent equipment maintenance and management.

[0033] It should be understood that the associated data may include the equipment's working environment, production tasks, maintenance records, etc. Through the study and analysis of these associated data, we can have a deeper understanding of the equipment's working status, discover potential problems and hidden dangers, and take measures in advance to ensure the normal operation and production efficiency of the equipment.

[0034] Step S20, performing an abnormality analysis based on the correlation between the operating data and the correlation data to obtain abnormal data.

[0035] It is understandable that operating data may be affected and changed by related data. For example, the temperature of industrial equipment will be higher when the ambient temperature is high. Short circuits and high-temperature damage to electronic components may occur more easily when the temperature is high, thus causing abnormal operating data.

[0036] It is understandable that, similarly, not all operating data will be affected by associated data. The operating data of industrial equipment is collected while also collecting associated data that has a high degree of correlation with the operating data of each industrial equipment.

[0037] It should be emphasized that there can be multiple or only one associated data of the operating data. The analysis is performed based on the correlation between the operating data and the associated data to determine whether there is abnormal data or whether the data is abnormal due to the influence of the associated data.

[0038] It should be understood that before performing the abnormality analysis, the associated data of each operating data may be determined through a test experiment, and a weight, ie, a correlation degree, may be set according to the correlation between each operating data and each associated data.

[0039] In a specific implementation, the abnormal data obtained by performing an anomaly analysis based on the correlation between the operating data and the related data can be by first comparing the real-time operating data of the industrial equipment with the normal data when the industrial equipment is running; and setting a data deviation ratio for each operating data. When the deviation between the real-time operating data and the normal data exceeds the deviation ratio, it is considered that the real-time operating data may be abnormal.

[0040] Furthermore, when it is considered that the real-time operation data may be abnormal, according to the pre-set associated data of each operation data, it is further determined whether the abnormality of the current operation data is caused by the current associated data. For example, if the operating temperature of the equipment is too high, it is related to the ambient temperature and the operating time. The correlation between the operating time and the ambient temperature is different. Then, according to the temperature deviation between the current ambient temperature and the normal temperature; according to the temperature rise correlation between the operating time and the temperature increase; and then according to the weight of the temperature deviation and the temperature rise correlation, it is calculated whether the current operation data is abnormal. If there is an abnormality, the data is regarded as abnormal data. According to the associated data, the calculation method for further determining whether the abnormality of the current operation data is caused by the current associated data can refer to the following formula:

[0041] Among them, P represents the degree of abnormality, θ represents the associated data, Indicates standard data of θ1.

[0042] Furthermore, an abnormality threshold is set based on the abnormality degree P, and when the abnormality degree is greater than or equal to the abnormality threshold, the operating data is used as an abnormality parameter.

[0043] Step S30, performing graph correlation analysis on the abnormal data according to a preset fault graph to obtain a fault type correlation degree.

[0044] It is understandable that the preset fault map can be a pre-established fault data structure diagram of various equipment fault types, such as abnormal data types a, b, and c corresponding to fault A. Among them, the data range under the structure of a specifically includes, the data range under the structure of b specifically includes, the data range under the structure of c specifically includes, and other data types can also be included under the structures of ac, thereby forming a preset fault map.

[0045] It should be understood that performing graph association analysis on the abnormal data according to a preset fault map may be to locate the abnormal data from the preset fault map, and then calculate the abnormal correlation between the abnormal data and each abnormal category according to the fault type associated with the abnormal data in the preset fault map.

[0046] It should be noted that multiple fault categories are pre-determined in the preset fault map, and the fault data generated when the fault type occurs is obtained through testing, and the various related data associated with the fault data are further associated, and the relationship between each fault data and each fault-related data is set with an associated weight or degree of association in advance based on expert opinions, and a degree of association or associated weight is also set between each fault type and fault data as a calculation parameter for whether the data will cause this type of equipment failure.

[0047] It should be emphasized that this matching degree can be quantified by various statistical methods or machine learning algorithms, such as using similarity calculations, pattern recognition techniques, or fault diagnosis models.

[0048] Step S40: determining the warning level and the predicted fault type according to the fault type correlation.

[0049] It is understandable that whether the fault occurrence threshold is exceeded is determined based on the correlation degree, and if exceeded, it is determined that a corresponding device fault may occur.

[0050] It should be understood that, when it is determined that a fault may occur, the type of the fault that may occur in the preset fault map is used as the predicted fault type.

[0051] It should be noted that a normal value can be set in advance for each abnormal data. The warning level is evaluated based on the percentage of the abnormal data exceeding the normal value or the size of the abnormal data exceeding the normal value. Different warning levels can give different warning feedback, such as voice reminders, data abnormality reporting, emergency reminders and other different types of warnings.

[0052] In a feasible implementation, step S40 may include steps A41 to A44: Step A41: taking the fault type with the greatest fault type correlation as the predicted fault type It is understandable that the higher the correlation, the higher the matching degree between the fault type and the current symptom, so that it can be determined which fault type is most likely to cause the current problem.

[0053] It should be noted that, according to the preset fault map, the correlation value between each data and each fault type can be obtained, which reflects the matching degree between the abnormal data and the possible equipment fault. The fault type with the highest correlation can be selected as the predicted fault type.

[0054] It is understandable that the predicted fault type can be the most likely cause based on the current performance of the equipment. Selecting this fault type as the basis for prediction can greatly improve the efficiency and accuracy of subsequent maintenance work, avoid unnecessary disassembly and inspection, reduce maintenance costs, and speed up the equipment's return to operation.

[0055] It should be emphasized that it is also possible to provide feedback on multiple possible predicted fault types with relatively high probability, so as to narrow the range of equipment fault types, and at the same time of early warning of equipment faults, the efficiency of equipment fault location can also be accelerated.

[0056] Step A42, obtaining the data abnormality degree according to the abnormal data and a preset data standard value.

[0057] It is understandable that the preset data standard value may be a preset value that each operating data has under normal circumstances.

[0058] It should be understood that if the operating data collected in real time is close to the preset data standard value, the data can be considered normal, and the more it deviates from the preset data standard value, the more abnormal the operating data can be considered.

[0059] It should be noted that the calculation of the preset data standard value can be the operation data of the industrial equipment collected in advance during normal operation, and multiple data of each operation data are taken to calculate the average value, and the average value is used as the preset data standard value.

[0060] It should be emphasized that the calculation of data anomaly can refer to the following formula:

[0061] Among them, w represents the data abnormality, x i Indicates abnormal data. Indicates the preset data standard value of the abnormal data.

[0062] Step A43, matching a preset fault level table with the data abnormality to obtain a warning level, wherein the preset fault level table includes one-to-one correspondence between data abnormality and fault level.

[0063] It is understood that the fault levels include normal, primary, secondary and tertiary.

[0064] Furthermore, the preset fault level table is matched with the predicted fault type to obtain the initial warning level, which can refer to the following formula:

[0065] Among them, the abnormal data is compared with the preset data standard value. If it is greater than or less than the preset data standard value by 8%, the abnormal data can be considered to be a normal deviation; if it is greater than or less than the preset data standard value by 20%, the abnormality of the abnormal data can be considered to be a first-level abnormality; if it is greater than or less than the preset data standard value by 40%, the abnormality of the abnormal data can be considered to be a second-level abnormality; if it is greater than or less than the preset data standard value by more than 60%, the abnormality of the abnormal data can be considered to be a third-level abnormality.

[0066] It is understandable that the classification of data anomaly levels and the data anomaly levels corresponding to the degree of deviation from the preset standard value can be adjusted. This embodiment does not limit this and can be adjusted according to actual conditions.

[0067] In this embodiment, by collecting the equipment's operating data, monitoring its performance indicators, and analyzing any abnormal signals or symptoms to accurately and quickly identify problems, the maintenance team will compare historical failure data with known failure modes to determine the type of abnormality of the equipment.

[0068] The above are only feasible implementations of step S40 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S40.

[0069] Step S50: performing a fault warning on the target industrial equipment based on the warning level and the predicted fault type.

[0070] It is understandable that performing fault warning according to the warning level and the predicted fault type may be determining the warning strategy according to the warning level.

[0071] It should be noted that the warning strategy does not issue a warning when the warning level is normal; when the warning level is level one, abnormal data is recorded and abnormal marks are made; when the warning level is level two, a text fault reminder is made based on the predicted fault type; when the warning level is level three, a voice alarm and text voice reminder are made and abnormal data is fed back for user viewing.

[0072] This embodiment provides an equipment fault warning method, which collects various sensor data of industrial equipment, performs abnormal data map analysis based on the correlation of various data at different faults in the fault map, identifies the root cause of the fault, and then quantifies the degree of correlation between different fault types, determines the fault type and determines the warning level, thereby improving the accuracy and efficiency of fault identification and performing equipment maintenance in advance based on potential fault problems.

[0073] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , step S30, the equipment failure early warning method further includes steps S31~S34: In this embodiment, the device failure early warning method includes steps S10 to S40: Step S31, identifying abnormal points between the abnormal data.

[0074] It is understandable that the abnormal data may be a plurality of data, and the abnormal point may be the location of the abnormal data with an abnormal degree higher than the abnormal threshold among the various abnormal data in the preset fault map.

[0075] It should be understood that identifying abnormal points facilitates locating the data that mainly generates abnormalities among a plurality of abnormal data, thereby facilitating analyzing the causes of data abnormalities based on the data that generates the main abnormalities.

[0076] It should be noted that the abnormal point can be one or more, and the position of the abnormal data with an abnormal degree higher than the abnormal threshold in the preset fault map can be regarded as an abnormal point. Among them, the abnormal threshold can be 160% of the standard data value of the abnormal data, and the abnormal data point can be regarded as an abnormal point.

[0077] Step S32, obtaining anomaly weights between various abnormal data based on the abnormal points.

[0078] It is understandable that after determining the abnormal point, the abnormal data can be located in the preset fault map, and the same abnormal data may have different weights in different fault types.

[0079] It should be understood that after the abnormal point is determined, the preset correlation between each abnormal data and the abnormal point under the graph of each abnormal type is used as the abnormal weight between the abnormal data and the abnormal point.

[0080] It should be emphasized that the abnormal weights between the abnormal point and each abnormal data under the preset graph of each possible abnormal type are analyzed respectively.

[0081] Step S33, determining preset fault data in a preset fault map according to the abnormal weight.

[0082] It should be noted that in the preset map, the correlation between various fault types and various operating data when abnormalities occur can be set. For example, the correlation between fault A and the abnormality of data a is 50%, which can be understood as the probability of fault A occurring when data a is abnormal is 50%. Furthermore, if the abnormality of data a is 50%, the correlation of the current data a with the occurrence of fault A is 25%.

[0083] It should be further explained that, if there are multiple associated data with abnormalities for fault A, the abnormal correlation degrees of the multiple associated data are added together as the weight of the occurrence of fault A.

[0084] In a feasible implementation, step S33 may include steps A331 to A333: Step A331, extracting abnormal features of the abnormal data, matching the abnormal features with preset fault data, and obtaining initial fault data.

[0085] It is understandable that the abnormal features can be numerical features and time features, and feature extraction is performed from two directions: time and numerical size.

[0086] It should be understood that the initial fault data may be analyzed according to the weights between the various abnormal data to determine which abnormal data is the most important among the various abnormal data, so that the fault type can be better located according to the analysis of the main abnormal data.

[0087] It should be noted that matching the abnormal characteristics with the preset fault data can be matching the abnormal characteristics with the numerical characteristics in each fault type. Different fault types have different standards for the same operating data. For example, the normal standard for data a in fault type A is 5, and the normal standard for data a in fault type B is 10.

[0088] It should be emphasized that matching the abnormal feature with the preset fault data may be matching the data associated with each abnormal point to obtain the initial fault data associated with the abnormal point.

[0089] Step A332: sort the initial fault data according to the abnormal weight of the fault data to obtain reference fault data.

[0090] It is understandable that the weights of various initial fault data and abnormal points in the fault type are not the same, and the initial fault data needs to be reduced in redundancy according to the weights to avoid excessive data volume.

[0091] It should be understood that the initial fault data may be sorted according to the correlation between the initial fault data and the abnormal point.

[0092] Step A333: taking the reference fault data whose weight is greater than a preset weight threshold in the reference fault data as preset fault data.

[0093] It is understandable that the preset weight threshold may be a pre-set evaluation value of the degree of association between two data, and may be adjusted according to actual conditions, which is not limited in this embodiment.

[0094] In this implementation manner, the weights between various fault data in the preset fault map are used to reduce the redundancy of the abnormal data, thereby reducing the amount of data calculation, and evaluating each fault type through data that is more representative of the fault type.

[0095] The above are only feasible implementations of step S33 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S33.

[0096] Step S34: determining the correlation degree of each fault type according to the preset fault data.

[0097] In a feasible implementation, step S34 may include steps A341 to A343: Step A341, obtaining preset fault data associated with each fault type in the preset fault map.

[0098] It is understandable that the preset fault data may be one or more.

[0099] Step A342, obtaining the failure rate of each failure type according to the weight of the preset failure data.

[0100] It is understandable that there is a preset weight between each preset fault data and each fault type, and the failure rate of the preset fault data and the fault type is obtained by adding the weight of each preset fault data and the fault type.

[0101] In the specific implementation, please refer to Figure 3 , Figure 3It is a schematic diagram of a preset fault spectrum, which includes fault type A and fault type B. The preset fault data of fault type A includes fault data a and fault data c, wherein the weight of fault data a and fault type A is wa1, and the weight of fault data c and fault type A is wc1. Then the failure rate of fault type A is a*wa1+c*wc1.

[0102] Step A343, obtaining the correlation degree of each fault type according to the abnormal weights between the various abnormal data.

[0103] It should be noted that the method of obtaining the correlation of each fault type based on the abnormal weights between the various abnormal data includes: obtaining a weight threshold; comparing the weight threshold and the abnormal weights between the various abnormal data to obtain a comparison result; obtaining the number of connection nodes of each abnormal point based on the comparison result; and obtaining the correlation of each fault type based on the number of connection nodes and the failure rate.

[0104] Among them, it is understandable that reference Figure 3 After calculation, the abnormal points are fault data a and fault data c. Among them, fault data a and fault data c have other related data, which are not marked one by one in the figure. The abnormal weight and weight threshold between the abnormal data of fault data a are compared. The abnormal data with weight greater than the weight threshold are used as connecting nodes, such as fault data 1 and fault data 2.

[0105] It can be known that the connection node data of fault type A in fault data a is 2, so when calculating the correlation degree, the fault rate can be corrected by the number of connection nodes.

[0106] The correction method may be to set the correction parameter closer to 1 as the number of connected nodes increases, and to perform correction by multiplying the number of connected nodes by the failure rate. Other correction strategies may also be set, which is not limited in this embodiment.

[0107] Among them, after obtaining the correlation of each fault type according to the number of connected nodes and the failure rate, it also includes: when the correlation is greater than or equal to the correlation threshold, executing the steps of determining the warning level and predicting the fault type according to the correlation of the fault type; when the correlation is less than the correlation threshold, generating an abnormal signal according to the abnormal data, and performing an abnormal alarm based on the abnormal signal; obtaining a reference abnormal type based on the abnormal alarm feedback from the user and generating an abnormal release signal; and updating the preset fault map according to the reference abnormal type and the abnormal release signal.

[0108] Among them, it is understandable that when an unrecognizable fault type occurs, it can be fed back to the user for manual identification, and after the user identifies it, the preset fault map is updated according to the detection data and the fault cause fed back by the user, and the fault map can be adaptively learned and continuously optimized and updated to ensure the accuracy of fault identification. In this embodiment, the failure rate of each fault type is calculated through preset fault map analysis, thereby improving the accuracy and efficiency of fault prediction and diagnosis, reducing downtime and maintenance costs caused by equipment failure, supporting predictive maintenance strategies, taking measures in advance to prevent failures, enhancing system stability and reliability, and improving overall performance.

[0109] The above are only feasible implementations of step S34 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S34.

[0110] This embodiment provides a method for early warning of equipment failures. By detecting abnormal values ​​in data, abnormal situations worthy of attention are quickly and accurately screened out from a large amount of data; the correlation or importance between different abnormal data is calculated, so as to assign a weight to each abnormality, and distinguish which abnormalities are more critical or more likely to indicate the existence of a specific problem; by comparing the abnormal data and its weight with a predefined fault map, the most matching fault type is found, thereby improving the accuracy of fault diagnosis and reducing false positives and negatives; and the mutual influence or connection between different fault types is evaluated to provide a more comprehensive fault view, helping maintenance personnel understand potential chain reactions or common causes.

[0111] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the equipment fault warning method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0112] This application also provides an equipment failure warning device, please refer to Figure 4 , the equipment failure early warning device comprises: The data acquisition module 10 is used to acquire the operation data of the target industrial equipment and the associated data of each operation data; A fault analysis module 20, configured to perform an abnormality analysis according to the correlation between the operation data and the correlation data to obtain abnormal data; The fault analysis module 20 is further used to perform a graph correlation analysis on the abnormal data according to a preset fault spectrum to obtain a fault type correlation degree; A fault warning module 30 is used to determine the warning level and predict the fault type according to the fault type correlation; The fault warning module 30 is used to provide fault warning for the target industrial equipment based on the warning level and the predicted fault type.

[0113] The equipment failure early warning device provided by the present application adopts the equipment failure early warning method in the above embodiment, which can solve the technical problem that in the equipment maintenance process of the factory, due to the large amount of equipment data and complex fault types, it is impossible to quickly and accurately identify the possible faults of the equipment. Compared with the prior art, the beneficial effects of the equipment failure early warning device provided by the present application are the same as the beneficial effects of the equipment failure early warning method provided by the above embodiment, and the other technical features in the equipment failure early warning device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0114] The present application provides an equipment failure warning device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the equipment failure warning method in the above-mentioned embodiment one.

[0115] Reference below Figure 5 , which shows a schematic diagram of the structure of a device failure warning device suitable for implementing the embodiment of the present application. The device failure warning device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The device failure warning device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0116] like Figure 5As shown, the equipment failure warning device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the equipment failure warning device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the equipment failure warning device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an equipment failure warning device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0117] 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, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0118] The equipment failure warning device provided by the present application adopts the equipment failure warning method in the above embodiment, which can solve the technical problem that in the equipment maintenance process of the factory, due to the large amount of equipment data and complex fault types, it is impossible to quickly and accurately identify the possible faults of the equipment. Compared with the prior art, the beneficial effects of the equipment failure warning device provided by the present application are the same as the beneficial effects of the equipment failure warning method provided by the above embodiment, and the other technical features in the equipment failure warning device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0119] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0120] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0121] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, the computer-readable program instructions being used to execute the device failure early warning method in the above-mentioned embodiment.

[0122] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0123] The computer-readable storage medium may be included in the equipment failure warning device; or may exist independently without being assembled into the equipment failure warning device.

[0124] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the equipment fault warning device, the equipment fault warning device: obtains the operating data of the target industrial equipment and the associated data of each operating data; performs an abnormal analysis based on the correlation between the operating data and the associated data to obtain abnormal data; performs a graph correlation analysis on the abnormal data based on a preset fault map to obtain the fault type correlation; determines the warning level and predicted fault type based on the fault type correlation; and performs fault warning on the target industrial equipment based on the warning level and the predicted fault type.

[0125] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0126] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0127] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0128] The readable 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 above-mentioned equipment failure early warning method, and can solve the technical problem that in the equipment maintenance process of the factory, due to the large amount of equipment and data, and the complex types of failures, it is impossible to quickly and accurately identify the possible failures of the equipment. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the equipment failure early warning method provided by the above-mentioned embodiment, and will not be repeated here.

[0129] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned device failure early warning method when executed by a processor.

[0130] The computer program product provided by the present application can solve the technical problem that in the process of equipment maintenance in a factory, due to the large amount of equipment and data, and the complex types of faults, it is impossible to quickly and accurately identify the possible faults of the equipment. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the equipment fault early warning method provided by the above embodiment, and will not be repeated here.

[0131] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A device failure early warning method, characterized in that: The device fault detection method comprises: Acquire the operation data of the target industrial equipment and the associated data of each operation data; Performing anomaly analysis according to the correlation between the operating data and the correlation data to obtain abnormal data; Performing graph correlation analysis on the abnormal data according to a preset fault graph to obtain a fault type correlation degree; Determine the warning level and the predicted fault type according to the fault type correlation; A fault warning is performed on the target industrial equipment based on the warning level and the predicted fault type.

2. The equipment failure early warning method according to claim 1, characterized in that: The performing graph correlation analysis on the abnormal data according to the preset fault graph to obtain the fault type correlation degree includes: identifying abnormal points among the abnormal data; Obtaining anomaly weights between various anomaly data based on the anomaly points; Determine preset fault data in a preset fault map according to the abnormal weight; The correlation degree of each fault type is determined according to the preset fault data.

3. The equipment failure early warning method according to claim 2, characterized in that: The step of determining the preset fault data in the preset fault map according to the abnormal weight includes: Extracting abnormal features of the abnormal data, matching the abnormal features with preset fault data, and obtaining initial fault data; sorting the initial fault data according to the abnormal weights of the fault data to obtain reference fault data; The reference fault data whose weight is greater than a preset weight threshold in the reference fault data is used as preset fault data.

4. The equipment failure early warning method according to claim 2, characterized in that: The determining the correlation degree of each fault type according to the preset fault data includes: Obtaining preset fault data associated with each fault type in the preset fault map; Obtaining the failure rate of each failure type according to the weight of the preset failure data; The correlation degree of each fault type is obtained according to the abnormal weights between the various abnormal data.

5. The equipment failure early warning method according to claim 4, characterized in that: The obtaining the correlation degree of each fault type according to the abnormal weights between the various abnormal data includes: Get the weight threshold; Comparing the weight threshold with the abnormal weights of the various abnormal data to obtain a comparison result; According to the comparison result, the number of connected nodes of each abnormal point is obtained; The correlation degree of each fault type is obtained according to the number of connected nodes and the fault rate.

6. The equipment failure early warning method according to claim 5, characterized in that: After obtaining the correlation degree of each fault type according to the number of connected nodes and the fault rate, the method further includes: When the correlation degree is greater than or equal to the correlation degree threshold, the steps of determining the warning level and predicting the fault type according to the fault type correlation degree are performed; When the correlation degree is less than a correlation degree threshold, generating an abnormal signal according to the abnormal data, and performing an abnormal alarm based on the abnormal signal; Obtaining a reference abnormality type based on the abnormal alarm feedback from the user and generating an abnormality release signal; The preset fault map is updated according to the reference abnormality type and the abnormality release signal.

7. The equipment failure early warning method according to any one of claims 1 to 6, characterized in that: The determining of the warning level and the predicted fault type according to the fault type correlation degree includes: The fault type with the largest fault type correlation is taken as the predicted fault type; Obtaining a data abnormality degree according to the abnormal data and a preset data standard value; A preset fault level table is matched with the data abnormality to obtain a warning level, wherein the preset fault level table includes one-to-one corresponding data abnormality and fault level.

8. An equipment failure early warning device, characterized in that: The equipment failure early warning device comprises: A data acquisition module, used to acquire the operating data of the target industrial equipment and the associated data of each operating data; A fault analysis module, used for performing an abnormality analysis according to the correlation between the operation data and the correlation data to obtain abnormal data; The fault analysis module is further used to perform graph correlation analysis on the abnormal data according to a preset fault spectrum to obtain a fault type correlation degree; A fault warning module, used to determine the warning level and predict the fault type according to the fault type correlation; The fault warning module is used to provide fault warning for the target industrial equipment based on the warning level and the predicted fault type.

9. An equipment failure early warning device, characterized in that: The device comprises: a memory, a processor, and a device failure warning program stored in the memory and executable on the processor, wherein the device failure warning program is configured to implement the device failure warning method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a device failure warning program, and when the device failure warning program is executed by the processor, the device failure warning method according to any one of claims 1 to 7 is implemented.

Images