Equipment security risk prediction method, system and equipment based on industrial Internet of Things

Abstract

The present invention discloses a method, system and device for predicting equipment safety risks based on industrial Internet of Things, which relates to the field of predictive data processing technology, including: establishing an equipment set; obtaining the first real-time operation log of the implemented equipment at time T, obtaining the type of fault that has occurred according to the first real-time operation log, collecting the type of fault that has occurred and establishing a historical fault type set; obtaining the second real-time operation log of the equipment to be predicted in real time at time T, obtaining the explicit fault type according to the second real-time operation log, judging whether there is an occurred fault type of the same type as the explicit fault type in the historical fault type set; if so, calculating the impact factor based on the impact model; calculating the predicted risk index of the equipment to be predicted based on the risk index generation model and the impact factor. The present invention has the advantages of comprehensive and accurate prediction, high data processing efficiency and dynamic adjustment.

Description

Technical Field

[0001] The present invention relates to the technical field of predictive data processing, and in particular to a method, system and device for predicting equipment safety risks based on industrial Internet of Things. Background Art

[0002] With the rapid development of Industrial Internet of Things (IIoT) technology, more and more industrial equipment are connected to the network, realizing data interaction and intelligent management between devices. This change has greatly improved production efficiency and reduced operating costs, but it has also brought unprecedented equipment security risks. In the IIoT environment, equipment security issues are not only related to the normal operation of a single device, but may also affect the stability and security of the entire production system, and even cause serious production accidents and economic losses.

[0003] At present, some equipment safety risk prediction methods based on data analysis have been proposed, but most of these methods focus on the safety risk prediction of a single device, such as the equipment's operating time, load conditions, etc., without linking these factors to the operation of multiple devices in the industrial Internet of Things environment, ignoring the impact of the interconnection between devices and the propagation of faults. At the same time, when facing large-scale, complex and changeable industrial Internet of Things systems, the algorithms are unscientific and inaccurate, resulting in inefficient handling of subsequent safety risks and failure to effectively ensure the safe operation of the industrial Internet of Things. Summary of the invention

[0004] In view of the defects in the prior art, the present invention provides a method, system and device for predicting equipment security risks based on industrial Internet of Things.

[0005] A method for predicting equipment safety risks based on the industrial Internet of Things comprises: collecting a plurality of implemented equipment of the same type in the industrial Internet of Things and establishing an equipment set; acquiring a first real-time operation log of each implemented equipment in the equipment set in real time at time T, acquiring a plurality of fault types of the implemented equipment according to the first real-time operation log, collecting all the fault types of all implemented equipment in the equipment set and establishing a historical fault type set; acquiring a second real-time operation log of a to-be-predicted equipment of the same type as the implemented equipment in real time at time T, acquiring the fault type of the to-be-predicted equipment according to the second real-time operation log and using it as an explicit fault type, judging whether there is a fault type of the same type as the explicit fault type in the historical fault type set; if so, calculating the influence factor between the explicit fault type in the historical fault type set and any other fault type that has occurred based on an influence model; and calculating the prediction risk index of the to-be-predicted equipment based on a risk index generation model and the influence factor.

[0006] Optionally, calculating the influence factor between an explicit fault type in a historical fault type set and any other fault type that has occurred based on an influence model includes: obtaining a first occurrence number of the explicit fault type in all implemented devices in the device set according to a first real-time operation log, and obtaining the explicit factor based on the influence model and the first occurrence number; obtaining a second occurrence number of the explicit fault type and any other fault type that has occurred in the historical fault type set that simultaneously appears in any implemented device in the device set according to the first real-time operation log, and obtaining an implicit factor corresponding to an occurred fault type based on the influence model and the second occurrence number, thereby obtaining multiple different implicit factors; calculating the explicit factor and multiple implicit factors based on the influence model and generating multiple different influence factors, the multiple influence factors respectively corresponding to multiple fault types that have occurred in the historical fault type set except the explicit fault type.

[0007] Optionally, calculating the predicted risk index of the equipment to be predicted based on the risk index generation model and the influencing factors includes: obtaining the degree of influence of the occurred fault type on the operation of the implemented equipment, wherein each occurred fault type in the historical fault type set corresponds to an influence degree; generating multiple failure coefficients based on the risk index generation model and multiple influence degrees, wherein each occurred fault type in the historical fault type set corresponds to a failure coefficient; calculating the predicted risk index of the equipment to be predicted based on the risk index generation model, multiple influencing factors and multiple failure coefficients.

[0008] Optionally, the influence model in obtaining the dominant factor based on the influence model and the first occurrence number is expressed as: ,in, The first fault type in the historical fault type set that is the same as the explicit fault type Types of faults that have occurred, for The dominant factor is the first adjustment parameter, For the first real-time running log, for The first occurrence number of all implemented devices in the device set; the influence model in the latent factor corresponding to a fault type that has occurred is obtained based on the influence model and the second occurrence number and is expressed as: ,in, is the first fault type in the historical fault type set except for the explicit fault type Types of faults that have occurred, for and The hidden factor is the second adjustment parameter, for and The number of second occurrences that occur simultaneously in any implemented device in the device set.

[0009] Optionally, the influence model is expressed as follows: ;in, for and The impact factor, is the third adjustment parameter, is the fourth adjustment parameter.

[0010] Optionally, the risk indicator generation model in calculating the predicted risk indicator of the equipment to be predicted based on the risk indicator generation model, multiple influencing factors and multiple failure coefficients is expressed as: ;in, To predict risk indicators, for failure coefficient.

[0011] Optionally, the method also includes: obtaining operation and maintenance priorities according to the predicted risk indicators; obtaining operation and maintenance strategies according to the operation and maintenance priorities, and managing and maintaining the predicted equipment according to the operation and maintenance strategies.

[0012] A device safety risk prediction system based on the industrial Internet of Things is also provided. The system includes a user platform, a service platform, and a management platform that are sequentially connected in communication. The service platform includes: a device set construction module, which is used to collect multiple implemented devices of the same type in the industrial Internet of Things and establish a device set; a fault set real-time construction module, which is used to obtain the first real-time operation log of each implemented device in the device set in real time at time T, and is also used to obtain multiple types of faults that have occurred in the implemented device according to the first real-time operation log, and is also used to collect all types of faults that have occurred in all implemented devices in the device set and establish a historical fault type set; a real-time judgment module, which is used to obtain in real time at time T the faults that are related to the implemented devices. The second real-time operation log of the device to be predicted of the same type as the equipment is used, and is also used to obtain the type of fault that has occurred in the device to be predicted according to the second real-time operation log and use it as the explicit fault type, and is also used to determine whether there is an occurred fault type of the same type as the explicit fault type in the historical fault type set; a real-time calculation module is used to calculate the influence factor between the explicit fault type in the historical fault type set and any other occurred fault type based on the influence model after there is an occurred fault type of the same type as the explicit fault type in the historical fault type set; a prediction output module is used to calculate the prediction risk index of the device to be predicted based on the risk index generation model and the influence factor.

[0013] Optionally, the real-time calculation module is also used to: obtain a first occurrence number of the explicit fault type in all implemented devices in the device set according to the first real-time operation log, and obtain an explicit factor based on the influence model and the first occurrence number; obtain a second occurrence number of the explicit fault type and any other occurred fault type in the historical fault type set appearing simultaneously in any implemented device in the device set according to the first real-time operation log, and obtain an implicit factor corresponding to an occurred fault type based on the influence model and the second occurrence number, thereby obtaining multiple different implicit factors; calculate the explicit factor and multiple implicit factors based on the influence model and generate multiple different influence factors, and the multiple influence factors respectively correspond to multiple occurred fault types in the historical fault type set except the explicit fault type.

[0014] An electronic device is also provided, comprising: a memory on which a computer program is stored; and a processor for executing the computer program in the memory to implement the above-mentioned equipment security risk prediction method based on industrial Internet of Things.

[0015] A non-temporary computer-readable storage medium is also provided, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned device security risk prediction method based on the industrial Internet of Things is implemented.

[0016] The beneficial effects of the present invention are embodied in:

[0017] The entire IIoT-based device security risk prediction method realizes centralized management and monitoring of similar devices by collecting multiple implemented devices of the same type in the IIoT and establishing a device set. This method not only considers the operating status of a single device, but also places it in the entire IIoT environment for analysis, thereby enabling a more comprehensive assessment of the device's security risks. Furthermore, it emphasizes real-time acquisition of the device's operating log at a specific time point T. By acquiring data at the same time point T, it ensures that the timeliness of the device status information to be predicted is highly consistent with the historical fault type set. This real-time nature makes the comparative analysis more accurate, and can capture the current security risk status of the device in a timely manner, avoiding misjudgment or omissions caused by data lags. judgment; further, an impact model is introduced to evaluate the mutual influence between fault types, which takes into account the influence of mutual correlation between devices and fault propagation, making the prediction results more in line with the complex situation in the actual industrial Internet of Things environment. By calculating the impact factor, the system can reflect the degree of correlation between different fault types and the possibility of fault propagation, which is of great significance for accurately predicting the future safety risks of equipment; further, a risk indicator generation model is adopted, which can output a quantitative risk indicator. On the basis of ensuring that the prediction results are more accurate and reliable, the safety risk information is more intuitive and easy to understand, which helps users to take more scientific decisions such as prevention and control measures in a timely manner, avoid the occurrence of safety risks or reduce their impact. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0019] Figure 1 A schematic diagram of the steps of an implementation of a method for predicting equipment security risks based on the industrial Internet of Things according to the present invention;

[0020] Figure 2 It is a schematic diagram of step S4 in the device security risk prediction method based on industrial Internet of Things of the present invention;

[0021] Figure 3 It is a schematic diagram of step S5 in the device security risk prediction method based on industrial Internet of Things of the present invention;

[0022] Figure 4 It is a schematic diagram of the steps of another embodiment of the method for predicting equipment security risks based on the industrial Internet of Things of the present invention;

[0023] Figure 5 It is a schematic diagram of the composition of the optimized industrial Internet of Things involved in the present invention;

[0024] Figure 6 It is a schematic diagram of the composition of the management platform and its adjacent platforms in the optimized industrial Internet of Things involved in the present invention;

[0025] Figure 7 The present invention is a block diagram of an electronic device according to an embodiment of the present invention.

[0026] Reference numerals:

[0027] 700 - electronic device, 701 - processor, 702 - memory, 703 - multimedia component, 704 - input / output (I / O) interface, 705 - communication component. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0029] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. In addition, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0031] like Figure 1 As shown, a method for predicting equipment security risks based on industrial Internet of Things is provided, including:

[0032] S1. Collect multiple implemented devices of the same type in the industrial Internet of Things and establish a device set;

[0033] S2. At time T, obtain in real time the first real-time operation log of each implemented device in the device set, obtain multiple types of faults that have occurred in the implemented devices according to the first real-time operation log, collect all types of faults that have occurred in all implemented devices in the device set and establish a historical fault type set;

[0034] S3, at time T, obtaining in real time a second real-time operation log of the device to be predicted that is of the same type as the implemented device, obtaining the type of fault that has occurred in the device to be predicted according to the second real-time operation log and using it as the explicit fault type, and determining whether there is a type of fault that has occurred that is of the same type as the explicit fault type in the historical fault type set;

[0035] S4. If it exists, the influence factor between the dominant fault type in the historical fault type set and any other fault type that has occurred is calculated based on the influence model;

[0036] S5. Calculate the predicted risk index of the equipment to be predicted based on the risk index generation model and the influencing factors.

[0037] In this implementation, it should be noted that in S1, a device set in the industrial Internet of Things environment is constructed to provide a data basis for subsequent security risk prediction; specifically, this step involves extensive collection of multiple implemented devices of the same type in the industrial Internet of Things. These devices may be distributed in different production lines, factories or geographical locations, but the common point is that they are of the same type, that is, they all belong to the same type or perform similar functions. By incorporating these devices into a unified device set, comprehensive monitoring and data collection of the operating status of these devices can be achieved; this process requires the collection of basic information of the equipment, such as equipment model, manufacturer, installation date and operating status. In summary, by establishing a device set, centralized management and monitoring of similar devices in the industrial Internet of Things can be achieved, which helps to improve the efficiency and accuracy of equipment management; secondly, the device set provides rich historical data and failure cases for subsequent security risk prediction. These data are the basis for building an impact model and a risk indicator generation model, and are crucial to improving prediction accuracy.

[0038] In S2, it is the key data collection and analysis link in the entire equipment safety risk prediction method. In this stage, a time point is first set, which is related to the equipment to be predicted. At a specific time point T, the first real-time operation log of each implemented equipment in the equipment set is obtained in real time; these logs contain various status information of the equipment during operation, such as key parameters such as operating time, load conditions, temperature, pressure, fault information and maintenance information; through in-depth analysis of these logs, it is possible to identify and record multiple different types of faults that have occurred in the implemented equipment; subsequently, these different types of faults that have occurred will be summarized to establish a comprehensive historical fault type set; this set contains all the types of faults that have occurred in all implemented equipment in the equipment set. In summary, by obtaining the operation logs of the equipment in real time, the system can ensure the timeliness and accuracy of the data, and provide a reliable basis for subsequent fault analysis and risk prediction; secondly, by establishing a historical fault type set, the system can accumulate a large number of fault cases and data, which are essential for training and optimizing the impact model and risk indicator generation model.

[0039] In S3, it is the analysis and judgment link in the equipment safety risk prediction method. In this stage, at the same time point T, the second real-time operation log of the device to be predicted, which is the same type as the implemented device, will be obtained in real time. The device to be predicted is the device to be predicted later. The second real-time operation log also contains various status information of the device to be predicted during operation. Based on these logs, the system will identify and extract the fault types that have occurred in the device to be predicted, which are called explicit fault types; then, the system will compare these explicit fault types with the fault types in the historical fault type set to determine whether there are the same or similar fault types. This step is crucial to determining the current safety risk status of the device to be predicted. In summary, by acquiring the operation log of the device to be predicted in real time, the system can quickly identify the explicit fault type and provide timely data support for subsequent fault analysis and risk prediction; secondly, by comparing with the historical fault type set, the system can accurately determine whether the device to be predicted has known safety risks, thereby helping users to take prevention and control measures in time to avoid the occurrence or spread of faults; finally, by acquiring data at the same time point T, it ensures that the timeliness of the device status information to be predicted and the historical fault type set is highly consistent. This real-time nature makes the comparison analysis more accurate and can capture the current safety risk status of the device in a timely manner, avoiding misjudgment or missed judgment due to data lag. The historical fault type set is continuously updated and optimized, and it contains the latest fault cases and data, which means that when the device to be predicted is compared, it can refer to the most comprehensive fault type information, thereby improving the comprehensiveness and accuracy of the prediction.

[0040] In S4, if the explicit fault type of the device to be predicted is the same or similar to the fault type in the historical fault type set, further in-depth analysis will be performed based on the impact model. However, if not, it is necessary to confirm again that the explicit fault type of the device to be predicted is indeed different from the fault type in the historical fault type set. If no directly related or similar fault type can be found, a general model or algorithm can be considered to predict the risk. These models or algorithms may be based on factors such as the operating parameters, working environment, and service life of the equipment to estimate the probability of the occurrence of the fault and the possible impact. The impact model in S4 is a mathematical model used to evaluate the mutual influence between fault types. It can calculate the influence factor between the explicit fault type in the historical fault type set and any other fault type that has occurred. These influence factors directly reflect the influence intensity between the fault that has occurred and other possible faults (hidden faults) of the device to be predicted. The larger the influence factor between the explicit fault type and a certain fault type that has occurred, the greater the impact of the fault type that has occurred on the future safety risk of the device to be predicted. This reflects the degree of correlation between different fault types and the possibility of fault propagation, which is of great significance for accurately predicting the future safety risk of the device to be predicted.

[0041] In S5, based on the explicit fault types, influencing factors and risk index generation model obtained from the previous analysis, the predicted risk index of the equipment to be predicted is comprehensively calculated; the risk index generation model is a mathematical model that comprehensively considers multiple factors (such as the different degrees of influence of different types of faults that have occurred on the complete failure of the equipment). It can output a quantitative risk index based on the input information to indicate the severity of the safety risk of the equipment to be predicted in the future. Through this step, the system can provide users with clear warnings and references about the safety risks of the equipment to be predicted. In summary, firstly, by comprehensively considering multiple factors and influencing factors, the system can more accurately predict the future safety risks of the equipment to be predicted, and improve the accuracy and reliability of the prediction; secondly, the quantitative risk index can provide users with intuitive and easy-to-understand warning information, helping users to take prevention and control measures in time to avoid the occurrence of safety risks or reduce their impact; finally, the prediction results of this stage can also provide decision support for subsequent equipment maintenance, overhaul and replacement, optimize the operation management of equipment, and improve the overall safety and efficiency of the industrial Internet of Things.

[0042] In summary, the entire industrial Internet of Things-based device security risk prediction method realizes centralized management and monitoring of similar devices by collecting multiple implemented devices of the same type in the industrial Internet of Things and establishing a device set. This method not only considers the operating status of a single device, but also places it in the entire industrial Internet of Things environment for analysis, so as to more comprehensively evaluate the security risks of the equipment; further, it emphasizes the real-time acquisition of the equipment's operation log at a specific time point T. By acquiring data at the same time point T, it ensures that the timeliness of the device status information to be predicted is highly consistent with the historical fault type set. This real-time nature makes the comparative analysis more accurate, and can capture the current security risk status of the equipment in a timely manner, avoiding errors caused by data lags. Furthermore, an impact model is introduced to evaluate the mutual influence between fault types, which takes into account the influence of mutual correlation between devices and fault propagation, making the prediction results more in line with the complex situation in the actual industrial Internet of Things environment. By calculating the impact factor, the system can reflect the degree of correlation between different fault types and the possibility of fault propagation, which is of great significance for accurately predicting the future safety risks of equipment. Furthermore, a risk indicator generation model is adopted, which can output a quantitative risk indicator. On the basis of ensuring that the prediction results are more accurate and reliable, the safety risk information is more intuitive and easy to understand, which helps users to take more scientific decisions such as prevention and control measures in time to avoid the occurrence of safety risks or reduce their impact.

[0043] like Figure 2 As shown, in one embodiment, calculating the influence factor between the dominant fault type in the historical fault type set and any other fault type that has occurred based on the influence degree model in S4 includes:

[0044] S41, obtaining the first occurrence number of the dominant fault type in all implemented devices in the device set according to the first real-time operation log, and obtaining the dominant factor based on the influence model and the first occurrence number;

[0045] S42, obtaining, according to the first real-time operation log, a second occurrence number of the explicit fault type and any other fault type that has occurred in the historical fault type set that simultaneously occurs in any implemented device in the device set, and obtaining an invisible factor corresponding to an already occurred fault type based on the influence model and the second occurrence number, thereby obtaining a plurality of different invisible factors;

[0046] S43. Calculate the explicit factor and multiple implicit factors based on the influence model and generate multiple different influence factors, where the multiple influence factors respectively correspond to multiple fault types that have occurred in the historical fault type set except the explicit fault type.

[0047] In this embodiment, it should be noted that in S41, first, it is necessary to extract relevant information of explicit fault types from the first real-time operation log of all implemented devices in the device set, and count the total number of times the explicit fault types appear in these devices, that is, the first number of occurrences; then, using the influence model, the first number of occurrences is used as one of the input parameters, and the influence model will calculate the explicit factor according to the algorithm expression. The explicit factor reflects the degree of influence of the explicit fault type itself on the equipment safety risk. The accurate calculation of the explicit factor provides more reliable data support for the subsequent generation and prediction of risk indicators; by counting the number of occurrences of explicit fault types in the actual operation data, the influence model is closer to the equipment operation status in the actual industrial Internet of Things environment.

[0048] In S42, the information of the explicit fault type and any other fault type that has occurred in the historical fault type set is extracted from the first real-time operation log, and the number of times these two fault types appear simultaneously in any implemented device in the device set is counted, that is, the second number of occurrences; then, the influence model is used, and the second number of occurrences is used as one of the input parameters. The influence model will comprehensively calculate the invisible factor corresponding to an already occurred fault type according to the algorithm expression, and repeat this process to obtain multiple invisible factors corresponding to multiple different already occurred fault types. By counting the number of times the explicit fault type and other fault types appear simultaneously and calculating the invisible factor, the correlation between faults can be revealed, which helps to have a deeper understanding of the interaction and propagation mechanism between faults, and provides strong support for subsequent fault prediction and prevention; the calculation of the invisible factor takes into account the joint influence of the explicit fault type and other fault types, making the prediction result more comprehensive and accurate, which helps to reduce the prediction error caused by ignoring the correlation of faults and improve the overall accuracy of the prediction.

[0049] In S43, the explicit factors calculated in step S41 and the multiple implicit factors calculated in step S42 are integrated to ensure that each type of fault that has occurred (except the explicit fault type) has a corresponding influencing factor; then, the impact degree model is used to further calculate the integrated factors, considering the interaction between the explicit factors and the implicit factors, as well as their comprehensive impact on the safety risk of the equipment, to generate the final influencing factors, which reflect the degree of mutual influence between the explicit fault type and other types of faults that have occurred; finally, the calculated influencing factors are output for subsequent risk indicator generation and early warning. By integrating the explicit factors and multiple implicit factors and calculating the final influencing factors, the mutual influence between the explicit fault type and other types of faults that have occurred can be fully reflected, which helps to more accurately evaluate the safety risk level of the equipment to be predicted under the joint action of multiple fault types; the accurate calculation results of the influencing factors provide more accurate data support for the subsequent risk indicator generation and early warning, and by considering the mutual influence of multiple fault types, the accuracy of the prediction can be further improved, and the prediction error caused by ignoring the interaction between faults can be reduced.

[0050] like Figure 3 As shown, in one embodiment, the calculation of the predicted risk index of the device to be predicted based on the risk index generation model and the influencing factor in S5 includes:

[0051] S51, obtaining the degree of influence of the fault type that has occurred on the operation of the implemented equipment, wherein each fault type that has occurred in the historical fault type set corresponds to an influence degree;

[0052] S52, generating multiple failure coefficients based on the risk indicator generation model and multiple impact levels, wherein each fault type that has occurred in the historical fault type set corresponds to a failure coefficient;

[0053] S53, calculating the predicted risk index of the equipment to be predicted based on the risk index generation model, multiple influencing factors and multiple failure coefficients.

[0054] In this embodiment, it should be noted that in S51, for each type of fault that has occurred in the set of historical fault types, the degree of impact on the operation of the implemented equipment is evaluated. The degree of impact can be a quantitative indicator, such as the equipment downtime caused by the fault, the percentage of reduction in production efficiency, the increase in maintenance costs, etc. The evaluation process may need to combine expert experience, historical data analysis, equipment performance models and other methods; then, the degree of impact obtained from the evaluation is sorted out to ensure that each type of fault that has occurred corresponds to a clear degree of impact, and the degree of impact data is output for use in subsequent steps.

[0055] In S52, the impact data of the type of fault that has occurred on the operation of the implemented equipment is obtained from step S51 to ensure that each type of fault that has occurred corresponds to a clear impact level; the risk indicator is used to generate a model, and the impact level of each type of fault that has occurred is used as an input parameter. The model will calculate the failure coefficient corresponding to each type of fault that has occurred based on the size of the impact level, combined with factors such as the performance characteristics of the equipment and the operating environment. The failure coefficient reflects the possibility of equipment failure or failure under a given impact level; finally, the calculated failure coefficients are sorted to ensure that each type of fault that has occurred corresponds to a failure coefficient, and the failure coefficient data is output for use in subsequent steps. For example: the impact of fault A is 0.6 (indicating that fault A causes a 60% drop in equipment performance), the impact of fault B is 0.3 (indicating that fault B causes a 30% drop in equipment performance), and the impact of fault C is 0.9 (indicating that fault C causes a 90% drop in equipment performance). In a risk indicator generation model, we use a simple linear relationship to calculate the failure coefficient. The relationship between the failure coefficient (S) and the impact (I) is: S=k*I, where k is a constant used to adjust the scale of the failure coefficient. For simplicity, we assume that k=1.5 (this value needs to be adjusted according to specific circumstances in actual applications). The failure coefficient of fault A is: F_A=1.5*0.6=0.9, the failure coefficient of fault B is: F_B=1.5*0.3=0.45, and the failure coefficient of fault C is: F_C=1.5*0.9=1.35. In this hypothetical example, Fault C has the highest impact on the device (0.9), so its failure coefficient is also the highest (1.35), indicating that the device is relatively likely to fail due to Fault C at a given impact. Conversely, Fault B has the lowest impact (0.3), so its failure coefficient is also the lowest (0.45).

[0056] In S53, the influence factors calculated in S4 and the failure coefficients generated in S52 are summarized to ensure that each type of fault that has occurred corresponds to an influence factor and a failure coefficient; then, the risk indicator generation model is used to take the influence factors and failure coefficients as input parameters, and the predicted risk indicators of the equipment to be predicted are calculated through the algorithm expression. The predicted risk indicator is a quantitative value used to indicate the risk level of the equipment failing or failing in the future. At the same time, the calculated predicted risk indicators are output, and necessary explanations and descriptions are provided. The predicted risk indicators can help users understand the safety risk status of the equipment and provide a basis for subsequent decision-making.

[0057] In one embodiment, the influence model of the dominant factor obtained based on the influence model and the first occurrence number in S41 is expressed as:

[0058] ,in, The first fault type in the historical fault type set that is the same as the explicit fault type Types of faults that have occurred, for The dominant factor is the first adjustment parameter, For the first real-time running log, for The first occurrence among all implemented devices in the device set;

[0059] Meanwhile, the influence model of the latent factor corresponding to a fault type that has occurred obtained based on the influence model and the second occurrence number in S42 is expressed as:

[0060] ,in, is the first fault type in the historical fault type set except for the explicit fault type Types of faults that have occurred, for and The hidden factor is the second adjustment parameter, for and The number of second occurrences that occur simultaneously in any implemented device in the device set.

[0061] In this embodiment, it should be noted that and By introducing the first occurrence number and the second occurrence , more accurately reflects the actual impact of fault types on equipment operation. More importantly, the exponential function is used to amplify or reduce the impact of the number of times that explicit fault types appear in the equipment set on its risk. When the number of times an explicit fault type appears is large, the exponential function can quickly increase the value of the explicit factor, thereby highlighting its importance, making high-frequency faults occupy a more important position in the prediction, which is in line with the law that the fault frequency and risk level are usually positively correlated in the actual industrial environment; at the same time, since the exponential function can quickly amplify the difference, it makes the risk comparison and sorting between different fault types easier and more intuitive. Users can sort the fault types according to the values ​​of the explicit factor and the implicit factor, so as to determine which fault types pose the greatest threat to the safe operation of the equipment; further, during the operation of the equipment, the occurrence of certain fault types may be cumulative, that is, their occurrence times will gradually increase over time. The exponential function can well reflect this cumulative effect, allowing users to more accurately evaluate the impact of these fault types on the long-term operation of the equipment; further, by setting the first adjustment parameter and the second adjustment parameter , the impact model has high flexibility. These parameters can be adjusted according to different equipment types, operating environments, fault characteristics and other factors to meet different prediction needs. The introduction of these adjustment parameters enables the model to better fit historical data while maintaining good generalization capabilities when new data appears.

[0062] In one embodiment, in S43, the influence model is expressed as follows:

[0063] ;in,

[0064] for and The impact factor, is the third adjustment parameter, is the fourth adjustment parameter.

[0065] In this embodiment, it should be noted that, in the prediction of equipment failure, it is not enough to only consider the impact of explicit fault types (i.e., directly observable faults). Implicit fault types (i.e., faults that are not easily observed directly but may be associated with other faults) also have an important impact on the overall risk of the equipment. Therefore, the model needs a mechanism to comprehensively consider explicit and implicit factors in order to more comprehensively evaluate the impact of fault types on equipment risk. At the same time, different fault types have different degrees of impact on equipment risk. Explicit fault types usually have a more direct impact on the performance and safety of the equipment, while implicit fault types may indirectly affect equipment risk by affecting the probability or severity of explicit faults. The model needs a way to reflect this relative importance in order to give appropriate weights to different fault types in the prediction. Finally, due to differences in factors such as equipment type, operating environment, and fault characteristics, different equipment failure prediction scenarios may require different model parameters, and the third adjustment parameter is introduced. and the fourth adjustment parameter Differences in the above factors can be simulated to adjust for different forecasting needs.

[0066] In summary, the model calculates the latent factors and dominant factors and multiplied by the third adjustment parameter , to reflect the interaction between explicit fault types and implicit fault types, which enables the model to more accurately predict the chain reaction and mutual influence between faults; the third adjustment parameter and the fourth adjustment parameter The introduction of enables the model to be adjusted according to different equipment types, operating environments, fault characteristics and other factors, which enhances the adaptability and generalization ability of the model, enabling it to maintain high accuracy in different prediction scenarios.

[0067] In one embodiment, the risk indicator generation model in calculating the predicted risk indicator of the device to be predicted based on the risk indicator generation model, multiple influencing factors and multiple failure coefficients in S53 is expressed as:

[0068] ;in,

[0069] To predict risk indicators, for failure coefficient.

[0070] In this embodiment, it should be noted that in the prediction of equipment failure, a single factor is often difficult to fully and accurately reflect the risk status of the equipment. Therefore, the model needs a mechanism to comprehensively consider multiple factors, including the influencing factors of the failure type. and failure coefficient By combining these two factors, the model can more comprehensively evaluate the impact of different fault types on equipment risk, thereby improving the accuracy of prediction; at the same time, there may be interactions between different fault types, that is, the occurrence of one fault may affect the probability or severity of another fault. The model calculates the influencing factor , taking into account the dominant fault type Hidden fault type The interaction between them makes the prediction more accurate; finally, the failure coefficient Reflects the type of fault By introducing the failure coefficient, the model can more accurately evaluate the contribution of different fault types to the overall risk of the equipment.

[0071] In summary, by accumulating the product of the failure coefficients and influence factors of all other fault types except the explicit fault type, even if some fault types may appear to have less risk individually, they may cause greater risks when interacting with other fault types. By accumulating the failure coefficients and influence factors of all fault types, it can be ensured that these potential risks will not be missed; further, the accumulation method comprehensively considers the influence of multiple fault types, making the prediction results more accurate, which helps users to more accurately understand the overall risk status of the equipment, thereby formulating more reasonable maintenance plans and risk prevention and control measures; further, when the data of certain fault types are incomplete or uncertain, the accumulation method can make up for these deficiencies by considering the influence of other fault types, which enhances the robustness of the model, so that it can still give reliable prediction results when faced with incomplete or uncertain data.

[0072] like Figure 4 As shown, in one embodiment, it further includes S6, and S6 includes:

[0073] Obtain the operation and maintenance priority based on the predicted risk indicators; obtain the operation and maintenance strategy based on the operation and maintenance priority, and manage and maintain the predicted equipment according to the operation and maintenance strategy.

[0074] In this embodiment, it should be noted that the operation and maintenance priority is obtained based on the predicted risk index calculated in the previous step. , sort the equipment or fault types to determine which equipment or fault types need priority maintenance; generally, equipment or fault types with higher predicted risk indicators will be given higher maintenance priorities to ensure that resources can be allocated to the areas that need the most attention first. According to the determined maintenance priorities, select or formulate corresponding maintenance strategies; these strategies may include regular maintenance, preventive replacement, troubleshooting, performance monitoring, etc.; the selection of maintenance strategies should be based on the type of equipment, operating environment, failure history, and available resources and technical means. Execute the selected maintenance strategy and perform actual management and maintenance operations on the equipment; this may involve inspection, testing, repair, replacement or upgrade of the equipment; when executing the maintenance strategy, ensure the safety and effectiveness of the operation, and record relevant maintenance information and data for subsequent analysis and evaluation.

[0075] like Figure 6 As shown, a device security risk prediction system based on the industrial Internet of Things is also provided. The system includes a user platform, a service platform, and a management platform that are sequentially connected in communication. The service platform includes:

[0076] A device set building module is used to collect multiple implemented devices of the same type in the industrial Internet of Things and establish a device set;

[0077] A fault set real-time construction module is used to obtain the first real-time operation log of each implemented device in the device set in real time at time T, and is also used to obtain multiple fault types that have occurred in the implemented device according to the first real-time operation log, and is also used to collect all the fault types that have occurred in all the implemented devices in the device set and establish a historical fault type set;

[0078] A real-time judgment module is used to obtain, in real time at time T, a second real-time operation log of a device to be predicted that is of the same type as the implemented device, and is also used to obtain the type of fault that has occurred in the device to be predicted according to the second real-time operation log and use it as the explicit fault type, and is also used to judge whether there is a type of fault that has occurred that is of the same type as the explicit fault type in the historical fault type set;

[0079] A real-time calculation module, for calculating the influence factor between the explicit fault type in the historical fault type set and any other occurred fault type based on the influence model after there is a occurred fault type of the same type as the explicit fault type in the historical fault type set;

[0080] The prediction output module is used to calculate the prediction risk index of the equipment to be predicted based on the risk index generation model and the influencing factors.

[0081] Optionally, the real-time calculation module is also used to: obtain a first occurrence number of the explicit fault type in all implemented devices in the device set according to the first real-time operation log, and obtain an explicit factor based on the influence model and the first occurrence number; obtain a second occurrence number of the explicit fault type and any other occurred fault type in the historical fault type set appearing simultaneously in any implemented device in the device set according to the first real-time operation log, and obtain an implicit factor corresponding to an occurred fault type based on the influence model and the second occurrence number, thereby obtaining multiple different implicit factors; calculate the explicit factor and multiple implicit factors based on the influence model and generate multiple different influence factors, and the multiple influence factors respectively correspond to multiple occurred fault types in the historical fault type set except the explicit fault type.

[0082] In this embodiment, it should be noted that, regarding the above-mentioned equipment security risk prediction system based on industrial Internet of Things, the specific method of performing operations has been described in detail in the implementation of the equipment security risk prediction method based on industrial Internet of Things, and will not be elaborated here.

[0083] It should also be noted that the entire industrial Internet of Things-based equipment security risk prediction system can be applied to the optimized industrial Internet of Things, such as Figure 5 As shown, the optimized industrial Internet of Things includes a user platform, a service platform, a management platform, a sensor network platform and an object platform that establish communication in sequence;

[0084] The user platform is configured to provide front-end service functions to users; users obtain the required perceived service information through the user platform, process the perceived service information, and convert it into user perceived information; users analyze the user perceived information and make corresponding decisions based on their own wishes, and convert the user perceived information into user control information through the corresponding information system and send it to the service platform, thereby expressing the user's corresponding service demand intention.

[0085] The physical entities of the user platform include various user terminals, such as mobile phones, computers, dedicated terminals, etc., which realize user-side services through integration with user information system software.

[0086] The service platform is configured as an API server or other general processing platform for establishing communication between the management platform and the user platform to implement corresponding functions; the physical entity of the service platform includes various servers.

[0087] The management platform is configured to perform at least one of equipment operation status monitoring management, data monitoring management, equipment parameter management, and life cycle management; the management platform is an operational coordination platform for the Internet of Things, which may include various management sub-platforms, and different management sub-platforms perform different management services; the physical entities of the management platform include various servers.

[0088] The sensor network platform is configured to perform at least one of network management, command management, device status management, data protocol management, data analysis, data classification, data transmission monitoring, and data transmission security management. The sensor network platform provides data communication, analysis, identification, classification, and other functions, avoiding the direct aggregation of data from various object platforms on the management platform, resulting in redundant data on the management platform and low data processing efficiency; the physical entities of the object platform include various gateways, edge computing devices, etc.

[0089] The object platform is configured to carry out specific production work such as production control, detection, and measurement; the physical entities of the production objects include various production equipment, sensors, etc.

[0090] Figure 7 is a block diagram of an electronic device for predicting device security risks based on the industrial Internet of Things according to an exemplary embodiment. Figure 7 As shown, the electronic device 700 may include: a processor 701 , a memory 702 . The electronic device 700 may also include one or more of a multimedia component 703 , an input / output (I / O) interface 704 , and a communication component 705 .

[0091] The processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned device security risk prediction method based on the industrial Internet of Things. The memory 702 is used to store various types of data to support the operation of the electronic device 700, and these data may include, for example, instructions for any application or method used to operate on the electronic device 700, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, which is used to receive external audio signals. The received audio signal may be further stored in the memory 702 or sent through the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, and the above-mentioned other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 705 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0092] In an exemplary embodiment, the electronic device 700 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned equipment security risk prediction method based on industrial Internet of Things.

[0093] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned device security risk prediction method based on the industrial Internet of Things are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions can be executed by the processor 701 of the electronic device 700 to complete the above-mentioned device security risk prediction method based on the industrial Internet of Things.

[0094] In another exemplary embodiment, a computer program product is also provided, which includes a computer program that can be executed by a programmable device, and the computer program has a code portion for executing the above-mentioned industrial Internet of Things-based equipment security risk prediction method when executed by the programmable device.

[0095] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0096] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0097] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for predicting equipment security risks based on industrial Internet of Things, characterized in that: include: Collect multiple implemented devices of the same type in the Industrial Internet of Things and establish a device set; At time T, the first real-time operation log of each implemented device in the device set is obtained in real time, and multiple types of faults that have occurred in the implemented devices are obtained according to the first real-time operation log, and all types of faults that have occurred in all implemented devices in the device set are collected and a historical fault type set is established; At time T, a second real-time operation log of the device to be predicted, which is the same type as the implemented device, is obtained in real time, and the type of fault that has occurred in the device to be predicted is obtained according to the second real-time operation log and used as the explicit fault type, and it is determined whether there is a type of fault that has occurred that is the same type as the explicit fault type in the historical fault type set; If it exists, then the influence factor between the explicit fault type in the historical fault type set and any other fault type that has occurred is calculated based on the influence model; wherein, the influence factor between the explicit fault type in the historical fault type set and any other fault type that has occurred is calculated based on the influence model, including: obtaining the first occurrence number of the explicit fault type in all implemented devices in the device set according to the first real-time operation log, and obtaining the explicit factor based on the influence model and the first occurrence number; obtaining the second occurrence number of the explicit fault type and any other fault type that has occurred in the historical fault type set in any implemented device in the device set according to the first real-time operation log, and obtaining the implicit factor corresponding to an already occurred fault type based on the influence model and the second occurrence number, thereby obtaining multiple different implicit factors; calculating the explicit factor and the multiple implicit factors based on the influence model and generating multiple different influence factors, and the multiple influence factors respectively correspond to multiple already occurred fault types in the historical fault type set except the explicit fault type; The influence model of the dominant factor obtained based on the influence model and the first occurrence number is expressed as: ,in, The first fault type in the historical fault type set that is the same as the explicit fault type Types of faults that have occurred, for The dominant factor is the first adjustment parameter, For the first real-time running log, for The first occurrence among all implemented devices in the device set; The influence model of the latent factor corresponding to a fault type that has occurred is obtained based on the influence model and the second occurrence number and is expressed as: ,in, is the first fault type in the historical fault type set except for the explicit fault type Types of faults that have occurred, for and The hidden factor is the second adjustment parameter, for and The number of second occurrences that occur simultaneously in any implemented device in the device set; The influence model for calculating the explicit factors and multiple implicit factors based on the influence model and generating multiple different influence factors is expressed as: ;in, for and The impact factor, is the third adjustment parameter, is the fourth adjustment parameter; Calculate the predicted risk index of the equipment to be predicted based on the risk index generation model and the influencing factors; wherein, calculating the predicted risk index of the equipment to be predicted based on the risk index generation model and the influencing factors includes: obtaining the degree of influence of the type of fault that has occurred on the operation of the implemented equipment, wherein each type of fault that has occurred in the historical fault type set corresponds to an influence degree; generating multiple failure coefficients based on the risk index generation model and multiple influence degrees, wherein each type of fault that has occurred in the historical fault type set corresponds to a failure coefficient; calculating the predicted risk index of the equipment to be predicted based on the risk index generation model, multiple influencing factors and multiple failure coefficients; The risk indicator generation model in calculating the predicted risk indicator of the equipment to be predicted based on the risk indicator generation model, multiple influencing factors and multiple failure coefficients is expressed as: ;in, To predict risk indicators, for failure coefficient.

2. The device security risk prediction method based on industrial Internet of Things according to claim 1 is characterized in that: Also includes: Obtain operation and maintenance priorities based on predicted risk indicators; Obtain the operation and maintenance strategy according to the operation and maintenance priority, and manage and maintain the predicted equipment according to the operation and maintenance strategy.

3. An equipment security risk prediction system based on industrial Internet of Things, characterized in that: The system includes a user platform, a service platform and a management platform which are connected in sequence, and the management platform includes: A device set building module is used to collect multiple implemented devices of the same type in the industrial Internet of Things and establish a device set; A fault set real-time construction module is used to obtain the first real-time operation log of each implemented device in the device set in real time at time T, and obtain multiple fault types of the implemented devices according to the first real-time operation log, and collect all the fault types of all the implemented devices in the device set and establish a historical fault type set; A real-time judgment module is used to obtain, in real time at time T, a second real-time operation log of a device to be predicted of the same type as the implemented device, and obtain the type of fault that has occurred of the device to be predicted according to the second real-time operation log as the explicit fault type, and judge whether there is a type of fault that has occurred that is the same as the explicit fault type in the historical fault type set; A real-time calculation module is used to calculate the influence factor between the explicit fault type in the historical fault type set and any other occurred fault type based on the influence model after there is an existing fault type of the same type as the explicit fault type in the historical fault type set; The real-time calculation module is also used to: obtain a first occurrence number of the explicit fault type in all implemented devices in the device set according to the first real-time operation log, and obtain an explicit factor based on the influence model and the first occurrence number; obtain a second occurrence number of the explicit fault type and any other occurred fault type in the historical fault type set appearing simultaneously in any implemented device in the device set according to the first real-time operation log, and obtain an invisible factor corresponding to an occurred fault type based on the influence model and the second occurrence number, thereby obtaining multiple different invisible factors; calculate the explicit factor and the multiple invisible factors based on the influence model and generate multiple different influence factors, and the multiple influence factors respectively correspond to multiple occurred fault types in the historical fault type set except the explicit fault type; The influence model of the dominant factor obtained based on the influence model and the first occurrence number is expressed as: ,in, The first fault type in the historical fault type set that is the same as the explicit fault type Types of faults that have occurred, for The dominant factor is the first adjustment parameter, For the first real-time running log, for The first occurrence among all implemented devices in the device set; The influence model of the latent factor corresponding to a fault type that has occurred is obtained based on the influence model and the second occurrence number and is expressed as: ,in, is the first fault type in the historical fault type set except for the explicit fault type Types of faults that have occurred, for and The hidden factor is the second adjustment parameter, for and The number of second occurrences that occur simultaneously in any implemented device in the device set; The influence model for calculating the explicit factors and multiple implicit factors based on the influence model and generating multiple different influence factors is expressed as: ;in, for and The impact factor, is the third adjustment parameter, is the fourth adjustment parameter; A prediction output module is used to calculate the prediction risk index of the equipment to be predicted based on the risk index generation model and the influencing factors; The prediction output module is also used to obtain the degree of influence of the type of fault that has occurred on the operation of the implemented equipment, wherein each type of fault that has occurred in the historical fault type set corresponds to an influence degree; generate multiple failure coefficients based on the risk indicator generation model and multiple influence degrees, wherein each type of fault that has occurred in the historical fault type set corresponds to a failure coefficient; calculate the prediction risk index of the equipment to be predicted based on the risk indicator generation model, multiple influence factors and multiple failure coefficients; The risk indicator generation model in calculating the predicted risk indicator of the equipment to be predicted based on the risk indicator generation model, multiple influencing factors and multiple failure coefficients is expressed as: ;in, To predict risk indicators, for failure coefficient.

4. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the equipment security risk prediction method based on industrial Internet of Things as described in claim 1.

Images