System safety control system based on Internet of Things technology

Abstract

The invention discloses a system safety control system based on the Internet of Things technology, and relates to the technical field of safety control, and the system comprises a PLC control module, a sensing collection module, a cloud server and a safety monitoring module. And the sensing acquisition module monitors data in real time and transmits the data to the cloud server for storage and analysis, so that algorithm application security, network communication security and data storage security are evaluated, the security of the Internet of Things system is comprehensively evaluated, the integrity of system security monitoring and the comprehensiveness of Internet of Things data processing are ensured, and the security of the Internet of Things system is ensured. Network attacks aiming at the industrial control system are effectively defended through hierarchical design and model fusion, and industrial production continuity and data security are ensured; and deep analysis is carried out through the safety monitoring module to realize alarm management, so that the response efficiency of safety risks is improved, the abnormity repair timeliness and the continuous stability of the system are ensured, and the intelligent application level of the Internet of Things system is improved.

Description

Technical Field

[0001] The present invention relates to the field of safety control technology, and in particular to a system safety control system based on Internet of Things technology. Background Art

[0002] In the Internet of Things (IoT) control system of the industrial production process, the deep integration of sensors, controllers, networks, cloud computing and other technologies through the Industrial Internet of Things has realized the intelligence and automation of the production process. However, the randomness and complexity of the corresponding system security risks are becoming increasingly prominent. Since industrial production has extremely high requirements for system reliability and security, any security incidents may lead to production interruptions, equipment damage and even casualties. Traditional security management mostly relies on static strategies and is difficult to adapt to the dynamically changing industrial environment. Therefore, refined security management must be implemented to deal with potential risks.

[0003] In the Internet of Things control system of the industrial production process, due to the randomness of system security risks, the sectors that may be threatened in real time include the algorithm application sector, network communication sector and data storage sector. However, it is difficult for the existing system security control system to finely determine the real-time threat sectors of system security risks, resulting in insufficient targeted risk management and difficulty in real-time and efficient defense against network attacks on industrial control systems, resulting in insufficient industrial production continuity and data security.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to solve the problems existing in traditional technologies, such as insufficient real-time and efficiency of system security risk monitoring, insufficient refinement and targeting of risk management, difficulty in real-time and efficient defense against network attacks on industrial control systems, and insufficient industrial production continuity and data security.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: The system safety control system based on the Internet of Things technology includes a PLC control module, a sensor acquisition module, a cloud server and a safety monitoring module, wherein the cloud server includes a data storage partition and a data processing partition, and the PLC control module, the sensor acquisition module, the cloud server and the safety monitoring module are connected in communication; The PLC control module is used to control the industrial production process of the Internet of Things: by receiving and executing the management instructions of the cloud server, the operation scheduling of the Internet of Things is carried out, and the automatic control of the Internet of Things is carried out by designing and applying the PLC control algorithm; The sensor acquisition module is used to collect IoT production data: real-time monitoring and acquisition of IoT industrial production processes are carried out through multi-source sensor equipment to obtain IoT production data; IoT production data includes algorithm application information, network communication information and data storage information; The cloud server is used to store and analyze IoT production data: the IoT database is established through data storage partitions to store IoT production data regularly; the IoT database is called through data processing partitions and data analysis and processing is performed to monitor the security of the IoT system; among them, the algorithm application security, network communication security and data storage security levels are evaluated respectively through algorithm application information, network communication information and data storage information, and then the security of the IoT system is comprehensively evaluated; The security monitoring module is used for in-depth analysis and alarm management: by deeply analyzing the security of the IoT system, it generates security alarm signals and management prompt signals for the IoT system, thereby prompting system managers to take corresponding measures for the security of the IoT system.

[0007] Furthermore, the specific process of monitoring the security of the IoT system is as follows: Obtain the algorithm application security score through the algorithm application information, so as to evaluate the algorithm application security level φa; Obtain network communication security score through network communication information, so as to evaluate the level of network communication security φb; Obtain a data storage security score through data storage information, thereby evaluating the data storage security level φc; Through the algorithm application security score, network communication security score and data storage security score, the IoT system security score index is comprehensively obtained to evaluate the security of the IoT system.

[0008] Furthermore, the specific process of evaluating the security of algorithm application is as follows: The algorithm application information includes equipment operation parameters and product processing parameters. Equipment operation parameters include product flatness and appearance information; equipment operation parameters include real-time energy consumption, temperature and vibration information of industrial equipment operation; The input and output data during the execution of the PLC control algorithm are modeled through the LSTM time series analysis model to detect abnormal behavior of the algorithm application; Set up the LSTM prediction model and input historical data of the algorithm application information. Perform time series analysis to obtain forecast output ; By predicting the output With the actual output Compare and obtain the abnormal scoring function Sa(t); Substitute each parameter index of the equipment operation parameters and product processing parameters into the LSTM prediction model in turn to obtain the abnormal scoring function of each parameter index, mark the number of parameter indexes of the algorithm application information as m1, and mark the abnormal scoring function of any parameter index j of the algorithm application information as Saj; The algorithm application security score Sv1 is obtained through the abnormal scoring function Saj ​​of m1 parameter indicators j, the evaluation interval of the algorithm application security score Sv1 is set, and the interval comparison is performed to evaluate the level φa of the algorithm application security.

[0009] Furthermore, the specific process of evaluating network communication security is as follows: Network communication information includes network traffic value, communication transmission frequency and network intrusion frequency; Setting up a communication feature model and sequentially inputting historical data of network communication information; By integrating the historical data of network communication information for statistical analysis, the mean and standard deviation of the corresponding parameter index are obtained, thereby obtaining the network anomaly scoring function Sn(t) of the parameter index p; The number of parameter indicators of network communication information is marked as m2, any parameter indicator of network communication information is marked as p, and the abnormal scoring function of any parameter indicator p of network communication information is marked as Snp; Through the network anomaly scoring function Snp with m2 parameter indicators p, the network communication security score Sv2 is obtained, the evaluation interval of the network communication security score Sv2 is set, and the interval comparison is performed to evaluate the level φb of network communication security.

[0010] Furthermore, the specific process of evaluating data storage security is as follows: Verify the integrity of data storage through hash functions and set access permissions to ensure the security of the data storage call process; Data storage information includes illegal access frequency and data block hash value; The frequency of illegal access to the IoT database at time node i is marked as M(t); Divide the stored data D in the IoT database into u data blocks, and calculate the hash value of the stored data in blocks, and then obtain the integrity scoring function Sd(t) of the hash value of the data block; By combining the illegal access frequency M(t) with the integrity scoring function Sd(t) of the data block hash value, the data storage security score Sv3 is obtained, the evaluation interval of the data storage security score Sv3 is set, and the interval comparison is performed to evaluate the data storage security level φc.

[0011] Furthermore, the specific process of evaluating the security of the IoT system is as follows: By combining the algorithm application security score Sv1, the network communication security score Sv2 and the data storage security score Sv3, the IoT system security score index ZH is comprehensively obtained, the evaluation interval of the IoT system security score index ZH is set, and the interval comparison is performed to evaluate the security level of the IoT system; Furthermore, the specific process of in-depth analysis of the security of the IoT system is as follows: Let the target value of IoT system security score index ZH be Ztarget; Through the IoT system security score index ZH and its target value Ztarget, the mean square error MSE is obtained, and the minimization objective function G is obtained: ; in, is the regularization coefficient, which ranges from 0.001 to 1. By iteratively updating the weight coefficient, the objective function G is gradually minimized and the optimal weight coefficient is obtained. , , , so that the output of the fusion model is closest to the target safety score.

[0012] Furthermore, the specific operation process of alarm management is as follows: Set the evaluation interval of the IoT system security score index ZH, and compare the intervals to evaluate the security level of the IoT system, thereby determining the risk level of system security, and thereby generating corresponding security alarm signals and management prompt signals; Among them, the security alarm signal is to give corresponding alarm prompts to system managers through sound signals and image signals; the management prompt signal is to set comparison factors to finely determine the real-time threat section of the system security risk.

[0013] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: The present invention controls the industrial production process of the Internet of Things through a PLC control module to realize intelligent control of the operation and scheduling of the Internet of Things, and then monitors and collects the production data of the Internet of Things in real time through a sensor collection module, and transmits it to a cloud server for storage and analysis, and simultaneously monitors and evaluates the level of algorithm application security, network communication security, and data storage security, and then comprehensively evaluates the security of the Internet of Things system, ensures the integrity of system security monitoring and the comprehensiveness of Internet of Things data processing, and effectively defends against network attacks on industrial control systems through layered design and model fusion, ensuring industrial production continuity and data security; The present invention implements alarm management through in-depth analysis by the security monitoring module, so as to finely determine the real-time threat sectors of system security risks, and carry out targeted system security risk management, improve the response efficiency of security risks, ensure the timeliness of abnormal repair and the continuous stability of the system, and enhance the intelligent application level of the Internet of Things system. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A connection diagram of the system modules of the present invention is shown; Figure 2 A schematic diagram showing the steps of the workflow of the present invention is shown. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. 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.

[0016] Embodiment 1: like Figure 1-Figure 2 As shown, the system security control system based on the Internet of Things technology includes a PLC control module, a sensor acquisition module, a cloud server and a security monitoring module, wherein the cloud server includes a data storage partition and a data processing partition, and the PLC control module, the sensor acquisition module, the cloud server and the security monitoring module are communicated with each other; The control objectives required by the PLC control algorithm in different industrial scenarios are different. For example, in the production and processing of industrial foil, a PLC control algorithm is designed and built, and laser ranging is used to input foil surface data to monitor the flatness of foil production. The algorithm is customized based on existing technology according to actual application needs, which will not be elaborated in this case.

[0017] The working steps are as follows: S1, PLC control module controls the IoT industrial production process: by receiving and executing the management instructions of the cloud server, the IoT operation scheduling work is carried out; among them, the IoT operation scheduling work refers to the intelligent control of operation scheduling in the IoT industrial production process, and the IoT automatic control is carried out by designing and applying PLC control algorithms. The IoT industrial production process includes product processing, product testing and product transportation.

[0018] S2, the sensor acquisition module collects IoT production data: real-time monitoring and collection of IoT industrial production processes are carried out through multi-source sensor equipment to obtain IoT production data; among which, IoT production data includes algorithm application information, network communication information and data storage information.

[0019] S3, cloud server stores and analyzes IoT production data: establishes IoT database through data storage partitions to store IoT production data regularly, thereby calling PLC control algorithm to generate corresponding management instructions; calls IoT database through data processing partitions and performs data analysis and processing, thereby monitoring IoT system security. Among them, the algorithm application information, network communication information and data storage information are used to evaluate the levels of algorithm application security, network communication security and data storage security, respectively, and then comprehensively evaluate the IoT system security.

[0020] The specific process of monitoring the security of the IoT system is: S3-1, obtain the algorithm application security score through the algorithm application information, so as to evaluate the algorithm application security level φa. The specific process is as follows: Algorithm application information includes equipment operating parameters and product processing parameters; Product processing parameters refer to the various parameter indicators that need to be tested for products to meet qualified standards, such as product flatness, appearance, gram weight, etc.; equipment operation parameters refer to the real-time energy consumption, temperature, vibration and other parameter indicators of industrial equipment operation. Specific parameter indicators are monitored in combination with actual industrial production needs; The input and output data during the execution of the PLC control algorithm are modeled through the LSTM time series analysis model to detect abnormal behavior of the algorithm application; Set up the LSTM prediction model and input historical data of the algorithm application information. Perform time series analysis to obtain forecast output : ,in, For input data, is the predicted output, t is the time node, and T is the historical data period; By predicting the output With the actual output Compare and obtain the abnormal scoring function Sa(t): ; Substitute each parameter index of the equipment operation parameters and product processing parameters into the LSTM prediction model in turn to obtain the abnormal scoring function of each parameter index, mark the number of parameter indexes of the algorithm application information as m1, and mark the abnormal scoring function of any parameter index j of the algorithm application information as Saj; The algorithm application security score Sv1 is obtained through the abnormal scoring function Saj ​​of m1 parameter indicator j: ; Among them, e is a natural constant with a value of 2.7. is the weight coefficient of the abnormal scoring function Saj ​​of parameter index i, and Greater than 0; when the abnormal scoring function Saj ​​of the m1 parameter index is higher, the algorithm application security score Sv1 is lower, and thus the level of algorithm application security is lower; By setting the evaluation interval of the algorithm application security score Sv1 and performing interval comparison, the level φa of the algorithm application security is evaluated.

[0021] S3-2, obtain the network communication security score through the network communication information, so as to evaluate the level φb of network communication security. The specific process is as follows: Network communication information includes network traffic value, communication transmission frequency, network intrusion frequency and other parameter indicators; Setting up a communication feature model and sequentially inputting historical data of network communication information; By integrating the historical data of network communication information for statistical analysis, the mean and standard deviation of the corresponding parameter indicators are obtained, thereby obtaining the network anomaly scoring function Sn(t) of the parameter indicator p: ; in, is the data value of parameter index p at time node t, and They are the mean and standard deviation of the historical data of parameter index p; The number of parameter indicators of network communication information is marked as m2, any parameter indicator of network communication information is marked as p, and the abnormal scoring function of any parameter indicator p of network communication information is marked as Snp; Through the network anomaly scoring function Snp with m2 parameter indicators p, the network communication security score Sv2 is obtained: ; in, is the weight coefficient of parameter index p and Greater than 0; when the network anomaly scoring function Snp of the m2 parameter index p is higher, the network communication security score Sv2 is lower, and thus the level of network communication security is evaluated to be lower; The network communication security level φb is evaluated by setting the evaluation interval of the network communication security score Sv2 and performing interval comparison.

[0022] S3-3, obtain the data storage security score through the data storage information, so as to evaluate the data storage security level φc. The specific process is as follows: Verify the integrity of data storage through hash functions and set access permissions to ensure the security of the data storage call process; Data storage information includes parameter indicators such as illegal access frequency and data block hash value; The frequency of illegal access to the IoT database at time node i is marked as M(t); Divide the stored data D in the IoT database into u data blocks, and calculate the hash value of the stored data in blocks: H(D)=Hash(D1||D2||…||Du), where Hash(·) is the hash function, and SHA-256 is selected; Then obtain the integrity score function Sd(t) of the data block hash value: ,in, is the kth data block, is the weight coefficient of data block k and Greater than 0; By combining the illegal access frequency M(t) with the integrity scoring function Sd(t) of the data block hash value, the data storage security score Sv3 is obtained: ,in, is the conversion coefficient and Greater than 0, conversion coefficient It refers to combining the illegal access frequency M(t) with the integrity scoring function Sd(t) to convert it into a preset constant of the data storage security score Sv3; when the illegal access frequency M(t) is lower and the integrity scoring function Sd(t) of the data block hash value is higher, the data storage security score Sv3 is higher, and thus the level φc of evaluating data storage security is higher; The data storage security level φc is evaluated by setting the evaluation interval of the data storage security score Sv3 and performing interval comparison.

[0023] S3-4, through the algorithm application security score, network communication security score and data storage security score, comprehensively obtain the IoT system security score index, so as to evaluate the security of the IoT system. The specific process is as follows: By combining the algorithm application security score Sv1, the network communication security score Sv2 and the data storage security score Sv3, the IoT system security score index ZH is comprehensively obtained: ; in, , and They are the weight factor coefficients of the algorithm application security score Sv1, the network communication security score Sv2, and the data storage security score Sv3. , and are greater than 0 and ; When the algorithm application security score Sv1, network communication security score Sv2 and data storage security score Sv3 are higher, the IoT system security score index ZH is higher; By setting the evaluation interval of the IoT system security score index ZH and comparing the intervals, the security level of the IoT system can be evaluated; The specific process of in-depth analysis of the security of the IoT system is as follows: Let the target value of IoT system security score index ZH be Ztarget; Through the IoT system security score index ZH and its target value Ztarget, the mean square error MSE is obtained: ; The minimized objective function G is obtained as follows: ; in, is the regularization coefficient, which ranges from 0.001 to 1 and is used to prevent overfitting. By iteratively updating the weight coefficient, the objective function G is gradually minimized and the optimal weight coefficient is obtained. , , , so that the output of the fusion model is closest to the target safety score; The minimization objective function based on the optimized fusion model comprehensively considers the fusion error, regularization term and weight constraint, and solves the optimal weight coefficient through the optimization method to achieve system security optimization and ensure the safety and stability of the system.

[0024] S4, security monitoring module performs in-depth analysis for alarm management: through in-depth analysis of the security of the IoT system, security alarm signals and management prompt signals of the IoT system are generated, thereby prompting system managers to take corresponding measures for the security of the IoT system.

[0025] The specific operation process of alarm management is as follows: The evaluation interval of the IoT system security score index ZH is set, and the interval comparison is performed to evaluate the security level of the IoT system, thereby determining the risk level of system security, thereby generating corresponding security alarm signals and management prompt signals, wherein the security alarm signal relies on sound signals and image signals to give corresponding alarm prompts to system managers; the management prompt signal is based on the analysis of the previous data and sets the comparison factor, thereby finely determining the real-time threat section of the system security risk, wherein the comparison factors of the algorithm application security score Sv1, the network communication security score Sv2, and the data storage security score Sv3 are set and marked respectively. , , ; When the algorithm application security score Sv1 is lower than the comparison factor When a real-time threat is detected in the algorithm application section, the algorithm application section is judged to have real-time threat, and security management is performed on the algorithm application section. For example, a dynamic update mechanism for the PLC control algorithm is designed to ensure that the algorithm can fix vulnerabilities or update defense strategies in a timely manner. When the network communication security score Sv2 is lower than the comparison factor When a real-time threat is detected in the network communication section, the system will determine that there is a real-time threat in the network communication section and perform security management on the network communication section. For example, the communication process will be encrypted to avoid network intrusion, improve communication transmission efficiency, and monitor network traffic characteristics in real time to realize timely alarm of communication anomalies. When the data storage security score Sv3 is lower than the comparison factor When a real-time threat is detected in the data storage section, the data storage section is determined to have real-time threat, and security management is performed on the data storage section. For example, the stored data is encrypted through encryption algorithms to prevent tampering or leakage.

[0026] To summarize, the present invention controls the industrial production process of the Internet of Things through the PLC control module to realize the intelligent control of the operation scheduling of the Internet of Things, and then monitors and collects the production data of the Internet of Things in real time through the sensor acquisition module, and transmits it to the cloud server for storage and analysis, and simultaneously monitors and evaluates the levels of algorithm application security, network communication security and data storage security, and then comprehensively evaluates the security of the Internet of Things system to ensure the integrity and comprehensiveness of system security monitoring, and then performs in-depth analysis through the security monitoring module to realize alarm management, so as to finely determine the real-time threat sector of the system security risk, and carry out targeted system security risk management, improve the response efficiency of security risks, ensure the timeliness of abnormal repair and the continuous stability of the system, and enhance the intelligent application level of the Internet of Things system.

[0027] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technical personnel in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0028] The above formulas are all dimensionless and numerical calculations. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formula are set by technicians in this field according to actual conditions. The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. System security control system based on Internet of Things technology, characterized by: It includes a PLC control module, a sensor acquisition module, a cloud server and a security monitoring module, wherein the cloud server includes a data storage partition and a data processing partition, and the PLC control module, the sensor acquisition module, the cloud server and the security monitoring module are connected in communication; The PLC control module is used to control the industrial production process of the Internet of Things: by receiving and executing the management instructions of the cloud server, the operation scheduling of the Internet of Things is carried out, and the automatic control of the Internet of Things is carried out by designing and applying the PLC control algorithm; The sensor acquisition module is used to collect IoT production data: real-time monitoring and acquisition of IoT industrial production processes are carried out through multi-source sensor equipment to obtain IoT production data; IoT production data includes algorithm application information, network communication information and data storage information; The cloud server is used to store and analyze IoT production data: the IoT database is established through data storage partitions to store IoT production data regularly; the IoT database is called through data processing partitions and data analysis and processing is performed to monitor the security of the IoT system; among them, the algorithm application security, network communication security and data storage security levels are evaluated respectively through algorithm application information, network communication information and data storage information, and then the security of the IoT system is comprehensively evaluated; The security monitoring module is used for in-depth analysis and alarm management: by deeply analyzing the security of the IoT system, it generates security alarm signals and management prompt signals for the IoT system, thereby prompting system managers to take corresponding measures for the security of the IoT system.

2. The system security control system based on Internet of Things technology according to claim 1 is characterized in that: The specific process of monitoring the security of the IoT system is: Obtain the algorithm application security score through the algorithm application information, so as to evaluate the algorithm application security level φa; Obtain network communication security score through network communication information, so as to evaluate the level of network communication security φb; Obtain a data storage security score through data storage information, thereby evaluating the data storage security level φc; Through the algorithm application security score, network communication security score and data storage security score, the IoT system security score index is comprehensively obtained to evaluate the security of the IoT system.

3. The system security control system based on Internet of Things technology according to claim 2 is characterized in that: The specific process of evaluating the security of algorithm application is as follows: The algorithm application information includes equipment operation parameters and product processing parameters. Equipment operation parameters include product flatness and appearance information; equipment operation parameters include real-time energy consumption, temperature and vibration information of industrial equipment operation; The input and output data during the execution of the PLC control algorithm are modeled through the LSTM time series analysis model to detect abnormal behavior of the algorithm application; Set up the LSTM prediction model and input historical data of the algorithm application information. Perform time series analysis to obtain forecast output ; By predicting the output The actual output Compare and obtain the abnormal scoring function Sa(t); Substitute each parameter index of the equipment operation parameters and product processing parameters into the LSTM prediction model in turn to obtain the abnormal scoring function of each parameter index, mark the number of parameter indexes of the algorithm application information as m1, and mark the abnormal scoring function of any parameter index j of the algorithm application information as Saj; The algorithm application security score Sv1 is obtained through the abnormal scoring function Saj ​​of m1 parameter indicators j, the evaluation interval of the algorithm application security score Sv1 is set, and the interval comparison is performed to evaluate the level φa of the algorithm application security.

4. The system safety control system based on Internet of Things technology according to claim 3 is characterized in that: The specific process of evaluating network communication security is as follows: Network communication information includes network traffic value, communication transmission frequency and network intrusion frequency; Setting up a communication feature model and sequentially inputting historical data of network communication information; By integrating the historical data of network communication information for statistical analysis, the mean and standard deviation of the corresponding parameter index are obtained, thereby obtaining the network anomaly scoring function Sn(t) of the parameter index p; The number of parameter indicators of network communication information is marked as m2, any parameter indicator of network communication information is marked as p, and the abnormal scoring function of any parameter indicator p of network communication information is marked as Snp; Through the network anomaly scoring function Snp with m2 parameter indicators p, the network communication security score Sv2 is obtained, the evaluation interval of the network communication security score Sv2 is set, and the interval comparison is performed to evaluate the level φb of network communication security.

5. The system safety control system based on Internet of Things technology according to claim 4 is characterized in that: The specific process of evaluating data storage security is: Verify the integrity of data storage through hash functions and set access permissions to ensure the security of the data storage call process; Data storage information includes illegal access frequency and data block hash value; The frequency of illegal access to the IoT database at time node i is marked as M(t); Divide the stored data D in the IoT database into u data blocks, and calculate the hash value of the stored data in blocks, and then obtain the integrity scoring function Sd(t) of the hash value of the data block; By combining the illegal access frequency M(t) with the integrity scoring function Sd(t) of the data block hash value, the data storage security score Sv3 is obtained, the evaluation interval of the data storage security score Sv3 is set, and the interval comparison is performed to evaluate the data storage security level φc.

6. The system safety control system based on Internet of Things technology according to claim 5 is characterized in that: The specific process of evaluating the security of an IoT system is as follows: By combining the algorithm application security score Sv1, the network communication security score Sv2 and the data storage security score Sv3, the IoT system security score index ZH is comprehensively obtained, the evaluation range of the IoT system security score index ZH is set, and the range comparison is performed to evaluate the security level of the IoT system.

7. The system safety control system based on Internet of Things technology according to claim 6 is characterized in that: The specific process of in-depth analysis of the security of the IoT system is as follows: Let the target value of IoT system security score index ZH be Ztarget; Through the IoT system security score index ZH and its target value Ztarget, the mean square error MSE is obtained, and the minimization objective function G is obtained: ; in, is the regularization coefficient, which ranges from 0.001 to 1. By iteratively updating the weight coefficient, the objective function G is gradually minimized and the optimal weight coefficient is obtained. , , , so that the output of the fusion model is closest to the target safety score.

8. The system safety control system based on Internet of Things technology according to claim 7 is characterized in that: The specific operation process of alarm management is as follows: Set the evaluation interval of the IoT system security score index ZH, and compare the intervals to evaluate the security level of the IoT system, thereby determining the risk level of system security, and thereby generating corresponding security alarm signals and management prompt signals; Among them, the security alarm signal is to give corresponding alarm prompts to system managers through sound signals and image signals; the management prompt signal is to set comparison factors to finely determine the real-time threat section of the system security risk.

Images