Trusted DCS upper computer system health monitoring and maintenance method, apparatus and device, and storage medium

Abstract

The invention discloses a trusted DCS upper computer system health monitoring and maintenance method, device and equipment and a storage medium, and belongs to the technical field of DCS controllers. The method comprises the following steps: firstly, monitoring hardware parameters, software process operation parameters and system security abnormity conditions of a DCS upper computer; when the monitoring result is displayed, the monitoring result is compared with a set threshold value, fault diagnosis is carried out, and a fault type is obtained through a neural network; and according to the fault diagnosis result and the fault type, repairing or sending a maintenance opinion message through a repairing program. According to the method, the health state of the upper computer system can be comprehensively evaluated, potential risk problems can be found in time, and an effective maintenance strategy is provided, so that stable and reliable operation of the trusted DCS upper computer system is guaranteed, the safety, efficiency and reliability of an industrial control system are improved, and remarkable positive influences are brought to production safety and efficiency.

Description

Technical Field

[0001] The present invention belongs to the field of trusted technology and relates to a trusted DCS host computer system health monitoring and maintenance method, device, equipment and storage medium. Background Art

[0002] As a key part of the trusted DCS, the host computer system is responsible for core tasks such as real-time data processing, system monitoring, and control strategy issuance. Its performance status is crucial to the normal operation of the entire control system. As the system operation time increases and the external environment changes, the host computer system may have hardware aging, software vulnerabilities, configuration errors and other problems. These problems may cause system performance degradation or even failure, affecting production safety and efficiency. Therefore, real-time health assessment and maintenance of the host computer system has become an important part of ensuring the stable operation of industrial control systems.

[0003] There are some host computer monitoring and maintenance tools, but these tools can only provide basic hardware monitoring functions and lack in-depth analysis and evaluation of the overall health status of the system. In addition, existing methods often lack effective prediction and automatic repair capabilities when facing complex system failures, and cannot meet the needs of high-reliability industrial environments. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a trusted DCS host computer system health monitoring and maintenance method, device, equipment and storage medium to solve the problem that the prior art currently has a monitoring function for the DCS host computer and lacks further analysis and evaluation, and lacks automatic repair capabilities for complex system failures.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A reliable DCS host computer system health monitoring and maintenance method includes the following steps: S1, monitor the hardware parameters of the DCS host computer, software process operation abnormal parameters and system security abnormalities; the hardware parameters include trusted chip parameters, hard disk I / O parameters and network bandwidth parameters; S2, displays hardware parameters, software process operation abnormal parameters and system security abnormalities; S3, based on hardware parameters and software process operation parameters, obtain real-time parameter statistics; perform fault diagnosis by comparing the real-time parameter statistics with the set threshold, where the set threshold is the statistical data when the system is operating normally; obtain the fault type through a neural network; and perform repairs through a repair program or issue a maintenance advice message based on the fault diagnosis result and the fault type.

[0006] A further improvement of the present invention is: Preferably, in S1, the trusted chip parameter is the chip utilization rate; the chip utilization rate is determined by the chip load and temperature, and the chip load includes the total chip usage, swap memory and swap space usage.

[0007] Preferably, in S1, the software process includes alarms, screens, reports, data transmission and permission verification; and the software process operation abnormality parameters include software process exit or restart.

[0008] Preferably, in S1, the system security anomaly includes system intrusion and system vulnerability, and the system security anomaly is obtained through vulnerability scanning software.

[0009] Preferably, in S3, KPCA is arranged before the neural network.

[0010] Preferably, in S3, hardware parameters and software process operation abnormality parameters are collected through sensors, logs and event records; The neural network is obtained after training with a training data set, wherein the training data set is processed by removing outliers, filling missing data and normalizing data.

[0011] A reliable DCS host computer system health monitoring and maintenance device, comprising: A monitoring module is used to monitor the hardware parameters, software process operation parameters and system security anomalies of the DCS host computer; the hardware parameters include trusted chip parameters, hard disk I / O parameters, and network bandwidth parameters; Display module, used to display monitoring hardware parameters, software process operation parameters and system security anomalies; The diagnosis and repair module is used to obtain real-time parameter statistics based on hardware parameters and software process operation parameters; perform fault diagnosis by comparing the real-time parameter statistics with a set threshold, where the set threshold is the statistical data when the system is operating normally; obtain the fault type through a neural network; and perform repairs through a repair program or issue a maintenance advice message based on the fault diagnosis result and the fault type.

[0012] Preferably, the diagnosis and repair module includes: The diagnostic module is used to perform fault diagnosis based on real-time hardware parameters and software process operation parameters by comparing them with set thresholds; A type judgment module is used to obtain the fault type through a neural network; The repair module is used to perform repairs or issue maintenance advice messages through repair programs according to the fault diagnosis results and fault types.

[0013] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-mentioned trusted DCS host computer system health monitoring and maintenance methods when executing the computer program.

[0014] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the trusted DCS host computer system health monitoring and maintenance method according to any one of claims 1 to 7 is implemented.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a method for health monitoring and maintenance of a trusted DCS host computer system. The method first monitors the hardware parameters, software process operation parameters and system safety anomalies of the DCS host computer; the hardware parameters include trusted chip parameters, hard disk I / O parameters, and network bandwidth parameters; while displaying the monitoring results, fault diagnosis is performed by comparing with set thresholds, and the fault type is obtained through a neural network; according to the fault diagnosis results and the fault type, repairs are performed through a repair program or maintenance advice messages are issued. The method can comprehensively evaluate the health status of the host computer system, timely discover potential risk problems, and provide effective maintenance strategies to ensure the stable and reliable operation of the trusted DCS host computer system. It improves the safety, efficiency and reliability of industrial control systems, and has a significant positive impact on production safety and efficiency. In addition, the present invention has the following advantages: (1) Comprehensive health assessment mechanism: Analyze hardware performance, software level and system security, accurately assess system health in multiple dimensions and levels, and provide a scientific basis for subsequent maintenance decisions.

[0016] (2) Health status visualization and alarm system: An intuitive user interface is used to display the health status of the system. The visual report and alarm system improves the work efficiency of operators.

[0017] (3) Predictive maintenance and automatic repair system: Build a predictive model to predict possible problems and failures in the system, issue warnings in advance, and also support automatic repair functions. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of the health monitoring and maintenance method of the trusted DCS host computer system of the present invention; Figure 2 This is a schematic diagram of the health monitoring and maintenance device for a trusted DCS host computer system of the present invention. DETAILED DESCRIPTION

[0019] In the following, the terms "first", "second", "third", and "fourth" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, a feature defined as "first", "second", "third", and "fourth" may explicitly or implicitly include one or more of the features.

[0020] The co-shooting method provided in the embodiment of the present application can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), etc. The embodiment of the present application does not impose any restrictions on the specific type of the terminal device.

[0021] It should be noted that the terms "first", "second", etc. in the specification and drawings of the present invention are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] See also Figure 1 The first aspect of the present invention discloses a method for health monitoring and maintenance of a trusted DCS host computer system, the method comprising the following steps: S1. Establish a health assessment mechanism and determine the details of the evaluation system reference The evaluation mechanism includes hardware-level evaluation: the health status of trusted chips, CPU usage, and memory occupancy; software-level evaluation: system service status, application running status, etc.; system security-level evaluation: abnormal access detection, software vulnerability assessment, etc.

[0023] Hardware level assessment: Develop system hardware monitoring software to monitor the performance and health of trusted chips, monitor the load and temperature of each trusted chip to evaluate the CPU usage, run shell scripts on the terminal, monitor the total usage, cache and swap space usage in real time, and analyze memory usage. At the same time, it also monitors the utilization of hard disk I / O performance and network bandwidth, and combines them to comprehensively judge the hardware operation status of the equipment; Software level assessment: Develop monitoring software to view the operation of the host computer background process, including alarms, screens, reports, data transmission, permission verification and other processes, and check whether some processes exit or restart abnormally; System security level: Develop an intrusion detection system to monitor and identify security threats such as unauthorized access and abnormal login attempts, and make corresponding records. At the same time, use vulnerability scanning software to scan the system to find possible system vulnerabilities and application vulnerabilities.

[0024] Specifically, the hard disk I / O performance includes I / O data per second, throughput, average I / O data size, disk utilization, service time, I / O waiting queue length and waiting time; the actual values ​​of the above parameters are compared with the set thresholds to determine whether the hard disk I / O performance meets the requirements.

[0025] Comprehensive evaluation of CPU utilization can be analyzed by monitoring load average, core utilization and temperature data. CPU performance usually involves checking load average, CPU utilization and temperature. The load average should be lower than the number of cores, CPU utilization should be maintained between 50%-70%, and the temperature should be between 30°C and 80°C.

[0026] S2, visual health status report and alarm The overall health status of the system is clearly displayed in the user interface, which can be achieved through charts, indicators, and color coding, so that operators can understand the system status at a glance.

[0027] The user interface can also provide maintenance suggestions, including recommended maintenance time, maintenance methods, and spare parts replacement cycles, to help operators reduce potential failure risks. It can also provide corresponding maintenance suggestions based on the monitored problems or risks. These suggestions can be repair measures for existing failures or preventive measures for potential problems. Through these suggestions, operators can better understand how to deal with current problems and take appropriate measures to reduce possible failures in the future.

[0028] Real-time updates and historical records: The system should be able to update health status, alarm information, and maintenance recommendations in real time and retain historical records. Operators can view the latest system status and review past data and events for more comprehensive analysis and evaluation.

[0029] Customization and report export: The system can support users to customize health status reports according to their own needs, and provide report export function so that users can share or archive relevant information.

[0030] S3, predictive fault diagnosis and automatic repair Based on data, the system status is monitored and evaluated in real time, and it also has the ability to predict fault diagnosis. The system collects historical data and real-time monitoring data through sensors, logs, event records, etc., including performance indicators, error logs, event records, etc. These data are used to evaluate the current status; at the same time, the collected data is cleaned and preprocessed to remove outliers, fill in missing data, and normalize the data to ensure the quality and reliability of the data, thereby preparing for subsequent model training and analysis; historical data and real-time monitoring data are used to establish a predictive fault diagnosis model, specifically using the KPCA+ neural network method. Once the system detects or predicts possible problems and failures, it will issue an alarm in advance; it also supports automatic repair functions. After detecting a problem with the system, it automatically executes the preset repair strategy, and can also issue maintenance suggestions to maintenance personnel, and write automated scripts or programs to perform automatic repair operations. For example, in the case of a software failure, the executable script can automatically restart the service or restore the configuration to improve system stability and reliability.

[0031] The predictive fault diagnosis model includes a diagnosis part and a fault type determination part; In the diagnosis part, Q and T^2 are first calculated as thresholds through historical normal data, and the real-time Q and T^2 are calculated through monitored data. The real-time Q value is compared with the set threshold Q, and T^2 is compared with the set threshold T^2. If it is greater than the threshold, it means that the entire system is abnormal and there is a problem.

[0032] The statistical data is the statistics of the collection parameters at each moment.

[0033] The two statistics, Q and T^2, have different focuses; one focuses on evaluating the position of samples in high-dimensional space and judging whether the samples significantly deviate from the normal distribution in the principal component space, and the other focuses on measuring the reconstruction error of samples, which can capture nonlinear reconstruction errors and thus identify abnormal samples in the data reconstruction after mapping to high-dimensional controls. The combination of the two can more comprehensively identify and evaluate data anomalies.

[0034] Furthermore, after determining that there is a problem with the system, KPCA and neural networks can be used to judge the fault data, so as to issue early warnings or take repair measures according to different fault types. The neural network input is the parameters corresponding to each fault type, and the output is the characteristic value corresponding to the fault type.

[0035] The KPCA and neural network are processed with different fault data in the early stage, and input into the neural network for training to obtain the feature set. Assume that there are multiple sets of data for fault type A, multiple sets of data for fault B, multiple sets of data for fault C, and multiple faults. After model training, the feature output of fault A through the neural network is a, the feature output of B is b, the feature output of C is c...Record the feature value set X{a,b,c,...x}.

[0036] KPCA is set before the neural network to perform nonlinear dimensionality reduction on the original data through KPCA, mapping high-dimensional data to low-dimensional space while retaining the key information of the data. This step aims to reduce the input dimension of the neural network, reduce the computational complexity, and possibly improve the generalization ability of the network.

[0037] The above-mentioned neural network can be multiple types of neural networks, such as feedforward neural networks, convolutional neural networks, recurrent neural networks and Transformers.

[0038] This method needs to be able to comprehensively evaluate the health status of the host computer system, promptly identify potential risk issues, and provide effective maintenance strategies to ensure the stable and reliable operation of the trusted DCS system. It can improve the safety, efficiency and reliability of industrial control systems and bring significant positive impacts on production safety and efficiency.

[0039] See also Figure 2 The second aspect of the present invention discloses a trusted DCS host computer system health monitoring and maintenance device, comprising: A monitoring module is used to monitor the hardware parameters, software process operation parameters and system security anomalies of the DCS host computer; the hardware parameters include trusted chip parameters, hard disk I / O parameters, and network bandwidth parameters; Display module, used to display monitoring hardware parameters, software process operation parameters and system security anomalies; The diagnosis and repair module is used to obtain real-time parameter statistics based on hardware parameters and software process operation parameters; perform fault diagnosis by comparing the real-time parameter statistics with a set threshold, where the set threshold is the statistical data when the system is operating normally; obtain the fault type through a neural network; and perform repairs through a repair program or issue a maintenance advice message based on the fault diagnosis result and the fault type.

[0040] Furthermore, the above-mentioned diagnosis and repair module includes: The diagnostic module is used to perform fault diagnosis based on real-time hardware parameters and software process operation parameters by comparing them with set thresholds; A type judgment module is used to obtain the fault type through a neural network; The repair module is used to perform repairs or issue maintenance advice messages through repair programs according to the fault diagnosis results and fault types.

[0041] The third aspect of the present invention discloses a computer device, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement the corresponding method flow. The processor described in this embodiment can be used to implement a trusted DCS host computer system health monitoring and maintenance method, including the following steps: S1, monitoring the hardware parameters, software process operation abnormal parameters and system safety abnormalities of the DCS host computer; the hardware parameters include trusted chip parameters, hard disk I / O parameters and network bandwidth parameters; S2, displaying the hardware parameters, software process operation abnormal parameters and system safety abnormalities; S3, based on the hardware parameters and software process operation parameters, obtaining real-time parameter statistics; by comparing the real-time parameter statistics with the set threshold value, performing fault diagnosis, the set threshold value is the statistical data when the system is operating normally; obtaining the fault type through a neural network; according to the fault diagnosis result and the fault type, repairing through a repair program or issuing a maintenance advice message.

[0042] The fourth aspect of the present invention discloses a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement a trusted DCS host computer system health monitoring and maintenance method in the above embodiment, including the following steps: S1, monitoring the hardware parameters, software process operation abnormality parameters and system safety abnormality of the DCS host computer; the hardware parameters include trusted chip parameters, hard disk I / O parameters and network bandwidth parameters; S2, displaying the hardware parameters, software process operation abnormality parameters and system safety abnormality; S3, obtaining real-time parameter statistical data based on the hardware parameters and software process operation parameters; performing fault diagnosis by comparing the real-time parameter statistical data with a set threshold, the set threshold being the statistical data when the system is operating normally; obtaining the fault type through a neural network; and performing repairs or issuing maintenance advice messages through a repair program according to the fault diagnosis result and the fault type.

[0043] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A trusted DCS host computer system health monitoring and maintenance method, characterized in that: The following steps are involved: S1, monitor the hardware parameters of the DCS host computer, software process operation abnormal parameters and system security abnormalities; the hardware parameters include trusted chip parameters, hard disk I / O parameters and network bandwidth parameters; S2, displays hardware parameters, software process operation abnormal parameters and system security abnormalities; S3, obtains real-time parameter statistics based on hardware parameters and software process running parameters; Fault diagnosis is performed by comparing real-time parameter statistics with set thresholds, where the set thresholds are statistical data when the system is operating normally; Based on hardware parameters and software process operation parameters, the fault type is obtained through neural network; Based on the fault diagnosis results and fault type, the fault is repaired through a repair program or a maintenance advice message is issued.

2. A trusted DCS host computer system health monitoring and maintenance method according to claim 1, characterized in that: In S1, the trusted chip parameter is the chip usage rate; the chip usage rate is determined by the chip load and temperature, and the chip load includes the total chip usage, swap memory and swap space usage.

3. A trusted DCS host computer system health monitoring and maintenance method according to claim 1, characterized in that: In S1, the software process running abnormal parameters include software process exit or restart.

4. A trusted DCS host computer system health monitoring and maintenance method according to claim 1, characterized in that: In S1, the system security anomalies include system intrusions and system vulnerabilities, and the system security anomalies are obtained through vulnerability scanning software.

5. A trusted DCS host computer system health monitoring and maintenance method according to claim 1, characterized in that: In S3, KPCA is arranged before the neural network.

6. A trusted DCS host computer system health monitoring and maintenance method according to claim 1, characterized in that: In S3, hardware parameters and software process operation abnormality parameters are collected through sensors, logs, and event records; The neural network is obtained after training with a training data set, wherein the training data set is processed by removing outliers, filling missing data and normalizing data.

7. A trusted DCS host computer system health monitoring and maintenance device, characterized in that: include: Monitoring module, used to monitor the hardware parameters of the DCS host computer, software process operation parameters and system safety anomalies; The hardware parameters include trusted chip parameters, hard disk I / O parameters, and network bandwidth parameters; Display module, used to display monitoring hardware parameters, software process operation parameters and system security anomalies; The diagnosis and repair module is used to obtain real-time parameter statistics based on hardware parameters and software process operation parameters; Fault diagnosis is performed by comparing real-time parameter statistics with set thresholds, where the set thresholds are statistical data when the system is operating normally; Obtain the fault type through neural network; Based on the fault diagnosis results and fault type, the fault is repaired through a repair program or a maintenance advice message is issued.

8. A trusted DCS host computer system health monitoring and maintenance device according to claim 7, characterized in that: The diagnosis and repair module comprises: The diagnostic module is used to perform fault diagnosis based on real-time hardware parameters and software process operation parameters by comparing them with set thresholds; A type judgment module is used to obtain the fault type through a neural network; The repair module is used to perform repairs or issue maintenance advice messages through repair programs according to the fault diagnosis results and fault types.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the trusted DCS host computer system health monitoring and maintenance method as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the trusted DCS host computer system health monitoring and maintenance method as claimed in any one of claims 1 to 7 is implemented.

Images