State monitoring equipment actively adaptive to industrial computer and health evaluation method

Abstract

The invention discloses state monitoring equipment actively adaptive to an industrial computer and a health evaluation method, and relates to the field of industrial computer equipment. The state monitoring equipment comprises a processor, a storage medium, a power supply module and a detachable communication module, supports AC / DC power supply, and can communicate with an industrial computer and other monitoring equipment. A computer program in the storage medium has a service mode and a client mode, and can push a modular mirror image file of adaptive hardware to the industrial computer during initial connection. In addition, a plurality of state monitoring devices can form a mesh network, thereby improving the reliability of data storage, ensuring that the data is not lost and the production state is quickly recovered when the industrial computer fails, and enhancing the continuity of the system. The core function is to automatically execute a health evaluation method, the equipment health degree is obtained by collecting original data, matching abnormal rules and calculating risk scores, and the remaining maximum load available time of each hardware is obtained through calculation, so that comprehensive monitoring of the industrial computer is realized.

Description

Technical Field

[0001] The present invention relates to the field of industrial computer equipment, and in particular to a state monitoring device and a health evaluation method that actively adapts to an industrial computer. Background Art

[0002] Traditional industrial computer status monitoring relies on regular manual inspections and simple threshold alarm systems. These methods are often inefficient, difficult to achieve real-time monitoring, and easily affected by human factors, resulting in inaccurate and inaccurate fault detection. In addition, static threshold monitoring systems lack flexibility and cannot adapt to dynamic changes in the operating status of equipment, resulting in inaccurate assessments of equipment health status. In terms of data management and analysis, traditional methods rely on decentralized data collection and manual recording, which results in low statistical efficiency and poor data timeliness, making it difficult to achieve refined management and control and effective use of energy.

[0003] In recent years, with the development of data analysis and machine learning technologies, some new technologies have emerged in the field of equipment condition monitoring and predictive maintenance. For example, by analyzing the historical data and real-time data of the equipment, the operating status and failure trend of the equipment can be predicted. Common data analysis and machine learning technologies include prediction algorithms and models, such as regression analysis, time series analysis, support vector machines, neural networks, etc. These algorithms can establish equipment health models and predict the time and probability of failure.

[0004] Although these technologies have improved the accuracy and efficiency of monitoring to a certain extent, there are still some shortcomings. For example, existing monitoring equipment often lacks modular design and cannot be optimized according to the specific hardware configuration of the target industrial computer, resulting in unnecessary performance burden and waste of storage space. At the same time, existing health assessment methods often use static thresholds or simple parameter comparisons in data collection and anomaly determination, lack dynamic analysis of hardware status changes, and limit the accuracy and timeliness of anomaly detection. In addition, the existing assessment methods have low computational efficiency when processing and analyzing large amounts of data, making it difficult to meet real-time requirements.

[0005] In response to the above problems, the present invention proposes a condition monitoring device and health evaluation method that actively adapts to industrial computers, aiming to improve the operating efficiency and reliability of industrial equipment through intelligent means, while providing a more objective, accurate and scientific equipment health status assessment and prediction method. Summary of the invention

[0006] In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide a condition monitoring device and a health assessment method that actively adapts to industrial computers to solve one or more problems in the prior art.

[0007] To achieve the above object, the technical solution of the present invention is as follows: A state monitoring device that actively adapts to an industrial computer comprises a processor, a storage medium, a power module, and a plurality of detachable communication modules, wherein the communication modules are all connected to the communication modules of the industrial computer and other state monitoring devices.

[0008] The storage medium stores a computer program, and the computer program has a service mode and a client mode.

[0009] When the communication module is connected to the industrial computer for the first time, the computer program instructs the processor to push its image file to the industrial computer.

[0010] The computer program enables the processor to automatically execute the health assessment method when running.

[0011] Specifically, the power supply module has two power supply modes: AC and DC.

[0012] Specifically, the computer program instructs the processor to push its image file to the industrial computer, including: Get details on Industrial Computer hardware.

[0013] Generate a modular image file adapted to the corresponding hardware based on the hardware details.

[0014] Push the image file to the industrial computer through the communication interface and request installation permission.

[0015] After the installation is allowed, install the image file to the industrial computer.

[0016] Specifically, when the communication module is connected to other status monitoring devices, the computer program enables multiple status monitoring devices to form a mesh computing and storage network.

[0017] Specifically, the preset parameters of the industrial computer are exported and imported through the communication interface.

[0018] In order to achieve a complete technical effect, the second technical solution of the present invention is a health assessment method, comprising the following steps: Initialize the industrial computer raw data collection task. After monitoring the task event through the system API, call the collection tool to execute the task and obtain the raw data.

[0019] According to the imported anomaly determination rule engine, the original data is matched with the rule features to obtain the anomaly data and anomaly details.

[0020] Bind the exception label to the corresponding exception data.

[0021] The total risk score is calculated based on the different weights of the abnormal details.

[0022] The device health is calculated based on the total risk score. The remaining maximum load available time is calculated based on the hardware type and abnormal data.

[0023] Further, matching the original data with the rule features includes, Threshold determination: set a threshold range for specific hardware and define the original data that does not belong to the threshold range as abnormal data.

[0024] Rated parameters and status comparison and judgment are performed, and the original data that does not fall within the rated parameter range is defined as abnormal data.

[0025] Time domain change analysis obtains the operating data of the hardware over a period of time, and generates a state characteristic curve based on the rated parameters in the hardware support document, monitors the subsequent operating data of the hardware, marks the hardware that permanently deviates from the curve as hardware with permanent degradation, and defines its operating data as abnormal data.

[0026] Record abnormal data and corresponding hardware information.

[0027] Specifically, calculating the remaining maximum load available time includes the following steps: Determine the parameter type of the hardware based on the support documents and rated data of each hardware. For the parameters with abnormal exponential change trend, the exponential fitting method is used to obtain the performance estimation curve formula of the parameter.

[0028] For the parameters with abnormal linear change trend, the linear fitting method is used to obtain the performance estimation curve formula of the parameter.

[0029] The remaining maximum load available time is defined as the difference between the time point when a certain operating parameter of the hardware permanently falls below the rated level and the present time.

[0030] According to the performance estimation curve formula of the parameters, the remaining maximum load available time of the corresponding hardware is calculated; Furthermore, when a certain hardware has multiple parameters at the same time resulting in multiple values ​​of the remaining maximum load available time, the actual remaining maximum load available time takes the minimum value.

[0031] Furthermore, the total risk score calculated based on different weights of the abnormal details includes: The total risk score is defined as the sum of the permanent anomaly score, temporary anomaly score, and aging anomaly score of the hardware.

[0032] The permanent anomaly score is defined as the product of the permanent anomaly degree and the corresponding weight. The temporary anomaly score is defined as the product of the temporary anomaly degree and the corresponding weight. The aging anomaly score is defined as the product of the aging anomaly degree and the corresponding weight.

[0033] Get the total risk score.

[0034] Furthermore, the permanent abnormality degree is defined as the sum of the products of the permanent degradation coefficients, abnormality level coefficients, and hardware coreness coefficients of all hardware.

[0035] The temporary abnormality is defined as a value obtained by screening in a preset reference matrix according to specific conditions.

[0036] The aging abnormality is defined as a value obtained by screening according to specific conditions in a preset reference table.

[0037] Furthermore, the equipment health calculated based on the total risk score includes: The device health is defined as the difference between 100 and the total risk score.

[0038] Get the device health status.

[0039] Compared with the prior art, the beneficial technical effects of the present invention are as follows (i) It has two power supply modes, AC and DC, which ensures the power flexibility and portability of the equipment. Through software and communication interfaces, the device can complete efficient data exchange with industrial computers. After the initial communication, the device will actively submit the adapted software image file to the industrial computer to adapt to various industrial computer hardware. The computer software contains the modular design of mainstream industrial computer hardware, which can actively adapt according to its hardware configuration when connected to the industrial computer. The software image file pushed to the industrial computer excludes inappropriate modules, thereby reducing hardware performance consumption and saving storage space. In addition, the communication interface can be replaced according to the industrial computer model in hardware, which enhances the flexibility of the equipment.

[0040] (ii) Multiple status monitoring devices form a peer-to-peer distributed mesh network to achieve distributed storage of relevant data of multiple monitored industrial computers. Compared with pure software solutions, this design can effectively prevent calculation errors caused by industrial computer failures and improve the reliability of calculation results of fault-free detection equipment. At the same time, compared with a single detection device, this storage solution is more reliable. Even if the storage of a device is damaged, it will not affect any data, ensuring the integrity and security of the data.

[0041] (III) The function of exporting and importing preset parameters of equipment, so as to achieve seamless connection of production status after the industrial computer is damaged or the hardware is replaced after a fault is found. This function will further improve the continuity and reliability of the system, ensure that when an industrial computer fails, it can quickly recover to normal operation, reduce downtime caused by failure, and improve the efficiency and stability of industrial production.

[0042] (IV) The present invention sets a complete and objective health evaluation method, so that the health evaluation of industrial computers has a standard to follow, and the evaluation itself is freed from traditional manual or cumbersome processes, so as to more efficiently respond to or reasonably prevent emergencies of equipment failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a schematic diagram of the logical steps of the health assessment method in an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer, the following is a further detailed description of a state monitoring device and health evaluation method for actively adapting to industrial computers proposed by the present invention in combination with the accompanying drawings and embodiments. It should be noted that the structure, proportion, size, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the limiting conditions for the implementation of the present invention, so they have no technical substantive significance. Any modification of the structure, change in the proportional relationship or adjustment of the size should still fall within the scope of the technical content disclosed by the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0045] Application Overview In the field of industrial computer condition monitoring, traditional technical solutions usually rely on manual inspections and static threshold monitoring systems, which have obvious limitations and shortcomings. First, manual inspections are inefficient, making it difficult to achieve real-time monitoring, and are easily affected by human factors, resulting in inaccurate and inaccurate fault detection. Second, static threshold monitoring systems lack flexibility and cannot adapt to dynamic changes in the operating status of equipment, resulting in inaccurate assessments of the health status of equipment. In addition, these traditional methods also have defects in data management and analysis, often relying on decentralized data collection and manual recording, which makes data statistics inefficient and time-sensitive, making it difficult to achieve refined management and control and effective use of energy.

[0046] In response to these technical problems, the present invention proposes an innovative condition monitoring device and health evaluation method. By setting a complete and objective health evaluation method, the present invention provides clear standards for the health evaluation of industrial computers, gets rid of traditional manual or cumbersome processes, and improves the efficiency and accuracy of the evaluation. This method can not only monitor the status of the equipment in real time, but also dynamically analyze the health of the equipment, and more efficiently respond to or prevent emergencies of equipment failure. Compared with traditional solutions, the present invention can provide more accurate and real-time equipment health status assessment, thereby reducing equipment replacement costs, reducing operation and maintenance costs, improving production efficiency, and achieving effective use of energy.

[0047] Example The present invention introduces a device specially designed for monitoring the status of industrial computers, which has high adaptability and flexibility and can operate stably in a variety of working environments. The device consists of several key parts: an efficient processor, a storage medium for storing data and programs, a power module that can provide stable power, and multiple communication modules that can be replaced as needed. These communication modules are designed with a unified interface, so that users can replace different types of communication modules according to different connection requirements, thereby improving the applicability of the device.

[0048] The power module is specially designed to support both AC and DC power supply modes. This design enables the monitoring equipment to continue to work through DC power supply in an environment without AC power supply. This flexible power supply capability, coupled with the moderate size of the device itself, allows the monitoring device to not only be fixed on an industrial computer for communication, but also be used as a portable device for on-site troubleshooting of industrial computers.

[0049] The computer program embedded in the storage medium is the core of this device. The program contains two operating modes: service mode and client mode. In service mode, the device can work with other monitoring devices to build an efficient mesh computing storage network. This network structure not only improves the efficiency of data processing, but also enhances data security. In client mode, the device communicates directly with the industrial computer to perform specific monitoring tasks. In addition, the computer program also allows the preset parameters of the industrial computer to be directly exported and imported through the communication interface, which greatly simplifies the configuration process of the device. This means that even if the hardware of the industrial computer changes due to repair or maintenance, the device can quickly help the industrial computer return to a productive state, reducing the downtime caused by equipment failure.

[0050] When the communication module is first connected to the industrial computer, the computer program automatically instructs the processor to push a modular image file configured specifically for the hardware. This process includes automatically obtaining the hardware details of the industrial computer, generating an adapted modular image file, and pushing it to the industrial computer through the communication interface to request installation permission. Once permission is obtained, the image file will be automatically installed to ensure that the device can communicate seamlessly with the industrial computer.

[0051] The present invention proposes a systematic health assessment method for evaluating the operating status of industrial computers.

[0052] The health assessment method realizes real-time monitoring and evaluation of the operating status of industrial computers in an automated way. The method first starts the data collection task, monitors and triggers related events through the system API, and uses the collection tool to collect raw data. These data are the basis for evaluating the health status of industrial computers and are also the key input for subsequent analysis.

[0053] Next, the device uses the anomaly determination rule engine to set threshold ranges for specific hardware and identify data outside these ranges as anomalies. This step is crucial because it helps us detect deviations in hardware performance in a timely manner and prevent possible failures. At the same time, the device will also compare the preset parameters and actual status of the hardware, and will also treat data that does not meet the parameter range as anomalies, further enhancing the accuracy of monitoring.

[0054] In addition, the device also generates characteristic curves of the hardware status through time domain change analysis and based on the rated parameters in the hardware support document, and marks data that permanently deviates from these curves as abnormal. This analysis method can reveal the trend of hardware performance changes over time, which is crucial for identifying potential long-term problems. All of this abnormal data and its related hardware information will be recorded, providing detailed data support for subsequent analysis and processing.

[0055] Specifically, calculating the remaining maximum load available time includes the following steps: Determine the parameter type of the hardware based on the support documents and rated data of each hardware. For the parameters with abnormal exponential change trend, the exponential fitting method is used to obtain the performance estimation curve formula of the parameter.

[0056] For the parameters with abnormal linear change trend, the linear fitting method is used to obtain the performance estimation curve formula of the parameter.

[0057] According to the performance estimation curve formula, we can infer the time point when the maximum load performance of a hardware item drops below the rated level. The time required from the current time to this time point is the remaining time that the hardware can maintain the maximum load operation. When the same hardware has parameters with different change trends and thus has multiple "Remaining Maximum Load Available Time" labels at the same time, the actual Remaining Maximum Load Available Time of the hardware selects the minimum value.

[0058] Specifically, fitting is performed on data with exponential change trends, such as the number of hard disk remapped sectors, the number of hard disk uncorrectable sectors, the CPU high-load power supply voltage, and the power supply voltage value / ripple value of each power supply. The specific fitting method is the nonlinear least squares method, that is, taking the natural logarithm of the preprocessed data to transform an exponential change into a linear fit. Then, after the least squares method is used for linear fitting, the exponential calculation with base e is performed in reverse to obtain its parameters.

[0059] The final fitted trend formula is: .

[0060] The data with linear change trends such as the remaining hard disk write life, hard disk spare space, hard disk helium pressure, fan speed and target speed difference are fitted. The specific fitting method uses the general least squares method to obtain its slope and intercept parameters.

[0061] The final fitted trend formula is: V(T)=M×T+A.

[0062] Where V(T) is the estimate of a parameter at a certain time point, M is the slope after fitting, T is the time, and is the intercept obtained after fitting. is the initial value obtained by fitting, is the natural exponential, t is the time increased relative to the initial value, and a is the parameter after fitting.

[0063] Furthermore, the device associates the abnormal data with the corresponding tags for better tracking and analysis. This step not only helps to quickly locate the problem, but also provides more contextual information for the cause of the fault, making problem solving more efficient.

[0064] After the abnormal data is collected and marked, the device calculates the total risk score, which is the cumulative result of the permanent anomaly score, temporary anomaly score, and aging anomaly score. These anomaly scores are defined based on the product of the permanent anomaly degree, temporary anomaly degree, and aging anomaly degree and their corresponding weights. Among them, the permanent anomaly degree is the sum of the products of the hardware's permanent degradation coefficient, anomaly level coefficient, and hardware core degree coefficient; while the temporary anomaly degree and aging anomaly degree are the values ​​obtained by screening under specific conditions based on the preset reference matrix and table.

[0065] Specifically, The calculation formula for the permanent abnormality of industrial computers is: ,This formula comprehensively considers the severity of the anomaly and the importance of the component, and provides a quantitative assessment of the degree of permanent anomaly.

[0066] in is the weight coefficient corresponding to the abnormal level. 1, medium level 0.6, low level is 0.2; C is the weight coefficient of each component for the stability of industrial computer operation, with core components being 1 and secondary components being 0.5; The value corresponding to whether the exception occurs or not, if it has been permanently degraded to 1, if it has not occurred, it is 0; That is, the permanent abnormality degree is the sum of the products of the permanent degradation coefficient of the hardware, the abnormality level coefficient and the hardware core degree coefficient, and the maximum value of the permanent abnormality degree is 100.

[0067] The temporary abnormality reference matrix is ​​as follows:

[0068] Temporary exception levels are defined as follows, High: It may cause the industrial computer to crash or run abnormally in a short period of time; Medium: If not handled for a long time, it may cause the industrial computer to crash or run stuck or abnormally; Low: It requires attention to its long-term development, and there is a small probability that it will cause abnormal operation of industrial computers; Information: No need to pay attention to, it only indicates that the device is switching normally and is not included in the calculation.

[0069] The frequency of temporary anomalies is defined as follows, Level 3: more than 5 times a day; Level 2: 2-5 times a day; Level 1: 1 day is less than or equal to 1.

[0070] The evaluation of aging anomaly is based on the online time of the hardware, and the risk score is calculated through a preset reference table. The aging anomaly reference table is as follows:

[0071] The aging abnormality is marked as This table takes into account the impact of hardware aging on performance over time and provides a quantitative indicator of aging anomaly.

[0072] Finally, by calculating the formula =100-0.5 -0.3 -0.2 , which is 100 minus the total risk score to get the health score of the device. The permanent anomaly score is equal to the permanent anomaly degree × weight 0.5, that is, 0.5 ; The temporary abnormality score is equal to the temporary abnormality × weight 0.3, that is, 0.3 ; The aging abnormality score is equal to the aging abnormality × weight 0.2, that is, 0.2 .

[0073] This formula combines the effects of permanent abnormality, temporary abnormality and aging abnormality, and provides a quantitative evaluation standard for the health of industrial computers. This method makes the health evaluation of equipment more objective and accurate, helps to timely discover and prevent potential failures, and improves the reliability and efficiency of industrial production.

[0074] Through this systematic health evaluation method, the present invention not only improves the monitoring efficiency of industrial computers, but also greatly enhances the understanding and control of the health status of equipment. This innovative monitoring equipment and method will undoubtedly bring a technological innovation to the industrial field and provide strong support for the stable operation of industrial equipment.

[0075] In practical applications, this condition monitoring equipment can be deployed in various industrial environments, such as manufacturing plants, power facilities, petrochemicals, etc. These environments have extremely high requirements for the stability and reliability of equipment. By real-time monitoring and evaluating the operating status of industrial computers, this device can help operators understand the health status of equipment in a timely manner, so as to take necessary maintenance measures and avoid production interruptions caused by equipment failures.

[0076] In addition, the design of this device also takes ease of use into consideration. Users can adapt to different monitoring needs through simple operations, such as replacing communication modules or adjusting the operating mode of computer programs. This design makes it easy for even non-professionals to use and maintain the device, reducing the dependence on professional technicians.

[0077] In the daily maintenance of the equipment, users can regularly check the working status of the power module to ensure stable power supply. At the same time, data can be synchronized and backed up with other monitoring devices through the service mode of the computer program to ensure the security and integrity of the data. When the equipment fails, users can use the portability of the equipment to quickly move the equipment to the fault site for on-site inspection and troubleshooting.

[0078] In general, the condition monitoring device of the present invention provides a new solution for the health management of industrial computers with its high adaptability, flexibility and ease of use. By real-time monitoring and evaluating the operating status of industrial computers, the device can help users to timely discover and prevent potential failures and improve the reliability and efficiency of industrial production. With the continuous development of industrial automation and intelligence, the application prospects of this device will become more and more extensive, contributing to the technological progress in the industrial field.

[0079] Specific working process The monitoring device establishes a communication connection with the industrial computer through its detachable communication module.

[0080] The communication module selects the appropriate communication interface for connection according to the model of the connected industrial computer.

[0081] The power module provides power to the monitoring device and supports AC or DC mode to ensure that the device starts.

[0082] After the monitoring device is started, the computer program in the storage medium is loaded and ready to run.

[0083] The computer program runs in service mode on the monitoring device, waiting for a connection request from the industrial computer.

[0084] The communication module connects other monitoring devices to build a mesh computing and storage network.

[0085] The monitoring device exports the preset parameters of the industrial computer through the communication interface, preparing for device configuration.

[0086] When the monitoring device is connected to the industrial computer for the first time, the computer program instructs the processor to push the image file to the industrial computer.

[0087] The monitoring device obtains the hardware details of the industrial computer and prepares for generating a modular image file that is compatible with the hardware.

[0088] Based on the hardware details, the monitoring device generates a modular image file adapted to the corresponding hardware.

[0089] The monitoring device pushes the image file to the industrial computer through the communication interface and requests installation permission.

[0090] After the industrial computer receives the image file, the user confirms the installation permission according to the prompts.

[0091] After obtaining permission, the monitoring device installs the image file to the industrial computer to complete the adaptation process.

[0092] The computer program runs in client mode on the industrial computer and starts automatically executing the health assessment method.

[0093] The health assessment method starts the data collection task. After the system API detects the task event, it calls the collection tool to execute the task and obtain the original data.

[0094] The anomaly determination rule engine analyzes the original data, sets the threshold range, and determines the abnormal data.

[0095] Built-in parameter and status comparison and judgment to identify abnormal data that is not within the parameter range.

[0096] The time domain change analysis generates a hardware status characteristic curve based on the rated parameters and operating data, monitors the subsequent raw data, marks the hardware that permanently deviates from the curve as hardware with permanent degradation, and marks the hardware data that deviates from the curve as abnormal data.

[0097] Abnormal data and its hardware information are recorded.

[0098] Exception labels are bound to corresponding exception data.

[0099] The parameter type of the hardware is determined according to the supporting documents and rated data of each hardware. For hardware with an abnormal exponential change trend, the exponential fitting method is used to obtain the performance estimation curve formula of the hardware; for hardware with an abnormal linear change trend, the linear fitting method is used to obtain the performance estimation curve formula of the hardware.

[0100] According to the performance estimation curve formula of the hardware, the remaining maximum load available time of the hardware is calculated.

[0101] Calculate the total risk score by adding the permanent anomaly score, temporary anomaly score, and aged anomaly score.

[0102] Each anomaly score is calculated based on the product of the permanent anomaly degree, temporary anomaly degree and aging anomaly degree and the corresponding weight.

[0103] Calculate the device health, which is 100 minus the total risk score, to get the device health score; obtain the remaining maximum load available time of each hardware.

[0104] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A condition monitoring device that actively adapts to industrial computers, characterized by: It includes a processor, a storage medium, a power module, and a plurality of detachable communication modules, wherein the communication modules are all connected to the communication modules of the industrial computer and other status monitoring equipment; The storage medium stores a computer program, and the computer program has a service mode and a client mode; When the communication module is connected to the industrial computer for the first time, the computer program causes the processor to push its image file to the industrial computer; The computer program enables the processor to automatically execute the health assessment method when running.

2. The condition monitoring device for actively adapting to industrial computers according to claim 1, characterized in that: The power supply module has two power supply modes: AC and DC; It is also characterized in that the computer program instructs the processor to push its image file to the industrial computer, including the following steps: Get the details of industrial computer hardware; Generate a modular image file adapted to the corresponding hardware based on the hardware details; Push the image file to the industrial computer through the communication interface and request installation permission; After the installation is allowed, install the image file to the industrial computer.

3. The condition monitoring device for actively adapting to industrial computers according to claim 1, characterized in that: When the communication module is connected to other status monitoring devices, the computer program enables the multiple status monitoring devices to form a mesh computing and storage network.

4. The condition monitoring device for actively adapting to industrial computers according to claim 1, characterized in that: Export and import preset parameters of industrial computers via the communication interface.

5. A health assessment method, characterized in that: The following steps are involved: Initialize the industrial computer raw data collection task. After monitoring the task event through the system API, call the collection tool to execute the task and obtain the raw data. According to the imported anomaly determination rule engine, the original data is matched with the rule features to obtain the anomaly data and anomaly details; Bind the exception label to the corresponding exception data; The total risk score is calculated based on the different weights of the abnormal details; The device health is calculated based on the total risk score; the remaining maximum load available time is calculated based on the hardware type and abnormal data.

6. The health assessment method according to claim 5, characterized in that: Matching raw data with rule features includes, Threshold determination: set a threshold interval for specific hardware and define the original data that does not belong to the threshold interval as abnormal data; Rated parameters and status comparison and judgment, defining the original data that does not fall within the rated parameter range as abnormal data; Time domain change analysis: obtain the operating data of the hardware over a period of time, and generate a state characteristic curve based on the rated parameters, monitor the subsequent operating data of the hardware, mark the hardware that permanently deviates from the curve as hardware with permanent degradation, and define its operating data as abnormal data; Record abnormal data and corresponding hardware information.

7. The health assessment method according to claim 5, characterized in that: Calculating the remaining peak load available time includes the following steps: Determine the parameter type of the hardware based on the support documents and rated data of each hardware. For the parameters with abnormal exponential change trend, the exponential fitting method is used to obtain the performance estimation curve formula of the parameter; For the parameters with abnormal linear change trend, the linear fitting method is used to obtain the performance estimation curve formula of the parameter; The remaining maximum load available time is defined as the difference between the time point when the hardware operating parameters are permanently lower than the rated parameters and the present time; According to the performance estimation curve formula of the parameters, the remaining maximum load available time of the corresponding hardware is calculated; The feature is also that: when a certain hardware has multiple parameters at the same time resulting in multiple values ​​of the remaining maximum load available time, the actual remaining maximum load available time takes the minimum value therein.

8. The health assessment method according to claim 5, characterized in that: The total risk score calculated based on the different weights of the abnormal details includes: The total risk score is defined as the sum of the hardware's permanent anomaly score, temporary anomaly score, and aging anomaly score; The permanent anomaly score is defined as the product of the permanent anomaly degree and the corresponding weight; the temporary anomaly score is defined as the product of the temporary anomaly degree and the corresponding weight; the aging anomaly score is defined as the product of the aging anomaly degree and the corresponding weight; Get the total risk score.

9. The health assessment method according to claim 8, characterized in that: The permanent abnormality is defined as the sum of the products of the permanent degradation coefficient, the abnormality level coefficient, and the hardware core coefficient of all hardware; The temporary abnormality is defined as a value obtained by screening according to specific conditions in a preset reference matrix; The aging abnormality is defined as a value obtained by screening according to specific conditions in a preset reference table.

10. The health assessment method according to claim 5, characterized in that: The equipment health calculated based on the total risk score includes: The device health is defined as the difference between 100 and the total risk score; Get device health and remaining peak load available time for each hardware.

Images