A fault early warning and monitoring method and system for industrial control computer DIO modules

Abstract

This invention discloses a fault early warning monitoring method and system for industrial control computer (ICC) DIO modules, belonging to the field of industrial automation and predictive maintenance technology. The method includes: collecting multi-dimensional operating parameters of the DIO module at fixed intervals and filtering them to obtain a purified parameter sequence; analyzing parameter trends using an anomaly detection algorithm, identifying potential anomalies and locating specific signal channels if parameters continuously exceed limits; analyzing the increase in contact resistance of the abnormal channel and determining the specific faulty hardware location using a position mapping model; calculating a risk level score and generating and issuing graded early warning signals; for advanced early warnings, calling matching parameter optimization instructions from a strategy library and dynamically adjusting the module output until stability is achieved using a feedback control algorithm. This invention realizes fault precursor identification, accurate location, intelligent graded early warning, and adaptive control, significantly improving the timeliness of monitoring and early warning and the reliability of the system.

Description

Technical Field

[0001] This invention relates to the field of industrial automation and predictive maintenance technology, specifically to a fault early warning and monitoring method and system for an industrial control computer's DIO module. Background Technology

[0002] In industrial control systems, the digital input / output (DIO) module of the industrial computer undertakes the key task of signal interaction between the control core and field sensors and actuators. Its operational stability is directly related to the continuity and reliability of the entire production line.

[0003] Currently, monitoring methods for DIO modules in industrial control computers generally focus on detection and recording after a fault occurs. Common monitoring software often uses a logic of timed inspection combined with fixed threshold judgment, mainly monitoring basic binary signals such as the module's online status and channel continuity. This post-event monitoring mode has significant drawbacks: First, fault detection is severely delayed, failing to identify early signs of faults such as parameter drift and slow increases in contact resistance before a fault occurs, often leading to unplanned downtime and production losses. Second, the monitoring dimensions are too singular, focusing only on the final result of signal transmission and lacking synchronous monitoring of multi-dimensional operating parameters such as the module's internal power quality (e.g., voltage and current fluctuations) and key hardware status (e.g., chip operating temperature, channel contact resistance), easily leading to missed hidden faults. Third, the fault location accuracy is low; existing technologies typically report anomalies at the module level, unable to further locate specific faulty channels or specific components on the board, making troubleshooting difficult for on-site maintenance personnel and prolonging the mean time to repair (MTBL). Fourth, the early warning mechanism is rigid and lacks a strategy to classify early warnings according to the level of fault risk. As a result, maintenance personnel cannot quickly judge the urgency and priority of the event from the alarm, which affects the efficiency of handling.

[0004] Therefore, there is an urgent need for an industrial control computer DIO module monitoring solution that can identify fault precursors, monitor multi-dimensional health status, accurately locate faults, and provide intelligent hierarchical early warning, in order to improve the predictive maintenance capabilities and operational reliability of industrial control systems. Summary of the Invention

[0005] The purpose of this invention is to provide a fault early warning and monitoring method and system for the DIO module of an industrial control computer, so as to solve the above-mentioned problems existing in the prior art.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A fault early warning and monitoring method for an industrial control computer's DIO module includes the following steps: S1. Data Acquisition and Preprocessing: At a preset fixed period, multi-dimensional operating parameters, including input voltage, current, channel signal level, chip temperature and contact resistance, are collected in real time from the industrial control computer's DIO module. The collected parameter sequence is then filtered and denoised to obtain a purified parameter sequence. S2. Anomaly detection and channel localization: Based on the purified parameter sequence, an anomaly detection algorithm is used to analyze the changing trend of each parameter. If the changing trend of any parameter continuously exceeds the preset threshold, it is determined that there is a potential anomaly, and the specific signal channel where the anomaly occurs is identified. S3. Fault Feature Analysis and Location: For the specific signal channel where the anomaly occurred, obtain the historical average value of its contact resistance, and calculate the increase in the current contact resistance value relative to the historical average value; if the increase is greater than a preset resistance threshold, then through a pre-stored location mapping model, associate the specific signal channel with the physical layout of the equipment to determine the specific faulty hardware location. S4. Risk Assessment and Graded Early Warning: Based on the specific location of the faulty hardware, the abnormal magnitude of the change trend, and the range of affected equipment, a comprehensive risk level score is calculated using a risk assessment algorithm; based on the risk level score, a corresponding level of early warning signal is generated and issued, wherein the early warning level includes at least a primary early warning for indicating a precursor to a fault, an intermediate early warning for indicating a moderate fault, and a high-level early warning for indicating a severe fault. S5. Adaptive Response and Control: If the triggered warning level is a high-level warning, the parameter optimization instruction matching the current fault type is called from the preset response strategy library. Based on the parameter optimization instruction, the output settings of the DIO module are dynamically adjusted using a feedback control algorithm until the module's operating state returns to stability.

[0007] Furthermore, in step S1, the preset fixed period is 50 milliseconds.

[0008] Furthermore, in step S2, the anomaly detection algorithm is the isolated forest algorithm; the continuous exceeding of the preset threshold means that the parameter value exceeds the corresponding normal fluctuation range in three consecutive collection cycles.

[0009] Furthermore, in step S4, the range of affected devices is obtained by querying a pre-stored system topology relationship, which defines one or more external devices connected to the specific faulty hardware location.

[0010] Furthermore, in step S5, the step of calling parameter optimization instructions that match the current fault type from the preset response strategy library includes: using a response matching degree evaluation method for screening; if the matching degree is lower than a preset threshold, then using a support vector machine algorithm to classify and learn historical optimization schemes to generate the optimal combination of module parameter values ​​under the current fault scenario.

[0011] Furthermore, in step S5, the step of "until the module's operating state returns to stability" includes: dynamically adjusting the output settings of the DIO module using a feedback control algorithm, continuously monitoring the deviation between the operating parameters and the target value, and if the deviation exceeds the stability threshold again, then re-executing the adaptive response and control steps.

[0012] Furthermore, after step S4, a data management step is also included: storing all operating parameters collected in S1, potential anomalies and specific signal channels where anomalies occur as determined in S2, early warning signals of corresponding levels generated in S4, and parameter optimization instructions called in S5 and adjustments to the output settings of the DIO module, and displaying them in the form of dashboards and trend curves.

[0013] Furthermore, it also includes a cloud collaboration step: synchronizing the operating parameters collected in S1, the early warning signals generated in S4, and the data stored in the data management step to the cloud server to achieve centralized monitoring and management of multiple industrial control computer DIO modules deployed in a distributed manner.

[0014] Another objective of this invention is to provide a fault early warning and monitoring system for an industrial control computer's DIO module, used to implement the aforementioned fault early warning and monitoring method for an industrial control computer's DIO module, the system comprising: The data acquisition and filtering module is used to acquire multi-dimensional operating parameters of the DIO module at fixed intervals and perform filtering and noise reduction to obtain a purified parameter sequence. An anomaly detection and localization module is used to perform anomaly trend analysis based on the purified parameter sequence in order to determine the specific signal channel where the anomaly occurred and the specific location of the faulty hardware. The risk assessment and early warning module is used to calculate the risk level score based on the specific location of the faulty hardware, the magnitude of the anomaly, and the range of affected equipment, and to generate corresponding graded early warning signals. The adaptive response control module is used to call parameter optimization instructions and adjust the output settings of the DIO module based on the feedback control algorithm when an advanced warning is triggered. The data management and human-computer interaction module is used to store all collected operating parameters, identified potential anomalies and specific signal channels where anomalies occur, generated early warning signals of corresponding levels, as well as parameter optimization instructions and adjustments to the DIO module output settings, and to display them visually.

[0015] Furthermore, the system is implemented using a layered architecture, which includes: The hardware adaptation layer is used to automatically identify and connect different types of DIO modules, providing hardware support for data acquisition. The data acquisition layer communicates with the hardware adaptation layer and includes the data acquisition and filtering module, which is used to periodically acquire raw parameters through the hardware adaptation layer. The data processing layer includes the anomaly detection and location module, which is used to clean data, identify early signs of failure, and locate the fault. The early warning decision layer includes the risk assessment and early warning module and the adaptive response control module, which are used to assess risks, decide on the early warning level, and perform parameter adjustments when a high-level early warning is triggered. The user interaction layer includes the data management and human-computer interaction module, which provides a human-computer interaction interface for parameter setting, status display, and early warning information.

[0016] Compared with the prior art, the present invention has the following beneficial effects: I. Early warning of faults is achieved. This invention, through high-frequency data acquisition and multi-dimensional trend analysis, can issue early warnings at the stage of fault precursors such as abnormal parameter drift and slow increase in contact resistance, transforming fault handling from post-event remediation to pre-event prevention, effectively reducing the probability of production line downtime caused by sudden failures of DIO modules.

[0017] Second, it improves the comprehensiveness and positioning accuracy of monitoring. The monitoring scope covers multiple core dimensions such as power supply, signal, and hardware status, and uses a location mapping model to associate abnormal signal channels with specific hardware locations, which greatly improves the fault detection coverage and can locate faults to specific channels or components, greatly shortening the on-site troubleshooting time.

[0018] Third, an intelligent hierarchical early warning mechanism has been introduced. Different levels of early warnings, such as yellow, orange, and red, are dynamically triggered based on risk assessment results, and different prompting methods are matched, from log recording to strong audible and visual alarms. This enables maintenance personnel to quickly identify fault priorities, optimize resource allocation, and significantly improve emergency response efficiency.

[0019] Fourth, it possesses adaptive optimization capabilities. For high-level faults, the system can automatically obtain or intelligently generate parameter optimization schemes from the strategy library, and adjust the module output through feedback control to attempt to autonomously restore stability. In some scenarios, this can avoid or delay downtime, enhancing the system's robustness.

[0020] V. Excellent compatibility and scalability. The layered architecture and hardware adaptation layer design enable the system to be compatible with various brands and models of DIO modules, while supporting cloud data synchronization. It is easy to expand into a distributed or centralized monitoring platform, adapting to complex industrial field environments. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0023] This embodiment provides a fault early warning and monitoring method for an industrial control computer's DIO module. The key lies in constructing a complete process of monitoring, analysis, decision-making, and control. This method begins with high-frequency, multi-dimensional data acquisition, identifies fault precursors and accurately locates them through trend analysis and feature matching, triggers tiered early warnings based on dynamic risk assessment, and performs adaptive parameter adjustment for advanced faults. Finally, all process data is visualized, recorded, and scalable to the cloud for centralized management. The method is implemented based on a hardware system, which is implemented in software using a clearly decoupled five-layer architecture, including a hardware adaptation layer, a data acquisition layer, a data processing layer, an early warning decision layer, and a user interaction layer. This architecture ensures the system's stability, compatibility, and maintainability. The following section will combine... Figure 1 The specific implementation process of the method will be described in detail.

[0024] S1. Data Acquisition and Preprocessing: At a preset fixed period, multi-dimensional operating parameters, including input voltage, current, channel signal level, chip temperature and contact resistance, are collected in real time from the industrial control computer's DIO module. The collected parameter sequence is then filtered and denoised to obtain a purified parameter sequence.

[0025] After system startup, initialization is performed first. The hardware adaptation layer begins operation, which incorporates universal drivers for various DIO modules such as Modbus TCP and PROFINET, as well as standard communication protocols. This layer can automatically scan and identify the connected DIO module models, establish a stable communication link, and provide transparent hardware support for data acquisition, thus solving the technical challenge of compatibility with modules from different brands. Subsequently, the data acquisition and filtering modules in the data acquisition layer begin operating at a very high fixed period. In a preferred embodiment, this preset fixed period is 50 milliseconds. Within this period, the modules synchronously acquire multi-dimensional operating parameters of the DIO modules through the interface provided by the hardware adaptation layer. These parameters go beyond the traditional approach of only monitoring on / off states, comprehensively covering the following: Power status: Module input voltage and operating current I; Channel status: Real-time signal level of each digital input / output channel; Hardware health status: temperature T of the core control chip and contact resistance of each signal channel. .

[0026] The collected raw parameter sequence This includes electromagnetic noise from the industrial environment. The data acquisition and filtering module immediately performs noise reduction filtering; in this embodiment, a first-order low-pass filter or moving average filter is used. This processing is a recursive process, and its general form can be expressed as: in, This represents the purified parameter value at the current time t. This represents the purified parameter value at the previous time (t-1). The filter coefficients are 0 < ≤1. The closer the value is to 1, the better the new sampled value. The larger the weight, the faster the filter output response, but the smoothing effect is weakened; The closer the value is to 0, the greater the weight of the historical filtered values, resulting in a smoother output but increased response delay. Through recursive calculation using this formula, the complete purified parameter sequence, which serves as input for subsequent steps, is obtained. .

[0027] S2. Anomaly Detection and Channel Localization: Based on the purified parameter sequence, an anomaly detection algorithm is used to analyze the changing trend of each parameter. If the changing trend of any parameter continuously exceeds the preset threshold, it is determined that there is a potential anomaly, and the specific signal channel where the anomaly occurs is identified.

[0028] Purified parameter sequence The data is then fed into the anomaly detection and localization module of the data processing layer. This module's task is to capture abnormal trends in parameter changes and provide early warnings. This embodiment preferably uses the Isolation Forest algorithm as the anomaly detection algorithm. This algorithm establishes a profile of the normal behavior for each parameter, such as voltage or contact resistance. The module analyzes the changing trend of each parameter using a sliding time window, for example, containing the most recent 10 sampling points. A continuous exceedance of a preset threshold is specifically defined as: any parameter value exceeding its preset normal fluctuation range for three consecutive sampling cycles (150 milliseconds). For example, a rated input voltage of 24V might have a normal range set to [23V, 25V]. If the detected voltage values ​​are 25.1V, 25.3V, and 25.2V in three consecutive cycles, all exceeding the 25V upper limit, it is considered a potential anomaly. Once a potential anomaly is identified, the module immediately records the time of the anomaly and determines the specific signal channel where the anomaly occurred, such as channel 3 of the DIO module. This process enables rapid filtering of abnormal signals from massive amounts of data, shifting fault identification from reactive to real-time, thus improving the timeliness of early warning.

[0029] S3. Fault Feature Analysis and Location: For the specific signal channel where the anomaly occurred, obtain its historical average contact resistance and calculate the increase in the current contact resistance value relative to the historical average value; if the increase is greater than a preset resistance threshold, then use a pre-stored location mapping model to associate the specific signal channel with the physical layout of the equipment to determine the specific faulty hardware location.

[0030] For the specific signal channel, such as channel 3, that exhibited an anomaly as identified in step S2, the system enters deep diagnostic mode. The initial trend of the anomaly may be caused by various factors; therefore, this invention introduces contact resistance analysis as a key diagnostic feature. The anomaly detection and localization module first retrieves the historical average contact resistance of the anomaly channel from the historical database over a period of time, such as the past 24 hours. Simultaneously, obtain the current contact resistance value of this channel. This parameter is derived from the latest post-purification parameter sequence. The increase in resistance is calculated. If ΔR is greater than the preset resistance threshold... ,For example Set as A failure rate of 20% strongly suggests a risk of loose hardware connections, oxidation, or physical damage at the channel. To guide maintenance personnel in rapid on-site handling, the system invokes a pre-stored location mapping model. This model is a lookup table or database that stores the precise mapping relationship between logical channel numbers and physical locations within the factory, such as the relationship between module A - channel 3 and production line 2 - cabinet 3 - servo motor start / stop control terminal block - X5 terminal. Through this model, the system can map the abstract, logical channel 3 anomaly to a specific, operable faulty hardware location, achieving a leap from anomaly detection to component location and overcoming the low positioning accuracy of traditional technologies.

[0031] S4. Risk Assessment and Graded Early Warning: Based on the specific location of the faulty hardware, the abnormal magnitude of the change trend, and the range of affected equipment, a comprehensive risk level score is calculated using a risk assessment algorithm; based on the risk level score, a corresponding level of early warning signal is generated and issued, wherein the early warning level includes at least a primary early warning for indicating a precursor to a fault, an intermediate early warning for indicating a moderate fault, and a high-level early warning for indicating a severe fault.

[0032] The risk assessment and early warning module of the early warning decision layer receives diagnostic results from the data processing layer, including: the specific location of the faulty hardware, the abnormal amplitude Δ, and the type of abnormal parameters. The module first queries the pre-stored system topology based on the specific location of the faulty hardware. This topology defines the upstream and downstream devices connected to the fault point. For example, if the fault location is the start / stop signal output terminal of a servo motor, the affected equipment includes the servo motor and the robotic arm it drives. Combining the abnormal amplitude Δ, such as voltage exceeding limits, percentage increase in resistance, and the scope of impact, the module uses a risk assessment algorithm for calculation. This algorithm can be a multi-factor weighted scoring model.

[0033] In this embodiment, the model is: Risk Score = w1 × Location Criticality Coefficient + w2 × Anomaly Amplitude Coefficient + w3 × Number of Affected Equipment Coefficient. The location criticality coefficient can be assigned a graded value based on the safety requirements, downtime losses, or process importance of the field equipment associated with the specific faulty hardware location in the production process. The anomaly amplitude coefficient can be obtained by normalizing the anomaly amplitude Δ to a preset scoring range, such as 0~1. The number of affected equipment coefficient can be assigned a tiered value based on the number of downstream equipment directly affected by the fault, such as 0.2 for affecting one piece of equipment and 1.0 for affecting a production line. The weights w1, w2, and w3 are preset values, reflecting the relative importance of the three evaluation dimensions: location criticality, anomaly amplitude, and impact scope. They can be configured and adjusted according to different emphases on safety, reliability, or production efficiency in specific application scenarios. Finally, a comprehensive risk level score is output, for example, 0-100 points. Based on this score, the system triggers a graded warning, specifically including: (1) Primary warning, or early warning of a fault, scores between 0 and 60. The system marks the corresponding module or channel status in yellow on the user interface and records the anomaly details in the log. At this time, maintenance personnel receive preventative maintenance suggestions.

[0034] (2) Intermediate warning, i.e., moderate fault, with a score of 60-85. The interface status turns orange, triggering a mild audible and visual alarm, such as intermittent buzzer sounding, and a non-blocking message pop-up window, which contains recommended troubleshooting steps.

[0035] (3) Advanced warning is a serious fault, with a score of 85-100. The interface status turns red, triggering a strong audible and visual alarm that continuously sounds and flashes, and pops up a full-screen or top-mounted fault details pop-up window, clearly displaying the fault location, possible causes, and emergency handling instructions.

[0036] This tiered mechanism enables staff to instantly assess the urgency of an incident, optimizes the response process, and greatly improves handling efficiency.

[0037] S5. Adaptive Response and Control: If the triggered warning level is a high-level warning, the parameter optimization instruction matching the current fault type is called from the preset response strategy library. Based on the parameter optimization instruction, the output settings of the DIO module are dynamically adjusted using a feedback control algorithm until the module's operating state returns to stability.

[0038] If the triggered warning level is a high-level warning, the adaptive response control module of the warning decision layer is activated to attempt autonomous intervention to avoid downtime. This module first retrieves instructions from a preset response strategy library. The strategy library stores historical parameter optimization instructions corresponding to various fault modes, including decreased output channel drive capability and weak input channel anti-interference capability. Corresponding historical parameter optimization instructions include increasing the output drive current by 10% and enabling input signal hysteresis filtering. The call process is not a simple match but uses a response matching degree evaluation method for filtering. If the matching degree between the current fault scenario and all historical records in the library is lower than a preset threshold, such as 80%, the system uses a Support Vector Machine (SVM) algorithm to classify and learn historical optimization schemes, intelligently generating the optimal combination of module parameter values ​​for the current fault scenario. After obtaining the optimization instructions, the module uses a feedback control algorithm, such as proportional-integral control, to dynamically adjust the output settings of the DIO module. In this embodiment, if the instruction is to increase the output current of channel 5 from 0.5A to 0.55A, the module writes new configuration parameters to the DIO module through the hardware adaptation layer.

[0039] After adjustment, the system does not immediately return to the initial steps. Instead, within the current adaptive response and control phase, it continuously monitors the deviations of key operating parameters from the target values. This continues until the module's operating state stabilizes. Specifically, if the deviation exceeds the stability threshold again, the adaptive response and control steps are re-executed, i.e., the adjustment command is recalculated and issued, forming a new control cycle. If the parameters remain within the normal threshold range for M consecutive cycles (M=10, i.e., 0.5 seconds), the system is considered to have stabilized, and the advanced warning can be downgraded or lifted. This forms a complete, rapid, intelligent control process of execution, monitoring, and re-execution within step S5, enhancing the system's autonomous resilience and robustness.

[0040] Furthermore, following step S4, a data management process is also included. All data generated throughout the monitoring and early warning process is uniformly managed by the data management and human-computer interaction module of the user interaction layer. This module executes the data management steps, specifically storing: all operating parameters collected in S1, i.e., the time-series database; potential anomalies identified in S2 and specific signal channels where anomalies occurred, i.e., the event log; the corresponding level of early warning signals generated in S4, i.e., the early warning log; and the parameter optimization instructions invoked and the adjustments to the DIO module output settings in S5, i.e., the operation audit log. This data is visualized in real time through dashboards and trend curves, providing operators with a global situational awareness.

[0041] Furthermore, the method also includes a cloud-based collaborative process. The operating parameters collected in S1, the early warning signals generated in S4, and the data stored in the data management steps are synchronized to a cloud server to achieve centralized monitoring and management of multiple distributed industrial control computer (DIO) modules. The cloud platform can aggregate data from hundreds of industrial control computer (DIO) modules within the factory, enabling centralized monitoring, big data analysis, and cross-device health status comparison, thus achieving group-based and intelligent management of distributed industrial equipment.

[0042] Based on the implementation process of the above method, this embodiment also provides a fault early warning and monitoring system for an industrial control computer DIO module, used to implement the aforementioned fault early warning and monitoring method for an industrial control computer DIO module, the system comprising: The data acquisition and filtering module is used to acquire multi-dimensional operating parameters of the DIO module at fixed intervals and perform filtering and noise reduction to obtain a purified parameter sequence. An anomaly detection and localization module is used to perform anomaly trend analysis based on the purified parameter sequence in order to determine the specific signal channel where the anomaly occurred and the specific location of the faulty hardware. The risk assessment and early warning module is used to calculate the risk level score based on the specific location of the faulty hardware, the magnitude of the anomaly, and the range of affected equipment, and to generate corresponding graded early warning signals. The adaptive response control module is used to call parameter optimization instructions and adjust the output settings of the DIO module based on the feedback control algorithm when an advanced warning is triggered. The data management and human-computer interaction module is used to store all collected operating parameters, identified potential anomalies and specific signal channels where anomalies occur, generated early warning signals of corresponding levels, as well as parameter optimization instructions and adjustments to the DIO module output settings, and to display them visually.

[0043] Furthermore, the system is implemented using a layered architecture, which includes: The hardware adaptation layer is used to automatically identify and connect different types of DIO modules, providing hardware support for data acquisition. The data acquisition layer communicates with the hardware adaptation layer and includes the data acquisition and filtering module, which is used to periodically acquire raw parameters through the hardware adaptation layer. The data processing layer includes the anomaly detection and location module, which is used to clean data, identify early signs of failure, and locate the fault. The early warning decision layer includes the risk assessment and early warning module and the adaptive response control module, which are used to assess risks, decide on early warning levels, and perform parameter adjustments when a high-level early warning is triggered. The user interaction layer includes the data management and human-computer interaction module, which provides a human-computer interaction interface for parameter setting, status display, and early warning information.

[0044] Data is exchanged between layers through well-defined interfaces, decoupling between layers and making the system stable, scalable and maintainable.

[0045] Through the above-described complete technical solution, this invention effectively achieves early warning, precise location, intelligent classification, and adaptive control of faults, comprehensively improving the reliability and maintainability of the DIO module in the industrial control system.

[0046] Embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0047] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0048] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0049] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0050] Contents not described in detail in this specification are prior art known to those skilled in the art. It is hereby indicated that the above description is intended to help those skilled in the art understand this invention, but does not limit the scope of protection of this invention. Any equivalent substitutions, modifications, improvements, or simplifications of the above descriptions that do not depart from the essential content of this invention fall within the scope of protection of this invention.

Claims

1. A fault early warning and monitoring method for an industrial control computer's DIO module, characterized in that, Includes the following steps: S1. Data Acquisition and Preprocessing: At a preset fixed period, multi-dimensional operating parameters, including input voltage, current, channel signal level, chip temperature and contact resistance, are collected in real time from the industrial control computer's DIO module. The collected parameter sequence is then filtered and denoised to obtain a purified parameter sequence. S2. Anomaly detection and channel localization: Based on the purified parameter sequence, an anomaly detection algorithm is used to analyze the changing trend of each parameter. If the changing trend of any parameter continuously exceeds the preset threshold, it is determined that there is a potential anomaly, and the specific signal channel where the anomaly occurs is identified. S3. Fault Feature Analysis and Location: For the specific signal channel where the anomaly occurred, obtain the historical average value of its contact resistance, and calculate the increase in the current contact resistance value relative to the historical average value; if the increase is greater than a preset resistance threshold, then through a pre-stored location mapping model, associate the specific signal channel with the physical layout of the equipment to determine the specific faulty hardware location. S4. Risk Assessment and Graded Early Warning: Based on the specific location of the faulty hardware, the abnormal magnitude of the change trend, and the range of affected equipment, a comprehensive risk level score is calculated using a risk assessment algorithm; based on the risk level score, a corresponding level of early warning signal is generated and issued, wherein the early warning level includes at least a primary early warning for indicating a precursor to a fault, an intermediate early warning for indicating a moderate fault, and a high-level early warning for indicating a severe fault. S5. Adaptive Response and Control: If the triggered warning level is a high-level warning, the parameter optimization instruction matching the current fault type is called from the preset response strategy library. Based on the parameter optimization instruction, the output settings of the DIO module are dynamically adjusted using a feedback control algorithm until the module's operating state returns to stability.

2. The fault early warning and monitoring method for an industrial control computer DIO module according to claim 1, characterized in that, In step S1, the preset fixed period is 50 milliseconds.

3. The fault early warning and monitoring method for an industrial control computer DIO module according to claim 1, characterized in that, In step S2, the anomaly detection algorithm is the isolated forest algorithm; the continuous exceeding of the preset threshold means that the parameter value exceeds the corresponding normal fluctuation range in three consecutive collection cycles.

4. The fault early warning and monitoring method for an industrial control computer DIO module according to claim 1, characterized in that, In step S4, the range of affected devices is obtained by querying a pre-stored system topology relationship, which defines one or more external devices connected to the specific faulty hardware location.

5. A fault early warning and monitoring method for an industrial control computer DIO module according to claim 1, characterized in that, In step S5, calling parameter optimization instructions that match the current fault type from the preset response strategy library includes: using a response matching degree evaluation method for screening; if the matching degree is lower than a preset threshold, using a support vector machine algorithm to classify and learn historical optimization schemes to generate the optimal combination of module parameter values ​​under the current fault scenario.

6. The fault early warning and monitoring method for an industrial control computer DIO module according to claim 1, characterized in that, In step S5, the step of "until the module's operating state returns to stability" includes: dynamically adjusting the output settings of the DIO module using a feedback control algorithm, continuously monitoring the deviation between the operating parameters and the target value, and if the deviation exceeds the stability threshold again, then re-executing the adaptive response and control steps.

7. A fault early warning and monitoring method for an industrial control computer DIO module according to claim 1, characterized in that, After step S4, a data management step is also included: storing all operating parameters collected in S1, potential anomalies and specific signal channels where anomalies occurred as determined in S2, early warning signals of the corresponding level generated in S4, and parameter optimization instructions called in S5 and adjustments to the output settings of the DIO module, and displaying them in the form of dashboards and trend curves.

8. A fault early warning and monitoring method for an industrial control computer DIO module according to claim 7, characterized in that, It also includes a cloud collaboration step: synchronizing the operating parameters collected in S1, the early warning signals generated in S4, and the data stored in the data management step to the cloud server to achieve centralized monitoring and management of multiple industrial control computer DIO modules in a distributed deployment.

9. A fault early warning and monitoring system for an industrial control computer DIO module, used to implement the fault early warning and monitoring method for an industrial control computer DIO module as described in any one of claims 7-8, characterized in that, The system includes: The data acquisition and filtering module is used to acquire multi-dimensional operating parameters of the DIO module at fixed intervals and perform filtering and noise reduction to obtain a purified parameter sequence. An anomaly detection and localization module is used to perform anomaly trend analysis based on the purified parameter sequence in order to determine the specific signal channel where the anomaly occurred and the specific location of the faulty hardware. The risk assessment and early warning module is used to calculate the risk level score based on the specific location of the faulty hardware, the magnitude of the anomaly, and the range of affected equipment, and to generate corresponding graded early warning signals. The adaptive response control module is used to call parameter optimization instructions and adjust the output settings of the DIO module based on the feedback control algorithm when an advanced warning is triggered. The data management and human-computer interaction module is used to store all collected operating parameters, identified potential anomalies and specific signal channels where anomalies occur, generated early warning signals of corresponding levels, as well as parameter optimization instructions and adjustments to the DIO module output settings, and to display them visually.

10. A fault early warning and monitoring system for an industrial control computer DIO module according to claim 9, characterized in that, The system is implemented using a layered architecture, which includes: The hardware adaptation layer is used to automatically identify and connect different types of DIO modules, providing hardware support for data acquisition. The data acquisition layer communicates with the hardware adaptation layer and includes the data acquisition and filtering module, which is used to periodically acquire raw parameters through the hardware adaptation layer. The data processing layer includes the anomaly detection and location module, which is used to clean data, identify early signs of failure, and locate the fault. The early warning decision layer includes the risk assessment and early warning module and the adaptive response control module, which are used to assess risks, decide on the early warning level, and perform parameter adjustments when a high-level early warning is triggered. The user interaction layer includes the data management and human-computer interaction module, which provides a human-computer interaction interface for parameter setting, status display, and early warning information.

Images