Intelligent operation and maintenance method, system and device of industrial data acquisition link and medium

Abstract

The invention relates to the technical field of equipment operation and maintenance, and provides an intelligent operation and maintenance method, system and device for an industrial data acquisition link and a medium, and the method comprises the steps: monitoring a data acquisition state of a data acquisition instrument, determining that the data acquisition instrument is in an offline state when monitoring that the data acquisition instrument does not acquire data within a continuous set time period, and sending the data to a server; the identification information of the data acquisition instruments is added to an offline state data acquisition instrument set; performing hierarchical link association analysis on the offline state data acquisition instrument set in response to meeting a preset analysis triggering condition, and determining fault information; based on the acquisition hierarchy of the fault, calling a diagnosis rule in the knowledge base to perform intelligent diagnosis, and generating a diagnosis result and a processing suggestion; and the diagnosis result and the processing suggestion are sent to the on-site terminal. According to the embodiment, the fault level is positioned through hierarchical link correlation analysis, and the targeted diagnosis result and the processing suggestion are generated in combination with the knowledge base rule, so that the operation and maintenance response efficiency is improved.

Description

Intelligent operation and maintenance methods, systems, devices and media for industrial data acquisition links Technical Field

[0001] This disclosure relates to the field of equipment operation and maintenance technology, and more specifically, to an intelligent operation and maintenance method, system, device, and medium for an industrial data acquisition link. Background Technology

[0002] With the continuous improvement of industrial informatization and intelligentization, energy data acquisition and equipment operation status monitoring have become a key foundation for modern industrial enterprises to achieve refined management, ensure production safety, and optimize energy efficiency. A typical industrial data acquisition system usually consists of field instruments, acquisition equipment, communication links, and network nodes, forming a complete link from physical sensing to data center. In the production environment, these acquisition points are numerous, widely distributed, and have complex network topologies. Failure in any link can lead to the loss or anomaly of critical data, directly affecting real-time control and decision analysis of production status.

[0003] In related technologies, troubleshooting primarily relies on alarm prompts from monitoring platforms and manual experience. When the system detects a data interruption at a particular instrument, it typically only provides isolated alarm messages such as "communication failure" or "data timeout" for that point. Maintenance personnel must rely on their personal experience to troubleshoot from the field instruments upwards, checking the acquisition modules, communication lines, gateway devices, and even network configurations—a tedious and time-consuming process that severely impacts fault recovery efficiency. Furthermore, existing systems lack the ability to systematically model and analyze the hierarchical relationships within the acquisition chain, making it impossible to intelligently infer common cause faults (such as a fault in a specific acquisition device or communication bus) based on the abnormal states of multiple related instruments. Simultaneously, while some systems record historical fault information, they fail to effectively transform it into structured diagnostic knowledge, unable to provide intelligent diagnostic and handling suggestions based on historical experience for current anomalies. This results in maintenance work being highly dependent on personnel skills, making it difficult to accumulate and reuse knowledge. Summary of the Invention

[0004] This disclosure provides at least one intelligent operation and maintenance method, system, device, and medium for industrial data acquisition links. By automatically monitoring the data acquisition status, using hierarchical link correlation analysis to locate the fault level, and combining knowledge base rules to generate targeted diagnostic results and processing suggestions, it achieves rapid identification and processing of data acquisition link faults, thereby improving operation and maintenance response efficiency.

[0005] This disclosure provides an intelligent operation and maintenance method for an industrial data acquisition link, comprising: monitoring the data acquisition status of data acquisition instruments; when it is detected that the data acquisition instrument has not acquired data for a continuously set period of time, determining that the data acquisition instrument is in an offline state, and adding the identification information of the data acquisition instrument to a set of offline data acquisition instruments; in response to meeting a preset analysis trigger condition, performing hierarchical link association analysis on the set of offline data acquisition instruments to determine fault information; wherein, the fault information includes the acquisition level at which the fault occurs; based on the acquisition level at which the fault occurs, calling diagnostic rules in a knowledge base to perform intelligent diagnosis, generating diagnostic results and processing suggestions; and sending the diagnostic results and processing suggestions to a field terminal.

[0006] This disclosure provides an intelligent operation and maintenance system for an industrial data acquisition link, comprising: a data monitoring unit, used to monitor the data acquisition status of data acquisition instruments; when a data acquisition instrument fails to acquire data for a continuously set time period, the unit determines that the data acquisition instrument is offline and adds the identification information of the data acquisition instrument to a set of offline data acquisition instruments; an anomaly detection unit, used to perform hierarchical link association analysis on the set of offline data acquisition instruments in response to the fulfillment of preset analysis trigger conditions, and determine fault information; wherein the fault information includes the acquisition level at which the fault occurs; and an intelligent diagnosis unit, with a built-in knowledge base, used to perform intelligent diagnosis based on the acquisition level at which the fault occurs, by calling the diagnostic rules in the knowledge base, generating diagnostic results and processing suggestions, and sending the diagnostic results and processing suggestions to the field terminal.

[0007] This disclosure provides an intelligent operation and maintenance device for an industrial data acquisition link, comprising: an instrument detection module for monitoring the data acquisition status of data acquisition instruments; when a data acquisition instrument fails to acquire data for a continuously set time period, the module determines that the data acquisition instrument is offline and adds the identification information of the data acquisition instrument to a set of offline data acquisition instruments; a fault analysis module for performing hierarchical link association analysis on the set of offline data acquisition instruments in response to the fulfillment of preset analysis trigger conditions to determine fault information; wherein the fault information includes the acquisition level at which the fault occurs; and a fault diagnosis module for performing intelligent diagnosis based on the acquisition level at which the fault occurs, calling diagnostic rules in a knowledge base, generating diagnostic results and processing suggestions, and sending the diagnostic results and processing suggestions to a field terminal.

[0008] This disclosure provides a computer device, including a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the intelligent operation and maintenance method for the industrial data acquisition link as described in any of the above possible embodiments.

[0009] This disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the intelligent operation and maintenance method for industrial data acquisition links as described in any of the possible embodiments above.

[0010] The intelligent operation and maintenance method, system, device, and medium for industrial data acquisition links provided in this disclosure can effectively narrow down the scope of fault investigation and improve fault diagnosis efficiency by locating the acquisition level of the fault through hierarchical link association analysis; intelligent diagnosis can be performed by calling knowledge base diagnostic rules, and fault diagnosis results and processing suggestions can be generated based on the knowledge system within the knowledge base, thereby improving the quality of fault handling; at the same time, the results and suggestions are sent to the field terminal, so that operation and maintenance personnel can obtain information in a timely manner and carry out maintenance work, reduce equipment downtime, and ensure the stable operation of industrial data acquisition links.

[0011] In this way, this disclosure achieves rapid identification and handling of data acquisition link faults by automatically monitoring the data acquisition status, using hierarchical link correlation analysis to locate the fault level, and combining knowledge base rules to generate targeted diagnostic results and handling suggestions, thereby improving the efficiency of operation and maintenance response.

[0012] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings referenced in the embodiments will be briefly described below. These drawings are incorporated in and constitute a part of this specification. They illustrate embodiments conforming to this disclosure and, together with the specification, serve to explain the technical solutions of this disclosure. It should be understood that the following drawings only show some embodiments of this disclosure and should not be considered as limiting the scope. Those skilled in the art can obtain other related drawings based on these drawings without creative effort.

[0014] Figure 1 shows a flowchart of an intelligent operation and maintenance method for an industrial data acquisition link provided in an embodiment of this disclosure; Figure 2 shows a flowchart of an intelligent diagnosis method provided in an embodiment of this disclosure; Figure 3 shows a flowchart of a knowledge base update and optimization method provided in an embodiment of this disclosure; Figure 4 shows a structural schematic diagram of an intelligent operation and maintenance system for an industrial data acquisition link provided in an embodiment of this disclosure; Figure 5 shows a structural schematic diagram of an intelligent operation and maintenance device for an industrial data acquisition link provided in an embodiment of this disclosure; Figure 6 shows a structural schematic diagram of a computer device provided in an embodiment of this disclosure. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. The components of the embodiments of this disclosure described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0016] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0017] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0018] To facilitate understanding of this embodiment, the executing entity of the intelligent operation and maintenance method for the industrial data acquisition link provided in this disclosure embodiment will first be described in detail. The executing entity of the intelligent operation and maintenance method for the industrial data acquisition link provided in this disclosure embodiment is a computer device. This computer device can be a terminal device or a server. The terminal device can also be a mobile device, a user terminal, a terminal, a handheld device, a computing device, an in-vehicle device, a wearable device, etc. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data, and artificial intelligence platforms. Optionally, this method can also be applied to an implementation environment composed of computer devices and servers.

[0019] The intelligent operation and maintenance method for industrial data acquisition links provided in this application embodiment will be described in detail below with reference to the accompanying drawings. Referring to Figure 1, which is a flowchart of an intelligent operation and maintenance method for industrial data acquisition links provided in this disclosure embodiment, the method includes the following S101~S103: S101, monitoring the data acquisition status of the data acquisition instrument, and when it is detected that the data acquisition instrument has not acquired data within a continuously set time period, determining that the data acquisition instrument is in an offline state, and adding the identification information of the data acquisition instrument to the offline state data acquisition instrument set.

[0020] As we understand it, data acquisition instruments refer to terminal devices installed in industrial sites to collect various physical quantity data during industrial production processes, such as smart meters, temperature sensors, and pressure transmitters. During continuous monitoring, the monitoring content includes whether the instruments return valid data according to preset cycles. If a data acquisition instrument fails to collect data for a continuously set period, for example, if no response is received for three consecutive acquisition cycles (one minute per cycle), it can be determined that the data acquisition instrument has entered an offline state. After determining that a data acquisition instrument is offline, its identification information can be added to the offline data acquisition instrument set. This set is a data structure temporarily stored in memory or a database, specifically used to store records of all instruments currently determined to be offline. The identification information is the smallest set of information that can uniquely identify the instrument, typically including at least the instrument's unique serial number or communication address.

[0021] Here, the continuous setting duration is a pre-set time range that can be set according to the actual needs of industrial production, data acquisition frequency, and network communication conditions. For example, if industrial production has high requirements for data real-time performance and the data acquisition frequency is once every 30 seconds, and the network communication is relatively stable, then the continuous setting duration can be set to 2 minutes (i.e., 4 acquisition cycles). If a certain instrument does not upload data within 2 minutes, it can be determined that the data acquisition instrument is in an offline state.

[0022] S102, in response to the satisfaction of the preset analysis triggering conditions, perform hierarchical link correlation analysis on the offline status data acquisition instrument set to determine fault information.

[0023] Here, when the set of offline data acquisition instruments meets the preset analysis trigger conditions, such as the number of instruments in the set reaching a threshold or the continuous offline time exceeding a set threshold, the hierarchical link correlation analysis process will be automatically triggered.

[0024] Specifically, hierarchical link correlation analysis is an analytical method. Industrial data acquisition links typically have a hierarchical structure, with different levels responsible for different ranges and types of data acquisition and transmission. For example, the bottom layer might be data acquisition instruments directly connected to production equipment, the middle layer might be node devices responsible for initial data aggregation and transmission, and the upper layer might be more advanced data processing and storage devices. Through this hierarchical link correlation analysis, fault information can be identified, including the acquisition level at which the fault occurred, i.e., at which specific level of the data acquisition link.

[0025] This disclosure proposes to pre-construct and maintain a hierarchical topology model comprising four layers: instrument layer, data acquisition device layer, communication link layer, and network node layer, based on actual physical connections and network configurations. This model defines the hierarchical dependencies of data from the acquisition end to the aggregation end and explicitly records the affiliation and connection relationships between various entities. Specifically, the instrument layer consists of data acquisition instruments directly installed in the industrial field for collecting various physical quantity data, serving as the data source; the data acquisition device layer consists of hardware units that directly connect to and manage a group of instruments, such as remote terminal units, serial port servers, or data acquisition gateways, responsible for polling, protocol conversion, and initial caching of data from subordinate instruments; the communication link layer refers to the physical or logical communication channel connecting the acquisition device and its subordinate instruments, such as RS-485 bus, CAN bus, LoRa wireless network, etc., with one communication link carrying data transmission from multiple instruments; and the network node layer consists of network devices that perform data aggregation, routing, and forwarding at a higher level, such as industrial Ethernet switches, routers, or aggregation gateways, with multiple acquisition devices connected to a single network node.

[0026] Based on the aforementioned four-layer topology model, hierarchical link correlation analysis can trace the identification information of each instrument in the offline instrument set back to its associated data acquisition device, communication link, and upper-layer network node. By comparing and inferring the overall operating status of these associated devices, the specific level of the fault can be determined, i.e., the core content of the fault information—the data acquisition level at which the fault occurs. In this way, a fault manifested as "instrument offline" can be located at whether it is an anomaly of a single instrument, an interruption of a communication link, a failure of a data acquisition device, or a failure of an upper-layer network node, thus greatly narrowing the scope of on-site troubleshooting.

[0027] For example, based on the membership and connection relationships defined in the pre-built hierarchical topology model, hierarchical link association analysis can be performed on each data acquisition instrument in the offline status data acquisition instrument set. The specific analysis logic can include the following four main scenarios.

[0028] First, if all data acquisition instruments in the offline data acquisition instrument set belong to the same acquisition device according to model queries, and status checks reveal that all data acquisition instruments under that acquisition device are offline, this means the fault affects all data acquisition instruments associated with the entire acquisition device. In this case, the fault level can be determined to be at the acquisition device level. In this scenario, the problem is likely to originate from the acquisition device itself, such as a power outage, hardware failure, main control module crash, or system software collapse, causing it to completely lose its data acquisition and upload capabilities.

[0029] Second, if all data acquisition instruments in the offline data acquisition instrument set are traced back to a specific communication link under the same acquisition device, and it is confirmed that all data acquisition instruments on that communication link are offline, while data acquisition instruments on other communication links managed by that acquisition device are all online normally, then the acquisition level of the fault can be determined to be at the communication link level. In this scenario, it means that the fault is isolated on a specific downlink communication channel of the acquisition device. Possible causes include a physical open circuit or short circuit on the RS-485 bus, failure of the bus terminating resistor, damage to the communication interface, or continuous and strong electromagnetic interference on the link.

[0030] Third, if the offline data acquisition instrument set contains only a single data acquisition instrument, the fault can be determined to be at the instrument level. This scenario points to an individual problem specific to that instrument, such as a power supply failure, damage to the internal sensing or metering module, loose or oxidized wiring terminals connecting the instrument to the bus, or a malfunction in its built-in communication module.

[0031] Fourth, if the data acquisition instruments in the offline data acquisition instrument set belong to multiple different acquisition devices, and status checks reveal that all data acquisition instruments under each of these acquisition devices are offline, and tracing back according to the pre-established data acquisition topology model confirms that these acquisition devices experiencing a global fault are all connected to the same upper-layer network node (such as an industrial Ethernet switch), then the acquisition layer at which the fault occurs can be determined to be the network node level. In this scenario, the root cause of the fault can be traced back to the network aggregation layer. The failure of this common network node (such as switch downtime, power failure, configuration error, or uplink port interruption) causes the network path of all connected devices below it to be interrupted.

[0032] In this way, through the hierarchical link correlation analysis proposed in this disclosure, and based on logical judgment of topological relationships, scattered instrument offline phenomena can be attributed to root causes at different levels, thereby achieving accurate fault location.

[0033] In some possible embodiments, the aforementioned hierarchical link association analysis can achieve more efficient computation using specific data structures and algorithms. Specifically, when constructing a hierarchical topology model, a graph structure can be used to model the multi-level dependencies between "instruments-acquisition devices-communication links-network nodes." In this graph model, each entity (such as an instrument or device) is a vertex, and the connections between entities are edges. To support fast relationship queries and hierarchical location, the model can simultaneously support two data representation forms: adjacency matrices and association tables. Adjacency matrices can clearly represent the direct connections between any two vertices in matrix form, facilitating rapid connectivity judgment and path query; association tables record the attributes and connection status of each edge in detail in a table structure, facilitating flexible condition filtering and detailed information retrieval. Based on this graph structure model and its supporting matrix or table query mechanism, the complete uplink path of offline instruments can be traced more efficiently, common ancestor nodes can be calculated, and the scope of influence can be determined, thereby achieving rapid calculation of multi-level dependencies and accurate location of fault levels.

[0034] S103, based on the acquisition level of the fault, call the diagnostic rules in the knowledge base to perform intelligent diagnosis, generate diagnostic results and processing suggestions, and send the diagnostic results and processing suggestions to the field terminal.

[0035] Specifically, the knowledge base is a database that pre-stores a large number of rules and experiences related to fault diagnosis in the industrial data acquisition chain. These diagnostic rules are derived from long-term practice and summarization, such as common fault types and corresponding diagnostic methods for a specific level of equipment. By calling these rules for intelligent diagnosis, diagnostic results and handling suggestions can be generated. The diagnostic results are the specific details of the fault, and the handling suggestions are the solutions provided for the fault, such as replacing a component or adjusting equipment parameters. Finally, the diagnostic results and handling suggestions can be sent to field terminals, which can be devices such as computers and mobile phones used by field operators, allowing operators to understand the fault situation in a timely manner and take appropriate measures.

[0036] For example, the knowledge base can store multiple interconnected data tables to structure and organize operational knowledge. These tables can primarily include: an instrument information table, storing basic information such as the unique ID, model, acquisition method, and communication parameters of each data acquisition instrument; an acquisition device table, managing the unique ID, communication interface type, and network segment information of acquisition devices; a link relationship table, recording the topological connections between nodes in the system (such as instruments, devices, and network ports), including the starting node, ending node, and current link status; an anomaly record table, archiving historical anomalies, recording their anomaly type, occurrence time, system diagnostic results, and final adopted solutions, providing a data foundation for subsequent learning; and a rule base table, storing the reasoning rules upon which intelligent diagnosis relies. Each rule includes a rule ID, a set of conditions defining the fault scenario, a result set pointing to conclusions and suggestions, an initial confidence level, and a dynamically adjustable weight value. Simultaneously, the knowledge base supports rapid querying of the above tables based on multi-level indexes such as device ID, link number, and anomaly type, and supports knowledge retrieval and reuse based on the similarity of historical case features, thereby efficiently supporting the diagnostic reasoning and self-learning process.

[0037] Here, the diagnostic rules stored in the knowledge base can be reasoning logic stored in the form of "if (condition) then (conclusion and recommendation)". The condition part can include features such as fault level, environmental parameters, and instrument model, while the conclusion part can include the fault cause, confidence level, and handling recommendations. For example, a diagnostic rule for a communication link-level fault might have the following condition part defined: the fault level is equal to the communication link level, the ambient humidity sensor reading is consistently higher than 80%RH, and the affected instrument model belongs to a specific series. The conclusion part might be defined as: the fault cause is that the 485 bus connector has increased contact resistance or physically disconnected due to oxidation from a continuously humid environment, with an initial confidence level of 0.75. The handling recommendation is to first check the terminal block connector status of all junction boxes or cabinets on this link, clean them with rust remover and retighten them, and simultaneously rectify the cabinet's sealing.

[0038] Specifically, when calling the diagnostic rules in the knowledge base to perform intelligent diagnosis, as shown in Figure 2, the following steps S201~S205 may be included: S201, constructing abnormal scene features based on the fault information.

[0039] Here, the abnormal scenario feature is a digital and structured description of the currently occurring fault event and its surrounding environment, serving as the foundational data unit for subsequent rule matching and reasoning. This feature at least includes the acquisition level of the fault as determined by hierarchical link correlation analysis, such as the instrument level, communication link level, acquisition device level, or network node level.

[0040] In some possible embodiments, this feature can be extended to include richer contextual information, thereby forming a multidimensional feature vector. The extended information may include the specific model and specifications of the affected acquisition device or instrument, the time point when the fault was first detected, the duration of the fault, the real-time and historical performance indicators of the related links or devices (such as signal strength and bit error rate), and the associated topology fragment information determined by the topology model (such as the affected gateway IP address, switch port number, bus identifier, etc.).

[0041] S202, Match at least one fault diagnosis rule related to the abnormal scene features from the knowledge base.

[0042] Specifically, using the constructed abnormal scenario features as input, a query is performed in the rule base table of the knowledge base: each dimension of the feature vector is compared with the condition part defined by each diagnostic rule in the rule base, and all rules whose conditions match all or part of the current features are retrieved. For example, all rules applicable to "communication link level" faults may be retrieved, and rules that mention a specific instrument model or high humidity environment in their conditions may be further filtered out.

[0043] Here, the matching process can employ mechanisms such as exact matching, range matching, or fuzzy matching based on similarity thresholds to ensure that all potentially relevant historical experiences can be recalled, without making specific limitations here.

[0044] S203, for each matching fault diagnosis rule, calculate the matching degree between the abnormal scene feature and the fault diagnosis rule; and calculate the confidence contribution value of the fault diagnosis rule based on the current weight of the fault diagnosis rule and the matching degree.

[0045] Understandably, the matching degree is a quantitative metric, primarily used to measure the degree of agreement between the current actual fault scenario and the typical fault scenario preset by a certain diagnostic rule. Its calculation can be based on a point-by-point comparison of feature vectors. For example, if the fault level and equipment model match perfectly, the matching degree for the corresponding feature item is 1; if the environmental parameters are within the threshold range defined by the current rule, the matching degree can be 0.8; if there are no relevant features, the matching degree may be 0. The matching degrees of each feature can be aggregated into a comprehensive matching degree value between 0 and 1 through weighted averaging or other methods.

[0046] Here, to more accurately evaluate the effectiveness of each diagnostic rule in this diagnosis, each diagnostic rule in the knowledge base also has a current weight dynamically maintained by the knowledge base's self-learning module. This weight reflects the accuracy and reliability of the rule's historical diagnoses, and the weight value is usually between 0 and 1. The confidence contribution value is calculated by multiplying the rule's current weight by its matching degree in the current scenario, i.e.: Confidence Contribution Value = Weight × Matching Degree. This value combines the rule's general credibility (weight) and its specificity for the current case (matching degree), representing the strength of the rule's support for the current diagnostic result. For example, if a rule has a current weight of 0.8 and a matching degree of 0.7 in the current scenario, then its confidence contribution value is 0.8 × 0.7 = 0.56. The higher this value, the stronger the rule's support for the current diagnostic result.

[0047] S204, the diagnosis result with the highest confidence contribution value among all matched fault diagnosis rules is taken as the diagnosis result.

[0048] Specifically, after obtaining the confidence contribution values ​​of all matching fault diagnosis rules, they are compared, and the fault cause pointed to by the rule with the highest confidence contribution value is selected as the final diagnosis result.

[0049] In some other embodiments, when determining the diagnostic results, the same or similar fault causes pointed to by multiple high contribution value rules can be merged, or the probability distribution of multiple possible causes can be calculated with contribution value as weight, and the cause with the highest probability can be output.

[0050] S205, Based on the diagnostic results, retrieve troubleshooting suggestions from the knowledge base.

[0051] Here, handling suggestions are typically included as part of the diagnostic rule conclusion or stored separately in the handling scheme table of the knowledge base and associated with a specific fault cause ID. Based on the finally adopted diagnostic result (i.e., the identified fault cause), a detailed list of handling steps for that fault cause, pre-stored in the knowledge base, can be retrieved by querying the association relationships. These suggestions are specific, actionable work instructions, such as: going to a specific location, using a multimeter to measure the resistance between two points, checking a junction box and re-crimping the connectors, or logging into the management interface of a network device to execute a specific restart command.

[0052] In some possible embodiments, after sending the diagnostic results and processing suggestions to the field terminal, subsequent relevant information can be continuously tracked and collected to further optimize and improve the fault diagnosis process and knowledge base content, and improve the accuracy and effectiveness of subsequent diagnoses. Referring to FIG3, after sending the diagnostic results and processing suggestions to the field terminal, the following steps S301~S302 may be included: S301, receiving feedback information from the field terminal regarding the diagnostic results and processing suggestions.

[0053] Understandably, after completing on-site troubleshooting and handling based on the pushed diagnostic results and handling suggestions, on-site maintenance personnel can send back processing feedback information through their on-site terminals (such as industrial tablets or mobile applications). This feedback information serves as a closed-loop confirmation and solidification of experience throughout the entire diagnostic and handling process. Its content can be structured data, including at least: the manually confirmed actual cause of the fault, the specific handling measures taken, whether the fault was successfully resolved, and the time consumed in the entire handling process. In addition, the feedback information may selectively include an evaluation of the accuracy of the diagnosis, supplementary descriptions of the on-site environment (such as the discovery of water ingress into the cabinet), or new problems encountered during the handling process.

[0054] S302, based on the feedback information, adjust the weights of the fault diagnosis rules related to this diagnosis in the knowledge base, and / or generate or update the fault diagnosis rules based on the feedback information.

[0055] Here, after receiving feedback from the on-site terminal, the diagnostic knowledge involved in this inference can be optimized based on the comparison between the feedback and the diagnostic conclusion. Specifically, the fault diagnosis rules that were invoked and participated in the confidence calculation during this diagnosis process can be used as the target rule set for this learning. If the feedback confirms that the diagnostic result given in this diagnosis is consistent with the actual cause of the fault, it indicates that the relevant diagnostic rules are effective in this scenario, and the weights of these rules can be increased, especially the weights of the rules that lead to the correct conclusion, to strengthen their future influence. For example, this can be achieved by slightly increasing the weight using the formula "new weight = min(original weight + α, 1.0)", where α is a small positive learning rate (e.g., 0.02). Increasing the weight allows the rule to have a higher confidence contribution value in similar scenarios in the future, thus making it more likely to be adopted. Conversely, if the diagnosis given in this diagnosis does not match the actual cause confirmed on site, it indicates that the rule in the target rule set that led to the wrong conclusion has been misjudged in this scenario. Its weight can be reduced to weaken its potential misleading impact in the future. The weight reduction can be achieved by the formula "new weight = max(original weight – β, 0)", where β is another learning rate parameter.

[0056] In some possible implementations, knowledge discovery and rule base expansion can also be performed based on feedback information. Specifically, when a certain number of recurring faults with the same (or highly similar) abnormal scenario characteristics are detected, and the actual fault causes confirmed by on-site feedback all point to the same conclusion, even if there may not be a readily available perfect matching rule in the knowledge base, the common features and solutions of these cases can be extracted to generate a new, more accurate fault diagnosis rule, which can then be added to the knowledge base. Simultaneously, for existing rules, the condition or suggestion parts of the rules can be refined and updated based on more specific fault descriptions (such as "connector oxidation" rather than the general "physical disconnection") or better processing steps in the feedback information, making them more targeted and instructive.

[0057] In this way, through the aforementioned feedback-based dynamic weight adjustment and rule iteration mechanism, the reliability and accuracy of its internal knowledge model (i.e., knowledge base) can be continuously and adaptively optimized. The diagnostic reasoning process can continuously improve itself with the accumulation of operational practices, gradually enhancing the accuracy and efficiency of future diagnoses.

[0058] The intelligent operation and maintenance method for the industrial data acquisition link proposed in this solution will be described in detail below with reference to a specific embodiment. Taking the energy monitoring system of a large food processing enterprise as an application scenario, this system deploys over 600 smart meters as data acquisition instruments. These meters are connected to 12 serial port servers via RS-485 bus, and then connected to the enterprise network via 6 wired acquisition gateways. Finally, the data is aggregated to the data center server, forming a four-layer topology structure with an instrument layer, an acquisition device layer, a communication link layer, and a network node layer. The system is preset to collect data once per minute. If an instrument does not return data for three consecutive minutes, it is considered offline, and an anomaly analysis process is triggered.

[0059] During a certain operation, at 09:25:30 on August 15, 2023, the system detected that six electricity meters (D201-D206) in Production Workshop 2 were simultaneously offline. A topology check revealed that all six meters were connected to the RS-485 bus belonging to port 1 (port 5001) of serial server S3. The system then initiated a hierarchical link correlation analysis: first, a data acquisition device-level analysis was performed, revealing that all meters under that port were offline; second, a link-level analysis was performed, confirming that meters under other ports of the same serial server were online; finally, an instrument-level analysis was performed, ruling out the possibility of a single meter failure. Based on this, the fault level can be determined to be the communication link layer, and the likely cause is an anomaly in the RS-485 bus.

[0060] Subsequently, the knowledge base is invoked for intelligent diagnosis: the knowledge base matches four relevant diagnostic rules, including "physical disconnection of the 485 bus" and "serial server port failure," etc. Based on the pre-set confidence level of each rule and the dynamic weight determined by historical performance, a weighted calculation is used to obtain the comprehensive diagnostic confidence level. The calculation results show that "physical disconnection of the 485 bus" is the most likely cause (confidence level 66%). This allows for the generation of diagnostic results and specific handling suggestions, such as checking physical connections and testing terminating resistors, and automatically generates a repair work order which is pushed to the terminal of field engineer Zhang San.

[0061] Following the work order instructions, on-site engineer Zhang San located the power distribution cabinet where the serial server S3 was located for inspection. He found that the 485 bus connectors were oxidized and corroded due to the humid environment, resulting in poor physical contact. After Zhang San re-crimped the wiring, the data acquisition of all six meters returned to normal. At the same time, Zhang San fed back the processing results (the actual cause was "corrosion of the bus connectors leading to physical disconnection") to the system through the on-site terminal.

[0062] Furthermore, upon receiving feedback, a self-learning mechanism can be initiated: Since the diagnosis was correct, the weight of the corresponding diagnostic rule (Rule 1) in the knowledge base is increased; simultaneously, based on the new feature combination of "humid environment" and "joint corrosion" (if it occurs multiple times), a new diagnostic rule (RULE-156) can be automatically extracted and generated. Its conditions include "humid environment" and "joint location," and its conclusion prioritizes checking joint corrosion. This new rule and its updated weight are stored in the knowledge base to optimize future diagnostic reasoning. Thus, this embodiment fully demonstrates the closed-loop operation and maintenance process from anomaly detection, hierarchical location, intelligent diagnosis, on-site repair to knowledge self-learning.

[0063] The intelligent operation and maintenance method, system, device, and medium for industrial data acquisition links provided in this disclosure improves operation and maintenance response efficiency by automatically monitoring the data acquisition status, using hierarchical link correlation analysis to locate the fault level, and combining knowledge base rules to generate targeted diagnostic results and processing suggestions.

[0064] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0065] Based on the same inventive concept, this disclosure also provides an intelligent operation and maintenance system for an industrial data acquisition link, which corresponds to the intelligent operation and maintenance method for the industrial data acquisition link. Since the principle of the system in this disclosure for solving problems is similar to the intelligent operation and maintenance method for the industrial data acquisition link described above, the implementation of the system can refer to the implementation of the method, and the repeated parts will not be described again.

[0066] Referring to Figure 4, which is a schematic diagram of an intelligent operation and maintenance system for an industrial data acquisition link provided in an embodiment of this disclosure, the system includes: a data monitoring unit, used to monitor the data acquisition status of data acquisition instruments; when it is detected that a data acquisition instrument has not acquired data for a continuously set period of time, it determines that the data acquisition instrument is offline and adds the identification information of the data acquisition instrument to the set of offline data acquisition instruments; an anomaly detection unit, used to perform hierarchical link association analysis on the set of offline data acquisition instruments in response to the satisfaction of preset analysis trigger conditions, and determine fault information; wherein, the fault information includes the acquisition level at which the fault occurs; and an intelligent diagnosis unit, with a built-in knowledge base, used to perform intelligent diagnosis based on the acquisition level at which the fault occurs, by calling the diagnostic rules in the knowledge base, generating diagnostic results and processing suggestions, and sending the diagnostic results and processing suggestions to the field terminal.

[0067] In some possible embodiments, the anomaly detection unit is specifically used for: if all data acquisition instruments in the offline data acquisition instrument set belong to the same acquisition device, and all data acquisition instruments under the acquisition device are offline, then the acquisition level of the fault is determined to be at the acquisition device level; if all data acquisition instruments in the offline data acquisition instrument set belong to the same communication link, and all data acquisition instruments on the communication link are offline, while other data acquisition instruments under the acquisition device corresponding to the communication link are in normal condition, then the acquisition level of the fault is determined to be at the communication link level; if the offline data acquisition instrument set contains only a single data acquisition instrument, then the acquisition level of the fault is determined to be at the instrument level; if each data acquisition instrument in the offline data acquisition instrument set belongs to multiple different acquisition devices, and all data acquisition instruments under the multiple different acquisition devices are offline, and it is determined according to a pre-established data acquisition topology model that the multiple different acquisition devices are connected to the same network node, then the acquisition level of the fault is determined to be at the network node level.

[0068] In some possible embodiments, the intelligent diagnostic unit is specifically used for: constructing abnormal scene features based on the fault information; wherein the abnormal scene features include at least the acquisition level at which the fault is located; matching at least one fault diagnosis rule related to the abnormal scene features from the knowledge base; calculating the matching degree between the abnormal scene features and the fault diagnosis rule for each matched fault diagnosis rule; calculating the confidence contribution value of the fault diagnosis rule based on the current weight of the fault diagnosis rule and the matching degree; taking the diagnosis result with the highest confidence contribution value among all matched fault diagnosis rules as the diagnosis result; and retrieving fault handling suggestions from the knowledge base based on the diagnosis result.

[0069] In some possible embodiments, the intelligent diagnostic unit is further configured to: receive feedback information from the field terminal regarding the diagnostic results and processing suggestions; adjust the weights of fault diagnosis rules related to the current diagnosis in the knowledge base based on the feedback information; and / or generate or update fault diagnosis rules based on the feedback information.

[0070] In some possible embodiments, the intelligent diagnostic unit is further configured to: increase the weight of the fault diagnosis rule corresponding to the diagnostic result if the diagnostic result is consistent with the actual fault cause confirmed in the feedback information; and decrease the weight of the fault diagnosis rule corresponding to the diagnostic result if the diagnostic result is inconsistent with the actual fault cause confirmed in the feedback information.

[0071] In some possible embodiments, the intelligent diagnostic unit is further configured to: when a fault with the same abnormal scenario characteristics occurs repeatedly to a preset number of times, and the fault cause is the same as the actual fault cause confirmed by the field terminal in the feedback information corresponding to the fault, generate a new fault diagnosis rule based on the abnormal scenario characteristics and the actual fault cause, and store it in the knowledge base.

[0072] Based on the same inventive concept, this disclosure also provides an intelligent operation and maintenance device for an industrial data acquisition link, which corresponds to the intelligent operation and maintenance method for the industrial data acquisition link. Since the principle of the device in this disclosure for solving the problem is similar to the intelligent operation and maintenance method for the industrial data acquisition link described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0073] Referring to Figure 5, which is a schematic diagram of an intelligent operation and maintenance device 500 for an industrial data acquisition link provided in an embodiment of this disclosure, the device includes: an instrument detection module 501, used to monitor the data acquisition status of data acquisition instruments; when it is detected that a data acquisition instrument has not acquired data for a continuously set period of time, it determines that the data acquisition instrument is offline and adds the identification information of the data acquisition instrument to the set of offline data acquisition instruments; a fault analysis module 502, used to perform hierarchical link association analysis on the set of offline data acquisition instruments in response to the satisfaction of preset analysis trigger conditions, and determine fault information; wherein, the fault information includes the acquisition level at which the fault occurs; and a fault diagnosis module 503, used to perform intelligent diagnosis based on the acquisition level at which the fault occurs, by calling diagnostic rules in the knowledge base, generating diagnostic results and processing suggestions; and sending the diagnostic results and processing suggestions to the field terminal.

[0074] In some possible embodiments, the fault analysis module 502 is specifically used for: if each data acquisition instrument in the offline data acquisition instrument set belongs to the same acquisition device, and all data acquisition instruments under the acquisition device are offline, then the acquisition level of the fault is determined to be at the acquisition device level; if each data acquisition instrument in the offline data acquisition instrument set belongs to the same communication link, and all data acquisition instruments on the communication link are offline, while other data acquisition instruments under the acquisition device corresponding to the communication link are in normal condition, then the acquisition level of the fault is determined to be at the communication link level; if the offline data acquisition instrument set contains only a single data acquisition instrument, then the acquisition level of the fault is determined to be at the instrument level; if each data acquisition instrument in the offline data acquisition instrument set belongs to multiple different acquisition devices, and all data acquisition instruments under the multiple different acquisition devices are offline, and it is determined according to the pre-established data acquisition topology model that the multiple different acquisition devices are connected to the same network node, then the acquisition level of the fault is determined to be at the network node level.

[0075] In some possible embodiments, the fault diagnosis module 503 is specifically used for: constructing abnormal scene features based on the fault information; wherein the abnormal scene features include at least the acquisition level at which the fault is located; matching at least one fault diagnosis rule related to the abnormal scene features from the knowledge base; calculating the matching degree between the abnormal scene features and the fault diagnosis rule for each matched fault diagnosis rule; calculating the confidence contribution value of the fault diagnosis rule based on the current weight of the fault diagnosis rule and the matching degree; taking the diagnosis result with the highest confidence contribution value among all matched fault diagnosis rules as the diagnosis result; and retrieving fault handling suggestions from the knowledge base based on the diagnosis result.

[0076] In some possible embodiments, the fault diagnosis module 503 is further configured to: receive feedback information from the field terminal regarding the diagnosis results and processing suggestions; adjust the weights of fault diagnosis rules related to the current diagnosis in the knowledge base according to the feedback information; and / or generate or update fault diagnosis rules according to the feedback information.

[0077] In some possible embodiments, the fault diagnosis module 503 is further configured to: if the diagnosis result is consistent with the actual fault cause confirmed in the feedback information, increase the weight of the fault diagnosis rule corresponding to the diagnosis result; if the diagnosis result is inconsistent with the actual fault cause confirmed in the feedback information, decrease the weight of the fault diagnosis rule corresponding to the diagnosis result.

[0078] In some possible embodiments, the fault diagnosis module 503 is further configured to: when a fault with the same abnormal scenario characteristics occurs repeatedly to a preset number of times, and the fault cause is the same as the actual fault cause confirmed by the field terminal in the feedback information corresponding to the fault, generate a new fault diagnosis rule based on the abnormal scenario characteristics and the actual fault cause and store it in the knowledge base.

[0079] Based on the same technical concept, this disclosure also provides a computer device. Referring to FIG6, which is a schematic diagram of the structure of the computer device 600 provided in this disclosure embodiment, it includes a processor 601, a memory 602, and a bus 603. The memory 602 is used to store execution instructions and includes a main memory 6021 and an external memory 6022; the main memory 6021, also called internal memory, is used to temporarily store the computational data in the processor 601, as well as the data exchanged with external memory 6022 such as a hard disk. The processor 601 exchanges data with the external memory 6022 through the main memory 6021.

[0080] In this embodiment, the memory 602 is specifically used to store application code that executes the solution of this application, and its execution is controlled by the processor 601. That is, when the computer device 600 is running, the processor 601 communicates with the memory 602 through the bus 603, so that the processor 601 executes the application code stored in the memory 602, and then executes the method described in any of the foregoing embodiments.

[0081] The memory 602 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0082] Processor 601 may be an integrated circuit chip with signal processing capabilities. The aforementioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor.

[0083] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the computer device 600. In other embodiments of this application, the computer device 600 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0084] This disclosure also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program performs the steps of the intelligent operation and maintenance method for the industrial data acquisition link described in the above method embodiments. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0085] This disclosure also provides a computer program product carrying program code. The program code includes instructions that can be used to execute the steps of the intelligent operation and maintenance method for the industrial data acquisition link described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0086] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0087] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this disclosure, it should be understood that the disclosed systems and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0088] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0089] In addition, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0090] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0091] Finally, it should be noted that the above-described embodiments are merely specific implementations of this disclosure, used to illustrate the technical solutions of this disclosure, and not to limit it. The protection scope of this disclosure is not limited thereto. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this disclosure. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be covered within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the protection scope of the claims.

Claims

1. A method for intelligent operation and maintenance of an industrial data acquisition link, characterized in that, include: The system monitors the data acquisition status of the data acquisition instrument. When it is detected that the data acquisition instrument has not acquired any data within a continuously set time period, it determines that the data acquisition instrument is in an offline state and adds the identification information of the data acquisition instrument to the set of offline data acquisition instruments. In response to the fulfillment of preset analysis trigger conditions, a hierarchical link association analysis is performed on the offline status data acquisition instrument set to determine fault information; wherein, the fault information includes the acquisition level at which the fault is located; based on the acquisition level at which the fault is located, diagnostic rules in the knowledge base are invoked to perform intelligent diagnosis, generate diagnostic results and processing suggestions; and the diagnostic results and processing suggestions are sent to the field terminal.

2. The method according to claim 1, characterized in that, The hierarchical link association analysis of the offline data acquisition instrument set includes: if all data acquisition instruments in the offline data acquisition instrument set belong to the same acquisition device, and all data acquisition instruments under the acquisition device are offline, then the acquisition level of the fault is determined to be the acquisition device level; if all data acquisition instruments in the offline data acquisition instrument set belong to the same communication link, and all data acquisition instruments on the communication link are offline, while other data acquisition instruments under the acquisition device corresponding to the communication link are in normal condition, then the acquisition level of the fault is determined to be the communication link level; if the offline data acquisition instrument set contains only a single data acquisition instrument, then the acquisition level of the fault is determined to be the instrument level; if each data acquisition instrument in the offline data acquisition instrument set belongs to multiple different acquisition devices, and all data acquisition instruments under the multiple different acquisition devices are offline, and the multiple different acquisition devices are connected to the same network node according to a pre-established data acquisition topology model, then the acquisition level of the fault is determined to be the network node level.

3. The method according to claim 1, characterized in that, The step of intelligent diagnosis based on the acquisition level of the fault and calling diagnostic rules in the knowledge base includes: constructing abnormal scene features based on the fault information; wherein the abnormal scene features include at least the acquisition level of the fault; matching at least one fault diagnosis rule related to the abnormal scene features from the knowledge base; calculating the matching degree between the abnormal scene features and the fault diagnosis rule for each matched fault diagnosis rule; calculating the confidence contribution value of the fault diagnosis rule based on the current weight of the fault diagnosis rule and the matching degree; taking the diagnosis result with the highest confidence contribution value among all matched fault diagnosis rules as the diagnosis result; and retrieving fault handling suggestions from the knowledge base based on the diagnosis result.

4. The method according to claim 3, characterized in that, After sending the diagnostic results and processing suggestions to the field terminal, the process includes: receiving feedback information from the field terminal regarding the diagnostic results and processing suggestions; adjusting the weights of fault diagnosis rules related to this diagnosis in the knowledge base based on the feedback information; and / or generating or updating fault diagnosis rules based on the feedback information.

5. The method according to claim 4, characterized in that, The step of adjusting the weights of fault diagnosis rules related to this diagnosis in the knowledge base based on the feedback information includes: if the diagnosis result is consistent with the actual fault cause confirmed in the feedback information, then the weight of the fault diagnosis rule corresponding to the diagnosis result is increased; if the diagnosis result is inconsistent with the actual fault cause confirmed in the feedback information, then the weight of the fault diagnosis rule corresponding to the diagnosis result is decreased.

6. The method according to claim 4, characterized in that, The step of generating or updating fault diagnosis rules based on the feedback information includes: when a fault with the same abnormal scenario characteristics occurs repeatedly to a preset number of times, and the fault cause is the same as the actual fault cause confirmed by the field terminal in the feedback information corresponding to the fault, a new fault diagnosis rule is generated based on the abnormal scenario characteristics and the actual fault cause and stored in the knowledge base.

7. An intelligent operation and maintenance system for an industrial data acquisition link, characterized in that, include: The data monitoring unit is used to monitor the data acquisition status of the data acquisition instrument. When it is detected that the data acquisition instrument has not acquired data within a continuously set time period, it determines that the data acquisition instrument is offline and adds the identification information of the data acquisition instrument to the offline data acquisition instrument set. An anomaly detection unit is used to perform hierarchical link correlation analysis on the offline status data acquisition instrument set in response to the fulfillment of preset analysis trigger conditions, and to determine fault information; wherein, the fault information includes the acquisition level at which the fault occurs; The intelligent diagnostic unit has a built-in knowledge base, which is used to perform intelligent diagnosis based on the acquisition level of the fault, call the diagnostic rules in the knowledge base, generate diagnostic results and processing suggestions, and send the diagnostic results and processing suggestions to the field terminal.

8. An intelligent operation and maintenance device for an industrial data acquisition link, characterized in that, include: The instrument detection module is used to monitor the data acquisition status of the data acquisition instrument. When it is detected that the data acquisition instrument has not acquired data within a continuously set time period, it determines that the data acquisition instrument is offline and adds the identification information of the data acquisition instrument to the offline data acquisition instrument set. The fault analysis module is used to perform hierarchical link association analysis on the offline status data acquisition instrument set in response to the fulfillment of preset analysis trigger conditions, and determine fault information; wherein, the fault information includes the acquisition level at which the fault is located; the fault diagnosis module is used to perform intelligent diagnosis based on the acquisition level at which the fault is located, by calling the diagnostic rules in the knowledge base, generating diagnostic results and processing suggestions; and sending the diagnostic results and processing suggestions to the field terminal.

9. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

10. A computer device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 6.

Images