Industrial equipment operation and maintenance management method and system driven by intelligent converged terminal

Abstract

The application discloses an intelligent fusion terminal driven industrial equipment operation and maintenance management method and system, relates to the technical field of intelligent communication management, and comprises the following steps: deploying a fusion terminal distribution network, extracting the cognitive vector of each terminal and evaluating the cognitive ability index thereof, extracting the terminal distribution subnetwork of each industrial equipment from the network according to the index; generating a plurality of operation and maintenance control parameter groups based on the subnetwork, and calculating and obtaining a consistency confidence index; when the consistency confidence index is greater than or equal to a preset threshold, the terminal is granted an interactive management right; and if the threshold is lower, the subnetwork is reconstructed and the right is redistributed. The application solves the technical problem that the existing equipment operation and maintenance management method relies on manual monitoring and is difficult to cope with complex and changeable industrial environments, resulting in low equipment collaboration efficiency and insufficient reliability, and achieves the technical effects of dynamic operation and maintenance optimization control and terminal management driven by intelligent fusion terminals, and improved equipment collaboration efficiency and reliability.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent communication management, and particularly relates to an intelligent fusion terminal driven industrial equipment operation and maintenance management method and system. BACKGROUND

[0002] In the field of industrial production, with the continuous growth of equipment complexity and production scale, the traditional operation and maintenance management mode faces many challenges. The existing technology mainly relies on manual inspection and simple sensor monitoring, which is difficult to realize comprehensive perception and real-time monitoring of the running state of the equipment. In addition, when multiple terminals are cooperatively managed, the consistency and reliability of the operation and maintenance parameters are difficult to guarantee, resulting in low operation and maintenance efficiency and untimely fault response. At the same time, unreasonable resource allocation further affects the effectiveness of operation and maintenance management. SUMMARY

[0003] The present application provides an intelligent fusion terminal driven industrial equipment operation and maintenance management method and system, which is used to solve the technical problems that the existing equipment operation and maintenance management method relies on manual monitoring, is difficult to cope with complex and changeable industrial environment, and leads to low equipment coordination efficiency and insufficient reliability.

[0004] In a first aspect, the present application provides an intelligent fusion terminal driven industrial equipment operation and maintenance management method, which comprises: deploying a fusion terminal distribution network, extracting a terminal cognitive vector from each fusion terminal, and evaluating a terminal cognitive ability index; extracting a terminal distribution sub-network of each industrial equipment from the fusion terminal distribution network according to the terminal cognitive ability index; generating a plurality of operation and maintenance control parameter groups of the corresponding industrial equipment category according to the terminal distribution sub-network, performing consistency confidence calculation according to the plurality of operation and maintenance control parameter groups, and obtaining a consistency confidence index; when the consistency confidence index is greater than or equal to a preset confidence index threshold, granting each fusion terminal in the terminal distribution sub-network the interactive management right of the corresponding industrial equipment; when the consistency confidence index is less than the preset confidence index threshold, reconstructing the terminal distribution sub-network, and granting each fusion terminal in the terminal distribution reconstruction sub-network the interactive management right of the corresponding industrial equipment.

[0005] In a second aspect of the present application, an intelligent fusion terminal driven industrial equipment operation and maintenance management system is provided, which comprises: a terminal cognitive vector extraction module, configured to deploy a fusion terminal distribution network, extract a terminal cognitive vector for each fusion terminal, and evaluate a terminal cognitive capability index; a terminal distribution sub-network extraction module, configured to extract a terminal distribution sub-network of each industrial equipment from the fusion terminal distribution network according to the terminal cognitive capability index; a consistency confidence calculation module, configured to generate a plurality of operation and maintenance control parameter groups of a corresponding industrial equipment category according to the terminal distribution sub-network, perform consistency confidence calculation according to the plurality of operation and maintenance control parameter groups, and obtain a consistency confidence index; a management authority granting module, configured to grant each fusion terminal in the terminal distribution sub-network an interactive management authority of the corresponding industrial equipment when the consistency confidence index is greater than or equal to a preset confidence index threshold; and a sub-network reconstruction module, configured to reconstruct the terminal distribution sub-network when the consistency confidence index is less than the preset confidence index threshold, and grant each fusion terminal in the terminal distribution reconstruction sub-network an interactive management authority of the corresponding industrial equipment.

[0006] The one or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0007] The intelligent fusion terminal driven industrial equipment operation and maintenance management method and system provided in the present application relate to the technical field of intelligent communication management, which deploys a fusion terminal distribution network, evaluates a terminal cognitive capability index, extracts a terminal distribution sub-network of each equipment based on the index, generates a plurality of operation and maintenance control parameter groups according to the sub-network, and evaluates a terminal management authority through consistency confidence calculation, and determines whether to grant the authority or reconstruct the sub-network according to a consistency confidence index, thereby realizing intelligent equipment operation and maintenance management, solving the technical problems that the existing equipment operation and maintenance management method relies on manual monitoring and is difficult to cope with complex and changeable industrial environments, resulting in low equipment collaboration efficiency and insufficient reliability, and achieving dynamic operation and maintenance optimization control and terminal management driven by intelligent fusion terminals, and improving the technical effects of equipment collaboration efficiency and reliability. BRIEF DESCRIPTION OF DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0009] Figure 1 The intelligent fusion terminal driven industrial equipment operation and maintenance management method flowchart provided in the embodiments of the present application is shown in the figure.

[0010] Figure 2The intelligent fusion terminal driven industrial equipment operation and maintenance management system structure schematic diagram provided by the embodiment of the application.

[0011] The reference signs are explained as follows: terminal cognition vector extraction module 11, terminal distribution sub-network extraction module 12, consistency confidence calculation module 13, management authority granting module 14, and sub-network reconstruction module 15. DETAILED DESCRIPTION

[0012] The application provides an intelligent fusion terminal driven industrial equipment operation and maintenance management method and system, and aims to solve the technical problems that the existing equipment operation and maintenance management method relies on manual monitoring, is difficult to cope with complex and changeable industrial environments, and leads to low equipment coordination efficiency and insufficient reliability.

[0013] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the application.

[0014] It should be noted that the terms “first”, “second” and the like in the specification and the above drawings of the application are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms “include” and “have” and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules that are not clearly listed or inherent to the process, method, product or device.

[0015] Embodiment one, as shown in the application, an intelligent fusion terminal driven industrial equipment operation and maintenance management method is provided, which comprises the following steps: Figure 1

[0016] P10: deploying a fusion terminal distribution network, performing terminal cognition vector extraction on each fusion terminal, and evaluating terminal cognition capability indexes.

[0017] Further, the step P10 of the embodiment of the application further comprises:

[0018] ​P11: synchronously collect a state perception dataset of each fusion terminal; P12: according to the state perception dataset, extract a terminal cognitive vector of each fusion terminal interacting with the industrial equipment connected by the corresponding communication, including interaction data transmission quality, interaction data processing efficiency, interaction data calculation complexity, and terminal health perception state; P13: according to the extracted terminal cognitive vector, establish a terminal cognitive ability index between each fusion terminal and the industrial equipment connected by the corresponding communication.

[0019] Specifically, by deploying a fusion terminal distribution network, the understanding ability of each fusion terminal to the running state of the industrial equipment is evaluated. The core of this process is to comprehensively analyze the interaction between the fusion terminal and the equipment, so as to quantify the cognitive degree of the equipment running state.

[0020] First, deploy a fusion terminal distribution network in an industrial environment. The fusion terminal distribution network is a network system composed of multiple intelligent fusion terminals, which are distributed around the industrial equipment to collect equipment running data and interact with the equipment. After deployment, enter the key terminal cognitive ability evaluation stage. In order to achieve this goal, it is necessary to synchronously collect a state perception dataset of each fusion terminal. The state perception dataset refers to the various data collected by the fusion terminal during operation about its own state and the interaction process with the industrial equipment, including equipment running parameters, environmental parameters, communication state, etc. By synchronously collecting these data, a comprehensive and real-time data basis can be provided for subsequent terminal cognitive vector extraction.

[0021] After collecting the state-aware data sets, the next step is to extract the terminal cognitive vector of each fusion terminal and the corresponding communication connection with the industrial equipment during the interaction process based on these data sets. The terminal cognitive vector can represent a vector set of multi-dimensional performance characteristics embodied by the fusion terminal during the interaction with the industrial equipment. These performance characteristics include the following key dimensions: interaction data transmission quality, interaction data processing efficiency, interaction data calculation complexity, and terminal health perception state. Among them, the interaction data transmission quality reflects the reliability and stability of data transmission between the fusion terminal and the industrial equipment, for example, by calculating the transmission success rate, retransmission rate, etc. Parameters can evaluate whether there are packet loss, packet error, etc. during data transmission. Interaction data processing efficiency is used to measure the speed and capacity of the fusion terminal in processing the collected data, for example, analyzing the time required for the fusion terminal to process data and the amount of data that can be processed per unit of time. Interaction data calculation complexity reflects the calculation difficulty faced by the fusion terminal when processing interaction data, for example, analyzing the algorithm complexity used by the fusion terminal when executing data processing tasks. The terminal health perception state is used to represent the health status of the fusion terminal itself, including the normal operation of the hardware device, the stability of the software system, etc., for example, by monitoring the readings of the hardware sensors of the fusion terminal and the error logs of the software system, etc. Information.

[0022] By extracting the data of the above four dimensions from the state-aware data set, the terminal cognitive vector of each fusion terminal is formed. This vector can comprehensively reflect the comprehensive performance of the fusion terminal during the interaction with the industrial equipment, and can provide quantitative basis for subsequent terminal cognitive ability evaluation.

[0023] Next, based on the extracted terminal cognitive vector, the terminal cognitive ability index between each fusion terminal and the corresponding industrial equipment is further established. The terminal cognitive ability index is a comprehensive evaluation value that reflects the completeness of the terminal's understanding of the device running state. In order to establish this index, a series of algorithm models can be used to weight and integrate each dimension in the cognitive vector. For example, using weighted average method, machine learning model, etc. to comprehensively analyze and calculate the data of each dimension. For example, different weights can be assigned to the interaction data transmission quality, interaction data processing efficiency, interaction data calculation complexity, and terminal health perception state, and a comprehensive terminal cognitive ability index can be calculated according to these weights and corresponding vector values. The high and low of the index directly reflects the cognitive ability and operation and maintenance ability of the fusion terminal to the device running state in the current industrial environment and device interaction scene.

[0024] Through the above process, the cognitive ability of each fusion terminal can be accurately evaluated, providing decision basis for subsequent industrial equipment operation and maintenance.

[0025] P20: Extracting a terminal distribution sub-network for each industrial device from the converged terminal distribution network according to the terminal cognitive capability index.

[0026] Further, the embodiment step P20 further includes:

[0027] P21: Obtaining a set of industrial devices and identifying a set of converged terminals corresponding to the communication connection of each industrial device; P22: Extracting a set of terminal cognitive capability indexes corresponding to the set of converged terminals; P23: Selecting N converged terminals with terminal cognitive capability indexes greater than a preset terminal cognitive capability index threshold from the set of terminal cognitive capability indexes, and constructing a terminal distribution sub-network for each industrial device based on the N converged terminals.

[0028] It should be understood that according to the terminal cognitive capability index, the terminals corresponding to each device are screened and evaluated, and the terminal distribution sub-network for each industrial device is extracted from the converged terminal distribution network.

[0029] First, a complete set of industrial devices needs to be obtained, which contains all the industrial devices that need to be managed and operated. These devices may be distributed in different production areas, have different functions and operating parameters. Then, for each industrial device, a set of converged terminals connected to it is identified. The key to this step is to determine which converged terminals have a direct communication relationship with each industrial device. For example, through the communication protocol of the device, the network topology structure or the device management system, it can be determined which converged terminals can directly interact with a specific industrial device, ensuring that all terminals related to the device are identified and classified into the corresponding set, forming the candidate terminal set of the industrial device.

[0030] After identifying the set of converged terminals corresponding to each industrial device, the next step is to extract the set of terminal cognitive capability indexes of these converged terminals. The terminal cognitive capability index is an important quantitative index that measures the completeness of the converged terminal's understanding of the industrial device's operating state, as described earlier. It reflects the performance of the converged terminal in multiple dimensions such as data transmission quality, processing efficiency, computational complexity and health perception state. By obtaining these indexes from the converged terminal distribution network, a terminal cognitive capability index value can be generated for each converged terminal, and these values form the terminal cognitive capability index set, providing a quantitative basis for subsequent screening. For example, for a specific industrial device, its corresponding set of converged terminals may contain multiple terminals, each with a corresponding terminal cognitive capability index value, which together form the terminal cognitive capability index set of the device.

[0031] Finally, from the extracted terminal cognitive ability index set, filter out N fusion terminals whose terminal cognitive ability index is greater than the preset terminal cognitive ability index threshold. The preset terminal cognitive ability index threshold is a benchmark value set according to actual application scenarios and operation and maintenance requirements, which is used to ensure that the selected fusion terminals have sufficient cognitive ability to effectively participate in the operation and maintenance management of industrial equipment. For example, if the preset terminal cognitive ability index threshold is 0.8, and assuming that the range of terminal cognitive ability index is 0 to 1, only those fusion terminals whose terminal cognitive ability index is greater than 0.8 will be selected. In this way, it can be ensured that each fusion terminal in the constructed terminal distribution subnetwork can reliably perceive and process the operation data of industrial equipment.

[0032] After filtering out N fusion terminals that meet the conditions, a terminal distribution subnetwork for each industrial equipment is constructed based on these terminals. The key of this step is to organize the filtered fusion terminals into an effective network structure to achieve efficient monitoring and management of industrial equipment. For example, a terminal distribution subnetwork that can respond to changes in device operation status in real time can be constructed by defining the communication path between terminals, data transmission protocol and cooperative working mechanism. This subnetwork will serve as the infrastructure for subsequent operation and maintenance, ensuring that each industrial equipment can receive accurate and efficient operation and maintenance support.

[0033] Through this process, the system can extract terminals that meet the requirements from the vast fusion terminal distribution network according to the cognitive ability index of the terminals, and construct a terminal distribution subnetwork that adapts to each industrial equipment. This process not only improves the intelligence of terminal selection, but also effectively improves the accuracy and efficiency of equipment operation and maintenance.

[0034] P30: According to the terminal distribution subnetwork, simultaneously generate a plurality of operation and maintenance control parameter groups corresponding to the industrial equipment category, perform consistency confidence calculation according to the plurality of operation and maintenance control parameter groups, and obtain a consistency confidence index.

[0035] Further, according to the terminal distribution subnetwork, simultaneously generate a plurality of operation and maintenance control parameter groups corresponding to the industrial equipment category, and the embodiment of the present application step P30 further comprises:

[0036] P31: The terminal distribution sub-network synchronously reads a multi-modal operation monitoring data set of the corresponding industrial equipment through each fusion terminal; P32: determines an operation and maintenance target, analyzes the multi-modal operation monitoring data set at the corresponding fusion terminal to obtain a parameter operation and maintenance control parameter group based on the operation and maintenance target, and obtains a plurality of operation and maintenance control parameter groups; P33: wherein the multi-modal operation monitoring data set is analyzed at the corresponding fusion terminal and is obtained through a target-driven analysis model constructed locally at the fusion terminal, the target-driven analysis model includes a locally downloaded Gaussian regression model, and a target function corresponding to the operation and maintenance target is constructed based on the Gaussian regression model to perform analysis.

[0037] Optionally, a plurality of operation and maintenance control parameter groups are generated simultaneously according to the terminal distribution sub-network, and consistency confidence calculation is performed according to these operation and maintenance control parameter groups, that is, adaptive operation and maintenance control parameter groups are generated according to the actual needs of each industrial equipment and the terminal capability, and through consistency evaluation, it is ensured that these parameter groups can maintain consistent and effective decision support in the equipment operation and maintenance process.

[0038] First, the terminal distribution sub-network synchronously reads a multi-modal operation monitoring data set of the corresponding industrial equipment through each fusion terminal. The multi-modal operation monitoring data set contains a plurality of types of data collected by the fusion terminal from the industrial equipment, including the temperature, pressure, vibration frequency, current and voltage of the equipment, and the image, sound and other non-traditional data of the equipment. By synchronously reading these multi-modal data, the running state of the industrial equipment can be comprehensively understood. For example, a fusion terminal may simultaneously collect temperature sensor data of the equipment and vibration sound signals during equipment operation, and these data collectively constitute the multi-modal operation monitoring data set, providing a rich information base for subsequent operation and maintenance control parameter group generation.

[0039] Next, the operation and maintenance target is determined, such as maximum efficiency, minimum energy consumption, reliability priority, or life balance, etc. Then, according to the determined operation and maintenance target, the multi-modal operation monitoring data set is analyzed, and a plurality of operation and maintenance control parameter groups are generated. Specifically, different analysis methods can be used to extract corresponding features from the data based on the requirements of each target, and control parameters that meet the target are generated. For example, if the operation and maintenance target is maximum efficiency, the fusion terminal will analyze the multi-modal operation monitoring data set, extract parameters related to the efficiency of the equipment, such as the speed and power of the equipment, and generate corresponding operation and maintenance control parameter groups based on these parameters. If the operation and maintenance target is minimum energy consumption, the fusion terminal will focus on energy-related parameters of the equipment, such as current and voltage, and generate operation and maintenance control parameter groups accordingly. In this way, each fusion terminal can generate a plurality of operation and maintenance control parameter groups according to different operation and maintenance targets, and these parameters will serve as the basis for operation and maintenance control, ensuring that the equipment can execute the optimal strategy when achieving a specific operation and maintenance target.

[0040] Exemplarily, in the process of parsing the multi-modal operation monitoring data set by the corresponding fusion terminal, the operation and maintenance control parameter group can be obtained by the target-driven parsing model constructed locally in the fusion terminal. The target-driven parsing model is a tool for extracting key information related to operation and maintenance targets from raw data. In this embodiment, the target-driven parsing model includes a locally downloaded Gaussian regression model. The Gaussian regression model is a regression analysis method based on probability statistics, which can predict the probability distribution of output values according to the input data. In specific operation, the fusion terminal downloads the Gaussian regression model locally, and executes parsing based on the model constructed according to the target function corresponding to the operation and maintenance target.

[0041] Specifically, first, each fusion terminal downloads a pre-trained Gaussian regression model from the central management system or a local server. The model is pre-trained based on historical operation data and expert knowledge, and can effectively perform regression analysis on multi-modal operation monitoring data. The Gaussian regression model is initialized locally in the fusion terminal, including loading model parameters, configuring input and output interfaces, etc. For example, the input interface of the model is configured to receive temperature, pressure, vibration frequency, etc. in the multi-modal operation monitoring data set, and the output interface is configured to generate operation and maintenance control parameters.

[0042] Next, according to specific operation and maintenance targets, such as maximum efficiency, minimum energy consumption, priority reliability, life balance, etc., a target function is constructed locally in the fusion terminal. For example, for the operation and maintenance target of maximum efficiency, the target function can be defined as the ratio of device output power to input energy consumption; for the target of minimum energy consumption, the target function can be defined as the energy consumption index of the device. The construction of the target function needs to combine the actual operation parameters and performance indicators of the device. For example, if the goal is to improve the operating efficiency of the device, the target function can be expressed as the ratio of the output power to the input energy consumption of the device; if the goal is to reduce energy consumption, the target function can be expressed as the product of the current, voltage and running time of the device.

[0043] Then, the multi-modal operation monitoring dataset is input into the corresponding Gaussian regression model. The model predicts the output value corresponding to the input data through regression analysis. For example, input the temperature and pressure data of the equipment, and output the expected energy consumption or efficiency of the equipment in the current state. Then, based on the output value of the Gaussian regression model, the optimization calculation is carried out combined with the objective function. For example, by adjusting the operation parameters of the equipment, the objective function reaches the optimal value. Specifically, gradient descent or other optimization algorithms can be used to adjust the parameters according to the output value of the model until the objective function reaches the preset optimization target, generating a set of operation and maintenance control parameters that can guide the equipment to achieve the best operation and maintenance effect under the current operating state. For example, the generated operation and maintenance control parameter set may include the optimal operating temperature range, pressure threshold, current limit, etc. of the equipment. In this way, the fusion terminal can use the Gaussian regression model and the objective function to analyze the operation and maintenance control parameter set that best meets the specific operation and maintenance target from the multi-modal operation monitoring dataset according to different operation and maintenance targets.

[0044] Next, the system will perform consistency confidence calculation based on these operation and maintenance control parameter sets to evaluate the coordination and consistency between different control parameter sets, so as to ensure that the operation and maintenance control strategies under multiple targets can work in coordination and will not conflict or contradict. The consistency confidence index can provide a quantitative basis for subsequent operation and maintenance decisions, which can help operation and maintenance personnel or the system to select the most suitable scheme from multiple possible control schemes to ensure the optimization of equipment operation.

[0045] Further, according to the consistency confidence calculation of the plurality of operation and maintenance control parameter sets, a consistency confidence index is obtained, and the embodiment P30 of the present application further comprises:

[0046] P34: determining at least one key operation and maintenance control parameter; P35: extracting a plurality of corresponding key operation and maintenance control parameters from the plurality of operation and maintenance control parameter sets according to the key operation and maintenance control parameter; P36: performing normalized parameter vector processing on the plurality of key operation and maintenance control parameters to obtain a plurality of key operation and maintenance control parameter vectors, and performing similarity calculation on the key operation and maintenance control parameter vectors corresponding to each two fusion terminals to construct a similarity matrix; P37: performing consistency confidence calculation by calculating the average similarity of the similarity matrix to obtain a consistency confidence index.

[0047] In a possible embodiment of the present application, the process of consistency confidence calculation according to the plurality of operation and maintenance control parameter sets is further refined to obtain a consistency confidence index, so as to ensure that the generated control strategy has consistency and coordination under multiple operation and maintenance targets.

[0048] Firstly, at least one key operation and maintenance control parameter needs to be determined. The key operation and maintenance control parameter is a core indicator that directly affects the running state and operation and maintenance effect of the industrial equipment, such as the temperature threshold, pressure range, energy consumption indicator, vibration frequency, etc. of the equipment. The purpose of selecting these key operation and maintenance control parameters is to focus on the most important factors in the subsequent calculation, thereby improving the efficiency and accuracy of the calculation. For example, in the operation and maintenance scenario of a motor equipment, the key operation and maintenance control parameters may include the operating temperature, current intensity and rotating speed of the motor.

[0049] Next, according to the determined key operation and maintenance control parameters, a plurality of specific key operation and maintenance control parameter values corresponding to the plurality of operation and maintenance control parameter groups are extracted. The purpose of this step is to extract the key parameters in each operation and maintenance control parameter group in order to simplify the subsequent analysis and focus on the most important factors. For example, if the key operation and maintenance control parameters are the temperature threshold and pressure range of the equipment, the specific values of these two parameters are extracted from each operation and maintenance control parameter group to form a key parameter set. Assuming that each operation and maintenance control parameter group contains multiple parameters such as temperature, pressure, current, etc., only the specific values of the two key parameters of temperature and pressure are retained to form a simplified parameter set.

[0050] Then, the extracted plurality of key operation and maintenance control parameters are subjected to normalized parameter vector processing to obtain a plurality of key operation and maintenance control parameter vectors. Normalization refers to converting all key operation and maintenance control parameters into the same standardized format so that the parameters can be compared on the same dimension. For example, by converting each key parameter value to a value between 0 and 1, a normalized key operation and maintenance control parameter vector can be obtained. For example, the maximum and minimum normalization method can be used, i.e. subtracting the minimum value of the parameter from the parameter value and dividing by the difference between the maximum and minimum values of the parameter. In this way, each operation and maintenance control parameter group corresponds to a key operation and maintenance control parameter vector, and these vectors will be used for subsequent similarity calculation.

[0051] Next, similarity calculation is performed on the key operation and maintenance control parameter vectors corresponding to each pair of fusion terminals to construct a similarity matrix. Similarity calculation can be achieved through various methods, such as calculating the cosine similarity or Euclidean distance between vectors. Cosine similarity measures the similarity between two vectors by calculating the cosine of the angle between them, and the closer the value is to 1, the higher the similarity; while Euclidean distance measures the straight-line distance between two vectors, and the smaller the distance, the higher the similarity. By comparing the similarity between each pair of vectors, a similarity matrix can be obtained, which reflects the similarity between different fusion terminals in terms of key operation and maintenance control parameters. For example, for two fusion terminals A and B, the cosine similarity between their key operation and maintenance control parameter vectors can be calculated and recorded in the corresponding position of the similarity matrix.

[0052] Finally, the consistency confidence index is obtained by calculating the average similarity of the similarity matrix. Each element in the similarity matrix represents the similarity between two fusion terminals, and the entire matrix reflects the coordination of multiple terminals on key operation and maintenance control parameters. Therefore, by calculating the average similarity of the similarity matrix, a comprehensive evaluation index, the consistency confidence index, can be obtained, which reflects the consistency of all fusion terminals on key operation and maintenance control parameters. If the consistency confidence index is high, it means that the operation and maintenance control parameter groups generated by different fusion terminals have high consistency on key parameters, so these parameter groups can be considered reliable and can be used for subsequent operation and maintenance. For example, set the threshold of the consistency confidence index to 0.8, if the calculated consistency confidence index is greater than or equal to 0.8, it is considered that the operation and maintenance control parameter group is reliable, and the corresponding interactive management right can be granted; otherwise, if the consistency confidence index is low, it may mean that there are inconsistent or conflicting control strategies, and the terminal distribution sub-network needs to be reconstructed.

[0053] This process provides data support for subsequent equipment operation and maintenance decisions, ensuring that the system can make stable and consistent operation and maintenance decisions in complex environments, thereby improving the efficiency and reliability of the equipment.

[0054] Further, the step P37 of the embodiment of the present application further includes:

[0055] P37-1: generating a cognitive weight coefficient according to the terminal cognitive ability index corresponding to each fusion terminal; P37-2: introducing the cognitive weight coefficient to perform weighted calculation on the similarity matrix to obtain a weighted similarity matrix, and performing consistency confidence calculation based on the average similarity of the weighted similarity matrix to re-obtain the consistency confidence index.

[0056] Optionally, the similarity matrix can be weighted calculated by introducing the cognitive weight coefficient to further improve the accuracy and pertinence of the consistency confidence calculation.

[0057] First, a cognitive weight coefficient is generated based on the terminal cognitive ability index corresponding to each converged terminal. The terminal cognitive ability index is a crucial quantitative indicator measuring the completeness of the converged terminal's understanding of the industrial equipment's operating status. It reflects the converged terminal's performance across multiple dimensions, including data transmission quality, processing efficiency, computational complexity, and health awareness. To reflect the influence of different terminals in the decision-making process, the system needs to assign a cognitive weight coefficient to each terminal. For example, assuming the terminal cognitive ability index ranges from 0 to 1, a converged terminal with a cognitive ability index of 0.9 might be assigned a higher weight coefficient, such as 0.9, while a terminal with a cognitive ability index of 0.6 might be assigned a lower weight coefficient, such as 0.6. This method of generating weight coefficients ensures that terminals with stronger cognitive abilities contribute more to the results in subsequent calculations, thereby improving the overall accuracy of the calculations.

[0058] Next, a cognitive weight coefficient is introduced to weight the similarity matrix, resulting in a weighted similarity matrix. Specifically, for each element in the similarity matrix (i.e., the similarity value between any two fusion terminals), its corresponding cognitive weight coefficient is multiplied. For example, assuming the similarity value between fusion terminals A and B is 0.8, the cognitive weight coefficient of terminal A is 0.9, and the cognitive weight coefficient of terminal B is 0.7, then the weighted similarity value is 0.8 × (0.9 + 0.7) / 2 = 0.76. In this way, a new weighted similarity matrix is ​​obtained, where each element considers the cognitive ability of the corresponding fusion terminal. This allows the system to adjust the similarity matrix, making the impact of terminals with stronger cognitive abilities more prominent in consistency assessment, thus more accurately reflecting the actual role of terminals in operation and maintenance control.

[0059] Finally, a consistency confidence index is recalculated based on the average similarity of the weighted similarity matrix. Similar to the previous average similarity calculation, the average of all elements in the weighted similarity matrix is ​​calculated to obtain the weighted average similarity. Then, the consistency confidence index is recalculated based on this weighted average similarity. For example, if the weighted average similarity is 0.76, and the consistency confidence index obtained through a certain calculation method (such as standardization) is 0.85, this indicates that the consistency of the operation and maintenance control parameter group has been more accurately assessed after considering the cognitive ability of the converged terminal. If this recalculated consistency confidence index meets the preset threshold requirement, such as being greater than or equal to 0.8, the operation and maintenance control parameter group can be considered to have high reliability and consistency and can be used for subsequent operation and maintenance management; otherwise, further adjustment or optimization of the operation and maintenance control parameter group may be necessary.

[0060] Through these steps, not only the consistency between terminals can be evaluated, but also the cognitive ability of each terminal can be weighted to ensure that terminals with stronger cognitive ability play a more important role in consistency calculation, further improving the coordination and accuracy of overall operation and maintenance decision-making.

[0061] P40: When the consistency confidence index is greater than or equal to the preset confidence index threshold, each fusion terminal in the terminal distribution sub-network is granted the interactive management right of the corresponding industrial equipment.

[0062] Further, the step P40 of the embodiments of the present application further comprises:

[0063] P41: Generate a digital permission token and issue the permission token to each fusion terminal in the terminal distribution sub-network; P42: Execute the operation and maintenance management of the corresponding industrial equipment through any fusion terminal issuing a set of operation and maintenance control parameters.

[0064] Specifically, when the consistency confidence index is greater than or equal to the preset confidence index threshold, it indicates that the fusion terminals in the terminal distribution sub-network have high consistency and reliability in key operation and maintenance control parameters, and the system will decide to grant each fusion terminal in the terminal distribution sub-network the interactive management right of the corresponding industrial equipment. Through this mechanism, only in the case of multi-party coordination and high consistency, the terminal can be allowed to operate and manage the equipment, thereby improving the intelligence and accuracy of equipment operation and maintenance.

[0065] First, a digital permission token is generated. The digital permission token is an electronic certificate used to prove that the fusion terminal has the right to interact with and manage a specific industrial equipment. Such a token can contain device identification, terminal identification, permission scope, validity period, etc. information, and through encryption technology to ensure its security and non-tamperability. In this step, a unique permission token needs to be generated for each fusion terminal to ensure that each fusion terminal only has the right to perform the corresponding operation under certain conditions.

[0066] Next, the generated permission token is issued to each fusion terminal in the terminal distribution sub-network. This process can be completed through a secure communication protocol to ensure the confidentiality and integrity of the token during transmission. For example, the Transport Layer Security (TLS) protocol can be used to encrypt token data, and the secure communication channel between the fusion terminal and the management system is used for transmission. After each fusion terminal receives the permission token, it is stored in the local secure storage area for subsequent operation and maintenance to verify its own authority.

[0067] Then, according to the previously generated operation and maintenance control parameter set, one of the fusion terminals is selected as the initiator, which is responsible for issuing operation commands and performing related operation and maintenance management tasks. The key of this step is to ensure that the fusion terminal can effectively monitor and control the industrial equipment according to the issued operation and maintenance control parameter set. For example, a fusion terminal can monitor the running state of the equipment in real time according to the temperature threshold and pressure range in the operation and maintenance control parameter set, and issue an alarm or automatically adjust the running parameters of the equipment when the parameters exceed the set range. In addition, the fusion terminal can also regularly check and maintain the equipment according to the maintenance period and alarm conditions in the operation and maintenance control parameter set, to ensure the normal operation of the equipment.

[0068] Through the above steps, the fusion terminals in the terminal distribution sub-network can be effectively granted interactive management authority, and these terminals can accurately perform operation and maintenance management on industrial equipment according to the issued operation and maintenance control parameter set. This process not only ensures the security and reliability of authorization through digital permission tokens, but also realizes real-time monitoring and management of equipment through specific operation and maintenance control parameter sets, improving the intelligent level and operation efficiency of the entire industrial equipment operation and maintenance management system.

[0069] Further, the step P42 of the embodiment of the present application further comprises:

[0070] P42-1: reading the permission fusion terminal corresponding to the industrial equipment; P42-2: analyzing according to the real-time task queue of the permission fusion terminal, obtaining a first permission fusion terminal, and performing operation and maintenance management of the corresponding industrial equipment according to the first permission fusion terminal.

[0071] It should be understood that the process of performing operation and maintenance management tasks of industrial equipment by fusion terminals can be further refined, especially how to select appropriate fusion terminals to perform these tasks.

[0072] First, read the permission fusion terminal corresponding to the industrial equipment. The operation of this step is to identify which fusion terminals have the authority to perform operation and maintenance management of the corresponding equipment. Each industrial equipment may interact with multiple fusion terminals, therefore, it is necessary to read the permission information related to the equipment, such as checking whether each terminal meets the authorization conditions according to the previously assigned permission tokens, to determine which terminals have the qualifications to manage and control the equipment. Only those terminals that have sufficient cognitive ability and are authorized after consistency confidence calculation are considered as permission fusion terminals. For example, assuming that the operation and maintenance management authority of industrial equipment A is granted to fusion terminals 1, 2 and 3, the permission tokens of these terminals will explicitly identify their management authority over equipment A. By reading these permission tokens, it can be quickly determined which terminals have the qualifications to perform operation and maintenance tasks.

[0073] Next, the real-time task queue of each permission fusion terminal is analyzed to select a first permission fusion terminal. The real-time task queue refers to the list of tasks that each fusion terminal is currently processing or waiting to process. Each permission fusion terminal can handle multiple tasks simultaneously, and the task queue reflects the execution order and priority of each task. By analyzing these task queues, the current load of each terminal can be evaluated, and a terminal that is most suitable for executing the current operation and maintenance task can be selected. For example, if fusion terminal 1 has multiple high-priority tasks in its task queue, and fusion terminal 2 has a relatively empty task queue, fusion terminal 2 can be selected as the first permission fusion terminal. The basis for selecting the first permission fusion terminal can include the length of the task queue, the priority of the task, the current load of the terminal, etc. For example, a load balancing algorithm can be used to preferentially select the terminal with the shortest task queue and the lowest current load to execute the operation and maintenance task.

[0074] Finally, the operation and maintenance management of the corresponding industrial equipment is performed according to the selected first permission fusion terminal. The first permission fusion terminal will perform specific operation and maintenance management operations on the industrial equipment according to the issued operation and maintenance control parameter set. For example, if the first permission fusion terminal is fusion terminal 2, it will monitor the running state of the equipment in real time according to the temperature threshold, pressure range, etc. in the operation and maintenance control parameter set, and issue an alarm or automatically adjust the running parameters of the equipment when the parameters exceed the set range. In addition, fusion terminal 2 can also perform regular inspection and maintenance of the equipment according to the maintenance period and alarm conditions in the operation and maintenance control parameter set, to ensure the normal operation of the equipment.

[0075] By introducing the analysis and priority sorting of the real-time task queue, the system can more intelligently and flexibly allocate operation and maintenance tasks in complex industrial environments. This method not only ensures the rationality of task allocation, but also improves the overall operation and maintenance efficiency of the system, making device management more refined and efficient.

[0076] P50: When the consistency confidence index is less than the preset confidence index threshold, reconstructing the terminal distribution sub-network, and granting each fusion terminal in the terminal distribution reconstruction sub-network the interactive management permission of the corresponding industrial equipment.

[0077] Further, the step P50 of the embodiments of the present application further includes:

[0078] P51: When the consistency confidence index is less than the preset confidence index threshold, locating an abnormal fusion terminal, the abnormal fusion terminal being a fusion terminal in the terminal distribution sub-network whose consistency deviation is greater than the element deviation threshold; P52: reselecting a reconstruction fusion terminal greater than the preset terminal cognitive ability index threshold from the fusion terminal distribution network; P53: reconstructing the terminal distribution sub-network according to the reconstruction fusion terminal to obtain a terminal distribution reconstruction sub-network.

[0079] Optionally, when the consistency confidence index is less than the preset confidence index threshold, it indicates that there is a large inconsistency in the key operation and maintenance control parameters of the fusion terminal in the terminal distribution sub-network, which may affect the reliability of device operation and maintenance management. In this case, it is necessary to first locate the abnormal fusion terminal. The abnormal fusion terminal refers to a fusion terminal in the terminal distribution sub-network whose consistency deviation is greater than the preset deviation threshold. These terminals may have unstable cognitive ability, poor data transmission quality or other factors, resulting in a large deviation in the management and control of the device. Therefore, it is necessary to locate these abnormal terminals by analyzing the behavior and cognitive ability of the terminal. For example, if the difference between the key parameters of a fusion terminal and the average value of the sub-network exceeds the preset deviation threshold, such as 0.2, the terminal is identified as an abnormal fusion terminal. By locating these abnormal terminals, the terminal objects that need to be adjusted or replaced can be determined.

[0080] Next, a reconstruction fusion terminal greater than the preset terminal cognitive ability index threshold is selected from the fusion terminal distribution network. Specifically, the system will select terminals with strong cognitive ability according to the terminal cognitive ability index generated previously to replace or supplement the abnormal terminals in the current sub-network. For example, if the preset terminal cognitive ability index threshold is 0.8, terminals with a cognitive ability index greater than 0.8 can be selected from the entire network as candidate reconstruction terminals. These terminals perform better in terms of data transmission quality, processing efficiency, computational complexity and health perception state, and can improve the overall performance of the sub-network.

[0081] Finally, the terminal distribution sub-network is reconstructed according to the selected reconstruction fusion terminal, obtaining a terminal distribution reconstruction sub-network. That is, the new reconstruction fusion terminal is added to the sub-network to replace or supplement the original abnormal terminal, and the topology and communication connection of the sub-network are adjusted. For example, if it is found that the consistency deviation of terminal A and terminal B is high after locating the abnormal terminal, two terminals C and D with strong cognitive ability can be selected from the entire network to replace terminals A and B. In this way, the reconstructed sub-network can better meet the consistency requirements, making the management of the device more stable and efficient.

[0082] This process not only identifies the objects that need to be adjusted by locating abnormal terminals, but also optimizes the performance of the sub-network by selecting and replacing terminals, so that the system can dynamically adapt to changes in the industrial environment and ensure that the operation and maintenance management of the device always maintains a high level of intelligence and stability.

[0083] In summary, the embodiments of the present application have at least the following technical effects:

[0084] The application realizes intelligent device operation and maintenance management by evaluating terminal cognitive ability and dynamically adjusting management authority, reduces manual intervention; according to terminal cognitive ability index and consistency confidence calculation, the collaborative management between multiple industrial devices is optimized, and the overall operation and maintenance efficiency is improved; according to the consistency confidence index, the terminal distribution subnetwork structure is adjusted to ensure the efficiency and consistency of the operation and maintenance control strategy; by intelligently calculating the consistency confidence index, the terminal is granted device management authority under appropriate conditions, and the stability and security of the system are improved.

[0085] The technical effects of improving the efficiency and reliability of device collaboration through intelligent fusion terminal driven dynamic operation and maintenance optimization control and terminal management are achieved.

[0086] Embodiment two, based on the same inventive concept as the intelligent fusion terminal driven industrial device operation and maintenance management method in the preceding embodiments, as Figure 2 shown, the application provides an intelligent fusion terminal driven industrial device operation and maintenance management system, and the system and method embodiments in the application embodiment are based on the same inventive concept. Wherein, the system comprises:

[0087] The terminal cognitive vector extraction module 11 is used to deploy a fusion terminal distribution network, extract a terminal cognitive vector from each fusion terminal, and evaluate the terminal cognitive ability index.

[0088] The terminal distribution subnetwork extraction module 12 is used to extract the terminal distribution subnetwork of each industrial device from the fusion terminal distribution network according to the terminal cognitive ability index.

[0089] The consistency confidence calculation module 13 is used to generate multiple operation and maintenance control parameter groups corresponding to the industrial device category according to the terminal distribution subnetwork, perform consistency confidence calculation according to the multiple operation and maintenance control parameter groups, and obtain a consistency confidence index.

[0090] The management authority granting module 14 is used to grant each fusion terminal in the terminal distribution subnetwork the interactive management authority of the corresponding industrial device when the consistency confidence index is greater than or equal to the preset confidence index threshold.

[0091] The subnetwork reconstruction module 15 is used to reconstruct the terminal distribution subnetwork when the consistency confidence index is less than the preset confidence index threshold, and grant each fusion terminal in the terminal distribution reconstruction subnetwork the interactive management authority of the corresponding industrial device.

[0092] Further, the terminal cognitive vector extraction module 11 is also used to perform the following steps:

[0093] Synchronously collecting a state perception data set of each fusion terminal; according to the state perception data set, extracting a terminal cognition vector of each fusion terminal and an industrial equipment corresponding to a communication connection in an interaction process, including interaction data transmission quality, interaction data processing efficiency, interaction data calculation complexity, and terminal health perception state; and establishing a terminal cognition capability index between each fusion terminal and the industrial equipment corresponding to the communication connection according to the extracted terminal cognition vector.

[0094] Further, the terminal distribution subnetwork extraction module 12 is further used to perform the following steps:

[0095] An industrial equipment set is obtained, a fusion terminal set corresponding to a communication connection of each industrial equipment is identified, a terminal cognition capability index set corresponding to the fusion terminal set is extracted, N fusion terminals greater than a preset terminal cognition capability index threshold are selected from the terminal cognition capability index set, and a terminal distribution subnetwork of each industrial equipment is constructed based on the N fusion terminals.

[0096] Further, the consistency confidence calculation module 13 is further used to perform the following steps:

[0097] The terminal distribution subnetwork synchronously reads a multi-modal operation monitoring data set of a corresponding industrial equipment through each fusion terminal; determines an operation and maintenance target, and obtains a plurality of operation and maintenance control parameter groups by analyzing the multi-modal operation monitoring data set corresponding to the fusion terminal to obtain a parameter operation and maintenance control parameter group based on the operation and maintenance target; wherein the multi-modal operation monitoring data set corresponding to the fusion terminal is obtained by a target-driven analysis model constructed locally on the fusion terminal, and the target-driven analysis model includes a locally downloaded Gaussian regression model, and a target function corresponding to the operation and maintenance target is constructed based on the Gaussian regression model to perform analysis.

[0098] Further, the consistency confidence calculation module 13 is further used to perform the following steps:

[0099] At least one key operation and maintenance control parameter is determined; a plurality of key operation and maintenance control parameters corresponding to the key operation and maintenance control parameter are extracted from the plurality of operation and maintenance control parameter groups; the plurality of key operation and maintenance control parameters are subjected to normalized parameter vector processing to obtain a plurality of key operation and maintenance control parameter vectors, similarity calculation is performed on the key operation and maintenance control parameter vectors corresponding to each of the two fusion terminals to construct a similarity matrix; and consistency confidence calculation is performed by calculating the average similarity of the similarity matrix to obtain a consistency confidence index.

[0100] Further, the consistency confidence calculation module 13 is further used to perform the following steps:

[0101] According to the terminal cognitive ability index corresponding to each fusion terminal, a cognitive weight coefficient is generated; the cognitive weight coefficient is introduced to perform weighted calculation on the similarity matrix, a weighted similarity matrix is obtained, consistency confidence calculation is performed based on the average similarity of the consistency confidence weighted similarity matrix, and a consistency confidence index is reacquired.

[0102] Further, the management permission granting module 14 is further used to perform the following steps:

[0103] Among them, including generating a digital permission token, issuing the permission token to each fusion terminal in the terminal distribution sub-network; issuing a set of operation and maintenance control parameters through any fusion terminal to perform operation and maintenance management of the corresponding industrial equipment.

[0104] Further, the management permission granting module 14 is further used to perform the following steps:

[0105] Read the permission fusion terminal of the corresponding industrial equipment; analyze according to the real-time task queue of the permission fusion terminal, acquire the first permission fusion terminal, and perform operation and maintenance management of the corresponding industrial equipment according to the first permission fusion terminal.

[0106] Further, the sub-network reconstruction module 15 is further used to perform the following steps:

[0107] When the consistency confidence index is less than a preset confidence index threshold, an abnormal fusion terminal is located, the abnormal fusion terminal is a fusion terminal in the terminal distribution sub-network whose consistency deviation is greater than an element deviation threshold; a reconstruction fusion terminal greater than the preset terminal cognitive ability index threshold is reselected from the fusion terminal distribution network; the terminal distribution sub-network is reconstructed according to the reconstruction fusion terminal, and a terminal distribution reconstruction sub-network is obtained.

[0108] It should be noted that the above sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the above describes a specific embodiment of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0109] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0110] The specification and drawings are, of course, to be regarded in an illustrative rather than a restrictive sense. It is to be understood that any such modifications, variations, combinations or equivalents that fall within the scope of the application are intended to be embraced herein.

Claims

1. An industrial equipment operation and maintenance management method driven by intelligent converged terminals, characterized in that, The method includes: A distributed network of converged terminals is deployed. By extracting terminal cognitive vectors from each converged terminal, terminal cognitive ability indicators are evaluated, including: Synchronously collect the status awareness dataset of each fusion terminal; Based on the state-aware dataset, extract the terminal cognition vector of each fusion terminal during the interaction process with the corresponding industrial equipment, including the interaction data transmission quality, interaction data processing efficiency, interaction data computation complexity, and terminal health perception status. Based on the extracted terminal cognitive vectors, establish terminal cognitive capability indicators between each fusion terminal and the corresponding communication-connected industrial equipment; Based on the terminal cognitive ability index, extract the terminal distribution sub-network of each industrial device from the fused terminal distribution network; The terminal distribution subnetwork simultaneously generates multiple operation and maintenance control parameter groups corresponding to the industrial equipment category, and performs consistency confidence calculation based on the multiple operation and maintenance control parameter groups to obtain a consistency confidence index. When the consistency confidence index is greater than or equal to a preset confidence index threshold, the corresponding industrial equipment interactive management permission is granted to each converged terminal in the terminal distribution sub-network. When the consistency confidence index is less than a preset confidence index threshold, the terminal distribution subnetwork is reconstructed, and each fusion terminal in the terminal distribution reconstruction subnetwork is granted the corresponding industrial equipment interaction management permission.

2. The method as described in claim 1, characterized in that, The method for extracting the terminal distribution sub-network of each industrial device from the fused terminal distribution network based on the terminal cognitive ability index includes: Acquire a set of industrial equipment and identify the set of converged terminals corresponding to the communication connections of each industrial equipment; Extract the set of terminal cognitive ability indicators corresponding to the fusion terminal set; N fusion terminals with values ​​greater than a preset threshold for terminal cognitive ability indicators are selected from the set of terminal cognitive ability indicators, and a terminal distribution sub-network for each industrial device is constructed based on the N fusion terminals.

3. The method as described in claim 1, characterized in that, The method for simultaneously generating multiple operation and maintenance control parameter groups for corresponding industrial equipment based on the terminal distribution subnetwork includes: The terminal distribution subnetwork synchronously reads the multimodal operation monitoring dataset of the corresponding industrial equipment through each fusion terminal; Determine the operation and maintenance objectives, and parse the multimodal operation monitoring dataset on the corresponding fusion terminal to obtain a set of parameter operation and maintenance control parameters based on the operation and maintenance objectives, thereby obtaining multiple sets of operation and maintenance control parameters; Specifically, the multimodal operation monitoring dataset is obtained by parsing the data on the corresponding fusion terminal through a target-driven parsing model built locally on the fusion terminal. The target-driven parsing model includes a locally downloaded Gaussian regression model, and a target function corresponding to the operation and maintenance target is constructed based on the Gaussian regression model for parsing.

4. The method as described in claim 1, characterized in that, The consistency confidence index is obtained by calculating the consistency confidence based on the multiple operation and maintenance control parameter groups. The method includes: Identify at least one key operation and maintenance control parameter; According to the key operation and maintenance control parameters, extract the corresponding key operation and maintenance control parameters from the multiple operation and maintenance control parameter groups respectively; The multiple key operation and maintenance control parameters are processed into normalized parameter vectors to obtain multiple key operation and maintenance control parameter vectors. A similarity calculation is performed on the key operation and maintenance control parameter vectors corresponding to each pair of fusion terminals to construct a similarity matrix. Consistency confidence index is obtained by calculating the average similarity of the similarity matrix.

5. The method as described in claim 1, characterized in that, When the consistency confidence index is greater than or equal to a preset confidence index threshold, the corresponding industrial equipment interactive management permission is granted to each converged terminal in the terminal distribution sub-network. This includes generating a digital permission token and distributing the permission token to each converged terminal in the terminal distribution subnetwork; A set of operation and maintenance control parameters can be issued from any converged terminal to execute the operation and maintenance management of the corresponding industrial equipment.

6. The method as described in claim 5, characterized in that, The method also includes executing the operation and maintenance management of corresponding industrial equipment by issuing a set of operation and maintenance control parameters through any converged terminal: The terminal integrates permissions to read the corresponding industrial equipment. The real-time task queue of the permission fusion terminal is analyzed to obtain the first permission fusion terminal, and the operation and maintenance management of the corresponding industrial equipment is performed according to the first permission fusion terminal.

7. The method as described in claim 2, characterized in that, When the consistency confidence index is less than a preset confidence index threshold, the terminal distribution subnetwork is reconstructed, the method including: When the consistency confidence index is less than the preset confidence index threshold, an abnormal fusion terminal is located. The abnormal fusion terminal is a fusion terminal in the terminal distribution sub-network whose consistency deviation is greater than the element and the deviation threshold. Re-select reconstructed converged terminals from the converged terminal distribution network that are greater than the preset terminal cognitive ability index threshold; The terminal distribution subnetwork is reconstructed based on the reconstructed fusion terminal to obtain the terminal distribution reconstructed subnetwork.

8. The method as described in claim 4, characterized in that, The method further includes calculating the consistency confidence index by calculating the average similarity of the similarity matrix, and obtaining the consistency confidence index by means of: Generate cognitive weight coefficients based on the terminal cognitive ability indicators corresponding to each converged terminal; The cognitive weight coefficient is introduced to perform a weighted calculation on the similarity matrix to obtain a weighted similarity matrix. Consistency confidence is then calculated based on the average similarity of the consistency confidence weighted similarity matrix to obtain a new consistency confidence index.

9. An industrial equipment operation and maintenance management system driven by intelligent converged terminals, characterized in that, The system includes: The terminal cognitive vector extraction module is used to deploy a converged terminal distribution network. By extracting the terminal cognitive vector of each converged terminal, the terminal cognitive ability index is evaluated. The terminal distribution sub-network extraction module is used to extract the terminal distribution sub-network of each industrial device from the fused terminal distribution network based on the terminal cognitive ability index. The consistency confidence calculation module is used to simultaneously generate multiple operation and maintenance control parameter groups corresponding to the industrial equipment category based on the terminal distribution sub-network, and perform consistency confidence calculation based on the multiple operation and maintenance control parameter groups to obtain a consistency confidence index. The management permission granting module is used to grant each converged terminal in the terminal distribution sub-network the corresponding industrial equipment's interactive management permission when the consistency confidence index is greater than or equal to a preset confidence index threshold. The sub-network reconstruction module is used to reconstruct the terminal distribution sub-network when the consistency confidence index is less than a preset confidence index threshold, and to grant each fusion terminal in the terminal distribution reconstruction sub-network the corresponding industrial equipment's interactive management permissions. The terminal cognitive vector extraction module is also used to perform the following steps: Synchronously collect the status awareness dataset of each fusion terminal; Based on the state-aware dataset, extract the terminal cognition vector of each fusion terminal during the interaction process with the corresponding industrial equipment, including the interaction data transmission quality, interaction data processing efficiency, interaction data computation complexity, and terminal health perception status. Based on the extracted terminal cognition vectors, a terminal cognition capability index is established between each fusion terminal and the corresponding industrial equipment with which it is connected.

Images