Intensive equipment data acquisition management and control optimization method, system and equipment and storage medium

Abstract

The invention discloses an intensive equipment data acquisition management and control optimization method, system and equipment and a storage medium, and relates to the technical field of industrial automation equipment management.The method comprises the steps that a tagged data link is constructed based on a unified coding system, a standardized data set is constructed, and a universal equipment model is constructed through the standardized data set hierarchy; customizing the working condition of the management equipment; performing real-time data trend identification and automatic working condition judgment through data identification of a polynomial data trend according to the characteristic quantity in the equipment file in combination with the state identification information of the domain model generation equipment; related business objects are automatically generated according to preset business rules, management and control optimization operation is executed in a linkage mode, and potential fault points are recognized in advance in combination with the reliability analysis technology of the deep neural network; according to the method, the intelligence and automation level of equipment management is improved, manual intervention is reduced, and the safety, accuracy and high efficiency of equipment operation are ensured.

Description

Technical Field

[0001] This invention relates to the field of industrial automation equipment management technology, specifically to an intensive method, system, equipment, and storage medium for optimizing equipment data acquisition, control, and management. Background Technology

[0002] As industrial production scale expands and equipment structure becomes more complex, equipment management systems continue to evolve. They are gradually shifting from a crude approach that relies on manual inspections and offline recording to a digital model that combines multi-source sensing, fusion processing, and online monitoring. Different equipment operating parameters, structural parameters, and environmental parameters are aggregated in real time through sensors, field acquisition terminals, and monitoring platforms, thus establishing a close link between equipment operating status and the production process.

[0003] With the development of information technology, data analysis technology, and communication technology, the scope of equipment data collection is expanding and the granularity of collection is becoming increasingly refined, exhibiting multi-dimensional, high-frequency, and continuous characteristics. Equipment operation records, maintenance history, technical parameters, and fault diagnosis information are continuously accumulating, providing conditions for building a data system covering the entire lifecycle. Equipment operation behavior is showing quantifiable and traceable characteristics, promoting the transformation of operation and maintenance management models towards data-driven directions. The industry is increasingly emphasizing equipment status expression methods, feature extraction methods, archive structure construction logic, and business linkage design, enabling various data objects to be associated according to established conventions to form a scalable information framework.

[0004] The existing equipment data system still has significant shortcomings. Differences in data sources lead to inconsistent formats, inconsistent field definitions, and inconsistent time bases, making data integration processes prone to omissions or contradictions. Equipment information has not fully formed a standardized system in terms of structured expression, hierarchical association, static attribute collection, and dynamic record updates, resulting in unclear data mapping relationships between sites, units, and components. When integrating operating parameters, historical fault records, and inspection records across sources, issues such as missing data, outliers, and time sequence misalignments easily occur, hindering the formation of stable data links. Equipment status quantification methods still generally rely on single parameters or single events, lacking the ability to jointly represent operating data with historical and structural information, which is detrimental to expressing the complexity of equipment status. The correlation between the data system and operation and maintenance processes is low, the business triggering mechanism lacks unified logic, and the maintenance cycle, inspection tasks, fault handling processes, and data are loosely linked, making it difficult to form a continuously updated business link. Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by this invention is that existing equipment health assessment methods are relatively simple, mainly based on local parameters and historical data of the equipment, lacking the ability to comprehensively consider multiple factors, resulting in low accuracy of equipment status analysis; the task scheduling methods for equipment maintenance and production scheduling are relatively fixed, lacking intelligent optimization methods, leading to low flexibility in production scheduling and low efficiency in equipment maintenance. The problem is how to improve the efficiency and accuracy of equipment management through standardized collection, real-time analysis and intelligent task scheduling mechanisms of multi-source data.

[0007] To address the aforementioned technical problems, this invention provides the following technical solution: a method for optimizing and managing centralized equipment data acquisition, including constructing a tagged data link based on a unified coding system to generate a standardized dataset; based on the standardized dataset, associating static and dynamic data in multiple dimensions to form an equipment file; generating equipment status identification information based on the feature quantities in the equipment file and combining it with a domain model; automatically generating relevant business objects according to preset business rules; and executing management and optimization operations in a coordinated manner; the business rules include automatically generating and scheduling periodic maintenance, repair work orders, and downtime tasks based on the equipment's health status and operating cycle; and automatically triggering the corresponding workflow when the equipment reaches a preset maintenance cycle or experiences a fault.

[0008] As a preferred embodiment of the intensive equipment data acquisition and management optimization method described in this invention, the standardized dataset includes data from different equipment information sources that are tagged based on a unified coding system; the different equipment information sources include SCADA, real-time monitoring equipment, and manually input data; the tagging process includes assigning a unique identifier, equipment number, site number, and timestamp to each data record, mapping data fields, adjusting the data source to the same fields and format, and performing quality verification; the quality verification includes verifying data missingness, outlier detection, and time consistency detection; verifying data missingness includes automatically identifying missing values ​​in the data based on the field mapping in the standardized dataset, and marking and filling in the missing data based on the average value, interpolation method, and regression model; outlier detection includes identifying extreme values ​​in the data using statistical methods and machine learning models, and marking outliers that deviate from the normal range by comparing them with the deviation from the normal data range; the time consistency detection includes automatically checking the time interval of data that conforms to the expected pattern by comparing the sorting and periodic verification of timestamps in the equipment data.

[0009] As a preferred embodiment of the intensive equipment data acquisition, management, and optimization method described in this invention, the feature quantities include: equipment operating parameters and historical fault records extracted from equipment files and real-time monitoring data, describing the equipment's operating status, health status, and fault risk index; comparative analysis of real-time monitoring and historical data of equipment operating parameters to obtain equipment health and efficiency loss; in-depth analysis of feature quantities using a domain model; and generation of equipment status identification information by comparing feature quantities of normal operating status and abnormal status; the fault risk index is expressed as: , in, This represents the equipment failure risk index; a higher value indicates a greater likelihood of equipment failure. Indicates the fault type Weighting factors Indicates the fault type At any moment The measured value, Indicates the type of obstacle The maximum allowable value, The weighting factor represents the historical fault records. This indicates the degree of damage recorded in the equipment's historical fault records. The total number of fault types; equipment health status, expressed as: , in, This indicates the health status of the device; the device is constantly... Overall health status This indicates the total number of equipment operating parameters. Indicates equipment operating parameters Weighting factors Indicates equipment operating parameters At any moment The actual measured value, Indicates equipment operating parameters The maximum value; efficiency loss, expressed as: , in, Indicates the device at time Efficiency loss, Indicates equipment operating parameters Expected value under normal working conditions.

[0010] As a preferred embodiment of the intensive equipment data acquisition, management, and optimization method described in this invention, the domain model includes: a wind turbine PHM model, a vibration analysis model, and a photovoltaic power generation model; the wind turbine PHM model includes health assessment based on the equipment's vibration data, temperature data, and operating parameters; the vibration analysis model includes detecting existing equipment faults and the risk of impending faults through collected vibration data; the photovoltaic power generation model includes obtaining the health status of the photovoltaic equipment by comparing real-time output power with ideal power.

[0011] As a preferred embodiment of the intensive equipment data acquisition and management optimization method described in this invention, the data identification of the polynomial data trend includes peak and trough identification and polynomial trend fitting; the peak and trough identification includes automatically detecting peaks and troughs in the data by analyzing the time series of equipment operation data, obtaining the moments of key changes during equipment operation, extracting the change patterns and trends of equipment operation, and judging abnormal operating conditions of the equipment; the polynomial trend fitting includes performing curve fitting on the peak and trough identification data results to obtain the smooth trend of equipment operation data, capturing the long-term change trend of equipment parameters, and identifying potential regular fluctuations.

[0012] As a preferred embodiment of the intensive equipment data acquisition and management optimization method described in this invention, the relevant business objects include production plans, maintenance work orders, and defect work orders; business rules automatically trigger the generation of corresponding business objects by setting parameters such as equipment status, fault type, and fault frequency, and dynamically associate them with the status information in the equipment file; when the equipment status identification information indicates that the equipment is in a fault state, a defect work order is automatically generated and a processing task is assigned; when the equipment reaches the preset maintenance cycle, a maintenance work order is automatically generated; when the equipment operating status changes, an adjusted production plan and task arrangement are generated.

[0013] As a preferred embodiment of the intensive equipment data acquisition and management optimization method described in this invention, the reliability analysis technology includes: constructing an early equipment degradation warning model based on GMM and linear Bayesian frameworks; identifying early degradation through unsupervised learning in the absence of equipment degradation and fault data; predicting future trends of equipment operating parameters based on a time series prediction model, setting over-limit thresholds, and providing early warning of equipment faults; reconstructing equipment operating data through autoencoders and generative GANs, using reconstruction errors to determine data anomalies, and identifying potential problems in equipment operation.

[0014] Another objective of this invention is to provide an intensive equipment data acquisition and management optimization system that can build a tagged data link based on a unified coding system, thereby solving the problems of inconsistent data sources, inconsistent formats, and difficulties in data fusion in current equipment data acquisition and management systems.

[0015] As a preferred embodiment of the integrated equipment data acquisition, management, and optimization system described in this invention, the system includes: a data standardization modeling module, a trend analysis and identification module, and a business rules and management optimization module. The data standardization modeling module is used to construct a tagged data link based on a unified coding system, generate a standardized dataset, and construct a general equipment model using a five-level hierarchical modeling approach ("site-unit-professional-system-equipment"), enabling customized management of equipment operating conditions and dynamic updates of equipment files. The trend analysis and identification module, combined with a domain model, generates equipment status identification information based on feature quantities in the equipment files, and performs real-time trend identification of equipment operating data using peak and trough identification and multinomial trend fitting methods, automatically judging equipment operating conditions and identifying abnormal features. The business rules and management optimization module automatically generates relevant business objects according to preset business rules, performs linked management optimization operations, and, combined with reliability analysis techniques based on GMM and linear Bayesian frameworks, predicts future trends of equipment operating parameters and provides early warnings of equipment failures.

[0016] Another object of the present invention is to provide an integrated equipment data acquisition, management and optimization device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement an integrated equipment data acquisition, management and optimization method.

[0017] Another object of the present invention is to provide an integrated equipment data acquisition, management and optimization storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of an integrated equipment data acquisition, management and optimization method.

[0018] The beneficial effects of this invention are as follows: The integrated equipment data acquisition and management optimization method provided by this invention constructs a tagged data link through a unified coding system, realizing standardized processing and quality verification of multi-source equipment data, and improving data consistency, accuracy, and real-time performance. Through equipment file management and feature quantity calculation, the static and dynamic data of the equipment are correlated in multiple dimensions to form a comprehensive equipment file, enhancing the ability to monitor equipment status, provide fault warnings, and update data in real time. By combining the feature quantities in the equipment file with the domain model, relevant business objects are automatically generated and management optimization operations are performed, improving the efficiency of task scheduling, production plan optimization, and equipment maintenance. This invention achieves better results in data processing, equipment management, and task scheduling. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the overall structure of an intensive equipment data acquisition, management and control optimization method provided in Embodiment 1 of the present invention.

[0021] Figure 2 A detailed flowchart of an intensive equipment data acquisition and management optimization method provided in Embodiment 1 of the present invention.

[0022] Figure 3 This is a sample point distribution map before data mining and cleaning for an intensive equipment data acquisition and management optimization method provided in Embodiment 1 of the present invention.

[0023] Figure 4 This is a data mining and cleaning sample point distribution map for an intensive equipment data acquisition and management optimization method provided in Embodiment 1 of the present invention. Detailed Implementation

[0024] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0025] Example 1, referring to Figure 1-4 As an embodiment of the present invention, a method for optimizing the data acquisition, management, and control of integrated equipment is provided, comprising: S1: Based on a unified coding system, a tagged data link is constructed to build a standardized dataset 100. A general equipment model 200 is constructed through the standardized dataset hierarchy to perform customized management of equipment operating conditions.

[0026] It should be noted that the standardized dataset 100 includes tagging data from different equipment information sources based on a unified coding system. These different equipment information sources include SCADA, real-time monitoring equipment, and manually entered data. Tagging includes assigning a unique identifier, equipment number, site number, and timestamp to each data record, mapping data fields, adjusting data sources to the same fields and formats, and performing quality checks. Quality checks include checking for missing data, outlier detection, and time consistency checks. Checking for missing data involves automatically identifying missing values ​​in the data based on the field mapping in the standardized dataset 100, and marking and imputing missing data based on averages, interpolation, and regression models. Outlier detection involves identifying extreme values ​​in the data using statistical methods and machine learning models, and marking outliers that deviate from the normal data range by comparing their deviations. Time consistency checks involve automatically checking the time intervals of data that conform to expected patterns by comparing the sorting and periodicity of timestamps in the equipment data.

[0027] First, a global unified coding system is constructed, including basic elements such as equipment number, site number, parameter field mapping, and timestamp. All collected data is marked through a tagging mechanism and equipped with a unique identifier. All equipment data sources from SCADA system, real-time monitoring equipment, and manually input data are standardized through this coding system. A time synchronization mechanism is introduced into the data link to synchronize the clock frequency and data type of collected data from different devices.

[0028] During the generation and tagging process of the data link, the system will automatically map the real-time data collected by the device to preset standard fields, and each data record will be assigned a unique identifier and a corresponding data source tag.

[0029] Quality verification takes into account changes in the equipment's operating environment, such as temperature fluctuations and equipment malfunctions, and automatically eliminates noise data through real-time detection and correction.

[0030] It should also be noted that the equipment operating conditions are defined based on the general equipment model 200. In addition to supporting parameter judgment conditions, the operating condition definition also supports complex rule judgment, such as duration, elapsed duration, and number of occurrences.

[0031] Equipment operating conditions are defined based on the changing states of equipment operating parameters. The operating condition judgment is based on real-time equipment data, historical data, and external environmental data. Duration: When the equipment is in a certain operating condition, it is judged that the operating condition continues for more than a preset time threshold. Elapsed time: The time since the last state switch of the equipment operating condition is calculated. If the equipment operating condition continues to run within the set time range, an alarm is triggered. Number of occurrences: When a certain operating condition of the equipment reaches a certain number of occurrences, the corresponding alarm rule is triggered.

[0032] The system supports defining alarm rules, including single-parameter anomaly alarms, equipment fault alarms, and comprehensive anomaly alarms. Single-parameter anomaly alarms are triggered when a certain operating parameter of the equipment exceeds the normal range, typically for short-term anomalies of a key indicator. Equipment fault alarms are triggered when the equipment malfunctions or is about to malfunction, to inform operators to take immediate action. Comprehensive anomaly alarms are triggered after considering multiple parameters or the status of multiple devices and performing a coordinated judgment; these are typically used for system-level faults or anomalies, such as when multiple devices malfunction together.

[0033] Alarm levels are defined as follows: Emergency alarm: Equipment failure, system failure, or major anomaly requiring immediate emergency measures, which usually involve shutdown and high-priority handling.

[0034] Warning / Alarm: If the equipment exhibits significant abnormalities or reduced operating efficiency, it must be inspected and addressed within the specified timeframe.

[0035] Alarm notification: Minor anomalies or long-term trend warnings do not require immediate action, but should be checked regularly to provide information to remind operators.

[0036] The frequency and duration of alarms also affect the adjustment of alarm levels. If the same type of alarm occurs frequently within a set time range, the system will automatically upgrade the alarm level. When an alarm lasts for more than a predetermined time, the alarm level will also be automatically upgraded. For example, if a device malfunction alarm lasts for more than 30 minutes, it will be upgraded to an emergency alarm, requiring immediate handling.

[0037] It should also be noted that all standardized datasets 100 are correlated with dynamic data such as equipment operating parameters, fault records, and health assessments in multiple dimensions to form a comprehensive equipment profile 300. By combining equipment feature quantities and domain models, the health status of the equipment is dynamically mapped to operating conditions, providing a comprehensive analysis of the current operating status of the equipment. This ensures that subsequent task scheduling, maintenance arrangements, and production plan generation can be based on the real-time health status and historical operating data of the equipment.

[0038] S2: Based on the feature quantities in the equipment file 300, and combined with the domain model, generate the equipment status identification information 400, and perform real-time data trend identification and automatic working condition judgment through multinomial data trend data identification 500.

[0039] It should be noted that the feature quantities include equipment operating parameters and historical fault records extracted from equipment files 300 and real-time monitoring data, which describe the equipment's operating status, health status, and fault risk index; the equipment's health and efficiency loss are obtained through comparative analysis of real-time monitoring and historical data of equipment operating parameters; the feature quantities are analyzed in depth by combining the domain model; and the equipment's status identification information 400 is generated by comparing the feature quantities of normal operating status and abnormal status.

[0040] The failure risk index is expressed as: , in, This represents the equipment failure risk index; a higher value indicates a greater likelihood of equipment failure. Indicates the fault type Weighting factors Indicates the fault type At any moment The measured value, Indicates the type of obstacle The maximum allowable value, The weighting factor represents the historical fault records. This indicates the degree of damage recorded in the equipment's historical fault records. This indicates the total number of fault types.

[0041] Device health status is represented as: , in, This indicates the health status of the device; the device is constantly... Overall health status This indicates the total number of equipment operating parameters. Indicates equipment operating parameters Weighting factors Indicates equipment operating parameters At any moment The actual measured value, Indicates equipment operating parameters The maximum value.

[0042] Efficiency loss, expressed as: , in, Indicates the device at time Efficiency loss, Indicates equipment operating parameters Expected value under normal working conditions.

[0043] It should be noted that the domain model includes a wind turbine PHM model, a vibration analysis model, and a photovoltaic power generation model. The wind turbine PHM model includes health assessment based on the equipment's vibration data, temperature data, and operating parameters. The vibration analysis model includes detecting existing equipment faults and the risk of impending faults through collected vibration data. The photovoltaic power generation model includes obtaining the health status of photovoltaic equipment by comparing real-time output power with ideal power.

[0044] It should be noted that the polynomial data trend identification 500 includes peak and trough identification 501 and polynomial trend fitting 502; peak and trough identification 501 includes automatically detecting peaks and troughs in the data by analyzing the time series of equipment operation data, obtaining the moments of key changes during equipment operation, extracting the change patterns and trends of equipment operation, and judging abnormal operating conditions of the equipment; polynomial trend fitting 502 includes performing curve fitting on the data results of peak and trough identification 501 to obtain the smooth trend of equipment operation data, capture the long-term change trend of equipment parameters, and identify potential regular fluctuations.

[0045] For reference Figure 3 The sample point distribution map before data mining and cleaning is shown. First, based on the start and end times of equipment operation, industrial data within the current time period is obtained and the corresponding timestamps are recorded. After data collection, data preprocessing is performed, including data cleaning, data filtering, and data format conversion. Through preprocessing, feature values ​​in the original data are extracted and several feature group arrays are generated, including at least the maximum value array, the minimum value array, and their corresponding time lists.

[0046] Polynomial curve fitting is performed on the preprocessed original data array and feature value array to obtain the slope value corresponding to each array. Combining the maximum value array, minimum value array, original data array and corresponding timestamp, the numerical values ​​are used as the x-axis and the timestamps are used as the y-axis for curve fitting. The data change trend is analyzed by calculating the slope value.

[0047] Based on the established analysis rules and the fitted slope value, the trend type of equipment data within the current time period is calculated. By monitoring the trend changes of equipment operation data in real time, the system automatically judges the working status and abnormal conditions of the equipment. Multidimensional data analysis and data mining techniques are used to clean the data, remove erroneous data points and abnormal operating condition data, and retain stable operating condition data, abnormal operating condition data, and historical best operating condition data.

[0048] For reference Figure 4The distribution map of sample points after data mining and cleaning is shown. After cleaning and filtering the data, the historical best benchmark line is generated by combining the historical best operating condition data. Through further mining and segmentation of stable operating condition sample points, the data is divided at equal intervals according to the load, and the historical best benchmark line is used to perform benchmark analysis on the equipment performance.

[0049] Combined with a big data rule engine computing platform, the platform is highly customizable and configurable, supporting real-time parsing and computation of data sources and rule requirements. It accepts various data sources, including relational data, real-time data, and high-frequency signal data. Through a rule parser and pre-compiler, the rules and data are combined to generate execution statements (QL) and distributed to different types of computation executors. The computation results will be output and stored in multiple data media, including relational databases, NoSQL databases, and in-memory databases.

[0050] S3: Automatically generates relevant business objects based on preset business rules, performs coordinated control and optimization operations, and identifies potential failure points in advance by combining deep neural network reliability analysis technology.

[0051] The relevant business objects include production plans, maintenance work orders, and defect work orders. Business rules automatically trigger the generation of corresponding business objects by setting parameters such as equipment status, fault type, and fault frequency, and dynamically associate them with the status information in the equipment file 300. When the equipment status identification information 400 indicates that the equipment is in a fault state, a defect work order is automatically generated and a processing task is assigned. When the equipment reaches the preset maintenance cycle, a maintenance work order is automatically generated. When the equipment operating status changes, an adjusted production plan and task arrangement are generated.

[0052] The management and control optimization operations include automatically scheduling and executing equipment maintenance, repair, and operation plans based on the generated equipment status identification information 400 and related business objects; automatically adjusting task priorities and optimizing equipment maintenance and operation cycles based on real-time changes in equipment health status and workload; and dynamically generating maintenance plans and repair arrangements based on equipment maintenance needs and historical fault records.

[0053] It should also be noted that, firstly, based on the Gaussian Mixture Model (GMM) and the linear Bayesian framework, the early deterioration warning model for equipment is constructed using an unsupervised learning method. It does not rely on equipment deterioration or failure data. In the normal operation data of the equipment, by analyzing the behavior patterns of the equipment, the model identifies the potential characteristics of early deterioration, including subtle fluctuations or abnormal trends in equipment operation. By learning the normal operation mode of the equipment, the model can issue warnings when minor abnormalities occur, and detect possible equipment deterioration in advance.

[0054] A time series forecasting model is used to predict the future trends of key operating parameters of the equipment. Historical operating data of the equipment is collected, and the data is trained using the time series model to predict the changing trend of equipment parameters over a period of time. Based on the predicted trend, an over-limit threshold is set. If the predicted value of the equipment parameter is close to or exceeds the set threshold, the system will issue an over-limit warning signal.

[0055] The device's operational data is reconstructed using autoencoders and generative adversarial networks (GANs). The autoencoder model learns the data characteristics of the device under normal operating conditions and encodes and reconstructs the device data. By comparing the error between the reconstructed data and the actual device data, it is determined whether the data is abnormal. If the reconstruction error is large, it indicates that the device's operational data deviates from the normal pattern, which may indicate a fault or potential problem. The generative adversarial network (GAN) further enhances the ability to detect data anomalies. Through adversarial training between the generator and discriminator, the anomaly detection performance of the model is optimized, accurately identifying potential fault risks in device operation.

[0056] It should also be noted that during equipment operation, when it is necessary to activate or deactivate the protection device, the system records the entire activation / deactivation process through the protection activation / deactivation application form. When the equipment status changes or the equipment needs to be temporarily deactivated or the protection function needs to be activated due to maintenance requirements, the site manager initiates a setting activation / deactivation application, including the reason for activation / deactivation, the activation / deactivation period, and safety measures.

[0057] Once all commissioning and decommissioning operations have gone through the approval process, the system will automatically assign commissioning and decommissioning tasks to the relevant responsible persons. The task executors will strictly follow the predetermined time nodes to carry out the commissioning and decommissioning operations according to the system prompts, and fill in the commissioning and decommissioning execution record after the operation is completed. The operation of fixed value commissioning is consistent with the commissioning and decommissioning process. When the commissioning and decommissioning is completed or the commissioning and decommissioning time limit is reached, the person in charge of the site work will initiate a fixed value restoration application to request that the equipment be restored to normal working status.

[0058] Example 2, an embodiment of the present invention, provides an intensive equipment data acquisition, management and optimization system, including a data standardization modeling module, a trend analysis and identification module, and a business rules and management optimization module.

[0059] The data standardization modeling module is used to build a tagged data link based on a unified coding system, generate a standardized dataset 100, and construct a general equipment model 200 using a five-level hierarchical modeling method of "station-unit-professional-system-equipment". It also enables customized management of equipment operating conditions and dynamic updating of equipment files 300.

[0060] The trend analysis and identification module is used to combine the domain model and generate equipment status identification information 400 based on the feature quantities in the equipment file 300. It uses peak and trough identification 501 and polynomial trend fitting 502 methods to perform real-time trend identification on equipment operation data, automatically judge equipment operating conditions and identify abnormal features.

[0061] The business rules and control optimization module is used to automatically generate relevant business objects according to preset business rules, and to perform control optimization operations in conjunction with the reliability analysis technology based on GMM and linear Bayesian framework 600 to predict the future trend of equipment operating parameters and provide early warning of equipment failure.

[0062] This embodiment also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements a personnel positioning safety management visualization analysis system as proposed in the above embodiment.

[0063] This embodiment also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a personnel positioning safety management visualization analysis system as proposed in the above embodiment.

[0064] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, 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 invention. 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.

[0065] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0066] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0067] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0068] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for optimizing the data acquisition, management, and control of integrated equipment, characterized in that, include: A standardized dataset is constructed based on a unified coding system and a tagged data link. A general equipment model is then built through the hierarchical structure of the standardized dataset to enable customized management of equipment operating conditions. Based on the feature quantities in the equipment file, combined with the domain model, the status identification information of the equipment is generated. Through multinomial data trend data recognition, real-time data trend recognition and automatic working condition judgment are performed. Relevant business objects are automatically generated based on preset business rules, and control and optimization operations are executed in conjunction with them. Potential failure points are identified in advance by combining deep neural network reliability analysis technology. The general equipment model includes a five-level modeling system: station, unit, specialty, system, and equipment. Static and dynamic data are correlated in multiple dimensions to form equipment files. Through real-time update function, dynamic information is updated when equipment fails or is maintained, and synchronized with external information. The business rules include automatically generating and scheduling regular maintenance, repair work orders, and downtime tasks based on the health status and operating cycle of the equipment. When the equipment reaches the preset maintenance cycle or a fault occurs, the corresponding workflow is automatically triggered.

2. The intensive equipment data acquisition, management, and optimization method as described in claim 1, characterized in that: The standardized dataset includes, Data from different device information sources is tagged based on a unified coding system; The different device information sources include SCADA, real-time monitoring equipment, and manually input data; The tagging process includes assigning a unique identifier, equipment number, site number, and timestamp to each data record, mapping data fields, adjusting the data source to the same fields and format, and performing quality verification. The quality verification includes checking for missing data, outlier detection, and time consistency detection. The verification of missing data includes automatically identifying missing values ​​in the data based on field mapping in a standardized dataset, and marking and filling in the missing data based on the average value, interpolation, and regression model. The outlier detection includes using statistical methods and machine learning models to identify extreme values ​​in the data, and marking outliers that deviate from the normal range by comparing them with deviations from the normal data range. The time consistency detection includes automatically checking the time intervals of data that conform to expected patterns by comparing the sorting and periodic verification of timestamps in the device data.

3. The method for optimizing data acquisition, management, and control of integrated equipment as described in claim 1 or 2, characterized in that: The characteristic quantities include, The equipment operating parameters and historical fault records extracted from equipment files and real-time monitoring data describe the equipment's operating status, health status, and fault risk index. Real-time monitoring of equipment operating parameters and comparative analysis of historical data are used to obtain equipment health and efficiency loss. In combination with the domain model, in-depth analysis of feature quantities is carried out. By comparing the feature quantities of normal operation state and abnormal state, the status identification information of the equipment is generated. The failure risk index is expressed as: ， in, This represents the equipment failure risk index; a higher value indicates a greater likelihood of equipment failure. Indicates the fault type Weighting factors Indicates the fault type At any moment The measured value, Indicates the type of obstacle The maximum allowable value, The weighting factor represents the historical fault records. This indicates the degree of damage recorded in the equipment's historical fault records. Indicates the total number of fault types; The device health status is expressed as: ， in, This indicates the health status of the device; the device is constantly... Overall health status This indicates the total number of equipment operating parameters. Indicates equipment operating parameters Weighting factors Indicates equipment operating parameters At any moment The actual measured value, Indicates equipment operating parameters The maximum value; The efficiency loss is expressed as: ， in, Indicates the device at time Efficiency loss, Indicates equipment operating parameters Expected value under normal working conditions.

4. The intensive equipment data acquisition, management, and optimization method as described in claim 3, characterized in that: The domain model includes, Wind turbine PHM model, vibration analysis model, photovoltaic power generation model; The wind turbine PHM model includes a health assessment based on the equipment's vibration data, temperature data, and operating parameters. The vibration analysis model includes detecting existing equipment faults and the risk of impending faults through the collected vibration data; The photovoltaic power generation model includes obtaining the health status of photovoltaic equipment by comparing the real-time output power with the ideal power.

5. The method for optimizing data acquisition, control, and management of integrated equipment as described in any one of claims 1, 2, and 4, characterized in that: The data identification of the polynomial data trend includes, Peak and trough identification and polynomial trend fitting; The peak and trough identification includes automatically detecting peaks and troughs in the data by analyzing the time series of equipment operation data, obtaining the moments of key changes during equipment operation, extracting the change patterns and trends of equipment operation, and judging abnormal operating conditions of the equipment. The polynomial trend fitting includes curve fitting of the peak and trough identification data results to obtain the smooth trend of equipment operation data, capture the long-term change trend of equipment parameters, and identify potential regular fluctuations.

6. The intensive equipment data acquisition, management, and optimization method as described in claim 5, characterized in that: The relevant business objects include, Production plans, maintenance work orders, and defect work orders; Business rules automatically trigger the generation of corresponding business objects by setting parameters such as device status, fault type, and fault frequency, and dynamically associate them with the status information in the device file. When the equipment status identification information indicates that the equipment is in a faulty state, a defect work order is automatically generated and a processing task is assigned. When the equipment reaches the preset maintenance cycle, a maintenance work order is automatically generated; When the operating status of the equipment changes, an adjusted production plan and task arrangement are generated.

7. The intensive equipment data acquisition, control and optimization method as described in any one of claims 1, 2, 4, and 6, characterized in that: The reliability analysis techniques include, A device early deterioration warning model is constructed based on the GMM and linear Bayesian framework, and early deterioration identification is performed in the absence of device deterioration and fault data through unsupervised learning. Based on time series forecasting models, the future trends of equipment operating parameters are predicted, and thresholds for exceeding limits are set to provide early warnings of equipment failures. The device operation data is reconstructed by an autoencoder and a generative GAN, and the reconstruction error is used to identify data anomalies and potential problems in the device operation.

8. An intensive equipment data acquisition, control, and optimization system, employing the intensive equipment data acquisition, control, and optimization method as described in any one of claims 1 to 7, characterized in that: It includes a data standardization modeling module, a trend analysis and identification module, and a business rules and control optimization module; The data standardization modeling module is used to build a tagged data link based on a unified coding system, generate a standardized dataset, and use a five-level hierarchical modeling approach of "station-unit-professional-system-equipment" to build a general equipment model, and to perform customized management of equipment operating conditions and dynamic updating of equipment files. The trend analysis and identification module is used to combine the domain model and generate equipment status identification information based on the feature quantities in the equipment file. It uses peak and trough identification and multinomial trend fitting method to perform real-time trend identification of equipment operation data, automatically judge the equipment operating condition and identify abnormal features. The business rules and control optimization module is used to automatically generate relevant business objects according to preset business rules, and to perform control optimization operations in conjunction with them. Combined with reliability analysis technology based on GMM and linear Bayesian framework, it predicts the future trend of equipment operating parameters and provides early warning of equipment failure.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the intensive equipment data acquisition and management optimization method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the intensive equipment data acquisition and management optimization method according to any one of claims 1 to 7.

Images