Enterprise business report generation method and system based on large model

Abstract

The invention relates to the technical field of report generation, in particular to an enterprise business report generation method and system based on a large model. The method comprises the following steps: acquiring component operation state data and production plan data of industrial equipment; performing master-slave relation division on internal components of the equipment according to the component operation state data, designating a driving device as a master component, designating a transmission component and an execution component as slave components, and constructing a component transfer chain relation graph; monitoring operation state parameters of the main component in the component transmission chain relation graph; extracting the master component of which the fluctuation of the operation state parameter exceeds a preset threshold value, and measuring the response parameter change condition of the connected slave component; and generating abnormal transmission confirmation data according to the response parameter change condition. According to the invention, based on abnormal transmission characteristics between components, early fault identification and propagation path tracking are realized, and a problem source is found before fault expansion.

Description

Technical Field

[0001] The present invention relates to the technical field of report generation, and in particular to a method and system for generating enterprise business reports based on a large model. Background Art

[0002] Large models refer to deep learning models with large parameter scales and complex computing structures, usually containing billions or even hundreds of billions of parameters. These models are based on the Transformer architecture and have strong language understanding and generation capabilities through training with massive data. Enterprise business reports are reports used for management and decision-making within the enterprise, usually including two categories: financial statements and non-financial statements. Financial statements mainly reflect the financial status and operating results of the enterprise, such as balance sheets, income statements, and cash flow statements; non-financial statements cover the company's operating data, production data, sales data, etc., which are used to evaluate the company's operating efficiency and business performance. The method of generating enterprise business reports refers to the collection, organization, and analysis of the company's financial data, operating data, market data, etc. through a series of processes and technical means, and finally presenting them in the form of reports.

[0003] However, the enterprise business report generation method often has the following problems during equipment maintenance: Equipment maintenance is often passive and responsive, and in most cases the problem can only be discovered after the failure occurs, resulting in unplanned downtime and high maintenance costs. Large industrial equipment (such as wind turbines and large metallurgical equipment) consists of thousands of components, and the performance status of each component affects each other, forming a complex failure evolution path. Traditional maintenance reports are mostly based on single indicator threshold monitoring, which makes it difficult to identify system-level failure precursors. Summary of the invention

[0004] Based on this, it is necessary for the present invention to provide a method and system for generating enterprise business reports based on a large model to solve at least one of the above technical problems.

[0005] To achieve the above purpose, a method for generating enterprise business reports based on a large model includes the following steps: Step S1: Acquire component operation status data and production plan data of industrial equipment; Step S2: dividing the components inside the device into master-slave relationships according to the component operation status data, designating the drive device as the master component, and designating the transmission component and the execution component as the slave components, and constructing a component transfer chain relationship diagram; Step S3: monitor the operating status parameters of the master components in the component transfer chain relationship diagram; extract the master components whose operating status parameter fluctuations exceed the preset threshold, and measure the response parameter changes of the connected slave components; generate abnormal transfer confirmation data according to the response parameter changes; Step S4: performing a time interval pattern analysis based on a large model on the abnormality of the master component and the abnormality of the slave component according to the abnormality transmission confirmation data, and combining the estimated running time required for the component to reach the critical maintenance state from the current state of the component with the preset historical fault data, to obtain the component maintenance window data; Step S5: Time-match the component maintenance window data with the production plan data, and identify the production gap period or low-load period to obtain the maintenance time data; generate the component status signal light diagram, the transmission chain map, the maintenance time and the equipment maintenance report of the maintenance material list according to the maintenance time data and the component transmission chain relationship diagram.

[0006] The present invention realizes intelligent optimization of equipment maintenance by acquiring component operation status data and production plan data of industrial equipment. First, based on the component operation status data, the master-slave relationship of the internal components of the equipment is divided, the driving device is set as the master component, the transmission component and the execution component are set as the slave component, so as to establish a hierarchical structure and logical relationship between the components, and construct a component transmission chain relationship diagram, so as to accurately track the impact of the change of the operation status on the overall equipment. On this basis, the operation status parameters of the main component are monitored, the main component whose fluctuation exceeds the preset threshold is accurately identified, and the response parameter changes of the connected slave components are measured to ensure the accuracy of the abnormal transmission situation, and generate abnormal transmission confirmation data to enhance the control ability of the fault propagation path. Combined with the time interval pattern analysis of the large model, the influence of the main component abnormality on the slave component is calculated, and the estimated operating time required for the current state of the slave component to reach the critical state of maintenance is inferred with reference to the historical fault data, so as to ensure that the maintenance strategy is forward-looking and feasible. Subsequently, the calculated maintenance window data is time-matched with the production plan data, and the production gap period or low-load period is intelligently identified to minimize the impact of maintenance on production and improve equipment availability and production continuity. In addition, based on the maintenance time data and the component transfer chain relationship diagram, the equipment maintenance report is automatically generated, including the component status signal light diagram, the transfer chain map, the maintenance time and the maintenance material list, ensuring that the maintenance personnel can clearly understand the equipment status, the fault propagation path and the resources required for maintenance, and improve the efficiency and accuracy of maintenance work. Overall, this method can optimize the maintenance time while ensuring the normal operation of the equipment, reduce the downtime risk caused by sudden equipment failures, reduce unnecessary maintenance costs, and enhance the intelligence and visualization level of equipment operation and maintenance management.

[0007] The present invention also provides a system for generating enterprise business reports based on a big model, which is used to execute the above-mentioned method for generating enterprise business reports based on a big model. The system for generating enterprise business reports based on a big model includes: Data acquisition module, used to obtain component operation status data and production plan data of industrial equipment; The component relationship division module is used to divide the master-slave relationship of the internal components of the equipment according to the component operation status data, designate the drive device as the master component, designate the transmission component and the execution component as the slave component, and construct the component transfer chain relationship diagram; The anomaly detection module is used to monitor the operating status parameters of the master components in the component transfer chain relationship diagram; extract the master components whose operating status parameter fluctuations exceed the preset threshold, and measure the response parameter changes of the connected slave components; generate abnormal transfer confirmation data according to the response parameter changes; The maintenance window analysis module is used to perform a time interval pattern analysis between the main component abnormality and the slave component abnormality based on a large model according to the abnormality transmission confirmation data, and obtain the component maintenance window data by combining the estimated running time required for the component current state to reach the maintenance critical state with the preset historical fault data; The maintenance plan generation module is used to time-match component maintenance window data with production plan data, identify production intervals or low-load periods, and obtain maintenance time data; based on the maintenance time data and the component transfer chain relationship diagram, it generates equipment maintenance reports such as component status signal light diagrams, transfer chain maps, maintenance time, and maintenance material lists.

[0008] The present invention accurately obtains the component operation status data and production plan data of industrial equipment through the data acquisition module, providing a reliable original data basis for subsequent analysis and decision-making. The component relationship division module analyzes the operation status data of each component inside the equipment, reasonably sets the drive device as the main component, and divides the transmission and execution components into slave components to form a component transfer chain relationship diagram. This operation helps to clarify the dependency relationship between the components, thereby improving the accuracy of fault detection. The abnormal detection module monitors the operation status of the main component, timely identifies the main component whose operation parameter fluctuation exceeds the threshold, and analyzes the response parameter changes of the connected slave components to generate abnormal transmission confirmation data, providing a basis for fault location and diagnosis. The maintenance window analysis module analyzes the abnormal transmission time interval pattern between the master and slave components through a large model based on the abnormal transmission confirmation data, and combines historical fault data to accurately predict the time required for the slave component to reach the critical state of maintenance, providing an accurate window period for equipment maintenance, and reducing the risk of premature or late maintenance. The maintenance plan generation module further connects the maintenance window data with the production plan data to ensure that maintenance activities can be carried out during the production interval or low load period to avoid production interference. At the same time, the equipment maintenance report generated based on the component transfer chain relationship diagram includes a component status signal light diagram, a transfer chain map, maintenance time, and a maintenance material list. It not only intuitively presents the health status of the equipment, but also provides maintenance personnel with a specific work plan, making the maintenance process more efficient, accurate, and controllable, thereby maximizing the operating efficiency of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings: Figure 1 A schematic diagram of the steps of a method for generating a business report of an enterprise based on a large model according to the present invention; Figure 2 for Figure 1 Detailed step flow chart of step S1 in FIG. DETAILED DESCRIPTION

[0010] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0011] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0012] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0013] To achieve this, please refer to Figure 1 to Figure 2 The present invention provides a method for generating an enterprise business report based on a large model, the method comprising the following steps: Step S1: Acquire component operation status data and production plan data of industrial equipment; In the injection molding equipment monitoring system, the embodiment of the present invention deploys a PCB 352C33 vibration sensor to monitor the vibration characteristics of the main motor EM-001 (37kW), uses a Pt100 temperature sensor to measure temperature, and uses a LEM HAS400-S current sensor to monitor current; installs a pressure and flow sensor on the hydraulic pump HP-001 (11kW); and installs an air pressure sensor on the pneumatic valve PA-001. All sensors are connected to the edge server via RS485 communication, and the acquisition frequency is 1-60 seconds / time. The system applies a filtering algorithm to process the data, and extracts a 30-day production plan from the ERP system, including equipment operation time (three shifts), product batches (such as daily production of ABS bumpers, injection pressure 21MPa), load rate (recorded by hour) and planned downtime (such as Sunday maintenance). The system integrates sensor data and production plans to form a comprehensive data structure.

[0014] Step S2: dividing the components inside the device into master-slave relationships according to the component operation status data, designating the drive device as the master component, and designating the transmission component and the execution component as the slave components, and constructing a component transfer chain relationship diagram; The embodiment of the present invention extracts the physical connection relationship of 94 components of the injection molding equipment from the drawings and BOM list, and divides the master-slave relationship based on the principle of energy flow. The energy input component is designated as the main component: 5 electrical main components such as the main drive motor EM-001, 2 hydraulic main components such as the main hydraulic pump HP-001, and 3 pneumatic main components such as the pneumatic valve PA-001, a total of 10 main components. The transmission components directly connected to the main components (such as the coupling LC-200 and the reducer GB-001) are marked as 25 first-level slave components, and the execution components connected to the first-level slave components are marked as 59 second-level slave components. The influence coefficient is calculated by analyzing the historical data of 3 months. For example, when the temperature of the main motor rises by 10°C, the temperature of the reducer rises by 6.7°C, and the influence coefficient is 0.67. The force-directed algorithm is used to construct the component transfer chain relationship diagram, with nodes representing components, lines representing influence relationships (line thickness represents strength), and colors are used to distinguish different types of components (electrical blue, hydraulic green, pneumatic yellow).

[0015] Step S3: monitor the operating status parameters of the master components in the component transfer chain relationship diagram; extract the master components whose operating status parameter fluctuations exceed the preset threshold, and measure the response parameter changes of the connected slave components; generate abnormal transfer confirmation data according to the response parameter changes; The embodiment of the present invention sets the monitoring priority according to the energy input of the main component and the number of connected slave components: 5 high-priority components such as the main motor EM-001 (5 seconds / time), 2 medium-priority components such as the hydraulic pump HP-001 (15 seconds / time), and 3 low-priority components such as the pneumatic valve PA-001 (30 seconds / time). The data is smoothed by a sliding window (window 10 points, the weight of the latest point is 0.3). When the temperature of the main motor reaches 80°C (exceeding the standard by 15°C), the vibration reaches 1.5mm / s, or the pressure of the hydraulic pump drops to 18.5MPa (lower than the rated 1.5MPa), the system marks it as abnormal and records the timestamp. Subsequently, the slave components connected to the abnormal main component are sampled at high frequency (0.5 seconds / time), and the response characteristics of the slave components 30 seconds before the abnormality, 0-60 seconds after the abnormality, and 60-120 seconds are analyzed, such as the reduction box temperature rises from 52.3°C to 61.5°C, with a rise rate of 5.5°C / minute. The system determines the response delay time, peak response and steady-state characteristics, matches the failure mode, and generates abnormal transmission confirmation data.

[0016] Step S4: performing a time interval pattern analysis based on a large model on the abnormality of the master component and the abnormality of the slave component according to the abnormality transmission confirmation data, and combining the estimated running time required for the component to reach the critical maintenance state from the current state of the component with the preset historical fault data, to obtain the component maintenance window data; The embodiment of the present invention constructs a master-slave component abnormal relationship matrix and determines the abnormal transmission path (such as main motor → coupling → reducer → bearing). Calculate the transmission time interval (the reducer responds 15 seconds after the main motor abnormality, and the bearing responds 7 seconds later) and its relationship with the load. Input the time data into the Transformer architecture large model (8-layer encoder, 12 attention heads), match the 35 feature vectors with historical faults, identify the "motor bearing overheating" mode (matching degree 83%), and adjust it to 100% probability in combination with environmental factors (28°C workshop temperature). The system analyzes similar cases, considering the current reducer temperature of 78°C and vibration of 1.8mm / s, and predicts that the critical value (temperature 90°C or vibration 2.5mm / s) will be reached after 17.5 hours under the load of 85%. Simulate different intervention measures: reducing the load to 65% can extend it to 30 hours, and increasing cooling can extend it to 36 hours, and generate component maintenance window data.

[0017] Step S5: Time-match the component maintenance window data with the production plan data, and identify the production gap period or low-load period to obtain the maintenance time data; generate the component status signal light diagram, the transmission chain map, the maintenance time and the equipment maintenance report of the maintenance material list according to the maintenance time data and the component transmission chain relationship diagram.

[0018] The embodiment of the present invention scores 17 components that need maintenance, considering the remaining time (weight 0.5), parameter deviation (weight 0.3) and impact range (weight 0.2), and classifies three components such as the gearbox GB-001 (8.7 points) as emergency maintenance, eight components such as the hydraulic valve HV-004 (6.2 points) as planned maintenance, and six components such as the cooling pump CP-002 (3.5 points) as monitoring maintenance. The two-week production plan is extracted from the ERP, and six production gaps (downtime > 4 hours) and four low-load periods (<40% load, > 6 hours) are identified, with a total of 80 hours of maintenance time. The multi-objective optimization algorithm matches components and time periods, considers time urgency, maintenance windows, production impacts and resource conflicts, and arranges emergency components in the recent gap period. The maintenance dependency is analyzed, and upstream and downstream related components (such as hydraulic pumps and control valves) are merged to optimize 17 tasks to 9. A maintenance report is generated, including component status diagrams, transfer chain maps, maintenance schedules and bills of materials.

[0019] Preferably, step S1 comprises the following steps: Step S11: deploying a device status collector, wherein the device status collector includes a vibration sensor, a temperature sensor and a current sensor; installing the vibration sensor on the surface of the main driving component, installing the temperature sensor on the part of the component that is prone to heat, and connecting the current sensor to the power input terminal to collect the original device operation data; The embodiment of the present invention uses the rotary kiln of a cement plant (95 meters long, 5.6 meters in diameter, and driven by a 2500kW main motor) as the implementation scenario. Three types of sensors are deployed: PCB 352C33 high-frequency vibration sensor (sensitivity 100mV / g, ±50g range), installed on 8 key drive components such as the main motor and reducer, and fixed with screws in the radial and axial positions of the bearing seat; Pt100 platinum resistance temperature sensor (-40℃ to 450℃, accuracy ±0.5℃), installed in 12 heat-prone parts such as motor windings and bearing seats; LEMHAS400-S Hall effect current sensor (0-400A range, response <1μs), connected to the power input terminal of the main motor. The sensor is connected to the data acquisition box via a 4-20mA signal or RS485, and the differential sampling frequency is set: vibration 1000Hz, temperature 0.1Hz, current 100Hz. The collected data is transmitted to the edge computing server via industrial Ethernet, forming a raw data stream containing timestamp and device ID, with a rate of approximately 20MB / hour.

[0020] Step S12: removing signal noise and abnormal interference values ​​from the original equipment operation data, thereby obtaining equipment operation data; The embodiment of the present invention performs differentiated signal processing on the raw data of the rotary kiln: the vibration data uses a Butterworth low-pass filter (cut-off frequency 500Hz) to remove high-frequency interference, and then uses db4 wavelet transform decomposition to remove environmental vibration; the temperature data uses a median filter (window 5 points) to eliminate mutation points, and uses an exponentially weighted moving average (α=0.2) to smooth the trend; the current data uses a notch filter (50Hz center frequency, 5Hz bandwidth) to eliminate grid interference, and uses a Kalman filter to remove spikes. The system automatically detects sensor failure: data with a deviation of more than 3 times the standard deviation or beyond the physical range (such as temperature>500℃) for 5 consecutive cycles is marked and removed, and an inspection warning is triggered. The processed data is saved in a structured format, including component ID, parameter type, processed value and credibility score, and the data efficiency is increased from 89% to 97%.

[0021] Step S13: classifying and sorting the equipment operation data based on component types, and calculating the parameter standard range of each component under normal operating conditions, thereby obtaining component operation benchmark data; The embodiment of the present invention classifies the data after the rotary kiln is cleaned by component type: electrical drive (extracting current and temperature parameters), mechanical transmission (extracting vibration and temperature parameters), thermal engineering (extracting temperature distribution parameters), and hydraulic (extracting pressure and flow parameters). The normal parameter range is established using historical data during the stable operation period of the equipment (continuous operation > 72 hours, load 80%-90%): the mean μ and standard deviation σ of continuous parameters are calculated by statistical methods, and the normal range is defined as [μ-2σ, μ+2σ]; the feature space boundary is established by the PCA method for complex parameters; and the state transition model is established for discrete parameters. For example, the normal range of the main motor bearing temperature is 60±8℃, the vibration speed is 0.5-2.8mm / s; the reducer oil temperature is 55±5℃; the main vibration frequency of the gearbox should be at the meshing frequency (12.5Hz) and the frequency multiple, and the acceleration peak is <4g. These parameters are integrated into a component operation benchmark database, which contains the standard range of each component under different loads (60%, 75%, 90%, 100%).

[0022] Step S14: Compare the component operation benchmark data with the component operation status parameters monitored in real time by the device status collector, and mark the components whose parameters deviate from the benchmark range to obtain the component operation status data; The edge server in the embodiment of the present invention compares the current rotary kiln equipment data with the benchmark database in real time. The system first identifies the current working conditions (load rate, ambient temperature, operating time), retrieves the corresponding benchmark range, and calculates the parameter deviation: the continuous parameters use the standardized calculation method (value-mean) / (range width / 2), and [-1,1] is considered as exceeding the standard; the complex parameters use the characteristic vector distance method; the discrete parameters compare the state transition time and steady-state value. For example, the main motor bearing temperature is 72°C, and the calculated deviation is (72-60) / 8=1.5, which exceeds the normal upper limit; the vibration spectrum of the reducer has a strong peak of non-meshing frequency, and the characteristic vector distance is 0.42 (exceeding the threshold of 0.3). The system is classified according to the degree of deviation: 0.8-1.2 is a yellow warning, 1.2-2.0 is an orange warning, and >2.0 is a red warning. All deviations (component ID, parameter type, current value, standard range, deviation, warning level) are recorded as operating status data, updated every 10 seconds, stored in the time series database and displayed on the monitoring screen.

[0023] Step S15: Obtain production plan data, including planned equipment operation time, production load rate and planned downtime for maintenance.

[0024] The embodiment of the present invention obtains the production plan of the rotary kiln of the cement plant through the SAP ERP and MES integrated system. The main production plan for the next 30 days is extracted through the API interface, including cement varieties, output, batches and time arrangements: the rotary kiln runs all day from Monday to Friday, runs from 8:00 to 20:00 on Saturday, and shuts down for maintenance on Sunday; the load rate of each period is recorded hourly, 90%-95% in the normal production period, and 60%-70% in the switching period; the downtime maintenance time includes 8 hours of routine maintenance every Sunday and 24-hour major overhaul once a month (Tuesday of the third week of the next month); details of each maintenance content, such as routine inspection of kiln head seal, cleaning of dust collector, and major overhaul including support roller adjustment, transmission inspection, etc. The data is stored in JSON format, including accurate timestamps, equipment IDs, plan types, load rates, etc. The system monitors the execution of the plan in real time, and automatically updates when the actual production deviates from the plan (such as early completion or temporary failure), to ensure that the maintenance decision is based on the latest operation plan.

[0025] The present invention realizes comprehensive monitoring of the operating status of industrial equipment by deploying equipment status collectors. The vibration sensor is installed on the surface of the main driving component to capture the vibration characteristics during operation. The temperature sensor is arranged at the heat-prone component to detect the temperature change in real time. The current sensor is connected to the power input terminal to monitor the current fluctuation of the equipment, so as to accurately obtain the original equipment operation data. Subsequently, the signal noise and abnormal interference value of the collected data are removed to ensure the accuracy and reliability of the data, and avoid misjudgment affecting the analysis results. On this basis, the equipment operation data is classified and sorted, and the parameter standard range under its normal operating state is calculated according to the component type, and the component operation benchmark data is established to provide an accurate reference standard. Combined with the real-time monitoring results of the equipment status collector, the current component operation status parameters are compared with the benchmark data, and the components with parameter deviation ranges are quickly identified to ensure that abnormal changes in the equipment operation status can be discovered and marked in time, providing a basis for subsequent maintenance decisions. At the same time, production planning data is obtained, including planned equipment operating time, production load rate and planned downtime maintenance time, to provide a time management basis for equipment operation and maintenance, combine fault analysis with production scheduling, and achieve the optimal formulation of maintenance strategies, thereby improving equipment stability and production continuity.

[0026] Preferably, step S2 comprises the following steps: Step S21: acquiring equipment structure drawing data, and extracting the physical connection relationship and energy transfer path information of the components from the equipment structure drawing data, thereby obtaining the physical topological structure data of the components; The embodiment of the present invention takes injection molding equipment as an example, and extracts engineering drawings from the enterprise PLM system, including two-dimensional assembly drawings in AutoCAD DWG format and three-dimensional models in STEP format. CAD parsing tools are used for processing: using graphic recognition algorithms to identify component boundaries and connection relationships in DWG; performing topological analysis on the STEP model to identify physical components and spatial position relationships; matching components with BOMs through coding rules to determine models and functions; and establishing physical connection maps between components based on physical contact and functional connections. At the same time, the energy transfer path is analyzed, such as electrical energy from the power supply through the control cabinet to the motor, through mechanical transmission to the hydraulic system, and finally driving the injection and clamping units. The system generates physical topological structure data containing 152 component nodes and 237 connection edges. Each node contains component ID, type, location, etc., and each connection contains connection type, transfer direction and physical distance.

[0027] Step S22: identifying the energy input component in the device based on the component physical topological structure data, and marking it as a main component, thereby obtaining preliminary main component identification data, wherein the energy input component includes a motor, a hydraulic pump, and a pneumatic device; The embodiment of the present invention automatically identifies the energy input components in the injection molding machine through the energy source identification algorithm. The algorithm checks the functional attribute labels of the components, screens "drive source" and "energy converter", analyzes the nodes in the topology diagram that have energy input but no upstream source, and verifies in combination with the equipment professional knowledge rule base. Three main types of energy input components are identified: electrical (1 37kW main drive motor, 4 2.2kW auxiliary motors, 6 servo motors); hydraulic (2 21MPa main hydraulic pumps, 3 14MPa auxiliary hydraulic pumps); pneumatic (4 0.8MPa pneumatic control valve groups). Each component is given a unique identification (such as EM-001, HP-002, PA-003) and key parameters (power, pressure, flow) are recorded to form a preliminary main component identification data table containing 17 main component records.

[0028] Step S23: determining the transmission component directly connected to the main component based on the energy flow direction in the preliminary main component identification data, marking it as a first-level slave component, thereby obtaining first-level slave component association data, wherein the transmission component includes a gear box, a pulley, and a bearing; Based on the preliminary main component identification data, the embodiment of the present invention analyzes the energy flow direction to determine the first-level slave components. For electrical main components, the transmission device is identified along the mechanical connection path, such as the coupling LC-200, the reduction box (10:1) and the pulley (3:1) connected to the main motor EM-001; for hydraulic main components, the hydraulic pipeline is tracked to identify the valve, such as the 25MPa directional control valve and the 200L / min flow control valve connected to the main hydraulic pump HP-001; for pneumatic main components, the gas path is analyzed to identify the distributor and amplifier. Verification is performed in combination with physical location and function, and the connection relationship and characteristics are recorded, such as the main motor and the reduction box are "mechanical direct connection", with an efficiency of 98% and a delay of <10ms; the hydraulic pump and the remote control valve are "hydraulic pipeline connection", with an efficiency of 85% and a delay of 50-100ms. The system generates first-level slave component association data containing 42 transmission components.

[0029] Step S24: determining the execution component connected to the first-level slave component along the energy transfer path according to the first-level slave component association data, and marking it as a second-level slave component, thereby obtaining master-slave component hierarchical data, wherein the execution component includes an actuator, a working head, and a functional component; The embodiment of the present invention determines the secondary slave components along the energy transfer path based on the associated data of the primary slave components. For the electrical-mechanical path, the actuator components connected to the reduction gearbox are identified, such as the injection screw and the template drive system; for the hydraulic path, the hydraulic cylinder and the actuator connected to the control valve are identified; for the pneumatic path, the cylinder and the ejector system connected to the pneumatic distributor are identified. The system records the specifications, positions and functional parameters of the secondary slave components, such as the maximum force, stroke and response characteristics of the injection actuator. The energy transfer characteristics are analyzed, such as the mechanical efficiency of the reduction gearbox to the injection unit is 92%, with a delay of about 25ms; the efficiency of the hydraulic valve to the hydraulic cylinder is 88%, with a delay of about 75ms. Finally, the master-slave component hierarchical data containing the complete hierarchical relationship of the primary and secondary slave components is generated, with a total of 94 key components in the hierarchical structure.

[0030] Step S25: performing correlation analysis of operating parameters between components according to component operating status data, calculating the influence of the master component parameter change on the slave component parameters, determining the parameter correlation strength, and thus obtaining a component parameter influence matrix; The embodiment of the present invention analyzes the correlation of each component in the 30-day (about 720-hour) operation data of the injection molding machine. The time series data is divided into 10-minute windows (step length 1 minute), and 43,200 analysis windows are generated. The main component parameter change points are marked, such as the main motor current increases from 35A to 48A, and the slave component response is tracked, such as the reduction box temperature increases from 45°C to 53°C. The parameter response characteristics are calculated by statistical analysis: average delay time (the average response from the motor current change to the reduction box temperature is 15 minutes), response amplitude ratio (a 37% increase in motor current leads to a 17.8% increase in reduction box temperature) and response consistency (the frequency of occurrence of this relationship). Calculate the influence coefficient: slave component change amplitude / main component change amplitude × delay inverse factor × consistency score, such as the main motor on the reduction box temperature influence coefficient = 17.8% / 37% × (1 / (15 / 60+0.1)) × 0.85 = 0.67. A 94×94 component parameter influence matrix is ​​formed, and the element value range 0-1 represents the influence intensity.

[0031] Step S26: construct a visualized component transfer chain relationship diagram based on the master-slave component hierarchy data and the component parameter influence matrix, wherein the nodes of the component transfer chain relationship diagram represent the components, the connecting lines represent the influence relationship between the components, and the line thickness represents the influence strength.

[0032] The embodiment of the present invention constructs a component transfer chain relationship diagram of an injection molding machine. In the graphics engine, 94 component nodes are arranged according to physical position and hierarchical relationship: the main component is at the top, the first-level slave component is in the middle, and the second-level slave component is at the bottom. The node size reflects the importance, such as 100 pixels for the main motor EM-001 and 60 pixels for the auxiliary valve PA-004. Adding connecting edges indicates the energy flow direction, and adjusting the line thickness according to the influence coefficient: 0.7-1.0 is 5 pixels, 0.4-0.7 is 3 pixels, 0.2-0.4 is 1.5 pixels, and <0.2 is a dotted line of 0.5 pixels. For example, the connection line from the main motor to the reducer is 4.5 pixels (influence coefficient 0.67). Use color coding to distinguish component types: electrical blue, hydraulic green, pneumatic yellow; connection type: mechanical black, hydraulic green, pneumatic yellow, signal red. Finally, an interactive chart in SVG or HTML5 format is generated, which supports zooming, viewing details and filtering display, and provides a visualization tool for fault analysis.

[0033] The present invention extracts the physical connection relationship and energy transfer path information of the components by parsing the equipment structure drawing data, and accurately obtains the physical topological structure of the components. Based on the topological structure, the energy input components in the equipment, such as motors, hydraulic pumps and pneumatic devices, are identified and marked as main components to ensure the correct understanding of the energy transfer process of the equipment. On this basis, according to the direction of energy flow, the transmission components directly connected to the main component, such as gear boxes, pulleys and bearings, are identified and marked as first-level slave components, so that the relationship between the master and slave components is clearer. Further along the energy transfer path, the execution components connected to the first-level slave components, including actuators, working heads and functional components, are determined, and are marked as second-level slave components to form a complete master-slave component hierarchical relationship. Combined with the component operation status data, the correlation analysis of the operating parameters between the components is performed, the degree of influence of the changes in the parameters of the main component on the slave components is calculated, the dependencies between the components are quantified, and the component parameter influence matrix is ​​obtained. Finally, based on the hierarchical relationship of master-slave components and the parameter impact matrix, a visual component transfer chain relationship diagram is constructed, with nodes representing each component, connecting lines representing the impact relationship between components, and line thickness reflecting the intensity of the impact. This provides intuitive data support for equipment operation monitoring, fault tracing, and maintenance optimization, and improves the accuracy of equipment status analysis.

[0034] Preferably, step S25 comprises the following steps: Step S251: extracting the time series of operating parameters of each component under different working conditions from the component operating status data, thereby obtaining component parameter historical change data; The embodiment of the present invention extracts the time series of the operating parameters of each component under different working conditions from the data acquisition platform of the injection molding equipment. The continuous production data of the last 30 days are selected, covering various working conditions of different product models and process parameters. The main components such as motors are sampled at a high frequency of 1Hz, and the parameters with slow changes such as temperature are sampled at a low frequency of 0.1Hz. The exported raw data include the current (1Hz, ±0.1A), temperature (0.1Hz, ±0.5℃) and vibration (10Hz, ±0.01mm / s) of the main motor EM-001, the pressure (1Hz, ±0.1MPa) and flow (1Hz, ±0.5%) of the main hydraulic pump HP-001, and the air pressure and flow of the main pneumatic valve PA-001. The data is preprocessed: the 3σ rule is used to detect outliers, the linear interpolation method is used to fill missing values, and the Butterworth low-pass filter is used to remove noise. The processed data is organized into a standard time series, including timestamp, component ID, parameter type, parameter value and working condition identification. For example, the current data of the main motor when producing ABS products and the mold temperature is 80°C contains about 2.6 million sampling points, forming a complete historical change curve. Finally, a parameter historical change data set is generated for 94 key components, with a total of about 500GB.

[0035] Step S252: segmenting the data of the main component in the component parameter historical change data, identifying the time point when the parameter changes significantly, and taking the time point when the parameter changes significantly as the reference time node, thereby obtaining the main component parameter change mark data; The embodiment of the present invention performs segmented processing and significant change point identification on the historical data of the main component parameters. Taking the main motor EM-001 as an example, it is first segmented according to the production batch, and each batch contains a complete injection molding cycle (20-35 seconds). The CUSUM cumulative sum algorithm is used to detect the trend change point, and the target average value is set to the normal operating parameter mean, the sensitivity parameter is 0.5 times the standard deviation, and the threshold is 5 times the standard deviation. At the same time, the sliding window method (window 5 seconds) is used to calculate the parameter change rate. When the current change rate exceeds 1A / second or the temperature change rate exceeds 0.5℃ / second, it is marked as a change point. The system calculates the percentage of the difference between the stable values ​​before and after the change to the value before the change as the change amplitude, and takes the average value of the 5 seconds before the change point before the change, and takes the average value of 5-10 seconds after the change point after the change. Screen out the key change points where the current change amplitude exceeds 10% or the temperature change amplitude exceeds 5%. For example, in a certain injection molding cycle, it is detected that the main motor current rises from 32A to 46A (change amplitude 43.8%) at t=128356 seconds, which is recorded as the key reference time node. The system identified approximately 12,800 significant change points in 30 days of data, forming a main component parameter change marker dataset.

[0036] Step S253: Analyze the parameter changes of the slave components before and after the corresponding time points according to the parameter change mark data of the master component, and calculate the time delay and response amplitude between the parameter changes of the slave components and the parameter changes of the master component, so as to obtain the parameter response characteristic data between the components; The embodiment of the present invention analyzes the parameter response characteristics of the slave component based on the main component change mark data. For each main component change point, a list of directly connected slave components is extracted from the component transfer chain diagram, and an observation window is defined (10 seconds before the main component change point to 120 seconds after). The slave component parameter change pattern is searched in the window, and the parameter trend change is detected by the pattern matching algorithm. When the parameter difference signs of three consecutive time points are the same and non-zero, it is determined to be a valid trend. The time difference between the slave component change point and the master component change point is calculated as the delay time, and the difference in parameter values ​​before and after the slave component change (5 seconds before and 5 seconds after the change point) is calculated as the percentage of the value before the change as the response amplitude. Record the response consistency index, that is, the percentage of samples with detected response relationships in the total number of samples. For example, after the current of the main motor EM-001 increases from 32A to 46A (43.8%), the temperature of the reducer GB-001 rises from 42°C to 48°C (14.3%) after 15 seconds. This response is consistent with 85% in the sample. The system generates a total of about 25,000 master-slave component parameter response records, forming inter-component parameter response characteristic data.

[0037] Step S254: Calculate the parameter influence coefficients between each pair of master and slave components according to the inter-component parameter response characteristic data, thereby obtaining a component influence coefficient matrix, wherein the parameter influence coefficient = (slave component parameter change amplitude / master component parameter change amplitude) × 1 / delay time; The embodiment of the present invention calculates the influence coefficient between the master and slave components and constructs a matrix based on the parameter response characteristic data. The influence coefficient calculation considers three factors: the ratio of the change amplitude of the slave component parameter to the change amplitude of the master component (transmission efficiency), the inverse factor of the time delay (the shorter the delay, the more direct the impact) and the response consistency percentage (to avoid accidental overestimation of association). The system sets the time delay influence parameter 0.05 and the parameter 0.1 to prevent the denominator from being zero. Filter valid samples with a response consistency greater than 50%, and take the average of multiple measurements to reduce random fluctuations. For example, the influence coefficient of the main motor EM-001 on the reducer GB-001 is calculated as follows: the temperature change of the reducer is 12% ÷ the main motor current change is 35% × 1 / (15 seconds delay × 0.05 + 0.1) × 85% consistency ≈ 0.55. The system calculates the influence coefficients of 94 key components in pairs, forming a 94×94 matrix, in which most of the elements are 0 (there is no direct impact between the two components), and the non-zero elements are concentrated between the interconnected component pairs, and the matrix sparsity is about 85%.

[0038] Step S255: normalizing the component influence coefficient matrix to obtain a component influence coefficient standard matrix; The embodiment of the present invention normalizes the matrix of component influence coefficients to make parameters of different types comparable. First, global maximum and minimum value normalization is performed, and each influence coefficient is subtracted from the minimum value of the non-zero elements of the matrix (0.05), and then divided by the difference between the maximum value (0.92) and the minimum value, and all coefficients are mapped to the range of 0-1. Then, correction coefficients are applied to different types of component pairs: the electrical-mechanical relationship is multiplied by 1.0, the electrical-hydraulic relationship is multiplied by 1.2 (the hydraulic response is slow and the impact is often underestimated), and the hydraulic-pneumatic relationship is multiplied by 1.1. Considering the differences in component importance, weights are assigned to each component according to its position and function in the transmission chain, such as a main motor weight of 1.0 and an auxiliary cooling pump weight of 0.7. The influence coefficient is adjusted by multiplying the geometric mean of the weights of the two components to highlight the impact of key components. Finally, fine-tuning is performed to ensure that important physical associations are not underestimated due to numerical calculations, and a standard matrix of component influence coefficients with a value range of 0-1 is generated.

[0039] Step S256: According to a preset influence threshold, the component influence coefficient standard matrix is ​​screened for component pairs whose influence coefficients are greater than the threshold, thereby obtaining a component parameter influence matrix.

[0040] The embodiment of the present invention sets hierarchical thresholds for screening based on the standard matrix of influence coefficients: the threshold for first-level component pairs (main components and directly connected slave components) is 0.2, the threshold for second-level component pairs (separated by one intermediate component) is 0.3, and the threshold for third-level and above component pairs is 0.4. The system determines the level relationship of each pair of components through the shortest path in the component transfer chain relationship diagram, and then compares it with the corresponding threshold. For example, the main motor EM-001 and the reduction box GB-001 are a first-level component pair, and the standardized influence coefficient of 0.78 is greater than the threshold of 0.2, and is retained in the final matrix; while the main motor and the remote actuator AC-008 are a third-level component pair, and the influence coefficient of 0.35 is less than the threshold of 0.4, and is set to zero in the final matrix. The sparsity of the component parameter influence matrix after screening is increased to about 95%, and only the most significant component influence relationship in the device is retained. The final matrix is ​​stored in a compressed sparse row format and exported to JSON or CSV format for easy use in other analysis systems.

[0041] The present invention constructs the historical change data of component parameters by extracting the time series of operating parameters of components under different working conditions, providing a basis for subsequent analysis. The parameter data of the main component is processed in sections, the time points when the parameters change significantly are identified, and these time points are used as reference nodes, so that the key state changes can be accurately located. Based on the parameter change mark data of the main component, the parameter changes of the slave component before and after the corresponding time point are analyzed, the response time delay and amplitude of the slave component to the change of the main component are calculated, the dynamic association relationship between the components is quantified, and the parameter response characteristic data between the components are obtained. On this basis, the parameter influence coefficient between the master and slave components is calculated, the influence degree of the master component change on the slave component is measured in a numerical way, and the component influence coefficient matrix is ​​formed. Subsequently, the component influence coefficient matrix is ​​normalized so that data of different magnitudes can be compared on the same scale to improve the accuracy of the calculation. Finally, according to the preset influence threshold, the component pairs with influence coefficients exceeding the threshold are screened out from the standardized influence coefficient matrix, and the component parameter influence matrix is ​​generated, so as to accurately reflect the dependency relationship between the master and slave components, and provide data support for equipment status monitoring, fault propagation analysis and predictive maintenance.

[0042] Preferably, the operating status parameters of the main components in the monitoring component transfer chain relationship diagram described in step S3 include: Determine the monitoring priority of the main component according to the component transfer chain relationship diagram, where the main component with energy input exceeding 15kW or connected to more than 5 slave components is set to high priority, the main component with energy input between 5kW-15kW or connected to 3-5 slave components is set to medium priority, and the remaining main components are set to low priority; Based on the monitoring priority of the main components, each main component is polled and sampled in different time periods to obtain the original data of the main component operation status; The original data of the main component operation status is smoothed based on a sliding window, with the window size being the first 10 sampling values, and weighted moving average processing is performed to obtain the smoothed data of the main component operation status, where the weight of the most recent time point is 0.3, and the sum of the weights of the remaining 9 historical points is 0.7; When the temperature deviation of the motor main component in the main component running status smoothing data exceeds 15°C, the vibration deviation exceeds 0.8mm / s, or the current deviation exceeds 12%, or when the pressure deviation of the hydraulic pump main component exceeds 1.5MPa, the flow deviation exceeds 10%, or the noise deviation exceeds 8dB, or when the air pressure deviation of the pneumatic device main component exceeds 0.1MPa, the flow deviation exceeds 15%, or the valve response time is extended by more than 30ms, the time point is recorded and the corresponding main component is marked as abnormal, and the abnormal timestamp data of the main component is obtained; According to the abnormal timestamp data of the main component, a set of slave components directly connected to the abnormal main component is extracted from the component transfer chain relationship diagram to obtain a list of related slave components; The main component operation status smoothing data, the main component abnormal timestamp data and the related slave component list are combined into the main component operation status parameters.

[0043] Based on the component transfer chain relationship diagram of the injection molding equipment, the embodiment of the present invention first scans all 17 identified main components and determines their monitoring priority levels according to the preset priority division rules. The specific operation method is: the system first reads the energy input parameters and the number of connected slave components of each main component from the component attribute database, for example, the rated power of the main drive motor EM-001 is 37kW, and the number of directly connected slave components is 6 (including coupling LC-200, reducer GB-001, etc.); the rated power of the main hydraulic pump HP-001 is 11kW, and the number of directly connected slave components is 4 (including various hydraulic valves and pipeline components); the rated power of the auxiliary pneumatic control valve PA-003 is 2.2kW, and the number of directly connected slave components is 2. The system classifies the main components according to the energy input threshold and the threshold of the number of connected slave components: when the energy input of the main component exceeds 15kW or the number of connected slave components exceeds 5, it is marked as high priority, for example, the main drive motor EM-001 (37kW, 6 slave components), the main load motor EM-002 (22kW, 5 slave components), a total of 5 components are marked as high priority; when the energy input of the main component is between 5kW and 15kW or the number of connected slave components is between 3 and 5, it is marked as medium priority, for example, the main hydraulic pump HP-001 (11kW, 4 slave components), the auxiliary drive motor EM-003 (7.5kW, 3 slave components), a total of 7 components are marked as medium priority; the remaining main components are marked as low priority, for example, the auxiliary pneumatic control valve PA-003 (2.2kW, 2 slave components), the small auxiliary motor EM-006 (1.1kW, 1 slave component), a total of 5 components are marked as low priority. Based on the monitoring priority of the main components, the system sets different data sampling frequencies: the sampling frequency of the high-priority main components is set to 5 seconds / time, the sampling frequency of the medium-priority main components is set to 15 seconds / time, and the sampling frequency of the low-priority main components is set to 30 seconds / time. The system develops a polling scheduler to sample each main component in an orderly manner according to the preset sampling schedule to avoid network congestion caused by sending data requests to multiple sensors at the same time. For different types of main components, the system configures dedicated data acquisition programs: the main components of motors mainly collect temperature, current and vibration parameters, the main components of hydraulic pumps mainly collect pressure, flow and oil temperature parameters, and the main components of pneumatic devices mainly collect air pressure, flow and response time parameters. The system also dynamically adjusts the sampling frequency according to the operating status of the component. When the main component parameters are close to the warning value (such as the motor temperature rises to 85% of the rated temperature), its sampling frequency is automatically increased. For periods of time when the working conditions change significantly (such as the injection stage and the pressure holding stage in the injection molding process), the system temporarily increases the sampling frequency of all main components to capture transient anomalies that may occur in key process processes. For example, during the injection phase of a certain injection molding cycle (lasting about 5 seconds), the system increases the sampling frequency of the main drive motor EM-001 from 5 seconds / time to 1 time per second.Through this time-segmented polling sampling mechanism, the system collected a total of about 286,000 pieces of raw data on the operating status of the main components during the three-shift production. For the acquired raw data, the system applied sliding window smoothing technology to eliminate short-term fluctuations and random noise. The system creates a data buffer for each parameter type of each main component, with a buffer size of 10 sampling points. For example, the temperature parameter buffer of the main drive motor EM-001 contains the temperature values ​​of the last 10 samples at a certain moment [65.2℃, 65.5℃, 66.1℃, 66.3℃, 66.8℃, 67.2℃, 67.5℃, 68.1℃, 68.4℃, 68.7℃]. The system applies a weighted moving average algorithm to the data in the buffer, with the latest data point assigned a weight of 0.3, and the remaining 9 historical data points sharing a weight of 0.7 (each is about 0.078). In the specific calculation, the system multiplies each data point by the corresponding weight and sums them up. For example, the weighted average of the above temperature data is 67.4℃. The system uses different smoothing techniques for different types of parameters: for vibration data, in addition to weighted moving average, frequency domain filtering technology is also used to remove specific frequency noise; for parameters with obvious periodicity, such as pressure changes in the injection molding cycle, the system uses a phase-aware smoothing algorithm to retain key cycle characteristics. The system also detects and processes abnormal outliers. When the deviation of a data point from the weighted average exceeds a preset threshold (such as 3 times the standard deviation), the point will be excluded from the smoothing calculation to avoid sensor failure or interference signals. Based on the smoothed data of the main component operation status, the system identifies and marks abnormal conditions for key parameters. The system reads the normal operating range and abnormal threshold of each main component parameter from the component configuration database: the standard operating temperature range of motor main components is ±10℃ of the rated temperature (the rated temperature of the main drive motor EM-001 is 55℃, and the normal range is 45-65℃), the standard vibration range is 0.1-0.6mm / s, and the rated current fluctuation range is ±8%; the standard pressure fluctuation range of hydraulic pump main components is ±5% of the rated pressure (the rated pressure of the main hydraulic pump HP-001 is 21MPa, and the normal range is 19.95-22.05MPa); the standard air pressure fluctuation range of pneumatic device main components is ±7% of the rated air pressure (the rated air pressure of the main pneumatic valve PA-001 is 0.8MPa, and the normal range is 0.744-0.856MPa).When the parameter deviates from the normal range and exceeds the preset threshold, the system marks the corresponding abnormal state: when the temperature of the main drive motor EM-001 reaches 80℃ (deviates from the rated temperature by more than 15℃), the vibration value reaches 1.5mm / s (exceeds the normal upper limit of 0.8mm / s) or the current deviation reaches 15% (exceeds the normal fluctuation range of 12%), the system marks it as motor abnormality; when the pressure of the main hydraulic pump HP-001 drops to 18.5MPa (deviates from the rated pressure by more than 1.5MPa) or the flow drops to 85% of the rated value (deviation exceeds 10%), the system marks it as hydraulic pump abnormality; when the air pressure of the pneumatic valve PA-001 drops to 0.65MPa (deviates from the rated air pressure by more than 0.1MPa) or the valve response time is extended to 60ms (exceeds the normal response time of 30ms), the system marks it as pneumatic equipment abnormality. The system records the exact timestamp of the abnormality, the type of abnormality, the abnormal parameter value and the degree of deviation, forming the abnormal timestamp data of the main component. For the identified abnormal main components, the system uses the component transfer chain relationship diagram to extract the slave components directly connected to these abnormal main components. First, the system reads the abnormal timestamp data of the main component to obtain the IDs of all currently detected abnormal main components; then, it queries the pre-built component transfer chain relationship diagram, executes the graph traversal algorithm, and starts from the abnormal node to find all directly connected slave component nodes; finally, it screens those component pairs whose influence coefficient exceeds 0.4 in the component parameter influence matrix to form a list of related slave components, including information such as slave component ID, type, functional description, connection relationship with the main component, and influence coefficient. The system finally integrates the main component operation status smoothing data, abnormal timestamp data, and related slave component lists to form a structured main component operation status parameter set, which includes basic information, status data, and related information, providing comprehensive data support for subsequent abnormal transmission analysis and maintenance decisions.

[0044] The present invention determines the monitoring priority of the main component through the component transfer chain relationship diagram, so that the monitoring resources are reasonably allocated. For the main component with energy input exceeding 15kW or more than 5 connected slave components, it is set to high priority to ensure real-time monitoring of key components; for the main component with energy input between 5kW and 15kW or 3-5 connected slave components, it is set to medium priority to achieve balanced monitoring; the remaining main components are set to low priority, so as to optimize the sampling frequency. Based on the monitoring priority, time-segment polling sampling is adopted to improve the monitoring efficiency and obtain the original data of the main component operation status. The smoothing processing and weighted moving average method of the sliding window are used to improve the stability and anti-interference ability of the data and reduce the impact of short-term fluctuations on the monitoring results. When the operating state deviation of the main component exceeds the set threshold, the abnormal timestamp is recorded in real time and the abnormal state is marked, so that the abnormal detection is more accurate and reliable. Subsequently, according to the abnormal timestamp data, the set of directly connected slave components is extracted in the component transfer chain relationship diagram, and the slave components that may be affected are quickly located to improve the fault tracing capability. Finally, the main component operating status smoothing data, abnormal timestamp data and related slave component lists are integrated to form complete main component operating status parameters, providing accurate data support for subsequent equipment health assessment, fault analysis and predictive maintenance.

[0045] Preferably, the extracting of the main component whose operating state parameter fluctuation exceeds a preset threshold value and measuring the response parameter change of the connected slave components in step S3 includes: Calculate the fluctuation amplitude of the main component of the main component operation status parameter; Compare the fluctuation amplitude data of the main components with the preset fluctuation thresholds to obtain the over-threshold main component identification data, where the preset fluctuation thresholds are: the temperature fluctuation threshold of the motor main components is 8%, and the speed fluctuation threshold is 5%; the pressure fluctuation threshold of the hydraulic pump main components is 12%; and the air pressure fluctuation threshold of the pneumatic device main components is 15%; According to the list of related slave components, the master components in the super-threshold master component identification data are screened based on the physical connection distance and the energy transfer efficiency to obtain a list of slave components to be tested; Perform high-frequency sampling on the slave components in the list of slave components to be tested to obtain the original response data of the slave components; The original data of the slave component response is processed based on segmentation before, during and after the fluctuation, and the average value, standard deviation and change trend of each time period are calculated. The temperature change slope, vibration spectrum change and pressure fluctuation characteristics are recorded respectively to obtain the characteristic data of the slave component response; The parameter change pattern analysis is performed on the component response characteristic data to identify the response delay time, peak response and steady-state response, and the response attenuation rate and resonant frequency are calculated to obtain the response parameter changes.

[0046] In the operation monitoring of the injection molding equipment of the embodiment of the present invention, the system first calculates the fluctuation amplitude of the operating status parameters of each main component and identifies abnormal parameter changes. The system sets an observation window (5 minutes) for different types of main components, focusing on the temperature, speed, and current parameters of motor components, the pressure, flow, and efficiency parameters of hydraulic pump components, and the air pressure, flow, and response time parameters of pneumatic device components. The maximum and minimum values ​​of the parameters are recorded in the observation window, such as the maximum temperature of the main drive motor EM-001 is 78°C and the minimum temperature is 72°C (standard operating temperature is 70°C). The system calculates the fluctuation amplitude, that is, the percentage of the difference between the maximum and minimum values ​​in the standard working value: the temperature fluctuation amplitude of the main motor EM-001 is (78-72) / 70×100%=8.57%; the speed fluctuation amplitude is (1580-1490) / 1500×100%=6%; the pressure fluctuation amplitude of the hydraulic pump HP-001 is (22.8-19.2) / 21×100%=17.14%; the air pressure fluctuation amplitude of the pneumatic valve PA-001 is (0.92-0.76) / 0.8×100%=20%. The system analyzes the fluctuation frequency characteristics through fast Fourier transform, such as the main frequency of the main motor temperature fluctuation is 0.033Hz (about 30 seconds per cycle). The system compares the fluctuation amplitude data with the preset threshold value, and reads the fluctuation threshold standards of different types of main components from the configuration database: the temperature fluctuation threshold of motor components is 8%, and the speed fluctuation threshold is 5%; the pressure fluctuation threshold of hydraulic pump components is 12%, and the flow fluctuation threshold is 10%; the air pressure fluctuation threshold of pneumatic device components is 15%, and the flow fluctuation threshold is 12%. When the actual fluctuation amplitude exceeds the threshold, it is marked as abnormal fluctuation: the main motor temperature fluctuation of 8.57%>8% is marked as abnormal temperature fluctuation; the main motor speed fluctuation of 6%>5% is marked as abnormal speed fluctuation; the hydraulic pump pressure fluctuation of 17.14%>12% is marked as abnormal pressure fluctuation; the pneumatic valve air pressure fluctuation of 20%>15% is marked as abnormal air pressure fluctuation. The system records the abnormal type, fluctuation amplitude, threshold exceeding degree and duration of each abnormal component, and classifies them by severity: exceeding the threshold by 0-20% is mild fluctuation abnormality, 20-50% is moderate fluctuation abnormality, and more than 50% is severe fluctuation abnormality. The system integrates all fluctuation abnormal component information into the identification data of the main component exceeding the threshold. Next, the system screens the slave components that may be affected, and extracts the slave components directly connected to each super-threshold master component from the component transfer chain relationship diagram, such as the coupling LC-200 and the reducer GB-001 connected to the main motor EM-001. The system performs preliminary screening based on the physical connection distance, giving priority to slave components that are closer to the main components, such as the distance between the coupling LC-200 and the main motor EM-001 is 0.15 meters, and the distance between the reducer GB-001 and the main motor is 0.3 meters, both of which are less than the threshold of 50 centimeters. The system also considers the energy transfer efficiency, such as the energy transfer efficiency from the main motor to the coupling is 98%, and the efficiency to the reducer is 95%, both of which are higher than the threshold of 65%.The system further considers the parameter influence coefficients, such as the temperature influence coefficient of the main motor on the reducer box is 0.67, and the temperature influence coefficient on the coupling is 0.82, both of which are higher than the threshold value of 0.3. Taking these factors into consideration, the system generates a priority list of slave components to be tested. The system performs high-frequency sampling (0.5 seconds / time) on the slave components to be tested, and configures monitoring parameters for different types of components: mechanical transmission components such as the reducer GB-001 monitor temperature (accuracy ±0.2℃), vibration (accuracy ±0.05mm / s) and noise (accuracy ±1dB); hydraulic components such as the control valve HV-004 monitor pressure (accuracy ±0.05MPa), flow (accuracy ±0.5%) and oil temperature (accuracy ±0.5℃). The system continuously monitors for 120 seconds, synchronously records the ambient temperature (22-28℃) and equipment load status, and adopts redundant sensor design to ensure data accuracy. The system processes the raw data of the slave component response in sections, which are divided into the pre-segment of fluctuation (30 seconds to 0 seconds before the main component abnormality), the middle segment of fluctuation (0 seconds to 60 seconds after the abnormality) and the post-segment of fluctuation (60 seconds to 120 seconds after the abnormality). Statistical features are calculated for each time period, such as the average temperature of the gearbox GB-001 in the pre-segment of fluctuation is 52.3℃ (standard deviation 0.5℃), the average temperature in the middle segment of fluctuation is 57.8℃ (standard deviation 2.1℃), and the average temperature in the post-segment of fluctuation is 61.5℃ (standard deviation 0.7℃). The system calculates the temperature change slope, such as the temperature change slope of the gearbox in the middle segment of fluctuation is 5.5℃ / minute; analyzes the vibration spectrum changes, such as the appearance of a new frequency component of 42Hz in the middle segment of fluctuation of the gearbox; analyzes the pressure fluctuation characteristics, such as the increase in the pressure fluctuation range of the hydraulic control valve in the middle segment of fluctuation; and performs fitting analysis on the change trend of each parameter to determine the change mode. Finally, the system analyzes the parameter change pattern and determines the response delay time, such as the temperature of the gearbox starts to rise 15 seconds after the main motor abnormality; identifies the peak response characteristics, such as the gearbox temperature reaches 63.2℃, with a change range of 10.9℃; analyzes the steady-state response characteristics, such as the gearbox temperature is stable at 62.5±0.5℃; calculates the response attenuation rate (0.82) and resonant frequency (0.05Hz); identifies the abnormal transmission mode and path, such as the abnormality is transmitted from the main motor to the coupling (8 seconds), then to the gearbox (15 seconds), and finally to the bearing (22 seconds), confirming that the abnormality is transmitted step by step along the energy transmission chain. These analysis results form a complete response parameter change situation, providing data support for subsequent abnormal transmission confirmation and fault diagnosis.

[0047] The present invention accurately evaluates the stability of the main component by calculating the fluctuation amplitude of the main component operation state parameters, and compares the calculation results with the preset fluctuation threshold to identify the main component that exceeds the threshold. Exclusive fluctuation thresholds are set for different types of main components, such as 8% temperature fluctuation and 5% speed fluctuation of motor main components, 12% pressure fluctuation of hydraulic pump main components, and 15% air pressure fluctuation of pneumatic device main components, to ensure the pertinence and accuracy of abnormal detection. For the main components that exceed the threshold, they are screened based on the physical connection distance and energy transfer efficiency to reduce the interference of irrelevant components, ensure the rationality of the analysis object, and then obtain the list of slave components to be tested. The slave components to be tested are sampled at high frequency to obtain accurate response data, and the data is processed in segments to extract the key parameters of the three time periods before, during and after the fluctuation, including the average value, standard deviation and change trend, so as to obtain the detailed response characteristics of the slave components. By calculating the temperature change slope, vibration spectrum change and pressure fluctuation characteristics, the understanding of the operating status is further improved. Subsequently, based on the parameter change pattern analysis, the response delay time, peak response and steady-state response of the slave components are identified, the response characteristics of the system are quantified, and the response attenuation rate and resonant frequency are calculated to evaluate the dynamic adaptability of the slave components and the stability of the system. Ultimately, this method forms the response parameter changes of the slave components, providing data support for accurately determining the abnormal transmission path, optimizing the equipment monitoring strategy and improving the accuracy of predictive maintenance.

[0048] Preferably, generating abnormal transmission confirmation data according to the response parameter change in step S3 includes: Establish equipment abnormal pattern recognition database; According to the equipment abnormal pattern recognition database, the response parameter changes are matched and calculated based on vector similarity to obtain the fault pattern matching data; Screen potential fault types with a matching degree exceeding 75% from the fault mode matching degree data to obtain the fault type probability distribution data; The deviation rate between the actual response delay time and the preset theoretical transmission time of the slave component response parameters is calculated, and the amplitude attenuation coefficient and spectrum feature offset analysis are performed to obtain the abnormal transmission confirmation probability data; The fault type probability distribution data and the abnormal transmission confirmation probability data are weighted and fused, and the credibility score is calculated. When the score exceeds the preset threshold of 0.8, it is confirmed as a valid abnormal transmission and the abnormal transmission confirmation result is obtained; According to the abnormal transmission confirmation result, the main component information, the slave component information, the fault type probability, the transmission characteristics and the credibility score are structured and integrated to obtain the abnormal transmission confirmation data.

[0049] In the intelligent maintenance system of injection molding equipment in the embodiment of the present invention, an equipment abnormal pattern recognition database is first established as the knowledge basis for abnormal diagnosis. The system extracts fault repair data from the enterprise equipment maintenance records for the past three years, involving 583 fault cases; employs 3 senior equipment maintenance experts to classify the faults into 12 main fault categories and 48 typical fault modes; for each fault mode, a characteristic parameter set is sorted out, including the abnormal parameter characteristics of the main component (temperature rise rate, vibration spectrum characteristics, etc.) and the response characteristics of the slave component (response delay time, peak response ratio, etc.); a feature vector containing 20-30 dimensions is established for each fault mode; the development speed, severity and recommended treatment measures of each fault mode are recorded; and finally a hybrid architecture database is formed with self-learning capabilities. Based on this database, the system performs fault pattern matching analysis on the current response parameter changes. First, the currently observed temperature anomaly of the main motor EM-001 and the response of the slave components are integrated into the query feature vector, including about 25 feature dimensions such as temperature rise rate (2.8℃ / minute), vibration frequency (35Hz), current fluctuation (12%), and gearbox response delay (15 seconds), temperature rise (10.9℃); the cosine similarity algorithm is used to calculate the similarity between the current feature and each fault mode in the database, and the feature vector is normalized and the similarity score is calculated; different weights are set for different feature dimensions, such as the temperature rise rate weight 1.5 and the vibration frequency feature weight 1.2; adaptive adjustments are made considering background information such as equipment running time and ambient temperature; finally, the similarity, matching feature number and key feature matching degree of each fault mode are recorded by score sorting, and the fault mode matching data is formed. The current case has a similarity of 0.83 (83%) with the "motor bearing overheating" mode, 0.65 (65%) with the "motor winding short circuit initial stage", and 0.59 (59%) with the "gearbox insufficient lubrication". The system sets the fault mode matching screening threshold to 75%, extracts the fault modes that meet the conditions from the matching results. In the current case, only "motor bearing overheating" (83%) exceeds the threshold; combined with the historical fault records of the equipment, the motor has experienced overheating caused by "bearing overheating" twice and "fan failure" once in the past two years, so the weight is increased by 0.15; considering seasonal factors, the fault occurrence rate in the high temperature environment in summer (28℃) is 30% higher than that in winter, and the weight is increased by 0.1; recalculate the probability distribution, the final probability of "motor bearing overheating" is 83%×(1+0.15+0.1)=103.75%, recorded as 100%; other fault modes with matching degrees lower than the threshold are used as secondary references, such as "motor winding short circuit in the early stage" (15%) and "gearbox insufficient lubrication" (10%). The system verifies the physical rationality of abnormal transmission, extracts the theoretical transmission time parameters between components from the physical model of the equipment, compares the actual response delay of the components with the theoretical time, and calculates the deviation rate.For example, the actual response delay from the main motor to the gearbox is 15 seconds, while the theoretical time is 8-12 milliseconds, and the deviation rate is about 124900%, indicating that this is caused by physical processes such as heat accumulation; analyzing the amplitude attenuation coefficient, the temperature rise of the main motor is 15℃, the temperature rise of the gearbox is 10.9℃, and the coefficient is 0.73, which is within the reasonable range of 0.6-0.9; analyzing the spectrum feature offset, the main motor vibrates 35Hz, and the gearbox is 34Hz, and the offset is within the reasonable range of ±5Hz; the comprehensive calculation of the physical credibility is 0.88 (88%), indicating that the abnormal transmission is physically reasonable. The system sets the fault type probability weight 0.6, the abnormal transmission confirmation probability weight 0.4, and calculates the comprehensive credibility score. For the transmission relationship of "motor bearing overheating" leading to abnormal gearbox temperature, the comprehensive score is 100%×0.6+88%×0.4=95.2%, which is much higher than the preset threshold of 0.8 (80%), so it is confirmed as effective abnormal transmission; compare the scores of different transmission paths to determine the main and secondary transmission paths. Finally, the system integrates the main component information (EM-001, main drive motor, temperature 80°C, exceeding the standard by 15°C, and lasting for 45 minutes), related slave component information (GB-001, LC-200, etc., including response parameters, values, and time), fault type probability ("motor bearing overheating" 100%, "initial motor winding short circuit" 15%, "inadequate reduction gearbox lubrication" 10%), transfer characteristics (transfer path, speed of approximately 8 cm / s, temperature transfer attenuation coefficient 0.73, heat conduction type transfer) and comprehensive credibility score (95.2%); calculates the fault severity level (level 3, moderate fault) and development expectations (expected to develop into level 4 severe fault after 12 hours), generates processing suggestions and maintenance window suggestions, and forms structured abnormal transmission confirmation data to provide comprehensive support for maintenance decisions.

[0050] The present invention constructs an equipment abnormal pattern recognition database, systematically stores the historical fault patterns of various types of equipment, and provides basic data support for subsequent matching calculations. According to the response parameter changes of the slave components, a matching analysis is performed using a vector similarity calculation method to quantify the matching degree of the fault pattern, and screen potential fault types with a matching degree of more than 75% to form fault type probability distribution data, thereby improving the accuracy of fault identification. On this basis, by calculating the deviation rate between the actual response delay time and the theoretical transmission time, and combining the amplitude attenuation coefficient and the spectrum feature offset analysis, the characteristics of the abnormal signal transmission between components are evaluated, and then the probability of abnormal transmission confirmation is quantified. Subsequently, the fault type probability distribution data and the abnormal transmission confirmation probability data are weighted and fused, and the credibility score is calculated to comprehensively measure the effectiveness of abnormal transmission. A credibility threshold of 0.8 is set. When the score exceeds the threshold, it can be determined that the abnormal transmission has been effectively confirmed, thereby improving the reliability of diagnosis. Ultimately, this method structuredly integrates the main component information, slave component information, fault type probability, transmission characteristics and credibility score to generate complete abnormal transmission confirmation data, providing a traceable and analyzable basis for equipment health management, while providing high-quality data support for accurate early warning and maintenance optimization.

[0051] Preferably, step S4 comprises the following steps: Step S41: Establish a master-slave component abnormal relationship matrix based on the abnormal transmission confirmation data, identify the main path and diffusion mode of abnormal transmission, and obtain abnormal propagation chain data; In the operation monitoring of a large injection molding equipment in the embodiment of the present invention, the system first extracts all abnormal transmission events recorded in the last 90 days from the abnormal transmission confirmation database, including 28 abnormal events and 63 slave component response events of main components such as 1 37kW main drive motor, 4 2.2kW auxiliary motors, 6 servo motors, 2 hydraulic pumps and 4 pneumatic control valve groups. The system uses these data to construct a 94×94 master-slave component abnormal relationship matrix (including all involved master components and slave components), and the element values ​​in the matrix represent the abnormal transmission confirmation probability between the corresponding components. For example, the abnormal transmission confirmation probability between the main drive motor EM-001 and the reduction box GB-001 is 0.87, indicating that when the main motor is abnormal, there is an 87% probability that the reduction box will subsequently be abnormal. Based on this matrix, the system applies the path analysis algorithm in graph theory, specifically adopting the weighted breadth-first search method, to identify the main path of abnormal transmission, such as the abnormal transmission path from the main drive motor (EM-001) → coupling (LC-200) → reduction box (GB-001) → bearing (B-001), with abnormal confirmation probabilities of 0.87, 0.76, and 0.68, forming the main transmission path; at the same time, the diffusion mode is identified, including the step-by-step attenuation mode (such as the gradual weakening of the impact of the main motor abnormality) and the branch diffusion mode (such as the hydraulic pump HP-001 abnormality affecting multiple hydraulic control valves at the same time). The system integrates these identified paths, impact strengths, and diffusion modes into an abnormal propagation chain data structure, which contains information such as abnormal source components, affected component sequences, impact probabilities at each level, and diffusion characteristics, providing a basis for subsequent time analysis.

[0052] Step S42: Statistically analyze the abnormal transmission time intervals of the connected components in the abnormal propagation chain data, calculate the average delay time and fluctuation range between different component pairs, and obtain the abnormal transmission time data between components; In the embodiment of the present invention, the system conducts in-depth analysis from the time dimension for the abnormal propagation chain data, focusing on the time characteristics of the transmission of abnormalities between the components of the injection molding equipment. In specific operations, the system first extracts the timestamps of abnormal events between each pair of connected components from the historical monitoring data of the injection molding equipment, such as the main drive motor EM-001 has a temperature abnormality at 10:23:45.32 on June 15, 2023, and the connected reducer GB-001 has a temperature rise abnormality at 10:24:12.58 on June 15, 2023, and the calculated time interval is 27.26 seconds. The system counts the historical abnormal events (a total of 47 times) of the same pair of components (such as EM-001 and GB-001), calculates the average delay time (28.35 seconds in this example) and its standard deviation (5.12 seconds), and thus determines the fluctuation range to be 18.11 seconds to 38.59 seconds (mean ± 2 times the standard deviation). The system further analyzed the relationship between the delay time and the equipment operating conditions and found that under high load conditions (such as when injecting high-viscosity materials), the average delay time was shortened to 22.65 seconds, while under low load conditions it was extended to 34.82 seconds, indicating that the load has a significant effect on the speed of abnormal transmission. In addition, the system also examined the ambient temperature factor and found that for every 5°C increase in ambient temperature, the average delay time decreased by about 2.3 seconds, indicating that temperature has a promoting effect on abnormal transmission. Finally, the system established a complete abnormal transmission time data model for each pair of connected components in the abnormal transmission chain, including parameters such as average delay time, fluctuation range, sensitivity of influencing factors, and conditional correlation, providing accurate time feature data for subsequent pattern learning and prediction.

[0053] Step S43: input the abnormal transmission time data between components into the large model to perform time series pattern learning, identify typical abnormal development laws including periodic patterns, gradual patterns and jump patterns, and obtain component abnormal time series feature data; The system of the injection molding equipment in the embodiment of the present invention inputs the calculated abnormal transmission time data between components into a large model based on the Transformer architecture for time series pattern learning, and the model analyzes and identifies the time pattern through the self-attention mechanism. In the specific implementation process, the abnormal transmission time data accumulated on the injection molding equipment is first grouped by component pairs to construct a feature vector sequence containing 968 abnormal transmission events in the past 12 months. 35 key features are extracted for each abnormal transmission event, including: main component type (such as 37kW main drive motor), slave component type (such as reducer), transmission time interval, main component abnormal intensity (such as temperature exceeding the standard), slave component response intensity, injection molding process parameters (such as injection pressure, holding time, injection speed), mold temperature, ambient temperature, operation duration, etc. The data is sorted into a standardized feature matrix and then input into the large model. The model parameters include: 8 layers of Transformer encoders, 12 attention heads per layer, hidden layer dimension 768, training batch size 32, learning rate set to 0.0001, Adam optimizer is used for training, and the training cycle is 100 rounds. Through model analysis, the system successfully identified three typical abnormal development patterns in injection molding equipment: periodic pattern (such as the hydraulic pump HP-001 has a fixed pressure fluctuation abnormality after 48 hours of continuous operation, with obvious periodic characteristics), gradual change pattern (such as the temperature of bearing B-001 slowly rises at an average rate of 0.5°C per hour, showing a linear growth trend) and jump pattern (such as the vibration value of reducer GB-001 suddenly increases by 65% ​​after being subjected to instantaneous overload, and stabilizes at a new level). The model's recognition accuracy for these patterns reached 92.3%, much higher than the 74.5% of traditional statistical methods. The system integrates the identified pattern characteristics, development laws and applicable conditions into component abnormal time series feature data, including information such as pattern type, key parameters, fitting equations, prediction reliability and applicable conditions.

[0054] Step S44: extracting the development trajectory of the fault from a preset historical fault database according to the component abnormal time series feature data, matching the evolution process of the fault from the initial abnormality to the maintenance critical state, thereby obtaining fault evolution reference data; Based on the component abnormal time series feature data, the system of the injection molding equipment in the embodiment of the present invention then matches and analyzes with the preset historical fault database. The database contains 2,835 equipment failure cases recorded by the injection molding equipment manufacturer in the past 10 years. Each case records in detail the complete information such as the faulty component, the initial abnormal performance, the abnormal development history, the maintenance measures and the replacement record. The system uses a similarity matching algorithm to compare the currently identified abnormal time series features with the historical cases and calculate the cosine similarity between the feature vectors. For example, it is currently detected that the temperature of the main drive motor EM-001 rises in a gradual mode, with an initial temperature of 65°C and a rising rate of 0.8°C / hour. The vibration spectrum has an obvious peak at 180Hz. The system matches these features with the cases in the historical database and finds a historical case with a similarity of 0.87 (case ID: FL20180329-EM016). The case records the complete development process of a motor of the same model from the beginning of abnormality to the complete damage of the bearing, including the temperature starting from 67°C, rising at a rate of 0.9°C / hour, and the bearing fails after reaching the critical value of 132°C after 72 hours. The system extracts the complete fault development trajectory of this case and five other cases with a similarity of more than 0.75, analyzes the parameter change trend, accelerated decay point and critical state characteristics, and establishes a fault evolution reference model for the current abnormality based on the commonalities and differences of these cases. The model records the possible evolution path from the current state (such as the bearing temperature of 65°C) to the critical state of maintenance (such as the temperature exceeds the rated value by 40°C and reaches 95°C), including key stage points, parameter change rate and state transition characteristics, forming a complete fault evolution reference data.

[0055] Step S45: Calculate the remaining time required for the component to reach the maintenance critical value based on the fault evolution reference data, and obtain the component maintenance window data, where the maintenance critical value of motor components is that the temperature exceeds the rated value by 40°C or the vibration amplitude exceeds 2.5mm / s, the maintenance critical value of hydraulic pump components is that the pressure fluctuation exceeds the rated value by 25% or the internal leakage rate exceeds 12%, and the maintenance critical value of pneumatic device components is that the air pressure drops by more than 30% of the rated value or the response time is extended by more than 150ms.

[0056] According to the fault evolution reference data, the system of the injection molding equipment in the embodiment of the present invention begins to accurately calculate the remaining time required for the component to reach the maintenance critical value. Taking the reduction box GB-001 that has detected an abnormality as an example, its current temperature is 78°C (28°C higher than the rated temperature of 50°C) and the vibration value is 1.8mm / s. The system first determines the maintenance critical value of the component: as a motor component, its maintenance critical value is that the temperature exceeds the rated value by 40°C (that is, reaches 90°C) or the vibration amplitude exceeds 2.5mm / s. According to the prediction model of the fault evolution reference data, under the current equipment load conditions (injection pressure 21MPa, injection speed 85mm / s, ambient temperature 28°C), the reduction box temperature is expected to rise at an average rate of 0.6°C per hour, and it takes (90-78) / 0.6=20 hours to reach the temperature critical value; at the same time, the vibration value increases at a rate of 0.04mm / s per hour, and it takes (2.5-1.8) / 0.04=17.5 hours to reach the vibration critical value. The system takes the shorter of the two times, 17.5 hours, as the estimated remaining operating time, and based on historical reliability analysis, calculates the predicted confidence interval to be 17.5±2.3 hours (95% confidence level). The system further analyzes and finds that if the equipment load is reduced to 65% (such as reducing the injection pressure to 15MPa), the temperature rise rate can be reduced to 0.4°C per hour, and the remaining operating time can be extended to 30 hours; if additional cooling measures are implemented (such as adding cooling fans), the temperature rise can be further suppressed and the remaining time can be extended to 36 hours. Taking these factors into consideration, the system generates component maintenance window data, including component ID, current status value, critical value, estimated remaining time (basic situation and intervention situation), predicted reliability and maintenance urgency, providing a decision-making basis for the maintenance plan of injection molding equipment.

[0057] The present invention systematically identifies the main path and diffusion mode of abnormal transmission by constructing the abnormal relationship matrix of the master-slave components, thereby forming abnormal propagation chain data, making the tracking of the abnormal development process more intuitive and quantifiable. On this basis, the abnormal transmission time interval of the components in the abnormal propagation chain data is statistically analyzed, and the average delay time and fluctuation range between each component pair are calculated to accurately characterize the timing characteristics of abnormal transmission and improve the predictability of the abnormal development process. Subsequently, the abnormal transmission time data between components is input into the large model for time series pattern learning, and the periodicity, gradual change or jump law in the abnormal evolution process is automatically identified, and the key time series features are extracted to provide deep data support for subsequent trend prediction and decision support. Combined with the historical fault database, the complete evolution trajectory of the fault from the initial abnormality to the critical state of maintenance is further matched to ensure the accuracy of the abnormal development law and provide reference data based on real fault cases. Based on the fault evolution reference data, the remaining time required for the slave component to reach the critical value of maintenance is calculated to form the component maintenance window data, providing a scientific basis for the maintenance of the equipment. Among them, specific maintenance critical standards are set for different types of components, such as the temperature and vibration amplitude of motor components, the pressure fluctuation and leakage rate of hydraulic pump components, and the air pressure drop and response time change of pneumatic device components, so as to realize differentiated maintenance strategies for different components. This method improves the accuracy of equipment abnormality prediction as a whole, makes maintenance plans more targeted, avoids resource waste or equipment damage caused by premature or late maintenance, and ultimately enhances the stability and reliability of equipment operation.

[0058] Preferably, step S5 comprises the following steps: Step S51: Classify the component maintenance window data into types, and classify the components into emergency maintenance, planned maintenance, and monitoring maintenance based on the maintenance urgency, to obtain maintenance priority data; The embodiment of the present invention evaluates the urgency of 17 components requiring maintenance identified from 94 components, and establishes a scoring model considering three key factors: expected remaining operating time (weight 0.5, 10 points for <24 hours, 6 points for 24-72 hours, 3 points for 72-168 hours, and 1 point for >168 hours), the degree of deviation of abnormal parameters (weight 0.3, 10 points for deviation >50%, 7 points for 30-50%, 4 points for 10-30%, and 1 point for <10%), and the impact range of component failure (weight 0.2, 10 points for impact on the entire machine, 6 points for impact on a single module, 3 points for impact on performance, and 1 point for impact on accuracy). The system calculates the comprehensive score of each component and classifies it into intervals: ≥8 points are classified as emergency maintenance (such as the reducer GB-001 with a score of 8.7 points), with a total of 3 points; 5-8 points are classified as planned maintenance (such as the hydraulic control valve HV-004 with a score of 6.2 points), with a total of 8 points; <5 points are classified as monitoring maintenance (such as the cooling pump CP-002 with a score of 3.5 points), with a total of 6 points. The system assigns a priority number (P1 / P2 / P3) and a sorting position to each component, and constructs a maintenance priority data structure. Step S52: Extract the equipment's planned operating time, production load rate, and planned downtime maintenance time from the production plan data, establish the equipment operation timeline, and obtain the equipment utilization timeline; The embodiment of the present invention extracts the production plan data for the next two weeks from the enterprise production management system, and exports the detailed production plan (15-minute granularity) of the equipment SJJ-350 in JSON format through the API interface, including daily operation schedule (three shifts on weekdays and two shifts on weekends), load rate of each period (such as 95% load from 08:00 to 12:00 on Monday), planned downtime maintenance time and detailed information of each production batch (such as production of automobile bumpers on June 18, injection pressure 21MPa, 3200 pieces). The system arranges this information in chronological order and constructs a timeline of equipment utilization of 1344 time points (14 days × 24 hours × 4 15 minutes). Each point contains a timestamp, operating status (1 / 0), load rate and special mark, which provides a basis for subsequent maintenance period identification.

[0059] Step S53: Identify the production gap period and the low load period according to the equipment utilization time axis, and obtain the data of the maintainable period, wherein the production gap period is defined as a period when the continuous downtime exceeds 4 hours, and the low load period is defined as a period when the production load rate is less than 40% and the duration exceeds 6 hours; The scanning device of the embodiment of the present invention uses the time axis to automatically identify the appropriate maintenance period. First, the search algorithm is applied to find the "production gap period" (a period of continuous shutdown > 4 hours), and the continuous time points with an operating status of 0 are grouped to calculate the duration, and 6 production gap periods are identified (such as a 16-hour shutdown from 06:00 to 22:00 on Sunday), totaling 52 hours of maintenance time. Secondly, the "low load period" (a period with a load rate <40% and a duration of >6 hours) is searched, and 4 low load periods are identified (such as the production of low-precision components from 22:00 on Monday to 04:00 on Tuesday, with a load rate of 35%), totaling 28 hours of potential maintenance time. The system integrates these 10 maintainable periods into a data set, including type, time, duration, average load rate and characteristic description, providing a total of 80 hours of potential maintenance time.

[0060] Step S54: Match and analyze the maintenance priority data with the maintainable time period data to obtain maintenance time data; The embodiment of the present invention develops a multi-objective optimization algorithm to match maintenance priorities with time periods, taking into account four factors: time urgency matching (e.g., the remaining operating time of the reducer is 17.5 hours, and the latest time period starts 12 hours later, with a score of 85 points), maintenance window sufficiency (e.g., the control valve needs 3.5 hours for maintenance, and a certain time period is 16 hours, with a score of 100 points), production impact (0 points for the interval period, and 10-40 points for the low-load period according to the load rate), and resource conflict (from 0 points for no conflict to 50 points for severe conflict). The system establishes a 17×10 matching score matrix, applies the Hungarian algorithm to solve the optimal match, and allocates the most suitable maintenance period, such as arranging the reducer GB-001 in the interval period of 00:00-05:00 on Wednesday, and arranging the control valve HV-004 in the downtime period of 06:00-22:00 on Sunday.

[0061] Step S55: Analyze the dependency relationship between maintenance components according to the maintenance time data and the component transfer chain relationship diagram. When multiple components have upstream and downstream transfer chain relationships, combine their maintenance times to obtain optimized maintenance scheduling data. The embodiment of the present invention analyzes the dependency relationship between maintenance components based on the component transfer chain relationship graph, extracts the upstream and downstream relationship of the components to be repaired from the graph data structure, and establishes a set of associated components. For example, if the control valve HV-004 and the hydraulic pump HP-001 have an upstream and downstream relationship, the system uses a graph traversal algorithm to search for two-level associated components, and analyzes the maintenance and disassembly sequence at the same time, and finds that there is overlap in the disassembly of some components (such as the maintenance of the control valve and the distributor requires the disassembly of the same shell). When the disassembly and assembly overlap rate is >30%, it is determined to be a highly associated task. The system optimizes the scheduling and arranges the upstream and downstream components (such as HP-001 and HV-004) in the same time period (Sunday 06:00-22:00), reducing the maintenance time by 25%, and ensuring that the upstream components are repaired before or at the same time. Finally, 17 maintenance tasks were merged into 9 centralized tasks, significantly improving efficiency.

[0062] Step S56: Calculate the estimated execution time and required resources of each maintenance task for the optimized maintenance scheduling data, and perform enterprise resource constraints to obtain maintenance execution feasibility data; The embodiment of the present invention calculates the execution details and resource requirements of the maintenance task, and extracts the standard working hours, skill requirements and spare parts list of each component from the maintenance knowledge base. For example, the maintenance of the hydraulic system requires 12.5 hours, 2 hydraulic professionals, 1 mechanical personnel, and spare parts such as seals and sensors. The system considers the complexity adjustment factor (equipment operation coefficient of 3.5 years is 1.15, 8 months without major repair coefficient is 0.9, and moderate abnormality coefficient is 1.1), calculates the adjusted execution time to be 14.3 hours, and checks the resource availability. It is found that there is only one hydraulic professional on Sunday (the standard requires 2), which will lead to a 40% increase in working hours, and there is only one pressure sensor in stock (2 are required), and the procurement cycle is 5 days. Based on this, feasibility data (score 70 points, there are risks but basically feasible) and deployment suggestions are generated.

[0063] Step S57: Generate an equipment maintenance report including a component status signal light diagram, a transfer chain map, a maintenance schedule and a maintenance material list according to the maintenance execution feasibility data and the component transfer chain relationship diagram.

[0064] The embodiment of the present invention generates an equipment maintenance report, which includes four parts: a component status signal light diagram (using red, yellow, blue and green to mark the status of each component on the three-dimensional model); a transfer chain map (a network diagram based on a force-directed algorithm, with nodes as components and lines representing influence relationships); a maintenance schedule (in the form of a Gantt chart, with a 14-day timeline on the horizontal axis and 9 maintenance tasks on the vertical axis, and color blocks representing maintenance periods); a maintenance material list (listing spare parts, tools, and consumables by task group, including codes, specifications, quantities, inventory status, procurement cycles, and costs). The report is in HTML5 format, supports multi-device viewing and interactive functions, and is automatically distributed to relevant personnel to ensure that maintenance work is carried out in a coordinated manner.

[0065] The present invention classifies the components according to the maintenance window data of the components, and divides them into emergency maintenance, planned maintenance and monitoring maintenance according to the maintenance urgency, so that the maintenance priority is clearer and helps to optimize the allocation of maintenance resources. Subsequently, the planned operation time of the equipment, the production load rate and the planned downtime maintenance time are extracted from the production plan data to establish a complete equipment utilization time axis to provide data support for the selection of maintenance timing. On this basis, the production gap period and the low load period are identified to form the data of the maintainable time period, so as to arrange the maintenance tasks without affecting the production efficiency and improve the equipment availability. Then, the maintenance priority data is matched and analyzed with the maintainable time period data to ensure that the high-priority maintenance tasks can be executed in the most appropriate time period to avoid production interruption or equipment damage caused by improper maintenance arrangement. In view of the correlation between maintenance tasks, the method combines the component transfer chain relationship diagram to comprehensively analyze the components with upstream and downstream dependencies, merges and optimizes their maintenance time, and reduces the resource consumption and production loss caused by multiple downtime maintenance. By further calculating the expected execution time and required resources of each maintenance task, and combining the enterprise resource constraints, the feasibility of the maintenance plan in actual operation is ensured to avoid maintenance delays caused by insufficient manpower, materials or equipment. Finally, a complete equipment maintenance report is generated based on all analysis results, including component status signal light diagram, transmission chain map, maintenance schedule and maintenance material list, making maintenance management more intuitive and executable, ensuring the reliability of equipment operation and the accuracy of maintenance decisions.

[0066] The present invention also provides a system for generating enterprise business reports based on a big model, which is used to execute the above-mentioned method for generating enterprise business reports based on a big model. The system for generating enterprise business reports based on a big model includes: Data acquisition module, used to obtain component operation status data and production plan data of industrial equipment; The component relationship division module is used to divide the master-slave relationship of the internal components of the equipment according to the component operation status data, designate the drive device as the master component, designate the transmission component and the execution component as the slave component, and construct the component transfer chain relationship diagram; The anomaly detection module is used to monitor the operating status parameters of the master components in the component transfer chain relationship diagram; extract the master components whose operating status parameter fluctuations exceed the preset threshold, and measure the response parameter changes of the connected slave components; generate abnormal transfer confirmation data according to the response parameter changes; The maintenance window analysis module is used to perform a time interval pattern analysis between the main component abnormality and the slave component abnormality based on a large model according to the abnormality transmission confirmation data, and obtain the component maintenance window data by combining the estimated running time required for the component current state to reach the maintenance critical state with the preset historical fault data; The maintenance plan generation module is used to time-match component maintenance window data with production plan data, identify production intervals or low-load periods, and obtain maintenance time data; based on the maintenance time data and the component transfer chain relationship diagram, it generates equipment maintenance reports such as component status signal light diagrams, transfer chain maps, maintenance time, and maintenance material lists.

[0067] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0068] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for generating enterprise business reports based on a large model, characterized in that: The following steps are involved: Step S1: Acquire component operation status data and production plan data of industrial equipment; Step S2: dividing the components inside the device into master-slave relationships according to the component operation status data, designating the drive device as the master component, and designating the transmission component and the execution component as the slave components, and constructing a component transfer chain relationship diagram; Step S3: monitor the operating status parameters of the master components in the component transfer chain relationship diagram; extract the master components whose operating status parameter fluctuations exceed the preset threshold, and measure the response parameter changes of the connected slave components; generate abnormal transfer confirmation data according to the response parameter changes; Step S4: performing a time interval pattern analysis based on a large model on the abnormality of the master component and the abnormality of the slave component according to the abnormality transmission confirmation data, and combining the estimated running time required for the component to reach the critical maintenance state from the current state of the component with the preset historical fault data, to obtain the component maintenance window data; Step S5: Time-matching the component maintenance window data with the production plan data, and identifying the production gap period or low-load period to obtain maintenance time data; Generate equipment maintenance reports including component status signal light diagram, transfer chain map, maintenance time and maintenance material list based on maintenance time data and component transfer chain relationship diagram.

2. The method for generating enterprise business reports based on a large model according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: deploying a device status collector, wherein the device status collector includes a vibration sensor, a temperature sensor and a current sensor; installing the vibration sensor on the surface of the main driving component, installing the temperature sensor on the part of the component that is prone to heat, and connecting the current sensor to the power input terminal to collect the original device operation data; Step S12: removing signal noise and abnormal interference values ​​from the original equipment operation data, thereby obtaining equipment operation data; Step S13: classifying and sorting the equipment operation data based on component types, and calculating the parameter standard range of each component under normal operating conditions, thereby obtaining component operation benchmark data; Step S14: Compare the component operation benchmark data with the component operation status parameters monitored in real time by the device status collector, and mark the components whose parameters deviate from the benchmark range to obtain the component operation status data; Step S15: Obtain production plan data, including planned equipment operation time, production load rate and planned downtime for maintenance.

3. The method for generating enterprise business reports based on a large model according to claim 2, characterized in that: Step S2 includes the following steps: Step S21: acquiring equipment structure drawing data, and extracting the physical connection relationship and energy transfer path information of the components from the equipment structure drawing data, thereby obtaining the physical topological structure data of the components; Step S22: identifying the energy input component in the device based on the component physical topological structure data, and marking it as a main component, thereby obtaining preliminary main component identification data, wherein the energy input component includes a motor, a hydraulic pump, and a pneumatic device; Step S23: determining the transmission component directly connected to the main component based on the energy flow direction in the preliminary main component identification data, marking it as a first-level slave component, thereby obtaining first-level slave component association data, wherein the transmission component includes a gear box, a pulley, and a bearing; Step S24: determining the execution component connected to the first-level slave component along the energy transfer path according to the first-level slave component association data, and marking it as a second-level slave component, thereby obtaining master-slave component hierarchical data, wherein the execution component includes an actuator, a working head, and a functional component; Step S25: performing correlation analysis of operating parameters between components according to component operating status data, calculating the influence of the master component parameter change on the slave component parameters, determining the parameter correlation strength, and thus obtaining a component parameter influence matrix; Step S26: construct a visualized component transfer chain relationship diagram based on the master-slave component hierarchy data and the component parameter influence matrix, wherein the nodes of the component transfer chain relationship diagram represent the components, the connecting lines represent the influence relationship between the components, and the line thickness represents the influence strength.

4. The method for generating enterprise business reports based on a large model according to claim 3 is characterized in that: Step S25 includes the following steps: Step S251: extracting the time series of operating parameters of each component under different working conditions from the component operating status data, thereby obtaining component parameter historical change data; Step S252: segmenting the data of the main component in the component parameter historical change data, identifying the time point when the parameter changes significantly, and taking the time point when the parameter changes significantly as the reference time node, thereby obtaining the main component parameter change mark data; Step S253: Analyze the parameter changes of the slave components before and after the corresponding time points according to the parameter change mark data of the master component, and calculate the time delay and response amplitude between the parameter changes of the slave components and the parameter changes of the master component, so as to obtain the parameter response characteristic data between the components; Step S254: Calculate the parameter influence coefficients between each pair of master and slave components according to the inter-component parameter response characteristic data, thereby obtaining a component influence coefficient matrix, wherein the parameter influence coefficient = (slave component parameter change amplitude / master component parameter change amplitude) × 1 / delay time; Step S255: normalizing the component influence coefficient matrix to obtain a component influence coefficient standard matrix; Step S256: According to a preset influence threshold, the component influence coefficient standard matrix is ​​screened for component pairs whose influence coefficients are greater than the threshold, thereby obtaining a component parameter influence matrix.

5. The method for generating enterprise business reports based on a large model according to claim 1, characterized in that: The operating status parameters of the main components in the monitoring component transfer chain relationship diagram described in step S3 include: Determine the monitoring priority of the main component according to the component transfer chain relationship diagram, where the main component with energy input exceeding 15kW or connected to more than 5 slave components is set to high priority, the main component with energy input between 5kW-15kW or connected to 3-5 slave components is set to medium priority, and the remaining main components are set to low priority; Based on the monitoring priority of the main components, each main component is polled and sampled in different time periods to obtain the original data of the main component operation status; The original data of the main component operation status is smoothed based on a sliding window, with the window size being the first 10 sampling values, and weighted moving average processing is performed to obtain the smoothed data of the main component operation status, where the weight of the most recent time point is 0.3, and the sum of the weights of the remaining 9 historical points is 0.7; When the temperature deviation of the motor main component in the main component running status smoothing data exceeds 15°C, the vibration deviation exceeds 0.8mm / s, or the current deviation exceeds 12%, or when the pressure deviation of the hydraulic pump main component exceeds 1.5MPa, the flow deviation exceeds 10%, or the noise deviation exceeds 8dB, or when the air pressure deviation of the pneumatic device main component exceeds 0.1MPa, the flow deviation exceeds 15%, or the valve response time is extended by more than 30ms, the time point is recorded and the corresponding main component is marked as abnormal, and the abnormal timestamp data of the main component is obtained; According to the abnormal timestamp data of the main component, a set of slave components directly connected to the abnormal main component is extracted from the component transfer chain relationship diagram to obtain a list of related slave components; The main component operation status smoothing data, the main component abnormal timestamp data and the related slave component list are combined into the main component operation status parameters.

6. The method for generating enterprise business reports based on a large model according to claim 1, characterized in that: The step S3 of extracting the main component whose operating state parameter fluctuation exceeds the preset threshold value and measuring the response parameter change of the connected slave components includes: Calculate the fluctuation amplitude of the main component of the main component operation status parameter; Compare the fluctuation amplitude data of the main components with the preset fluctuation thresholds to obtain the over-threshold main component identification data, where the preset fluctuation thresholds are: the temperature fluctuation threshold of the motor main components is 8%, and the speed fluctuation threshold is 5%; the pressure fluctuation threshold of the hydraulic pump main components is 12%; and the air pressure fluctuation threshold of the pneumatic device main components is 15%; According to the list of related slave components, the master components in the super-threshold master component identification data are screened based on the physical connection distance and the energy transfer efficiency to obtain a list of slave components to be tested; Perform high-frequency sampling on the slave components in the list of slave components to be tested to obtain the original response data of the slave components; The original data of the slave component response is processed based on segmentation before, during and after the fluctuation, and the average value, standard deviation and change trend of each time period are calculated. The temperature change slope, vibration spectrum change and pressure fluctuation characteristics are recorded respectively to obtain the characteristic data of the slave component response; The parameter change pattern analysis is performed on the component response characteristic data to identify the response delay time, peak response and steady-state response, and the response attenuation rate and resonant frequency are calculated to obtain the response parameter changes.

7. The method for generating enterprise business reports based on a large model according to claim 1, characterized in that: Generating abnormal transmission confirmation data according to the response parameter change described in step S3 includes: Establish equipment abnormal pattern recognition database; According to the equipment abnormal pattern recognition database, the response parameter changes are matched and calculated based on vector similarity to obtain the fault pattern matching data; Screen potential fault types with a matching degree exceeding 75% from the fault mode matching degree data to obtain the fault type probability distribution data; The deviation rate between the actual response delay time and the preset theoretical transmission time of the slave component response parameters is calculated, and the amplitude attenuation coefficient and spectrum feature offset analysis are performed to obtain the abnormal transmission confirmation probability data; The fault type probability distribution data and the abnormal transmission confirmation probability data are weighted and fused, and the credibility score is calculated. When the score exceeds the preset threshold of 0.8, it is confirmed as a valid abnormal transmission and the abnormal transmission confirmation result is obtained; According to the abnormal transmission confirmation result, the main component information, the slave component information, the fault type probability, the transmission characteristics and the credibility score are structured and integrated to obtain the abnormal transmission confirmation data.

8. The method for generating enterprise business reports based on a large model according to claim 7, characterized in that: Step S4 includes the following steps: Step S41: Establish a master-slave component abnormal relationship matrix based on the abnormal transmission confirmation data, identify the main path and diffusion mode of abnormal transmission, and obtain abnormal propagation chain data; Step S42: Statistically analyze the abnormal transmission time intervals of the connected components in the abnormal propagation chain data, calculate the average delay time and fluctuation range between different component pairs, and obtain the abnormal transmission time data between components; Step S43: input the abnormal transmission time data between components into the large model to perform time series pattern learning, identify typical abnormal development laws including periodic patterns, gradual patterns and jump patterns, and obtain component abnormal time series feature data; Step S44: extracting the development trajectory of the fault from a preset historical fault database according to the component abnormal time series feature data, matching the evolution process of the fault from the initial abnormality to the maintenance critical state, thereby obtaining fault evolution reference data; Step S45: Calculate the remaining time required for the component to reach the maintenance critical value based on the fault evolution reference data, and obtain the component maintenance window data, where the maintenance critical value of motor components is that the temperature exceeds the rated value by 40°C or the vibration amplitude exceeds 2.5mm / s, the maintenance critical value of hydraulic pump components is that the pressure fluctuation exceeds the rated value by 25% or the internal leakage rate exceeds 12%, and the maintenance critical value of pneumatic device components is that the air pressure drops by more than 30% of the rated value or the response time is extended by more than 150ms.

9. The method for generating enterprise business reports based on a large model according to claim 8, characterized in that: Step S5 includes the following steps: Step S51: Classify the component maintenance window data into types, and classify the components into emergency maintenance, planned maintenance, and monitoring maintenance based on the maintenance urgency, to obtain maintenance priority data; Step S52: extracting the equipment planned operation time, production load rate and planned downtime maintenance time from the production plan data, establishing the equipment operation time axis, and obtaining the equipment utilization time axis; Step S53: Identify the production gap period and the low load period according to the equipment utilization time axis, and obtain the data of the maintainable period, wherein the production gap period is defined as a period when the continuous downtime exceeds 4 hours, and the low load period is defined as a period when the production load rate is less than 40% and the duration exceeds 6 hours; Step S54: Match and analyze the maintenance priority data with the maintainable time period data to obtain maintenance time data; Step S55: Analyze the dependency relationship between maintenance components according to the maintenance time data and the component transfer chain relationship diagram. When multiple components have upstream and downstream transfer chain relationships, combine their maintenance times to obtain optimized maintenance scheduling data. Step S56: Calculate the estimated execution time and required resources of each maintenance task for the optimized maintenance scheduling data, and perform enterprise resource constraints to obtain maintenance execution feasibility data; Step S57: Generate an equipment maintenance report including a component status signal light diagram, a transfer chain map, a maintenance schedule and a maintenance material list according to the maintenance execution feasibility data and the component transfer chain relationship diagram.

10. A system for generating enterprise business reports based on a large model, characterized in that: Used to execute the enterprise business report generation method based on a big model as claimed in claim 1, the enterprise business report generation system based on a big model comprises: Data acquisition module, used to obtain component operation status data and production plan data of industrial equipment; The component relationship division module is used to divide the master-slave relationship of the internal components of the equipment according to the component operation status data, designate the drive device as the master component, designate the transmission component and the execution component as the slave component, and construct the component transfer chain relationship diagram; The anomaly detection module is used to monitor the operating status parameters of the master components in the component transfer chain relationship diagram; extract the master components whose operating status parameter fluctuations exceed the preset threshold, and measure the response parameter changes of the connected slave components; generate abnormal transfer confirmation data according to the response parameter changes; The maintenance window analysis module is used to perform a time interval pattern analysis between the main component abnormality and the slave component abnormality based on a large model according to the abnormality transmission confirmation data, and obtain the component maintenance window data by combining the estimated running time required for the component current state to reach the maintenance critical state with the preset historical fault data; The maintenance plan generation module is used to time-match component maintenance window data with production plan data, identify production intervals or low-load periods, and obtain maintenance time data; based on the maintenance time data and the component transfer chain relationship diagram, it generates equipment maintenance reports such as component status signal light diagrams, transfer chain maps, maintenance time, and maintenance material lists.

Images