Dynamic work auxiliary system based on three-dimensional model

Abstract

The invention discloses a dynamic work auxiliary system based on a three-dimensional model. The dynamic work auxiliary system comprises a data acquisition and transmission module, a digital twin model construction module, a data analysis and processing module and a three-dimensional visualization and interaction module. The system acquires equipment data in real time through the data acquisition and transmission module and transmits the equipment data to the background; and the background transmits the data to a digital twin model construction module, and a digital twin three-dimensional model of the equipment is constructed in real time to reflect the state of the equipment. The data analysis and processing module analyzes the real-time data, dynamically adjusts the content of a work manual according to a fault diagnosis model or a preset rule, and guides an operator to take corresponding measures. The three-dimensional visualization and interaction module displays the equipment and operation steps through a visual three-dimensional model, and can help an operator to timely know the equipment condition, deeply analyze the equipment state and find potential faults as soon as possible, thereby reducing the fault occurrence rate and improving the reliability and safety of the equipment.

Description

Technical Field

[0001] The invention belongs to the technical field of data processing, and in particular relates to a dynamic work assisting system based on a three-dimensional model. Background Art

[0002] Most of the existing 3D work manuals rely on traditional 2D drawings, or use CAD software to generate static 3D models, which are displayed in combination with the manual content. On the other hand, in the manufacturing, construction, energy and other industries, some systems based on digital twin technology have emerged. These systems use virtual models to guide the operation, maintenance and management of equipment.

[0003] In the prior art, for example, the technical solution described in the patent with publication number CN115687494 is “a digital twin monitoring system for a manufacturing system, which collects production system status data in real time and transmits data through an information-physical system bus to drive a three-dimensional model of a virtual scene, thereby achieving real-time mapping of production behaviors and visualization of key data.”

[0004] Most of the 3D work manuals currently available on the market rely on traditional 2D drawings, or generate static 3D models through computer-aided design (CAD) software and display them in combination with the manual content. Although this method improves the visualization of information to a certain extent, it still has some limitations in practical applications. For example, static 3D models cannot reflect the dynamic changes of the system in real time, nor can they provide interactive operation guidance, which often leads to difficulties in understanding and application for users during actual operation. Summary of the invention

[0005] The purpose of the present invention is to provide a dynamic work assistance system based on a three-dimensional model to solve the problem in the prior art proposed in the background technology that the three-dimensional manual fails to be effectively integrated with the real-time status of the equipment, sensor data, etc., only supports basic viewing functions, and lacks dynamic feedback on user operations.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0007] A dynamic work assistance system based on a three-dimensional model, comprising a data acquisition and transmission module, a digital twin model construction module, a data analysis and processing module, and a three-dimensional visualization and interaction module; wherein the real-time data of the equipment is collected by the data acquisition and transmission module, and the real-time data is transmitted to the system background; the system background transmits the collected equipment data to the digital twin model construction module, and the digital twin model construction module constructs a digital twin three-dimensional model of the equipment and reflects the status of the equipment in real time;

[0008] The data analysis and processing module processes real-time data, analyzes the status of the equipment, and dynamically adjusts the content of the work manual according to the fault diagnosis model or preset rules;

[0009] The 3D visualization and interaction module presents equipment and operation steps based on 3D models, supports user interactive operations, and provides instant feedback based on user selections.

[0010] According to the above technical solution, the digital twin model construction module constructs the digital twin 3D model of the device as follows:

[0011] Step S101, model initialization: based on collecting the device CAD file or point cloud data through the data acquisition and transmission module, an initial three-dimensional model of the device is established;

[0012] Step S102, real-time status mapping: dynamically update the status of the three-dimensional model according to the collected real-time data of the equipment; the mapping relationship between the equipment geometry and attribute parameters is as follows:

[0013] M(t)=f(P(t),D(t))

[0014] Where M(t) represents the state of the 3D model at time t, P(t) represents the geometric parameters of the device; D(t) represents the physical parameters of the device, and f represents the mapping function;

[0015] Step S103, real-time status update: based on the physical simulation engine, the dynamic behavior of the model is calculated in real time;

[0016] Step S104, state position change: according to the motion data provided by the sensor, use the rigid body dynamics formula to calculate:

[0017]

[0018] In the formula, the displacement of the object in the time interval Δt is described, Δt represents the time interval, x(t) represents the position of the object at time t, and represents the initial position; v(t) is the velocity at time t, and a(t) represents the acceleration of the object at t;

[0019] Step S105, state color coding: visually coding the model using real-time data.

[0020] According to the above technical solution, the content of the work manual is dynamically adjusted through the fault diagnosis model or preset rules as follows:

[0021] First, a machine learning model is used to analyze the data stream and detect device anomalies;

[0022]

[0023] Where s(x1) is the anomaly score, h(x) is the path length; C(n) is the reference length of the equipment operation path, that is, the historical average of the normal working path; by comparing the real-time path length of the equipment with the historical reference path length, it is judged whether the current operation status is abnormal; specifically, when E(h(x) is larger, it means that the average path length is longer, indicating that there is an abnormality in the equipment operation, which leads to a larger s(x), that is, a higher anomaly score;

[0024] Dynamically adjust the work manual content, use the rule engine to diagnose equipment failures, and dynamically adjust the work manual content;

[0025] Rules engine formula:

[0026] IF(T>Tthreshold)∧(P <Pthreshold)

[0027] In the formula, T represents temperature; P represents pressure;

[0028] Dynamic content generation: Based on the diagnosis results, the corresponding operation steps are dynamically called from the database and updated to the work manual.

[0029] According to the above technical solution, the 3D visualization and interaction module presents the device and operation steps based on the 3D model as follows:

[0030] Real-time equipment status display: The system combines the digital twin model with real-time data to present the dynamic status of the equipment; it uses materials and textures to update the model surface to intuitively reflect the equipment status;

[0031] Dynamic operation step linkage: According to the dynamic content update of the work manual, the 3D model synchronously displays the operation steps; through animation and guide arrows, the user is guided through the operation process;

[0032] User input and feedback: Support users to interact with the model through touch screen, mouse or voice: click on the parts to highlight the details; drag the model to rotate or zoom to view different angles;

[0033] Feedback update: After the user completes each step of the operation, the system records the operation log and updates the next step of guidance content in real time.

[0034] According to the above technical solution, in the data acquisition and transmission module, the operating status of the equipment is fed back to the digital twin 3D model in real time through the real-time data transmission interface. The digital twin 3D model automatically adjusts the steps or diagrams in the manual based on this information. The specific adjustment mechanism is:

[0035] Fault diagnosis and rule matching: Use rule-based fault diagnosis models or data-driven deep learning models to analyze device status.

[0036] State-step mapping: Map the diagnostic results to the preset step library;

[0037] S=f(D)

[0038] Where, S: step in the work manual, D: equipment diagnostic status;

[0039] Dynamic content adjustment algorithm: The system dynamically selects relevant steps based on the current status of the device;

[0040] Dynamic update step logic: Supdated = {s1, s3, s5}

[0041] Where, Supdated: the updated step sequence;

[0042] Graphic adjustment: Use dynamic templates to generate 3D graphics; Graphic generation algorithm:

[0043] I updated =g(m,S updated )

[0044] In the formula, I updated represents the updated three-dimensional diagram; M represents the status data of the digital twin model;

[0045] The specific implementation steps of the dynamic update mechanism are as follows: the system calls the rule engine to match the device status with the operation steps; extracts the adapted step sequence and adjusts the operation guidance content;

[0046] Dynamic generation of 3D diagrams: Call the diagram generation module to generate 3D visualization diagrams related to the steps based on the current state;

[0047] Real-time push updates: The updated work manual content and diagrams are displayed to users through the interactive interface.

[0048] According to the above technical solution, in the data analysis and processing module, the sensor data is denoised and smoothed by using the Kalman filter algorithm, and heterogeneous data from different sensors are fused.

[0049] According to the above technical solution, the Kalman filter algorithm is specifically as follows:

[0050]

[0051] Among them, K k is the Kalman gain, z k is the observed value, is the predicted value.

[0052] According to the above technical solution, the state change of the device is represented by the device state synchronization algorithm, and the device state synchronization algorithm is specifically:

[0053] x(t)=Ax(t-1)+Bu(t)+w(t)

[0054] Among them, xk is the state vector of the device at time t, u(t) is the control input, w(t) is the noise vector, A is the state transfer matrix, and B is the control matrix, which represents the impact of the control input on the device state.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] In the present invention, through the data acquisition and transmission module, the system can obtain the operating status of the equipment in real time, and reflect the status of the equipment in real time through the digital twin model, helping the operator to understand the equipment status in time. The data analysis and processing module can conduct in-depth analysis of the equipment status, detect potential faults as early as possible, and guide the operator to take corresponding measures by adjusting the content of the work manual, thereby reducing the failure rate and improving the reliability and safety of the equipment. The three-dimensional visualization and interaction module presents complex data in an intuitive three-dimensional model, so that users can more easily understand the equipment operation steps and obtain instant feedback according to their actual needs, thereby improving the accuracy and efficiency of the operation. The system dynamically adjusts the content of the work manual according to real-time data and fault diagnosis results to ensure that the operator uses the latest and most relevant information when performing tasks, thereby optimizing the workflow and reducing unnecessary waste of time. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 The following is a workflow diagram of the dynamic work assistance system of the three-dimensional model of the present invention. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] Embodiment 1

[0060] like Figure 1As shown, a dynamic work assistance system based on a three-dimensional model includes a data acquisition and transmission module, a digital twin model construction module, a data analysis and processing module, and a three-dimensional visualization and interaction module; wherein, the real-time data of the equipment is collected by the data acquisition and transmission module, and the real-time data is transmitted to the system background; the system background transmits the collected equipment data to the digital twin model construction module, the digital twin model construction module constructs a digital twin three-dimensional model of the equipment, and reflects the status of the equipment in real time; the data analysis and processing module processes the real-time data, analyzes the status of the equipment, and dynamically adjusts the content of the work manual according to the fault diagnosis model or preset rules; the three-dimensional visualization and interaction module presents the equipment and operation steps based on the three-dimensional model, supports user interactive operations, and provides instant feedback according to user selection.

[0061] In the present invention, through the data acquisition and transmission module, the system can obtain the operating status of the equipment in real time, and reflect the status of the equipment in real time through the digital twin model, helping the operator to understand the equipment status in time. The data analysis and processing module can conduct in-depth analysis of the equipment status, detect potential faults as early as possible, and guide the operator to take corresponding measures by adjusting the content of the work manual, thereby reducing the failure rate and improving the reliability and safety of the equipment. The three-dimensional visualization and interaction module presents complex data in an intuitive three-dimensional model, so that users can more easily understand the equipment operation steps and obtain instant feedback according to their actual needs, thereby improving the accuracy and efficiency of the operation. The system dynamically adjusts the content of the work manual according to real-time data and fault diagnosis results to ensure that the operator uses the latest and most relevant information when performing tasks, thereby optimizing the workflow and reducing unnecessary waste of time.

[0062] The system of the present invention provides a visual and interactive learning environment, which is particularly suitable for the training of new employees, so that they can quickly become familiar with equipment operation and maintenance knowledge. The system can accumulate and analyze historical data, provide scientific decision support for management, and promote the formulation of intelligent management and maintenance strategies for equipment.

[0063] Embodiment 2

[0064] This embodiment provides a specific implementation method.

[0065] The three-dimensional workbook system of the present invention comprises the following main modules:

[0066] Data collection and transmission module: Through sensors and Internet of Things technology, the working status data of the equipment is collected in real time and the data is transmitted to the system background.

[0067] Digital twin model construction module: By collecting the equipment's design drawings, operation manuals, historical data, etc., a digital twin 3D model of the equipment is constructed to reflect the equipment's status in real time.

[0068] Data analysis and processing module: processes real-time data, analyzes the status of equipment, and dynamically adjusts the content of the work manual according to the fault diagnosis model or preset rules.

[0069] 3D visualization and interaction module: presents equipment and operation steps based on 3D models, supports user interactive operations, and provides instant feedback based on user selections.

[0070] Automatic update and feedback module: The system automatically adjusts the content of the work manual according to changes in real-time data and provides the latest operation guidance.

[0071] The core idea of ​​this invention is to combine digital twins with three-dimensional visualization, and synchronize the dynamic work manual with the real-time information of the equipment through real-time monitoring of the status of the physical equipment. The specific principles are as follows:

[0072] Synchronization of equipment status and manual content: Through the real-time data transmission interface, the operating status of the equipment (such as temperature, pressure, speed, etc.) is fed back to the digital twin model in real time, and the model automatically adjusts the steps or diagrams in the manual based on this information. For example, if the temperature of the equipment is too high, the work manual can be automatically updated to "check the equipment cooling system."

[0073] Step 2, 3D interactive model: Use a 3D graphics engine (such as WebGL) to present the device model and environment in real time. Operators can interact with the virtual device by clicking or dragging to view operation steps or perform troubleshooting.

[0074] Action relationship description

[0075] Step 1, data collection: Sensors collect device status information, such as temperature, pressure, etc., and the data is transmitted to the cloud server through the IoT platform.

[0076] Step 2, state synchronization: The device state data is transmitted to the digital twin model, and the virtual device model is synchronized with the real device state.

[0077] Step 3, Dynamic Work Manual Generation: Based on the equipment status, the system automatically generates steps and instructions related to equipment operation. If the equipment is abnormal, the system will automatically adjust the manual content and provide solutions or warnings.

[0078] Step 4, Interaction and feedback: The operator interacts with the work manual through a 3D visualization interface, and the system updates the manual content in real time based on the operator's feedback to ensure correct operation.

[0079] In the data acquisition and transmission module, the operating status of the equipment is fed back to the digital twin 3D model in real time through the real-time data transmission interface. The digital twin 3D model automatically adjusts the steps or diagrams in the manual based on this information.

[0080] In the data analysis and processing module, the sensor data is denoised and smoothed by using the Kalman filter algorithm, and heterogeneous data from different sensors are fused.

[0081] The Kalman filter algorithm is used in the real-time data acquisition module to suppress noise and predict the state of sensor data to improve the accuracy and stability of the data.

[0082] The present invention utilizes the Kalman filter algorithm to perform multi-source data fusion and adaptive gain adjustment.

[0083] Multi-source data fusion: Input data from multiple sensors into the Kalman filter model and combine multi-dimensional data for state estimation.

[0084] Multidimensional state estimation update formula:

[0085]

[0086] in, represents the estimated value of the current state; F is the state transfer matrix; Z k Indicates the current measurement value; K k Represents the Kalman gain, which dynamically adjusts the noise weight.

[0087] Adaptive gain adjustment: Dynamically adjust the Kalman gain K according to the noise level of real-time data k :

[0088]

[0089] Among them, P k|k-1 represents the prediction error covariance matrix; R k represents the measurement noise covariance matrix.

[0090] Integration with the digital twin model includes real-time status updates and dynamic behavior predictions, where real-time status updates are specifically:

[0091] The filtered estimated state data is transmitted to the digital twin model module to dynamically update the three-dimensional model.

[0092] Dynamic Behavior Prediction:

[0093] The Kalman filter predicts the next behavior state of the device through the state estimation formula and adjusts the dynamic simulation parameters of the digital twin model.

[0094] Behavior prediction formula:

[0095]

[0096] Connection to the Workbook Dynamic Adjustment Module:

[0097] The Kalman filter algorithm not only processes real-time data, but also interacts with the work manual module by predicting equipment status, providing forward-looking data support for the dynamic adjustment of the work manual.

[0098] Diagnostic Support:

[0099] The state value predicted by the Kalman filter can trigger dynamic adjustments to the workbook. For example, when the temperature state prediction of the equipment exceeds the threshold, the workbook automatically jumps to the cooling operation step.

[0100] Adjust logic:

[0101] Kalman filter state output Combined with the rule engine, it is used to dynamically modify the content of the workbook:

[0102] condition:

[0103]

[0104] action:

[0105] THEN Update Manual.

[0106] in, is the estimated value of the state at time k+1. F is the state transition matrix, which describes how the system state evolves from time k to time k+1. is the state estimate at time k. B is the control input matrix, which transforms the control input u k Mapped to the state space. k is the control input at time k.

[0107] The principle of this formula is to predict the state at the next moment based on the current state estimation and control input. For example, in equipment monitoring, it may represent the current operating state of the equipment (such as temperature, pressure, etc.), or it may represent external control factors (such as input power, etc.). Through this formula, the operating state of the equipment at the next moment can be predicted.

[0108] Connection to the Workbook Dynamic Adjustment Module:

[0109] The Kalman filter predicts the next behavior of the device through the above formula. These prediction data are linked to the workbook module. For example, when the predicted value of a key parameter of the device (such as temperature) Exceeding a set threshold (such as ), it triggers an update operation of the work manual (such as "THEN Update Manual."). The significance of this connection is that it provides forward-looking data support, allowing the work manual to be adjusted in advance, rather than waiting until the problem occurs. For example, when it is predicted that the equipment temperature will exceed the safety threshold, the work manual can be updated in advance to the cooling operation steps to guide the operator to perform preventive operations, thereby avoiding equipment failure or safety accidents.

[0110] Diagnostic support and adjustment logic: The state value predicted by the Kalman filter can be used as a basis for diagnosis. For example, when the temperature state prediction of the equipment exceeds the threshold, the workbook automatically jumps to the cooling operation step. The specific adjustment logic is implemented through the rule engine. When the state output of the Kalman filter meets certain conditions (such as ), the rule engine triggers the corresponding action (such as updating the work manual). This mechanism makes the adjustment of the work manual more intelligent and automated, improving the efficiency and safety of equipment maintenance and operation.

[0111] Detailed description of the action meaning: Data-driven manual update: When the state estimate output by the Kalman filter meets certain conditions, the rule engine triggers the update of the work manual. For example, if the Kalman filter estimates that a key parameter of the equipment is out of the normal range, this indicates that there may be a potential problem with the equipment. At this time, the work manual needs to be updated to reflect how to deal with this situation.

[0112] Real-time and accuracy: Since Kalman filtering can effectively handle noise and uncertainty, the state estimation it provides is more reliable. Combined with the rule engine, it can ensure that the update of the work manual is based on accurate and real-time data. For example, in aviation maintenance, if the Kalman filter estimates that a parameter of the aircraft engine is abnormal, the work manual can be updated immediately to provide the corresponding maintenance steps to ensure flight safety.

[0113] Automation and intelligence: This combination realizes the automation and intelligence of work manual updates. Through pre-defined rules, the system can automatically determine when the manual needs to be updated and perform the corresponding update operations, reducing the need for manual intervention and improving work efficiency and accuracy.

[0114] In summary, the combination of Kalman filtering and rule engine is used to dynamically modify the content of work manuals, which can realize automatic manual updates based on real-time data and predefined rules, and improve the accuracy and efficiency of work.

[0115] The linkage with the 3D visualization module includes dynamic visual effect optimization and predictive animation generation.

[0116] Dynamic visual effects optimization:

[0117] The Kalman filtered data is used to dynamically adjust the visual effects of the 3D model. For example, the filtered vibration state can be displayed on the model surface using color coding.

[0118] Predictive animation generation:

[0119] Based on the filtered device status prediction results, operation suggestion animations are dynamically generated to provide intuitive guidance for users.

[0120] The improved Kalman filter integration process in the whole system:

[0121] Data acquisition and transmission module:

[0122] Collect multi-sensor data, denoise and fuse the data through the Kalman filter algorithm to generate equipment state estimation.

[0123] Digital twin model building blocks:

[0124] Receive filtered status data, dynamically update the 3D model, and synchronize the model with the equipment operating status.

[0125] Data analysis and workbook dynamic adjustment module:

[0126] The Kalman filter state prediction value is used to trigger the dynamic adjustment logic of the operation manual to update the operation steps and prompt content.

[0127] 3D visualization and interaction module:

[0128] The filtered state and prediction data are used to adjust the dynamic behavior and visual feedback of the 3D model to provide users with real-time interactive guidance.

[0129] Improved innovation and uniqueness analysis:

[0130] Enhanced module linkage: The Kalman filter algorithm is not only used for data processing, but also runs through the entire system, realizing functional linkage from data acquisition to 3D visualization.

[0131] Improved predictive capabilities: Through state estimation and behavior prediction, the system realizes forward-looking analysis of equipment status, making work manual adjustments more intelligent.

[0132] Dynamic feedback optimization: The filtered state data directly drives the dynamic behavior and visualization effect of the 3D model, improving the user experience.

[0133] Multi-sensor fusion: The improved Kalman filter algorithm supports multi-sensor data fusion, improving the robustness and accuracy of the system.

[0134] By improving the Kalman filter algorithm and deeply integrating it into the entire dynamic work assistance system, the present invention achieves close linkage between modules and significantly improves the overall performance, providing a more efficient and intelligent solution for digital twin application scenarios.

[0135] The state change of the device is represented by the device state synchronization algorithm, which is as follows:

[0136] x(t)=Ax(t-1)+Bu(t)+w(t)

[0137] Among them, x(t) is the state vector of the device at time t, u(t) is the control input, w(t) is the noise vector, A is the state transfer matrix, and B is the control matrix, which represents the impact of the control input on the device state.

[0138] The implementation of device state synchronization includes state update and execution of synchronization algorithm, wherein device state synchronization is implemented through the following steps:

[0139] Sensor data collection: Get key data (such as temperature, pressure, location information, etc.) from multiple sensors on the device in real time.

[0140] The data format is the state vector Zt = [z1, z2, ..., zn], where z i Represents the data of the i-th sensor.

[0141] State prediction: Based on the state X at the previous moment t-1 And control input Ut, predict the current state:

[0142]

[0143] Prediction results It is an estimate of the device state at the current moment.

[0144] State correction (synchronization): Use sensor data Zt to correct the predicted state:

[0145]

[0146] In the formula, K t represents the correction gain, which is defined as:

[0147] K t =P t H T (HP t H T +R t ) -1

[0148] Where Pt: uncertainty covariance matrix of predicted state. Rt: sensor noise covariance matrix. H: measurement matrix, mapping state vector Xt to sensor data space.

[0149] The execution flow of the synchronization algorithm:

[0150] Initialization: Initialize the device's initial state X0, state covariance P0, state transfer matrix A, control matrix B, measurement matrix H, and noise covariance matrices Q and R.

[0151] Real-time prediction and correction:

[0152] State prediction stage: Use the state transition equation to predict the current state:

[0153]

[0154] Update state covariance:

[0155] P t =AP t-1 A T +Q

[0156] State correction phase: Use sensor data to correct the predicted value and obtain the synchronization state:

[0157]

[0158] Update state covariance:

[0159] P t =(IK t H)P t

[0160] State synchronization to the digital twin model: The final synchronized state X t Mapped to the geometric parameters and dynamic behavior of the 3D model.

[0161] For example, the temperature state T is mapped to a color change. The position information [x, y, z] updates the position of the 3D model.

[0162] Function and improvement of the algorithm: The algorithm realizes real-time synchronization between the physical state of the equipment and the state of the digital twin model through the combination of state prediction and sensor correction.

[0163] Adaptive gain adjustment: Dynamically adjust Kt so that the system can adapt to fluctuations in sensor data quality.

[0164] Multi-sensor fusion: supports the fusion of multiple sensor data and further improves synchronization accuracy through joint state estimation.

[0165] Time synchronization mechanism: Use timestamps to interpolate and complete data to ensure the consistency of multi-source data in terms of time series.

[0166] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0167] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A dynamic work assistance system based on a three-dimensional model, characterized in that: It includes a data acquisition and transmission module, a digital twin model construction module, a data analysis and processing module, and a three-dimensional visualization and interaction module; the data acquisition and transmission module collects real-time data of the equipment and transmits the real-time data to the system background; the system background transmits the collected equipment data to the digital twin model construction module, and the digital twin model construction module constructs a digital twin three-dimensional model of the equipment and reflects the status of the equipment in real time; The data analysis and processing module processes real-time data, analyzes the status of the equipment, and dynamically adjusts the content of the work manual according to the fault diagnosis model or preset rules; The 3D visualization and interaction module presents equipment and operation steps based on 3D models, supports user interactive operations, and provides instant feedback based on user selections.

2. A dynamic work assistance system based on a three-dimensional model according to claim 1, characterized in that: The digital twin model construction module constructs the digital twin 3D model of the device as follows: Step S101, model initialization: based on collecting the device CAD file or point cloud data through the data acquisition and transmission module, an initial three-dimensional model of the device is established; Step S102, real-time status mapping: dynamically update the status of the three-dimensional model according to the collected real-time data of the equipment; the mapping relationship between the equipment geometry and attribute parameters is as follows: M(t)=f(P(t),D(t)) Where M(t) represents the state of the 3D model at time t, P(t) represents the geometric parameters of the device; D(t) represents the physical parameters of the device, and f represents the mapping function; Step S103, real-time status update: based on the physical simulation engine, the dynamic behavior of the model is calculated in real time; Step S104, state position change: according to the motion data provided by the sensor, use the rigid body dynamics formula to calculate: In the formula, the displacement of the object in the time interval Δt is described, Δt represents the time interval, x(t) represents the position of the object at time t, and represents the initial position; v(t) is the velocity at time t, and a(t) represents the acceleration of the object at t; Step S105, state color coding: visually coding the model using real-time data.

3. A dynamic work assistance system based on a three-dimensional model according to claim 2, characterized in that: Dynamically adjust the work manual content through fault interruption models or preset rules as follows: First, a machine learning model is used to analyze the data stream and detect device anomalies; Where s(x1) is the anomaly score, h(x) is the path length; C(n) is the reference length of the equipment operation path, that is, the historical average of the normal operation path; by comparing the real-time path length of the equipment with the historical reference path length, it is determined whether the current operation status is abnormal; Dynamically adjust the work manual content, use the rule engine to diagnose equipment failures, and dynamically adjust the work manual content; Rules engine formula: IF(T>Tthreshold)∧(P <Pthreshold) In the formula, T represents temperature; P represents pressure; Dynamic content generation: Based on the diagnosis results, the corresponding operation steps are dynamically called from the database and updated to the work manual.

4. A dynamic work assistance system based on a three-dimensional model according to claim 3, characterized in that: The 3D visualization and interaction module presents the equipment and operation steps based on the 3D model as follows: Real-time equipment status display: The system combines the digital twin model with real-time data to present the dynamic status of the equipment; it uses materials and textures to update the model surface to intuitively reflect the equipment status; Dynamic operation step linkage: According to the dynamic content update of the work manual, the 3D model synchronously displays the operation steps; through animation and guide arrows, the user is guided through the operation process; User input and feedback: Support users to interact with the model through touch screen, mouse or voice: click on the parts to highlight the details; drag the model to rotate or zoom to view different angles; Feedback update: After the user completes each step of the operation, the system records the operation log and updates the next step of guidance content in real time.

5. A dynamic work assistance system based on a three-dimensional model according to claim 4, characterized in that: In the data acquisition and transmission module, the operating status of the equipment is fed back to the digital twin 3D model in real time through the real-time data transmission interface. The digital twin 3D model automatically adjusts the steps or diagrams in the manual based on this information. The specific adjustment mechanism is as follows: Fault diagnosis and rule matching: Use rule-based fault diagnosis models or data-driven deep learning models to analyze device status. State-step mapping: Map the diagnostic results to the preset step library; S=f(D) Where, S: step in the work manual, D: equipment diagnostic status; Dynamic content adjustment algorithm: The system dynamically selects relevant steps based on the current status of the device; Dynamic update step logic: Supdated = {s1, s3, s5}; Where, Supdated: the updated step sequence; Graphic adjustment: Use dynamic templates to generate 3D graphics; Graphic generation algorithm: I updated =g(M,S updated ) In the formula, I updated represents the updated three-dimensional diagram; M represents the status data of the digital twin model; The specific implementation steps of the dynamic update mechanism are as follows: the system calls the rule engine to match the device status with the operation steps; extracts the adapted step sequence and adjusts the operation guidance content; Dynamic generation of 3D diagrams: Call the diagram generation module to generate 3D visualization diagrams related to the steps based on the current state; Real-time push updates: The updated work manual content and diagrams are displayed to users through the interactive interface.

6. A dynamic work assistance system based on a three-dimensional model according to claim 5, characterized in that: In the data analysis and processing module, the sensor data is denoised and smoothed by using the Kalman filter algorithm, and heterogeneous data from different sensors are fused.

7. A dynamic work assistance system based on a three-dimensional model according to claim 6, characterized in that: The Kalman filter algorithm is specifically: Among them, K k is the Kalman gain, z k is the observed value, is the predicted value.

8. The dynamic work assistance system based on a three-dimensional model according to claim 4, characterized in that: The state change of the device is represented by the device state synchronization algorithm, which is as follows: x(t)=Ax(t-1)+Bu(t)+w(t) Among them, x(t) is the state vector of the device at time t, u(t) is the control input, w(t) is the noise vector, A is the state transfer matrix, and B is the control matrix, which represents the impact of the control input on the device state.

Images