A worker ergonomics risk analysis method and system based on digital twinning

Abstract

The application belongs to the technical field of digital twinning, and discloses a worker ergonomics risk analysis method and system based on digital twinning. The method comprises the following steps: converting the space-time trajectory of the worker into a nested network of a region transfer network and a posture transformation network; calculating the node number, average node strength and transfer degree of the region transfer network and the posture transformation network respectively; using the node number, average node strength and transfer degree of the region transfer network and the posture transformation network to calculate the single action related ergonomics risk and the mechanical cycle action related ergonomics risk respectively, so as to realize ergonomics risk analysis. Through the application, the influence of the worker posture, environmental factors and mechanical cycle operation is comprehensively considered, a comprehensive worker risk identification model is constructed, and accurate risk monitoring and management are realized.

Description

Technical Field

[0001] The present invention belongs to the technical field related to digital twins, and more specifically, relates to a worker ergonomic risk analysis method and system based on digital twins. Background Art

[0002] As construction environments become increasingly complex, the interaction between workers' posture and the environment during work is attracting increasing attention. By leveraging digital twin technology and worker sensory data, the engineering community is exploring how to monitor workers' posture and its risk factors in real time to mitigate ergonomic risks caused by poor posture or environmental factors. Ergonomic risks faced by workers in current construction processes primarily arise from the interaction of poor posture, repetitive mechanical work, and environmental factors. However, existing monitoring technologies mostly focus on a single factor, making it difficult to comprehensively identify these complex risks. Existing research primarily relies on machine learning models to identify worker posture, but this carries high data collection costs and ignores environmental influences during construction, potentially overlooking some potential risks of musculoskeletal disorders. Furthermore, current research has limited research on identifying repetitive, monotonous, and cyclical mechanical work, which can pose a risk of musculoskeletal disorders even when performed with correct posture.

[0003] Existing research demonstrates the feasibility of using machine learning models to identify worker posture and movement from motion data captured by wearable inertial measurement units (IMUs). Advances in machine learning technology, particularly the application of neural network models, have significantly improved the classification accuracy of worker posture recognition. However, model training still faces the challenge of high data acquisition costs. Furthermore, because workers are highly dynamic during construction and are significantly affected by their location and environment, relying solely on posture information for identification while ignoring environmental factors can miss musculoskeletal disease risks. For example, even if workers maintain correct posture during work in high humidity or low temperatures, prolonged exposure to these conditions can still increase the strain on the musculoskeletal system, leading to occupational injuries or chronic damage. Furthermore, current research has focused less on identifying monotonous, repetitive tasks. However, maintaining correct posture for extended periods while performing monotonous, repetitive tasks can also lead to musculoskeletal disorders. Therefore, comprehensively identifying worker ergonomic risks remains a pressing challenge in current production and construction. Summary of the Invention

[0004] In response to the above-mentioned defects or improvement needs of the existing technology, the present invention provides a worker ergonomic risk analysis method and system based on digital twins to solve the problem that the monotonous and mechanical cyclic operations of workers are not taken into account when conducting risk analysis.

[0005] To achieve the above objectives, according to one aspect of the present invention, a method for analyzing worker ergonomic risks based on digital twins is provided, the method comprising the following steps:

[0006] Acquiring the worker's spatiotemporal trajectory and motion sequence data; converting the worker's spatiotemporal trajectory and motion sequence data into a region transfer network and a posture transformation network; and calculating the number of nodes, average node strength, and transfer degree of the region transfer network and the posture transformation network, respectively;

[0007] The number of nodes, average node strength and transfer degree of the regional transfer network and the posture transformation network are used to calculate the ergonomic risk associated with a single action and the ergonomic risk associated with a mechanical cycle action, respectively, to achieve ergonomic risk analysis.

[0008] Further preferably, before converting the space-time trajectory into the region transfer network and the posture transformation network, the space-time trajectory is converted into a space-time network according to the following steps:

[0009] Discretize the space-time trajectory according to preset time intervals to obtain the position of the worker at each moment after discretization;

[0010] Divide the workers' activity range into regions to obtain the region to which the workers' positions at each moment belong, as well as the transfer relationship between regions at different moments;

[0011] Regions are regarded as nodes, and the transfer relations between regions are regarded as edges connecting the nodes, thereby forming a network, that is, converting the spatiotemporal trajectory into a spatial unit transfer network.

[0012] Further preferably, the transfer relationship between the regions includes transfer between different regions and self-transfer within the same region.

[0013] Further preferably, the converting of the spatiotemporal trajectory into the regional transfer network is performed according to the following steps:

[0014] Nodes with the same region in the spatial unit network are merged to form a regional node, and the regional transfer relationship on the node before the merger is retained and converted into directed connection lines between regional nodes, thereby forming a new network, namely, a regional transfer network, wherein the number of directed connection lines on the regional node pointing to the current regional node is used as the weight of the current regional node.

[0015] Further preferably, the converting the spatiotemporal trajectory into a posture transformation network is performed according to the following steps:

[0016] In the spatial unit transfer network, for nodes in the same area at different times, determine the posture corresponding to each moment and the conversion relationship between postures at different moments;

[0017] Nodes with the same posture are merged into one posture node, and the posture conversion relationship on each node before the merger is retained and converted into directed connection lines connecting the posture nodes, thereby forming a posture transformation network, wherein the number of wired connection lines on the posture node pointing to the current posture node is used as the weight of the current posture node.

[0018] Further preferably, the formula for the ergonomic risk associated with the single action is as follows:

[0019]

[0020] Among them, Risk 单调 is the ergonomic risk associated with a single action, N R , are the number of nodes in the regional transfer network, the weight and risk value of the i-th node, is the number of posture transformation networks in the i-th node of the regional transfer network, N P is the number of nodes in the posture transformation network, and are the node weight and node risk value of the nth node in the jth posture transformation network in the i-th node of the regional transfer network, respectively. i is the node number in the regional transfer network, j is the jth posture transformation network in a certain region, and n is the node number in the posture transformation network.

[0021] Further preferably, the formula for the ergonomic risk associated with the mechanical cyclic action is as follows:

[0022]

[0023] Among them, Risk 循环 are ergonomic risks associated with mechanical cyclical movements, and are the transfer degree, average node strength and number of nodes of the jth posture transformation network in the i-th node of the regional transfer network, N R , are the number of nodes in the regional transfer network, the weight and risk value of the i-th node, is the number of attitude transformation networks in the i-th node of the regional transfer network; i is the node number in the regional transfer network, and j is the attitude transformation network number in a certain region.

[0024] Further preferably, the average node strength and transfer degree The formula is as follows:

[0025]

[0026] Where N is the number of nodes, s n is the node weight of the nth node, k n is the number of adjacent nodes of the nth node, t n is the number of edges connecting the adjacent nodes of the nth node.

[0027] According to another aspect of the present invention, a worker ergonomic risk analysis system based on digital twin is provided, which includes an actuator for executing the above-mentioned worker ergonomic risk analysis method based on digital twin.

[0028] In general, the above technical solutions conceived by the present invention have the following beneficial effects compared with the prior art:

[0029] 1. This invention converts spatiotemporal trajectories into a regional transfer network and a posture transformation network. It also utilizes two risk calculation methods when calculating risk values: the ergonomic risk associated with a single action and the risk associated with a mechanical cyclic action. Both the regional transfer network and the posture transformation network are taken into account. By comprehensively considering the impact of worker posture, environmental factors, and mechanical cyclic operations, a comprehensive worker risk identification model is constructed to achieve precise risk monitoring and management.

[0030] 2. This invention employs both monotonic and cyclic risk calculation methods to independently analyze the health risks associated with awkward worker postures and cyclic mechanical operations. Monotonic calculation is suitable for static tasks requiring prolonged maintenance of the same posture, assessing the risk of fatigue accumulation; cyclic calculation targets highly repetitive mechanical tasks, assessing the fatigue risk of the musculoskeletal system. This dual-calculation approach accurately identifies and quantifies health risks across different tasks, optimizes the work environment and workflow, and effectively reduces the probability of occupational diseases among workers, thereby improving workplace safety and health.

[0031] 3. The conversion method of the regional transfer network and the posture transformation network provided by the present invention comprehensively considers the correspondence between the worker posture and the regional environment by constructing a nested network of regional transfer and posture transformation, thereby further considering the environmental impact in the worker posture risk assessment and improving the accuracy and comprehensiveness of risk analysis.

[0032] 4. The present invention builds a digital twin model of the construction site and sets up an offline simulation mode and a real-time monitoring mode. The offline simulation mode facilitates the collection of training data sets for the worker posture recognition neural network model, reducing labor costs and time expenditure; the real-time monitoring mode provides data centralization function, promotes the extraction of scene interaction semantics and centralized data processing and display. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1is a flow chart of a worker ergonomic risk analysis method based on digital twins constructed according to a preferred embodiment of the present invention;

[0034] Figure 2 is a schematic diagram of a space-time trajectory constructed according to a preferred embodiment of the present invention;

[0035] Figure 3 It is a structural diagram of converting the spatiotemporal trajectory into a region transfer network and a posture transformation network constructed according to a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0037] A digital twin-based ergonomic risk analysis method for workers develops differentiated safety analysis strategies for different worker movement patterns, providing an important reference for adaptive ergonomic risk analysis. This analysis involves three steps: multiscale spatiotemporal network construction and transformation, and metric extraction. Specifically, the method includes the following steps:

[0038] (1) Use the digital twin model to obtain the workers' spatiotemporal trajectory at the construction site and identify their position and posture in the spatiotemporal trajectory.

[0039] Build a digital twin model of the construction site: Convert the 3D models of workers, buildings, and construction equipment into .FBX format and import them into Unity software to build the digital twin model of the construction site.

[0040] Configure the offline simulation mode and real-time monitoring mode of the construction site digital twin model:

[0041] Offline simulation mode: Skeletal models representing typical and awkward construction postures are bound to the worker model. A posture state machine is configured, and semantic labels are assigned to each posture to enable control over the worker model's switching between different construction postures. The worker model is then controlled through scripting. This mode allows the skeletal node data and corresponding posture semantics for each posture to be output by controlling the worker model's motion, generating a virtual dataset for training the neural network for worker posture recognition.

[0042] Real-time monitoring mode: Wearable inertial motion capture devices and UBW devices are used to collect worker posture and trajectory data, respectively. Data communication is established between the data acquisition devices and the worker model to map the worker's motion trajectory to the worker model. Construction areas are divided within the construction site digital twin model, and collision boxes are set and labeled for each area. The spatial intersection of the worker model's own collision box and the collision box of a specific area in the construction site digital twin model triggers the acquisition of information about the worker's area. Using a trained worker posture recognition neural network, the worker model's posture is recognized in real time, capturing the worker's posture information at every moment.

[0043] Based on this model, the workers' spatiotemporal trajectory and motion sequence data, as well as the area and posture information at each moment, can be obtained in real time from the digital twin model of the construction site.

[0044] (2) Convert the spatiotemporal trajectories in the workers’ digital twin data into a spatial unit transfer network. First, select an appropriate unit grid size to divide the construction site into multiple spatial units, assign corresponding semantic information to each unit, and mark the functional attributes of different areas. Then, by tracking the workers’ movement paths between different units in the construction site, obtain the time series data of the workers’ movement trajectories. Subsequently, using the time series network (chronnet) technology, these time series are converted into a complex network model for analysis.

[0045] In order to further explore the regional scale transfer law and attitude scale transformation characteristics of workers during the construction process, the spatial unit transfer network is further converted into a regional transfer network and an attitude transformation network;

[0046] (3) By analyzing the network structure and its related measurement methods, it is possible to identify potential nonlinear risk patterns in worker behavior. In this study, risk characteristics were quantitatively evaluated based on the complexity and density of the network, and ultimately, the ergonomic risks caused by monotonous and mechanical cyclical work under different risk environments were identified through risk intensity weighted calculation.

[0047] Specifically, the conversion of spatiotemporal trajectory data into a spatiotemporal network mainly involves using the time series network to convert the time series into a complex network. The specific steps are:

[0048] First, by selecting the appropriate time step and the spatial unit grid coordinates corresponding to each time point, the time series X = {r1, r2, ..., r T}, where T is the total length of the sequence. The i-th (i=1,2,...,T) time point r in the sequence i By event timestamp t i , location information L i ={La i ,Loi Area information j (j=1,2,...,M), action information k (k=1,2,...,N), where M and N are the total number of region categories and action categories respectively.

[0049] Afterwards, according to the spatial position of the trajectory points in the spatial network, if two consecutive time points r i (Located in the unit (La i ,Lo i ) and r i+1 (Located in the unit (La i+1 ,Lo i+1 )) appears continuously within the time window of 1s, then from node v i to v j Create a directed edge with weight 1. Node v i and v j Represents the ID of the cell where two consecutive trajectory points are located. If two nodes are located in the same cell, the node forms a self-loop. This process is repeated until the time length T. The edge weight between nodes is the number of transitions between adjacent cells or within a cell. Finally, a weighted directed complex network with self-loops is constructed—the spatial cell transition network.

[0050] Specifically, the spatial unit transfer network is converted into a regional transfer network. The specific steps are as follows: Since different spatial units may be located in the same region, nodes with the same region in the spatial unit transfer network are merged into a single node to generate a regional transfer network. In the regional transfer network, network nodes are converted into different regions, and edges between nodes indicate the existence of regional transfer relationships. Risk values ​​are artificially set for nodes in different regions. Edge weights are the sum of edge weights for the same regional transfer direction in the spatial unit transfer network, reflecting the number of transfers between the same or different regions. The newly generated network is still a weighted directed complex network with self-loops.

[0051] The spatial unit transfer network is converted into a posture transformation network. The specific steps are as follows: Within a region, each worker undergoes a series of posture transformations as the project progresses. Therefore, nodes with the same posture from multiple spatial unit transfer networks within a region are merged into a single node to generate a posture transformation network. In the posture transformation network, network nodes are transformed into different postures, and edges between nodes indicate the existence of posture transformation relationships. Network nodes are assigned risk values ​​based on the ergonomic risk level of each posture. Edge weights are the sum of edge weights for the same posture transition direction within the spatial unit transfer network, reflecting the number of transitions between the same or different postures. The resulting network is also a weighted directed complex network with self-loops. The risk value for each posture node is manually set.

[0052] Specifically, complexity measures the intensity with which workers transition between different risk levels within a network. Metrics include the number of nodes and the average network strength. Compactness measures the likelihood of repeated transitions between different risk levels. Metrics include the average network clustering coefficient and network modularity. The corresponding calculation formulas are shown in the table below. In complex network theory, the number of nodes, N, refers to the total number of vertices in the network. Networks with a large number of nodes indicate that workers tend to traverse more dangerous areas when transitioning between areas and that they are more attentive to avoiding repetitive movements and are less likely to suffer ergonomic injuries when rotating between positions. The average node strength, s, is the average risk strength of all nodes in the network. Higher values ​​indicate a greater tendency for workers to traverse high-risk areas and use high-risk construction positions.

[0053] The higher the transfer degree T of the network, the tighter the network is and the higher the degree of interconnection between different nodes.

[0054]

[0055] Where N is the number of nodes; s i is the weight of the i-th node, that is, the sum of the weights of all edges pointing to the node; k i is the number of adjacent nodes of the i-th node; t i is the number of edges connecting the adjacent nodes of the i-th node.

[0056] Specifically, the risk intensity weighted calculation is as follows:

[0057]

[0058] Among them, N R , are the number of nodes, node weight and node risk value of the regional transfer network respectively; is the number of posture transformation networks in the i-th node of the regional transfer network; N P is the number of nodes in the posture transformation network; are the node weight and node risk value of the j-th posture transformation network in the i-th node of the regional transfer network respectively; and are the transfer degree, average node weight and number of nodes of the jth posture transformation network in the i-th node of the regional transfer network, respectively.

[0059] It will be easily understood by those skilled in the art that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A worker ergonomic risk analysis method based on digital twins, characterized by: The method comprises the following steps: Acquiring the worker's spatiotemporal trajectory and motion sequence data; converting the worker's spatiotemporal trajectory and motion sequence data into a region transfer network and a posture transformation network; and calculating the number of nodes, average node strength, and transfer degree of the region transfer network and the posture transformation network, respectively; The number of nodes, average node strength and transfer degree of the region transfer network and the posture transformation network are used to calculate the ergonomic risk associated with a single action and the ergonomic risk associated with a mechanical cycle action, thereby achieving ergonomic risk analysis; The formula for the ergonomic risk associated with a single action is as follows: in, Risk 单调 is the ergonomic risk associated with a single action, are the number of nodes in the regional transfer network, i The weight and risk value of each node, It is the regional transfer network The number of posture transformation networks in the node, is the number of nodes in the posture transformation network, and Regional Transfer Network Node The node weight and node risk value of the nth node in the posture transformation network, i is the node number in the regional transfer network, j is the first j A pose transformation network, n is the node number in the posture transformation network; The formula for the ergonomic risk associated with the machine's cyclical motion is as follows: in, Risk 循环 are ergonomic risks associated with mechanical cycling movements, , and Regional Transfer Network Node The transfer degree, average node strength and number of nodes of the posture transformation network, are the number of nodes in the regional transfer network, i The weight and risk value of each node, It is the regional transfer network The number of posture transformation networks in the node; i is the node number in the regional transfer network, j It is the posture transformation network number within a certain area.

2. A worker ergonomic risk analysis method based on digital twins according to claim 1, characterized in that: The worker's spatiotemporal trajectory and action sequence data are obtained in the construction site digital twin model; before converting the spatiotemporal trajectory into a region transfer network and a posture transformation network, the spatiotemporal trajectory is converted into a spatiotemporal network according to the following steps: Discretize the space-time trajectory according to preset time intervals to obtain the position of the worker at each moment after discretization; Divide the workers' activity range into regions to obtain the region to which the workers' positions at each moment belong, as well as the transfer relationship between regions at different moments; Regions are regarded as nodes, and the transfer relations between regions are regarded as edges connecting the nodes, thereby forming a network, that is, converting the spatiotemporal trajectory into a spatial unit transfer network.

3. A worker ergonomic risk analysis method based on digital twins according to claim 2, characterized in that: The transfer relationship between the regions includes transfer between different regions and self-transfer within the same region.

4. A worker ergonomic risk analysis method based on digital twins according to claim 3, characterized in that: The conversion of spatiotemporal trajectories into regional transfer networks is performed according to the following steps: Nodes with the same region in the spatial unit network are merged to form a regional node, and the regional transfer relationship on the node before the merger is retained and converted into directed connection lines between regional nodes, thereby forming a new network, namely, a regional transfer network, wherein the number of directed connection lines on the regional node pointing to the current regional node is used as the weight of the current regional node.

5. The method for analyzing worker ergonomic risk based on digital twins according to claim 4, characterized in that: The transformation of spatiotemporal trajectories into a posture transformation network is performed in the following steps: In the spatial unit transfer network, for nodes in the same area at different times, determine the posture corresponding to each moment and the conversion relationship between postures at different moments; Nodes with the same posture are merged into one posture node, and the posture conversion relationship on each node before the merger is retained and converted into directed connection lines connecting the posture nodes, thereby forming a posture transformation network, wherein the number of wired connection lines on the posture node pointing to the current posture node is used as the weight of the current posture node.

6. The method for analyzing worker ergonomic risk based on digital twins according to claim 1, wherein: The average node strength and transfer degree The formula is as follows: Where N is the number of nodes, s n It is n The node weight of each node, k n It is n The number of adjacent nodes of a node, t n It is n The number of edges connecting adjacent nodes of a node.

7. A worker ergonomic risk analysis system based on digital twins, characterized by: The system includes an actuator for executing a worker ergonomic risk analysis method based on digital twins as described in any one of claims 1 to 6.

Images