CN-121994238-A - Operation path planning method and system integrating environment perception and occupational health

CN121994238ACN 121994238 ACN121994238 ACN 121994238ACN-121994238-A

Abstract

The invention provides a working path planning method and system integrating environment perception and occupational health, and particularly relates to a method and system for acquiring a three-dimensional map of a farm, establishing a harmful gas prediction model associated with an exhaust state, taking a personnel start point as a root node, carrying out offset sampling to a low concentration area according to the model, respectively constructing forward and backward random search trees, synthesizing geometric distance and predicted average concentration of path cost, carrying out reconnection optimization on double trees, updating father nodes of adjacent nodes with lower cost, generating an initial path by connecting the optimized double trees, calculating path cumulative harmful gas exposure, integrating the gas exposure as the product of residence time and concentration, determining target operation parameters of each exhaust device along the line, updating the prediction model by utilizing new parameters, repeatedly executing path search and exhaust parameter optimization until the total cost change of adjacent iterative paths is smaller than a convergence threshold, and outputting a working path and exhaust cooperation scheme.

Inventors

WANG SHENGNAN
FENG KAI
WANG KAI
YU XIAOSHENG
FENG YUKE

Assignees

河南牧业经济学院

Dates

Publication Date: 20260508
Application Date: 20260129

Claims (10)

1. A job path planning method integrating environment perception and occupational health is characterized by comprising the following steps: The method comprises the steps of acquiring a three-dimensional environment map of a farm, establishing a harmful gas distribution prediction model associated with the running state of exhaust equipment, taking a starting point and a target point of an operator as root nodes, and respectively constructing a forward search tree and a backward search tree by performing offset sampling in a sampling space; Reconnecting and optimizing the forward and backward search trees, and updating the father node of the adjacent node to be the new sampling node when a lower cost path reaching the adjacent node through the new sampling node exists in the search tree; taking the sum of the products of the estimated residence time of each position point on the path and the corresponding harmful gas concentration as the accumulated harmful gas exposure of the initial path, and determining the target operation parameters of each exhaust device along the path according to the exposure; And updating the harmful gas distribution prediction model according to the target operation parameters, repeatedly executing the path searching and exhaust parameter determining process based on the updated prediction model until the variation of the total cost of the path obtained by two adjacent iterations is smaller than a preset convergence threshold value, and outputting a cooperative scheme of the operation path and exhaust.
2. The method of claim 1, wherein the acquiring a three-dimensional environmental map of the farm, and establishing a harmful gas distribution prediction model associated with an operating state of the exhaust equipment, comprises: Gridding the three-dimensional environment map of the farm into a voxel set with a preset volume; based on a computational fluid dynamics method, a grid map, harmful gas source information and the running states of all exhaust devices are input as boundary conditions, and simulation calculation is performed to obtain the concentration value of the harmful gas in each voxel.
3. The method according to claim 1, characterized in that the offset sampling is in particular: randomly generating candidate sampling points and acquiring a predicted harmful gas concentration value; The probability of the candidate sampling point being admitted as a sampling node is inversely proportional to the predicted harmful gas concentration value.
4. The method of claim 1, wherein the connection-optimized forward and backward search trees generate an initial path comprising: Acquiring a complete forward search tree from a starting point to a target point and a complete backward search tree from the target point to the starting point; acquiring at least one region with a distance smaller than a preset value between a complete forward search tree and a complete backward search tree, and screening a candidate node pair in a terminal node set of which the distance between the complete forward search tree and the complete backward search tree is positioned in the region in each region; And obtaining an initial path by using the screened candidate node pairs.
5. The method of claim 1 or 4, wherein the reconnecting the forward and backward search trees to optimize, when there is a lower cost path in the search tree to a neighboring node via a new sampling node, updating the parent node of the neighboring node to be the new sampling node, comprising: Searching adjacent nodes in a neighborhood with a preset radius by taking the new sampling node as a center; if the path cost of reaching a certain adjacent node through the new sampling node is lower, the parent node of the adjacent node is updated to be the new sampling node.
6. A method according to any one of claims 1-3, wherein said taking as the cumulative exposure to the harmful gas of the initial path the sum of the products of the estimated residence time and the corresponding concentration of the harmful gas at each location on the path, comprises: discretizing the initial path into N path segments; Calculating estimated residence time of each path segment based on a preset moving speed v of an operator; And summing the product of the residence time of each path segment and the corresponding predicted harmful gas concentration to obtain the cumulative harmful gas exposure.
7. The method of claim 1, wherein said determining a target operating parameter for each exhaust device along the line based on said exposure comprises: And in the process of calculating the accumulated harmful gas exposure, identifying a path section with a total exposure contribution value exceeding a preset threshold value, and improving the target operation parameter of the exhaust equipment corresponding to the path section.
8. The job path planning system integrating environment perception and occupational health is characterized by comprising the following modules: the construction module is used for acquiring a three-dimensional environment map of the farm and establishing a harmful gas distribution prediction model related to the running state of the exhaust equipment, taking a starting point and a target point of an operator as root nodes, and respectively constructing a forward search tree and a backward search tree by carrying out offset sampling in a sampling space; the generation module is used for reconnecting and optimizing the forward and backward search trees, and updating the father node of the adjacent node to be the new sampling node when a lower cost path reaching the adjacent node through the new sampling node exists in the search tree; The determining module is used for taking the sum of products of the estimated residence time of each position point on the path and the corresponding harmful gas concentration as the accumulated harmful gas exposure of the initial path, and determining the target operation parameters of each exhaust device along the path according to the exposure; And the output module is used for updating the harmful gas distribution prediction model according to the target operation parameters, repeatedly executing the path searching and exhaust parameter determining process based on the updated prediction model until the variation of the total cost of the path obtained by two adjacent iterations is smaller than a preset convergence threshold value, and outputting a cooperative scheme of the operation path and exhaust.
9. The system of claim 8, wherein the acquiring a three-dimensional environmental map of the farm, building a harmful gas distribution prediction model associated with an operational state of the exhaust device, comprises: Gridding the three-dimensional environment map of the farm into a voxel set with a preset volume; based on a computational fluid dynamics method, a grid map, harmful gas source information and the running states of all exhaust devices are input as boundary conditions, and simulation calculation is performed to obtain the concentration value of the harmful gas in each voxel.
10. The system according to claim 8, characterized in that the offset sampling is in particular: randomly generating candidate sampling points and acquiring a predicted harmful gas concentration value; The probability of the candidate sampling point being admitted as a sampling node is inversely proportional to the predicted harmful gas concentration value.

Description

Operation path planning method and system integrating environment perception and occupational health Technical Field The application belongs to the field of path planning, and particularly relates to a job path planning method and system integrating environment awareness and occupational health. Background The farm dilutes and discharges harmful gases through exhaust equipment to maintain air quality. At present, manual start-stop, timing cycle or threshold linkage control based on a fixed position sensor is mostly adopted. The lack of awareness of the personnel location and specific work tasks in the field can not realize ventilation on demand, and it is difficult to carry out timely safety guarantee on the local sudden high-concentration pollution area or the path which the personnel will pass through. In route planning by an operator, a route is often selected based on personal experiences of the operator or only with the goal of shortening the travel distance, and risk factors of invisible but fatal concentration distribution of harmful gases are rarely considered. Although a path planning technology such as an a-algorithm and a fast-expansion random tree RRT algorithm mature exists in the robot field, the application scenario focuses on avoiding obstacles. The path planning of the personnel and the ventilation control of the environment are treated as two links, and an information interaction and collaborative decision mechanism is absent between the two links. May cause personnel to inadvertently traverse the high concentration risk area, and the ventilation system cannot predict the personnel's intent to travel, and cannot perform directional ventilation operations. And the existing forward and backward search trees are connected only according to distance, which is not necessarily optimal. Therefore, the optimal balance between ensuring personnel safety and improving ventilation efficiency cannot be achieved, and the improvement of the safe production and intelligent management level of the farm is limited. Disclosure of Invention The invention provides a working path planning method integrating environment perception and occupational health, which is used for solving the problem that the prior art cannot achieve the best balance between ensuring personnel safety and improving ventilation efficiency, and comprises the following steps: The method comprises the steps of acquiring a three-dimensional environment map of a farm, establishing a harmful gas distribution prediction model associated with the running state of exhaust equipment, taking a starting point and a target point of an operator as root nodes, and respectively constructing a forward search tree and a backward search tree by performing offset sampling in a sampling space; Reconnecting and optimizing the forward and backward search trees, and updating the father node of the adjacent node to be the new sampling node when a lower cost path reaching the adjacent node through the new sampling node exists in the search tree; taking the sum of the products of the estimated residence time of each position point on the path and the corresponding harmful gas concentration as the accumulated harmful gas exposure of the initial path, and determining the target operation parameters of each exhaust device along the path according to the exposure; And updating the harmful gas distribution prediction model according to the target operation parameters, repeatedly executing the path searching and exhaust parameter determining process based on the updated prediction model until the variation of the total cost of the path obtained by two adjacent iterations is smaller than a preset convergence threshold value, and outputting a cooperative scheme of the operation path and exhaust. In yet another aspect, the present invention provides a job path planning system that fuses environmental awareness and professional health, comprising: the construction module is used for acquiring a three-dimensional environment map of the farm and establishing a harmful gas distribution prediction model related to the running state of the exhaust equipment, taking a starting point and a target point of an operator as root nodes, and respectively constructing a forward search tree and a backward search tree by carrying out offset sampling in a sampling space; the generation module is used for reconnecting and optimizing the forward and backward search trees, and updating the father node of the adjacent node to be the new sampling node when a lower cost path reaching the adjacent node through the new sampling node exists in the search tree; The determining module is used for taking the sum of products of the estimated residence time of each position point on the path and the corresponding harmful gas concentration as the accumulated harmful gas exposure of the initial path, and determining the target operation parameters of each exhaust device along the path according to the expos