Engineering mechanical arm optimal energy consumption path optimization method based on closed-loop search units
A search unit, engineering machinery technology, applied in the direction of program control manipulators, manipulators, manufacturing tools, etc., can solve the problems of shortest path time-consuming, no real-time, poor timeliness, etc., to reduce computational complexity and shorten solution time , the effect of improving work efficiency
Active Publication Date: 2021-09-03
ZHEJIANG UNIV
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, applying the Dijkstra algorithm to solve the shortest path of a long-period fully connected neural network is too complicated and takes a long time. In industrial applications, the timeliness is poor and does not have real-time performance. Therefore, it is necessary to solve the shortest path with a shorter time Methods
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0036] The present invention will be further described in conjunction with specific embodiments and accompanying drawings.
[0037] Such as Figure 4 Shown, the present invention comprises the following steps:
[0038] 1) According to the position distribution of the engineering manipulator in the industrial scene, a fully connected neural network is constructed. The fully connected neural network is mainly composed of multiple fully connected sub-networks with the same structure connected sequentially, such as figure 1 shown;
[0039] Step 1) is specifically:
[0040] According to the position distribution of engineering robotic arms in industrial scenarios, each pick-and-place module is used as each fully-connected sub-network of the fully-connected neural network, and each area in each pick-and-place module is used as each layer of the current fully-connected sub-network. Each pick-and-place position of the engineering manipulator in the area is used as each neuron node of...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an engineering mechanical arm optimal energy consumption path optimization method based on closed-loop search units. The method comprises the following steps that 1), a full-connection neural network is constructed according to position distribution of engineering mechanical arms in an industrial scene; 2), the full-connection neural network is irregularly segmented to obtain multiple closed-loop search modules; 3), neuron nodes of different input layers in the closed-loop search modules are combined to obtain different closed-loop search units of all the closed-loop search modules, and the optimal closed-loop search units are selected; 4), open-loop search units of the full-connection neural network are determined, the shortest path composed of the optimal closed-loop search units and one open-loop search unit is calculated, the shortest path of the full-connection neural network is obtained, and the optimal energy consumption path of the engineering mechanical arms is obtained. According to the method, the optimal energy consumption path can be calculated under the condition of continuous work, and meanwhile compared with the mode that a Dijkstra algorithm is globally used for solving, the operation complexity of the optimization process can be significantly reduced.
Description
technical field [0001] The invention relates to a method for optimizing an optimal energy consumption path of an engineering mechanical arm in the field of engineering machinery path planning, in particular to a method for optimizing an optimal energy consumption path of an engineering mechanical arm based on a closed-loop search unit. Background technique [0002] In an actual industrial application scenario, the pick-and-place task of transferring objects from the starting point to the destination is realized by pipelined transfer of objects through many identical pick-and-place modules. Each pick-and-place module consists of many areas, and each area is equipped with an engineering robot arm, which can realize the picking and placing of objects in different positions in the area, and the objects are transmitted from the starting point to the end point through each area The engineering robotic arm picks and places objects in different positions and cooperates with the engi...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): B25J9/16G06N3/04
CPCB25J9/161B25J9/1664G06N3/045
Inventor 冯毅雄计若松洪兆溪
Owner ZHEJIANG UNIV