Heavy haul train reinforcement learning control method and system
A heavy-duty train and reinforcement learning technology, which is applied in general control systems, neural learning methods, control/regulation systems, etc., can solve complex process control that is not suitable for heavy-duty trains, poor performance of heavy-duty train control systems, and cumbersome calculations Complicated issues
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0064] Such as figure 1 As shown, a heavy-duty train reinforcement learning control method provided in this embodiment includes the following steps.
[0065] Step 101: Obtain the running status information of the heavy-duty train at the current moment; the heavy-duty train is composed of a plurality of vehicles, and the vehicles include traction locomotives and ordinary freight cars; the running status information includes the speed of the heavy-duty train and the speed of the heavy-duty train Location.
[0066] Step 102: According to the running state information of the heavy-duty train at the current moment and the virtual controller of the heavy-duty train, obtain the control instruction of the heavy-duty train at the next moment, and send the control instruction of the heavy-duty train at the next moment to the heavy-duty train The control unit is used to control the operation of heavy-duty trains.
[0067] Wherein, the heavy-haul train virtual controller stores line inf...
Embodiment 2
[0084] Such as figure 2 As shown, the present embodiment provides a heavy-duty train reinforcement learning control system, including:
[0085] The information acquisition module 201 is used to obtain the running status information of the heavy-duty train at the current moment; the heavy-duty train is composed of a plurality of vehicles, and the vehicles include traction locomotives and ordinary freight cars; the running status information includes the speed of the heavy-duty train and heavy haul train positions.
[0086] The control command determination module 202 is configured to obtain the heavy-duty train control command at the next moment according to the running state information of the heavy-duty train at the current moment and the virtual controller of the heavy-duty train, and transfer the heavy-duty train control command at the next moment Send it to the heavy-duty train control unit to control the operation of the heavy-duty train.
[0087] Wherein, the heavy-ha...
Embodiment 3
[0098] In order to achieve the above purpose, the present embodiment provides a heavy-duty train reinforcement learning control method, the method comprising:
[0099] Step 1: Build a heavy-duty train virtual controller
[0100] The recurrent neural network is pre-trained by using the actual operation history data of the heavy-duty train to obtain the expert experience network; the running process of the heavy-duty train is modeled by using the longitudinal dynamic equation of the multi-particle train, and the kinematic model of the heavy-duty train is obtained, and then strengthened In the learning environment, determine the reward function of the running process of the heavy-duty train (used as a reward evaluation for the current control command), the kinematics model of the heavy-duty train and the reward function constitute a heavy-duty train operation simulation environment, and the heavy-duty train operation simulation environment is controlled by input command to update...
PUM
![No PUM](https://static-eureka-patsnap-com.libproxy1.nus.edu.sg/ssr/23.2.0/_nuxt/noPUMSmall.5c5f49c7.png)
Abstract
Description
Claims
Application Information
![application no application](https://static-eureka-patsnap-com.libproxy1.nus.edu.sg/ssr/23.2.0/_nuxt/application.06fe782c.png)
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap