Multi-user aquaculture automatic regulation system and method based on reinforcement learning

Abstract

The present invention proposes a multi-user aquaculture automatic control system based on reinforcement learning, which mainly consists of three modules: a control terminal, a data terminal and a cloud platform. The control terminal is used to collect water body data and atmospheric environment data, and transmit the collected data To the data terminal, at the same time, it can control the automatic control module to adjust the aquatic environment; the data terminal is used to collect the data collected by the control terminal and report it to the cloud platform, and can receive the control instructions of the cloud platform, and distribute the control instructions to each control terminal; The cloud platform uses reinforcement learning algorithms to analyze fish pond water quality data, and automatically sends control instructions to the data terminal. The invention can monitor the aquaculture environment in real time, realize automatic regulation by means of automation, save manpower, and is suitable for large-scale deployment.

Description

technical field [0001] The present invention relates to a multi-user aquaculture automatic control system and method based on reinforcement learning, specifically a multi-user aquaculture automatic control system and method based on continuous time reinforcement learning Q-Learning algorithm, belonging to reinforcement learning, automatic Control and aquaculture technology field. Background technique [0002] In aquaculture, the growth of fish is not only affected by the aquatic environment, but also by the atmospheric environment. The water temperature, PH value, dissolved oxygen and food quantity of the aquatic environment are all very important to the production of fish, and these indicators need to be tested and monitored frequently. The oxygen content in water is mainly obtained from the contact with air and the photosynthesis of aquatic plants, so it is necessary to monitor the air pressure that affects the dissolved oxygen and the air humidity that affects the photos...

AI Technical Summary

Problems solved by technology

However, the actual aquatic environment is complex, and it is far from enough to judge the range of dissolved oxygen

Some use deep reinforcement learning algorithms to adapt the optimal dissolved oxygen regulation scheme for dissolved oxygen in the water environment (application number: CN201810501384), and perform remote control and automatic execution. However, different types of fish require different ranges of dissolved oxygen. The various aquatic environments (PH, feed, water body capacity, etc.) are also different, which is not conducive to the individual management of multiple fish ponds by each farmer, and is not conducive to the overall growth of fish

Images