Design of an Intelligent Variable-Flow Recirculating Aquaculture System Based on Machine Learning Methods
| Autor: | Yishuai Du, Xu Zhe, Tianlong Qiu, Ming Sun, Zhou Li, Chen Fudi, Jianping Xu, Ye Li, Sun Jianming |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Technology
QH301-705.5 Computer science QC1-999 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences gene algorithm support vector machine Water environment Process control General Materials Science Biology (General) Cuckoo search QD1-999 Instrumentation 0105 earth and related environmental sciences circulating pump-drum filter linkage working technique Fluid Flow and Transfer Processes variable-flow regulation model Artificial neural network business.industry Physics Process Chemistry and Technology General Engineering Recirculating aquaculture system 04 agricultural and veterinary sciences Engineering (General). Civil engineering (General) recirculating aquaculture system Computer Science Applications Support vector machine Chemistry Test set Hyperparameter optimization machine learning methods 040102 fisheries 0401 agriculture forestry and fisheries Artificial intelligence TA1-2040 business computer |
| Zdroj: | Applied Sciences, Vol 11, Iss 6546, p 6546 (2021) Applied Sciences Volume 11 Issue 14 |
| ISSN: | 2076-3417 |
| DOI: | 10.3390/app11146546 |
| Popis: | A recirculating aquaculture system (RAS) can reduce water and land requirements for intensive aquaculture production. However, a traditional RAS uses a fixed circulation flow rate for water treatment. In general, the water in an RAS is highly turbid only when the animals are fed and when they excrete. Therefore, RAS water quality regulation technology based on process control is proposed in this paper. The intelligent variable-flow RAS was designed based on the circulating pump-drum filter linkage working model. Machine learning methods were introduced to develop the intelligent regulation model to maintain a clean and stable water environment. Results showed that the long short-term memory network performed with the highest accuracy (training set 100%, test set 96.84%) and F1-score (training 100%, test 93.83%) among artificial neural networks. Optimization methods including grid search, cuckoo search, linear squares, and gene algorithm were proposed to improve the classification ability of support vector machine models. Results showed that all support vector machine models passed cross-validation and could meet accuracy standards. In summary, the gene algorithm support vector machine model (accuracy: training 100%, test 98.95% F1-score: training 100%, test 99.17%) is suitable as an optimal variable-flow regulation model for an intelligent variable-flow RAS. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|