{"title":"利用传感器和机器学习模型,在实际规模上监测和预测采用不同干燥和储存技术的大豆的质量","authors":"","doi":"10.1016/j.jspr.2024.102386","DOIUrl":null,"url":null,"abstract":"<div><p>The application of monitoring techniques associated with artificial intelligence in grain drying and storage operations can assist in decision-making processes, preventing deterioration. Therefore, the objective of this study was to evaluate the effects of different drying technologies (continuous drying and dryer-silos) and storage methods (vertical and horizontal silos) on the quality of soybeans associated with Machine Learning algorithms to predict changes in grain quality. The environmental and intergranular variables monitored during the processes were correlated with physical and chemical quality parameters of the grains for prediction through Machine Learning models. The equilibrium moisture content above 12% increased the respiration of the stored grain mass to CO<sub>2</sub> concentration levels above 600 ppm, causing changes in the soybean quality from 4 to 14% dry matter loss, and reducing the apparent mass specific at 650 kg m<sup>−3</sup>, germination at 60%, oil yield reduced at 18%, and crude protein at 34%, as well as increased the electrical conductivity at 500 mS cm<sup>−1</sup> g<sup>−1</sup>, the acidity oil increased at 7 mg KOH g<sup>−1</sup>. It was observed that grain subjected to drying and storage conditions in dryer-silos maintained the highest grain quality at the end of the process. Although there were differences related on the applied drying and storage technology regarding changes in grain quality, it was noticed that the Artificial Neural Networks model demonstrated superior performance in predicting grain quality. Thus, it is recommended to conduct post-harvest drying of soybeans and subsequent grain storage in dryer-silos, while monitoring environmental and intergranular variables. This approach is advised to be coupled with the utilization of Artificial Neural Networks models to anticipate losses and enhance grain conversation with greater efficiency.</p></div>","PeriodicalId":17019,"journal":{"name":"Journal of Stored Products Research","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Monitoring and predicting the quality of soybeans for different drying and storage technologies on a real scale using sensors and Machine Learning models\",\"authors\":\"\",\"doi\":\"10.1016/j.jspr.2024.102386\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The application of monitoring techniques associated with artificial intelligence in grain drying and storage operations can assist in decision-making processes, preventing deterioration. Therefore, the objective of this study was to evaluate the effects of different drying technologies (continuous drying and dryer-silos) and storage methods (vertical and horizontal silos) on the quality of soybeans associated with Machine Learning algorithms to predict changes in grain quality. The environmental and intergranular variables monitored during the processes were correlated with physical and chemical quality parameters of the grains for prediction through Machine Learning models. The equilibrium moisture content above 12% increased the respiration of the stored grain mass to CO<sub>2</sub> concentration levels above 600 ppm, causing changes in the soybean quality from 4 to 14% dry matter loss, and reducing the apparent mass specific at 650 kg m<sup>−3</sup>, germination at 60%, oil yield reduced at 18%, and crude protein at 34%, as well as increased the electrical conductivity at 500 mS cm<sup>−1</sup> g<sup>−1</sup>, the acidity oil increased at 7 mg KOH g<sup>−1</sup>. It was observed that grain subjected to drying and storage conditions in dryer-silos maintained the highest grain quality at the end of the process. Although there were differences related on the applied drying and storage technology regarding changes in grain quality, it was noticed that the Artificial Neural Networks model demonstrated superior performance in predicting grain quality. Thus, it is recommended to conduct post-harvest drying of soybeans and subsequent grain storage in dryer-silos, while monitoring environmental and intergranular variables. This approach is advised to be coupled with the utilization of Artificial Neural Networks models to anticipate losses and enhance grain conversation with greater efficiency.</p></div>\",\"PeriodicalId\":17019,\"journal\":{\"name\":\"Journal of Stored Products Research\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2024-07-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Stored Products Research\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0022474X24001437\",\"RegionNum\":2,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENTOMOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Stored Products Research","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0022474X24001437","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENTOMOLOGY","Score":null,"Total":0}
Monitoring and predicting the quality of soybeans for different drying and storage technologies on a real scale using sensors and Machine Learning models
The application of monitoring techniques associated with artificial intelligence in grain drying and storage operations can assist in decision-making processes, preventing deterioration. Therefore, the objective of this study was to evaluate the effects of different drying technologies (continuous drying and dryer-silos) and storage methods (vertical and horizontal silos) on the quality of soybeans associated with Machine Learning algorithms to predict changes in grain quality. The environmental and intergranular variables monitored during the processes were correlated with physical and chemical quality parameters of the grains for prediction through Machine Learning models. The equilibrium moisture content above 12% increased the respiration of the stored grain mass to CO2 concentration levels above 600 ppm, causing changes in the soybean quality from 4 to 14% dry matter loss, and reducing the apparent mass specific at 650 kg m−3, germination at 60%, oil yield reduced at 18%, and crude protein at 34%, as well as increased the electrical conductivity at 500 mS cm−1 g−1, the acidity oil increased at 7 mg KOH g−1. It was observed that grain subjected to drying and storage conditions in dryer-silos maintained the highest grain quality at the end of the process. Although there were differences related on the applied drying and storage technology regarding changes in grain quality, it was noticed that the Artificial Neural Networks model demonstrated superior performance in predicting grain quality. Thus, it is recommended to conduct post-harvest drying of soybeans and subsequent grain storage in dryer-silos, while monitoring environmental and intergranular variables. This approach is advised to be coupled with the utilization of Artificial Neural Networks models to anticipate losses and enhance grain conversation with greater efficiency.
期刊介绍:
The Journal of Stored Products Research provides an international medium for the publication of both reviews and original results from laboratory and field studies on the preservation and safety of stored products, notably food stocks, covering storage-related problems from the producer through the supply chain to the consumer. Stored products are characterised by having relatively low moisture content and include raw and semi-processed foods, animal feedstuffs, and a range of other durable items, including materials such as clothing or museum artefacts.