Dear Editor,The food industry emphasizes improving demand forecasting to align production with consumer needs and reduce waste.This letter thus presents a study that integrates artificial intelligence(AI)and digital t...Dear Editor,The food industry emphasizes improving demand forecasting to align production with consumer needs and reduce waste.This letter thus presents a study that integrates artificial intelligence(AI)and digital twin(DT)technologies to enhance decision-making and efficiency in food production.A data-driven DT was implemented in an Italian company for Raspberry production planning,based on a daily demand forecasting tool powered by a dynamic extreme gradient boosting(XGBoost)algorithm.The model achieved a mean absolute percentage error(MAPE)of 16.37%with 1.69 average of absolute extra working hours(AEW)and a tracking signal(TS)range of[−1.9,+4.3].展开更多
A standard skill assessment （SA） tool was developed and implemented to evaluate the performance of op- erational forecast models in the Korea operational oceanographic system. The SA tool provided a robust way to as...A standard skill assessment （SA） tool was developed and implemented to evaluate the performance of op- erational forecast models in the Korea operational oceanographic system. The SA tool provided a robust way to assess model skill in the system by comparing predictions and observations, and involved the com- putation of multiple skill metrics including correlation and error skills. User- and system-based acceptance criteria of skill metrics were applied to determine whether predictions were acceptable for the system. To achieve this, the tool produced a time series comparison plot, a skill score table, and an advanced sum- marized diagram to effectively demonstrate the multiple skill scores. Moreover, the SA was conducted to evaluate both atmospheric and hydrodynamic forecast variables. For the atmospheric variables, acceptable error criteria were preferable to acceptable correlation criteria over short timescales, since the mean square error overwhelmed the observation variance. Conversely, for the hydrodynamic variables, acceptable root mean square percentage error （e.g., perms） criteria were preferable to acceptable error （e.g., erms） criteria owing to the spatially variable tidal intensity around the Korean Peninsula. Furthermore, the SA indicated that predetermined acceptance error criteria were appropriate to satisfy a target central frequency （fc） for which errors fell within the specified limits （i.e., the .fc equals 70%）.展开更多
Aiming at the deficiency of the robustness of thermal error compensation models of CNC machine tools, the mechanism of improving the models＇ robustness is studied by regarding the Leaderway-V450 machining center as t...Aiming at the deficiency of the robustness of thermal error compensation models of CNC machine tools, the mechanism of improving the models＇ robustness is studied by regarding the Leaderway-V450 machining center as the object. Through the analysis of actual spindle air cutting experimental data on Leaderway-V450 machine, it is found that the temperature-sensitive points used for modeling is volatility, and this volatility directly leads to large changes on the collinear degree among modeling independent variables. Thus, the forecasting accuracy of multivariate regression model is severely affected, and the forecasting robustness becomes poor too. To overcome this effect, a modeling method of establishing thermal error models by using single temperature variable under the jamming of temperature-sensitive points＇ volatility is put forward. According to the actual data of thermal error measured in different seasons, it is proved that the single temperature variable model can reduce the loss of fore- casting accuracy resulted from the volatility of tempera- ture-sensitive points, especially for the prediction of cross quarter data, the improvement of forecasting accuracy is about 5 μm or more. The purpose that improving the robustness of the thermal error models is realized, which can provide a reference for selecting the modelingindependent variable in the application of thermal error compensation of CNC machine tools.展开更多
基金supported by European Union’s Horizon Europe Research and Innovation Programme(101092043)project AGILEHAND(Smart Grading,Handling and Packaging Solutions for Soft and Deformable Products in Agile and Reconfigurable Lines).
文摘Dear Editor,The food industry emphasizes improving demand forecasting to align production with consumer needs and reduce waste.This letter thus presents a study that integrates artificial intelligence(AI)and digital twin(DT)technologies to enhance decision-making and efficiency in food production.A data-driven DT was implemented in an Italian company for Raspberry production planning,based on a daily demand forecasting tool powered by a dynamic extreme gradient boosting(XGBoost)algorithm.The model achieved a mean absolute percentage error(MAPE)of 16.37%with 1.69 average of absolute extra working hours(AEW)and a tracking signal(TS)range of[−1.9,+4.3].
基金The Project"Development of Korea Operational Oceanographic System(PM57041)"funded by the Ministry of Land,Transport and Maritime Affairs of the Korean Governmentthe Project"Cooperation on the Development of Basic Technologies for the Yellow Sea and East China Sea Operational Oceanographic System(YOOS)"funded by the China-Korea Joint Ocean Research Center(CKJORC)
文摘A standard skill assessment （SA） tool was developed and implemented to evaluate the performance of op- erational forecast models in the Korea operational oceanographic system. The SA tool provided a robust way to assess model skill in the system by comparing predictions and observations, and involved the com- putation of multiple skill metrics including correlation and error skills. User- and system-based acceptance criteria of skill metrics were applied to determine whether predictions were acceptable for the system. To achieve this, the tool produced a time series comparison plot, a skill score table, and an advanced sum- marized diagram to effectively demonstrate the multiple skill scores. Moreover, the SA was conducted to evaluate both atmospheric and hydrodynamic forecast variables. For the atmospheric variables, acceptable error criteria were preferable to acceptable correlation criteria over short timescales, since the mean square error overwhelmed the observation variance. Conversely, for the hydrodynamic variables, acceptable root mean square percentage error （e.g., perms） criteria were preferable to acceptable error （e.g., erms） criteria owing to the spatially variable tidal intensity around the Korean Peninsula. Furthermore, the SA indicated that predetermined acceptance error criteria were appropriate to satisfy a target central frequency （fc） for which errors fell within the specified limits （i.e., the .fc equals 70%）.
基金Supported by Key Project of National Natural Science Fund of China(Grant No.51490660/51490661)National Natural Science Foundation of China(Grant No.51175142)
文摘Aiming at the deficiency of the robustness of thermal error compensation models of CNC machine tools, the mechanism of improving the models＇ robustness is studied by regarding the Leaderway-V450 machining center as the object. Through the analysis of actual spindle air cutting experimental data on Leaderway-V450 machine, it is found that the temperature-sensitive points used for modeling is volatility, and this volatility directly leads to large changes on the collinear degree among modeling independent variables. Thus, the forecasting accuracy of multivariate regression model is severely affected, and the forecasting robustness becomes poor too. To overcome this effect, a modeling method of establishing thermal error models by using single temperature variable under the jamming of temperature-sensitive points＇ volatility is put forward. According to the actual data of thermal error measured in different seasons, it is proved that the single temperature variable model can reduce the loss of fore- casting accuracy resulted from the volatility of tempera- ture-sensitive points, especially for the prediction of cross quarter data, the improvement of forecasting accuracy is about 5 μm or more. The purpose that improving the robustness of the thermal error models is realized, which can provide a reference for selecting the modelingindependent variable in the application of thermal error compensation of CNC machine tools.
