Given the challenge of estimating or calculating quantities of waste electrical and electronic equipment(WEEE)in developing countries,this article focuses on predicting the WEEE generated by Cameroonian small and medi...Given the challenge of estimating or calculating quantities of waste electrical and electronic equipment(WEEE)in developing countries,this article focuses on predicting the WEEE generated by Cameroonian small and medium enterprises(SMEs)that are engaged in ISO 14001:2015 initiatives and consume electrical and electronic equipment(EEE)to enhance their performance and profitability.The methodology employed an exploratory approach involving the application of general equilibrium theory(GET)to contextualize the study and generate relevant parameters for deploying the random forest regression learning algorithm for predictions.Machine learning was applied to 80%of the samples for training,while simulation was conducted on the remaining 20%of samples based on quantities of EEE utilized over a specific period,utilization rates,repair rates,and average lifespans.The results demonstrate that the model’s predicted values are significantly close to the actual quantities of generated WEEE,and the model’s performance was evaluated using the mean squared error(MSE)and yielding satisfactory results.Based on this model,both companies and stakeholders can set realistic objectives for managing companies’WEEE,fostering sustainable socio-environmental practices.展开更多
文摘Given the challenge of estimating or calculating quantities of waste electrical and electronic equipment(WEEE)in developing countries,this article focuses on predicting the WEEE generated by Cameroonian small and medium enterprises(SMEs)that are engaged in ISO 14001:2015 initiatives and consume electrical and electronic equipment(EEE)to enhance their performance and profitability.The methodology employed an exploratory approach involving the application of general equilibrium theory(GET)to contextualize the study and generate relevant parameters for deploying the random forest regression learning algorithm for predictions.Machine learning was applied to 80%of the samples for training,while simulation was conducted on the remaining 20%of samples based on quantities of EEE utilized over a specific period,utilization rates,repair rates,and average lifespans.The results demonstrate that the model’s predicted values are significantly close to the actual quantities of generated WEEE,and the model’s performance was evaluated using the mean squared error(MSE)and yielding satisfactory results.Based on this model,both companies and stakeholders can set realistic objectives for managing companies’WEEE,fostering sustainable socio-environmental practices.
文摘在空气绝缘变电站(air insulated substations,AIS)中,为了研究隔离开关分合空载母线产生的空间电磁环境对站内一次侧电子设备的影响,需要在实际变电站现场进行大量重复实验以获得空间电磁环境变化规律,但这对正常电力运维是不现实的。文中设计了可以模拟实际隔离开关操作产生的瞬态电磁场的隔离开关模拟骚扰源,利用该源对110 kV AIS隔离开关分合操作产生的电场随母线参数、隔离开关触头距离、电源容量进行研究。研究结果表明:该系统可以产生频率在0.9～2 MHz左右、强度在6～20 kV的空间瞬态电场,与现有文献报道的110 k V AIS站隔离开关操作实测瞬态电场数据相吻合。
