期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到3篇文章
< 1 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Integrated learning diagnosis,SHAP interpretation,and economic benefit evaluation of pre-ignition events in hydrogen direct-injection engines 认领 引用
1
作者 Siyi Sun Xin An Jiaming Shi 《Advances in Engineering Innovation》 2026年第6期138-149,共12页
This paper proposes an intelligent diagnostic method for PEMC events in hydrogen direct-injection engines based on multi-model ensemble learning and SHapley Additive exPlanations(SHAP)interpretability analysis.Using 5... This paper proposes an intelligent diagnostic method for PEMC events in hydrogen direct-injection engines based on multi-model ensemble learning and SHapley Additive exPlanations(SHAP)interpretability analysis.Using 576 sets of bench-test operating-condition data,three models-Random Forest(RF),Extreme Gradient Boosting(XGBoost),and Light Gradient Boosting Machine(LightGBM)-were compared under stratified five-fold cross-validation.The results indicate that all three models achieved excellent performance,while XGBoost and LightGBM slightly outperformed the standalone Random Forest model in terms of F1 score(approximately 0.95)and Matthews correlation coefficient(approximately 0.89).SHAP analysis revealed that injection timing was the overwhelmingly dominant factor affecting PEMC,with a SHAP importance value of 3.32,which was 3.9 times higher than that of the second most influential factor.Ignition timing and engine speed ranked next in importance.Furthermore,the SHAP dependence plot identified a sharp risk escalation boundary for injection timing within the range of 200-260°CA Before Top Dead Center(BTDC).The PEMC prediction model based on RF-XGBoost requires only seven operating-condition parameters and achieves an F1 score greater than 0.94.The proposed approach can shorten the research and development cycle by 30%,reduce costs by approximately RMB 6 million,and maintain low deployment costs,thereby demonstrating substantial engineering and economic value. 展开更多
关键词 hydrogen direct-injection engine PEMC prediction XGBoost SHAP economic benefit analysis
An Integrated Approach to Evaluate Benefits and Costs of Wastewater and Solid Waste Management to Improve the Living Environment: The Citarum River in West Java, Indonesia 认领 引用 被引量：3
2
作者 S. M. Kerstens G. Hutton +2 位作者 I. Firmansyah I. Leusbrock G. Zeeman 《Journal of Environmental Protection》 2016年第11期1439-1465,共27页
Absence of wastewater and solid waste facilities impacts the quality of life of many people in developing countries. Implementation of these facilities will benefit public health, water quality, livelihoods and proper... Absence of wastewater and solid waste facilities impacts the quality of life of many people in developing countries. Implementation of these facilities will benefit public health, water quality, livelihoods and property value. Additional benefits may result from the potential recovery of valuable resources from wastewater and solid waste, such as compost, energy, phosphorus, plastics and paper. Improving water quality through implementation of wastewater and solid waste interventions requires, among others, an analysis of i) sources of pollution, ii) mitigating measures and resource recovery potentials and their effect on water quality and health, and iii) benefits and costs of interventions. We present an integrated approach to evaluate costs and benefits of domestic and industrial wastewater and solid waste interventions. To support a policy maker in formulating a cost and environmentally effective approach, we quantified the impact of these interventions on 1) water quality improvement, 2) resource recovery potential, and 3) monetized benefits versus costs. The integration of technical, hydrological, agronomical and socio-economic elements to derive these three tangible outputs in a joint approach is a novelty. The approach is demonstrated using the heavily polluted Indonesian Upper Citarum River in the Bandung region. Domestic interventions, applying simple (anaerobic filter) technologies, were economically most attractive with a benefit cost ratio (BCR) of 3.2, but could not reach target water quality standards. To approach the target water quality, both advanced domestic (nutrient removal systems) and industrial wastewater treatment interventions were required, leading to a BCR of 2. We showed that benefits from selling recovered resources represent here an additional driver for improving water quality and outweigh the additional costs for resource recovery facilities. While included benefits captured some of the major items, these may have been undervalued. Based on these findings, water quality interventions justify their costs and are socially and economically beneficial. 展开更多
关键词 Sanitation Water Quality Modeling Economic Cost Benefit Analysis Resource Recovery Asia Indonesia
暂未订购 下载PDF
Predictive maintenance for wind turbines:A physics-driven reinforcement learning strategy with economic-reliability collaborative optimization 认领 引用
3
作者 Jianghao Zhu Wei Chen +3 位作者 Le Su Bin Lan Tingting Pei Long Jin 《Energy and AI》 EI CSCD 2025年第4期246-262,共17页
Wind turbine maintenance optimization faces challenges in balancing economic efficiency with operational reliability under environmental uncertainty.Traditional maintenance approaches exhibit limitations in adaptive d... Wind turbine maintenance optimization faces challenges in balancing economic efficiency with operational reliability under environmental uncertainty.Traditional maintenance approaches exhibit limitations in adaptive decision-making,leading to increased operational costs and reliability risks.This study develops a physicsinformed reinforcement learning framework that integrates established domain knowledge with adaptive deci-sion algorithms.The approach embeds physical principles-including Weibull wind dynamics and multi-stage degradation models-into a reinforcement learning architecture,while introducing bidirectional temperature-degradation coupling for enhanced failure prediction.A high-fidelity simulation environment enables policy training through Proximal Policy Optimization,capturing complex interactions between environmental vari-ability and equipment deterioration.The framework was validated through case study implementation using northern China wind farm operational data.Results demonstrate zero-failure operation over simulated 19-year lifecycles,with economic performance improvements of 109.3%and 54.5%compared to conventional periodic and threshold-based maintenance strategies.By integrating physical constraints with intelligent algorithms,the method achieves adaptive maintenance decisions based on multi-dimensional state information. 展开更多
关键词 Wind turbine maintenance Deep reinforcement learning Predictive maintenance Operational state simulation Maintenance strategy optimization Economic benefit analysis
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈