Accurate identification and effective support of key blocks are crucial for ensuring the stability and safety of rock slopes.The number of structural planes and rock blocks were reduced in previous studies.This impair...Accurate identification and effective support of key blocks are crucial for ensuring the stability and safety of rock slopes.The number of structural planes and rock blocks were reduced in previous studies.This impairs the ability to characterize complex rock slopes accurately and inhibits the identification of key blocks.In this paper,a knowledge-data dually driven paradigm for accurate identification of key blocks in complex rock slopes is proposed.Our basic idea is to integrate key block theory into data-driven models based on finely characterizing structural features to identify key blocks in complex rock slopes accurately.The proposed novel paradigm consists of(1)representing rock slopes as graph-structured data based on complex systems theory,(2)identifying key nodes in the graph-structured data using graph deep learning,and(3)mapping the key nodes of graph-structured data to corresponding key blocks in the rock slope.Verification experiments and real-case applications are conducted by the proposed method.The verification results demonstrate excellent model performance,strong generalization capability,and effective classification results.Moreover,the real case application is conducted on the northern slope of the Yanqianshan Iron Mine.The results show that the proposed method can accurately identify key blocks in complex rock slopes,which can provide a decision-making basis and rational recommendations for effective support and instability prevention of rock slopes,thereby ensuring the stability of rock engineering and the safety of life and property.展开更多
the demand for wide-speed-range and long-endurance aircraft continues to grow,variable cycle engines have become a research hotspot due to their excellent multitask adaptability.However,traditional overall performance...the demand for wide-speed-range and long-endurance aircraft continues to grow,variable cycle engines have become a research hotspot due to their excellent multitask adaptability.However,traditional overall performance simulation techniques face challenges when dealing with complex engine configurations,as they require solving largerscale and higher-dimensional computational problems.This results in decreased simulation efficiency and poorer convergence,making it difficult to meet the demands for rapid performance evaluation and optimization.Although existing overall performance surrogate models for engines offer notable computational advantages,they still suffer from high training costs,low prediction accuracy,and limited application scenarios.To address these issues,this paper proposes an engine overall performance surrogate model driven by both knowledge and data.This model innovatively incorporates fundamental physical laws and domain knowledge of the engine during training and application,transforming the traditional black-box surrogate model into a gray-box model with certain interpretability.This significantly enhances prediction accuracy and application flexibility.Numerical verification results using the adaptive cycle engine(one of the most complex variable cycle configurations)as the application object show that the proposed surrogate model not only effectively predicts engine performance with prediction errors controlled within 0.5%,but also significantly improves the convergence and computational efficiency of engine performance simulation models.When applied to engine performance optimization,it achieves a nearly 60-fold increase in computational speed compared to traditional optimization methods,with an optimization error of only 0.15%.This approach can be widely applied to various types of engines and supports more complex and diverse engineering needs,offering broad application prospects.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.42277161,42230709).
文摘Accurate identification and effective support of key blocks are crucial for ensuring the stability and safety of rock slopes.The number of structural planes and rock blocks were reduced in previous studies.This impairs the ability to characterize complex rock slopes accurately and inhibits the identification of key blocks.In this paper,a knowledge-data dually driven paradigm for accurate identification of key blocks in complex rock slopes is proposed.Our basic idea is to integrate key block theory into data-driven models based on finely characterizing structural features to identify key blocks in complex rock slopes accurately.The proposed novel paradigm consists of(1)representing rock slopes as graph-structured data based on complex systems theory,(2)identifying key nodes in the graph-structured data using graph deep learning,and(3)mapping the key nodes of graph-structured data to corresponding key blocks in the rock slope.Verification experiments and real-case applications are conducted by the proposed method.The verification results demonstrate excellent model performance,strong generalization capability,and effective classification results.Moreover,the real case application is conducted on the northern slope of the Yanqianshan Iron Mine.The results show that the proposed method can accurately identify key blocks in complex rock slopes,which can provide a decision-making basis and rational recommendations for effective support and instability prevention of rock slopes,thereby ensuring the stability of rock engineering and the safety of life and property.
基金funded by National Natural Science Foundation of China under Grants 52406006,Fund Project 127000020241460012024-CXPT-GF-JJ-88-0001Supported by National Key Laboratory of Science and Technology on Aero-Engine Aero-thermodynamics and the Outstanding Research Project of Shen Yuan Honors College,BUAA(230123208).
文摘the demand for wide-speed-range and long-endurance aircraft continues to grow,variable cycle engines have become a research hotspot due to their excellent multitask adaptability.However,traditional overall performance simulation techniques face challenges when dealing with complex engine configurations,as they require solving largerscale and higher-dimensional computational problems.This results in decreased simulation efficiency and poorer convergence,making it difficult to meet the demands for rapid performance evaluation and optimization.Although existing overall performance surrogate models for engines offer notable computational advantages,they still suffer from high training costs,low prediction accuracy,and limited application scenarios.To address these issues,this paper proposes an engine overall performance surrogate model driven by both knowledge and data.This model innovatively incorporates fundamental physical laws and domain knowledge of the engine during training and application,transforming the traditional black-box surrogate model into a gray-box model with certain interpretability.This significantly enhances prediction accuracy and application flexibility.Numerical verification results using the adaptive cycle engine(one of the most complex variable cycle configurations)as the application object show that the proposed surrogate model not only effectively predicts engine performance with prediction errors controlled within 0.5%,but also significantly improves the convergence and computational efficiency of engine performance simulation models.When applied to engine performance optimization,it achieves a nearly 60-fold increase in computational speed compared to traditional optimization methods,with an optimization error of only 0.15%.This approach can be widely applied to various types of engines and supports more complex and diverse engineering needs,offering broad application prospects.
