The neuro-fuzzy network (NFN) is used to model the rules and experience of the process planner. NFN is to select the manufacturing operations sequences for the part features. A detailed description of the NFN system d...The neuro-fuzzy network (NFN) is used to model the rules and experience of the process planner. NFN is to select the manufacturing operations sequences for the part features. A detailed description of the NFN system development is given. The rule structure utilizes sigmoid functions to fuzzify the inputs, multiplication to combine the if Part of the rules and summation to integrate the fired rules. Expert knowledge from previous process Plans is used in determinning the initial network structure and parameters of the membership functions. A back-propagation (BP) training algorithm was developed to fine tune the knowledge to company standards using the input-output data from executions of previous plans. The method is illustrated by an industrial example.展开更多
Apartis described using features.Aneuro fuzzy system then determines the machining sequence for each feature.Previous process plans were utilized to build,test,and validate the Neuro Fuzzy Network (NFN). Parts hav...Apartis described using features.Aneuro fuzzy system then determines the machining sequence for each feature.Previous process plans were utilized to build,test,and validate the Neuro Fuzzy Network (NFN). Parts having similar manufacturing sequences are grouped into families, also using an NFN. A standard manufacturing sequenceis obtained for each family comprising allthe operations applicable to the features ofthe partsinthefamily.An expertsystem then adaptsthisstandard sequence forthe particular partbeing planned.Theoptimaloperation sequenceisinherited by the new part.The procedure is demonstrated by an example industrial part.展开更多
文摘The neuro-fuzzy network (NFN) is used to model the rules and experience of the process planner. NFN is to select the manufacturing operations sequences for the part features. A detailed description of the NFN system development is given. The rule structure utilizes sigmoid functions to fuzzify the inputs, multiplication to combine the if Part of the rules and summation to integrate the fired rules. Expert knowledge from previous process Plans is used in determinning the initial network structure and parameters of the membership functions. A back-propagation (BP) training algorithm was developed to fine tune the knowledge to company standards using the input-output data from executions of previous plans. The method is illustrated by an industrial example.
文摘Apartis described using features.Aneuro fuzzy system then determines the machining sequence for each feature.Previous process plans were utilized to build,test,and validate the Neuro Fuzzy Network (NFN). Parts having similar manufacturing sequences are grouped into families, also using an NFN. A standard manufacturing sequenceis obtained for each family comprising allthe operations applicable to the features ofthe partsinthefamily.An expertsystem then adaptsthisstandard sequence forthe particular partbeing planned.Theoptimaloperation sequenceisinherited by the new part.The procedure is demonstrated by an example industrial part.
