<kbd id="jce9hi4y"></kbd><address id="jce9hi4y"><style id="jce9hi4y"></style></address><button id="jce9hi4y"></button>

              <kbd id="4tlelmvx"></kbd><address id="4tlelmvx"><style id="4tlelmvx"></style></address><button id="4tlelmvx"></button>

                      <kbd id="kvlgcbsj"></kbd><address id="kvlgcbsj"><style id="kvlgcbsj"></style></address><button id="kvlgcbsj"></button>

                              <kbd id="yxsvlxap"></kbd><address id="yxsvlxap"><style id="yxsvlxap"></style></address><button id="yxsvlxap"></button>

                                      <kbd id="dnsnbilw"></kbd><address id="dnsnbilw"><style id="dnsnbilw"></style></address><button id="dnsnbilw"></button>

                                              <kbd id="xvzwhkn3"></kbd><address id="xvzwhkn3"><style id="xvzwhkn3"></style></address><button id="xvzwhkn3"></button>

                                                      <kbd id="9ku4cife"></kbd><address id="9ku4cife"><style id="9ku4cife"></style></address><button id="9ku4cife"></button>

                                                              <kbd id="gja1ugfc"></kbd><address id="gja1ugfc"><style id="gja1ugfc"></style></address><button id="gja1ugfc"></button>

                                                                      <kbd id="rakt28ny"></kbd><address id="rakt28ny"><style id="rakt28ny"></style></address><button id="rakt28ny"></button>

                                                                              <kbd id="olq0r5t1"></kbd><address id="olq0r5t1"><style id="olq0r5t1"></style></address><button id="olq0r5t1"></button>

                                                                                  10博体育
                                                                                  學術動態
                                                                                  當前位置: 10博体育首頁 > 學術動態 > 正文

                                                                                  博士生潘彤陽參加國際會議回國報告

                                                                                  發佈時間:2019-08-01 點擊數:


                                                                                  彙報題目:INDIN’19 參會報告

                                                                                  彙報時間:201982(星期五) 19:00

                                                                                  彙報地點:科技園 西五樓 北樓A228會議室

                                                                                  彙報人:潘彤陽

                                                                                  會議名稱:IEEE International Conference on Industrial Informatics, INDIN’19

                                                                                  會議時間:22-25 July, 2019

                                                                                  會議地點Helsinki-Espoo, Finland

                                                                                  會議簡介:IEEE INDIN international conference provides a forum for presentation and discussion of the state-of-art and future perspectives of industrial information technologies. Industry experts, researchers and academics are gathering together to share ideas and experiences surrounding frontier technologies, breakthroughs, innovative solutions, research results, as well as initiatives related to industrial informatics and their applications.

                                                                                  參加論文信息

                                                                                  Title: An Adversarial Learning Framework for Zero-shot Fault Recognition of Mechanical Systems

                                                                                  Author: Jinglong Chen, Tongyang Pan, Zitong Zhou, Shuilong He

                                                                                  Abstract: Data imbalance is a major problem in intelligent fault diagnosis. Aiming at this problem, the paper proposed a novel adversarial learning framework for zero-shot fault recognition of mechanical systems. The proposed network consists of three parts which are the feature extractor, the generator and the discriminator. Trained with normal samples, the proposed method is capable of generating unseen fault samples by changing the condition of the generator. After, these synthetic samples are used to train an improved deep neural network for fault recognition. Results show that the proposed method can recognize the unseen faults even though none of fault samples are available during training, which is meaningful for industry application

                                                                                  地址:陝西省西安市咸寧西路28號 郵編:710049
                                                                                             版权所有:10博体育 站點維護: 數據與信息中心 陝ICP備06008037號