Intelligent+temperature+control+system+of+quench+furnace
Ｖ０１．１４Ｎｏ．４Ｔｒａｎｓ．ＮｏｎｆｅｒｒｏｕｓＭｅｔ．Ｓｏｃ．ＣｈｉｎａＡｕｇ．２００４ＡｒｔｉｃｌｅＩＤ：１００３—６３２６（２００４）０４—０８０７—０４
Ｉｎｔｅｌｌｉｇｅｎｔｔｅｍｐｅｒａｔｕｒｅｃｏｎｔｒｏｌｓｙｓｔｅｍｏｆｑｕｅｎｃｈｆｕｒｎａｃｅ①
ＨＵＹａｎ—ｙｕ（胡燕瑜）１，ＧＵＩＷｅｉ—ｈｕａ（桂卫华）１，ＴＡＮＧＺｈａｏ—ｈｕｉ（ＪＮｉＮＮ）１，ＴＡＮＧＬｉｎｇ（ｆ蕾玲）２（１．ＳｃｈｏｏｌｏｆＩｎｆｏｒｍａｔｉｏｎＳｃｉｅｎｃｅａｎｄＥｎｇｉｎｅｅｒｉｎｇ，ＣｅｎｔｒａｌｓｏｕｔｈＵｎｉｖｅｒｓｉｔｙ，Ｃｈａｎｇｓｈａ４１００８３，Ｃｈｉｎａ；
２．ＩｎｓｔｉｔｕｔｉｏｎｏｆＰｒｏｄｕｃｅＣｏｍｍｏｄｉｔｙＱｕａｌｉｔｙＳｕｐｅｒｖｉｓｉｏｎａｎｄＴｅｓｔｉｎｇ，Ｃｈａｎｇｓｈａ４１００８７，Ｃｈｉｎａ）
Ａｂｓｔｒａｃｔ：Ａｆｕｚｚｙ－ｎｅｕｒａｌｎｅｔｗｏｒｋｓｉｎｔｅｌｌｉｇｅｎｔｔｅｍｐｅｒａｔｕｒｅｃｏｎｔｒｏｌｓｙｓｔｅｍｏｆｑｕｅｎｃｈｆｕｒｎａｃｅｗａｓｐｒｅｓｅｎｔｅｄ．Ｃｏｍ—ｂｉｎｅｄｇｅｎｅｔｉｃａｌｇｏｒｉｔｈｍｗｉｔｈｂａｃｋ—ｐｒｏｐａｇａｔｉｏｎａｌｇｏｒｉｔｈｍ，ｔｈｅｗｅｉｇｈｔｖａｌｕｅｓｏｆｎｅｕｒａｌｎｅｔｗｏｒｋｓ，ｐａｒａｍｅｔｅｒｓｏｆｆｕｚｚｙｍｅｍｂｅｒｓｈｉｐｆｕｎｃｔｉｏｎｓａｎｄｉｎｆｅｒｅｎｃｅｒｕｌｅｓｃａｎｂｅａｄｊｕｓｔｅｄａｕｔｏｍａｔｉｃａｌｌｙ，ｗｈｉｃｈｒｅａｌｉｚｅｓｔｈｅｏｐｔｉｍａｌｃｏｎｔｒｏｌｏｆｔｅｒｎ—ｐｅｒａｔｕｒｅ．Ｔｈｅｒｅｓｕｌｔｓｓｈｏｗｔｈａｔｔｈｉｓｃｏｎｔｒ０１ｓｙｓｔｅｍｃａｎｒｕｎｅｆｆｅｃｔｉｖｅｌｙｗｉｔｈｓａｔｉｓｆｉｅｄｔｅｍｐｅｒａｔｕｒｅｐｒｅｃｉｓｉｏｎ：ｉｎ
ｔｅｒｎ—ｐｅｒａｔｕｒｅｕｐｒｉｓｉｎｇｓｔａｇｅ，ｏｖｅｒｓｈｏｔ
ｏｆｔｅｍｐｅｒａｔｕｒｅｉｓｕｎｄｅｒ４℃；ｉｎｓｔａｂｌｅｓｔａｇｅ，ｔｈｅｓｃｏｐｅｏｆｔｅｍｐｅｒａｔｕｒｅｃｈａｎｇｅｉｓｃｏｎｔｒｏｌｌｅｄｗｉｔｈｉｎ士２℃，ｗｈｉｃｈｍｅｅｔｓｔｈｅｎｅｅｄｏｆｃｏｎｔｒｏｌｖｅｒａｃｉｔｙｏｆｔｅｍｐｅｒａｔｕｒｅ．
Ｋｅｙｗｏｒｄｓ：ｆｕｚｚｙ－ｎｅｕｒａｌｎｅｔｗｏｒｋｓ；ＭＩＭＯｓｙｓｔｅｍ；ｇｅｎｅｔｉｃａｌｇｏｒｉｔｈｍ
ＣＬＣｎｕｍｂｅｒ：ＴＰ１８３Ｄｏｃｕｍｅｎｔｃｏｄｅ：Ａ
ｌＩＮＴＲｏＤＵＣＴＩｏＮ
Ｑｕｅｎｃｈｆｕｒｎａｃｅｉｓａｋｉｎｄｏｆｋｅｙｅｑｕｉｐｍｅｎｔ
ｕｓｅｄｔｏｈｅａｔｔｒｅａｔｌａｒｇｅｃｏｍｐｌｅｘｃｏｍｐｏｎｅｎｔｓｏｆａｉｒ—
ｃｒａｆｔｓｏｒｒｏｃｋｅｔｓ，ｗｉｔｈｈｅｉｇｈｔｏｆ２４ｍ，ｃｏｎｔａｉｎｉｎｇ
ｔｗｏｈｅａｔｉｎｇｒｏｏｍｓａｎｄａｗｏｒｋｒｏｏｍ，ｗｉｔｈｓｔｅｅｌ
ｂｏａｒｄｓｓｅｔｂｅｔｗｅｅｎｔｈｅｒｏｏｍｓ．Ｂｏｔｈｈｅａｔｉｎｇｒｏｏｍｓ
ａｒｅｓｅｐａｒａｔｅｄｉｎｔｏｓｉｘｓｅｃｔｉｏｎｓ，ｅａｃｈｏｆｗｈｉｃｈｃｏｎ—
ｔａｉｎｓａｈｅａｔｉｎｇｒｅｓｉｓｔａｎｃｅｃｏｎｔｒｏｌｌｅｄｂｙａｐｏｗｅｒａｄ—
ｊｕｓｔｅｒ．Ｗｏｒｋｐｉｅｃｅｓａｒｅｐｕｔｉｎｗｏｒｋｒｏｏｍ．Ａｃｅｎ—
ｔｒｉｆｕｇａｌｅｌｅｃｔｒｏｍｏｔｏｒｉｓｕｓｅｄｔｏｂｌｏｗｈｏｔａｉｒｉｎｔｏ
ｗｏｒｋｒｏｏｍｆｒｏｍｈｅａｔｉｎｇｒｏｏｍ．Ｔｈｅｄｅｍａｎｄｏｆａｌ—
ｌｏｙｉｎｔｅｍｐｅｒａｔｕｒｅ—ｒｉｓｉｎｇｒａｔｅａｎｄｓｔａｂｌｅｖｅｒａｃｉｔｙａｔ
ｆｉｘｅｄｔｅｍｐｅｒａｔｕｒｅｐｏｉｎｔｉｓｈｉｇｈ，ｒｉｓｉｎｇｔｉｍｅｎｅｅｄｓ
ｔｏｂｅｓｈｏｒｔ，ｏｖｅｒｓｈｏｏｔｔｅｍｐｅｒａｔｕｒｅｓｈｏｕｌｄｋｅｅｐ
ｕｎｄｅｒ６℃，ａｔｔｈｅｓｔａｂｌｅｓｔａｇｅ，ｔｈｅｓｃｏｐｅｏｆｔｅｍ—
ｐｅｒａｔｕｒｅｃｈａｎｇｅｉｓｎｏｔｍｏｒｅｔｈａｎ土３℃．Ｔｈｅｓｅ
ｔｗｏｆａｃｔｏｒｓａｆｆｅｃｔｔｈｅｓｔｒｕｃｔｕｒｅａｎｄｑｕａｌｉｔｙｏｆ
ｗｏｒｋｐｉｅｃｅｓ，ｅｓｐｅｃｉａｌｌｙｔｈｅｌａｔｔｅｒ．Ｔｈｅｓｔｒｕｃｔｕｒｅｏｆ
ｔｈｅｑｕｅｎｃｈｆｕｒｎａｃｅｉｓｓｈｏｗｎｉｎＦｉｇ．１．
Ｔｅｍｐｅｒａｔｕｒｅｃｏｎｔｒｏｌｓｙｓｔｅｍｏｆｑｕｅｎｃｈｆｕｒｎａｃｅ
ｉｓｎｏｎｌｉｎｅａｒ，ｓｔｒｏｎｇ—ｃｏｕｐｌｉｎｇ，ｔｉｍｅ—ｖａｒｙｍｇ，ｌｏｎｇ—
ｔｉｍｅｄｅｌａｙ，ｗｈｉｃｈｍａｋｅｓｃｏｎｓｔｒｕｃｔｉｏｎｏｆａｃｃｕｒａｃｙ
ｓｙｓｔｅｍｍｏｄｅｌｉｍｐｏｓｓｉｂｌｅ．Ｍａｔｈｅｍａｔｉｃａｌｍｏｄｅｌｗａｓ
ｄｉｓｃｕｓｓｅｄｉｎＲｅｆ．［１］，ｔｅｍｐｅｒａｔｕｒｅｐｒｅｄｉｃｔｉｏｎｗａｓ
ｇｉｖｅｎｂｙｔｈｅａｃｑｕｉｒｅｄｍａｔｈｅｍａｔｉｃｍｏｄｅｌｉｎＲｅｆ．
［２］，ｂｅｃａｕｓｅｔｈｅｅｘｉｓｔｅｎｃｅｏｆｕｎｄｅｔｅｒｍｉｎａｂｌｅｆａｃ—
ｔｏｒｓ，ｔｈｅｖｅｒａｃｉｔｙｏｆｍｏｄｅｌａｎｄｐｒｅｄｉｃｔｉｏｎｗｅｒｅ
ｃｏｎｓｔｒａｉｎｅｄ．Ｍｕｌｔｉ—ｓｅｃｔｉｏｎｔｅｍｐｅｒａｔｕｒｅｃｏｎｔｒｏｌｗａｓ
ｄｉｓｃｕｓｓｅｄｉｎＲｅｆ．Ｅ３］，ｗｈｉｃｈｗａｓａｌｓｏｂａｓｅｄｏｎｍｅ—
ｃｈａｎｉｃｍａｔｈｅｍａｔｉｃａｌｍｏｄｅｌ．
Ｗｈｅｎｔｈｅｓｙｓｔｅｍｍｏｄｅｌｉｓｃｏｍｐｌｉｃａｔｅｄｏｒｈａｒｄ
ｔｏｃｏｎｓｔｒｕｃｔ＇ｅｎｇｉｎｅｅｒｓｅｘｐｅｒｔｋｎｏｗｌｅｄｇｅａｎｄｍｅｔｈｏｄｓ，ｓｕｃｈａｓｆｕｚｚｙｏｆｔｅｎｄｅｓｃｒｉｂｅｔｈｅｐｌａｎｔｂｙ
ｃｏｎｔｒｏｌｉｔｂｙｉｎｔｅｌｌｉｇｅｎｔ
ｏｒｅｘｐｅｒｔ
ｍｅｔｈｏｄ．Ｉｆｆｕｚｚｙ
１＼／／／／／／５
２～么厂＼／，Ｋ
／
／
／６
／
差＼
／薹
／
／
——
乡
／８
，９
／
３～
墨
１
厚
／
ｒ］
７
§
４一一——
么至
７董
厂］至
Ｉ
Ｖ／／／／／／Ａ
Ｆｉｇ．１
Ｓｔｒｕｃｔｕｒｅｏｆｑｕｅｎｃｈｆｕｒｎａｃｅ
１一ｓｈｅｌｌ：２一Ｓｔｅｅｌｂｏａｒｄ；３－－Ｔｈｅｒｍｏｃｏｕｐｌｅｉｎ
ｈｅａｔｉｎｇｒｏｏｍ；４－－Ｔｈｅｒｍｏｃｏｕｐｌｅｉｎｗｏｒｋｒｏｏｍ；
５－－Ｄｉｒｅｃｔｉｏｎｏｆｗｉｎｄ；６一Ｈｅａｔｉｎｇｒｏｏｍ；７～Ｗｏｒｋｒｏｏｍ；
８－－Ｈｅａｔｉｎｇｒｅｓｉｓｔａｎｃｅ；９－－Ｅｌｅｅｔｒｏｍｏｔｏｒ
ｃｏｎｔｒｏｌｉｓｃｈｏｓｅｎ，ｔｈｅｋｎｏｗｌｅｄｇｅｂａｓｅ，ｒｕｌｅｂａｓｅ，
ｔｙｐｅ
ｏｆｍｅｍｂｅｒｓｈｉｐｆｕｎｃｔｉｏｎｓ，ｄｅｆｕｚｚｉｆｉｃａｔｉｏｎ
ｍｅｔｈｏｄｓａｎｄｓｏｏｎ，ｗｉｌｌａｌｌａｆｆｅｃｔｔｈｅｃｏｎｔｒｏｌ
ｅｆｆｅｃｔ．
２ＦＵＺＺＹ—ＮＥＵＲｏＳＴＲＵＣＴＵＲＥｏＦＣｏＮＴＲｏＬ
ＳＹＳＴＥＭ
Ｍａｎｙｒｅｓｅａｒｃｈｒｅｓｕｌｔｓｈａｖｅｂｅｅｎａｃｑｕｉｒｅｄｉｎ
ｇｅｎｅｒａｔｉｎｇｆｕｚｚｙｒｕｌｅｓａｎｄａｄｊｕｓｔｉｎｇｆｕｚｚｙｍｅｍｂｅｒ
ｆｕｎｃｔｉｏｎｓｂｙｎｅｕｒａｌｎｅｔｗｏｒｋｓｏｒｇｅｎｅｔｉｃａｌｇｏ—
ｒｉｔｈｍｓｃ４—８｜。ｔｈｅｃｏｍｂｉｎａｔｉｏｎｏｆｎｅｕｒａｌｎｅｔｗｏｒｋｓａｎｄ
ｆｕｚｚｙｉｎｆｅｒｅｎｃｅｈａｓｔｈｅａｄｖａｎｔａｇｅｓｏｆｓｅｌｆ—ｌｅａｒｎｉｎｇ
ａｎｄｉｎｆｅｒｅｎｃｅ．Ｉｔｈａｓｂｅｅｎｗｉｄｅｌｙａｐｐｌｉｅｄｉｎｓｏｌｖｉｎｇ
ｅｎｇｉｎｅｅｒｉｎｇｐｒｏｂｌｅｍｓ［９—１１｜．
Ａｍｏｎｇｔｈｅｓｅｒｅｓｅａｒｃｈｅｓ，ｍｏｓｔｏｆｔｈｅｍａｒｅ
ｓｉｍｐｌｅｉｎｐｕｔａｎｄｓｉｍｐｌｅｏｕｔｐｕｔｓｙｓｔｅｍ（ＳＩＳＯ）Ｉｓ－７］，
ｏｒｍｕｌｔｉ—ｉｎｐｕｔａｎｄｓｉｍｐｌｅｏｕｔｐｕｔｓｙｓｔｅｍ
①ＦｏｕｎｄａｔｉｏｎｉｔｅｍｌＰｒｏｊｅｃｔ（２００２ＣＢ３１２２００）ｓｕｐｐｏｒｔｅｄｂｙｔｈｅＮａｔｉｏｎａｌＢａｓｉｃＲｅｓｅａｒｃｈＰｒｏｇｒａｍｏｆＣｈｉｎａ
Ｒｅｃｅｉｖｅｄｄａｔｅ：２００３一１０—３０ｌＡｃｃｅｐｔｅｄｄａｔｅ：２００４—０２—１０
ＣｏｒｒｅｓｐｏｎｄｅｎｃｅｔＨＵＹａｎ－ｙｕ，ＰｈＤｃａｎｄｉｄａｔｅ，Ｔｅｌ：－Ｉ－８６—７３１—８８７６２６２；Ｅ－ｍａｉｌ：ｒｅｓｕｎ＿Ｏ＠１６３．ｃｏｍ
．８０８．Ｔｒａｎｓ．ＮｏｎｆｅｒｒｏｕｓＭｅｔ．Ｓｏｃ．ＣｈｉｎａＡｕｇ．２００４＿［４＇８ｔ９’１２’１３１．ｔｈｅｎｒｅｇａｒｄｉｎｇｔｈｅｍｕｌｔｉ—ｉｎｐｕｔａｎｄ
ｍｕｌｔｉ—ｏｕｔｐｕｔｓｙｓｔｅｍ（ＭＩＭｏ）ａｓｔｈｅｃｏｍｂｉｎａｔｉｏｎｏｆ
ＭＩＳＯｓｙｓｔｅｍ。ｉｎｔｈｅｍｅａｎｔｉｍｅ，ｎｕｍｂｅｒｏｆｔｈｅ
ｍｅｍｂｅｒｓｈｉｐｆｕｎｃｔｉｏｎｓｏｆｉｎｐｕｔａｎｄｏｕｔｐｕｔｉｓｒｅｇａｒ—
ｄｅｄｔｏｂｅｓｉｍｉｌａｒ．Ｒｅｓｅａｒｃｈｏｎａｂｓｔｒａｃｔｉｎｇｒｕｌｅｓｂｙ
ＧＡｃａｎｂｅｆｏｕｎｄｉｎＲｅｆｓ．Ｅ６，１４１，ｂｕｔｏｎｌｙＭＩＳＯ
ｓｙｓｔｅｍｗａｓｄｉｓｃｕｓｓｅｄ．Ｉｎｔｈｉｓｐａｐｅｒ，ＭＩＭＯｆｕｚｚｙ－
ｎｅｕｒｏｓｙｓｔｅｍｗｉｔｈｄｉｆｆｅｒｅｎｔｓｅｍａｎｔｉｃｔｅｒｍｉｓｄｉｓ—
ｃｕｓｓｅｄ，ＧＡｏｐｔｉｍａｌｍｅｔｈｏｄｉｓａｌｓｏｅｍｐｌｏｙｅｄｔｏａｔ—
ｔａｉｎｇｅｎｅｒａｌＭＩＭ０ｍｅｔｈｏｄ，ｅｖｅｎｔｕａｌｌｙ，ｔｈｉｓｍｅｔｈ－
ｏｄｉｓｕｓｅｄｉｎｔｅｍｐｅｒａｔｕｒｅｃｏｎｔｒｏｌｏｆｑｕｅｎｃｈｆｕｒ－
ｎａＣｅ．
２．１
ＭＩＭＯ
ｆｕｚｚｙ－ｎｅｕｒｏｓｙｓｔｅｍ
Ｓｕｐｐｏｓｅｃｏｎｔｒｏｌｓｙｓｔｅｍｈａｓｍｉｎｐｕｔｓａｎｄ咒
ｏｕｔｐｕｔｓ，ｅａｃｈｉｎｐｕｔｈａｓＳｆ（ｉ一１，２，…，仇）ｍｅｍｂｅｒ—ｓｈｉｐｆｕｎｃｔｉｏｎｓ，ｅａｃｈｏｕｔｐｕｔｈａｓＴｊｍｅｍｂｅｒｓｈｉｐｆｕｎｃｔｉｏｎ（Ｊ＝１，２，…，咒），ｔｈｅｎｔｈｅｔｏｔａｌｒｕｌｅｉｓｑ一ⅡＳｉ（１）ｉ＝１
Ｅｑｎ．（１）ｓｈｏｗｓｔｈａｔｔｈｅｒｕｌｅｎｕｍｂｅｒｉｎｃｒｅａｓｅｓｉｎｉｎｄｅｘｌａｗｗｉｔｈｔｈｅｖａｒｉａｂｌｅｓａｎｄｔｈｅｍｅｍｂｅｒｓｈｉｐｆｕｎｃｔｉｏｎｓｏｆｖａｒｉａｂｌｅｓ．Ｓｔｒｕｃｔｕｒｅｏｆｆｕｚｚｙ—ｎｅｕｒｏｓｙｓｔｅｍｉｓｓｈｏｗｎｉｎＦｉｇ．２．
Ｙｎ
ｘ１ｂＬａｙｅｒ５
Ｈ“５）
Ｌａｙｅｒ４
Ｈ一４）
ｍａｔｒｉｘｉｓｒｅｐｒｅｓｅｎｔｅｄｂｙ∥孙，ｎｕｍｂｅｒｏｆｒｏｗａｎｄ
ｌｉｎｅｉｓｉｄｅｎｔｉｃａｌ，ｓｏｉｔｉｓａｄｉａｇｏｎａｌｍａｔｒｉｘ．
Ｗ（２）。
＇．，（３）一
１
ａｌｌ
０
Ｏ
０
Ｏ１
１Ｏ
Ｏ１
…
Ｏ
１
０
０
Ｏ
Ｏ
１
口棚ｍ
０…０１
Ｔｈｅｔｈｉｒｄｌａｙｅｒｄｅｓｃｒｉｂｅｓｔｈｅａｎｔｅｃｅｄｅｎｔｐａｒｔｏｆｒｕｌｅｓ．Ａｔｔｈｅｂｅｇｉｎｎｉｎｇ，ｎｅｕｒｏｎｎｏｄｅｎｕｍｂｅｒｉｓ
ｔｈｅｍａｘｉｍｕｍｒｕｌｅｓ，ｔｈｅｗｅｉｇｈｔｓｍａｔｒｉｘｏｆｎｅｕｒａｌ
ｎｅｔｗｏｒｋｓｗ（３’ｉｓｕｓｅｄｔｏｄｅｓｃｒｉｂｅｔｈｅａｎｔｅｃｅｄｅｎｔ
ｐａｒｔ，ｅａｃｈｒｏｗｏｆｔｈｅｍａｔｒｉｘｒｅｐｒｅｓｅｎｔｓｔｈｅａｎｔｅ—
ｃｅｄｅｎｔｏｆａｒｕｌｅ．ｔｈｅｅｌｅｍｅｎｔｓｏｆｍａｔｒｉｘｃｏｎｓｉｓｔｏｆ１
ａｎｄ０，ｗｈｅｒｅ‘１’ｄｅｎｏｔｅｓｔｈａｔｔｈｅｃｏｒｒｅｓＤｏｎｄｅｎｔ
ａｎｔｅｃｅｄｅｎｔｅｘｉｓｔｓ，‘０’ｉｓｏｎｔｈｅｖｅｒｓｕｓ。ｔｈｅｔｏｔａｌ
ｎｕｍｂｅｒｏｆ１ｉｓｌｅｓｓｔｈａｎ７ｎ．Ｔｈｅｎｏｄｅｆｕｎｃｔｉｏｎｃａｌ—
ｃｕｌａｔｅｓｔｈｅｆｉｒｉｎｇｓｔｒｅｎｇｔｈ，ｍｕｌｔｉｐｌｉｅｒｍｅｔｈｏｄｉｓａ—
ｄｏｐｔｅｄ，ｓｏｔｈｅｊｔｈｏｕｔｐｕｔｎｏｄｅｈａｓｔｈｅｆｏｌｌｏｗｉｎｇ
ｆｏｒｍ：
Ｔｈｅｒｏｗａｎｄｌｉｎｅｏｆｗｅｉｇｈｔｍａｔｒｉｘｗ‘３’ＩＩＳ；
ｉ＝１
Ｌａｙｅｒ３”
讯３）ａｎｄ∑Ｓｉ，ｒｅｓｐｅｃｔｉｖｅｌｙ，ｔｈｅｅｌｅｍｅｎｔｓ１ｉｎｔｈｅｆｉｒｓｔ
Ｌａｙｅｒ２
Ｈ“２）
Ｌａｙｅｒｌ
ｗＯ）
Ｆｉｇ．２Ｓｔｒｕｃｔｕｒｅｏｆｆｕｚｚｙ－ｎｅｕｒｏｓｙｓｔｅｍ
Ｔｈｅｆｉｒｓｔｌａｙｅｒｉｓｉｎｐｕｔｌａｙｅｒｗｈｉｃｈｉｓｃｒｉｓｐ，ｔｈｅｎｏｄｅｆｕｎｃｔｉｏｎｓｐｅｒｆｏｒｍｔｈｅｔｒａｎｓｆｅｒｏｆｉｎｐｕｔｔｏｔｈｅｎｅｘｔ１ａｙｅｒ，ｅｑｕａｔｉｏｎｓｂｅｔｗｅｅｎｔｈｅｉｎｐｕｔｓａｎｄｔｈｅｏｕｔｐｕｔｓｃａｎｂｅｗｒｉｔｔｅｎａｓ
ｑｆｌ）一∞譬’ｚ：Ｄ—ｗｎ’ｚ；”
Ｔｈｅｓｅｃｏｎｄｌａｙｅｒｐｅｒｆｏｒｍｓｆｕｚｚｉｆｉｃａｔｉｏｎｏｆｔｈｅ
ｉｎｐｕｔｖａｒｉａｂｌｅｓ，ｔｈｅｎｅｕｒｏｎｎｏｄｅｆｕｎｃｔｉｏｎｓｔｒａｎｓｆｅｒｔｈｅｃｒｉｓｐｉｎｐｕｔｉｎｔｏｓｅｍａｎｔｉｃｔｅｒｍ。ｉｆｔｈｅＧａｕｓｓａｃ—
ｔｉｖａｔｉｏｎｆｕｎｃｔｉｏｎｉｓｅｍｐｌｏｙｅｄ，ｗｅｈａｖｅｔｈｅｆｏｌｌｏｗ—ｉｎｇｅｑｕａｔｉｏｎ：
ｑ２，一Ｈｉ—ｅｘｐ［一（挚）ｚ］孝）－掣，
“ｉｉ
（２）ｗｈｅｒｅｔｈｅｗｅｉｇｈｔｓａｎｄｂｉａｓｅｓｏｆｎｅｕｒａｌｎｅｔｗｏｒｋｓｒｅｐｒｅｓｅｎｔ
ｔｈｅｗｉｄｔｈｓ（ｎ』ｆ）ａｎｄｔｈｅｍｅａｎｓ（Ｃｊｉ）ｏｆｉｎｐｕｔｍｅｍｂｅｒｓｈｉｐｆｕｎｃｔｉｏｎｓｒｅｓｐｅｃｔｉｖｅｌｙ．Ｎｕｍｂｅｒｏｆｎｅｕｒｏｎｓａｔｔｈｉｓｌａｙｅｒｉｓｎ２＝∑Ｓｆ．Ｗｅｉｇｈｔｓ
ｉ雀１ｒｏｗａｎｄｔｈｅｓｅｃｏｎｄｃｏｌｕｍｎ，ｔｈｅｆｉｒｓｔｒｏｗａｎｄｔｈｅｌａｓｔｃｏｌｕｍｎｒｅｐｒｅｓｅｎｔｔｈｅｆｏｌｌｏｗｉｎｇａｎｔｅｃｅｄｅｎｔ：ｒｕ［ｅ２：ＩＦｘ１ＩＳＰ１２ＡＮＤ…ＡＮＤｘ。ＩＳ弘。ＭＴＨＥＮ…
Ｔｈｅｏｔｈｅｒｓｒｅｐｒｅｓｅｎｔｔｈｅａｎｔｅｃｅｄｅｎｔｏｆｒｕｌｅｓｉｎｔｈｅｓｉｍｉｌａｒｍａｎｎｅｒ．
Ｔｈｅｆｏｕｒｔｈｌａｙｅｒｃｏｎｓｉｓｔｓｏｆｏｕｔｐｕｔｓ．Ｎｅｕｒｏｎ
ｏｕｔｐｕｔｉｎｔｈｉｓｌａｙｅｒｉｓｔｈｅｓｕｍｏｆｆｉｒｉｎｇｓｔｒｅｎｇｔｈｏｆｒｕｌｅｓｗｉｔｈｓｉｍｉｌａｒｃｏｎｓｅｑｕｅｎｃｅ，ｔｈｅｎｕｍｂｅｒｏｆｎｅｕ一
＂
ｒｏｎｉｓｎ４一ｙＴｊ，ａｎｄ丁ｉｉｓｔｈｅｎｕｍｂｅｒｏｆｍｅｍ一篇。
ｂｅｒｓｈｉｐｆｕｎｃｔｉｏｎｏｆｊｔｈｏｕｔｐｕｔ．Ｗｅｉｇｈｔｍａｔｒｉｘｃａｎｂｅａｄｊｕｓｔｅｄｉｎｔｈｅｔｒａｉｎｉｎｇｐｒｏｃｅｓｓ，ｅｖｅｒｙｅｌｅｍｅｎｔ
ｉｎｗｈｉｃｈｃｏｎｓｉｓｔｓｏｆ０ｏｒ１，ｅａｃｈｒｏｗ
ｒｅｐｒｅｓｅｎｔｓｔｈｅｏｕｔｐｕｔｍｅｍｂｅｒｓｈｉｐｆｕｎｃｔｉｏｎｔｅｒｍｉｎｔｈｅｃｏｎｓｅ—ｑｕｅｎｃｅｐａｒｔｏｆａｒｕｌｅｗｈｉｃｈｉｓｄｅｆｉｎｅｄｂｙｃｏｌｕｍｎ
ｎｕｍｂｅｒ．Ｓｉｎｃｅｔｈｅｒｅ
ａｒｅ７２ｏｕｔｐｕｔｓ，ｎｓｅｐａｒａｔｅｂｌｏｃｋｍａｔｒｉｘｅｘｉｓｔｓｒｅｐｒｅｓｅｎｔｉｎｇｅｖｅｒｙｏｕｔｐｕｔ．
ｍ
ＲＯＷｏｆｅａｃｈｂｌｏｃｋｍａｔｒｉｘｉｓＬ，ｃｏｌｕｍｎｉｓ口ｓ｛，
ｉ＝１
ｔｈｅｆｏｒｍｏｆｗｈｉｃｈｉｓｓｉｍｉｌａｒｔｏｔｈｅ
Ｗ（２），ｏｎｌｙｔｈｅｎｕｍｂｅｒｏｆｒｏｗａｎｄｃｏｌｕｍｎａｎｄｔｈｅｎｕｍｂｅｒｏｆ１ｉｎｔｈｅｍｉｓｄｉｆｆｅｒｅｎｔ．Ｆｏｒｅｘａｍｐｌｅ，ｐｏｓｉｔｉｏｎｏｆ１ｉｎｔｈｅｆｉｒｓｔｒｏｗａｎｄｔｈｅｓｅｃｏｎｄｃｏｌｕｍｎｏｆｉｔｈｂｌｏｃｋｍａｔｒｉｘｒｏｗｓｈｏｗｔｈａｔｔｈｅｓｅｃｏｎｄｒｕｌｅｈａｓｔｈｅｉｔｈｍｅｍｂｅｒ—ｓｈｉｐｆｕｎｃｔｉｏｎｔｅｒｍｉｎｔｈｅｃｏｎｓｅｑｕｅｎｃｅｐａｒｔ，ａｓｉｎ
０
．
Ｏ
一２
ｏ
一吼ｏ
Ｓ”
。Ⅱ㈦ｏ
２
ｌ
一
”
“ｑ
一
＼，
纷
，Ｌ
ｍ
ｍ
一
谚
Ｖ０１．１４№．４Ｉｎｔｅｌｌｉｇｅｎｔｔｅｍｐｅｒａｔｕｒｅｃｏｎｔｒｏｌｓｙｓｔｅｍｏｆｑｕｅｎｃｈｆｕｒｎａｃｅ?８０９?
ｔｈｅｆｏｌｌｏｗｉｎｇ：
Ｒ２：ＩＦ…ＴＨＥＮ…ＹｉＩＳＴ＿
Ｓｅｖｅｒａｌ‘１’ｍａｙｅｘｉｓｔｉｎｅａｃｈｒｏｗｏｆｗ‘”ｂｅ—
ｃａｕｓｅｃｏｎｓｅｑｕｅｎｃｅｏｆｓｅｖｅｒａｌｒｕｌｅｓｍａｙｈａｖｅｓｉｍｉｌａｒ
ｏｕｔｐｕｔｓｅｍａｎｔｉｃｔｅｒｍ，ｈｏｗｅｖｅｒ，ａｒｕｌｅｃａｎｈａｖｅ
ｏｎｌｙｏｎｅｏｕｔｐｕｔｔｅｒｍ，ｎｕｍｂｅｒｏｆ１ｉｎａｃｏｌｕｍｎｉｓ
ｎｏｔｍｏｒｅｔｈａｎ
ｗ“’一［硼１
ｒ０
ｏｎｅ，ｔｈｅｎ
ｗ２｜¨?１ｗ。
１
…１
ｗ‘４’ｉｓａｓ
｜¨?ｌ叫。］Ｔ
驴雌０?．００００。卜２，…川
毗一｜｜ｏ‘．１严ｌ＇Ｚ，…川
…
Ｔｈｅｆｉｆｔｈｌａｙｅｒｉｓｏｕｔｐｕｔｌａｙｅｒ，ｄｅｆｕｚｚｉｆｉｃａｔｉｏｎｉｓｐｅｒｆｏｒｍｅｄｉｎｔｈｉｓｌａｙｅｒ，ｉｆｃｅｎｔｅｒｏｆｇｒａｖｉｔｙｍｅｔｈｏｄｉｓｅｍｐｌｏｙｅｄ，ｏｕｔｐｕｔｃａｎｂｅｗｒｉｔｔｅｎａｓ
３，ｌ
２∑ｍ刍站口，／∑懿ａ，（４）』＝１Ｊ＝１
ｗｈｅｒｅｍＳａｎｄ毽ａｒｅｍｅａｎａｎｄｗｉｄｔｈｏｆｔｈｅｊｔｈｏｕｔ—ｐｕｔｍｅｍｂｅｒｓｈｉｐｆｕｎｃｔｉｏｎｆｏｒｔｈｅｉｔｈｓｙｓｔｅｍｏｕｔｐｕｔ．Ｗｅｉｇｈｔｍａｔｒｉｘｉｓｓｉｍｉｌａｒｔｏｔｈｅｓｅｃｏｎｄｌａｙｅｒ，ｒｏｗａｎｄｃｏｌｕｍｎａｒｅｅｑｕａｌ，ｉｔｃｏｎｓｉｓｔｓｏｆａｄｉａｇｏｎａｌｍａｔｒｉｘ．２．２Ｆｕｚｚｙ－ｎｅｕｒｏｓｔｒｕｃｔｕｒｅｏｆｑｕｅｎｃｈｆｕｒｎａｃｅＢｅｃａｕｓｅｔｈｅｔｗｏｈｅａｔｉｎｇｒｏｏｍｓｈａｖｅｔｈｅｓａｍｅｓｔｒｕｃｔｕｒｅ，ｈｅｒｅｏｎｌｙｏｎｅｉｓｄｉｓｃｕｓｓｅｄ，ｔｈｅｑｕｅｎｃｈ
ｆｕｒｎａｃｅｃａｎｂｅｔｒｅａｔｅｄ
ａｓａ６ｉｎｐｕｔｓ
ａｎｄ３ｏｕｔｐｕｔｓｃｏｎｔｒｏｌｓｙｓｔｅｍ．Ｔｈｅｉｎｐｕｔｓｃｏｎｔｒｏｌｔｈｅｏｎａｎｄｏｆｆｔｉｍｅｏｆｔｈｅｒｅｓｉｓｔａｎｃｅ，ｏｕｔｐｕｔｉｓｔｈｅｔｅｍｐｅｒａｔｕｒｅｏｆｗｏｒｋｒｏｏｍ．Ｉｎｔｈｅｈｅａｔｉｎｇｒｏｏｍ，ｈｏｔａｉｒｒｉｓｅｓ，ｓｏｔｈｅｂｏｔｔｏｍｒｅｓｉｓｔａｎｃｅｎｅｅｄｓｔｏｐｒｏｄｕｃｅｍｏｒｅｈｅａｔｔｏｍａｉｎｔａｉｎｔｈｅｕｎｉｆｏｒｍｉｔｙｏｆｔｈｅｔｅｍｐｅｒａｔｕｒｅｉｎｔｈｅｗｏｒｋｉｎｇｒｏｏｍ．Ｉｎｔｈｅｗｏｒｋｉｎｇｒｏｏｍ，ｔｈｅｈｏｔａｉｒｉ８ｆｒｏｍｔｏｐｔｏｂｏｔｔｏｍ，１０ａｄｉｎｇｗｏｒｋｐｉｅｃｅｓｉｓｔｈｒｏｕｇｈｂｏｔｔｏｍ，ｗｈｉｃｈｃａｕｓｅｓｔｈｅｌｏｗｅｒｐａｒｔｗｉｔｈ１０ｗｔｅｍｐｅｒａｔｕｒｅ．Ｉｎｏｒｄｅｒｔｏｓｉｍｐｌｉｆｙｔｈｅｐｒｏｂｌｅｍ，ｔｅｍｐｅｒａｔｕｒｅｖａｌｕｅｍｅａｓｕｒｅｄｉｎｕｐａｎｄｍｉｄｄｌｅｐａｒｔｉｓａｖｅｒａｇｅｄ，ｔｒｅａｔｅｄａｓｏｎｅｏｕｔｐｕｔ．
Ｔｈｅｄｉｆｆｅｒｅｎｃｅｏｆｔｅｍｐｅｒａｔｕｒｅ（ｅ）ａｎｄｔｈｅｃｈａｎｇｅｏｆｄｉｆｆｅｒｅｎｃｅ（Ａｅ）ａｒｅｔｒｅａｔｅｄａｓｆｕｚｚｙ－ｎｅｕｒｏｉｎｐｕｔｓ，ｔｈｅｄｉｆｆｅｒｅｎｃｅｉｓｄｅｓｃｒｉｂｅｄｂｙ５ｓｅ—ｍａｎｔｉｃｔｅｒｍｓ，ｔｈｅｃｈａｎｇｅｏｆｄｉｆｆｅｒｅｎｃｅｉｓｄｅｓｃｒｉｂｅｄｂｙ３ｓｅｍａｎｔｉｃｔｅｒｍｓ．Ｓｏｔｈｅｆｕｚｚｙ—ｎｅｕｒｏｎｅｔｗｏｒｋｓｈａｓ４ｎｏｄｅｓｉｎｔｈｅｆｉｒｓｔｌａｙｅｒ．１６ａｎｄ２２５ｎｏｄｅｓｉｎｔｈｅｓｅｃｏｎｄａｎｄｔｈｉｒｄｌａｙｅｒ，ｒｅｓｐｅｃｔｉｖｅｌｙ．Ｌｉｋｅｔｈｅｏｕｔｐｕｔｏｆｔｅｍｐｅｒａｔｕｒｅ，ｔｈｅｂｏｔｔｏｍｈｅａｔｉｎｇｒｏｏｍｉｓｄｅｓｃｒｉｂｅｄｂｙ５，ｔｈｅｏｔｈｅｒｓｕｓｅｄ３ｔｏｐｒｅｓｅｎｔ，ｓｏｔｈｅｆｏｕｒｔｈｌａｙｅｒａｎｄｔｈｅｆｉｆｔｈｌａｙｅｒｈａｓ２０ａｎｄ６ｎｏｄｅｓ，ｒｅｓｐｅｃｔｉｖｅｌｙ，ａｎｄｔｈｕｓｔｈｅｆｕｚｚｙ－ｎｅｕｒｏｎｅｔ—ｗｏｒｋｓｉｓｄｅｔｅｒｍｉｎｅｄ，ｔｈｅｗｅｉｇｈｔｍａｔｒｉｘｉｓａｄｊｕｓｔｅｄｂｙＧＡａｎｄＢＰ，ｏｐｔｉｃａｌｒｅａｌｉｚａｔｉｏｎｏｆｔｈｅｓｙｓｔｅｍａｒｅａｃｑｕｉｒｅｄｂｙｔｈｅｏｐｔｉｃａｌｐａｒａｍｅｔｅｒｓ．
３ＧＡＡＮＤＢＰＴＲＡＩＮＩＮＧＡＬＧｏＲＩＴＨＭＳＩｎｏｄｅｒｔｏａｃｑｕｉｒｅａｎｏｐｔｉｍａｌｆｕｚｚｙ－ｎｅｕｒｏｓｔｒｕｃｔｕｒｅｏｆｔｈｅｓｙｓｔｅｍ，ｔｒａｉｎｉｎｇｉｓｐｅｒｆｏｒｍｅｄｂｙｅｘｐｅｒｉｍｅｎｔｄａｔａ，ｂｙａｄｊｕｓｔｉｎｇｔｈｅｐａｒａｍｅｔｅｒｓａｎｄｒｕｌｅｓ．Ｂｅｆｏｒｅｔｒａｉｎｉｎｇｐｒｏｃｅｓｓ．ｔｈｅｉｎｉｔｉａｌｐａｒａｍｅ—ｔｅｒｓａｎｄｒｕｌｅｓａｒｅｃｈｏｓｅｎａｔｒａｎｄｏｍｏｒｂｙｅｘｐｅｒｔｅｘｐｅｒｉｅｎｃｅ．ＴｈｅｓｔｒｕｃｔｕｒｅｆｒａｍｅｉｓｓｈｏｗｎｉｎＦｉｇ．３．
Ｆｉｇ．３Ｓｔｒｕｃｔｕｒｅｏｆｃｏｎｔｒｏｌｓｙｓｔｅｍ
Ｆｒｏｍｔｈｅａｂｏｖｅａｎａｌｙｓｉｓ，ｗｅｋｎｏｗｔｈａｔｔｈｅｆｕｚｚｙｒｕｌｅｓａｒｅｄｅｆｉｎｅｄｉｎｌａｙｅｒｓ３ａｎｄ４．ＴｈｅｗｅｉｇｈｔｍａｔｒｉｘｉｓｃｏｄｅｄａｓｔｈｅｃｈｒｏｍｏｓｏｍｅｓｏｆＧＡ。ｗｈｉｃｈｈａｓｔｈｅｓｔｒｕｃｔｕｒｅａｓｆｏｌｌｏｗｓ：ｅａｃｈｃｈｒｏｍｏ—ｓｏｍｅｈａｓｎｐａｒｔｓ，ｅａｃｈｐａｒｔｉｓｃａｌｌｅｄａｓｕｂ—ｃｈｒｏｍｏ—ｓｏｍｅ，ｔｈｅｎｕｍｂｅｒｏｆｇｅｎｅｓｉｎｅａｃｈｓｕｂ－ｃｈｒｏｍｏ—ｓｏｍｅｉｓｔｈｅｓｕｍｏｆｒｕｌｅｓＱ，ｔｈｅａｎｔｅｃｅｄｅｎｔａｎｄｃｏｎｃｌｕｓｉｏｎｍａｔｒｉｘｉｓｅｎｃｏｄｅｄｂｙａｎｉｎｔｅｇｅｒ，ｗｈｉｃｈｂｅｌｏｎｇｔｏａｓｅｔＧ∈［ｏ，１，…，ｔ］（‘『一１，２，…，Ｑ）．Ｉｎｔｈｅｉｎｉｔｉａｌｐｈａｓｅ，ｔｈｅｌｅｎｇｔｈｏｆｅａｃｈ
ｐａｒｔｉｓｅｑｕａｌｔｏｔｈｅｎｕｍｂｅｒｏｆｍｅｍｂｅｒｓｈｉｐｆｕｎｃｔｉｏｎ，ｔｈｅｖａｌｕｅｏｆＣｉｄｅｎｏｔｅｓｔｈｅｒｏｗｐｏｓｉｔｉｏｎｏｆ１ｉｎｅａｃｈｃｏｌｕｍｎｏｆｔｈｅｉｔｈｃｏｎｃｌｕｓｉｏｎｂｌｏｃｋｍａｔｒｉｘ：ｉｆｔｈｅｒｅｉｓｎｏｍｅｍｂｅｒｓｈｉｐｆｕｎｃｔｉｏｎｏｆｃｅｒｔａｉｎｏｕｔｐｕｔ，Ｃｊｉｓｚｅｒｏ，ｔｈｅｓｔｒｕｃｔｕｒｅｏｆｃｈｒｏｍｏｓｏｍｅｃａｎｂｅｄｅｐｉｃｔｅｄｉｎＦｉｇ．４．
Ｆｉｇ．４
Ｆｏｒｍｏｆｃｈｒｏｍｏｓｏｍｅ
ＧＡａｃｔｓｏｎｅａｃｈｓｕｂ－ｃｈｒｏｍｏｓｏｍｅｔｏｆｉｎｄｔｈｅｏｐｔｉ—
ｒｅａｌｆｕｚｚｙｒｕｌｅｓ．Ｃａｌｃｕｌａｔｉｎｇｔｈｅｓｕｍｏｆｓｑｕａｒｅ
ｅｒｒｏｒｏｆｄｉｆｆｅｒｅｎｃｅｆｏｒｅａｃｈｉｎｄｉｖｉｄｕａｌｉｎｔｈｅｐｏｐｕｌａｔｉｏｎ．ｓｕｂ—
ｔｒａｃｔｉｎｇｉｔ
ｆｒｏｍｔｈｅｌａｒｇｅｓｔ
ｅｒｒｏｒｖａｌｕｅｏｆｔｈａｔｇｅｎｅｒａ—ｔｉｏｎｍａｋｅｓｔｈｅｆｉｔｎｅｓｓｆｕｎｃｔｉｏｎｏｆｅａｃｈｉｎｄｉｖｉｄｕａｌ。ｉｆｔｈｅｒｅａｒｅｅｎｏｕｇｈｉｎｐｕｔ／ｏｕｔｐｕｔｅｘｐｅｒｉｍｅｎｔｄａｔａ，ＧＡｃａｎｂｅａｐｐｌｉｅｄｔｏｆｉｎｄｔｈｅｏｐｔｉｍａｌｓｅｔｏｆｆｕｚｚｙｒｕｌｅｓ．Ｉｎｉｔｉａｌｉｚａｔｉｏｎｃｏｎｔｅｎｔｓｃｏｎｔａｉｎｔｈｅｆｏｌｌｏｗｉｎｇ：ｎｕｍｂｅｒｏｆｐｏｐｕｌａｔｉｏｎ，ｔｉｍｅｓｏｆｉｔｅｒａｔｉｏｎ，ｐｅｒｍｉｔｔｅｄｅｒｒｏｒｓ，ｓｅｌｅｃ—ｔｉｏｎｐｒｏｂａｂｉｌｉｔｙ，ｃｒｏｓｓｐｒｏｂａｂｉｌｉｔｙ，ｍｕｔａｔｉｏｎｐｒｏｂａｂｉｌｉ—ｔｙａｎｄＳＯｏｎ，ｔｈｅｃｈｒｏｍｏｓｏｍｅｓａｒｅｃｈｏｓｅｎｒａｎｄｏｍｌｙａｔｔｈｅｂｅｇｉｎｎｉｎｇ，ｄｅｎｏｔｉｎｇｔｈｅｗｅｉｇｈｔｍａｔｒｉｘｏｆｌａｙｅｒｓ３ａｎｄ４．
ＢｅｃａｕｓｅｔｈｅｉｎｉｔｉａｌｐａｒａｍｅｔｅｒｓｏｆＧａｕｓｓｆｕｎｃ—
ｔｉｏｎｉｓｃｈｏｓｅｎａｔｒａｎｄｏｍｏｒｂｙｅｘｐｅｒｔ
ｅｘｐｅｒｉｅｎｃｅ，ＢＰａｌｇｏｒｉｔｈｍｉｓｅｍｐｌｏｙｅｄｔｏｏｐｔｉｍｉｚｅｔｈｅｗｅｉｇｈｔｍａｔｒｉｘｐａｒａｍｅｔｅｒｓｏｆｌａｙｅｒｓ２ａｎｄ５．Ｔｈｅｏｂｊｅｃｔ
ｆｕｎｃｔｉｏｎｉｓｔｈｅｍｉｎｉｍｕｍｏｆｓｑｕａｒｅ
ｅｒｒｏｒｓｕｍ．
１』Ｌ
Ｅ一专≥：（ｙ＾一ｙ埘）２（５）
●Ｅ＝１
Ｔｈｅｏｐｔｉｍａｌｗｅｉｇｈｔｓａｎｄｔｈｒｅｓｈｏｌｄｓ
ａｒｅａｔｔａｉｎｅｄｂｙＢＰａｌｇｏｒｉｔｈｍ，ｗｈｉｃｈａｒｅｔｈｅｏｐｔｉｍａＩｍｅｍｂｅｒｓｈｉｐｆｕｎｃｔｉｏｎｐａｒａｍｅｔｅｒｓｏｆｉｎｐｕｔｓａｎｄｏｕｔｐｕｔｓ．ＴｗｏｉｎｐｕｔｓＭ噼ｈａｖｅｔｈｅｓｉｍｉｌａｒｐａｒａｍｅｔｅｒｓ．ａｎｄｔｈｅｕｐｐｅｒ５ｏｕｔ—
?８１０?
Ｔｒａｎｓ．ＮｏｎｆｅｒｒｏｕｓＭｅｔ．Ｓｏｃ．ＣｈｉｎａＡｕｇ．２００４
ｐｕｔｓ
ｈａｖｅｔｈｅｓｉｍｉｌａｒＭＦｐａｒａｍｅｔｅｒｓ．
４ＲＥＳＵＬＴＳ
Ｔｈｅｔｅｍｐｅｒａｔｕｒｅｉｓｍｅａｓｕｒｅｄｅｖｅｒｙ４００ｍｉｌｌｉ—ｓｅｃｏｎｄ，ａｖｅｒａｇｅｖａｌｕｅｏｆｅｖｅｒｙ５ｍｅａｓｕｒｅｖａｌｕｅｓａｓｏｎｅｍｅａｓｕｒｅｖａｌｕｅ，ａｖｅｒａｇｅｖａｌｕｅｏｆｅｖｅｒｙ４ｍｅａｓ—ｕｒｅｖａｌｕｅａｓｏｎｅｓａｍｐｌｅｖａｌｕｅ．Ｔｈｅｓｅｔｔｅｍｐｅｒａｔｕｒｅｖａｌｕｅｏｆｕｐａｎｄｍｉｄｄｌｅｐａｒｔｉｎｗｏｒｋｒｏｏｍｉｓ４７０，４６８℃ａｔｂｏｔｔｏｍｐａｒｔ，ｒｅｓｐｅｃｔｉｖｅｌｙ．Ｓａｍｐｌｅｉｎｔｅｒ—ｎａｌｉｓ８ｓ，ｔｈｅｓａｍｐｌｅｄａｔａｉｓａｌｓｏｔｈｅｆｅｅｄｂａｃｋｖａｌｕｅｏｆｃｏｎｔｒｏｌｓｙｓｔｅｍ．ＩｎＧＡ，ｉｎｉｔｉａｌｐｏｐｕｌａｔｉｏｎｉｓ５０，ｉｔｅｒａｔｉｖｅｔｉｍｅｓｉｓ２００，ｐｅｒｍｉｔｔｅｄｅｒｒｏｒｉｓ０．３℃，ｓｅｌｅｃｔｉｏｎｐｒｏｂａｂｉｌｉｔｙｉｓ０．５，ｃｒｏｓｓｐｒｏｂａｂｉｌｉｔｙｉｓ０．３，ｍｕｔａｔｉｏｎｐｒｏｂａｂｉｌｉｔｙｉｓ０．０５，ａｆｔｅｒｔｈｅＧＡａｎｄＢＰ，ｔｈｅｄａｔａｉｎＴａｂｌｅｓ１ａｎｄ２ａｒｅａｃｑｕｉｒｅｄ．ＥｘｐｅｒｉｍｅｎｔｓｈｏｗｓｔｈａｔｂｅｔｔｅｒｃｏｎｔｒｏＩｅｆｆｅｃｔｉｓａｔ—ｔａｉｎｅｄｂｙｔｈｅｓｅｐａｒａｍｅｔｅｒｓ，ｔｈｅｂｉｇｇｅｓｔｒｅｌａｔｉｖｅｅｒ—ｒｏｒｉｓ０．８９％．
Ｔａｂｌｅ１ＭＦＰａｒａｍｅｔｅｒｏｆ３ｉｎｐｕｔｓ
８ＡｅＣｌａｓｓＣｌａｓｓ
口ｆｎＣＮＢ９０１８２Ｎ３４３８
ＮＳ８５２６２Ｚ３８６８
Ｚ７１３３８Ｐ４２９８
ＰＳ５８３９６
ＰＢ５２４４５
Ｔａｂｌｅ２ＭＦＰａｒａｍｅｔｅｒｓｏｆ６ｏｕｔｐｕｔｓＣｌａｓｓ占ｍＣｌａｓｓ占ｍＳ０．２４０．３２ＶＳ０．２００．２５
Ｍ０．１６０．６８ＳＯ．１３Ｏ．４３
Ｂ０．２２０．８７Ｍ０．１４０．５６
Ｂ０．２３０．７１
ＶＢＯ．３０Ｏ．８６
５ＣｏＮＣＬＵＳＩｏＮＳ
１）ＴｈｅＭＩＭＯｓｙｓｔｅｍｍｏｄｅｌｏｆｑｕｅｎｃｈｆｕｒ—ｎａｃｅｉｓｃｏｎｓｔｒｕｃｔｅｄａｃｃｏｒｄｉｎｇｔｏｔｈｅｄｅｍａｎｄｏｆｔｅｍｐｅｒａｔｕｒｅ．Ｃｏｍｂｉｎｉｎｇｇｅｎｅｔｉｃａｌｇｏｒｉｔｈｍｗｉｔｈｂａｃｋ—ｐｒｏｐａｇａｔｉｏｎａｌｇｏｒｉｔｈｍ，ｔｈｅｗｅｉｇｈｔｖａｌｕｅｓｏｆｎｅｕｒａｌｎｅｔｗｏｒｋｓ，ｐａｒａｍｅｔｅｒｓｏｆｆｕｚｚｙｍｅｍｂｅｒｓｈｉｐｆｕｎｃｔｉｏｎｓａｎｄｉｎｆｅｒｅｎｃｅｒｕｌｅｓａｒｅａｄｊｕｓｔｅｄａｕｔｏｍａｔ—ｉｃａｌｌｙｔｏｒｅａｌｉｚｅｔｈｅｏｐｔｉｍａｌｃｏｎｔｒｏｌｏｆｔｅｍｐｅｒａｔｕｒｅ．２）Ｔｈｉｓｃｏｎｔｒ０１ｓｙｓｔｅｍｃａｎｒｕｎｅｆｆｅｃｔｉｖｅｌｖｗｉｔｈｓａｔｉｓｆａｃｔｏｒｙｔｅｍｐｅｒａｔｕｒｅｐｒｅｃｉｓｉｏｎ：ｉｎｕｐｒｉｓｉｎｇｓｔａｇｅ，ｏｖｅｒｓｈｏｔｏｆｔｅｍｐｅｒａｔｕｒｅｉｓ３℃，ｉｎｓｔａｂｌｅｓｔａｇｅ，ｔｈｅｓｃｏｐｅｏｆｔｅｍｐｅｒａｔｕｒｅｃｈａｎｇｅｉｓｃｏｎ—ｔｒｏｌｌｅｄｗｉｔｈｉｎ±２℃．Ｉｔｈａｓｂｅｅｎｕｓｅｄｉｎａｆａｃｔｏｒｙｓｕｃｃｅｓｓｆｕｌｌｙ．
［１１
［２３
［３］
［４１
［５１
［６］
［７３
［８］
［９１
［１０］
［１１］
［１２１
［１３］
［１４］
ＲＥＦＥＲＥＮＣＥＳ
ＬＩＵＧｕｉ—ｑｉｎｇ，ＨａｋａｍａｄａＨ．Ｍｏｄｅｌａｎａｌｙｓｉｓｆｏｒｃｏｒｎ—
ｂｕｓｔｉｏｎｃｈａｒａｃｔｅｒｉｓｔｉｃｓｏｆＲＤＦｐｅｌｌｅｔ［Ｊ＿：］．ＴｒａｎｓＮｏｎ—ｆｅｒｒｏｕｓＭｅｔＳｏｃＣｈｉｎａ，２００２，１２（３）：５３４—５３９．
ＺＨＥＮＱｉａｎｇ，ＢＡ０Ｈｏｎｇ，ＷＡＮＧＦｕ—ｍｉｎｇ，ｅｔａ１．
Ｐｒｅｄｉｃｔｉｏｎｏｆｔｈｅｒｍｏｄｙｎａｍｉｃｐｒｏｐｅｒｔｉｅｓｆｏｒｍｕｌｔｉｃｏｍ—
ｐｏｎｅｎｔｓｙｓｔｅｍｗｉｔｈＣｈｏｕｍｏｄｅｌ［Ｊ１．ＴｒａｎｓＮｏｎｆｅｒｒｏｕｓ
ＭｅｔＳｏｃＣｈｉｎａ，２０００，１０（５）：６４２—６４４．
ＣＨＥＮＧＸｉａｏ—ｒｕｉｎｇ．Ｒｅｓｅａｒｃｈｏｎｓｕｂｓｅｃｔｉｏｎｔｅｍｐｅｒａ—ｔｕｒｅｃｏｎｔｒｏｌｓｙｓｔｅｍ［Ｊ］．ＴｈｅＣｈｉｎｅｓｅＪｏｕｒｎａｌｏｆＮｏｎ—ｆｅｒｒｏｕｓＭｅｔａｌｓ，１９９８，８（Ｓ３）：１０３—１０５．（ｉｎＣｈｉｎｅｓｅ）
ＷＵＳｈｉ—ｑｉａｎ，ＪｏｏＥｒＭ，ＹＡＮＧＧａｏ．Ａｆａｓｔａｐｐｒｏａｃｈ
ｆｏｒａｕｔｏｍａｔｉｃｇｅｎｅｒａｔｉｏｎｏｆｆｕｚｚｙｒｕｌｅｓｂｙｇｅｎｅｒａｌｉｚｅｄｄｙｎａｍｉｃｆｕｚｚｙｎｅｕｒａｌｎｅｔｗｏｒｋｓ［Ｊ１．ＩＥＥＥＴｒａｎｓａｃｔｉｏｎｏｎＦｕｚｚｙＳｙｓｔｅｍｓ，２００１（４）：５７８—５９３．
ＣｈｅｏｎｇＦ，ＬａｉＲ．Ｃｏｎｓｔｒａｉｎｉｎｇｔｈｅｏｐｔｉｍｉｚａｔｉｏｎｏｆａｆｕｚｚｙｌｏｇｉｃｃｏｎｔｒｏｌｌｅｒｕｓｉｎｇａｎｅｎｈａｎｃｅｄｇｅｎｅｔｉｃａｌｇｏ—
ｒｉｔｈｍ［Ｊ］．ＩＥＥＥＴｒａｎｓａｃｔｉｏｎｏｎＳｙｓｔｅｍｓ，Ｍａｎ，ａｎｄ
Ｃｙｂｅｒｎｅｔｉｃｓ－－ＰａｒｔＢ，２０００（１）：３１—４５．
ＷＡＮＧＪｉｎｇ，ＬＩＹｕ－ｌａｎ，ＣＡＩＺｉ—ｘｉｎ，ｅｔａ１．Ｏｐｔｉｍａｌｄｅｓｉｇｎｍｅｔｈｏｄｏｆｆｕｚｚｙｓｙｓｔｅｍｂａｓｅｄｏｎｇａｓ［Ｊ］．Ｃｏｎ—
ｔｒｏｌＴｈｅｏｒｙａｎｄＡｐｐｌｉｃａｔｉｏｎ，１９９９（５）：７２８—７３４．（ｉｎＣｈｉｎｅｓｅ）
ＺＨＡＮＧＹｕｎ，ＭＡＯＺｈｏｎｇ—ｙｕａｎ．Ａｇｅｎｅｒａｌｉｚｅｄｆｕｚｚ—
ｙ－ＡＮＮｎｅｔｗｏｒｋｓａｎｄｉｔｓｌｅａｒｎｉｎｇａｌｇｏｒｉｔｈｍ［Ｊ］．Ｃｏｎ—
ｔｒｏｌＴｈｅｏｒｙａｎｄＡｐｐｌｉｃａｔｉｏｎ，１９９８（１）：１４８—１５１．（ｉｎＣｈｉｎｅｓｅ）
ＷＡＮＧｙｉｎ，ＲｏＮＧＧａｎｇ．Ａｓｅｌｆ－ｏｒｇａｎｉｚｉｎｇｎｅｕｒａｌ－ｎｅｔｗｏｒｋ—ｂａｓｅｄｆｕｚｚｙｓｙｓｔｅｍ［Ｊ１．ＣｏｎｔｒｏｌＴｈｅｏｒｙａｎｄＡｐｐｌｉｃａｔｉｏｎ，１９９９（６）：４５５—４５７．（ｉｎＣｈｉｎｅｓｅ）
ＷＡＮＧＹａｏ－ｎａｎ，ＺＨＡＮＧＣｈａｎｇ—ｆａｎ．Ｇｅｎｅｔｉｃ．ｂａｓｅｄ
ｎｅｕｒｏｆｕｚｚｙｎｅｔｗｏｒｋｃｏｎｔｒ０１ｆｏｒｃｏｍｐｌｉｃａｔｅｄｉｎｄｕｓｔｒｉａｌ
ｐｒｏｃｅｓｓ［Ｊ］．ＣｏｎｔｒｏｌＴｈｅｏｒｙａｎｄＡｐｐｌｉｃａｔｉｏｎ，１９９９（６）：８８６—８９１．（ｉｎＣｈｉｎｅｓｅ）
ＺＨＡＮＧＹｉ，ＬＩＲｅｎ－ｈｏｕ．Ｄｅｓｉｇｎｏｆｍｕｌｔｉ—ｖａｒｉａｎｃｅ
ｆｕｚｚｙｃｏｎｔｒｏｌｌｅｒｂａｓｅｄｏｎｇａｓ［Ｊ］．ＣｏｎｔｒｏｌＴｈｅｏｒｙａｎｄ
Ａｐｐｌｉｃａｔｉｏｎ，１９９６（５）：４０９—４１６．（ｉｎＣｈｉｎｅｓｅ）
ＹＡ０Ｙｉ—ｗｕ，ＸＩｏＮＧＪｉｎｇ－ｔａｏ，ＭＡ０Ｚｈｏｎｇ－ｙｕａｎ．
Ｓｅｌｆ－ｏｒｇａｎｉｚｅｄｆｕｚｚｙｃｏｎｔｒｏｌｌｅｒ［Ｊ］．ＣｏｎｔｒｏｌＴｈｅｏｒｙ
ａｎｄＡｐｐｌｉｃａｔｉｏｎ，１９９６（６）：７３８—７４３．（ｉｎＣｈｉｎｅｓｅ）
ＣＨＥＮＪｉａｎ－ｑｉｎ，ＣＨＥＮＬａｉ－ｊｉｕ．Ｌｅａｒｎｉｎｇｏｆｆｕｚｚｙ
ｒｕｌｅｓｂａｓｅｄｏｎｓｅｌｆ－ａｄａｐｔｉｖｅｎｅｕｒｏｎｓ［Ｊ１．Ｃｏｎｔｒｏｌａｎｄ
Ｄｅｃｉｓｉｏｎ，１９９４（５）：３５０—３５５．（ｉｎＣｈｉｎｅｓｅ）
ＳａｎｔｏｓＭ，ＤｅｘｔｅｒＡＬ．Ｔｅｍｐｅｒａｔｕｒｅｃｏｎｔｒ０１ｉｎ１ｉａｕｉｄ
ｈｅｌｉｕｍ
ｃｒｙｏｓｔａｔｕｓｉｎｇｓｅｌｆ－ｌｅａｒｎｉｎｇｎｅｕｒｏｆｕｚｚｙｃｏｎ—ｔｒｏｌｌｅｒ［Ｊ］．ＩＥＥＥＰｒｏｃ—ＣｏｎｔｒｏｌＴｈｅｏｒｙＡｐｐｌ，２００１
（３）：２３３—２３８．
ＳｅｔｔｅＳ，ＢｏｕｌｌａｒｔＬ．Ａｎｉｍｐｌｅｍｅｎｔａｔｉｏｎｏｆｇｅｎｅｔｉｃａｌ—
ｇｏｒｉｔｈｍｓｆｏｒｒｕｌｅｂａｓｅｄｍａｃｈｉｎｅｌｅａｒｎｉｎｇ［Ｊ］．Ｅｎｇｉ—
ｎｅｅｒｉｎｇＡｐｐｌｉｃａｔｉｏｎｏｆＡｒｔｉｆｉｃｉａｌＩｎｔｅｌｌｉｇｅｎｃｅ，２０００，
１３：３８１—３９０．
（ＥｄｉｔｅｄｂｙＬＯＮＧＨｕａｉ—ｚｈｏｎｇ）
Intelligent temperature control system of quench
furnace
作者：胡燕瑜， 桂卫华， 唐朝晖， 唐玲
作者单位：胡燕瑜,桂卫华,唐朝晖(School of Information Science and Engineering,Central south University,Changsha 410083,China)， 唐玲(Institution of Produce Commodity
Quality Supervision and Testing,Changsha 410087,China)
刊名：
中国有色金属学会会刊(英文版)
英文刊名：TRANSACTIONS OF NONFERROUS METALS SOCIETY OF CHINA
年，卷(期)：2004，14(4)
被引用次数：1次
参考文献(14条)
1.LIU Gui-qing.Hakamada H Model analysis for combustion characteristics of RDF pellet 2002(03)
2.ZHEN Qiang.BAO Hong.WANG Fu-ming Prediction of thermodynamic properties for multicomponent system with Chou model[期刊论文]-Transactions of Nonferrous Metals Society of China 2000(05)
3.CHENG Xiao ming Research on subsection temperature control system 1998(zk)
4.WU Shi-qian.Joo Er M.YANG Gao A fast approach for automatic generation of fuzzy rules by generalized dynamic fuzzy neural networks 2001(04)
5.Cheong https://www.wendangku.net/doc/178143874.html,i R Constraining the optimization of a fuzzy logic controller using an enhanced genetic algorithm 2000(01)
6.Wang Jing.LI Yu-lan.CAI Zi-xin Optimal design method of fuzzy system based on gas 1999(05)
7.Zhang Yun.MAO Zhong-yuan A generalized fuzzy-ANN networks and its learning algorithm 1998(01)
8.Wang Yin.RONG Gang A self-organizing neuralnetwork-based fuzzy system 1999(06)
9.Wang Yao-nan.ZHANG Chang-fan Genetic-based neurofuzzy network control for complicated industrial process 1999(06)
10.Zhang Yi.LI Ren-hou Design of multi-variance fuzzy controller based on gas 1996(05)
11.YAO Yi-wu.XIONG Jing-tao.MAO Zhong-yuan Self-organized fuzzy controller 1996(06)
12.CHEN Jian-qin.CHEN Lai-jiu Learning of fuzzy rules based on self-adaptive neurons 1994(05)
13.Santos M.Dexter A L Temperature control in liquid helium cryostat using self-learning neurofuzzy controller 2001(03)
14.Sette S.Boullart L An implementation of genetic algorithms for rule based machine learning 2000
相似文献(2条)
1.外文期刊HU Yan-yu.GUI Wei-hua.TANG Zhao-hui Intelligent temperature control system of quench
furnace
A fuzzy-neural networks intelligent temperature control system of quench furnace was presented. Combined genetic algorithm with back-propagation algorithm, the weight values of neural networks, parameters of fuzzy membership functions and inference rules can be adjusted automatically, which realizes the optimal control of temperature. The results show that this control system can run effectively with satisfied temperature precision; in temperature uprising stage, overshot of temperature is under 4 deg C ; in stable stage, the scope of temperature change is controlled within + - 2 deg C , which meets the need of control veracity of temperature.
2.外文会议Shuqing Wang.Hui Liu.Zipeng Zhang.Suyi Liu Research on the Intelligent Control Strategy
Based on FNNC and GAs for Hydraulic Turbine Generating Units
It is difficult to gain better control performance using general control strategy to control Hydraulic turbine generating units system because it is a complicated non-linear MIMO system. In this study, a new control technique, which efficiently get optimal control parameters for fuzzy neural network controller through the training of neural network and Genetic algorithms, was proposed and then applied to control turbine generating unit system. In the designed control system, fuzzy reasoning rules, member function
error is less. The improved genetic algorithms, which overcomes general genetic algorithms' disadvantage, has quick training speed and gives whole optimized parameters for fuzzy neural network controller. RBF neural network is employed to identify and predict the relation between input and output of hydroelectric generating units system. Simulation experiment results show that the designed controller can control hydraulic turbine generating units efficaciously and has quick controlling speed and less controlling max-error. So it provides a good control strategy for hydraulic turbine generating units system.
引证文献(1条)
1.姚玲英多参数解析描述的模糊控制规则及其优化方法[期刊论文]-广东教育学院学报 2005(3)
本文链接：https://www.wendangku.net/doc/178143874.html,/Periodical_zgysjsxb-e200404034.aspx
授权使用：河南工程学院(hngcxy)，授权号：89a855b5-fd10-4ab3-bc46-9e9900a22268
下载时间：2011年3月1日