【正文】 (4) Research results show that 0e increases as the evaporation temperature increases or the condensation temperature decreases [4,6],and a higher evaporation temperature and a lower condensation temperature are beneficial to keep fruits and vegetable fresh . Thus the refrigeration system should run under a higher evaporation temperature and a lower condensation temperature. However the evaporation temperature is apparently limited by the temperature of the object under refrigeration. For a special kind of fruit or vegetable just entering the cold storage, its optimum storage temperature can be got with the orthogonal experimental method. The optimum storage temperature decreases with the increasing of the storage time. The loss of per unit of i th fruit or vegetable is (1) ( 2 )i i iL L L=+ (5) where (1)iL is produced by frostbiting, while (2)iL by deteriorating .When temperature increases , (1)iL decreases and (2)iL increases .Both of them are related to the storage time t , thus ( 1 ) ( 2 )( 1 ) 0 ( 2 ) 0[ , ] , [ , ]iii i i iLLf T t t f T t ttt抖 = = 抖 (6) where (1)if decreases and (2)if increases respectively when the temperature T increases , 0it denotes the time of entering the storage, while 0itt denotes the storage time, then we have 0( 1 ) 0 ( 2 ) 0{ [ , ] [ , ] }iti i i i itL f T t t f T t t d t= + 242。 從表 ,我們可以看到 ,通過使用本文提出的控制方法 ,保鮮效果已經(jīng)大大提高 ,系統(tǒng)運行更穩(wěn)定 本文提出了一種兩級 RBF神經(jīng)網(wǎng)絡計算的最佳冷藏溫度和溫度的預測。1 1a b a b a b a b a b a b? ＃ ＃ ? 所有的 1 1 2 2 3 3, , , , ,a b a b a b的初始值可以被選為 13 。D = + + + + +（ 20） 2 2 2( ) ( ) ( 1 ) ( 2 )e k e k e k e ka b g217。當狀態(tài)變量的穩(wěn)定值 ,控制算法用于計算倉庫的溫度 , 因此預測變量的集合不包含任何變量控制。 考慮一個時間窗口組成的 2Q 個 時間點 , 1212( 1 ) , ( 2 ) , . . ., . . . Qt t Q t t t Q t t tt t t t t Q t+= D = D == + D = + D (12) 分別用 ()qru 和 ()qsu 表示 ru 和 su 在 qt 時的值，令 ( 1 ) ( 1 ) ( 1 ) ( 1 ) ( ) ( ) ( ) ( )1 1 1 1( , .. ., , , .. ., , .. ., , .. ., , , .. . )Q Q Q Q TR S R Sx u u v v u u v v= (13) ( 1 ) ( 2 ) ( 1 ) 211( , ..., , ..., , ..., )Q Q Q Q TSSy v v v v++= (14) 式中 ( ) ,n R S Q m QS= + =，這些預測的作用是根據(jù)（ 13）式中的向量x 確定（ 14）式中的 y ，在當前時間 0t ， 所有的測量結果可以用來構造預測網(wǎng)絡的輸入。因為他們的魯棒 性 ,基于神經(jīng)網(wǎng)絡的預測方法吸引了越來越多的關注。 (9) 設 *T 表示 最佳儲存溫度。 單位水果或者蔬菜的損失滿足公式 (1) (2)i i iL L L=+ (5) 式中 (1)iL 是由水果或蔬菜被凍傷造成的，而 (2)iL 是由于時間關系而日益惡化造成的。 (3) 在這里 ,分子是一種傳統(tǒng)的 RBF 插值算法表達式 ,而分母不變的插值表達式 （ 1） 通過這種分母 ,衰減指數(shù)函數(shù)的分子是取消了極大的分母。一般來說 ,假設 n 個 輸入變量 1x ,… , nx 和 m 個 輸出變量 1y ,… , my .則： 1( ,..., )Tnx x x= (1) 1( ,..., )Tmy y y= (2) 使用 RBF 神經(jīng)網(wǎng)絡最優(yōu)控制冷藏 ， x 代表一個點的 n 維輸入空間nR ,而 y 代表一個點的 m 維輸出空間 mR ,假設隱藏的單位的數(shù)量 是 H。近年來 ,英國石油公司 將 神經(jīng)網(wǎng)絡用于冷庫溫度的最優(yōu)控制。因此本文提出了一種兩級RBF 神經(jīng)網(wǎng)絡。一個 RBF 神經(jīng)網(wǎng)絡有很強的非線性映射能力 ,一個好的插值性能 ,價值和更高的訓練速度。 后 來 ,毛皮商的轉換方法 ,切比雪夫的理論和一些基礎知識 的系統(tǒng) 我們得到了并且使用了 更好的結 論 ( 3)。第一階段是用來確定最佳值的冷藏溫度 , 而 第二個是用來預測溫度。229。最佳儲存溫度 隨著 儲存時間的增加而減小。 229。 冷庫溫度的在線預測 最優(yōu)控制的關鍵問題之一的存儲溫度是如何準確預測溫度。 輸入變量的選擇考慮是否 有 執(zhí)行控制 ,涉及以下兩種不同的情況 : 案例 l:自動控制系統(tǒng) 假設有 R 個 冷藏的操作變量 1,... Ruu和 S 個 狀態(tài)變量 1,...Svv。 RBF 神經(jīng)網(wǎng)絡的非線性映射函數(shù)是用來設計穩(wěn)定模型。 令 1( ) [ ( ) ( 1 ) ] [ ( 1 ) ( ) ] [ ( 2 ) ( 1 ) ]e k e k e k e k e k e k e ka b g217。 0 , 。229。 （ 15） Where su and ()uk are the initial value and the current value of the controlled variable respectively . ()ei is the difference between the assigned value and the real value of the control object, that is ( ) ( )e i v it= （ 16） where ()vi and t are the real value at i th time point and the assigned value of the control object respectively. Write equation (15) in the incremental form ,then we have ( ) ( ) ( 1 ) [ ( ) ( 1 ) ] ( )[ ( ) 2 ( 1 ) ( 2 ) ]cidu k u k u k K e k e k K e kK e k e k e kD = = + + + （ 17） Where siciTKKT= is the integral coefficient, ddcsTKKT=is the differential coefficient .Write the above equations in another form, then we have 2( ) ( ) ( ) ( )c i du k K e k K e k K e kD = D + + D （ 18） Under the case of having got the predicted value of the controlled variable ,equations(17)and(18)should be changed .Let kt denote the current time ,and suppose that the predicted values at the instants 1kt+ and 2kt+ of variable v with RBF neural work are ( 1)vk+ and ( 2)vk+ respectively ， Let ( 1) ( 1)e k v kt+ = + ( 2) ( 2)e k v kt+ = + （ 19） Combine the historic values with the predicted values of the variable to calculate the right side of equation(18).Let 1( ) [ ( ) ( 1 ) ] [ ( 1 ) ( ) ] [ ( 2 ) ( 1 ) ]e k e k e k e k e k e k e ka b g217。1 1a b a b a b a b a b a b? ＃ ＃ ? All of the initial values of 1 1 2 2 3 3, , , , ,a b a b a bcan be chosen as 13 . 6. APPLICATION The methods proposed in the paper have been used for the optimum control over the temperature of a cold storage for fruits and vegetables. Table 1 lists the daily storing losses of the fruits and vegetables before and after the methods proposed in the paper are used. For a special kind of fruit or vegetable, its daily loss rate is defined as / ,1i i il L E i N= ＃ Where N is the number of the kinds of fruits and vegetables, iL and iE are the loss and the market price of daily entry volume of i th special kind fruit or vegetable respectively,1 iN＃ .The loss does not only include the discarded part caused by deteriorating, but also the price decrease caused by the decreasing of the freshness .Suppose that the market value of i th fruit or vegetable based on its storing volume is iW ,define 1/Ni i jjw W W== 229。 gTXRm 6X4NGpP$vSTTamp。gTXRm 6X4NGpP$vSTTamp。 gTXRm 6X4NGpP$vSTTamp。 gTXRm6X4NGpP$vSTTamp。 UE9aQGn8xp$Ramp。 gTXRm6X4NGpP$vSTTamp。 gTXRm 6X4NGpP$vSTTa