(1. 東北大學(xué) 材料電磁過程研究教育部重點(diǎn)實(shí)驗(yàn)室，沈陽 110004；
2. 沈陽大學(xué) 機(jī)械工程學(xué)院，沈陽 110044)
摘 要: 在電磁半連續(xù)鑄造條件下，針對(duì)不同工藝參數(shù)下鋁合金圓鑄錠的裂紋傾向，建立一種基于多層前饋神經(jīng)網(wǎng)絡(luò)的預(yù)測(cè)模型。網(wǎng)絡(luò)的輸入變量為鋁合金鑄錠的尺寸、成分以及工藝參數(shù)，輸出變量為裂紋的量化值，采用改進(jìn)后的帶動(dòng)量因子的BP訓(xùn)練算法，計(jì)算多組不同工藝條件下的裂紋預(yù)測(cè)值，并進(jìn)行真實(shí)試鑄實(shí)驗(yàn)。結(jié)果表明：裂紋預(yù)測(cè)結(jié)果的最大相對(duì)誤差為13.9%，最小相對(duì)誤差為0；在工藝指標(biāo)控制范圍內(nèi)，模型的裂紋預(yù)測(cè)曲線能較好地反映鑄錠裂紋的真實(shí)傾向。
關(guān)鍵字: 鋁合金；鑄錠裂紋；預(yù)測(cè)模型；人工神經(jīng)網(wǎng)絡(luò)
（1. The Key Laboratory of Electromagnetic Processing of Materials, Ministry of Education, Northeastern University, Shenyang 110004, China;
2. Academy of Mechanical Engineering, Shenyang University, Shenyang 110044, China）
Abstract:A prediction model based on multiplayer feed-forward artificial neural networks(ANN) was developed for modeling the correlation among different process parameters and cracks tendency of Al alloy ingot. The input variables were the size, composition and process parameters of ingots. The output variable was the quantified value of ingot cracks. The model was trained by the improved BP algorithm. The results show that the maximal relative error of prediction value is 13.9% and the minimal one is 0. The prediction curve makes a good performance in reflecting the ingot crack tendency.
Key words: Al alloy; ingot crack; prediction model; artificial neural network
