CAJ | 학술논문

生物氧化预处理过程是一个复杂非线性的耦合过程，该过程关键参数氧化还原电位通常难以准确检测。为了预估该参数，将PSO算法与LSSVM相结合构建生物氧化预处理过程氧化还原电位预估模型。该模型采用改进的PSO算法优化LSSVM模型参数，克服了参数恒择的盲目性和耗时，具有恘习速度恩速、预测精度较高以及泛化能力强的优点。以新疆某金矿的实际数据进行仿真研究，结果表明：改进的PSO-LSSVM方法建立的模型的预测值与实测值拟合较好，对于生物氧化预处理过程的关键参数氧化还原电位的预估有一定的指导意义。
생물양화예처리과정시일개복잡비선성적우합과정，해과정관건삼수양화환원전위통상난이준학검측。위료예고해삼수，장PSO산법여LSSVM상결합구건생물양화예처리과정양화환원전위예고모형。해모형채용개진적PSO산법우화LSSVM모형삼수，극복료삼수항택적맹목성화모시，구유규습속도은속、예측정도교고이급범화능력강적우점。이신강모금광적실제수거진행방진연구，결과표명：개진적PSO-LSSVM방법건립적모형적예측치여실측치의합교호，대우생물양화예처리과정적관건삼수양화환원전위적예고유일정적지도의의。
The biological oxidation pretreatment process is a complex nonlinear and coupling process. It is difficult to measure the oxidation reduction potential by using conventional physical sensors. A soft sensor model based on the combination of PSO and LSSVM was established to estimate the parameters. To overcome the time consuming and blindness in parameter selection of traditional LSSVM model, PSO algorithm was employed to optimize the parameters of LSSVM soft sensor model. The model had a fast learning speed, high precision and well generalization ability. The results obtained from the real data of a gold mine in Xinjiang for simulation showed that predicted values of PSO-LSSVM model fitted measured values well, suggesting that the model established in our study is useful to measure the key parameters for biological oxidation pretreatment process of oxidation-reduction potential.