With the industrial data, this model could forecast the nitrogen content and the Ar blowing time required to control the nitrogen level of the stainless steel in AOD refining process.
模型可利用生产现场的实际操作数据预测钢中氮含量，并可预测冶炼过程中控制钢中氮含量所需要的吹氩时间。
Simulation results with factual industrial data demonstrate that the two methods are both fast in computation and accurate in prediction, so they are suitable to practical application.
通过实际工业数据仿真表明，这两种方法均具有计算速度快、模型精度高的特点，适合实际工程应用的需求。
The developed model got high accuracy and good trend tracking performance on the real industrial data.
所构建的粘度软测量模型预报精度较高，趋势跟踪性能良好。
MATLAB is applied to program and the industrial data of refrigerating system are regressed and predicted with satisfactory results.
应用编制的程序对制冷系统的生产数据进行回归、预测，结果令人满意。
The deactivation kinetics equations of ethylene oxide synthesis silver catalyst were obtained from the calculation of real industrial data.
根据工业实际生产数据反算得到能够反映催化剂失活特性的银催化剂失活动力学方程。
According to the high dimensions and uncertainty of process industrial data, the fuzzy set and rough set of granularity data mining are studied for process data.
针对流程工业数据的高维数、不确定的特点，研究适合处理流程数据的模糊集、粗糙集的粒度数据挖掘理论和方法。
The process was analyzed by the comparison between the simulated results and the industrial data and the optimum operation parameters for the practical production were provided.
把所得模拟结果和实际生产相比较，对工艺流程进行分析，获得了对脂肪醇实际生产具有指导意义的优化操作参数。
The reactor of ethylene oxide prepared by ethylene oxidation was simulated by one-dimension and two-dimension models. The simulation results were coincident with the industrial data.
用一维和二维数学模型模拟了乙烯氧化制环氧乙烷反应器，模拟结果与工业实际生产的数据吻合较好。
The experimental results on the real industrial data demonstrate that the model based on SVM achieves good performance and has less prediction errors than those of BPNN and RBFNN models.
在实际工业数据上进行的实验结果表明，支持向量机模型对丙酮纯度具有良好的预测效果，性能优于反向传播神经网络和径向基网络模型。
The experimental results on the real industrial data demonstrate that the model based on SVM achieves good performance and has less prediction errors than those of BPNN and RBFNN models.
在实际工业数据上进行的实验结果表明，支持向量机模型对丙酮纯度具有良好的预测效果，性能优于反向传播神经网络和径向基网络模型。
应用推荐