基于IQPSO优化ELM的熟料质量指标软测量研究

水泥熟料游离氧化钙(f Ca O)含量是水泥生产过程的重要质量指标。针对难以建立其精确的数学模型和难以实时在线测量的问题,首先采用序列二次规划方法增强量子粒子群算法的局部搜索能力,提出了一种局部区域可调的改进量子粒子群优化(IQPSO)算法,并采用提出的IQPSO算法优化超限学习机(ELM)的输入层权值和隐层阈值参数,在优化过程中同时兼顾均方根误差和隐层输出矩阵条件数最小的原则,建立了基于IQPSO优化ELM的水泥熟料f Ca O软测量模型,仿真验证结果表明,IQPSO算法具有较高的搜索精度以及较快的收敛速度,建立的软测量模型精度高、泛化能力强。最后基于该模型,通过软件编程的方法给出了水泥熟料质量指标软测量仪表,实现了f Ca O含量的在线软测量。

Soft sensor for cement clinker quality indicator based on IQPSO optimize ELM

The content of free calcium oxide (fCaO) in clinker is an important quality indicator of the cement production process. Because of the difficulty in both real time measurement and establishing precise mathematical model of the fCaO content, building the cement clinker fCaO soft measurement model is particularly important. The Improved Quantum Particle Swarm Optimization (IQPSO) algorithm, whose local search area is modified with the number of iterations, is presented based on using the sequential quadratic programming algorithm to enhance the local search ability. Because the traditional extreme learning machine (ELM) may require high number of hidden neurons and lead to ill condition problem due to the random determination of the input weights and hidden biases, the IQPSO algorithm is used to optimize the ELM parameters. The optimization process takes not only the root mean squared error on validation set but also the condition number of the hidden layer output matrix in to consideration. Finally, the cement clinker fCaO soft sensor model is established based on the IQPSO ELM method. Simulation results indicate that the IQPSO algorithm has better performance than comparing algorithm, and the soft sensor modeling method improves the precision and generalization ability of the cement clinker fCaO model. Online measurement of the content of fCaO is realized by the soft sensor instrument, which is based on the IQPSO ELM soft sensor model.