论文部分内容阅读
提出了一种基于核主成分分析(KPCA)-高斯混合模型(GMM)的球磨机状态实时监测与评估新方法。通过选取不同工况下的球磨机过程参数,基于KPCA提取反映设备运行状态的特征量,基于GMM建立表征不同工况的球磨机状态模型,并引入高斯混模型概率距离,计算当前状态与正常工况的相似度,作为状态指标(SI)实时监控球磨机的运行状态。通过对某电厂球磨机实际运行过程的监控与评估,表明所提方法的有效性和实用性。
A new method for real-time monitoring and evaluation of ball mill condition based on kernel principal component analysis (KPCA) -Gaussian mixture model (GMM) is proposed. By selecting the parameters of ball mill under different operating conditions and extracting the characteristic quantities reflecting the operation state of equipment based on KPCA, the state model of ball mill characterizing different operating conditions is established based on GMM, and the probability distance of Gaussian mixture model is introduced to calculate the current state and normal operating conditions Similarity, as a status indicator (SI) to monitor the running status of the ball mill in real time. Through the monitoring and evaluation of the actual running process of a ball mill in a power plant, the effectiveness and practicability of the proposed method are demonstrated.