Power plant condition monitoring by means of coal powder granulometry classification. (July 2018)

• Record Type: Journal Article
• Authors: Rossetti, Damiano; Squartini, Stefano; Collura, Stefano; Zhang, Yu
• Is Part Of: Measurement. Volume 123(2018)
• Page Start: 39
• Page End: 47
• Publication Date: 2018-07
• Subjects: PSD Particle Size Distribution -- AE Acoustic Emission -- SVM Support Vector Machine -- ANN Artificial Neural Network -- ELM Extreme Learning Machine -- FP False Positive -- WP Wavelet Packet -- CV Cross Validation -- G-PSD Good PSD -- P-PSD Poor PSD -- DTT Decision Threshold Technique -- ROC Receive Operating Curve -- DET Detection Error Trade-off -- TPR True Positive Rate -- FPR False Positive Rate -- FNR False Negative Rate -- ACC Accuracy -- SENS Sensitivity -- TP True Positive -- TN True Negative -- FN False Negative -- STD Original Classifier; Condition monitoring -- Particle size distribution -- Classification -- Machine learning; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2018.03.028
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: A condition monitoring approach based on particle size classification is proposed. A non-invasive technique is used to monitor the particle size inside the power plant duct. Both binary and multiclass classification can be employed for a monitoring purpose. A limited amount of training samples can be used to train the models. The amount of the false positive can be effectively reduced. Abstract: In this work, a condition monitoring approach suitable for coal fired power plant is proposed. This approach is based on classification techniques and it is applied for the monitoring of the Particle Size Distribution (PSD) of coal powder. For coal fired power plant, the PSD of coal can affect the combustion performance, therefore it is a meaningful parameter of the operating condition of the plant. Three tests have been carried out aimed to study the effect of the class numbers, the dataset size, and the reduction of the number of false positives on the effectiveness of the approach. For each designed test, three standard classification algorithms, i.e. Artificial Neural Network, Extreme Learning Machine and Support Vector Machine, have been employed and compared. Experimental data taken from 13 measuring point on 13 burners of two different industrial power plants have been used. Obtained results showed that, using two classes give the most accurate results, using only the 90% of the available data can still provide comparable classification results, and the level of false positive can be effectively reduced.