Development of an efficient cement production monitoring system based on the improved random forest algorithm

Abstract

Strengthening production plants and process control functions contribute to a global improvement of manufacturing systems because of their cross-functional characteristics in the industry. Companies established various innovative and operational strategies and there is increasing competitiveness among them and increase companies' value. Machine Learning (ML) techniques have become an intelligent enticing option to address industrial issues in the current manufacturing sector since the emergence of Industry 4.0, and the extensive integration of paradigms such as big data, cloud computing, high computational power, and enormous storage capacity. Implementing a system that can identify faults early to avoid critical situations in the line production and environment is crucial. Therefore, one of the powerful machine learning algorithms is Random Forest (RF). The ensemble learning algorithm is performed to fault diagnosis and SCADA real-time data classi cation and predicting the state of the line production. Random Forests proved to be a better classi er with a 95% accuracy. Comparing to the SVM model, the accuracy is 94.18%, however, the K-NN model accuracy is about 93.83%, an accuracy of 80.25% is achieved using the logistic regression model, nally, about 83.73% is obtained by the decision tree model. The excellent experimental results achieved on the Random Forest model showed the merits of this implementation in the production performance, ensuring predictive maintenance, and avoid wasting energy.

Forecasting material quantity using machine learning and times series techniques

“…Information gain is the reduction in entropy achieved by a split and guides the tree construction. Random Forest is an ensemble learning method based on Decision Trees [28]. It constructs a multitude of Decision Trees during training and outputs the mode of the classes (classification) or the mean prediction (regression) of the individual trees.…”

Improving the intelligent algorithm in the intelligent monitoring model of human settlement environment under fuzzy comprehensive evaluation (FCE)

“…The development of agricultural products with local characteristics is conducive to extending the industrial chain, establishing product processing zones and rural service areas, making its economic development more rapid. At the same time, it also achieves the original intention of reducing environmental pollution and realizing green products 8 . In order to realize the beauty of China's countryside, the happiness of farmers, industrial linkage, agriculture as the root, ecology as the foundation, and the construction of three modern and simultaneous beautiful villages, the concept of harmonious urban and rural development and simultaneous and coordinated economic and social development is realized.…”

Construction of an Integrated Framework for Complex Product Design Manufacturing and Service Based on Reliability Data

“…Enhancing production plant and manufacturing process control helps improve the overall performance of the complex product manufacturing system. Based on machine-learning, IIoT, high-precision sensors and other technologies and tools, the solution of fault diagnosis, real-time data classification and prediction of machine operating status in the intelligent manufacturing process of complex products has become a priority for the production performance, predictive maintenance and avoidance of energy waste in intelligent manufacturing systems of complex products [57]. Based on reliability-data-driven methods, extracting and processing the failure characteristic signals related to machine damage, degradation and methods to identify degradation patterns related to technical conditions are becoming one of the main directions in the research of reliability optimization of manufacturing processes based on machine states [58].…”