An Innovative NOx Emissions Prediction Model Based on Random Forest Feature Selection and Evolutionary Reformer

Processes, Journal Year: 2025, Volume and Issue: 13(1), P. 107 - 107

Published: Jan. 3, 2025

Developing more precise NOx emission prediction models is pivotal for effectively controlling emissions from gas turbines. In this paper, a Reformer combined with random forest (RF) feature selection and the chaos game optimization (CGO) algorithm to predict in Firstly, RF evaluates importance of data features reduces dimensionality multidimensional improve predictive performance model. Secondly, model extracts inherent pattern different explores intrinsic connection between turbine variables establish accurate Thirdly, CGO parameter-free meta-heuristic used find best parameters The was improved using Chebyshev Chaos Mapping initial population quality algorithm. To evaluate efficiency proposed model, dataset turbines north-western Turkey studied, results obtained are compared seven benchmark models. final paper show that can select appropriate input variables, extract links build At same time, ICGO optimize effectively.

Language: Английский

Algorithm and Methods for Analyzing Power Consumption Behavior of Industrial Enterprises Considering Process Characteristics

Algorithms, Journal Year: 2025, Volume and Issue: 18(1), P. 49 - 49

Published: Jan. 16, 2025

Power consumption management is crucial to maintaining the reliable operation of power grids, especially in context decarbonization electric industry. Managing industrial enterprises by personnel proved ineffective, which required development and implementation automatic energy systems. Optimization behavior requires comprehensive information on parameters technological processes an enterprise. The paper explores specific features non-stationary conditions output production assesses potential for under these conditions. analysis modes was carried out based consideration random factors determined both internal external circumstances, subject fulfillment plan. This made it possible increase efficiency mechanical engineering taking into account uncertainty seasonal fluctuations 15–20%, study presents a justification utilizing theory level-crossings enhance reliability input information. need analyze probabilistic structure functions proven. justified because becomes fulfill plan with productivity and, accordingly, consumption, exceeds nominal values more than 5%. In addition, emission characteristics are clear, easy measure, allow transition from analog digital presentation. algorithm methods developed patterns can be used develop

Language: Английский

Evolving Electricity Demand Modelling in Microgrids Using a Kolmogorov-Arnold Network

Informatica, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 22

Published: Jan. 1, 2025

Electricity demand estimation is vital for the optimal design and operation of microgrids, especially in isolated, unelectrified, or partially electrified areas where patterns evolve with electricity adoption. This study proposes a causal model that explicitly considers electrification process along key factors such as hour, month, weekday/weekend distinction, temperature, humidity, effectively capturing both temporal environmental patterns. To capture process, “Degree Adoption” factor has been included, making it distinctive feature this approach. Through variable, accounts evolving growth usage, an essential consideration accurately estimating newly electrifying consumers gain access to integrate new electrical appliances. Another contribution successful application Kolmogorov–Arnold Network (KAN), architecture designed complex nonlinear relationships more than conventional neural networks rely on standard activation functions, ReLU sigmoid. validate effectiveness proposed modelling approaches, comprehensive experiments were conducted using dataset covering 578 days consumption from El Espino, Bolivia. enabled robust comparisons among KAN network architectures, Deep Feedforward Neural (DFNN) Multi-Layer Perceptron (MLP), while also assessing impact incorporating Degree Adoption factor. The empirical results clearly demonstrate KAN, combined Adoption, achieved superior performance, obtaining error 0.042, compared DFNN (0.049) MLP (0.09). Additionally, integrating significantly enhanced by reducing approximately 10%. These findings adoption dynamics confirm KAN’s relevance estimation, highlighting its potential support microgrid operation.

Language: Английский