Optimal System Research Articles

Application of machine learning for environmentally friendly advancement: exploring biomass-derived materials in wastewater treatment and agricultural sector - a review.

There are several uses for biomass-derived materials (BDMs) in the irrigation and farming industries. To solve problems with material, process, and supply chain design, BDM systems have started to use machine learning (ML), a new technique approach. This study examined articles published since 2015 to understand better the current status, future possibilities, and capabilities of ML in supporting environmentally friendly development and BDM applications. Previous ML applications were classified into three categories according to their objectives: material and process design, performance prediction and sustainability evaluation. ML helps optimize BDMs systems, predict material properties and performance, reverse engineering, and solve data difficulties in sustainability evaluations. Ensemble models and cutting-edge Neural Networks operate satisfactorily on these datasets and are easily generalized. Ensemble and neural network models have poor interpretability, and there have not been any studies in sustainability assessment that consider geo-temporal dynamics; thus, building ML methods for BDM systems is currently not practical. Future ML research for BDM systems should follow a workflow. Investigating the potential uses of ML in BDM system optimization, evaluation and sustainable development requires further investigation.

Enhanced anaerobic digestion model no.1 for high solids fermentation: Integrating homoacetogenesis and chain elongation.

The production of volatile fatty acids (VFA) through high-solids anaerobic fermentation of organic waste offers a promising route for resource recovery. This study used a batch-mode anaerobic leach bed reactor (LBR) with leachate circulation to ferment the organic fraction of municipal solid waste, producing high concentrations of butyric acid, along with notable amounts of lactic and caproic acids. These results provide valuable insights and underscore the need for process optimization within conventional fermentation systems. To better model the LBR's complex dynamics, the Anaerobic Digestion Model No.1 (ADM1) was modified and extended to account for slow hydrolysis in dry fermentation conditions, thermodynamic constraints imposed by Gibbs Free Energy and hydrogen partial pressures, as well as lactic acid production and chain elongation pathways including homoacetogenesis and caproic acid formation. These enhancements provided deeper insights into high-solids anaerobic fermentation, advancing strategies for improved process control and system optimization.

Research on fluctuation attenuation and optimization of passive residual heat removal system based on spring vibrator

Research on fluctuation attenuation and optimization of passive residual heat removal system based on spring vibrator

Optimization and operational strategy analysis of steam-driven CAES systems coupled with thermal power for energy generation

Optimization and operational strategy analysis of steam-driven CAES systems coupled with thermal power for energy generation

Machining parameter optimization for a batch milling system using multi-task deep reinforcement learning

The integrated multi-objective optimization of machining parameters for improved machining quality and efficiency is important in batch milling systems. Due to the change of the batch milling system state, the continuous use of the same machining parameters may lead to degradation in quality and efficiency for workpieces in batches. Machining parameter optimization is usually determined by manual experience or trial-and-error methods, making it difficult to achieve a synergistic consideration of both quality and efficiency. To address this issue, a novel multi-task deep reinforcement learning method for machining parameter optimization in a batch machining system is proposed. Firstly, a reliable parallel joint estimation model of multiple machining quality and efficiency indicators is established using a multi-task time series estimation method, which can learn the correlation of these indicators to improve estimation accuracy. Then, the parameter optimization problem is formalized as a Markov decision process supported by a reinforcement learning virtual environment and an agent. The reinforcement learning virtual environment with the joint estimation model is constructed to improve the accuracy of optimized machining parameters for the collaborative optimization of quality and efficiency indicators. Within the virtual environment, time series sequential state, sequential action, multi-objective reward function, and constraint conditions adapted to the joint estimation model are defined to repeatedly evaluate different machining parameters. The agent with a multi-head attention and a dynamic weight adjustment mechanism is designed to improve the stability of the optimization process. Finally, experiments on a real machining dataset of thin-walled parts show that compared with the traditional deep reinforcement learning algorithm, the optimization effect of the proposed framework is improved by 9%-12%, and the standard deviation is decreased by 9% -18%.

Performance prediction and operating conditions optimization for aerobic fermentation heat recovery system based on machine learning

Performance prediction and operating conditions optimization for aerobic fermentation heat recovery system based on machine learning

Entropy optimization of stagnant blood flow systems with tetra-hybrid nano additives under viscous dissipation, joule heating and thermal radiation effects

Entropy optimization of stagnant blood flow systems with tetra-hybrid nano additives under viscous dissipation, joule heating and thermal radiation effects

Optimization and economic analysis of hybrid renewable energy system

Optimization and economic analysis of hybrid renewable energy system

Dimensionality reduction enabled efficient kinetic parameters estimation and process optimization during continuous flow synthesis of ibuprofen

Complex reaction networks with multiple components and unknown kinetic parameters are commonly encountered in the process of reaction kinetic and reactor modeling. In this study, a dimensionality reduction strategy is used to effectively solve complex reaction kinetics-reactor coupled model. Ten unknown kinetic parameters from the synthesis of ibuprofen are identified based on genetic algorithm, which employs the elite and adaptation strategies. A convergence region is determined to compromise the accuracy and stability of the solutions. The statistical analyses are performed to clarify the reliability of the estimated parameters, which are also validated by the experimental data. Dynamic analyses show that only 1.2 times of the average residence time is required to make the flow-reaction process reach steady state. The sensitivity analyses help bridge the gap between the yield of ibuprofen and operating conditions. The proposed method can provide general guidelines for kinetic parameters estimation and optimization in similar systems.

An advanced physics-informed neural operator for comprehensive design optimization of highly-nonlinear systems: An aerospace composites processing case study

An advanced physics-informed neural operator for comprehensive design optimization of highly-nonlinear systems: An aerospace composites processing case study

Design and optimization for photovoltaic heat pump system integrating thermal energy storage and battery energy storage

Design and optimization for photovoltaic heat pump system integrating thermal energy storage and battery energy storage

DCARES: deep convolutional neural network with neural-based optimization for image-based product recommender system

DCARES: deep convolutional neural network with neural-based optimization for image-based product recommender system

Process Optimization And Life Cycle Assessment In a 10MWth food waste chemical looping gasification system for hydrogen production

Process Optimization And Life Cycle Assessment In a 10MWth food waste chemical looping gasification system for hydrogen production

MILP optimization of the multi-heat pump waste heat recovery system integrated with full-free cooling data center through lake water

MILP optimization of the multi-heat pump waste heat recovery system integrated with full-free cooling data center through lake water

Niosome-embedded in situ gels for root canal irrigation: preparation and optimization of a composite system for chlorhexidine delivery

Niosomes could increase the efficacy of the irrigants by providing a controlled drug release. Incorporating niosomes into an in situ gel matrix maximizes the drug retention time in the root canal system. The focus of this study was the fabrication and characterization of a niosomal in situ gel system for delivering chlorhexidine to root canals. For this aim, chlorhexidine-loaded niosomes were optimized by evaluating the impacts of surfactant type, surfactant-to-cholesterol ratio, lipid-to-drug weight ratio, and ethanol concentration on particle size and entrapment efficiency (EE) using an experimental design. The in situ gels were also optimized with the aid of an experimental design by identifying the effects of chitosan and β-glycerophosphate concentrations as well as the solution stirring time on the gelation time and gelation temperature. The optimum niosomal nanoformulation showed an average particle size of 115 nm, EE% of ∼80%, and PDI of 0.1. The optimum in situ gels showed the lowest gelation time and appropriate gelation temperature (60 s and 29 °C, respectively). The in vitro release studies showed that niosomal in situ gels successfully sustained the release of ∼97% of chlorhexidine over 144 hours with Higuchi kinetics. Furthermore, the biological evaluations revealed that the niosomal in situ gels were cytocompatible. The system also exhibited antibacterial activity against Enterococcus faecalis bacteria, Streptococcus mutants, and Aggregatibacter actinomycetemcomitans by respectively showing 18.0, 33.3, and 48.3 mm inhibition zones in the disk diffusion test. Overall, the results indicated that niosome-embedded in situ gels showed promising potential for antimicrobial delivery to root canals.

Innovative optimization of hybrid energy storage systems for electric vehicles: Integrating FBPINN-SAO to enhance performance and efficiency

Innovative optimization of hybrid energy storage systems for electric vehicles: Integrating FBPINN-SAO to enhance performance and efficiency

Performance optimization of photovoltaic thermoelectric systems based on phase change materials

Performance optimization of photovoltaic thermoelectric systems based on phase change materials

How far back shall we peer? Optimal air handling unit control leveraging extensive past observations

Heating, Ventilation, and Air Conditioning (HVAC) systems play a critical role in ensuring occupant comfort in buildings. Traditional Rule-Based Feedback Control (RBFC) systems, while widely deployed for their simplicity, suffer from low adaptability. Recent improvements, such as Model Predictive Control (MPC) methods demand complex mathematical modeling and substantial expert knowledge, creating a high barrier for system design and optimization. Reinforcement Learning (RL) emerges as a promising solution with its adaptability and model-free nature, albeit challenged by sample inefficiency and suboptimal convergence. Given the intrinsic delayed effects from previous actions and prolonged thermal inertia in the HVAC systems, this study introduces an innovative deep RL framework that can leverage historical observations to refine RL agent performance. By incorporating a state-of-the-art (SOTA) Transformer model, we capture the temporal patterns in HVAC data and build a more precise RL training environment. Implemented on high-resolution, real-world HVAC datasets, our framework showed superior performance in both HVAC system modeling and RL control performance. Specifically, compared to the two baseline models—Bidirectional Long Short-Term Memory (Bi-LSTM) and vanilla Transformer, our proposed RL environment model achieved an average of 30.5% and 35.8% prediction accuracy improvement, respectively. Moreover, our optimal past observable RL agent swiftly delivers 35.3% of electricity saving and 54.4% of thermal comfort improvement over traditional RBFC. These results show the effectiveness of the pioneering integration of extensive historical observations for HVAC operation optimization.

Techno-economic dataset for energy market and capacity payment co-optimization in the Dominican Republic's power market.

The electric power industry has an impact on fossil fuel consumption, which must be considered in decarbonization strategies. Energy systems optimization modelling can be applied to evaluate policy scenarios in the power sector to accelerate energy transitions. These modelling tools need data to simulate different scenarios in the power system to clarify the design of energy policies. For this reason, collecting and processing technical and economic data is needed to guarantee quality input for the modelling tools. This article presents a dataset for an optimization model of the generation mix and the energy demand in the power system of the Dominican Republic to determine the capacity value of variable renewable energy (VRE), i.e., wind and solar, that can serve as an incentive for these technologies. While the data corresponds to the Dominican Republic's power system, the method of collecting and processing data can be implemented in other countries. The data collected is an open-access database of the independent system operator, the power sector regulator, and utilities, as well as websites and databases of international organizations.

Advances in Artificial Intelligence and Computational Methods: Enhancing Modeling, Prediction, and Optimization

bstract: This area of artificial intelligence and computational methods has witnessed tremendous development, especially with the solution of highly complex problems across scientific disciplines. This review brings together the latest advancements in the integration of AI with traditional computational techniques, focusing on their applications in numerical simulations, system optimization, and predictive modeling. Key contributions include AI-augmented finite difference methods for solving partial differential equations, advancements in material and energy systems optimization, and innovative approaches to highperformance computing. Future directions emphasize scalability, interdisciplinary applications, and the integration of emerging technologies such as quantum computing and reconfigurable hardware.