Multi-objective optimization of a time-delay compensated ventilation control system in a subway facility – A harmony search strategy

Loy-Benitez, Jorge; Li, Qian; Nam, KiJeon; Nguyen, Hai-Tra; Kim, Minjeong; Park, DuckShin

doi:10.1016/j.buildenv.2020.107543

Cited by 16 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of metaheuristic optimization algorithms to structural optimization is an active area of research. Among a large number of metaheuristic algorithms, the harmony search (HS) algorithm is one of the most widely used and established techniques, and applied to numerous areas such as structural design [ 23 ], water network design [ 24 ], flood model calibration [ 25 ], economic load dispatch [ 26 ], concrete mix proportion design [ 27 ], chaotic systems [ 28 ], timetabling [ 29 ], weapon target assignment [ 30 ], stock price prediction [ 31 ], mobile network security [ 32 ], COVID-19 detection from CT scans [ 33 ], and subway ventilation [ 34 ].…”

Section: Methods Of Optimization and Predictive Model Developmentmentioning

confidence: 99%

Optimal Dimensioning of Retaining Walls Using Explainable Ensemble Learning Algorithms

et al. 2022

View full text Add to dashboard Cite

This paper develops predictive models for optimal dimensions that minimize the construction cost associated with reinforced concrete retaining walls. Random Forest, Extreme Gradient Boosting (XGBoost), Categorical Gradient Boosting (CatBoost), and Light Gradient Boosting Machine (LightGBM) algorithms were applied to obtain the predictive models. Predictive models were trained using a comprehensive dataset, which was generated using the Harmony Search (HS) algorithm. Each data sample in this database consists of a unique combination of the soil density, friction angle, ultimate bearing pressure, surcharge, the unit cost of concrete, and six different dimensions that describe an optimal retaining wall geometry. The influence of these design features on the optimal dimensioning and their interdependence are explained and visualized using the SHapley Additive exPlanations (SHAP) algorithm. The prediction accuracy of the used ensemble learning methods is evaluated with different metrics of accuracy such as the coefficient of determination, root mean square error, and mean absolute error. Comparing predicted and actual optimal dimensions on a test set showed that an R2 score of 0.99 could be achieved. In terms of computational speed, the LightGBM algorithm was found to be the fastest, with an average execution speed of 6.17 s for the training and testing of the model. On the other hand, the highest accuracy could be achieved by the CatBoost algorithm. The availability of open-source machine learning algorithms and high-quality datasets makes it possible for designers to supplement traditional design procedures with newly developed machine learning techniques. The novel methodology proposed in this paper aims at producing larger datasets, thereby increasing the applicability and accuracy of machine learning algorithms in relation to optimal dimensioning of structures.

show abstract

Section: Methods Of Optimization and Predictive Model Developmentmentioning

confidence: 99%

Optimal Dimensioning of Retaining Walls Using Explainable Ensemble Learning Algorithms

et al. 2022

View full text Add to dashboard Cite

show abstract

“…For buses, studies applied optimisation to design the main powertrain components of electric buses (fuel cell, electric motor, and battery) [120,129], for locating charging facilities [36,39,133], for network design (routes) and frequencies setting [56,57,81,118], fleet composition [81,122], and vehicle scheduling [81,119,123,132]. In rail systems, studies sought to determine station location [144] and to elaborate a dynamic operation plan for a ventilation control system in metro stations [138]. There were two studies that focused on shared mobility, aiming at determining station location [141], routes, scheduling, and fleet sizing of shared systems in suburban contexts [142].…”

Section: B Environmental Variablesmentioning

confidence: 99%

“…Finally, Qiang et al[66] had a similar purpose of Li and Lu[87], but additionally considering walking as a transport mode.Regarding the objective functions, all the studies considered more than one perspective. Loy-Benitez et al[138] considered the passengers' and operators' perspectives by minimising indoor PM 10 concentration and ventilation energy consumption of metro stations. Regarding passengers' and community's interests, Duran et al[56] and Abudayyeh et al[137] aimed at minimising total travel time and CO 2 emissions, while Doorley et al[135] sought to maximise societal benefit through a function of travel and infrastructure costs, health impacts, traffic collisions, and environmental impacts.…”

mentioning

confidence: 99%

A Comprehensive Survey and Future Directions on Optimising Sustainable Urban Mobility

Borchers,

Wittowsky,

Augusto Souza Fernandes

2024

IEEE Access

View full text Add to dashboard Cite

Climate change is currently the biggest environmental threat, being the cities responsible for a significant impact on greenhouse gas emissions. In this sense, the transport sector is among the main causes for both emissions and the depletion of non-renewable resources. Considering this scenario, there is an appeal to build more accessible, smart, sustainable and energy-efficient cities, promoting energy transition in urban systems and increasing the quality of urban life. This review aims to analyse transport and urban mobility studies that employ optimisation techniques to achieve environmental, sustainability or climate change mitigation goals. After an overview regarding modelling aspects of how such goals were addressed, the nature of the objective functions, the perspectives considered, and the network application, such studies were classified into five areas and further detailed. The areas comprise: (i) planning and policy-making; (ii) environmental variables; (iii) demand and traffic management; (iv) technology and energy; and (v) nonspatial measures. In this sense, future research directions should include optimisation models that consider the social aspects of transport and the interests of passengers, operators and the community simultaneously, improve the modelling of environmental impacts to increase its robustness, and deal with large network problems.INDEX TERMS Climate change, Greenhouse gas (GHG) emissions, Optimisation, Passenger urban transport, Sustainable mobility.

show abstract

“…At the same time, the ripening room has a certain area, and the distribution of environmental parameters in different areas is not uniform, so it is not possible to simply analyze a certain area when carrying out control. Due to the area of the storage room and the sensor itself, the system will experience a certain time delay and need to wait for a certain period of time to determine the real environmental state (Loy‐Benitez et al, 2021; Tariq et al, 2020). Therefore, it is crucial to establish a control model with fast, accurate and stable.…”

Section: Introductionmentioning

confidence: 99%

Consumer‐oriented intelligent ripening control system for post‐ripening fruit

Li,

Huang,

et al. 2023

J Food Process Engineering

View full text Add to dashboard Cite

To address the issues commonly encountered in traditional fruit ripening processes, which include reliance on manual experience, low efficiency, single control parameter, and significant fluctuations, a new intelligent fruit ripening control system has been designed. This system is based on a mathematical modeling algorithm, which allows for more effective and precise control over the ripening process. To ensure that the ripe fruits are transported to the fruit processing center in a low ripeness state, the proposed system adopts a strategy of precise control of temperature and ethylene, as well as range control of other environmental parameters. The RSSA‐PID model is used for ethylene and temperature control, which has high smoothness, fast response time, and high stability. Compared with the traditional PID model, the RSSA‐PID model has better dynamic performance and stability. Finally, the proposed system is applied to the ripening process of post‐ripening fruits, and the results show that the system achieves intelligent ripening, precise control, and low power consumption. The temperature and ethylene concentration are controlled within a variation of no more than 0.5%, and the humidity, oxygen, and carbon dioxide are maintained within reasonable thresholds. Overall, this paper provides a promising solution for the ripening process of post‐ripening fruits, which can benefit the fruit industry by improving the efficiency and quality of the supply chain.Practical ApplicationThe ripening chamber environment is a dynamic equilibrium environment with non‐linear characteristics because the fruits in the ripening chamber are constantly exchanging substances and energy with the environment through respiration and transpiration. An intelligent ripening control system (IRCS) for post‐ripening fruits is proposed in this paper (Figure 1). The whole ripening process runs automatically, which significantly reduces the ripening time and saves a lot of post‐processing time. The shorter ripening time combined with the latest intelligent software and hardware means that only as much energy as is actually needed is consumed. If the sales market changes, the fruit can be stored under air conditioning (CA) until the scheduled delivery date without significant further ripening and losses and complaints can be minimized.

show abstract

Multi-objective optimization of a time-delay compensated ventilation control system in a subway facility – A harmony search strategy

Cited by 16 publications

References 37 publications

Optimal Dimensioning of Retaining Walls Using Explainable Ensemble Learning Algorithms

Optimal Dimensioning of Retaining Walls Using Explainable Ensemble Learning Algorithms

A Comprehensive Survey and Future Directions on Optimising Sustainable Urban Mobility

Consumer‐oriented intelligent ripening control system for post‐ripening fruit

Contact Info

Product

Resources

About