Search

Designing a sustainable Closed-Loop Supply Chain (CLSC) network is imperative for the apparel industry, given its escalating adverse effects on economic, environmental, and social dimensions. In this study, a novel tri-objective location-allocation optimization model is specifically developed for designing a sustainable apparel CLSC, incorporating the industry's unique facilities. The aim of the model is to simultaneously minimize the costs and negative environmental impacts while maximizing social benefits under demands and returns uncertainty. A notable research contribution lies in addressing the unique challenges of treating different types of returns, including commercial, End Of Use (EOU) and End Of Life (EOL) returns due to their uncertain quality and quantity. Additionally, the model optimizes the environmental performance levels of production facilities, a novel aspect in the apparel CLSC research. Moreover, the flexibility of constraints related to the demand fulfilment is considered. To cope with such flexibility and uncertainties, a new hybrid robust possibilistic flexible programming model is developed, by extending the previous methodologies. A core innovation of this solution approach lies in the pioneering utilization of hexagonal fuzzy numbers for uncertain epistemic parameters, making a significant advancement in the field of CLSC. Comparative analysis with the similar studies demonstrates the superiority of the proposed model, incorporating hexagonal fuzzy numbers over the method using triangular fuzzy numbers. Furthermore, AUGMECON method using lexicographic optimization is applied to handle the multi-objective model. The application of the proposed model is shown focusing on Southwestern Ontario in Canada. The results reveal that commercial and EOU returns have a more detrimental impact on economic, environmental, and social sustainability aspects compared to EOL returns. • Designing a novel sustainable closed-loop supply chain for the apparel industry. • Developing a new robust possibilistic flexible model with hexagonal fuzzy numbers. • Optimizing environmental performance levels of the production facilities. • Applying an augmented ε -constraint method using lexicography optimization. • Comparative analysis shows the superiority of this model over existing studies. [ABSTRACT FROM AUTHOR]

Assessing the energy performance of existing residential buildings (ERB) has been identified as key to improving building energy efficiency and reducing associated greenhouse gas emissions in Canada. However, identifying optimal retrofit packages requires a significant amount of knowledge of building energy modelling, and it is a time-consuming and laborious process. This paper proposed a data-driven framework that combines machine learning, multi-objective optimization, and multi-criteria decision-making techniques to evaluate the energy performance of ERB and thereby formulate optimal retrofit plans. First, an artificial neural network (ANN) was developed to predict the energy performance of a wide range of retrofit packages. A genetic algorithm was employed to determine the best structure and hyperparameters of the ANN model. Then, the energy consumption results were integrated with environmental and economic impact data to evaluate the environmental and economic performance of retrofit packages and thereby identify Pareto optimal solutions. Finally, a multi-criteria decision-making method was used to select the best retrofit packages among the optimal solutions. The proposed framework was validated using data on a typical residential building in British Columbia, Canada. The results indicated that this framework could effectively predict building energy performance and help decision-makers to make an optimal decision when choosing retrofit packages. [ABSTRACT FROM AUTHOR]

• A model was created to examine the reliability of maintenance budget allocation. • The model was applied to network-level pavement maintenance in Canada. • The impacts of algorithm selection and parameter tuning were studied. • The significance of pavement clustering in increasing reliability was highlighted. • The importance of incorporating actual pavement improvement curves was clarified. The purpose of this paper is to increase the reliability of the network-level pavement maintenance budget allocation by reducing uncertainties of algorithm selection and parameter tuning. In this paper, reliability is defined as the ability of a network-level pavement maintenance plan to improve the condition of a pavement network within a certain budget. In order to quantify reliability, the reliability index is defined as the ratio between the post-maintenance network condition and the net maintenance cost. With this purpose in mind, a two-objective optimization model was developed. To test its applicability, the model was applied to a pavement network in Canada. The model was solved using the Non-Dominated Sorting Genetic Algorithm II and the differential evolution algorithms. Finally, the reliability indices of algorithms and termination criteria were computed. The results indicated that the differential evolution algorithm recommended less frequent but more intense interventions that made the solutions expensive and less reliable. This paper contributed to the network-level pavement maintenance body of knowledge by (1) developing a multi-objective optimization model to reduce uncertainties of parameter tuning and algorithm selection; (2) increasing the reliability of budget allocation; (3) showcasing the significance of pavement clustering in increasing reliability; and (4) developing and incorporating actual pavement improvement curves. [Display omitted] [ABSTRACT FROM AUTHOR]

Marine oil spill response is a time sensitive and complex task, in which the management of oily wastewater generated from response operations could be a bottleneck limiting the response capacity and efficiency. This study developed a multi-agent decision support system to effectively coordinate mechanical containment and recovery (MCR) of spilt oil and oily wastewater management (OWM) operations. The system aims to minimize the overall response time, cost, and the volume of weathered oil by applying evolutionary optimization, oil weathering process, and response operational agents. The multi-agent system was used to manage an incident through a hypothetical case study in Canada. The system enables the scheduling of available response assets considering all complex operational details of MCR and OWM, such as available oily wastewater storage and transportation capacities and the competitive skimming process of various response vessels. Implementing the evolutionary multi-objective optimization led to a considerable reduction in response time (about 13.6% or 67 hr), cost (about 1.4% or CA$24,800), and volume of weathered oil (about 9.2% or 19 m3) compared to the shortest distance approach. The developed multi-agent system can facilitate decision-making in complex marine oil spill response tasks for maximizing response efficiency. [Display omitted] • A decision support system is developed for effective marine oil spill management. • Oil spill response and oily waste management operations were optimized together. • Overall response time and cost, as well as volume of weathered oil were minimized. • The multi-agent system was tested on a comprehensive case study in Western Canada. • Multi-objective optimization approaches outperformed shortest distance model. [ABSTRACT FROM AUTHOR]

Highlights • A hybrid model was developed to simulate spatiotemporal changes in open wetlands. • Logistic regression, Markov chain methods and a multi-objective land allocation model were used to develop a hybrid geosimulation model. • Kappa standard, location and allocation measurements, figure of merit as well as landscape metrics indices were used to validate the model. • Increases in open wetlands from 1985 to 2005 were captured using remotely sensed images and trends simulated into future. • Previsions of changes in open wetlands were calculated from 2015 to 2055. Abstract Among the most productive ecosystems around the world, wetlands support a wide range of biodiversity such as waterfowl, fish, amphibians, plants and many other species. They also provide ecosystem services that play important roles in relation to nutrient cycling, climate mitigation and adaptation, as well as food security. In this research, we examined and projected the spatiotemporal trends of change in open wetlands by coupling logistic regression, Markov chain methods and a multi-objective land allocation model into a hybrid geosimulation model. To study the changes in open wetlands we used multi-temporal land cover information interpreted from LANDSAT images (1985, 1995, and 2005). We predicted future spatial distributions of open wetlands in the administrative region of Abitibi-Témiscamingue, Quebec, Canada for 2015, 2025, 2035, 2045 and 2055. A comparison and assessment of the model's outcomes were performed using map-comparison techniques as well as landscape metrics. Change analysis between 1985 and 2005 showed an increase of about 63% in open wetlands, while simulation results indicated that this tendency would persist into 2055 with a continuous augmentation of open wetlands in the region. The spatial distribution of predicted trends in open wetlands could provide support to local biodiversity assessments, management and conservation planning of the open wetlands in Quebec, Canada. [ABSTRACT FROM AUTHOR]

In Canada, most of the forests are publicly owned and forest products companies depend on timber licenses issued by the provincial governments for their wood supplies. According to the Sustainable Forest Development Act effective in the province of Quebec since April 2013, the government is responsible for harvest area selection and timber allocation to companies. This is a complex tactical planning decision with important impacts on downstream economic activities. Moreover, to avoid high grading of forest resources and to determine a sustainable tactical plan that ensures a stable level of availability, quality, and cost of supply over several years, it is necessary to take these criteria into consideration simultaneously during the planning process. We propose a mixed-integer nonlinear goal-programming formulation while employing Nadir theory as a reliable scaling technique to model this multi-objective planning problem. The model is solved by a linearization approach for a real case in the province of Quebec. The proposed solution method enables us to obtain good-quality solutions for relatively large cases. Results show that the proposed model outperforms conventional cost-minimization planning strategy by ensuring a more balanced use of wood supply and costs for all stakeholders over a longer period. [ABSTRACT FROM AUTHOR]

[Display omitted] • A novel system for production and storage of H 2 with net-zero carbon emissions is developed. • High-temperature fuel cells and biogas upgrading unit are efficiently integrated. • Waste heat of the fuel cells is recovered in the Cu-Cl unit for hydrogen production. • Integrated process can generate 108 kmol/h liquid hydrogen and 18.88 MW power. • A hybrid method of the GA and artificial intelligence tools is applied for optimization. Global energy consumption has been exponentially increasing, leading to the depletion of conventional energy sources and a considerable increase in greenhouse gas emissions. The exploitation of sustainable energy sources and the development of innovative methods for mitigation of CO 2 emissions is necessary. Hydrogen (H 2) as a versatile and green fuel can be produced and stored in liquid form using sustainable energy sources through innovative methods. In this paper, a novel optimal hybrid structure is proposed for hydrogen production and storage with net-zero CO 2 emissions. A high-temperature fuel cell is utilized to reduce CO 2 emissions and supply the heat and power needed to produce and liquefy hydrogen. The hybrid configuration employs an electro-thermochemical unit for hydrogen production, molten carbonate fuel cells, a hydrogen liquefaction process, and a biogas upgrading by water scrubbing. A robust combination of meta-heuristic algorithms and artificial intelligence is developed to optimize the investment return period and energy/exergy efficiencies. The fuzzy Bellman-Zadeh, LINMAP, and TOPSIS techniques are also used to make decisions in multi-objective optimization. This innovative configuration generates 108 kmol/h liquid hydrogen, 18.88 MW power, 54 kmol/h oxygen, and 3258 kmol/h hot water. Pinch, sensitivity, exergy, and economic assessments are implemented to evaluate the performance of the hybrid structure. The thermal and exergy efficiencies of the proposed configuration are obtained to be 78.21 % and 64.83 %, respectively. The greatest portions of destructed exergy are resulted from the fuel cells-gas turbine hybrid system (63.63 %), electro-thermochemical unit (25.96 %), and biogas upgrading technology (6.23 %). The returns period on investment, the prime price of electricity, and the net benefit are computed as 4.854 years, 0.0420 US$/kWh, and 15.73 million US$/years, respectively, based on the energy potentials of Newfoundland and Labrador, Canada. [ABSTRACT FROM AUTHOR]

The water distribution system hydraulic model for an Ontario, Canada town has been calibrated by engineers familiar with the system. Their calibration procedure was mainly an expert-based approach using judgment and trial-and-error and did not rely on optimization. The purpose of this study is to resolve the corresponding calibration problem with optimization tools and compare the calibration solutions in terms of quality (closeness to measured data) and calibration parameter values. The calibration problem is posed as a multi-objective optimization problem and solved with the PA-DDS algorithm described in [1]. The precise calibration objectives are roughly matched to the manual calibration objectives specified by the engineers who calibrated the model. Multi-objective optimization results are compared with the current solution to determine if the current solution is non-dominated. [ABSTRACT FROM AUTHOR]

Patients' waiting time is a major issue in the Canadian healthcare system. The planning for resource allocation impacts patients' waiting time in medicare settings. This research focuses on the reduction of patients' waiting time by providing better planning for radiological resource allocation and efficient workload distribution. Resource allocation planning is directly related to the number of patient-arrival and it is hard to predict such uncertain parameters in the future time frame. The number of patient-arrival also varies across different modalities and different timeframes which makes the patient-arrival prediction challenging. In this research, a new three-phase solution framework is proposed where a new multi-target machine learning technique is integrated with an optimization model. In the first phase, a novel Ensemble of Pruned Regressor Chain (EPRC) model is developed and trained offline to predict uncertain parameters, such as patients' arrival. The proposed model is then compared with two popular multi-target prediction methods to evaluate the model's accuracy. In the second phase, the trained model is deployed in the real-time environment to forecast patients' arrival, miss Turn Around Time (miss-TAT) rate, and probable workload count. The forecasted data is used in phase three where a new multi-objective optimization model is developed to determine workload allocation. The Weighted-sum method is used to get efficient solutions. The proposed model is deployed in a Canadian healthcare company and evaluated using real-time healthcare data. It is observed in terms of accuracy, the proposed EPRC model performed 10.81 % better compared to the other multi-target models considered in this study. It is also noticed that the forecasting results have a direct impact on the workload distribution, where the proposed model decreases the total workload by approximately 25 %. Besides, the result shows the efficient workload distribution provided by the proposed framework can reduce the average patients' waiting time by 8.17 %., (Copyright © 2022 Elsevier B.V. All rights reserved.)

• Proposed dimensionality reduction semi-supervised Variational Autoencoders (VAEs). • VAEs can generate scenarios for all building renovation considering TEC and LCC. • The applicability of VAEs for building energy renovation has been proven. • Significant computational time improvement is achieved with acceptable accuracy. • Overall good agreement between SBMO and VAE has been observed. Buildings consume a huge amount of energy, resulting in a considerable impact on the environment. In Canada, almost 70% of the total energy used by the commercial and institutional sectors was consumed by Heating, Ventilation and Air-Conditioning (HVAC) and lighting systems, which makes them the main targets of energy performance optimization methods. Furthermore, based on a governmental report, 40% of Quebec university buildings are in poor or very poor shape regarding structure and materials, and require immediate renovation. Therefore, it is of utmost importance to reduce energy consumption, and this can be accomplished by improving the design of new buildings or by renovating existing ones. Moreover, Simulation-Based Multi-Objective Optimization (SBMO) models can be used for optimizing and assessing different renovation scenarios considering Total Energy Consumption (TEC) and Life Cycle Cost (LCC). The time-consuming nature of SBMO has triggered the development of simplified and surrogate models within the design process. This study proposes a generative deep learning building energy model using Variational Autoencoders (VAEs), which could potentially overcome the current limitations. The proposed VAEs extract deep features from a whole building renovation dataset and generate renovation scenarios considering TEC and LCC of the existing institutional buildings. The proposed model also has the generalization ability due to its potential to reuse the dataset from a specific case in similar situations. The performance of the developed model has been demonstrated using a simulated renovation dataset to prove its potential. The results show that using generative VAEs is acceptable considering computational time and accuracy. [ABSTRACT FROM AUTHOR]

• Flow partitioning based model-wrapper significantly improves the simulation results. • Model wrapper helps identify redundant models for multi-modelling. • Signature-based multi-criteria auto-calibration helps parameter identifiability. Multi-modelling aims to make use of the strengths of single hydrologic models to improve the accuracy of simulating the watershed system behavior. Considering hydrological signatures such as the flow duration curve segmentation in the calibration of each hydrologic model leads to a better parameter identifiability. In this study, a novel weighted average model-wrapper based on flow duration curve segmentation is introduced to aggregate the calibrated models into a multi-model. The proposed framework is applied to develop a model-wrapper of the Upper Assiniboine River Basin for flood forecasting upstream of the Shellmouth reservoir in the Prairie region of Canada. The HEC-HMS, HBV-EC, HSPF, and WATFLOOD hydrologic models that are being used at the Hydrologic Forecast Centre of Manitoba Infrastructure for operational inflow forecasting are calibrated using signature-based multi-objective optimization. These models have significantly different structural complexities. The calibration of each of these models is set up as three simulation-optimization problems with different objective functions to balance the model capability in simulating multiple important hydrological signatures. Results show that the model-wrapper outperforms each of the single calibrated models that are of operational use at Manitoba Infrastructure, e.g. NSE improved from 0.44 for the best individual model to 0.76 for the model-wrapper in the calibration period. Moreover, the weights associated with each hydrologic model component indicate the contribution rate of the individual models to the model-wrapper in high-flow, mid-flow, and low-flow portions of streamflow time series. Quantifying the contribution of each model component provides a deeper insight into model selection strategy, especially when a component has minimal or no contribution, e.g. HEC-HMS and HBV-EC in this paper, to the model-wrapper performance in all ranges of streamflow simulation compared to other model components. [ABSTRACT FROM AUTHOR]