Change search
Link to record
Permanent link

Direct link
Alternative names
Publications (10 of 45) Show all publications
Feng, K., Chen, S., Lu, W., Wang, S., Yang, B., Sun, C. & Wang, Y. (2023). Embedding ensemble learning into simulation-based optimisation: a learning-based optimisation approach for construction planning. Engineering Construction and Architectural Management, 30(1), 259-295
Open this publication in new window or tab >>Embedding ensemble learning into simulation-based optimisation: a learning-based optimisation approach for construction planning
Show others...
2023 (English)In: Engineering Construction and Architectural Management, ISSN 0969-9988, E-ISSN 1365-232X, Vol. 30, no 1, p. 259-295Article in journal (Refereed) Published
Abstract [en]

Purpose - Simulation-based optimisation (SO) is a popular optimisation approach for building and civil engineering construction planning. However, in the framework of SO, the simulation is continuously invoked during the optimisation trajectory, which increases the computational loads to levels unrealistic for timely construction decisions. Modification on the optimisation settings such as reducing searching ability is a popular method to address this challenge, but the quality measurement of the obtained optimal decisions, also termed as optimisation quality, is also reduced by this setting. Therefore, this study aims to develop an optimisation approach for construction planning that reduces the high computational loads of SO and provides reliable optimisation quality simultaneously.

Design/methodology/approach - This study proposes the optimisation approach by modifying the SO framework through establishing an embedded connection between simulation and optimisation technologies. This approach reduces the computational loads and ensures the optimisation quality associated with the conventional SO approach by accurately learning the knowledge from construction simulations using embedded ensemble learning algorithms, which automatically provides efficient and reliable fitness evaluations for optimisation iterations.

Findings - A large-scale project application shows that the proposed approach was able to reduce computational loads of SO by approximately 90%. Meanwhile, the proposed approach outperformed SO in terms of optimisation quality when the optimisation has limited searching ability.

Originality/value - The core contribution of this research is to provide an innovative method that improves efficiency and ensures effectiveness, simultaneously, of the well-known SO approach in construction applications. The proposed method is an alternative approach to SO that can run on standard computing platforms and support nearly real-time construction on-site decision-making.

Place, publisher, year, edition, pages
Emerald Group Publishing Limited, 2023
Keywords
Construction planning, Information and communication technology (ICT) applications, Optimisation, Simulation, Novel method
National Category
Construction Management
Research subject
Construction Management and Building Technology; Building Materials
Identifiers
urn:nbn:se:ltu:diva-86995 (URN)10.1108/ECAM-02-2021-0114 (DOI)000691298400001 ()2-s2.0-85113891374 (Scopus ID)
Funder
Swedish Research Council Formas
Note

Validerad;2023;Nivå 2;2023-08-15 (hanlid);

Forskningsfinansiär: China Postdoctoral Science Foundation (2020M670918); National Natural Science Foundation of China (51878026); China Association of Construction Education (2019087)

Available from: 2021-09-07 Created: 2021-09-07 Last updated: 2023-08-15Bibliographically approved
Jassim, H., Krantz, J., Lu, W. & Olofsson, T. (2020). A Model to Reduce Earthmoving Impacts. Journal of Civil Engineering and Management, 26(6), 490-512
Open this publication in new window or tab >>A Model to Reduce Earthmoving Impacts
2020 (English)In: Journal of Civil Engineering and Management, ISSN 1392-3730, E-ISSN 1822-3605, Vol. 26, no 6, p. 490-512Article in journal (Refereed) Published
Abstract [en]

Meeting increasingly ambitious carbon regulations in the construction industry is particularly challenging for earthmoving operations due to the extensive use of heavy-duty diesel equipment. Better planning of operations and balancing of competing demands linked to environmental concerns, costs, and duration is needed. However, existing approaches (theoretical and practical) rarely address all of these demands simultaneously, and are often limited to parts of the process, such as earth allocation methods or equipment allocation methods based on practitioners’ past experience or goals. Thus, this study proposes a method that can integrate multiple planning techniques to maximize mitigation of project impacts cost-effectively, including the noted approaches together with others developed to facilitate effective decision-making. The model is adapted for planners and contractors to optimize mass flows and allocate earthmoving equipment configurations with respect to tradeoffs between duration, cost, CO2 emissions, and energy use. Three equipment allocation approaches are proposed and demonstrated in a case study. A rule-based approach that allocates equipment configurations according to hauling distances provided the best-performing approach in terms of costs, CO2 emissions, energy use and simplicity (which facilitates practical application at construction sites). The study also indicates that trucks are major contributors to earthmoving operations’ costs and environmental impacts.

Place, publisher, year, edition, pages
VGTU Press, 2020
Keywords
earthmoving operations, optimization framework, optimum configuration, tradeoff duration, cost, emissions
National Category
Construction Management
Research subject
Construction Management and Building Technology
Identifiers
urn:nbn:se:ltu:diva-73322 (URN)10.3846/jcem.2020.12641 (DOI)000544410400001 ()2-s2.0-85088745185 (Scopus ID)
Note

Validerad;2020;Nivå 2;2020-07-23 (cisjan)

Available from: 2019-03-26 Created: 2019-03-26 Last updated: 2020-09-02Bibliographically approved
Lu, W. & Feng, K. (2020). Big-data driven building retrofitting: An integrated Support Vector Machines and Fuzzy C-means clustering method. In: Holger Wallbaum; Alexander Hollberg; Liane Thuvander; Paula Femenias; Izabela Kurkowska; Kristina Mjörnell; Colin Fudge (Ed.), WSBE 20 - World Sustainable Built Environment - Beyond2020 2-4 November 2020, Gothenburg, Sweden: . Paper presented at World Sustainable Built Enviroment Conference BEYOND 2020 (WSBE 20), Online, November 2-4, 2020. Institute of Physics (IOP), Article ID 042013.
Open this publication in new window or tab >>Big-data driven building retrofitting: An integrated Support Vector Machines and Fuzzy C-means clustering method
2020 (English)In: WSBE 20 - World Sustainable Built Environment - Beyond2020 2-4 November 2020, Gothenburg, Sweden / [ed] Holger Wallbaum; Alexander Hollberg; Liane Thuvander; Paula Femenias; Izabela Kurkowska; Kristina Mjörnell; Colin Fudge, Institute of Physics (IOP), 2020, article id 042013Conference paper, Published paper (Refereed)
Abstract [en]

It has become a mainstream to use physical models to quantify expected energy savings from alternative retrofit methods and technologies. However, they are not suitable for predicting energy use of buildings when detailed and specified input parameters are unavailable. The overall purpose of the research is to support the stakeholders in taking decisions on refurbishments options when not all of physical information is available, in order to achieve the Swedish Energy Agency's measurements of near-zero energy buildings. The research will transfer big data from Swedish Energy Performance Certificates for building retrofitting. A Support Vector Machines and Fuzzy C-means clustering (SVM-FCM) integrated machine learning algorithm is used directly to extract the case-specific knowledge from EPC big data regarding building characteristics and energy saving of retrofit measures. It enables to prioritize retrofit measures and compute their expected energy savings for buildings. This proposed data driven method is an attempt of taking advantage of big data for practical building retrofit selection.

Place, publisher, year, edition, pages
Institute of Physics (IOP), 2020
Series
IOP Conference Series: Earth and Environmental Science (EES), ISSN 1755-1315 ; 588(1.11 – 1.14)
National Category
Building Technologies
Research subject
Construction Management and Building Technology
Identifiers
urn:nbn:se:ltu:diva-85828 (URN)10.1088/1755-1315/588/4/042013 (DOI)2-s2.0-85097166873 (Scopus ID)
Conference
World Sustainable Built Enviroment Conference BEYOND 2020 (WSBE 20), Online, November 2-4, 2020
Funder
Swedish Research Council Formas
Note

Finansiär: China Postdoctoral Science Foundation (2020M670918)

Available from: 2021-06-22 Created: 2021-06-22 Last updated: 2021-06-22Bibliographically approved
Chen, S., Lu, W., Olofsson, T., Dehghanimohammadabadi, M., Emborg, M., Nilimaa, J., . . . Kailun, F. (2020). Concrete Construction: How to Explore Environmental and Economic Sustainability in Cold Climates. Sustainability, 12(9), Article ID 3809.
Open this publication in new window or tab >>Concrete Construction: How to Explore Environmental and Economic Sustainability in Cold Climates
Show others...
2020 (English)In: Sustainability, E-ISSN 2071-1050, Vol. 12, no 9, article id 3809Article in journal (Refereed) Published
Abstract [en]

In many cold regions around the world, such as northern China and the Nordic countries,on‐site concrete is often cured in cold weather conditions. To protect the concrete from freezing or excessively long maturation during the hardening process, contractors use curing measures. Different types of curing measures have different effects on construction duration, cost, and greenhouse gas emissions. Thus, to maximize their sustainability and financial benefits, contractors need to select the appropriate curing measures against different weather conditions. However, there is still a lack of efficient decision support tools for selecting the optimal curing measures, considering the temperature conditions and effects on construction performance. Therefore, the aim of this study was to develop a Modeling‐Automation‐Decision Support (MADS) framework and tool to help contractors select curing measures to optimize performance in terms of duration, cost, and CO2 emissions under prevailing temperatures. The developed framework combines a concrete maturity analysis (CMA) tool, a discrete event simulation (DES), and a decision support module to select the best curing measures. The CMA tool calculates the duration of concrete curing needed to reach the required strength, based on the chosen curing measures and anticipated weather conditions. The DES simulates all construction activities to provide input for the CMA and uses the CMA results to evaluate construction performance. To analyze the effectiveness of the proposed framework, a software prototype was developed and tested on a case study in Sweden. The results show that the developed framework can efficiently propose solutions that significantlyreduce curing duration and CO2 emissions.

Place, publisher, year, edition, pages
MDPI, 2020
Keywords
cold climate, discrete event simulation, concrete maturity analysis, curing measures, decision support
National Category
Other Materials Engineering Construction Management Other Civil Engineering
Research subject
Structural Engineering; Construction Management and Building Technology; Building Materials
Identifiers
urn:nbn:se:ltu:diva-78824 (URN)10.3390/su12093809 (DOI)000537476200307 ()2-s2.0-85085985324 (Scopus ID)
Note

Validerad;2020;Nivå 2;2020-05-11 (johcin)

Available from: 2020-05-08 Created: 2020-05-08 Last updated: 2022-02-10Bibliographically approved
Feng, K., Lu, W., Chen, S., Wang, S., Yang, B., Sun, C. & Wang, Y. (2020). Embedding Ensemble Learning into Construction Optimisation: A Computational Reduction Approach.
Open this publication in new window or tab >>Embedding Ensemble Learning into Construction Optimisation: A Computational Reduction Approach
Show others...
2020 (English)Article in journal (Refereed) Submitted
Abstract [en]

Simulation-based optimisation (SO), which combines simulation and optimisation technologies, is a popular approach for construction planning optimisation. However, in the framework of SO, the simulation is continuously invoked during the optimisation trajectory, which increases the computing loads to levels that are unrealistic to support the real-time construction decision. This study proposes ensemble learning embedded simulation optimisation (ESO) as an alternative approach for construction optimisation. The ensemble learning (EL) algorithm modifies the SO framework through establishing a connection between the simulation and optimisation technologies. This approach reduces the computing loads associated with the conventional SO framework by accurately learning from simulations and providing efficient fitness evaluations for optimisation. A large-scale project application shows that the proposed approach was able to reduce the computing loads of SO by approximately 90% yet still provide comparable optimisation quality. The proposed method is an alternative approach to SO that can be run on standard computing platforms and supports nearly real-time optimisation decisions.

Place, publisher, year, edition, pages
Elsevier, 2020
Keywords
Ensemble learning, Construction simulation, Decision optimisation, Construction method
National Category
Construction Management
Research subject
Construction Management and Building Technology
Identifiers
urn:nbn:se:ltu:diva-80775 (URN)
Funder
Swedish Research Council Formas
Available from: 2020-09-15 Created: 2020-09-15 Last updated: 2020-12-11
Segerstedt, A., Pettersen, J.-A., Holmbom, M., Lu, W. & Zhang, Q. (2020). Order quantities in a production line: influences on production output and lead-time.
Open this publication in new window or tab >>Order quantities in a production line: influences on production output and lead-time
Show others...
2020 (English)Manuscript (preprint) (Other academic)
Abstract [en]

This article tests the effect of different order quantities and setup times and its dependence of maximum Work-in-Process (WIP). The main studied supply chain consists of five linked machines with a fixed setup time for every batch in every machine, and stochastic operation times for every item in the batch. Additionally three linked machines with a clear bottleneck are studied. Production management can only control maximum WIP and not average WIP. Average WIP is a consequence of released work, variations, capacity and maximum WIP. A number of test cases are made where the number of units in the machines and the buffer areas are restricted. Previous studies have shown the dominance of CONWIP over Kanban, so only situations where maximum WIP is restricted in the total production line is studied. – The results show that increased maximum WIP leads to longer average lead-time but also that its coefficient of variation increases, independent of setup time and order quantity. A literature review confirms our assumption and opinion that large variations in lead-times are worse than long lead-times. A smaller order quantity leads to a lower production rate if not the setup time is decreased proportionally. A reduction of the order quantity can also increase the lead-time and its variation. A decrease of the order quantity requires a reduction of maximum WIP to implement its advantages. Therefore, reducing order quantities but still use the same parameters in in the companies’ computer system for material- and production control will prevent improvements. It is always favourable to reduce setup times and/or variation in operation times.

Keywords
order quantity, production batch, variation, setup time, lead-time, production rate
National Category
Construction Management Production Engineering, Human Work Science and Ergonomics
Research subject
Construction Management and Building Technology; Industrial Logistics
Identifiers
urn:nbn:se:ltu:diva-78720 (URN)
Available from: 2020-04-29 Created: 2020-04-29 Last updated: 2020-04-29
Feng, K., Wang, S. & Lu, W. (2020). Uncertainty Analysis Approach for Construction under Deep Uncertainty. Journal of construction engineering and management
Open this publication in new window or tab >>Uncertainty Analysis Approach for Construction under Deep Uncertainty
2020 (English)In: Journal of construction engineering and management, ISSN 0733-9364, E-ISSN 1943-7862Article in journal (Refereed) Submitted
Abstract [en]

Construction processes usually occur under uncertain conditions, such as uncertain labour work productivity, equipment failure rate, weather situation and off-site transport condition. These uncertain factors can significantly affect project outcomes. However, for projects lacking a full understanding of uncertain factors, uncertainty analysis approaches relying on prior probability distribution or reasonable range are no longer applicable. Situations in which uncertain factors cannot be fully understood in decision-making are defined as deep uncertainty problems.

This study proposes an uncertainty analysis approach that integrates process simulation and data mining to be a data-driven method for decision-making in construction projects under deep uncertainty. In process simulation, a Latin Hypercube Sampling (LHS) generates the samples of uncertainty scenario, and Discrete-Event Simulation (DES) quantifies robustness of alternative schemes under uncertain scenarios. In data mining, the Patient Rule Induction Method (PRIM) algorithm reveals the vulnerability of decisions that lead to unacceptable project performance. A real construction case was used to test the presented approach, with the results revealing that the approach is valuable for decision-makers who need to analyse uncertainty without reliable prior probability distributions and reasonable range of certain uncertain factors. It quantified the robustness of various construction schemes, as well as identified the vulnerable scenarios that could jeopardise project completion. The developed approach is an applicable uncertainty analysis approach to support decision-making of construction project under deep uncertainty.

Place, publisher, year, edition, pages
American Society of Civil Engineers (ASCE), 2020
Keywords
Construction, Deep uncertainty, Decision-Making, Robustness, Vulnerability analysis
National Category
Construction Management
Research subject
Construction Management and Building Technology
Identifiers
urn:nbn:se:ltu:diva-80796 (URN)
Funder
Swedish Research Council Formas
Available from: 2020-09-15 Created: 2020-09-15 Last updated: 2020-09-15
Chen, S., Feng, K., Lu, W., Wang, Y., Chen, X. & Wang, S. (2019). A Discrete Event Simulation-Based Analysis of Precast Concrete Supply Chain Strategies Considering Suppliers’ Production and Transportation Capabilities. In: Yaowu Wang; Mohamed Al-Hussein; Geoffrey Q. P. Shen (Ed.), ICCREM 2019: Innovative Construction Project Management and Construction Industrialization: Proceedings of the International Conference on Construction and Real Estate Management 2019. Paper presented at International Conference on Construction and Real Estate Management (ICCREM 2019), Banff, Canada, May 21-24, 2019 (pp. 12-24). American Society of Civil Engineers (ASCE)
Open this publication in new window or tab >>A Discrete Event Simulation-Based Analysis of Precast Concrete Supply Chain Strategies Considering Suppliers’ Production and Transportation Capabilities
Show others...
2019 (English)In: ICCREM 2019: Innovative Construction Project Management and Construction Industrialization: Proceedings of the International Conference on Construction and Real Estate Management 2019 / [ed] Yaowu Wang; Mohamed Al-Hussein; Geoffrey Q. P. Shen, American Society of Civil Engineers (ASCE), 2019, p. 12-24Conference paper, Published paper (Refereed)
Abstract [en]

The production and transportation capabilities of a precast concrete (PC) component supplier have great impact on the construction of a PC building project. In China, the production and transportation capabilities of different PC suppliers can vary greatly, which will influence contractors’ selection of PC supply chain strategies. However, previous studies often considered the capabilities of PC suppliers to be ideal and failed to compare different PC supply chain strategies under different levels of suppliers capabilities. This study collects detailed data from a PC building project and uses discrete event simulation (DES) to compare different supply chain strategies under different production and transportation capability levels of PC suppliers. Construction duration, construction cost, and greenhouse gas emissions are selected as indicators to compare three different supply chain strategies: just-in-time, on-site storage, and off-site storage. The strengths and weaknesses of each strategy under different capabilities of PC suppliers are found. The results provides guidance for contractors in selecting supply chain strategies when considering PC suppliers’ production and transportation capabilities.  

Place, publisher, year, edition, pages
American Society of Civil Engineers (ASCE), 2019
National Category
Construction Management
Research subject
Construction Management and Building Technology; Building Materials
Identifiers
urn:nbn:se:ltu:diva-86166 (URN)10.1061/9780784482308.002 (DOI)2-s2.0-85072941071 (Scopus ID)
Conference
International Conference on Construction and Real Estate Management (ICCREM 2019), Banff, Canada, May 21-24, 2019
Funder
Swedish Research Council FormasThe Swedish Foundation for International Cooperation in Research and Higher Education (STINT)
Note

ISBN för värdpublikation: 978-0-7844-8230-8;

Finansiär: National key research and development Program of China (2016YFC0701904)

Available from: 2021-06-30 Created: 2021-06-30 Last updated: 2024-12-03Bibliographically approved
Chen, S., Feng, K. & Lu, W. (2019). A Simulation-Based Optimisation for Contractors in Precast Concrete Projects. In: : . Paper presented at 10th Nordic Conference on Construction Economics and Organization, 7-8 May 2019, Tallinn, Estonia (pp. 137-145). Emerald Group Publishing Limited, 2
Open this publication in new window or tab >>A Simulation-Based Optimisation for Contractors in Precast Concrete Projects
2019 (English)Conference paper, Published paper (Refereed)
Abstract [en]

Purpose

This paper aims to provide decision support for precast concrete contractors about both precastconcrete supply chain strategies and construction configurations.

Design/Methodology/Approach

This paper proposes a simulation-based optimisation for supplychain and construction (SOSC) during the planning phase of PC building projects. The discrete eventsimulation is used to capture the characteristics of supply chain and construction processes, and calculate construction objectives under different plans. Particle swarm optimisation is combined with simulation tofind optimal supply chain strategies and construction configurations.

Findings

The efficiency of SOSC is compared with the parametric simulation approach. Over 70 per centof time and effort used to simulate and compare alternative plans is saved owing to SOSC.

Research Limitations/Implications

Building simulation model costs a lot of time and effort. The data requirement of the proposed method is high.

Practical Implications

The proposed SOSC approach can provide decision support for PC contractorsby optimising supply chain strategies and construction configurations.

Originality/Value

This paper has two contributions: one is in providing a decision support tool SOSC tooptimise both supply chain strategies and construction configurations, while the other is in building aprototype of SOSC and testing it in a case study.

Place, publisher, year, edition, pages
Emerald Group Publishing Limited, 2019
Keywords
Precast concrete, Supply chain, Building construction, Discrete event simulation, Particle swarm optimization, Simulation-based optimization
National Category
Construction Management
Research subject
Construction Management and Building Technology
Identifiers
urn:nbn:se:ltu:diva-74055 (URN)10.1108/S2516-285320190000002019 (DOI)001316119300017 ()2-s2.0-85084806967 (Scopus ID)
Conference
10th Nordic Conference on Construction Economics and Organization, 7-8 May 2019, Tallinn, Estonia
Funder
Swedish Research Council FormasThe Swedish Foundation for International Cooperation in Research and Higher Education (STINT)
Note

Full text license: CC BY

Available from: 2019-05-27 Created: 2019-05-27 Last updated: 2024-11-20Bibliographically approved
Feng, K., Lu, W. & Wang, Y. (2019). Assessing environmental performance in early building design stage: An integrated parametric design and machine learning method. Sustainable cities and society, 50, Article ID 101596.
Open this publication in new window or tab >>Assessing environmental performance in early building design stage: An integrated parametric design and machine learning method
2019 (English)In: Sustainable cities and society, ISSN 2210-6707, Vol. 50, article id 101596Article in journal (Refereed) Published
Abstract [en]

Decisions made at early design stage have major impacts on buildings’ life-cycle environmental performance. However, when only a few parameters are determined in early design stages, the detailed design decisions may still vary significantly. This may cause same early design to have quite different environmental impacts. Moreover, default settings for unknown detailed design parameters clearly cannot cover all possible variations in impact, and Monte Carlo analysis is sometimes not applicable as parameters’ probability distributions are usually unknown. Thus, uncertainties about detailed design make it difficult for existing environmental assessment methods to support early design decisions.

Thus, this study developed a quantitative method using parametric design technology and machine learning algorithms for assessing buildings’ environmental performance in early decision stages, considering uncertainty associated with detailed design decisions. The parametric design technology creates design scenarios dataset, then associated environmental performances are assessed using environmental assessment databases and building performance simulations. Based on the generated samples, a machine learning algorithm integrating fuzzy C-means clustering and extreme learning machine extracts the case-specific knowledge regarding designed buildings’ early design associated with environmental uncertainty. Proposed method is an alternative but more generally applicable method to previous approaches to assess building's environmental uncertainty in early design stages.

Place, publisher, year, edition, pages
Elsevier, 2019
Keywords
Building early design, Parametric design, Machine learning, Environmental impact, Prediction intervals
National Category
Construction Management
Research subject
Construction Management and Building Technology
Identifiers
urn:nbn:se:ltu:diva-75133 (URN)10.1016/j.scs.2019.101596 (DOI)000484255800005 ()2-s2.0-85067201337 (Scopus ID)
Note

Validerad;2019;Nivå 2;2019-06-28 (johcin)

Available from: 2019-06-28 Created: 2019-06-28 Last updated: 2019-09-27Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-4695-5369

Search in DiVA

Show all publications