CC BY
5
RISK MANAGEMENT USING ARTIFICIAL INTELLIGENCE IN THE ORGANIZATION OF CONSTRUCTION AND ERECTION OF MONOLITHIC REINFORCED CONCRETE STRUCTURES IN THE FAR NORTH AND ARCTIC ZONE CONDITIONS
Azariy Lapidus, Tembot Bidov, Alan Khubaev, Roman Samsonov
National Research Moscow State Construction University, RUSSIA
Abstract
The study is focused on the application of artificial intelligence (AI) in the construction and erection of monolithic reinforced concrete structures in the Far North and Arctic zone, with the aim of managing potential risks. The topic deals with various ways required to mitigate risks associated with the unique climatic and weather conditions of these regions. The objective of this study is to develop a methodology for forecasting and risk management using AI. In this study, data on construction processes and potential risks in Far North and Arctic zone conditions was utilised. The methodology is based on the application of artificial intelligence algorithms for data processing and analysis.
The study resulted in the proposal of an AI-based risk management methodology. This methodology enables the prediction of potential issues and comprehensive risk management at all stages of construction and erection of monolithic reinforced concrete structures. The application of AI in construction risk management in the Far North and Arctic zone increases the efficiency and safety of construction processes. The use of the developed model is recommended for risk minimization and optimization of construction in complex climatic conditions.
Keywords: Risk management, artificial intelligence, monolithic reinforced concrete structures, Far North, Arctic zone, risk forecasting
I. Introduction
The construction and erection of monolithic reinforced concrete structures in the Far North and Arctic zone presents a number of significant risks, including those associated with harsh climatic conditions, limited availability of resources, and complex logistics [1-6]. It is of the utmost importance to manage these risks in order to guarantee the safety, quality, and efficiency of construction projects in these regions.
The organization of construction and erection of monolithic reinforced concrete structures in the Far North and Arctic zone presents a unique set of risks, largely due to the harsh climate, limited access to resources, and specific reliability and durability requirements. [7,8] Further discussions will be undertaken to evaluate all types of risk.
1. Climate risks:
- Low temperatures: Paving concrete at sub-zero temperatures requires specific steps such as heating the concrete mix placed in the formwork, using anti-freeze additives, and insulating the formwork. Failure to comply with these technical requirements may result in failure to achieve the design strength of the concrete, cracking and other defects.
588
- Strong winds: Strong winds can impede the operation of construction equipment, prevent concrete from gaining strength, damage building structures, and increase the risk of accidents.
- Snow drifts: Snow drifts can impede access to the construction site and delay delivery of materials and equipment.
- Polar Night: Limited visibility during polar night can impede work and increase the risk of accidents.
2. Logistical Risks:
- Remoteness from suppliers: Delivery of materials and equipment can be difficult and expensive in remote areas of the Arctic. [9,10]
- Limited access to transportation infrastructure: Lack of roads, ports and airfields can make it difficult to deliver supplies and move personnel. [11,12]
- Dependence on weather conditions: Transportation of cargo on snow-covered roads may be difficult during winter.
3. Technical Risks:
- Permafrost: Construction requires the use of special foundation solutions to prevent subsidence and deformation of structures. This issue requires particular attention in light of the current global warming trend.
- Seismic activity: Some areas of the Arctic are subject to seismic activity, therefore seismic loads in the design of structures shall be taken into consideration [13-15].
- Corrosion: The presence of salty seawater and corrosive atmospheres can accelerate the corrosion of metal structures.
4. Personnel-related risks:
- Extreme conditions: Working in the Far North and Arctic zone can be physically and psychologically challenging, as such can lead to decreased productivity and increased risk of accidents.
- Lack of qualified specialists: It can be challenging to identify, recruit and retain qualified professionals willing to work in extreme conditions.
5. Economic Risks:
- Significant construction costs: Projects pertaining to the construction of facilities in the Arctic is associated with significant coast implications related to logistics, materials, equipment, and labor.
- Price instability: It is possible that prices for construction materials and other related services fluctuate, which could result in budget overruns.
- Potential for delays: Delays in deliveries, weather and other factors can result in construction delays, which in turn can increase costs.
It is of the utmost importance to manage these risks effectively in order to ensure successful construction in the Far North and Arctic zone. The use of AI can help identify, analyze, and manage risks, thereby improving construction efficiency and safety.
Traditional risk management methods are not always effective in addressing the increasing complexity and uncertainty of factors in extreme conditions in the North. The application of advanced technologies, such as artificial intelligence (AI), can be regarded as an invaluable opportunity to enhance the effectiveness of risk management in construction projects. [16-20]
While there is growing interest in the use of AI in construction, there is still a lack of research on its application in extreme conditions, such as those found in the Far North and the Arctic. Implementation of AI in construction can resolve problems in the following key areas:
- Improving construction efficiency: Artificial intelligence (AI) can optimize planning, logistics, resource management, and quality control, thereby reducing construction time and costs.
- Improving structural quality: AI systems can analyze data on weather conditions, material properties, and manufacturing processes to assist in decision-making, thereby improving the reliability and durability of structures.
- Workplace safety: AI can be utilized to monitor the condition of construction projects, predict potential risks, and automate hazardous operations, thereby enhancing worker safety.
The objective of this article is twofold: firstly, to assess the potential of AI in the organisation of construction and erection of monolithic reinforced concrete structures in the Far North and Arctic zone; secondly, to identify key problems and areas for further research. The research will propose a risk management methodology and methods for implementing it in the process of erecting monolithic reinforced concrete structures in the Far North and Arctic zone. [21-24]
II. Materials and methods
The scientific literature was analyzed as part of a study on the application of AI in construction. Additionally, case studies were conducted on the use of AI in other industries operating in extreme environments.
The following aspects were considered in order to evaluate the potential of AI in construction in the Arctic:
- Planning and design: The use of AI to optimize construction site selection, site-specific structural design, and cost forecasting.
- Logistics and resource management: The use of AI to optimize material delivery routes, manage inventory, and forecast demand.
- Quality Control: The application of AI to the analysis of data from sensors on construction projects enables the monitoring of structural health and the determination, identification and troubleshooting of defects.
- Workplace safety: By leveraging AI, we can predict potential risks, automate hazardous operations, and monitor the condition of personnel.
It is essential that risk management methodology be comprehensive and take into account both traditional approaches and the specific features of AI use in the context of AI application in the organization of construction and erection of monolithic reinforced concrete structures in the Far North and Arctic zone [24-28].
III. Results
The result of the research is the methodology of risk management when using AI in the construction of monolithic reinforced concrete structures in the Far North and Arctic zone, as presented below. This is an algorithm of step-by-step actions. Please refer to Table 1 for details.
Table 1: Methodology of risk management when using AI
№ Stage Actions
1 Project Initialization • Define project objectives and requirements. • Form a project team, including AI and construction specialists.
2 Data Collection • Obtain data from completed projects in similar environments. • Analyze the available information on climatic conditions, logistics, material supply, and technical aspects.
3 Risk Identification • Conduct brainstorming sessions with all stakeholders. • Utilize AI to analyze the collected data and identify potential risks.
4 Risk Assessment: • Evaluate the likelihood and impact of each identified risk. • Apply an AI model to predict potential scenarios and their consequences.
5 Risk Mitigation Planning • Develop a risk management strategy (avoidance, mitigation, transfer, acceptability). • Identify specific actions for each risk, including the reservation of necessary resources.
6 Implement the risk management • Implement the risk management plan. • Assigning responsibility for monitoring and controlling risks.
plan.
7 Monitoring and Control: • It is essential to regularly track the status of the project and any associated risks. • Use AI for continuous monitoring and early warning of problems.
8 Risk Response • In the event of a risk, the implementation of response plans is to be initiated without delay. • Adjusting actions according to the current situation.
9 Analyze and adapt • Analyze the effectiveness of risk management measures. • Modify risk management plans as needed.
10 Reporting and Communication • Regular reporting of risk status and management actions. • Maintaining open communication about risks and risk management actions.
11 Project Completion and Learning • After project completion, analyze the project with a focus on risk management. • Leveraging the insights gained to enhance the training of staff and optimize risk management processes in future projects.
12 Repeat the cycle. • Apply the updated risk management methodology to future projects, taking into account lessons learned and new AI capabilities.
The process of collecting data on implemented projects begins with the identification of key indicators and risks that warrant analysis. Subsequently, questionnaires, interviews, and document analysis can be employed to procure data on previous projects. It is crucial to ensure anonymity of responses and to analyze the collected data in order to reveal trends and findings that will help in planning future projects.
Table 2: Risk matrix
№ Risk Description Probability (P) Impact (I) Risk Class Risk Indicator (R) Management Measures
1 Delay in delivery of materials High (0.8) Medium (50,000 rubles) High 40,000 •Close standby contracts •Create a stock of materials
2 Inconsistency in material quality Medium (0.5) High (100 000 rubles) High 50 000 •Careful quality control at acceptance |
3 Shortage of qualified personnel Low (0.2) Medium (20 000 rubles.) Средний 4 000 •Contracting back-up contracts
4 Changes in legislation Low (0.1) High (200 000 rubles) Medium 20 000 •Monitoring changes in legislation •Consultation with lawyers
5 Unexpected force majeure Low (0.1) Very high (500 000 rubles.) very high 50 000 •Development of a plan of action in case of force majeure •Insurance against force majeure risks
The risk identification phase commences with the definition of project goals and objectives, followed by brainstorming sessions with the project team and stakeholders. It is also important to analyze past projects in order to identify potential problems and consider external factors that may affect the project. The next step is to generate a comprehensive list of all potential risks. This list will then be analyzed and classified according to the level of threat posed.
The risk assessment phase commences with the categorization of identified risks according to their level of likelihood and potential impact. A risk matrix can be utilized for this purpose, with each risk rated on a scale from low to high. For each risk, specific impact indicators are identified, such as financial loss, project delivery time, or reputational risks. A risk score is calculated for each element based on these scores, which allows the risks to be ranked in order of hazard.
The probability (P) is calculated using historical data, expert opinion, and an analysis of the current situation as presented in the table. Impact is estimated in monetary terms, in days of delay, or as a percentage of the planned outcome. The risk class is determined by combining probability and impact. The risk score (R) is calculated by multiplying the probability and impact factors together (P * I). Management measures have been defined for each risk, with the objective of minimizing or preventing it.
In the Monitoring and Control phase, AI is leveraged to facilitate continuous tracking and risk management. This encompasses a range of activities, including continuous data analysis, prediction and warning, decision optimization, automation, and data visualization.
In the seventh and eighth phases, the methodologies are employed to actively manage risks throughout the project lifecycle. The project team employs AI systems to monitor the situation continuously, analyzing large volumes of data in real time during the monitoring and control phase.
This allows for the timely identification of any deviations from the plan and potential threats. The risk response stage requires the ability to make quick and flexible decisions. In the event of an issue, the team promptly assesses the situation, activates pre-prepared response plans, and, if necessary, adapts them to the current circumstances. The AI's ability to rapidly simulate a range of potential scenarios is a crucial factor in enabling optimal decision-making in the challenging conditions of the Far North.
IV. Conclusions
The use of artificial intelligence in risk management may prove to be effective tool for managing risks in the construction of monolithic reinforced concrete structures in the Far North and Arctic zone. The use of AI enhances the precision of risk identification and assessment, optimizes decision-making, and facilitates real-time risk monitoring.
Further research could focus on improving data processing and analysis methods, developing AI models, and exploring specific aspects of risk management in different types of Arctic projects. The successful implementation of AI in construction in the Arctic requires:
• Create databases of construction in these environments that can be used to train AI models.
• Develop AI systems that are tailored to the specific operational conditions in the Arctic.
• It is essential to provide adequate training to qualified professionals who are capable of developing, implementing, and maintaining AI systems.
The set up of AI in construction in the Arctic is a complex system, but nevertheless a positive undertaking given the fact that it has the potential to drive significant progress in this field. We anticipate active development of AI in construction over the coming years. It is anticipated that AI development will include the Arctic. The advent of new AI technologies and tools, coupled with the growing accessibility of construction data in challenging environments, will drive the broader adoption of AI in this sector.
References
[1] Tsygankova A.A., Romanchenko O. V., Shemetkova O. L. Infrastructure of the Arctic zone of the Russian Federation: state, economic instruments of development and priority projects. Regional Economics and Management: electronic scientific journal. - 2016. - №. 4 (48). - p. 181-193.
[2] Savinova V., M.M. Brodach, Features of design and construction in the Arctic region. High Technology Buildings. - 2018. - № 4.
[3] Kalinina N.S., N.V. Morozov, Architectural, technical and design features of designing residential and public buildings in the Far North. System Technologies. - 2019. - № 3(32).
[4] Khubaev, A.O. Improvement of the production process of winter concreting on the basis of the potential of organizational and technical solutions: specialty 05.02.22 "Production organization (by branches) »: dissertation for the degree of Candidate of Technical Sciences /2022. -178 p.
[5] Akshov E.A. Use of computational design and artificial intelligence in modeling architectural objects. Architecture and Modern Information Technologies. - 2023. - №. 2 (63). - p. 298-315.
[6] Abioye S. O., L. O. Oyedele, L. Akanbi, Artificial intelligence in the construction industry: A review of present status, opportunities and future challenges. Journal of Building Engineering. -2021. - Vol. 44. - P. 103299. - DOI 10.1016/j.jobe.2021.103299.
[7] Koshelev V. A. Risk management mechanism in construction. Voprosy ekonomiki i prava. - 2014. - №. 74. - p. 122-127.
[8] Korabelnikova S.S., S.K. Korabelnikova, Digital technologies as an element of risk reduction in construction. Discussion. - 2019. - № 2(93). - p. 18-27. - DOI 10.24411/2077-7639-201810002.
[9] Lapidus A.A., I.L. Abramov, T.K. Kuzmina, A.I. Abramova, Sustainability of the activity of construction organizations under the conditions of risk factors. Industrial and Civil Engineering. - 2023. - № 11. - p. 97-104. - DOI 10.33622/0869-7019.2023.11.97-104.
[10] Abramov I., AlZaidi Z. A. K., Evaluation of the Effective Functioning of Construction Enterprises in the Conditions of Occurrence of Diverse Risk Factors. Buildings. -2023. - T. 13. - №. 4. - p. 995. - DOI 10.3390/buildings13040995.
[11] Lapidus A.A., I. Abramov, T. Kuzmina, Abramova A., Alzaidi Z.A.K. Study of the Sustainable Functioning of Construction Companies in the Conditions of Risk Factors. Buildings. -2023. - Vol. 13, No. 9. - P. 2282. - DOI 10.3390/buildings13092282
[12] Schreiber, I. Abramov, Z. Al-Zaidi, Assessment of risk-forming factors of construction production in conditions of uncertainty. E3S Web of Conferences. - EDP Sciences, 2021. - T. 258. - p. 09052. - DOI 10.1051/e3sconf/202125809052
[13] Makarov A. "Organization of Construction Quality Control based on a Priori Risks of Works," International Journal of Engineering Trends and Technology, vol. 71, no. 1, pp. 134-140, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I1P212
[14] Szymanski P., "Risk management in construction projects", Procedia Engineering 208, 174-182 (2017). https://doi.org/10.1016Zj.proeng.2017.11.036
[15] Wang T., et al, "A meta-network-based risk evaluation and control method for industrialized building construction projects", Journal of Cleaner Production 205, 552-564 (2018). https://doi.org/10.1016/j.jclepro.2018.09.127
[16] Hwang B.G. , X. Zhao and L. P. Toh, "Risk management in small construction projects in Singapore: Status, barriers and impact", International Journal of Project Management 32(1), 116-124 (2014). https://doi.org/10.1016/j.ijproman.2013.01.007
[17] Zhou H. , et al, "Risk assessment and management via multi-source information fusion for undersea tunnel construction", Automation in Construction 111, 103050 (2020).
[18] Dziadosz A. , A. Tomczyk and O. Kaplinski, "Financial risk estimation in construction contracts", Procedia Engineering 122, 120-128 (2015). https://doi.org/10.1016/j.proeng.2015.10.015
[19] Mohamed M. and D. Q. Tran, "Risk-based inspection for concrete pavement construction using fuzzy sets and bayesian networks", Automation in Construction 128, 103761 (2021). https://doi.org/10.1016/j.autcon.2021.103761
[20] Zheng X.-W. , H.-N. Li and P. Gardoni, "Life-cycle probabilistic seismic risk assessment of high-rise buildings considering carbonation induced deterioration", Engineering Structures 231, 111752 (2021).https://doi.org/10.1016/j.engstruct.2020.111752
[21] Ilyin, A.V., N.V. Vladimirov, The use of artificial intelligence in construction. Bulletin of the Master's degree program. - 2022. - № 4-2(127). - p. 5-7.
[22] Zavgorodniy A. M., Vakurov A. E. Use of Artificial Intelligence in Construction. Description and advantages of smartvid. io to ensure safety at the construction site. BST: Bulletin of construction technology. - 2018. - №. 12. - p. 52-53.
[23] Topchiy D. V., Tokarskiy A. Ya. The concept of quality control of the organization of construction processes during construction supervision based on the use of information technology. Vestnik Eurasian Science. - 2019. - T. 11. - №. 3. - p. 49.
[24] Khubaev A. O., Sahakyan S. S. Increasing the efficiency of monolithic construction with the use of virtual and augmented reality technology. Proceedings of Tula State University. Technical Sciences. - 2019. - №. 12. - p. 492-495.
[25] Bidov T.H., A.O. Khubaev, A.A. Shabanova, Organizational and technical modeling of the complex system of concrete works production in winter period during the construction of residential buildings. Construction and Geotechnics. - 2021. - T. 12, № 2. - p. 15-25. - DOI 10.15593/2224-9826/2021.2.02.
[26] Khubaev A.O., Determination of the efficiency of the production process of winter concreting based on field studies. E3S Web of Conferences: Ural Environmental Science Forum "Sustainable Development of Industrial Region" (UENF-2023), Chelyabinsk, April 25-28, 2023. Vol. 389. - Chelyabinsk: EDP-Nauka, 2023. - P. 06012. - DOI 10.1051/e3sconf/202338906012.
[27] Lapidus A., A. Khubaev, T. Bidov, A. Regression analysis of the calculation of organizational and technological potential for the production of cold-weather concreting. IOP Conference Series: Materials Science and Engineering: 23, Construction - The Formation of Living Environment, 55 Giai Phong Road, Hanoi, September 23-26, 2020. - 55 Giai Phong Road, Hanoi, 2020. - P. 072033. - DOI 10.1088/1757-899X/869/7/072033.
[28] Lapidus A.A., A.O. Khubaev, Increasing the efficiency of winter concreting production through the use of software "potential-cwc". // Izvestiya Tula State University. Technical Sciences. - 2020. - № 5. - p. 18-26.
