Machine learning and reasoning for predictive maintenance in Industry 4.0: Current status and challenges

The Architecture, Engineering, Construction, and Facility Management (AEC-FM) industry is increasingly affected by digital technologies that monitor sensor network data and control automation systems. Advances in digital technologies like Digital Twin offer a high-level representation of buildings and their assets by integrating the physical and digital world. This paper examines patterns, gaps, and trends in the AEC-FM sector and contributes to digitalization and automation solutions for building management. This work covers a broad range of research topics, from intelligent information management of complex models to building information management and the interaction of building systems, where researchers are increasingly interested in using the Digital Twin to manage their information and in developing new research lines focused on data interchange and the interoperability of building information modeling (BIM) and facility management (FM). After a complete bibliometric search of several databases and following selection criteria, 77 academic publications about the Digital Twin application in the AEC-FM industry were labeled and clustered accordingly. This study analyzed in detail the concept of key technologies, including “Digital Twin in Facility Lifecycle Management,” “Digital Twin-Information Integration Standards,” “Digital Twin-Based Occupants Centric Building Design,” “Digital Twin-Based Predictive Maintenance,” “Semantic Digital Twin for Facility Maintenance,” and “Digital Twin-Based Human Knowledge.” The findings show that information standardization is the first major hurdle that must be overcome before the actual use of Digital Twin can be realized in the AEC-FM industry. Based on that, this paper provides a conceptual framework of Digital Twin for building management as a starting point for future research.

/pdf/a-review-of-the-digital-twin-technology-in-the-aec-fm-2w816uw8.pdf

A Review of the Digital Twin Technology in the AEC-FM Industry

Efficient removal of tar employing dolomite catalyst in gasification: Challenges and opportunities.

Healthcare facilities are constantly deteriorating due to tight budgets allocated to the upkeep of building assets. This entails the need for improved deterioration modeling of such buildings in order to enforce a predictive maintenance approach that decreases the unexpected occurrence of failures and the corresponding downtime elapsed to repair or replace the faulty asset components. Currently, hospitals utilize subjective deterioration prediction methodologies that mostly rely on age as the sole indicator of degradation to forecast the useful lives of the building components. Thus, this paper aims at formulating a more efficient stochastic deterioration prediction model that integrates the latest observed condition into the forecasting procedure to overcome the subjectivity and uncertainties associated with the currently employed methods. This is achieved by means of developing a hybrid genetic algorithm-based fuzzy Markovian model that simulates the deterioration process given the scarcity of available data demonstrating the condition assessment and evaluation for such critical facilities. A nonhomogeneous transition probability matrix (TPM) based on fuzzy membership functions representing the condition, age and relative deterioration rate of the hospital systems is utilized to address the inherited uncertainties. The TPM is further calibrated by means of a genetic algorithm to circumvent the drawbacks of the expert-based models. A sensitivity analysis was carried out to analyze the possible changes in the output resulting from predefined modifications to the input parameters in order to ensure the robustness of the model. The performance of the deterioration prediction model developed is then validated through a comparison with a state-of-art stochastic model in contrast to real hospital datasets, and the results obtained from the developed model significantly outperformed the long-established Weibull distribution-based deterioration prediction methodology with mean absolute errors of 1.405 and 9.852, respectively. Therefore, the developed model is expected to assist decision-makers in creating more efficient maintenance programs as well as more data-driven capital renewal plans.

https://www.mdpi.com/1999-4893/13/9/210/pdf

A Hybrid Genetic Algorithm-Based Fuzzy Markovian Model for the Deterioration Modeling of Healthcare Facilities

Modeling impacts of climate change on the potential distribution of three endemic Aloe species critically endangered in East Africa

Climate change is expected to threaten endemic plants in the Alps. In this context, the factors that may modulate species responses are rarely investigated at a local scale. We analyzed eight alpine narrow endemics of the Dolomites (southeastern Alps) under different predicted climate change scenarios at fine spatial resolutions. We tested possible differences in elevation, topographic heterogeneity and velocity of climate change among areas of gained, lost, or stable climatic habitat. The negative impact of climate change ranged from moderate to severe, depending on scenario and species. Generally, range loss occurred at the lowest elevations, while gained and stable areas were located at highest elevations. For six of the species, climate change velocity had higher values in stable and gained areas than in lost ones. Our findings support the role of topographic heterogeneity in maintaining climatic microrefugia, however, the peculiar topography of the Dolomites, characterized by high altitude plateaus, resulted in high climate change velocity in areas of projected future climatic suitability. Our study supports the usefulness of multiple predictors of spatio-temporal range dynamics for regional climate-adapted management and eventual assisted colonization planning to not overlook or overestimate the potential impact of climate change locally. 

/pdf/topography-of-the-dolomites-modulates-range-dynamics-of-26yvugu8.pdf

Topography of the Dolomites modulates range dynamics of narrow endemic plants under climate change

I4.0 revolution is permeating every technical sector, by promoting deployment of enabling technologies (ETs), also in the facility management (FM) discipline. As FM regards the integration of processes within an organization to support activities, it is clear how ETs can trigger, in the FM area, significant innovations like a better failure knowledge management and a sustainable use of resources. More specifically, the implementation in building maintenance of dynamic systems, linked to sensors networks, can allow changes into knowledge management and FM decision-making processes. Starting from these premises, the paper deals with an ongoing research, whose aim is to investigate how ETs may innovate the traditional maintenance strategies with new approaches in corrective, condition-based and predetermined maintenance. According to the above, building maintenance, which is traditionally reactive, may actually become proactive if failure management policy is set. The aim of this paper is to demonstrate how ETs adoption may promote innovation in FM processes focusing on maintenance in service equipment field. More specifically, an operative and methodological framework for reaching proactive maintenance is described through the support of a case study concerning two major healthcare infrastructures in Italy, managed by a major FM company.

https://iopscience.iop.org/article/10.1088/1755-1315/296/1/012055/pdf

Industry 4.0 for failure information management within Proactive Maintenance

For an effective risk management of complex buildings it is required to dynamically estimate the risk on the service and take proper responsive measures to contrast it. This implies being able to estimate the evolving probabilities of failures over time and the way their occurrence is trust in affecting the service. This is now possible thanks to the advent of new sensing technologies and data-driven models to estimate failure probabilities, as well as solid risk management methodologies to estimate their effect on the service. However, it needs to be considered that the implementation of a dynamic risk management in standard building operation has to consider the reconfiguration of some processes to include the use of enabling technologies. In this paper a new dynamic risk management methodology is proposed to consistently (i) model the service, estimate the risk, first (ii) statically, using fault tree analysis, and then (iii) dynamically, using sensing technologies for data gathering and data-driven models for dynamic probability estimate, and finally (iv) implement the required intervention measures to minimize the risk. Then an application of the methodology is presented, for the risk management of an air handling unit, using a convolutional neural network, and its outcomes discussed. Conclusions are also drawn on the implications of integrating such a methodology in the current whole building risk management process and several outlooks are proposed.

A New Risk Management Methodology for Infrastructure Based on Real-Time Monitoring and Dynamic Interventions: An Example Application on an Air Handling Unit

Resilience of the built environment, particularly in complex buildings, is strictly related to the effectiveness of systems and sub-systems that provide the expected features to manage risk scenarios in routine and non-routine conditions. In this perspective, maintenance is therefore a key factor to assure building resilience by keeping systems and equipment in the required operational state. Risk management can be empowered if system resilience and disruptive events are monitored in real-time, and, to this aim, proactive maintenance can nowadays monitor systems resilience with innovative digital tools.

/pdf/proactive-maintenance-strategy-based-on-resilience-1keaoqa38n.pdf

Proactive Maintenance Strategy Based on Resilience Empowerment for Complex Buildings

Nowadays, the FM scenario is undergoing a deep transformation due to the increasing adoption of information and communication technologies (ICTs). Real-time data, new storage possibilities and data analytics are changing the modalities of monitoring and control of service performances offered at the building scale. Data-driven approaches based on predictive analyses applied in FM are meeting a large consensus from FM operators which are perceiving the related achievable benefits. However, applications of ICTs in FM are still at an experimental stage and they can be subjected to a variable level of uncertainty due to the lack of knowledge about systems behaviors. This uncertainty can not only affect the calculation of the expected service performance (SLA) but also the deviation between expected and actual service performances. The uncertainty on expected performances gains a higher relevance when FM services are outsourced to an external provider (especially in performance-based contracts). The paper aims to propose a methodology to quantify and manage the deviation between expected and actual service performances within FM contracts, acting both in the contracting phase (SLAs definition) and during the service provision (deviation expected/actual performance). This methodology would support FM stakeholders in managing the level of uncertainty on expected service performances, mitigating related risks.

Francesco Rota

Papers

Topography of the Dolomites modulates range dynamics of narrow endemic plants under climate change

Industry 4.0 for failure information management within Proactive Maintenance

A New Risk Management Methodology for Infrastructure Based on Real-Time Monitoring and Dynamic Interventions: An Example Application on an Air Handling Unit

Proactive Maintenance Strategy Based on Resilience Empowerment for Complex Buildings

Dealing with Uncertainty in Facility Management (FM) Contracts Through a Data-Driven Approach