With the tremendous revival of artificial intelligence, predictive maintenance (PdM) based on data-driven methods has become the most effective solution to address smart manufacturing and industrial big data, especially for performing health perception (e.g., fault diagnosis and remaining life assessment). Moreover, because the existing PdM research is still in primary experimental stage, most works are conducted utilizing several open-datasets, and the combination with specific applications such as rotating machinery is especially rare. Hence, in this paper, we focus on data-driven methods for PdM, present a comprehensive survey on its applications, and attempt to provide graduate students, companies, and institutions with the preliminary understanding of the existing works recently published. Specifically, we first briefly introduce the PdM approach, illustrate our PdM scheme for automatic washing equipment , and demonstrate the challenges encountered when we conduct a PdM research. Second, we classify the specific industrial applications based on six algorithms of machine learning and deep learning (DL), and compare five performance metrics for each classification. Furthermore, the accuracy (a metric to evaluate the algorithm performance) of these PdM applications is analyzed in detail. There are some important conclusions: 1) the data used in the summarized literature are mostly from public datasets, such as case western reserve university (CWRU)/intelligent maintenance systems (IMS); and 2) in recent years, researchers seem to focus more on DL algorithms for PdM research. Finally, we summarize the common features regarding our surveyed PdM applications and discuss several potential directions.

Data-Driven Methods for Predictive Maintenance of Industrial Equipment: A Survey

Resilience to disruptions and sustainability are both of paramount importance to supply chains. However, the interactions between the two have not been thoroughly explored in the academic literatur...

Resilient and sustainable supply chain design: sustainability analysis under disruption risks

Electric vehicles (EVs) have been popularly adopted and deployed over the past few years because they are environment-friendly. When integrated into smart grids, EVs can operate as flexible loads or energy storage devices to participate in demand response (DR). By taking advantage of time-varying electricity prices in DR, the charging cost can be reduced by optimizing the charging/discharging schedules. However, since there exists randomness in the arrival and departure time of an EV and the electricity price, it is difficult to determine the optimal charging/discharging schedules to guarantee that the EV is fully charged upon departure. To address this issue, we formulate the EV charging/discharging scheduling problem as a constrained Markov Decision Process (CMDP). The aim is to find a constrained charging/discharging scheduling strategy to minimize the charging cost as well as guarantee the EV can be fully charged. To solve the CMDP, a model-free approach based on safe deep reinforcement learning (SDRL) is proposed. The proposed approach does not require any domain knowledge about the randomness. It directly learns to generate the constrained optimal charging/discharging schedules with a deep neural network (DNN). Unlike existing reinforcement learning (RL) or deep RL (DRL) paradigms, the proposed approach does not need to manually design a penalty term or tune a penalty coefficient. Numerical experiments with real-world electricity prices demonstrate the effectiveness of the proposed approach.

Constrained EV Charging Scheduling Based on Safe Deep Reinforcement Learning

Efficiency and effectiveness in the urban public transport sector: A critical review with directions for future research

The increased rate of cyber-attacks on the power system necessitates the need for innovative solutions to ensure its resiliency. This work builds on the advancement in the IoT to provide a practical framework that is able to respond to multiple attacks on a network of interconnected microgrids. This paper provides an IoT-based digital twin (DT) of the cyber-physical system that interacts with the control system to ensure its proper operation. The IoT cloud provision of the energy cyber-physical and the DT are mathematically formulated. Unlike other cybersecurity frameworks in the literature, the proposed one can mitigate an individual as well as coordinated attacks. The framework is tested on a distributed control system and the security measures are implemented using cloud computing. The physical controllers are implemented using single-board computers. The practical results show that the proposed DT is able to mitigate the coordinated false data injection and the denial of service cyber-attacks.

On the Implementation of IoT-Based Digital Twin for Networked Microgrids Resiliency Against Cyber Attacks

The increasing deployment of electric vehicles (EVs) across the United States has introduced many new opportunities and challenges with regards to energy management and control. In smart and connected communities (SCCs), where advanced communication infrastructures are in place, optimal coordination of EVs can significantly impact EV owners, power systems, and charging station owners. This paper develops two scheduling frameworks (static and dynamic) for optimal coordination of a fleet of cooperative EVs in a community with many charging stations and potentially different types of chargers (e.g., level 1, level 2, and DC fast). The scheduling problems are formulated as mixed-integer multi-objective optimization models and then multi-objective solution methods are utilized to find the optimal solution for each of the two scheduling frameworks. Numerical experiments simulated based on the State of Florida verify the usefulness of smart charging for better energy management and satisfying key players’ objectives and constraints.

Smart Control of Fleets of Electric Vehicles in Smart and Connected Communities

A Deep Reinforcement Learning Approach for Real-time Sensor-Driven Decision Making and Predictive Analytics

Scheduling of transit networks is one of the most addressed problems in the mathematical optimization science, due to the increase of public transportation in the last decade. Researchers have introduced various formulations to address the problem of timetabling, using different objectives like bus synchronization and passenger demand. In this paper, we present a mixed-integer linear programming formulation with the objective of minimizing passenger waiting times at transitional transfer nodes, taking also into consideration high passenger demand that occurs at certain times.

Minimizing waiting times at transitional nodes for public bus transportation in Greece

We present a new model for reliability analysis that is able to employ condition monitoring data in order to simultaneously monitor the latent degradation level and track failure progress over time. The method presented in this paper is a bridge between Bayesian filtering and classical binary classification, both of which have been employed successfully in various application domains. The Kalman filter is used to model a discrete-time continuous-state degradation process that is hidden and for which only indirect information is available through a multi-dimensional observation process. Logistic regression is then used to connect the latent degradation state with the failure process that is itself a discrete-space stochastic process. We present a closed-form solution for the marginal log-likelihood function and provide formulas for few important reliability measures. A dynamic cost-effective maintenance policy is finally introduced that can employ sensor signals for real-time decision-making. We finally de...

A condition monitoring approach for real-time monitoring of degrading systems using Kalman filter and logistic regression

Scheduling of transit networks is one of the most addressed problems at the mathematical optimization science, due to the increase of public transportation in the last decade. Researchers have introduced various formulations to address the problem of timetabling, using different objectives like bus synchronization and passenger demand. In this paper we present two mixed-integer linear programming models with the objective of minimizing passenger waiting times at transitional transfer nodes, taking into consideration high passenger demand that occurs at certain times.

Erotokritos Skordilis

Papers

Smart Control of Fleets of Electric Vehicles in Smart and Connected Communities

A Deep Reinforcement Learning Approach for Real-time Sensor-Driven Decision Making and Predictive Analytics

Minimizing waiting times at transitional nodes for public bus transportation in Greece

A condition monitoring approach for real-time monitoring of degrading systems using Kalman filter and logistic regression

Minimizing Waiting Times at Transitional Nodes for Public Bus Transportation in Greece