Supervisory Control Research Articles

Water and Thermal Management in PEM Fuel Cells Using Feasible Humidity Plots and Model Predictive Controllers

Water and thermal management are critical for the performance, efficiency and longevity of PEM fuel cells (PEMFCs). Effective water and thermal management require the design of control systems that can maintain the water balance and temperature at stable and optimal levels. In this paper, we consider a stack of PEM fuel cells integrated with a water recovery and cooling system. A mechanistic dynamic model is developed to be able to predict the water content and temperature in response to the fuel cell inputs. Water management uses a cascade arrangement of a supervisory Model Predictive Controller (MPC) and local anode and cathode PID humidity controllers to balance the membrane water content. Thermal management consists of a separate MPC controller to regulate the fuel stack temperature. One novelty of this work lies in identifying and utilizing the feasible region for the relative humidities of the anode and cathode when controlling the membrane water content. We introduce the feasible humidity plots (FHP) which define the feasible values for the anode and cathode relative humidities for a given fuel cell design and its operating conditions. This useful information helps to assign the set-point values to the local PID humidity controllers of the water management system. It is shown by simulations that the water and thermal management MPC controllers work in tandem and successfully track the desired set-point changes in humidity and temperature while rejecting external disturbances such as load changes. In addition, the control system is robust against modeling errors and possible model-plant mismatch introduced by fuel cell aging.

Adaptive Supervisory Control of Automated Manufacturing Systems With Unreliable Resources Based on Smart Switch Controllers

Adaptive Supervisory Control of Automated Manufacturing Systems With Unreliable Resources Based on Smart Switch Controllers

Heat pump and thermal energy storage: Influences of photovoltaic, the control strategy, and price assumptions on the optimal design

Combining heat pump, thermal energy storage, and photovoltaic is a common option to increase renewable energy usage in building energy systems. While research finds that optimal system design depends on the control, design guidelines neglect an influence of (1) photovoltaic, (2) the supervisory control, and (3) prices assumptions on the design of heat pump and thermal energy storage. We analyze how these influences may impact the optimal design. To analyze possible impacts, a pre-screening approach is used to identify relevant model input combinations with a potentially high influence on the optimal design. Applying a simulation-based design optimization with a detailed building energy system model, we optimize three cases: no photovoltaic, no supervisory control, and a state-of-the-art supervisory control. Results indicate that cost optimal design does not change with photovoltaic or the supervisory control, but heat pump size increases with higher electricity prices. For the storage, maximizing the size achieves high self-sufficiency degrees, but cost optimal design changes only for selected price assumptions. Overall, we find that neglecting photovoltaic and surplus control in the system design is a valid assumption. However, price assumptions should be included to allow simple but optimal design rules in current guidelines.

Design of an Advanced Optimal Fuzzy Controller For a Binary Distillation Column

The most common control philosophy followed in the chemical process industries is the SISO system using the conventional PID controller algorithms. One drawback is relying on models for both control and design work in Chemical process industries (CPI) is that many problems are very complex and accurate models are difficult, if not impossible to obtain. To overcome these problems, it will be helpful to apply techniques that use human judgment and experience rather than precise mathematical models, which in the major cases deduced from the linearization of the system and simplification hypothesis. The fuzzy logic systems are capable of handling complex, nonlinear systems using simple solutions. However, obtaining an optimal set of fuzzy membership functions is not an easy task. In this chapter a solution based on artificial intelligence is proposed to improve the control of a binary distillation column. The solution is based on the use of the advantages of both fuzzy logic and genetic algorithms. The fuzzy logic is used as a supervisory PI controller that is a simple PI controller that generally used in controlling distillation columns with parameters deduced from the fuzzy supervisor. The membership functions shape is deduced by using research algorithms based on hierarchical genetic algorithms. The results show that the Fuzzy supervisory PI controller provide an excellent tracking toward set point change.

Advancing predictive maintenance: a comprehensive case study through industry 4.0

The paper is focused on predictive maintenance in the automotive industry with a specialization in technologies related to Industry 4.0. The emergence of predictive maintenance with Industry 4.0 technologies is also called Maintenance 4.0. The article describes specific Industry 4.0 technologies, such as supervisory control and data acquisition (SCADA) and Predictive Maintenance (PdM), that are being implemented in manufacturing companies. The sample for the case study consisted of a paint shop from the automotive sector that operates in Turkey. In the data collection step, SCADA collected data from pressure sensors to create a historical database for PdM. The purpose of this article is to illustrate, through a case study, the importance of PdM using SCADA using Industry 4.0 instruments such as the Internet of Things and big data. 18 filters, which were replaced every 6 months during preventive maintenance, are now replaced at different intervals through PDM after this study. Based on SCADA data, a total of 2 filters experience blockage in both the primer and topcoat paint processes every 6 months. Over a 12-month period, an extra 9 filters are blocked across all processes. Furthermore, within a 24-month timeframe, a total of 7 more filters become blocked in the entirety of the operational processes. The results showed that the PdM combination increased the effectiveness of care by 45.83%.

Wind turbine foundation ring fatigue reliability analysis under wind-load using SCADA system

Under the action of wind load, the foundation ring of the fan will generate stress concentration and alternating stress, leading to fatigue failure. Based on the average wind speed obtained from the supervisory control and data acquisition (SCADA) system, the orthogonal expansion method of random pulsating wind field and the number theory point selection method are used to calculate and simulate the corresponding pulsating wind speed time series, and then calculate the wind speed time series and wind load time series. Based on the ABAQUS finite element software, a model of a 5 MW wind turbine is established. The modal analysis is used to obtain the modal vibration pattern and the intrinsic frequency to verify the reasonableness of the structural modeling. Subsequently, the wind load time series is applied to the wind turbine model to obtain the stress time series using instantaneous modal dynamic analysis (Modal dynamics). The stress time series at the location of maximum stress concentration in the foundation ring is extracted, and the stress time series with the same stress amplitude is obtained through conversion, which has Wiener characteristics. After obtaining the stress amplitude using the rainflow counting method, the fatigue reliability is calculated based on the structural fatigue reliability analysis method considering the threshold crossing duration of the random process. This research holds reference significance for the calculation of fatigue reliability under approximate working conditions.

Mobile robots control with neuromorphic classifires of environment states

The article proposes to implement mobile robots control systems using neuromorphic classifiers, in which biosimi-lar neurons are built on an original neuro-fuzzy model, trained to display the function of the Izhikevich neuron. Us-ing this approach, neuromorphic classifiers of spatial and spatiotemporal patterns were developed. Such a classi-fiers were used in non-contact supervisory control system for mobile robot based on static and dynamic states of the environment. The experiments performed demonstrated the effectiveness of using the neuromorphic classifi-ers, both in a neural interface when recognizing imaginary supervisory commands of the user, and when solving problems of robot navigation in environments with static and dynamic obstacles. At comparative analysis of navi-gation systems implemented using the neuromorphic classifiers, modular fuzzy logic and the adaptive neuro-fuzzy system ANFIS it was shown that the system with the neuromorphic classifiers give the highest average speed of the robot, as well as the shortest travel time. An experiment with the use of the neuromorphic classifiers in the con-trol system based on dynamic states of the environment showed that robot successfully avoids collisions with per-son.

A Comprehensive Review of SCADA-Based Wind Turbine Performance and Reliability Modeling with Machine Learning Approaches

The increasing reliance on wind energy to meet global energy demands has made wind turbine performance optimization and reliability a critical area of research. Supervisory Control and Data Acquisition (SCADA) data, which provides real-time operational insights into wind turbines, plays a pivotal role in predictive maintenance, fault detection, and energy output optimization. This review explores the current methodologies and advancements in wind turbine performance modeling and reliability analysis, with a particular emphasis on machine learning (ML) approaches. Existing studies that utilize SCADA data to implement various ML models, such as decision trees, neural networks, and ensemble learning techniques (bagging, boosting, stacking), are analyzed for their effectiveness in predicting turbine failures, improving energy efficiency, and optimizing maintenance schedules. Key findings from multiple studies are synthesized, highlighting the strengths, limitations, and real-world applications of these models. Challenges in data quality, model generalization, and the implementation of real-time ML-driven systems in wind farms are also addressed. This review aims to provide a comprehensive overview of the current state of SCADA-based wind turbine analysis and to offer a roadmap for future research that bridges the gap between data-driven models and their practical deployment in wind energy systems.

Maximum fault-free enforcement in Petri nets using supervisory control

Abstract Fault diagnosis and maximum fault-free execution are essential for the development and operation of computer-integrated systems covering aircraft systems, power grid systems, production processes, etc. This paper focuses on the problem of fault diagnosis and maximum fault-free enforcement of systems modeled by labelled Petri nets. Given a system modeled by a labelled Petri net that may enter deadlocks, an extended basis reachability graph that contains sufficient information to characterize deadlocks is used to compress the state space and verify the diagnosability for the considered system. Furthermore, the proposed graph offers sufficient and necessary conditions for fault-free enforcement and deadlock-free enforcement. Finally, a lock-free event set and a supervisor are designed for a system such that any possible fault or dead behaviour is prohibited in the controlled system.

Quality of Service-Aware Multi-Objective Enhanced Differential Evolution Optimization for Time Slotted Channel Hopping Scheduling in Heterogeneous Internet of Things Sensor Networks.

The emergence of the Internet of Things (IoT) has attracted significant attention in industrial environments. These applications necessitate meeting stringent latency and reliability standards. To address this, the IEEE 802.15.4e standard introduces a novel Medium Access Control (MAC) protocol called Time Slotted Channel Hopping (TSCH). Designing a centralized scheduling system that simultaneously achieves the required Quality of Service (QoS) is challenging due to the multi-objective optimization nature of the problem. This paper introduces a novel optimization algorithm, QoS-aware Multi-objective enhanced Differential Evolution optimization (QMDE), designed to handle the QoS metrics, such as delay and packet loss, across multiple services in heterogeneous networks while also achieving the anticipated service throughput. Through co-simulation between TSCH-SIM and Matlab, R2023a we conducted multiple simulations across diverse sensor network topologies and industrial QoS scenarios. The evaluation results illustrate that an optimal schedule generated by QMDE can effectively fulfill the QoS requirements of closed-loop supervisory control and condition monitoring industrial services in sensor networks from 16 to 100 nodes. Through extensive simulations and comparative evaluations against the Traffic-Aware Scheduling Algorithm (TASA), this study reveals the superior performance of QMDE, achieving significant enhancements in both Packet Delivery Ratio (PDR) and delay metrics.

Fault detection framework in wind turbine pitch systems using machine learning: Development, validation, and results

This work develops a methodology for detecting faults in wind turbines through supervised machine-learning classification methods focusing in two modes of operation. The Normal mode will be related to the regular operation of the wind turbines and in the case of the abnormal mode, the system will be cataloged as Pitch system failure. This methodology uses real data through the supervisory control and data acquisition (SCADA) system and the recording of events and actions (LOG alarm system). Sixteen classifications artificial intelligence (AI) models were tested, such as Random Forest Classifier (RF), Gradient Boosting Classifier (GBC), Extra Trees Classifier (ET), Extreme Gradient Boosting (XGBOOST), Light Gradient Boosting Machine (LIGHTGBM), Categorical Boosting Classifier (CATBOOST), Adaptative Boosting Classifier (ADA), Decision Tree Classifier (DT), Linear Discriminant Analysis (LDA), K-Nearest Neighbors Classifier (KNN), Logistic Regression (LR), Naive Bayes (NB), Quadratic Discriminant Analysis (QDA), Dummy Classifier (DC), Super vector machine (SVM), Ridge Classifier (RC). The training process model was carried out by structuring the dataset in 75% for training and validation and 25% for the final test, considering cross-validation and optimization of the hyperparameters. The Random Forest Classifier (RF) and Extra Trees Classifier (ET) classifiers models presented the best performances, and the models with the lowest performances were K-Nearest Neighbors Classifier (KNN) and Linear Discriminant Analysis (LDA) ones. The average hit effectiveness for both Healthy and Faulty operating modes was approximately 80% across most of the models developed.

Trust in Automation (TiA): Simulation Model, and Empirical Findings in Supervisory Control of Maritime Autonomous Surface Ships (MASS)

Over the past three decades, Trust in Automation (TiA) has been the subject of extensive research. However, a large portion of the research takes a “static” approach to modeling trust and views trust as a linear unidirectional phenomenon. This view fails to recognize that trust is a dynamic construct that changes over time as an outcome of prolonged interaction with automation. The present study aims to address this gap and explore the nonlinear dynamic nature of trust by developing a simulation model of Trust in Automation (TiA) that can demonstrate trust evolution, deterioration, and recovery within the context of supervisory control of Maritime Autonomous Surface Ships (MASS). Employing System Dynamics (SD) approach, the model captures trust’s non-linear and reciprocal nature through dynamic feedback loops, producing behavioral patterns consistent with empirical observations of trust. The simulation results showcase the crucial role of initial trust conditions and the alignment of expectations with system performance in fostering trust and effective automation use. The study also explores the timing of system malfunctions, revealing that early faults have a greater negative impact on trust compared to later faults of the same magnitude. We tested a segment of the proposed model in an experimental study involving 30 human participants to investigate the effects of automation malfunctions on operators’ trust and behavioral responses during the supervisory control of MASS. Results not only validated the proposed model but demonstrated a significant decline in perceived reliability and trust in automation as well as the monitoring strategy after the automation malfunction.

Intelligent Monitoring and Optimization of Wind Turbine Operation Status on Basis of Vibration Signals

In response to the large monitoring errors and incomplete consideration of fault locations in the operation status of wind turbines, this paper combined vibration signals and used a model constructed using nonlinear state estimation technology (NSET) to monitor and optimize the operation status of wind turbines. Firstly, it collected relevant SCADA (supervisory control and data acquisition) and vibration sensor data of Unit 5 of Guangdong Yangjiang Shaba Offshore Wind Farm on site, and used wavelet transform to denoise the vibration signal. Then, full consideration can be given to the faulty parts such as wind blades and gearboxes, and a model constructed by NSET using Markov distance to construct a process memory matrix can be used to monitor the status of the wind turbine equipment. Finally, the multi-level fuzzy comprehensive evaluation method can be used to optimize the comprehensive evaluation of the operating status of wind turbines, reducing monitoring errors.

Wind energy system fault classification using deep CNN and improved PSO‐tuned extreme gradient boosting

AbstractIntelligent fault diagnosis for wind energy systems requires identifying unique characteristics to differentiate various fault types effectively, even when data discrepancy occurs due to the unpredictable and dynamic nature of its environment. This article addresses some of the challenges of fault classification in wind energy systems by proposing an integrated approach that combines deep learning features with a resampled supervisory control and data acquisition (SCADA) dataset. The methodology involves resampling the imbalanced SCADA dataset using synthetic minority oversampling technique (SMOTE) and near‐miss undersampling techniques, extracting deep learning features using deep convolutional neural network, and feeding them into an XGBoost (extreme gradient boosting) classifier with tuned parameters using adaptive elite‐particle swarm optimization (AEPSO). The effectiveness of the proposed method is demonstrated through validation conducted on a different imbalanced dataset showing superior performance metrics in terms of accuracy. Additionally, the study contributes to methodological advancements in wind turbine fault diagnosis by providing a rigorous framework for fault classification. It is confirmed that utilizing the extracted deep learning features into the resampled data can significantly affect the classification performance metrics. Furthermore, the proposed integrated approach shows significance for fault diagnosis enhancement in wind energy systems and advancing the field towards more efficient and reliable operation.

Integrated Supervisory Control and Data Acquisition System for Optimized Energy Management: Leveraging Photovoltaic and Phase Change Material Thermal Storage

ABSTRACTReliable energy sources are crucial for both economic growth and quality of life. In developing countries, where expensive fuels are often the primary energy source, governments are exploring innovative solutions like small‐scale, IoT‐based projects to achieve energy independence in buildings. This research investigates the integration of renewable energy technologies, statistical modeling, cloud computing, and IoT to develop a self‐managing energy system for buildings. The system prioritizes renewable sources, specifically monocrystalline solar cells with 20% efficiency for photovoltaic (PV) energy and flat plate collectors with 90% efficiency and minimal energy loss for thermal energy. Thermal energy is stored in paraffin wax, chosen for its high storage efficiency and thermal properties. The system also utilizes an absorption chiller with a high coefficient of performance (COP) to provide cooling using solar thermal energy. The building's energy loads are categorized as A, B, C, and D, each utilizing both PV and thermal energy. A SCADA system oversees the operation, monitoring the on–off status of these loads. The system is designed for continuous operation, with simulations conducted using Anaconda Jupyter Notebook and Python. This model aims to offer a sustainable and efficient energy solution for buildings, meeting energy demands while optimizing energy use.

Energy efficiency evaluation of wind turbines based on entropy weight method and stacked autoencoder

Abstract To solve the problems of complex operating conditions of wind turbines and difficult to measure and evaluate energy efficiency, a quantitative evaluation method of energy efficiency of wind turbines based on the entropy weight method (EWM) and stacked automatic encoder (SAE) was proposed. Firstly, based on the Supervisory Control And Data Acquisition (SCADA) data of wind turbines, key evaluation indicators are extracted through preprocessing and feature extraction of wind turbine data. The EWM is used to determine the weights, and deep learning is combined with SAE to comprehensively obtain the energy efficiency value of wind turbines. Subsequently, the quartile method was used to determine the discrimination threshold for inefficient units, and the effectiveness of this method on SCADA data of a 5.5MW offshore wind farm was verified through numerical examples. The results show that this method can evaluate the energy efficiency level of wind turbines in real time and achieve 100% accuracy in identifying inefficient units, providing a reference for the maintenance and technical improvement of wind turbine energy efficiency performance.

Estimation and Prevention of Actuator Enablement Attacks in Discrete-Event Systems Under Supervisory Control

Estimation and Prevention of Actuator Enablement Attacks in Discrete-Event Systems Under Supervisory Control

Intelligent mission planning for autonomous distributed satellite systems

System autonomy plays a critical role in the success of next generation Distributed Satellite Systems (DSS) mission architectures, enabling the inference of external and internal environment conditions to support system adaptation in unexpected and unfamiliar situations. Artificial Intelligence (AI) based techniques show promise in achieving this desired self-adaptive capability by offering on-board predictive real time analytics, supporting an evolution towards Trusted Autonomous Satellite Operations (TASO). In parallel, TASO requires an evolution of the control and coordination of increasingly autonomous large scale DSS, achieved in the design and operation of intelligent Mission Planning Systems (MPS). In this paper, we focus on intelligent mission planning functionality problem utilising a distributed ant colony optimisation approach to achieve local task allocation and platform coordination. The approach is implemented in the context of a Space-Based Space Surveillance (SBSS) mission architecture that considers self-adaptive capabilities, global coordination and supervisory control aspects. The effectiveness of the approach is shown, demonstrating that the proposed solution based on metaheuristics supports an efficient and pervasive SBSS capability.

Degradation assessment of wind turbine based on additional load measurements

In recent years, there has been an increasing focus on the degradation assessment of wind turbines using supervisory control and data acquisition (SCADA) data, establishing condition monitoring as the preferred approach. However, SCADA data primarily focuses on general condition variables, such as temperature, while overlooking critical metrics like load factors for assessing the mechanical properties of wind turbines. The load parameters can be utilized to assess the mechanical stresses and strains experienced by wind turbine components, thereby offering more precise information on degradation. To address this gap, we explore the feasibility of implementing additional load monitoring for the degradation assessment of wind turbines. Specifically, we design a cost-effective load sensor system for collecting load data from wind turbines. On this basis, a novel degradation assessment method that incorporates additional load data and a nonlinear dynamic state-space neural network model is proposed to extract degradation information from wind turbines. Then, we introduce a dynamic degradation index, derived through trend analysis, which effectively captures and quantifies the degradation levels of wind turbines over time. Finally, a case study using a dataset collected from a real wind farm is provided to validate the proposed method. The results demonstrate a significant enhancement in degradation assessment. By incorporating additional load data, the proposed method exhibits heightened responsiveness to degradation levels and more effectively captures the progression of degradation trends.

The data recovery strategy on machine learning against false data injection attacks in power cyber physical systems

During the transmission of power measurement data through communication networks from remote terminal unit (RTU) to the state estimator in Supervisory Control and Data Acquisition (SCADA), power cyber-physical systems (PCPSs) are more susceptible to cyber-attacks. To mitigate that threat, this paper is concerned with a new data recovery strategy on machine learning against false data injection attacks (FDIAs) in PCPSs. Firstly, in view of the limited resources (such as limited energy) of adversaries and system protections, a sparse target false data injection attack (FDIA) is constructed. Then, the FDIA detection problem is transformed into a tripartite separation problem, and the alternating direction method of multipliers on proximal exchange (ADMM-PE) is adopted to complete the intrusion detection of FDIAs. In addition, with the help of reliable mask information and real incomplete measurement data provided by the FDIA detection, a similar supervised generative adversarial imputation networks (GAIN) is proposed to complete the measurement data recovery after FDIAs. Specifically, the pseudo labels generated by data analysis methods such as k-means clustering and support vector machine (SVM) to improve the accuracy of measurement data recovery. Finally, the experimental results of PCPSs show the effectiveness and superiority of the proposed data recovery strategy against FDIAs.