Learning-Based Control of Autonomous Vehicles Using an Adaptive Neuro-Fuzzy Inference System and the Linear Matrix Inequality Approach.

This paper proposes a learning-based control approach for autonomous vehicles. An explicit Takagi-Sugeno (TS) controller is learned using input and output data from a preexisting controller, employing the Adaptive Neuro-Fuzzy Inference System (ANFIS) algorithm. At the same time, the vehicle model is identified in the TS model form for closed-loop stability assessment using Lyapunov theory and LMIs. The proposed approach is applied to learn the control law from an MPC controller, thus avoiding the use of online optimization. This reduces the computational burden of the control loop and facilitates real-time implementation. Finally, the proposed approach is assessed through simulation using a small-scale autonomous racing car.

Advances in the Monitoring, Diagnosis and Optimisation of Water Systems.

In the context of global climate change, with the increasing frequency and severity of extreme events-such as draughts and floods-which will likely make water demand more uncertain and jeopardise its availability, those in charge of water system management face new operational challenges because of increasing resource scarcity, intensive energy requirements, growing populations (especially in urban areas), costly and ageing infrastructures, increasingly stringent regulations, and rising attention towards the environmental impact of water use [...].

Recursive zonotopic set-membership approach for system-level prognostics with application to linear parameter-varying systems.

A robust recursive zonotopic set-membership approach for remaining useful life forecasting with application to linear parameter-varying systems is proposed in this paper. The proposed approach addresses systems with degraded components formulated as a system-level prognostics problem. Thus, the critical degraded components of the system are augmented to the states resulting a nonlinear system that is reformulated as a linear parameter-varying model. Hence, joint estimation of states and parameters is adopted in a zonotopic set-membership scheme with an optimal linear matrix inequality-based tuning and assuming unknown-but-bounded noises and uncertainties. As a result, a recursive zonotopic set-membership approach is proposed for remaining useful life forecasting based on the prediction of the failure precursors of degraded systems. Finally, this approach is tested on a DC-DC converter case study with unknown degradation behaviors, and the obtained results show the estimation and the forecasting accuracy of this methodology.

Kinematic/Dynamic SLAM for Autonomous Vehicles Using the Linear Parameter Varying Approach.

Most existing algorithms in mobile robotics consider a kinematic robot model for the the Simultaneous Localization and Mapping (SLAM) problem. However, in the case of autonomous vehicles, because of the increase in the mass and velocities, a kinematic model is not enough to characterize some physical effects as, e.g., the slip angle. For this reason, when applying SLAM to autonomous vehicles, the model used should be augmented considering both kinematic and dynamic behaviours. The inclusion of dynamic behaviour implies that nonlinearities of the vehicle model are most important. For this reason, classical observation techniques based on the the linearization of the system model around the operation point, such as the well known Extended Kalman Filter (EKF), should be improved. Consequently, new techniques of advanced control must be introduced to more efficiently treat the nonlinearities of the involved models. The Linear Parameter Varying (LPV) technique allows working with nonlinear models, making a pseudolinear representation, and establishing systematic methodologies to design state estimation schemes applying several specifications. In recent years, it has been proved in many applications that this advanced technique is very useful in real applications, and it has been already implemented in a wide variety of application fields. In this article, we present a SLAM-based localization system for an autonomous vehicle considering the dynamic behaviour using LPV techniques. Comparison results are provided to show how our proposal outperforms classical observation techniques based on model linearization.

LPV Control and Virtual-Sensor-Based Fault Tolerant Strategies for a Three-Axis Gimbal System.

This paper deals with the LPV control of a three-axis gimbal including fault-tolerant capabilities. First, the derivation of an analytical model for the considered system based on the robotics Serial-Link (SL) theory is derived. Then, a series of simplifications that allow obtaining a quasi-LPV model for the considered gimbal is proposed. Gain scheduling LPV controllers with PID structure are designed using pole placement by means of linear matrix inequalities (LMIs). Moreover, exploiting the sensor redundancy available in the gimbal, a virtual-sensor-based fault tolerant control (FTC) strategy is proposed. This virtual sensor uses a Recursive Least Square (RLS) estimation algorithm and an LPV observer for fault detection and estimation. Finally, the proposed LPV control scheme including the virtual sensor strategy is tested in simulation in several scenarios.

Economic Linear Parameter Varying Model Predictive Control of the Aeration System of a Wastewater Treatment Plant.

This work proposes an economic model predictive control (EMPC) strategy in the linear parameter varying (LPV) framework for the control of dissolved oxygen concentrations in the aerated reactors of a wastewater treatment plant (WWTP). A reduced model of the complex nonlinear plant is represented in a quasi-linear parameter varying (qLPV) form to reduce computational burden, enabling the real-time operation. To facilitate the formulation of the time-varying parameters which are functions of system states, as well as for feedback control purposes, a moving horizon estimator (MHE) that uses the qLPV WWTP model is proposed. The control strategy is investigated and evaluated based on the ASM1 simulation benchmark for performance assessment. The obtained results applying the EMPC strategy for the control of the aeration system in the WWTP of Girona (Spain) show its effectiveness.

Zonotopic Linear Parameter Varying SLAM Applied to Autonomous Vehicles.

This article presents an approach to address the problem of localisation within the autonomous driving framework. In particular, this work takes advantage of the properties of polytopic Linear Parameter Varying (LPV) systems and set-based methodologies applied to Kalman filters to precisely locate both a set of landmarks and the vehicle itself. Using these techniques, we present an alternative approach to localisation algorithms that relies on the use of zonotopes to provide a guaranteed estimation of the states of the vehicle and its surroundings, which does not depend on any assumption of the noise nature other than its limits. LPV theory is used to model the dynamics of the vehicle and implement both an LPV-model predictive controller and a Zonotopic Kalman filter that allow localisation and navigation of the robot. The control and estimation scheme is validated in simulation using the Robotic Operating System (ROS) framework, where its effectiveness is demonstrated.

Autonomous Vehicle State Estimation and Mapping Using Takagi-Sugeno Modeling Approach.

This paper proposes an optimal approach for state estimation based on the Takagi-Sugeno (TS) Kalman filter using measurement sensors and rough pose obtained from LIDAR scan end-points matching. To obtain stable and optimal TS Kalman gain for estimator design, a linear matrix inequality (LMI) is optimized which is constructed from Lyapunov stability criteria and dual linear quadratic regulator (LQR). The technique utilizes a Takagi-Sugeno (TS) representation of the system, which allows modeling the complex nonlinear dynamics in such a way that linearization is not required for the estimator or controller design. In addition, the TS fuzzy representation is exploited to obtain a real-time Kalman gain, avoiding the expensive optimization of LMIs at every step. The estimation schema is integrated with a nonlinear model-predictive control (NMPC) that is in charge of controlling the vehicle. For the demonstration, the approach is tested in the simulation, and for practical validity, a small-scale autonomous car is used.

Comparison of Optimisation Algorithms for Centralised Anaerobic Co-Digestion in a Real River Basin Case Study in Catalonia.

Anaerobic digestion (AnD) is a process that allows the conversion of organic waste into a source of energy such as biogas, introducing sustainability and circular economy in waste treatment. AnD is an intricate process because of multiple parameters involved, and its complexity increases when the wastes are from different types of generators. In this case, a key point to achieve good performance is optimisation methods. Currently, many tools have been developed to optimise a single AnD plant. However, the study of a network of AnD plants and multiple waste generators, all in different locations, remains unexplored. This novel approach requires the use of optimisation methodologies with the capacity to deal with a highly complex combinatorial problem. This paper proposes and compares the use of three evolutionary algorithms: ant colony optimisation (ACO), genetic algorithm (GA) and particle swarm optimisation (PSO), which are especially suited for this type of application. The algorithms successfully solve the problem, using an objective function that includes terms related to quality and logistics. Their application to a real case study in Catalonia (Spain) shows their usefulness (ACO and GA to achieve maximum biogas production and PSO for safer operation conditions) for AnD facilities.

Water Quality Indicator Interval Prediction in Wastewater Treatment Process Based on the Improved BES-LSSVM Algorithm.

This paper proposes a novel interval prediction method for effluent water quality indicators (including biochemical oxygen demand (BOD) and ammonia nitrogen (NH3-N)), which are key performance indices in the water quality monitoring and control of a wastewater treatment plant. Firstly, the effluent data regarding BOD/NH3-N and their necessary auxiliary variables are collected. After some basic data pre-processing techniques, the key indicators with high correlation degrees of BOD and NH3-N are analyzed and selected based on a gray correlation analysis algorithm. Next, an improved IBES-LSSVM algorithm is designed to predict the BOD/NH3-N effluent data of a wastewater treatment plant. This algorithm relies on an improved bald eagle search (IBES) optimization algorithm that is used to find the optimal parameters of least squares support vector machine (LSSVM). Then, an interval estimation method is used to analyze the uncertainty of the optimized LSSVM model. Finally, the experimental results demonstrate that the proposed approach can obtain high prediction accuracy, with reduced computational time and an easy calculation process, in predicting effluent water quality parameters compared with other existing algorithms.

Pressure Sensor Placement for Leak Localization in Water Distribution Networks Using Information Theory.

This paper presents a method for optimal pressure sensor placement in water distribution networks using information theory. The criterion for selecting the network nodes where to place the pressure sensors was that they provide the most useful information for locating leaks in the network. Considering that the node pressures measured by the sensors can be correlated (mutual information), a subset of sensor nodes in the network was chosen. The relevance of information was maximized, and information redundancy was minimized simultaneously. The selection of the nodes where to place the sensors was performed on datasets of pressure changes caused by multiple leak scenarios, which were synthetically generated by simulation using the EPANET software application. In order to select the optimal subset of nodes, the candidate nodes were ranked using a heuristic algorithm with quadratic computational cost, which made it time-efficient compared to other sensor placement algorithms. The sensor placement algorithm was implemented in MATLAB and tested on the Hanoi network. It was verified by exhaustive analysis that the selected nodes were the best combination to place the sensors and detect leaks.

Set-membership-based distributed moving horizon estimation of large-scale systems.

This work is concerned with the design of a two-step distributed state estimation scheme for large-scale systems in the presence of unknown-but-bounded disturbances and noise. The set-membership approach is employed to construct a compact set containing the states consistent with system measurements and bounded noise and disturbances. The tightened feasible region is then provided to a moving horizon estimator that determines the optimal state estimates. Partitioning of the overall problem and coordination of the resulting subproblems are achieved using decomposition of the optimality conditions and community detection. The proposed strategy is tested on a case study based on a reactor-separator system widely used in the literature. Its performance is compared to those of centralized and distributed (without set-membership) implementations, allowing to highlight its effectiveness.

A Hybrid Automata Approach for Monitoring the Patient in the Loop in Artificial Pancreas Systems.

The use of automated insulin delivery systems has become a reality for people with type 1 diabetes (T1D), with several hybrid systems already on the market. One of the particularities of this technology is that the patient is in the loop. People with T1D are the plant to control and also a plant operator, because they may have to provide information to the control loop. The most immediate information provided by patients that affects performance and safety are the announcement of meals and exercise. Therefore, to ensure safety and performance, the human factor impact needs to be addressed by designing fault monitoring strategies. In this paper, a monitoring system is developed to diagnose potential patient modes and faults. The monitoring system is based on the residual generation of a bank of observers. To that aim, a linear parameter varying (LPV) polytopic representation of the system is adopted and a bank of Kalman filters is designed using linear matrix inequalities (LMI). The system uncertainty is propagated using a zonotopic-set representation, which allows determining confidence bounds for each of the observer outputs and residuals. For the detection of modes, a hybrid automaton model is generated and diagnosis is performed by interpreting the events and transitions within the automaton. The developed system is tested in simulation, showing the potential benefits of using the proposed approach for artificial pancreas systems.

Control-oriented quality modelling approach of sewer networks.

A control-oriented quality modeling approach is proposed for sewer networks, which can represent quality dynamics using simple equations in order to optimize pollution load from combined sewer overflows in large scale sewer network in real time. Total suspended solid has been selected as the quality indicator, regarding it is easy to be estimated through measuring turbidity and correlated with other quality indicators. The model equations are independent for different elements in sewer network, which allows a scalable usage. In order to ensure accuracy of the proposed models, a calibration procedure and a sensitivity analysis have been presented using data generated by virtual reality simulation. Afterwards, a quality-based model predictive control has been developed based on the proposed models. To validate effectiveness and efficiency of the modelling and optimization approaches, a pilot case, based on the Badalona sewer network in Spain is used. Application results under different scenarios show that the control-oriented modelling approach works properly to cope with quality dynamics in sewers. The quality-based optimization approach can provide strategies in reducing pollution loads in real time.

Health-aware control design based on remaining useful life estimation for autonomous racing vehicle.

The accurate estimation of the State of Charge (SOC) and an acceptable prediction of the Remaining Useful Life (RUL) of batteries in autonomous vehicles are essential for safe and lifetime optimized operation. The estimation of the expected RUL is quite helpful to reduce maintenance cost, safety hazards, and operational downtime. This paper proposes an innovative health-aware control approach for autonomous racing vehicles to simultaneously control it to the driving limits and to follow the desired path based on maximization of the battery RUL. To deal with the non-linear behavior of the vehicle, a Linear Parameter Varying (LPV) model is developed. Based on this model, a robust controller is designed and synthesized by means of the Linear Matrix Inequality (LMI) approach, where the general objective is to maximize progress on the track subject to win racing and saving energy. The main contribution of the paper consists in preserving the lifetime of battery and optimizing a lap time to achieve the best path of a racing vehicle. The control design is divided into two layers with different time scale, path planner and controller. The first optimization problem is related to the path planner where the objective is to optimize the lap time and to maximize the battery RUL to obtain the best trajectory under the constraints of the circuit. The proposed approach is formulated as an optimal on-line robust LMI based Model Predictive Control (MPC) that steered from Lyapunov stability. The second part is focused on a controller gain synthesis solved by LPV based on Linear Quadratic Regulator (LPV-LQR) problem in LMI formulation with integral action for tracking the trajectory. The proposed approach is evaluated in simulation and results show the effectiveness of the proposed planner for optimizing the lap time and especially for maximizing the battery RUL.

Factors influencing the stormwater quality model of sewer networks and a case study of Louis Fargue urban catchment in Bordeaux, France.

Pollution caused by combined sewer overflows has become a global threat to the environment. Under this challenge, quality-based real-time control (RTC) is considered as an effective approach to minimize pollution through generating optimal operation strategies for the sewer infrastructure. To suit the fast computation requirement of RTC implementation, simplified quality models are required. However, due to the hydrological complexity, it is not easy to develop simplified quality models which are amenable to be used in real-time computations. Under this context, this paper contributes a preliminary analysis of influencing factors for the quality models of sewer networks in order to give supportive knowledge for both model development and application. Conceptual quality models which were proposed previously by the authors, with total suspended solids (TSS) as quality indicator, are used in this study. A clustering algorithm is used for exploratory analysis. Further analysis about the correlations between different factors and model performance is also carried out. The study and analysis are demonstrated on a real pilot based on the Louis Fargue urban catchment in Bordeaux. Conclusive results about the influencing factors, flow rate, rain intensity and pipe length, as well as their correlations with the TSS models are elaborated.

Integrated pollution-based real-time control of sanitation systems.

An integrated pollution-based real-time control (RTC) approach is proposed for a sewer network (SN) integrated with wastewater treatment plants (WWTPs) in a sanitation system (SS) to mitigate the impacts of pollution from combined sewer overflows (CSOs) on ecosystems. To obtain the optimal solution for the SS while considering both quantity and quality dynamics for multiple objectives, model predictive control (MPC) is selected as the optimal control method. To integrate SN and WWTP management, a feedback coordination algorithm is developed. A closed-loop virtual-reality simulator is used to assess the results of the optimal management approach achieved by applying MPC. The Badalona SS (Spain) provides a pilot case study to assess the efficacy and applicability of the proposed approach. A comparison with local rule-based and volume-based control strategies currently in use indicates that the proposed integrated pollution-based RTC approach can reduce the pollutant loads released to the receiving environment.

Prognosis of Water Quality Sensors Using Advanced Data Analytics: Application to the Barcelona Drinking Water Network.

Water Utilities (WU) are responsible for supplying water for residential, commercial and industrial use guaranteeing the sanitary and quality standards established by different regulations. To assure the satisfaction of such standards a set of quality sensors that monitor continuously the Water Distribution System (WDS) are used. Unfortunately, those sensors require continuous maintenance in order to guarantee their right and reliable operation. In order to program the maintenance of those sensors taking into account the health state of the sensor, a prognosis system should be deployed. Moreover, before proceeding with the prognosis of the sensors, the data provided with those sensors should be validated using data from other sensors and models. This paper provides an advanced data analytics framework that will allow us to diagnose water quality sensor faults and to detect water quality events. Moreover, a data-driven prognosis module will be able to assess the sensitivity degradation of the chlorine sensors estimating the remaining useful life (RUL), taking into account uncertainty quantification, that allows us to program the maintenance actions based on the state of health of sensors instead on a regular basis. The fault and event detection module is based on a methodology that combines time and spatial models obtained from historical data that are integrated with a discrete-event system and are able to distinguish between a quality event or a sensor fault. The prognosis module analyses the quality sensor time series forecasting the degradation and therefore providing a predictive maintenance plan avoiding unsafe situations in the WDS.

Gain-scheduling multivariable LPV control of an irrigation canal system.

The purpose of this paper is to present a multivariable linear parameter varying (LPV) controller with a gain scheduling Smith Predictor (SP) scheme applicable to open-flow canal systems. This LPV controller based on SP is designed taking into account the uncertainty in the estimation of delay and the variation of plant parameters according to the operating point. This new methodology can be applied to a class of delay systems that can be represented by a set of models that can be factorized into a rational multivariable model in series with left/right diagonal (multiple) delays, such as, the case of irrigation canals. A multiple pool canal system is used to test and validate the proposed control approach.

Optimal sensor placement for leak location in water distribution networks using genetic algorithms.

This paper proposes a new sensor placement approach for leak location in water distribution networks (WDNs). The sensor placement problem is formulated as an integer optimization problem. The optimization criterion consists in minimizing the number of non-isolable leaks according to the isolability criteria introduced. Because of the large size and non-linear integer nature of the resulting optimization problem, genetic algorithms (GAs) are used as the solution approach. The obtained results are compared with a semi-exhaustive search method with higher computational effort, proving that GA allows one to find near-optimal solutions with less computational load. Moreover, three ways of increasing the robustness of the GA-based sensor placement method have been proposed using a time horizon analysis, a distance-based scoring and considering different leaks sizes. A great advantage of the proposed methodology is that it does not depend on the isolation method chosen by the user, as long as it is based on leak sensitivity analysis. Experiments in two networks allow us to evaluate the performance of the proposed approach.