In this paper, we present a decision support tool to optimize two of the most critical activities in intermodal railroad container terminals, in an iterative and integrated framework devoted to the terminal profit improvement. First, the model allows optimizing the freight trains composition, maximizing the company profit, while respecting physical and economic constraints, and placing in the train head/tail containers prosecuting to subsequent destinations. Hence, based on the resulting train composition, the decision support system allows optimizing the containers allocation in the terminal storage yard, in order to maximize the filling level while respecting physical constraints. The model is successfully tested on a real case study, the inland railroad terminal of a leading Italian intermodal logistics company.

This paper considers the non-convex Economic Dispatch Problem (EDP) with power losses, prohibited operating zones, and generation cost functions modeling both valve-point loading effects and multiple fuel options. This constrained problem is stated as an unconstrained problem by using the augmented Lagrange formulation, while introducing Lagrange multipliers and penalty parameters. Then, a genetic algorithm (GA) relying on two iterative loops is described: the inner loop executes a GA with fixed penalty parameters and Lagrange multipliers, while the outer loop updates such parameters when required. The effects of four different mutation operators based on the Gaussian and Cauchy distributions is also investigated. Finally, the effectiveness of the proposed approach is shown by numerical simulations on two practical test systems.

This paper focuses on modelling and performance evaluation of an Intermodal Freight Transport Terminal (IFTT), the rail-road inland terminal of a leading Italian intermodal logistics company. The IFTT is regarded as a discrete event system and is modelled in a timed Petri net framework. By means of suitable performance indices, we simulate the Petri net model and evaluate the operational performance of the transport system. This allows assessing the efficiency level of the terminal and identifying its criticalities and bottlenecks. Further, the model allows evaluating different solutions to the recognized criticalities under alternative scenarios (e.g., when inflow traffic increases and congestions may occur).

In this paper we present a decision support scheme to help managing and optimizing two critical activities in intermodal terminals, namely the containers allocation in the terminal yard and the freight trains composition. In particular, the focus of this paper is on the first problem and the goal is that of maximizing the utilization of the available space while keeping into account several constraints. The approach was successfully tested on a real case study, the rail-road terminal of a leading intermodal logistics company.

This paper presents a distributed algorithm based on auction techniques and consensus protocols to solve the nonconvex economic dispatch problem. The optimization problem of the nonconvex economic dispatch includes several constraints such as valve-point loading effect, multiple fuel option, and prohibited operating zones. Each generating unit locally evaluates quantities used as bids in the auction mechanism. These units send their bids to their neighbors in a communication graph that supports the power system and which provides the required information flow. A consensus procedure is used to share the bids among the network agents and resolves the auction. As a result, the power distribution of generating units is updated and the generation cost is minimized. The effectiveness of this approach is demonstrated by simulations on standard test systems.

Despite the emerging positive trend of rail freight transport, especially in intermodal contexts, the optimization of intermodal terminals is addressed only by few studies and mainly for seaport terminals. This paper fills this gap presenting a train load1 planning optimization model for intermodal rail-road terminals. The proposed model maximizes the train commercial value while respecting priority, physical, financial, and prosecution constraints (i.e., taking into account containers that prosecute to a subsequent terminal after the train destination). The presented method has been successfully tested on a real case study - the rail-road terminal of an Italian intermodal logistics company that is a leader in the European market - showing its effectiveness and ease of application.

This paper describes a control system for a tubular synchronous linear motor based on a combination of a linear PID controller and a nonlinear neural network. The nonlinear part of the controller is introduced to progressively augment the tracking performance of the system and is trained online by a compact GA. We implement a variant of a known compact GA that well lends itself to practical implementations in low capacity microcontrollers, thanks to its reduced memory requirements and better distributed computational loads. The potential of the proposed approach is assessed by means of a simulation study on a detailed model of a linear motor. The control system obtained through genetic search outperforms alternative schemes obtained with linear design techniques.

This paper considers the problem of coordinating the production and distribution activities of a network of independent supply centers. In particular, we focus on the supply of rapidly perishable goods (ready-mixed concrete) that must be delivered to customers in strict time windows. The problem presents three main challenges. First, it includes several interrelated scheduling and routing problems, each affected by nearly prohibitive combinatorial complexity. Second, due to the perishable nature of the supplied products, effective solutions must not only optimize the objective function related to resource utilization and cost minimization, but also tolerate the small and frequent stochastic perturbations (transport delays) of the operating environment. Third, if major perturbations occur, the decision strategy must be able to respond in real time with effective rescheduling interventions restoring the indispensable synchronization of activities in progress, and avoiding extremely undesirable circumstances related to product decay. After providing a detailed mathematical model of the considered problem, this paper proposes a hybrid metaheuristic approach integrating a genetic algorithm with a number of problem-specific constructive heuristics. The effectiveness of the approach is evaluated against other scheduling heuristics on an industrial case study.

This paper uses a novel discrete-event controller (DEC) for the coordination of cooperating heterogeneous wireless sensor networks (WSNs) containing both unattended ground sensors (UGSs) and mobile sensor robots. The DEC sequences the most suitable tasks for each agent and assigns sensor resources according to the current perception of the environment. A matrix formulation makes this DEC particularly useful for WSN, where missions change and sensor agents may be added or may fail. WSN have peculiarities that complicate their supervisory control. Therefore, this paper introduces several new tools for DEC design and operation, including methods for generating the required supervisory matrices based on mission planning, methods for modifying the matrices in the event of failed nodes, or nodes entering the network, and a novel dynamic priority assignment weighting approach for selecting the most appropriate and useful sensors for a given mission task. The resulting DEC represents a complete dynamical description of the WSN system, which allows a fast programming of deployable WSN, a computer simulation analysis, and an efficient implementation. The DEC is actually implemented on an experimental wireless-sensor-network prototyping system. Both simulation and experimental results are presented to show the effectiveness and versatility of the developed control architecture.

This paper proposes a hybrid approach for the design of adaptive fuzzy controllers (FCs) in which two learning algorithms with different characteristics are merged together to obtain an improved method. The approach combines a genetic algorithm (GA), devised to optimize all the configuration parameters of the FC, including the number of membership functions and rules, and a Lyapunov-based adaptation law performing a local tuning of the output singletons of the controller, and guaranteeing the stability of each new controller investigated by the GA. The effectiveness of the proposed method is confirmed using both numerical simulations on a known case study and experiments on a nonlinear hardware benchmark.

This paper describes an algorithm based on fuzzy logic for the real-time detection and removal of impulsive spike noise from measures of track geometry in railway infrastructures. Spike noise is caused by random events, including anomalous reflections of external lights, detection or transmission errors within the measuring systems, and singular parts of tracks (switches, level crossings) hiding the rail profile. Its effects are extremely undesirable because they can generate erroneous alerts about inexistent railway defects. The real-time detection of spike noise is generally difficult, as the inspected tracks have extremely variable characteristics, and the measurement is performed in dynamic and turbulent conditions. By incorporating in a fuzzy system the typical rules used for offline analysis of the measured data, we develop a filtering algorithm that is able to perform spike removal in real time. Moreover, we also propose a variant of the fuzzy filter that improves the reconstruction of the corrupted measures. The proposed algorithm is validated on an extensive set of experimental investigations, which include a comparison with other algorithms selected from recent literature. The results confirm the effectiveness of the filtering algorithm, which has been recently implemented on some measuring vehicles for high-speed lines

This paper describes an intelligent optical sensor for real time defect detection in gas metal arc welding processes. The sensor measures the radiations emitted by the plasma surrounding the welding arc, and analyzes the information in real time to determine an index of local quality of the weld. The data processing algorithm encompasses a Kalman filter to reduce the heavy amount of noise affecting the measured signals, and an intelligent fuzzy system to assess the degree of acceptability of the weld. The fuzzy system is also able to detect the risk of specific problems (e.g., anomalies in the current, voltage or speed of the arc, contamination with other materials, holes) and the position of defects along the welding line. In an extensive experimental comparison, the fuzzy system outperforms a former version of the detection algorithm based on a statistical approach.

In many manufacturing environments, automated guided vehicles are used to move the processed materials between various pickup and delivery points. The assignment of vehicles to unit loads is a complex problem that is often solved in real-time with simple dispatching rules. This paper proposes an automated guided vehicles dispatching approach based on computational intelligence. We adopt a fuzzy multicriteria decision strategy to simultaneously take into account multiple aspects in every dispatching decision. Since the typical short-term view of dispatching rules is one of the main limitations of such real-time assignment heuristics, we also incorporate in the multicriteria algorithm a specific heuristic rule that takes into account the empty-vehicle travel on a longer time-horizon. Moreover, we also adopt a genetic algorithm to tune the weights associated to each decision criteria in the global decision algorithm. The proposed approach is validated by means of a comparison with other dispatching rules, and with other recently proposed multicriteria dispatching strategies also based on computational Intelligence. The analysis of the results obtained by the proposed dispatching approach in both nominal and perturbed operating conditions (congestions, faults) confirms its effectiveness.

In this paper, we describe an evolutionary design procedure for discrete-time anti-windup controller for electrical drives. Using a genetic algorithm devised to test and compare controllers of different orders, we search for the discrete anti-windup controller achieving the optimal compromise of weighted cost and performance indices. The search is performed on-line, on the physical hardware, by continuously downloading and testing new solutions on a microprocessor running the control algorithms in real time. The controller obtained through genetic search significantly outperforms alternative schemes obtained with conventional design techniques.

This paper proposes a new approach for real-time weld quality monitoring based on the combination of optical sensors with fuzzy logic classification algorithms. The sensing hardware encompasses photodiodes measuring the relations emitted by the plasma surrounding the welding arc and A/D converters. The measured data is then filtered and processed to determine in real-time indices of local quality of the welding process. These indices are then fed to a fuzzy system, which provides an index of the overall quality of the weld, classifying type and position of specific events (e.g. anomalies in the current, voltage or speed of the arc, the contamination with other materials, holes). In an expensive experimental comparison, the fuzzy system outperforms the former version of the detection algorithm based on a statistical approach.

This paper describes a multi-objective evolutionary algorithm for a typical serial production problem, in which two or more consecutive departments must schedule their internal work, each taking into account the requirements of the other departments. There are various single-objective heuristics to deal with this problem, while the multi-objective formulation calls for innovative approaches. To this aim, we devise a novel evolutionary algorithm, and compare it with two other state-of-art genetic optimizers used in similar contexts. The results obtained on both small-size problems with known Pareto-sets, and larger problems derived from industrial production of furniture confirm the effectiveness of the proposed approach.

An effective variant of the projection algorithm frequently used in adaptive fuzzy control is presented. The proposed algorithm preserves the formal guarantees that the adapted parameters and some related system variables remain within the prescribed bounds, and improves the speed of convergence of the adaptation. The effectiveness of our approach is shown both in simulation and experimental case studies.

In this paper, we describe a new design procedure for cascaded controller for electrical drives based on evolutionary algorithms. Most electric drives have two separate controllers for current and speed control, which are in general designed in two consecutive steps (firstly the current controller and then the speed one). Using a hybrid evolutionary algorithm designed to test and compare controllers of different orders, we search simultaneously for the couple of discrete anti-windup controllers achieving the optimal compromise of cost and performance indices related to both current and speed responses. Simulation comparison with conventional design techniques on a non-linear DC drive with variable load are presented to show the effectiveness of the approach.

The use of shared resources by multiple part types in automated manufacturing systems (AMSs) can cause deadlock, i.e., a situation in which the flow of parts is permanently inhibited and the processing of jobs is partially or completely blocked. Most of the work existing in literature focuses on systems in which every operation is performed by only one resource. The paper analyzes deadlock conditions for systems in which multiple resource acquisitions are allowed to complete a working operation (conjunctive resource service, CRS). Extending a digraph representation already used for systems with one-resource operation to the case of CRS allows us a formal characterization of deadlock. This leads to an easy solving approach, consisting of a detection/recovery policy. The paper also shows that some results on the safe states of systems with one-resource operation cannot be extended to CRS. As a consequence, some maximally permissive policies for deadlock avoidance cannot be applied to this kind of system.

Swinging up an inverted pendulum is a common benchmark task for the investigation of automatic control techniques. In this paper we introduce a new Fuzzy Sliding Mode (FSM) technique for swinging-up an inverted pendulum and controlling the connected cart, while minimizing the swing-up time, the cart travel and the required control action. The FSM technique adopted is based on a piecewise linear sliding manifold that is bent towards the far off zones of the pole phase plane, thus enabling the reduction of the control action. Further, in order to limit the cart overshoot two variable gains were inserted in the cart controller. We tested our technique both on a nonlinear model, including friction, and on a lab equipment: we report both on the upwards stabilization and swing-up. The pendulum upwards equilibrium point was made globally stable.

Flexible manufacturing systems (FMSs) are modern production facilities with easy adaptability to variable production plans and goals. These systems may exhibit deadlock situations occurring when a circular wait arises because each piece in a set requires a resource currently held by another job in the same set. Several authors have proposed different policies to control resource allocation in order to avoid deadlock problems. These approaches are mainly based on some formal models of manufacturing systems, such as Petri nets (PNs), directed graphs, etc. Since they describe various peculiarities of the FMS operation in a modular and systematic way, PNs are the most extensively used tool to model such systems. On the other hand, digraphs are more synthetic than PNs because their vertices are just the system resources. So, digraphs describe the interactions between jobs and resources only, while neglecting other details on the system operation. The aim of this paper is to show the tight connections between the two approaches to the deadlock problem, by proposing a unitary framework that links graph-theoretic and PN models and results. In this context, we establish a direct correspondence between the structural elements of the PN (empty siphons) and those of the digraphs (maximal-weight zero-outdegree strong components) characterizing a deadlock occurrence. The paper also shows that the avoidance policies derived from digraphs can be implemented by controlled PNs.

We develop control policies to avoid deadlocks in cellular manufacturing systems (CMSs). We take advantage of the structure of a CMS to develop a distributed control system in which each cell is controlled locally and independently. The controller of each cell is a local agent that adopts his own control law to improve flexibility and performance measures.

Deals with real-time part routing in flexible manufacturing systems. At each production step, each part can autonomously choose its next server according to a fuzzy multiple criteria evaluation of each available destination. The influence of each criterion is graded to improve the effects of part decisions. A simulation study confirms the effectiveness of the approach.

Modern production facilities (i.e. flexible manufacturing systems) exhibit a high degree of resource sharing, a situation in which deadlocks (circular waits) can arise. Using digraph theoretic concepts we derive necessary and sufficient conditions for a deadlock occurrence and rigorously characterize highly undesirable situations (second level deadlocks), which inevitably evolve to circular waits in the next future. We assume that the system dynamics is described by a discrete event dynamical model, whose state provides the information on the current interactions job-resources. This theoretic material allows us to introduce some control laws (named restriction policies) which use the state knowledge to avoid deadlocks by inhibiting or by enabling some transitions. The restriction policies involve small on-line computation costs, so they are suitable for real-time implementation. For a meaningful class of systems one of these policies is the least restrictive deadlock-free policy one can find, namely it inhibits resource allocation only if leads directly to a deadlock. Finally, the paper discusses the computational complexity of all the proposed restriction policies and shows some examples to compare their performances.

Potentially, flexible manufacturing systems (FMSs) possess the ability to attain efficiency and versatility in small batches, variable mix production. However, the FMS potentiality is not yet fully used, because of the high cost of specific control software. Hence, a generic software, usable in an arbitrary FMS, producing an arbitrary part mix, appears as an important means to minimize programming and re-programming effort. In this context, modeling and control problem formalization emerge as a main issue. In this paper the authors refer to Zeigler's system-theoretic formalism for modeling the dynamics of a generic FMS at the job release and job how levels. The authors' discrete event dynamic system (DEDS) model establishes an abstract comprehensive framework for developing a generic control software at such levels. The model is able to represent both hardware/software components of the FMS and processing activity plans with a common "language". A modular structure underlies the description of both the shop-floor dynamics and control rules. So, the software architecture emerges as a direct consequence of the proposed approach and consists of three main parts: the system state knowledge base, the job release manager and the job flow manager.

Two different approaches for routing optimization are proposed and compared. The first method is open-loop and selects the route so that the job percentage on each alternative path approximates an optimal offline predetermined percentage. In the second approach decision-making is based on a merit index taking into account the current work in progress and the consequent machine availability, i.e., the current system's state. The decision is taken by comparing the index values for each one of the alternative paths allows for the job entering the system. Online simulation is used to estimate the near future system's state trajectory and to compute the merit index. Some case studies are presented comparing the method in terms of efficiency and implementation effort.>