Raúl Pino

A decision support system for applying failure mode and effects analysis

This study describes an alternative way of applying failure mode and effects analysis (FMEA) to a wide variety of problems. It presents a methodology based on a decision system supported by qualitative rules which provides a ranking of the risks of potential causes of production system failures. By providing an illustrative example, it highlights the advantages of this flexible system over the traditional FMEA model. Finally, a fuzzy decision model is proposed, which improves the initial decision system by introducing the element of uncertainty.

Forecasting next-day price of electricity in the Spanish energy market using artificial neural networks

In this paper, next-day hourly forecasts are calculated for the energy price in the electricity production market of Spain. The methodology used to achieve these forecasts is based on artificial neural networks, which have been used successfully in recent years in many forecasting applications. The days to be forecast include working days as well as weekends and holidays, due to the fact that energy price has different behaviours depending on the kind of day to be forecast. Besides, energy price time series are usually composed of too many data, which could be a problem if we are looking for a short period of time to reach an adequate forecast. In this paper, a training method for artificial neural nets is proposed, which is based on making a previous selection for the multilayer perceptron (MLP) training samples, using an ART-type neural network. The MLP is then trained and finally used to calculate forecasts. These forecasts are compared to those obtained from the well-known Box-Jenkins ARIMA forecasting method. Results show that neural nets perform better than ARIMA models, especially for weekends and holidays. Both methodologies calculate more accurate forecasts-in terms of mean absolute percentage error-for working days that for weekends and holidays. Agents involved in the electricity production market, who may need fast forecasts for the price of electricity, would benefit from the results of this study.

Systemic approach to supply chain management through the viable system model and the theory of constraints

Abstract In today’s environment, Supply Chain Management (SCM) takes a key role in business strategy. A major challenge is achieving high customer service level under a reasonable operating expense and investment. The traditional approach to SCM, based on local optimisation, is a proven cause of meaningful inefficiencies – e.g. the Bullwhip Effect – that obstruct the throughput. The systemic (holistic) approach, based on global optimisation, has been shown to perform significantly better. Nevertheless, it is not widely expanded, since the implementation of an efficient solution requires a suitable scheme. Under these circumstances, this paper proposes an integrative framework for supply chain collaboration aimed at increasing its efficiency. This is based on the combined application of the Beer’s Viable System Model (VSM) and the Goldratt’s Theory of Constraints (TOC). VSM defines the systemic structure of the supply chain and orchestrates the collaboration, while TOC implements the systemic behaviour – i.e. integrate processes – and define performance measures. To support this proposal, we detail its application to the widely used Beer Game scenario. In addition, we discuss its implementation in real supply chains, highlighting the key points that must be considered.

Forecasting IBEX-35 moves using support vector machines

This research aims at examining the application of support vector machines (SVMs) to the task of forecasting the weekly change in the Madrid IBEX-35 stock index. The data cover the period between 10/18/1990 and 10/29/2010. A trading simulation is implemented so that statistical efficiency is complemented by measures of economic performance. The inputs retained are traditional technical trading rules commonly used in the analysis of equity markets such as the Relative Strength Index (RSI) and the Moving Average Convergence Divergence (MACD) decision rules. The SVMs with given values of the RSI and MACD indicators are used in order to determine the best situations to buy or sell the market. The two outputs of the SVM are both the direction of the market and the probability attached to each forecast market move. The best result that it has been achieved is a hit ratio of 100% using the SVM classifier under some chosen risk-aversion parameters. However, these results are obtained analyzing recent periods rather than using all the dataset information.

Holism versus reductionism in supply chain management

Since supply chains are increasingly built on complex interdependences, concerns to adopt new managerial approaches based on collaboration have surged. Nonetheless, implementing an efficient collaborative solution is a wide process where several obstacles must be faced. This work explores the key role of experimentation as a model-driven decision support system for managers in the convoluted decision-making process required to evolve from a reductionist approach (where the overall strategy is the sum of individual strategies) to a holistic approach (where global optimization is sought through collaboration). We simulate a four-echelon supply chain within a large noise scenario, while a fractional factorial design of experiments (DoE) with eleven factors was used to explore cause-effect relationships. By providing evidence in a wide range of conditions of the superiority of the holistic approach, supply chain participants can be certain to move away from their natural reductionist behavior. Thereupon, practitioners focus on implementing the solution. The theory of constraints (TOC) defines an appropriate framework, where the Drum-Buffer-Rope (DBR) method integrates supply chain processes and synchronizes decisions. In addition, this work provides evidence of the need for aligning incentives in order to eliminate the risk to deviate. Modeling and simulation, especially agent-based techniques, allows practitioners to develop awareness of complex organizational problems. Hence, these prototypes can be interpreted as forceful laboratories for decision making and business transformation. We model an agent-based supply chain under a large noise scenario.A fractional factorial DoE with eleven factors has been used.Economic robustness of the TOC is shown compared to the classic OUT policy.The research brings evidence of the need for aligning incentives in the system.ABM prototypes are highlighted as powerful model-driven DSSs for supply chains.

Dynamic scheduling of manufacturing systems using machine learning: An updated review

Abstract A common way of dynamically scheduling jobs in a manufacturing system is by implementing dispatching rules. The issues with this method are that the performance of these rules depends on the state the system is in at each moment and also that no “ideal” single rule exists for all the possible states that the system may be in. Therefore, it would be interesting to use the most appropriate dispatching rule for each instance. To achieve this goal, a scheduling approach that uses machine learning can be used. Analyzing the previous performance of the system (training examples) by means of this technique, knowledge is obtained that can be used to decide which is the most appropriate dispatching rule at each moment in time. In this paper, a literature review of the main machine learning based scheduling approaches from the last decade is presented.

LEARNING-BASED SCHEDULING OF FLEXIBLE MANUFACTURING SYSTEMS USING SUPPORT VECTOR MACHINES

Dispatching rules are usually applied to dynamically schedule jobs in flexible manufacturing systems (FMSs). Despite their frequent use a significant drawback is that the performance level of the rule is dictated by the current state of the manufacturing system. Because no rule is better than any other for every system state, it would be highly desirable to know which rule is the most appropriate for each given condition. To achieve this goal we propose a scheduling approach using support vector machines (SVMs). By using this technique and by analyzing the earlier performance of the system, “scheduling knowledge” is obtained whereby the right dispatching rule at each particular moment can be determined. Simulation results show that the proposed approach leads to significant performance improvements over existing dispatching rules. In the same way it is also confirmed that SVMs perform better than other traditional machine learning algorithms as the inductive learning when applied to FMS scheduling problem, due to their better generalization capability.

Intelligent decision support system for real-time water demand management

AbstractEnvironmental and demographic pressures have led to the current importance of Water Demand Management (WDM), where the concepts of efficiency and sustainability now play a key role. Water must be conveyed to where it is needed, in the right quantity, at the required pressure, and at the right time using the fewest resources. This paper shows how modern Artificial Intelligence (AI) techniques can be applied on this issue from a holistic perspective. More specifically, the multi-agent methodology has been used in order to design an Intelligent Decision Support System (IDSS) for real-time WDM. It determines the optimal pumping quantity from the storage reservoirs to the points-of-consumption in an hourly basis. This application integrates advanced forecasting techniques, such as Artificial Neural Networks (ANNs), and other components within the overall aim of minimizing WDM costs. In the tests we have performed, the system achieves a large reduction in these costs. Moreover, the multi-agent environme...

Supply Chain Management by Means of Simulation

Several changes in the macro environment of the companies over the last two decades have meant that the competition is no longer constrained to the product itself, but the overall concept of supply chain. Under these circumstances, the supply chain management stands as a major concern for companies nowadays. One of the prime goals to be achieved is the reduction of the Bullwhip Effect, related to the amplification of the demand supported by the different levels, as they are further away from customer. It is a major cause of inefficiency in the supply chain. Thus, this paper presents the application of simulation techniques to the study of the Bullwhip Effect in comparison to modern alternatives such as the representation of the supply chain as a network of intelligent agents. We conclude that the supply chain simulation is a particularly interesting tool for performing sensitivity analyses in order to measure the impact of changes in a quantitative parameter on the generated Bullwhip Effect. By way of example, a sensitivity analysis for safety stock has been performed to assess the relationship between Bullwhip Effect and safety stock.

Application of Genetic Algorithms to Container Loading Optimization

—Standardization of transport means, such as, containers has a direct impact on the transportation efficiency sought by European transport policies. In this paper, we present a genetic algorithm application to the container loading problem trying to maximize the cargo volume accommodated in the container whilst ensuring that loading restrictions are met, and thus achieving a reduction in the number of freight to hire and thereby a reduction in costs. The proposed method has been compared to similar models, and the results obtained are similar or even improved.