Browsing by Author "Mendia, Izaskun"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item An Intelligent Procedure for the Methodology of Energy Consumption in Industrial Environments(Springer, 2020-10-27) Mendia, Izaskun; Gil-Lopez, Sergio; Del Ser, Javier; Grau, Iñaki; Lejarazu, Adelaida; Maqueda, Erik; Perea, Eugenio; Analide, Cesar; Novais, Paulo; Camacho, David; Yin, Hujun; Tecnalia Research & Innovation; IA; DIGITAL ENERGYThe concern of the industrial sector about the increase of energy costs has stimulated the development of new strategies for the effective management of energy consumption in industrial setups. Along with this growth, the irruption and continuous development of digital technologies have generated increasingly complex industrial ecosystems. These ecosystems are supported by a large number of variables and procedures for the operation and control of industrial processes and assets. This heterogeneous technological scenario has made industries difficult to manage by traditional means. In this context, the disruptive potential of cyber physical systems is beginning to be considered in the automation and improvement of industrial services. Particularly, intelligent data-driven approaches relying on the combination of Energy Management Systems (EMS), Manufacturing Execution Systems (MES), Internet of Things (IoT) and Data Analytics provide the intelligence needed to optimally operate these complex industrial environments. The work presented in this manuscript contributes to the definition of the aforementioned intelligent data-driven approaches, defining a systematic, intelligent procedure for the energy efficiency diagnosis and improvement of industrial plants. This data-based diagnostic procedure hinges on the analysis of data collected from industrial plants, aimed at minimizing energy costs through the continuous assessment of the production-consumption ratio of the plant (i.e. energy per piece or kg produced). The proposed methodology aims to support managers and energy-efficiency technicians to minimize the plant’s energy consumption without affecting the production and therefore, increase its competitiveness. The data used in the design of this methodology are real data from a company dedicated to the design and manufacture of automotive components and one of the main manufacturers in the automotive sector worldwide. The present methodology is under the pending patent application EU19382002.4-120.Item Machine learning based adaptive soft sensor for flash point inference in a refinery realtime process(2022-03) Mendia, Izaskun; Gil-López, Sergio; Landa-Torres, Itziar; Orbe, Lucía; Maqueda, Erik; Tecnalia Research & Innovation; IA; DIGITAL ENERGYIn industrial control processes, certain characteristics are sometimes difficult to measure by a physical sensor due to technical and/or economic limitations. This fact is especially true in the petrochemical industry. Some of those quantities are especially crucial for operators and process safety. This is the case for the automotive diesel Flash Point Temperature (FT). Traditional methods for FT estimation are based on the study of the empirical inference between flammability properties and the denoted target magnitude. The necessary measures are taken indirectly by samples from the process and analyzing them in the laboratory, this process implies time (can take hours from collection to flash temperature measurement) and thus make it very difficult for real-time monitorization, which in fact results in security and economical losses. This study defines a procedure based on Machine Learning modules that demonstrate the power of real-time monitorization over real data from an important international refinery. As input, easily measured values provided in real-time, such as temperature, pressure, and hydraulic flow are used and a benchmark of different regressive algorithms for FT estimation is presented. The study highlights the importance of sequencing preprocessing techniques for the correct inference of values. The implementation of adaptive learning strategies achieves considerable economic benefits in the productization of this soft sensor. The validity of the method is tested in the reality of a refinery. In addition, real-world industrial data sets tend to be unstable and volatile, and the data is often affected by noise, outliers, irrelevant or unnecessary features, and missing data. This contribution demonstrates with the inclusion of a new concept, called an adaptive soft sensor, the importance of the dynamic adaptation of the conformed schemes based on Machine Learning through their combination with feature selection, dimensional reduction, and signal processing techniques. The economic benefits of applying this soft sensor in the refinery's production plant and presented as potential semi-annual savings.Item A novel approach for the detection of anomalous energy consumption patterns in industrial cyber-physical systems(2024-02) Mendia, Izaskun; Gil-Lopez, Sergio; Grau, Iñaki; Del Ser, Javier; Gil‐Lopez, Sergio; Tecnalia Research & Innovation; IAMost scenarios emerging from the Industry 4.0 paradigm rely on the concept of cyber-physical production systems (CPPS), which allow them to synergistically connect physical to digital setups so as to integrate them over all stages of product development. Unfortunately, endowing CPPS with AI-based functionalities poses its own challenges: although advances in the performance of AI models keep blossoming in the community, their penetration in real-world industrial solutions has not so far developed at the same pace. Currently, 90% of AI-based models never reach production due to a manifold of assorted reasons not only related to complexity and performance: decisions issued by AI-based systems must be explained, understood and trusted by their end users. This study elaborates on a novel tool designed to characterize, in a non-supervised, human-understandable fashion, the nominal performance of a factory in terms of production and energy consumption. The traceability and analysis of energy consumption data traces and the monitoring of the factory's production permit to detect anomalies and inefficiencies in the working regime of the overall factory. By virtue of the transparency of the detection process, the proposed approach elicits understandable information about the root cause from the perspective of the production line, process and/or machine that generates the identified inefficiency. This methodology allows for the identification of the machines and/or processes that cause energy inefficiencies in the manufacturing system, and enables significant energy consumption savings by acting on these elements. We assess the performance of our designed method over a real-world case study from the automotive sector, comparing it to an extensive benchmark comprising state-of-the-art unsupervised and semi-supervised anomaly detection algorithms, from classical algorithms to modern generative neural counterparts. The superior quantitative results attained by our proposal complements its better interpretability with respect to the rest of algorithms in the comparison, which emphasizes the utmost relevance of considering the available domain knowledge and the target audience when design AI-based industrial solutions of practical value. Finally, the work described in this paper has been successfully deployed on a large scale in several industrial factories with significant international projection.Item Optimal Phase Swapping in Low Voltage Distribution Networks Based on Smart Meter Data and Optimization Heuristics(Springer Verlag, 2017) Mendia, Izaskun; Gil-López, Sergio; Del Ser, Javier; Bordagaray, Ana González; Prado, Jesús García; Vélez, Manuel; Del Ser, Javier; Tecnalia Research & Innovation; IAIn this paper a modified version of the Harmony Search algorithm is proposed as a novel tool for phase swapping in Low Voltage Distribution Networks where the objective is to determine to which phase each load should be connected in order to reduce the unbalance when all phases are added into the neutral conductor. Unbalanced loads deteriorate power quality and increase costs of investment and operation. A correct assignment is a direct, effective alternative to prevent voltage peaks and network outages. The main contribution of this paper is the proposal of an optimization model for allocating phases consumers according to their individual consumption in the network of low-voltage distribution considering mono and bi-phase connections using real hourly load patterns, which implies that the computational complexity of the defined combinatorial optimization problem is heavily increased. For this purpose a novel metric function is defined in the proposed scheme. The performance of the HS algorithm has been compared with classical Genetic Algorithm. Presented results show that HS outperforms GA not only on terms of quality but on the convergence rate, reducing the computational complexity of the proposed scheme while provide mono and bi phase connections.Item Semantic-based Context Modeling for Quality of Service Support in IoT Platforms(IEEE, 2016-06-21) Mingozzi, Enzo; Tanganelli, Giacomo; Vallati, Carlo; Martinez-Rodriguez, Belen; Mendia, Izaskun; Gonzalez-Rodriguez, M.; Tecnalia Research & Innovation; BIGDATA; SGThe Internet of Things (IoT) envisions billions of devices seamlessly connected to information systems, thus providing a sensing platform for applications. The availability of such a huge number of smart things will entail a multiplicity of devices collecting overlapping data and/or providing similar functionalities. In this scenario, efficient discovery and appropriate selection of things through proper context acquisition and management will represent a critical requirement and a challenge for future IoT platforms. In this work we present a practical approach to model and manage context, and how this information can be exploited to implement QoS-aware thing service selection. In particular, it is shown how context can be used to infer knowledge on the equivalence of thing services through semantic reasoning, and how such information can be exploited to allocate thing services to applications while meeting QoS requirements even in case of failures. The proposed approach is demonstrated through a simple yet illustrative experiment in a smart home scenario.