Miguel A. Prada

Remote laboratory of a quadruple tank process for learning in control engineering using different industrial controllers

Education in technological disciplines requires students to be always in contact with real systems, where they can apply their theoretical knowledge. These systems tend to be expensive and the high initial investment is returned after a long time, as the resource can only be used by a limited number of students during the on‐site practical classes. The use of remote laboratories, which allow students to access the system through the Internet, optimizes resources by providing access to a larger number of users at any time. In this article, we present a remote laboratory of a quadruple‐tank industrial scale model, with real industrial equipment. The students carry out control activities on the system through the Internet as they would do in a laboratory classroom. The remote laboratory architecture is based on a three layer (physical layer–server layer–client layer) whose middle layer consists of four servers: Web Server, Proxy Server, Database Server, and Control Server. In the Control server, a link application based on OPC (Ole for Process Control) standard to select different industrial controllers which are connected to the scale model simultaneously has been implemented. Since the application is based on a standard, this structure can be expanded easily with other industrial controllers from other manufacturers. The remote laboratory is used in automatic and control subjects from different Spanish universities. Surveys conducted among the students about the use of Laboratory show that they perceive an improvement of their learning using the lab.

Visual dynamic model based on self-organizing maps for supervision and fault detection in industrial processes

Visual data mining techniques have experienced a growing interest for processing and interpretation of the large amounts of multidimensional data available in current industrial processes. One of the approaches to visualize data is based on self-organizing maps (SOM), which define a projection of the input space onto a 2D or 3D space that can be used to obtain visual representations. Although these techniques have been usually applied to visualize static relations among the process variables, they have proven to be very useful to display dynamic features of the processes. In this work, an approach based on the SOM to model the dynamics of multivariable processes is presented. The proposed method identifies the process conditions (clusters) and the probabilities of transition among them, using the trajectory followed by the input data on the 2D visualization space. Furthermore, a new method of residual computation for fault detection and identification that uses the dynamic information provided by the model of transitions is proposed. The proposed method for modeling and fault identification has been applied to supervise a real industrial plant and the results are included.

Three-way analysis of structural health monitoring data

Structural Health Monitoring aims to identify damages in engineering structures by monitoring changes in their vibration response. Unsupervised learning algorithms can be used to obtain a model of the undamaged condition and detect which samples are not in agreement with it. However, in real structures with a sensor network configuration, the number of candidate features usually becomes large. Therefore, complexity increases and it is necessary to perform feature selection and/or dimensionality reduction. We propose to exploit the three-way structure of data and apply a true multi-way data analysis algorithm: parallel factor analysis. A simple model is obtained and used to train accurate novelty detectors. The methods are tested both with real and simulated structural data to assess that three-way analysis can be successfully used in structural health monitoring.

Challenges and solutions in remote laboratories. Application to a remote laboratory of an electro-pneumatic classification cell

The field of remote laboratories has been developed over the years. These laboratories are valuable educational tools that allow students and faculty interact with real equipment through the Internet, as if they were physically in front of the system. When a remote laboratory is developed, many technical difficulties are found, mainly with respect to the links between the different elements such as physical system, database and clients. In this work, we analyze the challenges and propose approaches to develop remote laboratories that achieve flexibility, scalability and greater educational value. In particular, we present a remote laboratory for automatic control, which includes an electro-pneumatic classification cell. The architecture of the laboratory is based on the three-tier architecture (physical system layer, server layer and client layer). The client layer has been implemented with web standards such as HTML5, AJAX and CSS3, the clients interact with the system using a content management system and the communication interface between the physical system and the database uses a middleware based on OPC (Ole for Process Control). Engineering students have regularly used the remote laboratory and they have evaluated it through surveys. We review the main challenges of remote laboratories and propose solutions.We present a middleware based on OPC for the communication with the physical systems.We present client rich applications based on JavaScript and HTML5.We test the technological platform with the addition of an electro-pneumatic classification cell.We propose practical tasks and evaluate their educational value through feedback from students.

A Virtual Laboratory of D.C. Motors for Learning Control Theory

The application of Information and Communication Technologies to education has promoted the development of new educational methodologies that lead to new learning spaces. A particular case, especially in the engineering field, is that of Virtual and Remote Laboratories through the Internet. These are powerful tools that let the student operate on simulated and/or real technological equipment with the only requirements of a PC, a web browser and an Internet connection. In this work, we present a virtual laboratory of an educational set for d.c. motor control, Feedback MS-150, which is widely used as practical equipment in laboratories of introductory control theory courses. A simulation of all the functionalities of the modular equipment was developed in Easy Java Simulation (EJS). The simulation was included in the Remote Laboratory of Automatic Control at the University of León (LRA-ULE), which is managed by a Drupal content management system. Engineering students have regularly used the virtual laboratory and have evaluated it through surveys.

Novelty detection in projected spaces for structural health monitoring

The aim of Structural Health Monitoring (SHM) is to detect and identify damages in man-made structures such as bridges by monitoring features derived from vibration data. A usual approach is to deal with vibration measurements, obtained by acceleration sensors during the service life of the structure. In this case, only normal data from healthy operation are available, so damage detection becomes a novelty detection problem. However, when prior knowledge about the structure is limited, the set of candidate features that can be extracted from the set of sensors is large and dimensionality reduction of the input space can result in more precise and efficient novelty detectors. We assess the effect of linear, nonlinear, and random projection to low-dimensional spaces in novelty detection by means of probabilistic and nearest-neighbor methods. The methods are assessed with real-life data from a wooden bridge model, where structural damages are simulated with small added weights.

Analysis of electricity consumption profiles in public buildings with dimensionality reduction techniques

The analysis of the daily electricity consumption profile of a building and its correlation with environmental factors makes it possible to examine and estimate its electricity demand. As an alternative to the traditional correlation analysis, a new approach is proposed to provide a detailed and visual analysis of the correlations between consumption and environmental variables. Since consumption profiles can be characterized by many components, the input space is high dimensional. For that reason, it is necessary to apply dimensionality reduction techniques that enable a projection of these data onto an easily interpretable 2D space. In this paper, several dimensionality reduction techniques are tested in order to determine the most appropriate one for the stated purpose. Later, the proposed approach uses the chosen algorithm to analyze the influence of the environmental variables on the electricity consumption in public buildings located at the University of Leon. Finally, electricity profiles from all buildings are compared with regard to two aspects, the magnitude and dynamics of the consumption.

EnvSOM: a SOM algorithm conditioned on the environment for clustering and visualization

In this paper, we present a new approach suitable for analysis of large data sets, conditioned on the environment. Mainly, the envSOM algorithm consists of two consecutive trainings of the self-organizing map. In the first phase, a SOM is trained using every available variable, but only those which characterize the environment are used to compute the winner unit. Therefore, this phase produces an accurate model of the environment. In the second phase, a new SOM is initialized appropriately with information from the codebooks of the first SOM. The new SOM uses all the variables for winner selection. However, in this case the environmental variables are kept fixed and only the remaining ones are involved in the update process. A model of the whole data set influenced by the environmental conditions is obtained in this second phase. The result of this algorithm represents a probability function of a data set, given the environment information. Therefore, it could be very useful in the analysis of processes which have close dependencies on environmental conditions.

Dimensionality reduction techniques to analyze heating systems in buildings

The highest cause of energy consumption in buildings is due to Heating, Ventilation, and Air Conditioning (HVAC) systems. A large number of interconnected variables are involved in the control of these systems, so conventional analysis approaches are often difficult. For that reason, data analysis by means of dimensionality reduction techniques can be a useful approach to address energy efficiency in buildings. In this paper, a method is proposed to visualize the relevant features of a heating system and its behavior and to help finding correlations between temporal, production and distribution variables. For that purpose, a modification of the self-organizing map is used. The energy consumption of HVAC systems is also analyzed using a dimensionality reduction technique (t-Distributed Stochastic Neighbor Embedding, t-SNE). The proposed approach is applied to a real building at the University of Leon.

Monitoring industrial processes with SOM-based dissimilarity maps

Todays large scale availability of data from industrial plants is an invaluable resource to monitor industrial processes. Data-based methods can lead to better understanding, optimization or detection of anomalies. As a particular case, batch processes have attracted special interest due to their widespread presence in the industry. The aim of monitoring, in this case, is to compare different runs or implementations of a process with the baseline or normal operating one. On the other hand, visual exploration tools for process monitoring have been a prolific application field for self-organizing maps (SOM). In this paper, we exploit data-based models, obtained by means of SOM, for the visual comparison of industrial processes. For that purpose, we propose a method that defines a new visual exploration tool, called dissimilarity map. We also expose the need to consider dynamic information for effective comparison. The method is assessed in two industrial pilot plants that implement the same process. The results are discussed.