Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 11
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

LSTM-Based Wastewater Treatment Plants Operation Strategies for Effluent Quality Improvement

  • Pisa, Ivan|||0000-0003-3931-9257
  • Santín López, Ignacio|||0000-0002-4312-1035
  • Morell, Antoni|||0000-0003-2249-8594
  • Lopez Vicario, Jose|||0000-0002-3574-4697
  • Vilanova, Ramon|||0000-0002-8035-5199
Wastewater Treatment Plants (WWTPs) are facilities devoted to managing and reducing the pollutant concentrations present in the urban residual waters. Some of them consist in nitrogen and phosphorus derived products which are harmful for the environment. Consequently, certain constraints are applied to pollutant concentrations in order to make sure that treated waters comply with the established regulations. In that sense, efforts have been applied to the development of control strategies that help in the pollutant reduction tasks. Furthermore, the appearance of Artificial Neural Networks (ANNs) has encouraged the adoption of predictive control strategies. In such a fashion, this work is mainly focused on the adoption and development of them to actuate over the pollutant concentrations only when predictions of effluents determine that violations will be produced. In that manner, the overall WWTP's operational costs can be reduced. Predictions are generated by means of an ANN-based Soft-Sensor which adopts Long-Short Term Memory cells to predict effluent pollutant levels. These are the ammonium (S-{NH,e}) and the total nitrogen (S-{Ntot,e}) which are predicted considering influent parameters such as the ammonium concentration at the entrance of the WWTP reactor tanks (S-{NH,po}), the reactors' input flow rate (Q-{po}), the WWTP recirculation rate (Q-{a}) and the environmental temperature (T-{as}). Moreover, this work presents a new multi-objective control scenario which consists in a unique control structure performing the reduction of S-{NH,e} and S-{Ntot,e} concentrations simultaneously. Performance of this new control approach is contrasted with other strategies to determine the improvement provided by the ANN-based Soft-Sensor as well as by the fact of being controlling two pollutants at the same time. Results show that some brief and small violations are still produced. Nevertheless, an improvement in the WWTPs performance w.r.t.The most common control strategies around 96.58% and 98.31% is achieved for S-{NH,e} and S-{Ntot,e}, respectively.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

ANN-based soft sensor to predict effluent violations in wastewater treatment plants

  • Pisa, Ivan|||0000-0003-3931-9257
  • Santín López, Ignacio|||0000-0002-4312-1035
  • Lopez Vicario, Jose|||0000-0002-3574-4697
  • Morell, Antoni|||0000-0003-2249-8594
  • Vilanova, Ramon|||0000-0002-8035-5199
Wastewater treatment plants (WWTPs) form an industry whose main goal is to reduce water's pollutant products, which are harmful to the environment at high concentrations. In addition, regulations are applied by administrations to limit pollutant concentrations in effluent. In this context, control strategies have been adopted by WWTPs to avoid violating these limits; however, some violations still occur. For that reason, this work proposes the deployment of an artificial neural network (ANN)-based soft sensor in which a Long-Short Term Memory (LSTM) network is used to generate predictions of nitrogen-derived components, specifically ammonium (S ) and total nitrogen (S ). S is a limiting nutrient and can therefore cause eutrophication, while nitrogen in the S form is toxic to aquatic life. These parameters are used by control strategies to allow actions to be taken in advance and only when violations are predicted. Since predictions complement control strategies, the evaluation of the ANN-based soft sensor was carried out using the Benchmark Simulation Model N.2. (BSM2) and three different control strategies (from low to high control complexity). Results show that our proposed method is able to predict nitrogen-derived products with good accuracy: the probability of detecting violations of BSM2's limits is 86-94%. Moreover, the prediction accuracy can be improved by calibrating the soft sensor; for example, perfect prediction of all future violations can be achieved at the expense of increasing the false positive rate.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Denoising Autoencoders and LSTM-Based Artificial Neural Networks Data Processing for Its Application to Internal Model Control in Industrial Environments-The Wastewater Treatment Plant Control Case

  • Pisa, Ivan|||0000-0003-3931-9257
  • Morell, Antoni|||0000-0003-2249-8594
  • Lopez Vicario, Jose|||0000-0002-3574-4697
  • Vilanova, Ramon|||0000-0002-8035-5199
The evolution of industry towards the Industry 4.0 paradigm has become a reality where different data-driven methods are adopted to support industrial processes. One of them corresponds to Artificial Neural Networks (ANNs), which are able to model highly complex and non-linear processes. This motivates their adoption as part of new data-driven based control strategies. The ANN-based Internal Model Controller (ANN-based IMC) is an example which takes advantage of the ANNs characteristics by modelling the direct and inverse relationships of the process under control with them. This approach has been implemented in Wastewater Treatment Plants (WWTP), where results show a significant improvement on control performance metrics with respect to (w.r.t.) the WWTP default control strategy. However, this structure is very sensible to non-desired effects in the measurements-when a real scenario showing noise-corrupted data is considered, the control performance drops. To solve this, a new ANN-based IMC approach is designed with a two-fold objective, improve the control performance and denoise the noise-corrupted measurements to reduce the performance degradation. Results show that the proposed structure improves the control metrics, (the Integrated Absolute Error (IAE) and the Integrated Squared Error (ISE)), around a 21.25% and a 54.64%, respectively.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Industrial Control under Non-Ideal Measurements, Data-Based Signal Processing as an Alternative to Controller Retuning

  • Pisa, Ivan|||0000-0003-3931-9257
  • Morell, Antoni|||0000-0003-2249-8594
  • Vilanova, Ramon|||0000-0002-8035-5199
  • Lopez Vicario, Jose|||0000-0002-3574-4697
Industrial environments are characterised by the non-lineal and highly complex processes they perform. Different control strategies are considered to assure that these processes are correctly performed. Nevertheless, these strategies are sensible to noise-corrupted and delayed measurements. For that reason, denoising techniques and delay correction methodologies should be considered but, most of these techniques require a complex design and optimisation process as a function of the scenario where they are applied. To alleviate this, a complete data-based approach devoted to denoising and correcting the delay of measurements is proposed here with a two-fold objective: simplify the solution design process and achieve its decoupling from the considered control strategy as well as from the scenario. Here it corresponds to a Wastewater Treatment Plant (WWTP). However, the proposed solution can be adopted at any industrial environment since neither an optimization nor a design focused on the scenario is required, only pairs of input and output data. Results show that a minimum Root Mean Squared Error (RMSE) improvement of a 63.87% is achieved when the new proposed data-based denoising approach is considered. In addition, the whole system performance show that similar and even better results are obtained when compared to scenario-optimised methodologies.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Transfer learning in wastewater treatment plant control design, from conventional to long short-term memory-based controllers

  • Pisa, Ivan|||0000-0003-3931-9257
  • Morell, Antoni|||0000-0003-2249-8594
  • Vilanova, Ramon|||0000-0002-8035-5199
  • Lopez Vicario, Jose|||0000-0002-3574-4697
In the last decade, industrial environments have been experiencing a change in their control processes. It is more frequent that control strategies adopt Artificial Neural Networks (ANNs) to support control operations, or even as the main control structure. Thus, control structures can be directly obtained from input and output measurements without requiring a huge knowledge of the processes under control. However, ANNs have to be designed, implemented, and trained, which can become complex and time-demanding processes. This can be alleviated by means of Transfer Learning (TL) methodologies, where the knowledge obtained from a unique ANN is transferred to the remaining nets reducing the ANN design time. From the control viewpoint, the first ANN can be easily obtained and then transferred to the remaining control loops. In this manuscript, the application of TL methodologies to design and implement the control loops of a Wastewater Treatment Plant (WWTP) is analysed. Results show that the adoption of this TL-based methodology allows the development of new control loops without requiring a huge knowledge of the processes under control. Besides, a wide improvement in terms of the control performance with respect to conventional control structures is also obtained. For instance, results have shown that less oscillations in the tracking of desired set-points are produced by achieving improvements in the Integrated Absolute Error and Integrated Square Error which go from 40.17% to 94.29% and from 34.27% to 99.71%, respectively.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Transfer Learning Improving Predictive Mortality Models for Patients in End-Stage Renal Disease

  • Macias Toro, Edwar Hernando|||0000-0001-5568-9237
  • Lopez Vicario, Jose|||0000-0002-3574-4697
  • Serrano, Javier|||0000-0003-1235-2145
  • Ibeas, Jose|||0000-0002-1292-7271
  • Morell, Antoni|||0000-0003-2249-8594
Deep learning is becoming a fundamental piece in the paradigm shift from evidence-based to data-based medicine. However, its learning capacity is rarely exploited when working with small data sets. Through transfer learning (TL), information from a source domain is transferred to a target one to enhance a learning task in such domain. The proposed TL mechanisms are based on sample and feature space augmentation. Thus, deep autoencoders extract complex representations for the data in the TL approach. Their latent representations, the so-called codes, are handled to transfer information among domains. The transfer of samples is carried out by computing a latent space mapping matrix that links codes from both domains for later reconstruction. The feature space augmentation is based on the computation of the average of the most similar codes from one domain. Such an average augments the features in a target domain. The proposed framework is evaluated in the prediction of mortality in patients in end-stage renal disease, transferring information related to the mortality of patients with acute kidney injury from the massive database MIMIC-III. Compared to other TL mechanisms, the proposed approach improves 6-11% in previous mortality predictive models. The integration of TL approaches into learning tasks in pathologies with data volume issues could encourage the use of data-based medicine in a clinical setting.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Ternary Neural Networks Based on on/off Memristors, set-Up and Training

  • Morell, Antoni|||0000-0003-2249-8594
  • Diaz Machado, Elvis|||0000-0002-6583-8547
  • Miranda, E.|||0000-0003-0470-5318
  • Boquet, Guillem|||0000-0002-8683-0421
  • Lopez Vicario, Jose|||0000-0002-3574-4697
Neuromorphic systems based on hardware neural networks (HNNs) are expected to be an energy and time-efficient computing architecture for solving complex tasks. In this paper, we consider the implementation of deep neural networks (DNNs) using crossbar arrays of memristors. More specifically, we considered the case where such devices can be configured in just two states: the low-resistance state (LRS) and the high-resistance state (HRS). HNNs suffer from several non-idealities that need to be solved when mapping our software-based models. A clear example in memristor-based neural networks is conductance variability, which is inherent to resistive switching devices, so achieving good performance in an HNN largely depends on the development of reliable weight storage or, alternatively, mitigation techniques against weight uncertainty. In this manuscript, we provide guidelines for a system-level designer where we take into account several issues related to the set-up of the HNN, such as what the appropriate conductance value in the LRS is or the adaptive conversion of current outputs at one stage to input voltages for the next stage. A second contribution is the training of the system, which is performed via offline learning, and considering the hardware imperfections, which in this case are conductance fluctuations. Finally, the resulting inference system is tested in two well-known databases from MNIST, showing that is competitive in terms of classification performance against the software-based counterpart. Additional advice and insights on system tuning and expected performance are given throughout the paper.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Multiple imputation using the average code from autoencoders

  • Macias Toro, Edwar Hernando|||0000-0001-5568-9237
  • Serrano, Javier|||0000-0003-1235-2145
  • Lopez Vicario, Jose|||0000-0002-3574-4697
  • Morell, Antoni|||0000-0003-2249-8594
Background: Missing information is a constant issue in the clinical setting. The presence of missing values (MV) is triggered by the wrong acquisition of data or sudden events in the patient's health condition. Imputation arises to replace the non-existent information with the twofold purpose of benefiting from existing information and reducing bias in clinical settings. Mechanisms based on deep learning and multiple imputation (MI) are leading alternatives to impute MVs because of their capacity to extract complex relationships and the consideration of uncertainty that MI adds. Objective: This study aims to improve the reconstruction of missing information through a novel imputation alternative that integrates a MI paradigm into deep learning models. Methods: The proposed method integrates the MI paradigm into the latent representations of an autoencoder, the so-called codes. The average code is then computed, boosting a better latent representation of data. Finally, the average code is decoded to reconstruct MVs. Results: The proposed method is tested in 6 datasets with different patters of MVs. It is compared with solutions based on autoencoders and generative adversarial networks. For the random appearance of MVs, the proposed method outperforms 97% of the scenarios with a reconstruction gain that ranges 1.04-1.45. For the other MVs mechanisms, the proposed method improves the reconstruction in at least 69% of the experiments, with a gain of 1.13-1.91. Conclusion: The findings of the proposed approach showed that the reconstructive capacity of the average code outperforms in most of the scenarios its competitors and close to the best solution in the rest of the scenarios. The integration of the MI paradigm into latent representations of data and the computation of average codes allow a more robust representation of the data and enables the enhancement of current state-of-the-art methods for high MVs rates.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Mortality prediction enhancement in end-stage renal disease, A machine learning approach

  • Macias Toro, Edwar Hernando|||0000-0001-5568-9237
  • Morell, Antoni|||0000-0003-2249-8594
  • Serrano, Javier|||0000-0003-1235-2145
  • Lopez Vicario, Jose|||0000-0002-3574-4697
  • Ibeas, Jose|||0000-0002-1292-7271
In this work, we propose to combine massive variables collected during the evolution of patients in end-stage renal disease (ESRD), along with machine learning techniques to improve mortality prediction in ESRD. This work was carried out with a retrospective cohort of 261 patients, their evolution from diagnoses, laboratory tests, and variables recorded during haemodialysis sessions was combined. Random forest (RF) was used to explore the inference of the variables and define a base performance for long short-term memory (LSTM) recurrent neural networks. Then, LSTMs were trained with several groups of variables chosen by expert staff, the ones found by RF and all the available ones. The best performance was obtained using all the variables, but the ones found by RF had better predictive capacity than those chosen with expert knowledge. Integrating the three sources of information supposes an improvement in more than 4% in the area under the receiver operating characteristic curve. The approach is sufficientlyrobust to predict mortality at different time ranges. The massive integration of variables from patients in ESRD, together with the use of LSMTs, supposes an exceptional improvement in the predictive models of mortality. In conclusion, the machine learning approach can lead to a change in the paradigm in the analysis of predictive factors in mortality in ESRD.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Adaptive beaconing for RSU-based intersection assistance systems, Protocols analysis and enhancement

  • Boquet, Guillem|||0000-0002-8683-0421
  • Pisa, Ivan|||0000-0003-3931-9257
  • Lopez Vicario, Jose|||0000-0002-3574-4697
  • Morell, Antoni|||0000-0003-2249-8594
  • Serrano, Javier|||0000-0003-1235-2145
Current envisaged cooperative vehicular applications require moderate to severe requirements of reliability and latency according to their purpose. Dedicated Short Range Communications (DSRC)-based applications mainly rely on the periodic exchange of information that under certain circumstances may cause congestion problems on the communication channel obtaining unreliable and outdated information at application level. Adaptive beaconing protocols adapt transmission parameters to different criteria such as the channel load and application requirements to improve the overall performance of the vehicle network. Nevertheless, it has not been determined yet if the information disseminated by these protocols is suitable enough for the implementation of specific applications, e.g., Road Side Unit (RSU)-based Intersection Assistance Systems (IAS) like Intersection Collision Risk Warning (ICRW). In this context, we first analyze the network behavior in a realistic simulated intersection area where probability of packet reception becomes difficult to predict and models become highly complex. In that scenario, we present a critical analysis on the performance of current EU and US decentralized congestion control protocols while their performance is evaluated with respect to tracking accuracies required by Intelligent Transportation System (ITS) applications. Results obtained lead us to conclude that adaptation criteria of beaconing protocols is not able to support different safety applications at the same time, that is, there is a tradeoff in the selection of such criteria between enhancing applications supporting vehicles or infrastructure. In that sense, we discuss and provide novel adaptation criteria (Intersection Assistance State Machine, IASM) to improve the performance of beaconing protocols towards assisting safety RSU-based IAS. Finally, we propose and validate through simulations a novel beaconing protocol (Intersection Assistance Protocol, IAP) that improves performance over studied protocols.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

A variational autoencoder solution for road traffic forecasting systems, missing data imputation, dimension reduction, model selection and anomaly detection

  • Boquet, Guillem|||0000-0002-8683-0421
  • Morell, Antoni|||0000-0003-2249-8594
  • Serrano, Javier|||0000-0003-1235-2145
  • Lopez Vicario, Jose|||0000-0002-3574-4697
Efforts devoted to mitigate the effects of road traffic congestion have been conducted since 1970s. Nowadays, there is a need for prominent solutions capable of mining information from messy and multidimensional road traffic data sets with few modeling constraints. In that sense, we propose a unique and versatile model to address different major challenges of traffic forecasting in an unsupervised manner. We formulate the road traffic forecasting problem as a latent variable model, assuming that traffic data is not generated randomly but from a latent space with fewer dimensions containing the underlying characteristics of traffic. We solve the problem by proposing a variational autoencoder (VAE) model to learn how traffic data are generated and inferred, while validating it against three different real-world traffic data sets. Under this framework, we propose an online unsupervised imputation method for unobserved traffic data with missing values. Additionally, taking advantage of the low dimension latent space learned, we compress the traffic data before applying a prediction model obtaining improvements in the forecasting accuracy. Finally, given that the model not only learns useful forecasting features but also meaningful characteristics, we explore the latent space as a tool for model and data selection and traffic anomaly detection from the point of view of traffic modelers.