Transfer Learning in Wastewater Treatment Plant Control Design: From Conventional to Long Short-Term Memory-Based Controllers.

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.

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

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.

UV light dosage distribution over irregular respirator surfaces. Methods and implications for safety.

The SARS-CoV-2 pandemic has led to a global decrease in personal protective equipment (PPE), especially filtering facepiece respirators (FFRs). Ultraviolet-C wavelength is a promising way of decontamination, however adequate dosimetry is needed to ensure balance between over and underexposed areas and provide reliable results. Our study demonstrates that UVGI light irradiance varies significantly on different respirator angles and propose a method to decontaminate several masks at once ensuring appropriate dosage in shaded zones. An UVGI irradiator was built with internal dimensions of 69.5 × 55 × 33 cm with three 15 W UV lamps. Inside, a grating of 58 × 41 × 15 cm was placed to hold the masks. Two different flat fold respirator models were used to assess irradiance, four of model Aura 9322 3 M of dimensions 17 × 9 × 4 cm (tri-fold), and two of model SAFE 231FFP3NR (bi-fold) with dimensions 17 × 6 × 5 cm. An STN-SilverNova spectrometer was employed to verify wavelength spectrum and surface irradiance. A simulation was performed to find the irradiance pattern inside the box and the six masks placed inside. These simulations were carried out using the software DIALUX EVO 8.2. The data obtained reveal that the irradiance received inside the manufactured UVGI-irradiator depends not only on the distance between the lamps' plane and the base of the respirators but also on the orientation and shape of the masks. This point becomes relevant to assure that all the respirators inside the chamber receive the correct dosage. Irradiance over FFR surfaces depend on several factors such as distance and angle of incidence of the light source. Careful irradiance measurement and simulation can ensure reliable dosage in the whole mask surface, balancing overexposure. Closed box systems might provide a more reliable, reproducible UVGI dosage than open settings.

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.

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.

ANN-Based Soft Sensor to Predict Effluent Violations in Wastewater Treatment Plants.

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 N H ) and total nitrogen ( S N t o t ). S N t o t is a limiting nutrient and can therefore cause eutrophication, while nitrogen in the S N H 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.

Tuning rules for robust FOPID controllers based on multi-objective optimization with FOPDT models.

In this paper a set of optimally balanced tuning rules for fractional-order proportional-integral-derivative controllers is proposed. The control problem of minimizing at once the integrated absolute error for both the set-point and the load disturbance responses is addressed. The control problem is stated as a multi-objective optimization problem where a first-order-plus-dead-time process model subject to a robustness, maximum sensitivity based, constraint has been considered. A set of Pareto optimal solutions is obtained for different normalized dead times and then the optimal balance between the competing objectives is obtained by choosing the Nash solution among the Pareto-optimal ones. A curve fitting procedure has then been applied in order to generate suitable tuning rules. Several simulation results show the effectiveness of the proposed approach.