Benchmark Simulation Model Research Articles

Monitoring of wastewater treatment process based on multi-stage variational autoencoder

The wastewater treatment process (WWTP) is a physical and biochemical reaction process with multi-stage, non-linear and non-Gaussian characteristics. The multi-stage means that the data has diversity in different substages. In the process monitoring of the WWTP, Affinity Propagation (AP) algorithm is first used to divide the data of the WWTP into stages to process the stage characteristics of data. Next, the capability of Variational Auto-Encoder (VAE) monitoring model to restrict the Gaussian distribution in hidden layers is utilized to address the coexistence of non-Gaussian and nonlinearity. Finally, to illustrate the superiority and feasibility, the proposed model is conducted on the Benchmark Simulation Model 1 (BSM1). The experimental result illustrates that the multistage variational autoencoder (M-VAE) can extract the characteristics of data more comprehensively, with an improvement of average monitoring accuracy by 37.8%, 2.7%, 12.7% and 0.52% in 10/8 process faults compared to the state-of-the-art fault monitoring methods Auto-encoder (AE), VAE, Deep Recurrent Neural Network (DRNN), deep recurrent network with high-order statistic information (HSI-DRNN) respectively.

Causal Network Structure Learning Based on Partial Least Squares and Causal Inference of Nonoptimal Performance in the Wastewater Treatment Process

Due to environmental fluctuations, the operating performance of complex industrial processes may deteriorate and affect economic benefits. In order to obtain maximal economic benefits, operating performance assessment is a novel focus. Therefore, this paper proposes a whole framework from operating performance assessment to nonoptimal cause identification based on partial-least-squares-based Granger causality analysis (PLS-GC) and Bayesian networks (BNs). The proposed method has three main contributions. First, a multiblock operating performance assessment model is established to correspondingly extract economic-related information and dynamic information. Then, a Bayesian network structure is established by PLS-GC that excludes the strong coupling of variables and simplifies the network structure. Lastly, nonoptimal root cause and and nonoptimal transmission path are identified by Bayesian inference. The effectiveness of the proposed method was verified on Benchmark Simulation Model 1.

Fractional order-based hierarchical controller design and evaluation with Bürger-Diehl settler model in a total nitrogen removal wastewater treatment process.

The primary objective of this study was to establish two-level structured control techniques based on the globally known benchmark simulation model no. 1 (BSM1) and the Bürger-Diehl settler model in order to improve effluent quality. The latter was based on the activated sludge model no. 1 (ASM1), while the classic Takacs model was superseded by the more recent Bürger-Diehl settler model with enhanced predictive potential. A two-level hierarchical control structure was considered to maintain the dissolved oxygen concentration basing on the ammonia levels and also a nitrate controller was considered to improve nitrogen removal efficiency. Fractional order PI controllers were considered at the secondary level and advanced control techniques, namely, MPC and fuzzy, were implemented at the primary level. Two advance control schemes, being, FPI-MPC and FPI-fuzzy were designed in the present work. The controllers were designed based on the plant model which was identified using prediction-error minimization method. It was observed that the implemented control strategies in consideration with the plant modifications showed a profound impact in improving the plant performance in terms of the effluent quality. FPI-fuzzy resulted in noticeable 60% and 53% reduction in total nitrogen violations for dry and storm climatic conditions, respectively.

Knowledge-Data-Driven Flexible Switching Control for Wastewater Treatment Process

The wastewater treatment process (WWTP), including multiple operation conditions, is a complex industrial process with strong nonlinearity and time-varying dynamics. It is a challenge to design an effective controller for this kind of process. To solve this problem, a knowledge-data-driven flexible switching controller is designed and analyzed to achieve reliable control performance. First, a flexible switching control strategy is proposed to build multiple operation models to approximate different operation conditions. Then, multiple subcontrollers are designed for the multiple operation models to suppress the nonlinearity and time-varying dynamics of WWTP. Second, a knowledge-data-driven framework, based on data sharing and knowledge-driven mechanisms, is developed to learn the subcontrollers. Then, the internal data and external knowledge can be fully leveraged to improve the control accuracy. Third, the stability of the proposed control strategy is given in detail. The corresponding stability conditions are provided to guide its application. Finally, the control performance is confirmed on the benchmark simulation model No. 1. The results demonstrate that the proposed KDFSC can achieve excellent control performance.

Dynamic alpha factors: Prediction in time and evolution along reactors

The performance of aeration – one of the most costly processes at water resource recovery facilities – is heavily impacted by actual wastewater characteristics which are commonly taken into account using the alpha factor (α). This factor varies depending on hydraulic and organic loading; such variance includes both time and spatial fluctuations. In standard design practice, it is often considered as a fixed number, or at best, a predefined time series. The objective of this paper is to propose a new method of predicting plantwide trends in the α factor through the use of process modelling which can accommodate diurnal and seasonal variations. The authors’ concept takes into account the dependence of α on sludge retention time in the form of degradation kinetics, the effects of organic loading (influent filtered COD), the presence or absence of anoxic zones, diffuser depth, and the impact of high MLSS found in certain, e.g., MBR, technologies. The developed model was calibrated using data from numerous facilities, relying on off-gas measurements and tests in clean and process water. Model validation was carried out against averaged α factor gradient data from one plant, and against diurnal air flow measurements from another. The Benchmark Simulation Model 1 configuration was used to demonstrate the applicability of the proposed model – in estimation of blower energy consumption and peak air flow requirements – comparing it with constant and scheduled α factor-based approaches.

Dynamic optimization of wastewater treatment process based on novel multi-objective ant lion optimization and deep learning algorithm

In this paper, a novel dynamic optimization control based on multi-objective ant lion optimization (DMOALO) and deep learning algorithm is proposed, which could optimize energy consumption (EC) and effluent quality (EQ) simultaneously in the wastewater treatment processes. In order to overcome the difficulty that there is no clear function relationship between the dynamic parameters and the performance indicators, a novel deep belief network (DBN) model for predicting EC and EQ as objective function is proposed. Then, this objective function with constraints is solved by DMOALO method, and the optimal solution would be selected by the intelligent decision system. Finally, Proportional Integral (PI) controllers would be used to track and control these optimal dynamic parameters. DBN-DMOALO-PI optimization control strategy is evaluated in benchmark simulation model 1(BSM1), the simulation results demonstrated this novel optimization control strategy could reduce the EC significantly while meeting the standards of effluent quality parameters. EC is decreased by 3.31% compared with PI optimization control strategy. Therefore, this novel method may reduce the cost of wastewater treatment process effectively, and realize the carbon neutrality in wastewater treatment process.

How elevation dictates technology selection in biological wastewater treatment

Most wastewater treatment facilities are built using procedures from previous designs which are predominantly from sites and regions not located at high elevation. Recognizing this limitation, we assessed the effects of elevation above sea level on the suitability of process configurations and technologies as well as their associated energy costs. Using the International Water Association (IWA) benchmark simulation model No. 2 (modified Ludzack-Ettinger process layout) as a reference, we simulated scenarios including different activated sludge process configurations, operating under different environmental and process conditions. In order to include a wide sample of environmental conditions, data on atmospheric pressure, wastewater temperature, air temperature, and relative humidity (for average, warmest, and coldest months) were collected from municipal wastewater treatment plants located at different latitudes and elevations. The results confirm that elevation is a driver against the selection of diffused aeration technologies. Aeration costs for aerobic wastewater treatment are highly influenced by local project conditions, particularly by elevation and wastewater temperature, which together influence the driving force for oxygen transfer into water. When the driving force is low, operating costs are high. Recommendations for designing treatment processes effectively, including diffused aeration systems operating at high elevations above sea level, are proposed.

Integrated fault detection for industrial process monitoring based on multi-dimensional Taylor network

PurposeThis paper aims to provide a novel integrated fault detection method for industrial process monitoring.Design/methodology/approachA novel integrated fault detection method based on the combination of Mallat (MA) algorithm, weight-elimination (WE) algorithm, conjugate gradient (CG) algorithm and multi-dimensional Taylor network (MTN) dynamic model, namely, MA-WE-CG-MTN, is proposed in this paper. First, MA algorithm is taken as data pre-processing. Second, in virtue of approximation ability and low computation complexity owing to the simple structure of MTN, MTN dynamic models are constructed for each frequency band. Furthermore, the CG algorithm is used to discipline the model parameters and the outputs of MTN model of each frequency band are gained. Third, the authors introduce the WE algorithm to cut down the number of middle layer nodes of MTN, reducing the complexity of the network. Finally, the outputs of MTN model for each frequency band are superimposed to achieve outputs of MTN model, and fault detection is proceeded by the residual error generator based on the difference between the output of MTN model and the actual output.FindingsThe novel proposed method is used to perform fault detection for industrial process monitoring effectively, such as the Benchmark Simulation Model 1 wastewater treatment process.Originality/valueThe novel proposed method has generality and provides considerably improved performance and effectiveness, which is used to perform fault detection for industrial process monitoring. The proposed method has good robustness, low complexity and easy implementation.

About the classical and structural controllability and observability of a common class of activated sludge plants

In this work, the stability, controllability and observability properties of a class of activated sludge plants are analysed. Specifically, the five biological reactors and the secondary settler in the Benchmark Simulation Model no. 1 (BSM1) are studied. For the task, we represented the plant as a dynamical system consisting of 145 state variables, 13 controls, 14 disturbances and 15 outputs and as a complex networks to study its full-state controllability and observability properties from a structural and a classical point of view. By analysing the topology of the network, we show how this class of systems is controllable but not observable in a structural sense, and thus how it is controllable but not observable in a classical sense for almost all possible realisations. We also show how a linearisation commonly used in the literature is neither full-state controllable nor full-state observable in the classical sense. The control and observation efforts are quantified in terms of energy- and centrality-based based metrics.

Model-based analysis of the effect of temperature in biological wastewater treatment plants for simultaneous removal of organic matter, nitrogen, and phosphorous

The effect of temperature on the phosphorous, nitrogen, and organic matter removal in an activated sludge system(ASS) has been assessed in this research. Benchmark Simulation Model No.1 (BSM1-P) with an ASS (ASM3bioP) is used and the temperature is chosen between 10 to 35°C. The kinetic expressions for the maximum growth rate of heterotrophic biomass, autotrophic, and phosphate accumulating organisms and their decay rates are considered. Total ammonia, nitrogen, and phosphorous in the effluent are analysed and when the range of temperature is less than 15°C and greater than 30°C, the effluent quality deviates from the legal requirements.

Sliding window neural network based sensing of bacteria in wastewater treatment plants

Ensuring the performance of wastewater treatment processes is important to guarantee that the final treated wastewater quality is safe for reuse. However, bacterial concentration present along the different stages of treatment process is not easily measured routinely for the plant operators. In this paper, a moving horizon sensing approach based on neural networks is proposed to estimate the bacterial concentration in wastewater sampled along different stages of the plant. Due to the difficulties to measure the bacteria and the lack of a sufficiently large dataset, a Wasserstein generative adversarial network (WGAN) is designed to generate synthetic data. The Wasserstein critic loss is computed on a held-out validation set to evaluate the WGAN. Then, the generated data is used to train a long short term memory (LSTM) neural network that is developed to predict the biomass concentration and update the LSTM weights by a sliding window learning approach. Two datasets for WWTP are used to test the proposed method: first, effluent concentrations simulated using a benchmark simulation model no.1 (BSM) based on membrane bioreactor (MBR), where three different weather profiles of influent data were considered then, sampled data from MBR plant at King Abdullah University of Science and Technology (KAUST). Finally, the prediction results indicate that WGAN successfully generates realistic samples that are used to train the LSTM neural network. In addition, estimation performance of the proposed method is compared with a multilayer perceptron neural network (MLP-NN). Results showed that the proposed method improves the bacteria estimation performance compared to MLP-NN.

Hierarchical nonlinear model predictive control with multi-time-scale for wastewater treatment process

Different time scales are inevitable for the controlled variables of wastewater treatment process (WWTP), which may degrade the operation performance or even destroy the stability of the closed-loop system. In this paper, a hierarchical nonlinear model predictive control (HNMPC) strategy is developed to deal with the different time scales of controlled variables to improve the operation performance of WWTP. The main merits of HNMPC are three-fold. First, a hierarchical control structure is developed to obtain reasonable control laws. Then, the controlled variables with different time scales can be tracked by different level controllers. Second, a gradient method is developed to solve the hierarchical optimization problem of HNMPC to reduce the computational cost. Then, the fast response of HNMPC can be achieved to improve the operation performance. Third, the stability of HNMPC is proved in theory. Then, the corresponding stability conditions are given to guide the practical application. Finally, the testing results on the benchmark simulation model verify that the proposed HNMPC can achieve suitable operation performance in terms of control accuracy.

Energy Flexibility Chances for the Wastewater Treatment Plant of the Benchmark Simulation Model 1

Future energy systems must mainly generate electricity from renewable resources. To deal with the fluctuating availability of wind and solar power, new versatile electricity markets and sustainable solutions concentrating on energy flexibility are needed. In this research, we investigated the potential of energy flexibility achieved through demand-side response for the wastewater treatment plant of the Benchmark Simulation Model 1. First, seven control strategies were simulated and assessed. Next, the flexibility calls were identified, two energy flexibility scenarios were defined and incorporated into the model, and the control strategies were evaluated anew. In this research, the effluent ammonia concentration needed to be maintained within the limits for as long as possible. Strategy 5, which controlled ammonia in Tank 5 at a low value and did not control any nitrate in Tank 2, of Scenario 1, which was characterized by an undetermined on/off aeration cycle, was then found to be the best. Although this control strategy led to high total energy consumption, the percentage of time during which aeration was nearly suspended was one of the highest. This work proposes a methodology that will be useful to plant operators who should soon reduce energy consumption during spikes in electricity prices.

Design of Feedback Control Strategies in a Plant-Wide Wastewater Treatment Plant for Simultaneous Evaluation of Economics, Energy Usage, and Removal of Nutrients

Simultaneous removal of nitrogen and phosphorous is a recommended practice while treating wastewater. In the present study, control strategies based on proportional-integral (PI), model predictive control (MPC), and fuzzy logic are developed and implemented on a plant-wide wastewater treatment plant. Four combinations of control frameworks are developed in order to reduce the operational cost and improve the effluent quality. As a working platform, a Benchmark simulation model (BSM2-P) is used. A default control framework with PI controllers is used to control nitrate and dissolved oxygen (DO) by manipulating the internal recycle and oxygen mass transfer coefficient (KLa). Hierarchical control topology is proposed in which a lower-level control framework with PI controllers is implemented to DO in the sixth reactor by regulating the KLa of the fifth, sixth, and seventh reactors, and fuzzy and MPC are used at the supervisory level. This supervisory level considers the ammonia in the last aerobic reactor as a feedback signal to alter the DO set-points. PI-fuzzy showed improved effluent quality by 21.1%, total phosphorus removal rate by 33.3% with an increase of operational cost, and a slight increase in the production rates of greenhouse gases. In all the control design frameworks, a trade-off is observed between operational cost and effluent quality.

Integrated supervisory and override control strategies for effective biological phosphorus removal and reduced operational costs in wastewater treatment processes

A novel control strategy is developed for a municipal wastewater treatment plant (WWTP) consisting of anaerobic-anoxic-aerobic reactors. The idea is to generate more organic matter with a reduction of nitrate concentration in the anoxic section so that more biological phosphorus (P) removal happens. For this, the Supervisory and Override Control Approach (SOPCA) is designed based on the benchmark simulation model (BSM1-P) and is evaluated by considering dynamic influent. In the supervisory layer, proportional integral (PI) and fuzzy controllers are designed. Additionally, dissolved oxygen (So) control loops in the aerobic reactors are designed. PI controller is designed for control of nitrate levels in the anoxic reactors and is integrated with override control and supervisory layer. It is found that the novel SOPCA approach gave better nutrient removal with slightly higher operating costs when So control is not put in place. With three So control loops in place, the WWTP showed better effluent quality and lower cost. Here, the improved removal efficiency of 28.5% and 20.5% are obtained when Fuzzy and PI control schemes respectively are used in the supervisory layer. Therefore, the application of SOPCA is recommended for a better P removal rate.

Type-2 fuzzy broad learning controller for wastewater treatment process

Affected by multiple operation conditions, wastewater treatment process (WWTP) is a complex industrial process with strong nonlinearity and disturbance. How to enhance the rapid tracking response-ability and robustness of the controller is still a challenge when the operation conditions change. To solve this problem, a type-2 fuzzy broad learning controller (T2FBLC) is proposed in this paper. First, a type-2 fuzzy broad learning system (T2FBLS) is constructed in T2FBLC by replacing nodes in feature window with a group of interval type-2 fuzzy submodules. Then, the proposed T2FBLC can take tracking error as inputs while its outputs acting on WWTP to directly obtain a control law, and the controller makes a quick tracking response in different operation conditions. Second, the weight parameters of T2FBLC are adjusted by using the gradient descent method to ensure the control performance. In this way, the developed T2FBLC can realize online learning to reduce tracking errors. Third, according to the Lyapunov function theory, the stability of control strategy is proved. Finally, benchmark simulation model 1 (BSM1) is adopted to verify the effectiveness of T2FBLC. The experimental results prove the applicability and superior tracking performance of the proposed method.

Adaptive dynamic prediction of effluent quality in wastewater treatment processes using partial least squares embedded with relevance vector machine

Recycling of water resources through wastewater treatment process (WWTP) is widely considered for a viable option for different water demands and sustainable production due to water shortage and pollution. Thus, accurate and real-time prediction of effluent quality is of vital importance to maintain the stable process control of WWTP system. Taking into account the complex biochemical characteristics of WWTP, an adaptive dynamic nonlinear partial least squares (PLS) model has been proposed to improve the prediction performance and stability of effluent quality indexes. First, an adaptive matrix expansion scheme is introduced to exploit the specific dynamic features of different data sets. Then the linear PLS model is conducted and the inner function between each pair of latent variables is rebuilt by relevance vector machine (RVM) with sparse and probabilistic structure, which is robust for the nonlinearity and random noises among process variables. The performance of the proposed adaptive dynamic RVM-based PLS (D-RVM-PLS) model is evaluated through two case studies based on benchmark simulation model No.1 and a real industrial WWTP, respectively. Experimental results show the superiority of the proposed model in prediction accuracy, stability, and execution efficiency. For the modeling accuracy of effluent chemical oxygen demand in real industrial case, adaptive D-RVM-PLS provides the lowest root-mean-square error, which is decreased by approximately 5.01%–49.19% in comparison with linear PLS model, Gaussian process regression-based PLS model, and their dynamic models without adaptive selection procedure.

A supervisory fuzzy logic control scheme to improve effluent quality of a wastewater treatment plant.

The application of control strategies in wastewater treatment plants has increased to improve their performance for treating influent. The fuzzy logic controller plays a vital role in this work and simulation work was carried out in a benchmark simulation model no.1 (BSM1) framework. The attempted work proposes two control schemes with the objectives of improving the effluent quality and minimizing the number of measurements taken from the plant. The design of fuzzy control schemes is based on five inputs and six outputs in order to accomplish the objectives. Experimental results show improvement in the effluent quality and increase in the efficacy of the control system. The proposed design is implemented using MATLAB with the adaptation in 2014a.

Intelligent Optimal Control System With Flexible Objective Functions and Its Applications in Wastewater Treatment Process

Optimal control system has been considered as a valuable technique to enhance the reliability and security of wastewater treatment process (WWTP). However, due to the complex environments, it is difficult to realize the optimal control with changeable operational conditions in WWTP. To overcome this problem, an intelligent optimal control system with flexible objective functions (IOCS-FOF) was proposed in this paper. The main merits of this proposed IOCS-FOF were shown as follows. First, an optimal control system scheme was developed, where different time-scale operational objectives were detailed to describe the operational features. Second, a flexible objective strategy was designed to determine suitable objective functions, which could adapt to complex environments of WWTP. Third, a novel dynamic multiobjective optimization algorithm for flexible objectives (FO-DMOA) was developed to obtain the optimal solutions of IOCS-FOF. Finally, the proposed IOCS-FOF was applied in the benchmark simulation model No. 1 (BSM1) to confirm its technique capability. The results demonstrate that this proposed method can improve the operation performance of WWTP.

Reinforcement learning-based particle swarm optimization for sewage treatment control

To solve the problem of high-energy consumption in activated sludge wastewater treatment, a reinforcement learning-based particle swarm optimization (RLPSO) was proposed to optimize the control setting in the sewage process. This algorithm tries to take advantage of the valid history information to guide the behavior of particles through a reinforcement learning strategy. First, an elite network is constructed by selecting elite particles and recording their successful search behavior. Then the network is trained and evaluated to effectively predict the particle velocity. In the periodic wastewater treatment process, the RLPSO runs repeatedly according to the optimized cycle. Finally, RLPSO was tested based on Benchmark Simulation Model 1 (BSM1) of sewage treatment, and the simulation results showed that it could effectively reduce the energy consumption on the premise of ensuring qualified water quality. Furthermore, the performance of RLPSO was analyzed using the benchmarks with higher dimension, which verifies the effectiveness of the algorithm and provides the possibility for RLPSO to be applied to a wider range of problems.