Papermaking Wastewater Treatment Research Articles

Multiobjective Optimization of Papermaking Wastewater Treatment Processes under Economic, Energy, and Environmental Goals.

Due to the heterogeneity of recycled paper materials and the production conditions, pollutants in papermaking wastewater fluctuate sharply over time. Quality control of the papermaking wastewater treatment process (PWTP) is challenging and costly. As regulations are also growing about the environmental effects of the PWTP on greenhouse gas (GHG) emission, energy consumption, etc., the PWTP formulates a complex multiobjective optimization problem. This research established a multiagent deep reinforcement learning framework to simultaneously optimize process cost, energy consumption, and GHG emission in the PWTP, subjected to the effluent quality, to realize economic, energy, and environmental (3E) goals. The biological treatment process of wastewater in paper mills was simulated using benchmark simulation model no. 1 (BSM1). The data generated based on the BSM manual was utilized for model training, and real data acquired from a local papermaking factory was used to estimate the model performance. The results show that the proposed method outperforms conventional techniques in identifying the best control strategies for multiple targets.

Treatment of secondary fiber papermaking wastewater with aerobic granular sludge cultured in a sequencing batch biofilter granular reactor

Abstract Secondary fiber papermaking wastewater (SPW) has received increasing interest because of its enormous discharge, typical high COD, and low biodegradability. The dense and compact structure of aerobic granular sludge (AGS) results in a high sludge concentration in the sequencing batch biofilter granular reactor (SBBGR), which provides superior conditions for the treatment of highly concentrated wastewater. This study constructed an SBBGR to treat SPW, investigated the changes in the species and structural characteristics of pollutants during wastewater treatment, and analyzed the dominant populations that can degrade pollutants in the SPW. The results showed that SBBGR had a good treatment effect on SPW and the removal rates of COD, TN, TP, SS, and color were 90.3 %, 81.9 %, 85.2 %, 73.1 %, and 75.1 % respectively with the influent organic load of 8.1 kg COD m−3 d−1, which was attributed to its outstanding biodegradability. The types and quantities of aromatic compounds in SPW were significantly reduced, according to the results of FTIR, UV–vis, and GC-MS. Microbial community analysis showed that the presence of Bacteroidetes, Proteobacteria, Macellibacteroides, Chlorobium, and Brachymonas in the SBBGR was responsible for the outstanding biodegradation of pollutants in the SPW. In summary, the treatment of SPW with SBBGR is extremely promising for applications.

Interpretable GHG emission prediction for papermaking wastewater treatment process with deep learning

The content of pollutants in papermaking wastewater is highly varied due to heterogeneous raw materials, product types, and biochemical process conditions, resulting in significant uncertainty of GHG emissions mitigation in the treatment process. This study established a modified Benchmark Simulation Model no.1-based mechanism model to reveal the characteristics of GHG emissions and support GHG reduction in the papermaking wastewater treatment process. Due to its heavy dependence on the Benchmark Simulation Model No. 1 (BSM1) and plentiful parameters, it was instead further proposed Deep Neural Networks (DNN) models and Long Short-Term Memory (LSTM) models to estimate GHG emissions with high accuracy (R2 > 0.94) greatly reduced computational complexity (8920.6 times). The global sensitivity analysis upon DNN revealed key factors for GHG emission with strong explainability, supporting the development of GHG reduction control strategies for the papermaking wastewater treatment process.

New insights into toxicity reduction and pollutants removal during typical treatment of papermaking wastewater

Papermaking wastewater contained various of toxic and hazardous pollutants that pose significant threats to both the ecosystem and human health. Despite these risks, limited research has addressed the detoxification efficiency and mechanism involved in the typical process treatment of papermaking wastewater. In this study, the acute toxicity of papermaking wastewater after different treatment processes was assessed using luminousbacteria, zebrafish and Daphnia magna (D. magna). Meanwhile, the pollution parament of the corresponding wastewater were measured, and the transformation of organic pollutant in the wastewater was identified by three-dimensional fluorescence and other techniques. Finally, the possible mechanism of toxicity variation in different treatment processes were explored in combination with correlation analyses. The results showed that raw papermaking wastewater displayed high acute toxicity to luminousbacteria, and exhibited slight acute toxicity and acute toxicity effect to zebrafish and D. magna, respectively. After physical and biochemical processes, not only the toxicity of the wastewater to zebrafish and D. magna was completely eliminated, but also the inhibitory effect on luminousbacteria was significantly reduced (TU value decreased from 11.07 to 1.66). Among them, the order of detoxification efficiency on luminousbacteria was air flotation > hydrolysis acidification > IC > aerobic process. Correlation analyses revealed a direct link between the reduced of Total Organic Carbon (TOC) and Chemical Oxygen Demand (COD) and the detoxification efficiency of the different processes on the wastewater. In particular, the removal of benzene-containing aromatic pollutant correlated positively with decreased toxicity. However, the Fenton process, despite lowering TOC and COD, increased of the acute toxicity of the luminousbacteria (TU value increased from 1.66 to 2.33). This may result from the transformation generation of organic pollutant and oxidant residues during the Fenton process. Hence, oxidation technologies such as the Fenton process, as a deep treatment process, should be more concerned about the ecological risks that may be caused while focusing on their effectiveness in removing pollutant.

Preparation of the modified chitosan flocculant introduced acryloyloxyethyl trimethyl ammonium chloride and 2-acrylamido-2-methyl propane sulfonic acid for the treatment of papermaking wastewater

To solve the shortcomings of poor solubility, low cationic strength, and small molecular weight of chitosan (CTS), acryloyloxyethyl trimethyl ammonium chloride (DAC) and 2-acrylamido-2-methylpropanesulfonic acid (AMPS) were introduced into the amino group of chitosan by graft copolymerization, and the modified chitosan flocculant CTS-DAC-AMPS was successfully prepared. The performance of CTS-DAC-AMPS in the treatment of papermaking wastewater was investigated, and the mechanism of the flocculation process was analyzed. The results showed that the crystal habit of CTS-DAC-AMPS was reduced, and the solubility range was broadened compared with CTS due to the introduction of DAC and AMPS. In addition, CTS-DAC-AMPS with quaternary ammonium and sulfonic groups prompted its cationic strength stronger than CTS. In addition to high thermal stability, CTS-DAC-AMPS, composed of two CTS molecules, one DAC molecule, and one AMPS molecule, had a long molecular chain. The results of flocculation experiments showed that the performance of CTS-DAC-AMPS in treating papermaking wastewater was better than that of unmodified CTS and commercially available flocculants. Based on the experimental results, the mechanism of CTS-DAC-AMPS treatment of papermaking wastewater was mainly charge neutralization.

SBR-Extended Kalman Filter model-based fault diagnosis and signal reconstruction for the papermaking wastewater treatment process

In the study, for an existing paper mill, to realize the fault diagnosis and further fault signal reconstruction for the papermaking SBR wastewater treatment process, a novel model-based SBR-EKF (Extended Kalman Filter) fault diagnosis model has been proposed. Combining the SBR process model and EKF method, using the field 120 sets of normal data of dissolved oxygen (DO) and level (L) from a paper mill, the model-based SBR-EKF fault diagnosis model for the papermaking SBR wastewater treatment process was established, and the weighted sum of squared residuals thresholds (WSSR0) was determined off-line. Subsequently, based on the normal data, four common types of faults, fixed bias, drift bias, total failure, and precision degradation, were generated and applied to the developed SBR-EKF model for on-line monitoring. The fault diagnostic results show that, by comparing the calculated WSSR with the obtained WSSR0, the developed model-based SBR-EKF model demonstrated acceptable fault detection rates for DO and L. Moreover, using the filtered value of the SBR-EKF model, the effective signal reconstructions for L and DO were realized. These investigation results reveal the effectiveness of the proposed SBR-EKF fault diagnosis model, achieving fault diagnosis with acceptable precision and reconstructed signal.

The performance and microbial community of anaerobic membrane bioreactor for high calcium papermaking wastewater treatment

High calcium papermaking wastewater challenges anaerobic biological technology applications, leading to sludge calcification and unstable reactor operation. This study employed an anaerobic membrane bioreactor (AnMBR) to treat high-calcium papermaking wastewater (1000 mg/L) and achieved an average chemical oxygen demand removal efficiency of 90.1%. No significant accumulation of volatile fatty acids was observed during the entire experimental period. The methane production capacity decreased with the increasing inlet calcium ion concentration, and the maximum methane production rate in Stage 4 was 115.4 mL·(gVSS·d)−1. The maximum transmembrane pressure reached was 4.33 kPa, and the sludge was primarily present in the form of flocs due to the hydraulic shear effects. Anaerolineaceae, Bacteroidetes_vadinHA17, Methanosaetaceae and Methanobacteriaceae were identified as the dominant bacterial species in Stage 4, correlating with the robust anaerobic digestion performance. In conclusion, the AnMBR exhibited a reliable and effective treatment method for high calcium papermaking wastewater.

Towards low-carbon papermaking wastewater treatment process based on Kriging surrogate predictive model

Papermaking wastewater contains a diverse range of organic carbon, nitrogen and other pollutants, which could lead to the emission of greenhouse gases (GHG) during biochemical treatment process. Despite the importance of decarbonizing the papermaking wastewater treatment process, the mechanisms underlying the generation of greenhouse gases remain elusive and no models currently exist to describe the process. To address this issue, this study employed benchmark simulation model No. 1 (BSM1) to simulate, the papermaking wastewater treatment process, and applied the steady-state output value of simulation to calculate the GHG emissions. Kriging surrogate model was applied to establish the emission model for GHG in the papermaking wastewater treatment process. The model provides a reference for the control and optimization of GHG emission reduction and a high accuracy was achieved with determination coefficient (R2) of above 96%. Further analysis of the parameter impact of process control on GHG emissions and the optimization effects of controllable variables contributes to the goal of reducing GHG emissions in the papermaking wastewater treatment process.

Papermaking wastewater treatment coupled to 2,3-butanediol production by engineered psychrotrophic Raoultella terrigena

The simultaneous bioremediation and bioconversion of papermaking wastewater by psychrotrophic microorganisms holds great promise for developing sustainable environments and economies in cold regions. Here, the psychrotrophic bacterium Raoultella terrigena HC6 presented high endoglucanase (26.3 U/mL), xylosidase (732 U/mL), and laccase (8.07 U/mL) activities for lignocellulose deconstruction at 15 °C. mRNA monitoring and phenotypic variation analyses confirmed that cold-inducible cold shock protein A (CspA) facilitated the expression of the cel208, xynB68, and lac432 genes to increase the enzyme activities in strain HC6. Furthermore, the cspA gene-overexpressing mutant (strain HC6-cspA) was deployed in actual papermaking wastewater and achieved 44.3%, 34.1%, 18.4%, 80.2% and 100% removal rates for cellulose, hemicellulose, lignin, COD, and NO3--N at 15 °C. Simultaneously, 2,3-butanediol (2,3-BD) was produced from the effluent with a titer of 2.98 g/L and productivity of 0.154 g/L/h. This study reveals an association between the cold regulon and lignocellulolytic enzymes and provides a promising candidate for simultaneous papermaking wastewater treatment and 2,3-BD production.

A hierarchical intelligent control strategy for greenhouse gas reduction in wastewater treatment process of paper mill

Due to the huge amounts of wastewater discharge and the high pollution loads in papermaking industry, many greenhouse gases (GHG) are emitted in the papermaking wastewater treatment process. The wastewater dissolved oxygen (DO) control has been considered as the most cost-effective control solution for GHG reduction in wastewater treatment plants (WWTP). However, the competition between contaminant removal efficiency and GHG reduction hinders the drastic reduction of GHG emissions from WWTP. In this study, based on the established integrated GHG emission model, explicitly considering the total GHG reduction targets on the premise of effluent compliance, an intelligent control scheme has been developed for an activated sludge process in a paper mill. Regarding DO as the controlled variable, the proposed hierarchical optimal proportional-integral (HOPI) control scheme was established consisting of three layers: 1) Layer 1 for the effluent quality estimation, 2) Layer 2 for the optimal DO set point determined by genetic algorithm with the influent variations to obey discharging norms and reduce GHG emissions, 3) Layer 3 for the DO tracking proportional integral (PI) control with the controller parameters adjusted by the back propagation neural network to track the dynamically optimized DO set points. The simulation results showed that, compared with the open-loop (OL) operation (averaged aeration, 10/h), the proposed HOPI control (averaged aeration, 7.9/h) reduced the GHG emissions by 12.54% under the premise of discharging norms, which was mainly attributed to the reduction of the aeration electricity consumption. In contrast, the PI control (averaged aeration, 12.9/h) increased the GHG emissions by 7.48% compared with the OL operation. Thus, the proposed HOPI control strategy has demonstrated potential for the application of GHG reduction in industrial WWTPs.

Integration of Zeolite Membrane Bioreactor With Granular Sludge-Based Anammox in High-Efficiency Nitrogen Removal From Iron Oxide Red Wastewater.

Acquisition of stable nitritation and efficient anammox play a crucial role in partial nitritation (PN) combined with anammox for nitrogen removal from ammonium-rich wastewater. Due to the limitation of ammonia-oxidizing bacteria (AOB) enrichment and nitrite-oxidizing bacteria (NOB) control in traditional membrane biological reactor (MBR), it can result in a lower nitrite production rate (NPR) and unstable PN, eventually reducing the nitrogen removal rate (NRR) via PN-anammox. In this study, we developed a zeolite membrane biological reactor (ZMBR) to enhance the PN of iron oxide red wastewater (IORW), in which the biofilm derived from the zeolite surface can provide free ammonia (FA)-containing microenvironment for AOB enrichment and NOB inhibition. The results showed that ZMBR can tolerate a higher influent nitrogen loading rate (NLR) of 2.78 kg/(m3⋅day) in comparison to the traditional MBR [2.02 kg/(m3⋅day)] and the NPR in ZMBR and traditional MBR were 1.39 and 0.96 kg/(m3⋅day), respectively. The mass concentration ratio of -N/-N ranged from 1.05 to 1.33 in ZMBR, suggesting a suitable condition for nitrogen removal via anammox. Subsequently, the domesticated granular sludge obtained from a paper-making wastewater treatment was used as the carrier of anammox bacteria to remove nitrogen. After 93 days of operation, the NRR was observed to be 2.33 kg/(m3⋅day) and high-throughput sequencing indicated that the relatively higher abundance (45.0%) of Candidatus Kuenenia stuttgartiensis was detected in the granular sludge of the bottom part of the reactor, which can produce more proteins and lipids, suggesting a good settleability. Overall, this study provides a high-efficient method to control PN and domesticate anammox for nitrogen removal from IORW.

Explorations of complex thermally induced phase separation (C-TIPS) method for manufacturing novel diphenyl ether polysulfate flat microporous membranes

A complex thermally induced phase separation (C-TIPS) method combining the advantages of non-solvent induced phase separation (NIPS) and thermally induced phase separation (TIPS) was proposed to prepare novel diphenyl ether polysulfate (De-PSE) flat membranes, using a good solvent Dimethyl acetamide (DMAC) and a neutral solvent Triethyl phosphate (TEP) as mixed solvents and a non-solvent Polyethylene glycol (PEG-400) as additive. The competition between NIPS and TIPS processes was regulated by adjusting the composition and temperature of quenching bath, so as to achieve fine tuning of membrane surface pore size, morphology, as well as permeability and mechanical property. The membrane cross section exhibited the coexistence of bi-continuous and finger-like pore structures. Compared with membranes prepared by the mainstream NIPS method, the pure water flux improved from 187.62 to 945.27 L m−2 h−1·bar−1 with a mean pore size increased from 30 nm to 195 nm, while the tensile strength enhanced from 2.31 to 5.89 MPa. This work demonstrated a simple strategy to improve the comprehensive performances of De-PSE membranes. Coupled with the strong acid-alkali resistance of the membrane, it greatly expanded the membrane application prospect, especially in the treatment of high polymer textile and papermaking wastewater with large volumes and strong alkalinity.

Recent advances in the treatment of lignin in papermaking wastewater.

More than 695.7millionm3 of papermaking wastewater is discharged globally. It contains a mixture of complex pollutants, of which lignin is the major constituent (600-1000mg/L) of papermaking black liquor, making it the second-largest energy-containing biomass globally and accounting for 47.4% and 59.4% of chemical oxygen demand (16,400 ± 120mg/L) and chroma (3100 ± 22.32mg/L) of papermaking wastewater. The complex process and dissolved pollutants are responsible for high pH, biochemical oxygen demand, chemical oxygen demand, total suspended solids, dark color, and toxicity. Papermaking wastewater has emerged as a substantial source of environmental pollution as the conventional wastewater treatment processes are high cost and seldom efficacious. This work introduces the shortcomings of the common treatment methods for papermaking wastewater and lignin, focusing on lignin biodegradation and discussing the metabolic pathways and application prospects of lignin-degrading microbial species. A comprehensive review of the existing lignin treatment methods has proposed that the reasonable amalgamation of biodegradation and various physicochemical techniques are environmentally friendly, sustainable, and economical. Lignin extraction from papermaking wastewater by technology combination is an effective approach to recover valuable organic materials and detoxify wastewater. This review focuses on recent breakthroughs and future trends in papermaking wastewater treatment and lignin removal, with special emphasis on biodegradation, recovery, and utilization of lignin, providing guidance for the mechanism exploration of lignin-degrading microorganisms and the optimization of high-value chemical production.

Water quality prediction model using Gaussian process regression based on deep learning for carbon neutrality in papermaking wastewater treatment system

Wastewater recycling is the measure with enormous potentiality to achieve carbon neutrality in wastewater treatment plants. High-precision online monitoring can improve the stability of wastewater treatment system and help wastewater recycling. A new water quality prediction CSWLSTM-GPR model, which fused the spatial feature of convolutional neural network (CNN), the temporal feature of sharing-weight long short-term memory (SWLSTM) and the probabilistic reliability of Gaussian process regression (GPR), was applied for monitoring papermaking wastewater treatment system with high-precision point prediction and interval prediction. Compared with SWLSTM-GPR and CLSTM-GPR, RMSE of CSWLSTM-GPR reduced by more than 48.9% on effluent chemical oxygen demand (CODeff), MAE reduced by more than 49.3%, R2 increased by more than 25.14%, R increased by more than 7.07%. And for the effluent suspended solids (SSeff), CSWLSTM-GPR had better predictive results than SWLSTM-GPR and CSWLSTM-GPR. Compared with SWLSTM-GPR, RMSE, MAE, R, R2 of CSWLSTM-GPR on effluent suspended solids (SSeff) were improved by 4.8%, 6.1%, 29.01% and 31.15%, respectively. Simulation results showed convincing comprehensive forecasting ability were obtained and the true values frequently stayed within the water quality range obtained by CSWLSTM-GPR model, which provided important insights for online monitoring, wastewater recycling and carbon neutrality of papermaking industry.

Monitoring of papermaking wastewater treatment processes using t-distributed stochastic neighbor embedding

A combination of t-distribution stochastic neighbor embedding with a Gaussian mixture model (t-SNE-GMM) is proposed for sensor fault detection in wastewater treatment processes. The proposed method can be used to handle the non-Gaussian and nonlinear characteristics of wastewater treatment processes simultaneously. The t-SNE method is first used to reduce the dimension of process data, and then GMM only uses the normal process data to accomplish fault detection. With manifold learning, the hybrid model can reduce computation complexity and improve detection accuracy. Two methods that combined GMM with principal component analysis (PCA-GMM) and kernel PCA-GMM (KPCA-GMM) are used for comparing with t-SNE-GMM. The fault detection performance was verified by simulating sensor faults in the wastewater treatment process. Among them, the fault detection rates of bias fault, drifting fault, and complete failure fault using t-SNE-GMM are increased by 67.8%, 5%, and 109.52%, respectively, compared with KPCA-GMM. Although the improvement of the fault detection rate of drifting faults is not obvious, it has an excellent performance in the false alarm rate. The combined method has the capability of detecting the sensor faults in the wastewater treatment process.

Fabricating novel PVDF-g-IBMA copolymer hydrophilic ultrafiltration membrane for treating papermaking wastewater with good antifouling property.

Ultrafiltration membranes are widely used for the treatment of papermaking wastewater. The antifouling performance of polyvinylidene fluoride (PVDF) ultrafiltration membranes can be improved by changing the hydrophilicity. Here, a novel amphiphilic copolymer material, PVDF grafted with N-isobutoxy methacrylamide (PVDF-g-IBMA), was prepared using ultraviolet-induced Cu(II)-mediated reversible deactivation radical polymerization. The amphipathic copolymer was used to prepare ultrafiltration membrane via NIPS. The prepared PVDF-g-IBMA ultrafiltration membrane was estimated using 1H NMR, FT-IR, and DSC. The contact angle, casting viscosity, and the permeation performance of the PVDF-g-IBMA ultrafiltration membrane were also determined. The pure water flux, bovine serum albumin removal rate, and pure water flux recovery rate of the PVDF-g-IBMA ultrafiltration membrane were 432.8 L·m-2·h-1, 88.4%, and 90.8%, respectively. Furthermore, for the treatment of actual papermaking wastewater, the chemical oxygen demand and turbidity removal rates of the membrane were 61.5% and 92.8%, respectively. The PVDF-g-IBMA amphiphilic copolymer ultrafiltration membrane exhibited good hydrophilicity and antifouling properties, indicating its potential for treating papermaking wastewater.

Neighborhood component analysis for modeling papermaking wastewater treatment processes.

It is of great importance to obtain accurate effluent quality indices in time for pulping and papermaking wastewater treatment processes. However, considering the complex characteristics of industrial wastewater treatment systems, conventional modeling methods such as partial least squares (PLS) and artificial neural networks (ANN) cannot achieve satisfactory prediction accuracy. As a supervised metric learning method, neighborhood component analysis (NCA) is able to significantly improve the prediction performance by training an appropriate model in metric space using the distance between samples for papermaking wastewater treatment processes. The results on two data sets show that NCA has a higher prediction accuracy compared with PLS and ANN. Specifically, NCA has the highest determination coefficient (R2) and the lowest root mean square error in a benchmark simulation data set. On the other hand, the results on the data from an industrial wastewater process indicate that NCA has better modeling accuracy and its R2 increases by 32.80% and 29.08% compared with PLS and ANN, respectively. NCA provides a feasible way to realize online monitoring and automatic control in wastewater treatment processes.

Quality-related monitoring of papermaking wastewater treatment processes using dynamic multiblock partial least squares

Environmental problems have attracted much attention in recent years, especially for papermaking wastewater discharge. To reduce the loss of effluence discharge violation, quality-related multivariate statistical methods have been successfully applied to achieve a robust wastewater treatment system. In this work, a new dynamic multiblock partial least squares (DMBPLS) is proposed to extract the time-varying information in a large-scale papermaking wastewater treatment process. By introducing augmented matrices to input and output data, the proposed method not only handles the dynamic characteristic of data and reduces the time delay of fault detection, but enhances the interpretability of model. In addition, the DMBPLS provides a capability of fault location, which has certain guiding significance for fault recovery. In comparison with other models, the DMBPLS has a superior fault detection result. Specifically, the maximum fault detection rate of the DMBPLS is improved by 35.93% and 12.5% for bias and drifting faults, respectively, in comparison with partial least squares (PLS).

Improvement in calcified anaerobic granular sludge performance by exogenous acyl-homoserine lactones

Given the high content of Ca2+ in waste paper recycling wastewater, the anaerobic granular sludge (AnGS) undergoes calcification during wastewater treatment and affects the treatment efficiency. To restore the activity of calcified AnGS and improve the performance of AnGS, four types of N-acyl-homoserine lactones (AHLs) were added to the AnGS system while papermaking wastewater treatment. The addition of N-butyryl-DL-homoserine lactone(C4-HSL) and N-octanoyl-DL-homoserine lactone (C8-HSL) had an inhibitory affect the COD removal efficiency and SMA of sludge at the inception. The addition of N-hexanoyl-L-homoserine lactone (C6-HSL) has no obvious effect on the COD removal efficiency, but can improve the SMA of sludge more obviously. The addition of N-(β-ketocaproyl)-DL-homoserine lactone (3O-C6-HSL) can increased COD removal efficiency and promoted SMA together obviously. The addition of C6-HSL and 3O-C6-HSL can increase volatile suspended solid (VSS)/total suspended solid (TSS), and regulate extracellular polymeric substance (EPS) secretion in AnGS. Analysis of microbial sequencing revealed changes in the microbial community structure following AHL addition, which enhanced the methane metabolism pathway in sludge. The addition of C6-HSL, C8-HSL, and 3O-C6-HSL increased Methanosaeta population, thus increasing the aceticlastic pathway in sludge. Thus, exogenous AHLs can play an important role in regulating microbial community structure, and in improving the performance of AnGS.

Effluent quality prediction in papermaking wastewater treatment processes using dynamic Bayesian networks

Effective online modeling of papermaking wastewater treatment processes (WWTPs) is an important means to ensure wastewater recycling and harmless discharge. A composite model integrating variable importance in projection with dynamic Bayesian networks (VIP-DBN) is proposed to improve the modeling ability and reliability in WWTPs. First, a variable selection method is applied to simplify the network structure and reduce modeling costs. Then the augmented matrices technique is embedded into the Bayesian networks to cope with the dynamic characteristics, nonlinearity, and uncertainty simultaneously. The modeling performance of VIP-DBN is evaluated through two case studies, a simulated WWTP based on benchmark simulation model no. 1 (BSM1) and a real papermaking WWTPs, in which the VIP-DBN model shows better modeling performance than its rivals. Specifically, compared with partial least squares, artificial neural networks, and Bayesian networks, the determination coefficient value of VIP-DBN is increased by 34.36%, 20.55%, and 3.30%, respectively, for the prediction of effluent nitrate in BSM1. The VIP-DBN can be used to deal with complex WWTPs in industrial applications, which provides a better practical method for soft sensor modeling and a guarantee for the effective decision-making of wastewater treatment processes for papermaking enterprises.