Soft Sensor Modeling Method for the Marine Lysozyme Fermentation Process Based on ISOA-GPR Weighted Ensemble Learning.

Due to the highly nonlinear, multi-stage, and time-varying characteristics of the marine lysozyme fermentation process, the global soft sensor models established using traditional single modeling methods cannot describe the dynamic characteristics of the entire fermentation process. Therefore, this study proposes a weighted ensemble learning soft sensor modeling method based on an improved seagull optimization algorithm (ISOA) and Gaussian process regression (GPR). First, an improved density peak clustering algorithm (ADPC) was used to divide the sample dataset into multiple local sample subsets. Second, an improved seagull optimization algorithm was used to optimize and transform the Gaussian process regression model, and a sub-prediction model was established. Finally, the fusion strategy was determined according to the connectivity between the test samples and local sample subsets. The proposed soft sensor model was applied to the prediction of key biochemical parameters of the marine lysozyme fermentation process. The simulation results show that the proposed soft sensor model can effectively predict the key biochemical parameters with relatively small prediction errors in the case of limited training data. According to the results, this model can be expanded to the soft sensor prediction applications in general nonlinear systems.

Recent Advances of Constructing Metal/Semiconductor Catalysts Designing for Photocatalytic CO2 Hydrogenation.

With the development of the world economy and the rapid advancement of global industrialization, the demand for energy continues to grow. The significant consumption of fossil fuels, such as oil, coal, and natural gas, has led to excessive carbon dioxide emissions, causing global ecological problems. CO2 hydrogenation technology can convert CO2 into high-value chemicals and is considered one of the potential ways to solve the problem of CO2 emissions. Metal/semiconductor catalysts have shown good activity in carbon dioxide hydrogenation reactions and have attracted widespread attention. Therefore, we summarize the recent research on metal/semiconductor catalysts for photocatalytic CO2 hydrogenation from the design of catalysts to the structure of active sites and mechanistic investigations, and the internal mechanism of the enhanced activity is elaborated to give guidance for the design of highly active catalysts. Finally, based on a good understanding of the above issues, this review looks forward to the development of future CO2 hydrogenation catalysts.

Light Control-Induced Oxygen Vacancy Generation and In Situ Surface Heterojunction Reconstruction for Boosting CO2 Reduction.

The weak adsorption of CO2 and the fast recombination of photogenerated charges harshly restrain the photocatalytic CO2 reduction efficiency. The simultaneous catalyst design with strong CO2 capture ability and fast charge separation efficiency is challenging. Herein, taking advantage of the metastable characteristic of oxygen vacancy, amorphous defect Bi2O2CO3 (named BOvC) was built on the surface of defect-rich BiOBr (named BOvB) through an in situ surface reconstruction progress, in which the CO32- in solution reacted with the generated Bi(3-x)+ around the oxygen vacancies. The in situ formed BOvC is tightly in contact with the BOvB and can prevent the further destruction of the oxygen vacancy sites essential for CO2 adsorption and visible light utilization. Additionally, the superficial BOvC associated with the internal BOvB forms a typical heterojunction promoting the interface carriers' separation. Finally, the in situ formation of BOvC boosted the BOvB and showed better activity in the photocatalytic reduction of CO2 into CO (three times compared to that of pristine BiOBr). This work provides a comprehensive solution for governing defects chemistry and heterojunction design, as well as gives an in-depth understanding of the function of vacancies in CO2 reduction.

Supercharged CO2 Photothermal Catalytic Methanation: High Conversion, Rate, and Selectivity.

To overcome the thermodynamic and kinetic impediments of the Sabatier CO2 methanation reaction, the process must be operated under very high temperature and pressure conditions, to obtain an industrially viable conversion, rate, and selectivity. Herein, we report that these technologically relevant performance metrics have been achieved under much milder conditions using solar rather than thermal energy, where the methanation reaction is enabled by a novel nickel-boron nitride catalyst. In this regard, an in situ generated HOB⋅⋅⋅B surface frustrated Lewis's pair is considered responsible for the high Sabatier conversion 87.68 %, reaction rate 2.03 mol gNi -1 h-1 , and near 100 % selectivity, realized under ambient pressure conditions. This discovery bodes well for an opto-chemical engineering strategy aimed at the development and implementation of a sustainable 'Solar Sabatier' methanation process.

A soft sensor model of Pichia pastoris cell concentration based on IBDA-RELM.

For Pichia pastoris fermentation process with multi-operating conditions, it is difficult to predict the cell concentration under the new operating conditions by the soft sensor model established under the specific operating conditions. Inspired by the idea of transfer learning, a method based on an improved balanced distribution adaptive regularization extreme learning machine (IBDA-RELM) was proposed to solve the problem. The domain adaptation (DA) method in transfer learning is developed to reduce distribution distance by transforming data. However, the joint distribution adaptation (JDA) and the balanced distribution adaptation (BDA) in DA cannot be directly applied to regression problems. The fuzzy sets (FSs) method was proposed to solve this issue. Finally, a soft sensor model of Pichia pastoris cell concentration was realized by inputting the converted data to the RELM model. Simulation verification was carried out with three operating conditions at the scene of fermentation. The transfer effects of three DA methods, including transfer component analysis (TCA), improved joint distribution adaptation (IJDA) as well as IBDA, were compared. The predicted results show that IBDA-RELM had a better performance in the soft sensor of Pichia pastoris cell concentration under multi-operating conditions.

Unique Dual-Sites Boosting Overall CO2 Photoconversion by Hierarchical Electron Harvesters.

Low selectivity and poor activity of photocatalytic CO2 reduction process are usually limiting factors for its applicability. Herein, a hierarchical electron harvesting system is designed on CoNiP hollow nano-millefeuille (CoNiP NH), which enables the charge enrichment on CoNi dual active sites and selective conversion of CO2 to CH4 . The CoNiP serves as an electron harvester and photonic "black hole" accelerating the kinetics for CO2 -catalyzed reactions. Moreover, the dual sites form from highly stable CoONiC intermediates, which thermodynamically not only lower the reaction energy barrier but also transform the reaction pathways, thus enabling the highly selective generation of CH4 from CO2 . As an outcome, the CoNiP NH/black phosphorus with dual sites leads to a tremendously improved photocatalytic CH4 generation with a selectivity of 86.6% and an impressive activity of 38.7 µmol g-1  h-1 .

Study on Multi-Model Soft Sensor Modeling Method and Its Model Optimization for the Fermentation Process of Pichia pastoris.

The problems that the key biomass variables in Pichia pastoris fermentation process are difficult measure in real time; this paper mainly proposes a multi-model soft sensor modeling method based on the piecewise affine (PWA) modeling method, which is optimized by particle swarm optimization (PSO) with an improved compression factor (ICF). Firstly, the false nearest neighbor method was used to determine the order of the PWA model. Secondly, the ICF-PSO algorithm was proposed to cooperatively optimize the number of PWA models and the parameters of each local model. Finally, a least squares support vector machine was adopted to determine the scope of action of each local model. Simulation results show that the proposed ICF-PSO-PWA multi-model soft sensor modeling method accurately approximated the nonlinear features of Pichia pastoris fermentation, and the model prediction accuracy is improved by 4.4884% compared with the weighted least squares vector regression model optimized by PSO.

A dynamic soft senor modeling method based on MW-ELWPLS in marine alkaline protease fermentation process.

The vital state variables in marine alkaline protease (MP) fermentation are difficult to measure in real-time online, hardly is the optimal control either. In this article, a dynamic soft sensor modeling method which combined just-in-time learning (JITL) technique and ensemble learning is proposed. First, the local weighted partial least squares algorithm (LWPLS) with JITL strategy is used as the basic modeling method. For further improving the prediction accuracy, the moving window (MW) is used to divide sub-dataset. Then the MW-LWPLS sub-model is built by selecting the diverse sub-datasets according to the cumulative similarity. Finally, stacking ensemble-learning method is utilized to fuse each MW-LWPLS sub-models. The proposed method is applied to predict the vital state variables in the MP fermentation process. The experiments and simulations results show that the prediction accuracy is better compared to other methods.

Soft - sensing modeling based on ABC - MLSSVM inversion for marine low - temperature alkaline protease MP fermentation process.

BACKGROUND: Aiming at the characteristics of nonlinear, multi-parameter, strong coupling and difficulty in direct on-line measurement of key biological parameters of marine low-temperature protease fermentation process, a soft-sensing modeling method based on artificial bee colony (ABC) and multiple least squares support vector machine (MLSSVM) inversion for marine protease fermentation process is proposed. METHODS: Firstly, based on the material balance and the characteristics of the fermentation process, the dynamic "grey box" model of the fed-batch fermentation process of marine protease is established. The inverse model is constructed by analyzing the inverse system existence and introducing the characteristic information of the fermentation process. Then, the inverse model is identified off-line using MLSSVM. Meanwhile, in order to reduce the model error, the ABC algorithm is used to correct the inverse model. Finally, the corrected inverse model is connected in series to the marine alkaline protease MP fermentation process to form a composite pseudo-linear system, thus, real-time on-line prediction of key biological parameters in fermentation process can be realized. RESULTS: Taking the alkaline protease MP fermentation process as an example, the simulation results demonstrate that the soft-sensing modeling method can solve the real-time prediction problem of key biological parameters in the fermentation process on-line, and has higher accuracy and generalization ability than the traditional soft-sensing method of support vector machine. CONCLUSIONS: The research provides a new method for soft-sensing modeling of key biological parameters in fermentation process, which can be extended to soft-sensing modeling of general nonlinear systems.

Modern Soft-Sensing Modeling Methods for Fermentation Processes.

For effective monitoring and control of the fermentation process, an accurate real-time measurement of important variables is necessary. These variables are very hard to measure in real-time due to constraints such as the time-varying, nonlinearity, strong coupling, and complex mechanism of the fermentation process. Constructing soft sensors with outstanding performance and robustness has become a core issue in industrial procedures. In this paper, a comprehensive review of existing data pre-processing approaches, variable selection methods, data-driven (black-box) soft-sensing modeling methods and optimization techniques was carried out. The data-driven methods used for the soft-sensing modeling such as support vector machine, multiple least square support vector machine, neural network, deep learning, fuzzy logic, probabilistic latent variable models are reviewed in detail. The optimization techniques used for the estimation of model parameters such as particle swarm optimization algorithm, ant colony optimization, artificial bee colony, cuckoo search algorithm, and genetic algorithm, are also discussed. A comprehensive analysis of various soft-sensing models is presented in tabular form which highlights the important methods used in the field of fermentation. More than 70 research publications on soft-sensing modeling methods for the estimation of variables have been examined and listed for quick reference. This review paper may be regarded as a useful source as a reference point for researchers to explore the opportunities for further enhancement in the field of soft-sensing modeling.

A Non-linear Model Predictive Control Based on Grey-Wolf Optimization Using Least-Square Support Vector Machine for Product Concentration Control in L-Lysine Fermentation.

L-Lysine is produced by a complex non-linear fermentation process. A non-linear model predictive control (NMPC) scheme is proposed to control product concentration in real time for enhancing production. However, product concentration cannot be directly measured in real time. Least-square support vector machine (LSSVM) is used to predict product concentration in real time. Grey-Wolf Optimization (GWO) algorithm is used to optimize the key model parameters (penalty factor and kernel width) of LSSVM for increasing its prediction accuracy (GWO-LSSVM). The proposed optimal prediction model is used as a process model in the non-linear model predictive control to predict product concentration. GWO is also used to solve the non-convex optimization problem in non-linear model predictive control (GWO-NMPC) for calculating optimal future inputs. The proposed GWO-based prediction model (GWO-LSSVM) and non-linear model predictive control (GWO-NMPC) are compared with the Particle Swarm Optimization (PSO)-based prediction model (PSO-LSSVM) and non-linear model predictive control (PSO-NMPC) to validate their effectiveness. The comparative results show that the prediction accuracy, adaptability, real-time tracking ability, overall error and control precision of GWO-based predictive control is better compared to PSO-based predictive control.

Soft-sensing method based on FDLS-SVM in marine alkaline protease fermentation process.

To overcome the problem that soft-sensing model cannot be updated with the bioprocess changes, this article proposed a soft-sensing modeling method which combined fuzzy c-means clustering (FCM) algorithm with least squares support vector machine theory (LS-SVM). FCM is used for separating a whole training data set into several clusters with different centers, each subset is trained by LS-SVM and sub-models are developed to fit different hierarchical property of the process. The new sample data that bring new operation information is introduced in the model, and the fuzzy membership function of the sample to each clustering is first calculated by the FCM algorithm. Then, a corresponding LS-SVM sub-model of the clustering with the largest fuzzy membership function is used for performing dynamic learning so that the model can update online. The proposed method is applied to predict the key biological parameters in the marine alkaline protease MP process. The simulation result indicates that the soft-sensing modeling method increases the model's adaptive abilities in various operation conditions and can improve its generalization ability.

Enhancing photocatalytic CO2 reduction with TiO2-based materials: Strategies, mechanisms, challenges, and perspectives.

The concentration of atmospheric CO2 has exceeded 400 ppm, surpassing its natural variability and raising concerns about uncontrollable shifts in the carbon cycle, leading to significant climate and environmental impacts. A promising method to balance carbon levels and mitigate atmospheric CO2 rise is through photocatalytic CO2 reduction. Titanium dioxide (TiO2), renowned for its affordability, stability, availability, and eco-friendliness, stands out as an exemplary catalyst in photocatalytic CO2 reduction. Various strategies have been proposed to modify TiO2 for photocatalytic CO2 reduction and improve catalytic activity and product selectivity. However, few studies have systematically summarized these strategies and analyzed their advantages, disadvantages, and current progress. Here, we comprehensively review recent advancements in TiO2 engineering, focusing on crystal engineering, interface design, and reactive site construction to enhance photocatalytic efficiency and product selectivity. We discuss how modifications in TiO2's optical characteristics, carrier migration, and active site design have led to varied and selective CO2 reduction products. These enhancements are thoroughly analyzed through experimental data and theoretical calculations. Additionally, we identify current challenges and suggest future research directions, emphasizing the role of TiO2-based materials in understanding photocatalytic CO2 reduction mechanisms and in designing effective catalysts. This review is expected to contribute to the global pursuit of carbon neutrality by providing foundational insights into the mechanisms of photocatalytic CO2 reduction with TiO2-based materials and guiding the development of efficient photocatalysts.

Structurally disordered MoSe2 with rich 1T phase as a universal platform for enhanced photocatalytic hydrogen production.

The improvement of surface reactivity in noble-metal-free cocatalysts is crucial for the development of efficient and cost-effective photocatalytic systems. However, the influence of crystallinity on catalytic efficacy has received limited attention. Herein, we report the utilization of structurally disordered MoSe2 with abundant 1T phase as a versatile cocatalyst for photocatalytic hydrogen evolution. Using MoSe2/carbon nitride (CN) hybrids as a case study, it is demonstrated that amorphous MoSe2 significantly enhances the hydrogen evolution rate of CN, achieving up to 11.37 µmol h-1, surpassing both low crystallinity (8.24 µmol h-1) and high crystallinity MoSe2 (3.86 µmol h-1). Experimental analysis indicates that the disordered structure of amorphous MoSe2, characterized by coordination-unsaturated surface sites and a rich 1T phase with abundant active sites at the basal plane, predominantly facilitates the conversion of surface-bound protons to hydrogen. Conversely, the heightened charge transfer capacity of the highly crystalline counterpart plays a minor role in enhancing practical catalytic performance. This approach is applicable for enhancing the photocatalytic hydrogen evolution performance of various semiconducting photocatalysts, including CdS, TiO2, and ZnIn2S4, thereby offering novel insights into the advancement of high-performance non-precious catalysts through phase engineering.

Adjacent Mn site boosts photocatalytic hydrogen evolution of MnXCd1-XS solid solution through a dual-metal-site design.

CdS has emerged as a possible candidate for photocatalytic hydrogen generation. However, further improvement in the performance of the Cd metal site is challenging due to limited optimization space. To solve this limitation, in this work, the Mn-Cd dual-metal photocatalyst was synthesized by a one-step solvothermal method, and the effects of different proportions of bimetals on hydrogen production activity were systematically studied. The ingenious design of the bimetallic sites enhances the carrier separation efficiency and the built-in electric field intensity, which leads to significant improvement in the photocatalytic hydrogen production performance of MCS0.19. Density functional theory (DFT) calculations confirm that the introduction of the Mn element can drive electrons through the Fermi level, resulting in enhanced conductivity of the catalyst. Meanwhile, electron channels are built between Mn and S, which speeds up the rate of electron transfer and is conducive to improving hydrogen production activity. This work provides a technical-methodological entrance to improve the photocatalytic hydrogen production performance of dual-metal S solid solutions and also promises to open a novel approach to creating high-efficiency solid solution photocatalysts.

Accelerated Photoreduction of CO2 to CO over a Stable Heterostructure with a Seamless Interface.

Photocatalytic CO2 reduction is a means of alleviating energy crisis and environmental deterioration. In this work, a rising two-dimensional (2D) material rarely reported in the field of photocatalytic CO2 reduction, black phosphorus (BP) nanosheets, is synthesized, on which Co2P is in situ grown by solvothermal treatment using BP itself as a P source. Co2P on the BP nanosheets (BPs) surface can prevent the destruction of BPs in ambient air and, in the meantime, favor charge separation and CO2 adsorption and activation during the catalytic process. Upon light irradiation, Co2P can extract the photogenerated electrons effectively across the intimate interface and lower the CO2 activation energy barrier, supported by both experimental characterizations and theoretical calculations. Benefitting from integrated advantages of BPs and Co2P, the optimal Co2P/BPs exhibit photocatalytic reduction of CO2 to CO at a rate of 25.5 µmol g-1 h-1 with a selectivity of 91.4%, both of which are higher than those of pristine BPs. This work presents ideas for stabilizing BPs and improving their CO2 reduction performance simultaneously.

[Baseline drift of electrocardiograph dealt with mathematical morphology filter in real-time].

We have done a research on mathematical morphology filter in order to eliminate baseline drift in the wave of electrocardiograph (ECG). Marago morphology filter type was chosen and flat structuring element filtering was found to be the best morphology filter modality for eliminating baseline drift, and the ratio of "signal numerical frequency to length of structuring element" determined the attenuation magnitude of the signal eliminated. We have come to the conclusion that the length of flat structuring element ought to be greater than or equal to the width of the signal component to be eliminated. The arithmetical algorithm was simulated with Matlab software, and was transplanted to DSP hardware platform. The result of experiment has shown that the arithmetic operation is simple and the method spends a short time (less than 1 ms) in eliminating the baseline drift of ECG effectively and instantly.

Soft-sensor modeling for L-lysine fermentation process based on hybrid ICS-MLSSVM.

The L-lysine fermentation process is a complex, nonlinear, dynamic biochemical reaction process with multiple inputs and multiple outputs. There is a complex nonlinear dynamic relationship between each state variable. Some key variables in the fermentation process that directly reflect the quality of the fermentation cannot be measured online in real-time which greatly limits the application of advanced control technology in biochemical processes. This work introduces a hybrid ICS-MLSSVM soft-sensor modeling method to realize the online detection of key biochemical variables (cell concentration, substrate concentration, product concentration) of the L-lysine fermentation process. First of all, a multi-output least squares support vector machine regressor (MLSSVM) model is constructed based on the multi-input and multi-output characteristics of L-lysine fermentation process. Then, important parameters ([Formula: see text], [Formula: see text], [Formula: see text]) of MLSSVM model are optimized by using the Improved Cuckoo Search (ICS) optimization algorithm. In the end, the hybrid ICS-MLSSVM soft-sensor model is developed by using optimized model parameter values, and the key biochemical variables of the L-lysine fermentation process are realized online. The simulation results confirm that the proposed regression model can accurately predict the key biochemical variables. Furthermore, the hybrid ICS-MLSSVM soft-sensor model is better than the MLSSVM soft-sensor model based on standard CS (CS-MLSSVM), particle swarm optimization (PSO) algorithm (PSO-MLSSVM) and genetic algorithm (GA-MLSSVM) in prediction accuracy and adaptability.

The generalized predictive control of bacteria concentration in marine lysozyme fermentation process.

Due to the high degree of strong coupling and nonlinearity of marine lysozyme fermentation process, it is difficult to accurately model the mechanism. In order to achieve real-time online measurement and effective control of bacterial concentration during fermentation, a generalized predictive control method based on least squares support vector machines is proposed. The particle swarm optimization least squares support vector machine (PSO-LS-SVM) model of lysozyme concentration is established by optimizing the regularization parameters and the kernel parameters of the least squares support vector machine by particle swarm optimization. To avoid the nonlinear problems in predictive control, the model is linearized at each sampling point and the generalized predictive algorithm is used to predict the bacteria concentration of lysozyme. The experimental simulation shows that the least squares support vector machine model with particle swarm optimization can achieve good prediction effect. The linearized model performs generalized predictive control, which makes the total activity of the enzyme increased from 60% to 80% and the yield improved by 30%.

In Situ Decoration of Znx Cd1-x S with FeP for Efficient Photocatalytic Generation of Hydrogen under Irradiation with Visible Light.

FeP as a noble-metal-free catalyst has been successfully decorated onto the Znx Cd1-x S photocatalyst surface through an in situ phosphating process. In particular, the 2 % FeP/Zn0.5 Cd0.5 S-P sample showed the best hydrogen generation activity of 24.45 mmol h-1 g-1 which is over 130 times higher than that of pure Zn0.5 Cd0.5 S and nearly 1.3 times higher than that of the 1 % Pt-loaded Zn0.5 Cd0.5 S-P sample. The apparent quantum yield (AQY) of the 2 % FeP/Zn0.5 Cd0.5 S-P was estimated to be over 10 % at wavelengths up to 470 nm. The fluorescence spectra and electrochemical measurement results suggest that the decorated FeP not only reduces the overpotential for H2 evolution but also promotes the separation of the photogenerated charge carriers through formation of a heterojunction with Zn0.5 Cd0.5 S, which eventually leads to the superior activity of the FeP/Zn0.5 Cd0.5 S-P photocatalyst for visible-light-driven hydrogen generation.