Fed-batch Penicillin Fermentation Process Research Articles

An improved transfer learning approach based on geodesic flow kernel for multiphase batch process soft sensor modeling

For multiphase batch process, the characteristics of process data under various batches differ. Consequently, the soft sensor model built for a particular working condition is inapplicable to other working conditions. Besides, each batch can be divided into several phases whose characteristics are probably different. To address the above problems, a soft sensor model based on phase division and transfer learning strategy is proposed. First, transfer learning strategy is adopted to construct a soft sensor model applicable to various working conditions. Specifically, geodesic flow kernel based on linear local tangent space alignment (LLTSA-GFK) algorithm is designed. By projecting process data to the common manifold subspace, the distribution difference of data between various batches is reduced and the performance of the soft sensor model is enhanced. In addition, sequence-based fuzzy clustering and just-in-time learning (JITL) are adopted to solve the multistage characteristic for batch process. The root-mean-square error ( RMSE), coefficient of determination [Formula: see text], and mean absolute error ( MAE) are adopted to compare the conventional soft sensing approach (i.e., partial least-square regression based on JITL, support vector regression, and back propagation neural network) with the proposed approach. The superiority of the proposed model is verified by a fed-batch penicillin fermentation process.

Data-Driven Soft Sensing for Batch Processes Using Neural Network-Based Deep Quality-Relevant Representation Learning

Soft sensors provide a means to reliably estimate unmeasurable variables, thereby playing a prevalent role in formulating closed-loop control in batch processes. In soft sensor development, enhancing quality-relevant information and eliminating quality-irrelevant information are important. This study proposes a neural network-based deep quality-relevant representation learning approach to improve the soft sensing performance in dynamic batch processes. The structure of a deep neural network is optimized in a layer-by-layer manner. First, given the generally abundant predictor variables, the maximal relevanceminimal redundancy criterion is used to optimize the input layer, select the most beneficial variables, and eliminate modeling redundancy. Second, mutual information-based quality-relevant representation selection is performed in the middle layers to enhance the quality-relevant information and eliminate the influence of irrelevant representations. Third, deep quality-relevant representations are extracted, and a soft sensor model is developed. The proposed method is tested on a fed-batch penicillin fermentation process and an industrial injection molding process. Lastly, it shows that the proposed method outperforms several state-of-the-art approaches, thereby confirming its effectiveness.

Two-dimensional multiphase batch process monitoring based on sparse canonical variate analysis

Most industrial batch processes involve inherent dynamic characteristics in both within-batch time direction and batch-wise direction. In order to ensure process safety and improve process performance, the two-dimensional dynamics should be analyzed during batch process monitoring. In this work, two-dimensional region of support (2D-ROS) is first constructed to select and preserve the relevant samples for the current measured sample by calculating autoregressive orders with Akaike information criterion (AIC) in time direction and measuring the similarity with the weighted Euclidean distance in batch-wise direction. Afterwards, sparse canonical variate analysis (SCVA) algorithm is performed to yield sparse canonical vectors, which is especially advantageous for eliminating the irrelevant variables and facilitating the interpretation of underlying relationships of process variables. Meanwhile, given most measurements are subject to the non-Gaussian distribution, the upper control limits (UCLs) in 2D-SCVA can be estimated using kernel density estimation (KDE). The achieved results obtained from a numerical dynamic example and the benchmark fed-batch penicillin fermentation process clearly verify that the proposed method performs well for detecting abnormal operation for the batch processes.

Incipient Fault Diagnosis of Batch Process Based on Deep Time Series Feature Extraction

Intelligence modeling interpretable for incipient fault diagnosis of batch process represents a serious challenge. For the multivariate, nonlinear, and high-dimensionality characteristics of process data, existing fault diagnosis solutions are easily concealed by noise while neglect the low amplitude and noise interference of the incipient faults. In this paper, an intelligent incipient fault diagnosis model based on deep time series feature extraction network is proposed, which integrates denoising autoencoder (DAE), layer normalization and dropout layer added LSTM (LD-LSTM), and stacked autoencoder (SAE) to obtain the efficient features. DAE is applied to restore the data and eliminate noise interference. LD-LSTM is utilized to extract time series features, in which the layer normalization and the dropout layer are added between the layers of the LSTM to solve the problems of slow model convergence and over-fitting. SAE performs the feature extraction to obtain deep time series features and learns more efficient expressions. The softmax function is applied to achieve the incipient fault diagnosis based on the deep time series features. A case study on a fed-batch penicillin fermentation process suggests that the proposed method can obtain an accuracy rate of 98.97%, which has increased an average of 20% than the traditional shallow machine learning. The accuracy of fault recognition and comparative experiments demonstrate the effectiveness and feasibility of this model, and provide a solution for the application of intelligent fault diagnosis in batch industries.

Quality relevant over-complete independent component analysis based monitoring for non-linear and non-Gaussian batch process

A large number of multivariate statistical methods have been applied to process monitoring, but conventional methods only extract limited feature information that often cannot effectively monitor the quality related changes of production characteristics in batch processes. In order to improve the effect of the process monitoring, this paper proposes a batch process monitoring method based on Multistage Over-complete Independent Component Analysis (OICA) algorithm. Firstly, the Affinity Propagation algorithm (AP) is used to divide the batch production process. Secondly, the extra quality information extracted by Partial Least Squares (PLS) algorithm is input into OICA algorithm. Finally, a monitoring model is established for process monitoring in each sub-stage. The effectiveness of the proposed method has been verified by comparing with the conventional methods in the fed-batch penicillin fermentation process.

Robust Multi-Objective Singular Optimal Control Ofpenicillin Fermentation Process

The determination of optimal feeding profile of fed-batch fermentation requires the solution of a singular optimal control problem. The complexity in obtaining the solution to this singular problem is due to the nonlinear dynamics of the system model, the presence of control variables in linear form and the existence of constraints in both the state and control variables. Traditionally, during the optimization process, uncertainties associated with design variables, control parameters and mathematical model are not considered. In this contribution, a systematic methodology to evaluate uncertainties during the resolution of a singular optimal control problem is proposed. This approach consists of the Multi-objective Optimization Differential Evolution algorithm associated with Effective Mean Concept. The proposed methodology is applied to determine the feed substrate concentration in fed-batch penicillin fermentation process. The robust multi- objective singular optimal control problem consists of maximizing the productivity and minimizing the operation total time.

Phase partition and identification based on kernel entropy component analysis and multi-class support vector machines-fireworks algorithm for multi-phase batch process fault diagnosis

For the characteristics of nonlinear and multi-phase in the batch process, a self-adaptive multi-phase batch process fault diagnosis method is proposed in this paper. Firstly, kernel entropy component analysis (KECA) method is used to achieve multi-phase partition adaptively, which makes the process data mapped into the high-dimensional feature space and then constructs the core entropy and the angular structure similarity. Then a multi-phase KECA failure monitoring model is developed by using the angular structure similarity as the statistic, which is based on the partitioned phases and the effective failure features by the KECA feature extraction method. A multi-phase batch process fault diagnosis method, which applies the multi-class support vector machines (MSVM) and fireworks algorithm (FWA), is proposed to recognize each sub-phase fault diagnosis automatically. The effectiveness and advantages of the proposed multi-phase fault diagnosis method are illustrated with a case study on a fed-batch penicillin fermentation process.

Quality-Relevant Monitoring of Batch Processes Based on Stochastic Programming with Multiple Output Modes

To implement the quality-relevant monitoring scheme for batch processes with multiple output modes, this paper presents a novel methodology based on stochastic programming. Bringing together tools from stochastic programming and ensemble learning, the developed methodology focuses on the robust monitoring of process quality-relevant variables by taking the stochastic nature of batch process parameters explicitly into consideration. To handle the problem of missing data and lack of historical batch data, a bagging approach is introduced to generate individual quality-relevant sub-datasets, which are used to construct the corresponding monitoring sub-models. For each model, stochastic programming is used to construct an optimal quality trajectory, which is regarded as the reference for online quality monitoring. Then, for each sub-model, a corresponding control limit is obtained by computing historical residuals between the actual output and the optimal trajectory. For online monitoring, the current sample is examined by all sub-models, and whether the monitoring statistic exceeds the control limits is recorded for further analysis. The final step is ensemble learning via Bayesian fusion strategy, which is under the probabilistic framework. The implementation and effectiveness of the developed methodology are demonstrated through two case studies, including a numerical example, and a simulated fed-batch penicillin fermentation process.

Nonlinear process modelling using echo state networks optimised by covariance matrix adaption evolutionary strategy

Echo state networks (ESN) have been shown to be an effective alternative to conventional recurrent neural networks (RNNs) due to its fast training process and good performance in dynamic system modelling. However, the performance of ESN can be affected by the randomly generated reservoir. This paper presents nonlinear process modelling using ESN optimized by covariance matrix adaption evolutionary strategy (CMA-ES). CMA-ES is used to optimize the structural parameters of ESN: reservoir size, spectral radius, and leak rate. The proposed method is applied to three case studies: modelling a time series, modelling a conic tank, and modelling a fed-batch penicillin fermentation process. The results are compared with those from the original ESN, long short-term memory network, GA-ESN (ESN optimized by genetic algorithm), and feedforward neural networks. It is shown that the proposed method gives much better performance than the original ESN and other networks on all the three case studies.

LSTM Soft Sensor Development of Batch Processes With Multivariate Trajectory-Based Ensemble Just-in-Time Learning

To implement the quality prediction scheme for batch processes, long short-term memory (LSTM) neural network is a feasible tool to handle with the process dynamics and nonlinearity. However, a global LSTM soft sensor suffers a decline in performance facing batch-to-batch variations. To overcome the batch diversity problem and take advantage of LSTM model, a multivariate trajectory based ensemble just-in-time learning strategy is proposed in this paper. Different trajectory based similarity measurements are designed to extract historical batch trajectories which share similar spatial positions and trends. For each selected trajectory, an online local LSTM soft sensing model is constructed and the real-time quality prediction result for each local model can be obtained. Then, a weighting parameter is determined for each model by cross validation. Bringing together quality prediction results from different local models, the ensemble prediction result can be finally figured out. Two case studies are carried out to prove the effectiveness of the proposed methodology including a fed-batch reactor and the fed-batch penicillin fermentation process.

Nonlinear Fault Detection of Batch Processes Using Functional Local Kernel Principal Component Analysis

In order to guarantee and improve the product quality, the data-driven fault detection technique has been widely used in industry. For three-way datasets of batch process in industry process (i.e., batch × variable × time), a novel method named functional local kernel principal component analysis (FLKPCA) is proposed. Since the variables' trajectories often show functional nature and can be considered as smooth functions rather than just vectors. Firstly, the variables' trajectory is expressed as the combination of smooth basis functions using functional data analysis (FDA), which means that the datasets of batches process would be transformed from the three-ways array into two-ways function matrix. Then, kernel locality preserving projections (LKPCA) is used to perform dimensionality reduction on two-way function matrix directly. Different from kernel principal component analysis (KPCA). LKPCA aims at preserving the both local and global structure of the data in a new optimization objective. Consequently, FLKPCA could more effectively seek the potential information that hidden in the three-ways datasets. Lastly, the effectiveness of the proposed approach is illustrated by the benchmark of fed-batch penicillin fermentation process and the hot strip rolling process.

Data-Driven Batch-End Quality Modeling and Monitoring Based on Optimized Sparse Partial Least Squares

Batch-end quality modeling is used to predict the quality by using batch measurements and generally involves a large number of predictor variables. However, not all of the variables are beneficial for the prediction. Conventional multiway partial least squares (PLS) may not function properly for batch-end quality modeling because of many irrelevant predictor variables. This paper proposes an optimized sparse PLS (OSPLS) modeling approach for simultaneous batch-end quality prediction and relevant-variable selection. The effect of irrelevant variables on the quality-prediction performance is analyzed, and the importance of the relevant-variable selection is emphasized. Then, an OSPLS batch-end quality modeling approach is developed by incorporating the variable resolution optimization and sparse PLS modeling. The quality-prediction accuracy and modeling interpretability are improved because only quality-relevant variables are selected, and quality-irrelevant variables are eliminated. Based on the selected quality-relevant variables, a statistic is established for monitoring the quality status. The proposed OSPLS-based modeling and monitoring approach is applied on a fed-batch penicillin fermentation process and an industrial injection molding process. The results are compared with the state-of-the-art methods to verify the effectiveness of the OSPLS approach.

Incipient Fault Detection for Multiphase Batch Processes With Limited Batches

Sufficient batches are in general, required for fault detection of batch processes. However, sometimes, it is difficult and may be impractical to conduct multiple cycles and wait until enough batches are available. Without batch-wise normalization step, the nonstationary cannot be efficiently removed by time-wise normalization. The mean values of the nonstationary variables are still time varying and the interval of fault-free data is very wide in each phase. Therefore, the incipient fault, which has a small magnitude including early changing and the slow developing, may be buried by nonstationary trends resulting in low fault detection rate. To address the above issue, a two-layer fault detection method is proposed to detect the incipient fault for multiphase batch processes with limited batches. First, a concurrent variable separation strategy is proposed to distinguish nonstationary variables from stationary variables for multiple batches in each phase. Second, a two-layer fault detection model is constructed to detect the incipient fault. Cointegration analysis-based fault detection model is built to investigate the relationship between nonstationary variables, which can effectively distinguish the incipient fault from the normal trend of the nonstationary variables. Principal component analysis is adopted to describe the correlation of stationary variables. Afterward, a total fault detection model is constructed to monitor the relation between nonstationary variables and stationary variables. To illustrate the feasibility and effectiveness, the proposed algorithm is applied to two multiphase batch processes including fed-batch penicillin fermentation process and semiconductor etch process.

Ensemble just-in-time learning framework through evolutionary multi-objective optimization for soft sensor development of nonlinear industrial processes

Just-in-time learning (JIT) has recently gained growing popularity for soft sensor development of nonlinear processes. However, traditional JIT methods aim to pursue a globally optimal learning configuration while ignoring the diversity of JIT learning. Since strong JIT learners are desirable yet difficult to get while weak JIT learners are easy to obtain in real practice, a novel soft sensor modeling framework, referred to as evolutional multi-objective optimization (EMO) based ensemble JIT learning (EMO-EJIT), is proposed. Within this framework, the diversity of JIT learning is created by perturbing the weighted Euclidean distance (WED) based similarity measure. Then diverse and accurate JIT learners equipped with diverse WED similarity measures are generated using an EMO approach. Finally, a stacking strategy is used to achieve ensemble prediction. By employing the proposed modeling framework, EMO based ensemble locally weighted partial least squares (EMO-ELWPLS) and EMO based ensemble JIT extreme learning machine (EMO-EJITELM) soft sensors are developed. The application results from a simulated fed-batch penicillin fermentation process and an industrial fed-batch chlortetracycline fermentation process have demonstrated the effectiveness and superiority of the proposed method.

Unsupervised-Multiscale-Sequential-Partitioning and Multiple-SVDD-Model-Based Process-Monitoring Method for Multiphase Batch Processes

For the effective monitoring of batch processes with uneven multiphases, phase partitioning and discriminant analysis are two critical problems. To fully solve these two problems, a systematic strategy including fuzzy phase partitioning and hybrid discriminant analysis is proposed. First, using a new unsupervised, multiscale, sequential partition (UMSP), each batch is divided into phases with transitions using different clustering scales. On this basis, two multiple-support-vector-data-description (SVDD) models are built for online phase partitioning and monitoring, and a hybrid-discriminant-analysis method is then developed for online fault detection. The effectiveness and advantages of the proposed method are illustrated with a 2D, handwritten example and a fed-batch penicillin-fermentation process.

Nonlinear fault detection of batch processes based on functional kernel locality preserving projections

Data-driven fault detection technique has exhibited its wide applications in industrial process monitoring. The batch dataset is often organized as a special three-way array (i.e., batch × variable × time), and the research of data-based batch process monitoring has attracted considerable attention in the literature. A novel method named functional kernel locality preserving projections (FKLPP) is proposed for batch process monitoring. Since the variables' trajectories often show functional nature and can be considered as smooth functions rather than just vectors, then the three-way data can be transformed into a two-way function matrix. Firstly, the variables’ trajectories are expressed by using the functional data analysis (FDA). By doing so, the original batch process data can be transformed into a two-way manner (batches × functions of the variable trajectories) by describing each variable trajectory as a function of time. Then, kernel locality preserving projections is used to perform dimensionality reduction on two-way function matrix directly. Different from principal component analysis (PCA) which aims at preserving the global Euclidean structure of the data, the FKLPP aims to preserve the local neighborhood information and to detect the intrinsic manifold structure of the data. The kernel trick is applied to the construction of nonlinear kernel model. Consequently, FKLPP may be useful to seek more meaningful intrinsic information hidden in the observations. Lastly, the effectiveness and potentials of the FKLPP-based monitoring approach are illustrated by a benchmark fed-batch penicillin fermentation process and the hot strip rolling process.

Similar Batch Process Monitoring With Orthogonal Subspace Alignment

In industrial batch productions, operating conditions should be altered frequently to meet the ever-changing market requirements. Although changed conditions will result in variant data properties, those generated target batches share similar running properties with source batches. To effectively and efficiently monitor those similar processes, a novel multiphase orthogonal subspace manifold alignment diagram is proposed in this work. With the extracted orthogonal locality preserving projection subspace manifolds from two corresponding batches, the phase-based Procrustes analysis is conducted to make a source-target coordinate system for similarity matching and alignment. On the basis of that, the new batch matches the old data and the multiphase k -nearest neighborhood monitoring charts can be developed for monitoring the new process within the historical domain knowledge. Finally, a systematic modeling and monitoring framework has been established, with which the laborious efforts for repetitive modeling can be reduced, and the monitoring performance can be improved. For industrial validation, the feasibility and superiority of the general diagram are demonstrated on the fed-batch penicillin fermentation process and the semiconductor manufacturing process.

Batch process fault detection and identification based on discriminant global preserving kernel slow feature analysis

As an attractive nonlinear dynamic data analysis tool, global preserving kernel slow feature analysis (GKSFA) has achieved great success in extracting the high nonlinearity and inherently time-varying dynamics of batch process. However, GKSFA is an unsupervised feature extraction method and lacks the ability to utilize batch process class label information, which may not offer the most effective means for dealing with batch process monitoring. To overcome this problem, we propose a novel batch process monitoring method based on the modified GKSFA, referred to as discriminant global preserving kernel slow feature analysis (DGKSFA), by closely integrating discriminant analysis and GKSFA. The proposed DGKSFA method can extract discriminant feature of batch process as well as preserve global and local geometrical structure information of observed data. For the purpose of fault detection, a monitoring statistic is constructed based on the distance between the optimal kernel feature vectors of test data and normal data. To tackle the challenging issue of nonlinear fault variable identification, a new nonlinear contribution plot method is also developed to help identifying the fault variable after a fault is detected, which is derived from the idea of variable pseudo-sample trajectory projection in DGKSFA nonlinear biplot. Simulation results conducted on a numerical nonlinear dynamic system and the benchmark fed-batch penicillin fermentation process demonstrate that the proposed process monitoring and fault diagnosis approach can effectively detect fault and distinguish fault variables from normal variables.

Inner-phase and inter-phase analysis based operating performance assessment and nonoptimal cause identification for multiphase batch processes

Batch processes play a significant role in modern industrial processes. Nevertheless, the process operating performance may degrade from optimal level, which cancels the economic profits of the plant, and effective techniques for operating performance assessment are essential. Although multimodel approaches are proposed to fit its multiphase characteristic, the effect of combined action of multiple phases on the operating performance of the overall batch, which is very important for operating performance assessment, is neglected. In this study, a novel inner-phase and inter-phase analysis based operating performance assessment and nonoptimal cause identification strategy is proposed to overcome it. The key characteristic of the proposed method is that the inter-phase assessment models are developed based on the inner-phase assessment models of each phase, which takes the correlations and interactions between phases into consideration and reveals the combined effect of multiple phases on the operating performance of the overall batch. Furthermore, online local and global assessments are performed to master the operating performance from different perspectives and improve the algorithm performance. Possible cause variables can be determined by variable contributions under nonoptimal level. The effectiveness of the proposed methodology is demonstrated through a fed-batch penicillin fermentation process and a injection molding process.

Multiphase batch process with transitions monitoring based on global preserving statistics slow feature analysis

Abstract Most previous studies have shown that the multiphase characteristics of batch processes are critical for process monitoring; however, revealing and utilizing the information of multiplicity in multiphase batch process monitoring remains challenging. In this paper, statistics slow feature analysis (SSFA) is developed to extract slowly varying information at the same sampling time among different batches based on various statistics of the original variables. Then, a new index called the phase recognition factor (PRF), which is based on SSFA, is introduced to automatically achieve phase division. The proposed PRF takes advantage of the time sequence of process phases and does not require predefined parameters. After phase division, global preserving SSFA (GSSFA) is proposed not only to explore the time-varying dynamic information of batch processes but also to consider the mining of global data structure information. Furthermore, a novel process monitoring strategy based on the GSSFA model is developed to monitor batch processes with transitions. In each steady phase, a representative GSSFA model is built for process monitoring; in the transition period, different local GSSFA models are constructed online to monitor the test samples based on the just-in-time learning method. Two case studies, one simple numerical multiphase system and a benchmark fed-batch penicillin fermentation process, are used to demonstrate the effectiveness and superiority of the proposed method.