Browsing by Author "Mohanta, Hare Krishna"

Now showing 1 - 20 of 32

Adaptive non-linear soft sensor for quality monitoring in refineries using Just-in-Time Learning—Generalized regression neural network approach
(Elsevier, 2022-04) Mohanta, Hare Krishna; Pani, Ajaya Kumar
Real time estimation of target quality variables using soft sensor relevant to time varying process conditions will be a significant step forward in effective implementation of Industry 4.0. Generalized Regression neural network (GRNN) has been used as a steady state quality monitoring soft sensor with reasonable estimation accuracy. However, the accurate prediction capability of GRNN has rarely been explored in a time varying environment. This article reports design of adaptive soft sensor using GRNN as a local model in Just-in-Time learning (JITL-GRNN) framework. The JITL-GRNN adaptive soft sensing technique is further investigated in various dimensions such as, the effect of different similarity index criteria and relevant dataset size on model prediction accuracy and model computation time. Performance of the proposed JITL-GRNN soft sensor is investigated by assessing its prediction accuracy on two benchmark industrial datasets. In addition, dynamic Non-linear autoregressive with exogenous inputs (NARX) neural network model is also developed and the performance of NARX model was compared with the proposed JITL-GRNN model. Results show that the JITL-GRNN adaptive soft sensor has at par or better prediction capability than the NARX model and many other models reported in literature.
Adaptive soft sensor design using a regression neural network and bias update strategy for non-linear industrial processes
(IOP, 2023-05) Rout, Bijay Kumar; Mohanta, Hare Krishna; Pani, Ajaya Kumar
Soft sensing of quality parameters in process industries has been an active area of research for the past two decades. To improve the performance of soft sensors in the scenario of time varying process states, adaptation capability is incorporated into the soft sensor model. In this work, recursive (R), sliding window (SW) and just-in-time learning (JITL) frameworks are used for adaptive soft sensor design. A rarely explored modeling technique in the adaptation framework, the generalized regression neural network (GRNN) is used as a local modeling strategy. A bias update procedure is applied during the model adaptation activity to improve the prediction accuracy. Further, the performances of the developed models are tested against input–output data dimension mismatch along with various concept drift phenomena by considering a different number of labeled samples for inputs and outputs. The proposed adaptation strategy is applied on two benchmark industrial processes. Simulation results show that the GRNN local modeling approach combined with the bias update strategy gives higher prediction accuracy than other adaptive soft sensors proposed in the literature. Moreover, GRNN local modeling strategy using SW adaptation mechanism has the least computation time among the three adaptation methods due to the use of a low number of samples for model development.
Application of Soft Sensors in Process Monitoring and Control: A Review
(SSRN, 2010-01-04) Mohanta, Hare Krishna; Pani, Ajaya Kumar
A major problem in product quality control in process industries is the difficulty of continuous online measurement of certain output variables especially related to composition. Although analytical instruments are available in some cases, significant time delays associated with most of such instruments make timely control difficult and sometimes impossible. Soft sensor is a modeling approach to estimate hard-to-measure process variables (primary variables) from easy-to-measure online process variables (secondary variables). The important steps of soft sensor development are collection of historical plant data for different variables and their processing, development of a model based on the available data and validation of the model. This paper presents the need and advantages of soft sensor implementation in process industries and does a critical review of various techniques available for data handling and modeling.
Application of Wavelet Transform in Controls: A Review
(IUP, 2005-03) Mohanta, Hare Krishna
Wavelet analysis is an emerging field of mathematics that has provided new tools and algorithms suited for the type of problems encountered in process monitoring and control. In this paper, a review is presented for the applications of wavelet transform in advanced control systems, particularly in Model Predictive Control, Intelligent Control, Robust Control, Adaptive Control, Nonlinear Control, Process Modeling and Control, Process Identification and Control, Process Monitoring, Diagnosis and Control, Statistical Process Control and Optimal Control. The underlying principles in each of these control strategies have also been briefly discussed. Over the past few years, wavelets and wavelet-based analysis have found their way into many different fields of science and engineering. The wavelet transform is a tool that provides descriptions of functions or signals in the time-frequency plane (Daubechies, 1992). Using traditional mathematical tools, one can study the properties of a phenomenon either in time domain or frequency domain. Although the Fourier transform and its inverse allow a passage from one domain to another domain, it does not give a simultaneous view of the phenomenon in both domains. Wavelets, on the other hand, are the basis functions, which are localized in both time and frequency domains. A basis, which preserves the time-frequency information of the signal, is of significant advantage in control system synthesis and analysis. Wavelets, because of their time-frequency localization and multiresolution properties offer an efficient framework for representation and characterization of signals, especially that non-stationary in nature. Wavelets can also be useful in obtaining process models that describe the process behavior on different time scales. These properties are very attractive from process identification and controller design prospective and recently have been shown to be of significant advantage for some of the process engineering problems (Bakshi and Stephanopoulos, 1993; Palavajjhala et al., 1994).
BINIVOX catalyst for hydrogen production from ethanol by low temperature steam reforming (LTSR)
(Springer, 2017-11) Roy, Banasri; Mohanta, Hare Krishna
Nickel doped bismuth vanadate [;BINIVOX] calcined at (BINIVOX-800) catalyst is prepared by a solution combustion method. The catalytic activity study is carried in the temperature range of 250–, and with the molar feed ratios of water: ethanol at 23:1 and 2.5:1. The study reveals an increase in the ethanol conversion and selectivity of carbon dioxide & hydrogen but a decrease in the selectivity of carbon monoxide and methane with an increase in temperature and water: ethanol mole ratio. Fresh and used catalysts are characterized using DTA, TGA, XRD and FTIR. XRD results reveal that the fresh catalyst is phase pure γ-BINIVOX. The phase purity and crystallinity of the catalyst is retained after 30 h of activity study.
Development and comparison of neural network based soft sensors for online estimation of cement clinker quality
(Elsiever, 2013-01) Mohanta, Hare Krishna; Pani, Ajaya Kumar
The online estimation of process outputs mostly related to quality, as opposed to their belated measurement by means of hardware measuring devices and laboratory analysis, represents the most valuable feature of soft sensors. As of now there have been very few attempts for soft sensing of cement clinker quality which is mostly done by offline laboratory analysis resulting at times in low quality clinker. In the present work three different neural network based soft sensors have been developed for online estimation of cement clinker properties. Different input and output data for a rotary cement kiln were collected from a cement plant producing 10,000 tons of clinker per day. The raw data were pre-processed to remove the outliers and the resulting missing data were imputed. The processed data were then used to develop a back propagation neural network model, a radial basis network model and a regression network model to estimate the clinker quality online. A comparison of the estimation capabilities of the three models has been done by simulation of the developed models. It was observed that radial basis network model produced better estimation capabilities than the back propagation and regression network models.
Differential evolution based optimal fuzzy logic control of pH neutralization process
(IEEE, 2014) Bhanot, Surekha; Mohanta, Hare Krishna
Differential evolution (DE) is a member of evolutionary algorithm family which has gained popularity due to its conceptual simplicity and better convergence. This paper presents fuzzy logic based pH control scheme for neutralization process in which DE is used to optimize the input and output membership functions of fuzzy inference system (FIS). The fitness function for optimization is integral of squared errors (ISE). DE is able to converge and find optimal global solution over narrow as well as wide search spaces. Finally the controller performance has been evaluated for servo and regulatory operations.
Digital image analysis of gas bypassing and mixing in gas-fluidized bed: effect of particle shape
(Wiley, 2024-10) Mohanta, Hare Krishna; Goyal, Navneet; Sande, Priya Christina; Sharma, Arvind Kumar
The study investigates effect of particle shape on gas bypassing and mixing of gas-fluidized Geldart A particles. A shallow fluidized bed (FB), configured at benchscale, was used with digital image analysis (DIA) for the investigation. The extent of scatter of tracer particles throughout the bed was assessed from DIA images of defluidized powder. A novel method employing Jupyter notebook software, was used to directly determine Mixing Index from digital images. Remarkably, platelet-shaped China clay powder displayed the best mixing characteristics (Mixing Index: 0.79) with no significant bypassing. Angular shaped Quartz displayed moderate mixing (Mixing Index: 0.67), but high bypassing (Bypassing Index: 0.75). Contrary to conventional assumptions, spherical-shaped diatomite exhibited poor mixing (Mixing Index: 0.61) with the highest bypassing (Bypassing Index: 0.82). Platelet particles performed well even with fines removal. Most likely, particle shape significantly influenced the number of available particle contact points, tracer migration, and traceronparticle binding.
Generic Model Controller with Adaptive State Estimation for Nonlinear Cstr
(IUP, 2009) Mohanta, Hare Krishna
A hybrid control scheme consisting of a generic model control (GMC) and a nonlinear adaptive state estimator (ASE) is designed. The ASE estimates the partially known parameters in the presence of process/predictor mismatch, whereas GMC takes care of the nonlinearities and interactions in the nonlinear industrial processes. The developed GMC-ASE controller is implemented in a jacketed continuous stirred-tank reactor (CSTR). The performance of the developed controller is compared with a conventional proportional-integral (PI) controller. It is observed that a GMC-ASE controller shows relatively better performance than the PI controller due to the exponential error convergence capability of the ASE estimator and high quality performance of the GMC controller.
Genetic Optimization based Adaptive Fuzzy Logic Control of a pH Neutralization Process
(Sersc, 2014) Mohanta, Hare Krishna; Bhanot, Surekha
A hybrid soft sensing approach of a cement mill using principal component analysis and artificial neural networks
(IEEE, 2013) Pani, Ajaya Kumar; Mohanta, Hare Krishna
Soft sensors play an important role in predicting the values of unmeasured process variables from knowledge of easily measured process variables. Online estimation of particle size is vital for efficient control of a grinding circuit. Due to high energy consumption in cement grinding processes and unavailability of reliable hardware sensors for continuous monitoring, soft sensors have tremendous scope of application in cement mills. Modern cement plants are increasingly using vertical roller mills for clinker grinding. While there have been some works reported in the literature about modelling of ball mills, very few research work is available on vertical roller mill modelling. In the present work a PCA based neural network model of a cement mill is developed based on the actual plant data for estimation of cement fineness. Real time data for all process variables relevant to cement grinding process were collected from a cement plant having a clinker grinding capacity of 235 TPH. The collected raw industrial data were pre processed for outlier removal and missing value imputation. Principal component analysis of the input data was performed to transform the original variables to a less number of un correlated principal components. The selected principal component scores were divided to a training set and a validation set using Kennard-Stone subset selection algorithm. The training set was used to develop a back propagation neural network model which was subsequently tested with the validation set. Simulations results show satisfactory prediction capabilities of the developed model over that of linear regression and principal component regression models.
Machine learning applied to predict key petroleum crude oil constituents
(Wiley, 2023-10) Mohanta, Hare Krishna; Sande, Priya Christina
Sulfur compounds are the most important inorganic constituents of petroleum and require to be estimated beforehand because of their corrosive nature and other processing anomalies during crude oil processing. Paraffins, naphthene, and aromatics form the bulk of crude oil. Machine learning (ML) predictions of these constituents were made by training the ML model with a diverse industrial data set of 515 oils. The XGBoost model gave an excellent R2 in the range 0.88–0.99 for the bulk compounds. R2 for sulfur was in the modest range of 0.45–0.6, which improved significantly to 0.8 for additional inputs. ML applicability was thereby found to depend on the nature of the constituent. This work furthers ML-based predictions, with the incentive of reducing expensive spectroscopic analytical methods.
Magnesium Aluminate Catalyzed Pyrolysis of n-Heptane
(IJCS, 2010) Mohanta, Hare Krishna
The effect of magnesium oxide precursor on the activity of magnesium aluminate catalyst for the pyrolysis of n-heptane has been investigated. Magnesium oxide was prepared either from magnesium acetate, magnesium nitrate, magnesium carbonate or hydrated magnesium oxide. In each case, magnesium aluminate (containing 28 wt.% MgO) was prepared. The prepared catalysts were characterized by X-ray diffraction, surface area and pore volume measurement, thermogravimetric analysis and chemisorption of carbon dioxide. Compared to noncatalytic pyrolysis, the conversion of n-heptane increased in the presence of each of the catalysts. Depending on the salt used for the preparation of MgO, the conversion, product yields and coke deposition were different. The cracking activity increased with an increase in the total basicity of the catalyst. Magnesium aluminate prepared using magnesium oxide obtained from magnesium acetate showed the highest conversion as well as the highest yields of ethylene.
Neural Control of Neutralization Process using Fuzzy Inference System based Lookup Table
(IJCA, 2021-10-20) Mohanta, Hare Krishna; Bhanot, Surekha
Over a number of years, pH control of neutralization process is recognized as a benchmark for modeling and control of nonlinear processes. This paper first describes dynamic modeling of pH neutralization process. Thereafter fuzzy logic based pH control scheme for neutralization process is developed. Further, a two-dimensional (2-D) lookup table is generated based on defuzzification mechanism of fuzzy inference system (FIS). Finally, using this lookup table, a neural network control for pH neutralization process is developed. Performances of fuzzy logic based control and lookup table based neural network control for servo and regulatory operations are compared based on integral square error (ISE) and integral absolute error (IAE) criterions. Results indicate that lookup table based neural network control performs better than fuzzy logic based control.
Neural Network Soft Sensor Application in Cement Industry: Prediction of Clinker Quality Parameters
(IEEE, 2011) Pani, Ajaya Kumar; Mohanta, Hare Krishna
A soft sensor tries to estimate difficult to measure quality parameters from the knowledge of easy to measure online process variables. Empirical approach of soft sensor development has gained much popularity recently due to availability of huge quantity of actual process data stored in the industrial database. In this work a soft sensor based on back propagation neural network has been developed for rotary cement kiln. For this purpose, data for all variables associated with rotary cement kiln were collected over a period of one month from a cement industry having a capacity of 10000 tons of clinker production per day. Data preprocessing of the raw data has been performed to remove the anomalies present in the original data. The processed data was used to develop the neural network model of the kiln. Model simulation produced quite satisfactory prediction of free lime, C 3 S, C 2 S and C 3 A.
Non-negative matrix factorization combined with Fuzzy C-means enhanced k-nearest neighbor for fault detection and diagnosis in process industries
(Elsevier, 2026-01) Mohanta, Hare Krishna; Garg, Girish Kant; Pani, Ajaya Kumar
In the context of Industry 4.0, modern industrial processes generate high-dimensional, non-negative and potentially non-linear data streams, posing significant challenges for effective fault detection and diagnosis. Traditional statistical and multivariate techniques mostly assume restrictions such as a Gaussian distribution and linear relationships, which limit their use in real-world problems. This paper proposes a novel hybrid technique, Non-negative Matrix Factorization (NMF)–Enhanced Local Weighting Fuzzy C-Means (FCM) with Distance-Based k-Nearest Neighbors (NEFkNN), for fault detection. Initially, NMF is applied for dimensionality reduction. This is followed by FCM clustering, where cluster centers were refined with an enhanced local weighting (ELW) strategy. Detection threshold is determined by calculating the Euclidean distance between each sample and the enhanced cluster centers. A cluster-sensitive feature attribution method called Cluster-Aware Residual Contribution Analysis (CARCA) is proposed for fault diagnosis, which adjusts each feature's contribution to a fault by accounting for the local variance within its assigned cluster, enhancing interpretability. The NEFkNN technique was evaluated on two benchmark systems of a wastewater treatment plant(WWTP) and a continuous stirred tank reactor(CSTR) and achieved high fault detection rates and low false alarm rates. The diagnosis indicates that the fault is highly localized and attributable to a single process variable.
Online implementation of wavelet-based identification and dynamic matrix control in a heat exchanger unit
(Inderscience, 2010-06) Mohanta, Hare Krishna
This paper presents an online implementation of wavelet-based least-square identification (WLSI) and wavelet-based dynamic matrix control (WDMC) in a plate-type heat exchanger unit. Wavelet domain |blocking| and |condensing| (B&C) techniques are used to reduce the computation time for optimisation of dynamic matrix control (DMC) performance index. Algorithms for WLSI and WDMC are developed and implemented in the online identification and control of temperature in a heat exchanger unit. The results are compared with conventional PID and DMC controllers. It is observed that the WDMC is better and robust than the other controllers
Online monitoring and control of particle size in the grinding process using least square support vector regression and resilient back propagation neural network
(Elsiever, 2015-05) Mohanta, Hare Krishna; Pani, Ajaya Kumar
Particle size soft sensing in cement mills will be largely helpful in maintaining desired cement fineness or Blaine. Despite the growing use of vertical roller mills (VRM) for clinker grinding, very few research work is available on VRM modeling. This article reports the design of three types of feed forward neural network models and least square support vector regression (LS-SVR) model of a VRM for online monitoring of cement fineness based on mill data collected from a cement plant. In the data pre-processing step, a comparative study of the various outlier detection algorithms has been performed. Subsequently, for model development, the advantage of algorithm based data splitting over random selection is presented. The training data set obtained by use of Kennard–Stone maximal intra distance criterion (CADEX algorithm) was used for development of LS-SVR, back propagation neural network, radial basis function neural network and generalized regression neural network models. Simulation results show that resilient back propagation model performs better than RBF network, regression network and LS-SVR model. Model implementation has been done in SIMULINK platform showing the online detection of abnormal data and real time estimation of cement Blaine from the knowledge of the input variables. Finally, closed loop study shows how the model can be effectively utilized for maintaining cement fineness at desired value.
Online monitoring of cement clinker quality using multivariate statistics and Takagi-Sugeno fuzzy-inference technique
(Elsiever, 2016-12) Pani, Ajaya Kumar; Mohanta, Hare Krishna
This article addresses the issue of outlier detection in industrial data using robust multivariate techniques and soft sensing of clinker quality in cement industries. Feed-forward artificial neural network (back propagation, radial basis function and regression neural network) and fuzzy inference (Mamdani and Takagi-Sugeno (T-S)) based soft sensor models are developed for simultaneous prediction of eight clinker quality parameters (free lime, lime saturation factor, silica modulus, alumina modulus, alite, belite, aluminite and ferrite). Required input-output data for cement clinkerization process were obtained from a cement plant with a production capacity of 10000 t of clinker per day. In the initial data preprocessing activity, various distance based robust multivariate outlier detection techniques were applied and their performances were compared. The developed soft-sensors were investigated for their performance by computing various statistical model performance parameters. Results indicate that the accuracy and computation time of the T-S fuzzy inference model is quite acceptable for online monitoring of clinker quality.
Optimized adaptive neuro-fuzzy inference system for pH control
(IEEE, 2013) Bhanot, Surekha; Mohanta, Hare Krishna
pH control plays an important role in many modern industrial plants due to strict environment regulations. This paper presents fuzzy logic based pH control scheme for neutralization process in which genetic algorithm is used to optimize the various membership functions of fuzzy inference system. Further, using this optimized fuzzy inference system, adaptive neuro-fuzzy inference system for pH neutralization process is developed. Performances of both control schemes are compared for servo and regulatory operations. Results indicate that adaptive neuro-fuzzy inference system based control uses fewer rules as compared to optimized fuzzy logic based control.