{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:54:02Z","timestamp":1740149642276,"version":"3.37.3"},"reference-count":54,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T00:00:00Z","timestamp":1694563200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"This study investigates the integration of soft sensors and deep learning in the oil-refinery industry to improve monitoring efficiency and predictive accuracy in complex industrial processes, particularly de-ethanization and debutanization. Soft sensor models were developed to estimate critical variables such as the C2 and C5 contents in liquefied petroleum gas (LPG) after distillation and the energy consumption of distillation columns. The refinery\u2019s LPG purification process relies on periodic sampling and laboratory analysis to maintain product specifications. The models were tested using data from actual refinery operations, addressing challenges such as scalability and handling dirty data. Two deep learning models, an artificial neural network (ANN) soft sensor model and an ensemble random forest regressor (RFR) model, were developed. This study emphasizes model interpretability and the potential for real-time updating or online learning. The study also proposes a comprehensive, iterative solution for predicting and optimizing component concentrations within a dual-column distillation system, highlighting its high applicability and potential for replication in similar industrial scenarios.<\/jats:p>","DOI":"10.3390\/s23187858","type":"journal-article","created":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T14:09:22Z","timestamp":1694700562000},"page":"7858","source":"Crossref","is-referenced-by-count":6,"title":["Soft Sensing of LPG Processes Using Deep Learning"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7568-764X","authenticated-orcid":false,"given":"Nikolaos","family":"Sifakis","sequence":"first","affiliation":[{"name":"Industrial and Digital Innovations Research Group (INDIGO), School of Production Engineering and Management, Akrotiri Campus, Technical University of Crete, 73100 Chania, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4263-9123","authenticated-orcid":false,"given":"Nikolaos","family":"Sarantinoudis","sequence":"additional","affiliation":[{"name":"Industrial and Digital Innovations Research Group (INDIGO), School of Production Engineering and Management, Akrotiri Campus, Technical University of Crete, 73100 Chania, Greece"}]},{"given":"George","family":"Tsinarakis","sequence":"additional","affiliation":[{"name":"Industrial and Digital Innovations Research Group (INDIGO), School of Production Engineering and Management, Akrotiri Campus, Technical University of Crete, 73100 Chania, Greece"}]},{"given":"Christos","family":"Politis","sequence":"additional","affiliation":[{"name":"Industrial and Digital Innovations Research Group (INDIGO), School of Production Engineering and Management, Akrotiri Campus, Technical University of Crete, 73100 Chania, Greece"}]},{"given":"George","family":"Arampatzis","sequence":"additional","affiliation":[{"name":"Industrial and Digital Innovations Research Group (INDIGO), School of Production Engineering and Management, Akrotiri Campus, Technical University of Crete, 73100 Chania, Greece"}]}],"member":"1968","published-online":{"date-parts":[[2023,9,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"103025","DOI":"10.1016\/j.jprocont.2023.103025","article-title":"Just-in-Time Based Soft Sensors for Process Industries: A Status Report and Recommendations","volume":"128","author":"Yeo","year":"2023","journal-title":"J. Process Control"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.aei.2018.03.003","article-title":"Soft Sensor Based on Stacked Auto-Encoder Deep Neural Network for Air Preheater Rotor Deformation Prediction","volume":"36","author":"Wang","year":"2018","journal-title":"Adv. Eng. Inform."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1175","DOI":"10.1016\/j.ifacol.2017.08.270","article-title":"An IsaMillTM Soft Sensor Based on Random Forests and Principal Component Analysis","volume":"50","author":"Napier","year":"2017","journal-title":"IFAC-PapersOnLine"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"105292","DOI":"10.1016\/j.conengprac.2022.105292","article-title":"Enhancing the Reliability and Accuracy of Data-Driven Dynamic Soft Sensor Based on Selective Dynamic Partial Least Squares Models","volume":"127","author":"Shao","year":"2022","journal-title":"Control Eng. Pract."},{"key":"ref_5","unstructured":"Sujatha, K., Krishnakumar, R., Deepalakshmi, B., Bhavani, N.P.G., and Srividhya, V. (2021). Handbook of Nanomaterials for Sensing Applications, Elsevier."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.ces.2013.02.069","article-title":"Soft Sensor Assisted Dynamic Bioprocess Control: Efficient Tools for Bioprocess Development","volume":"96","author":"Sagmeister","year":"2013","journal-title":"Chem. Eng. Sci."},{"key":"ref_7","first-page":"100263","article-title":"Digitization in Bioprocessing: The Role of Soft Sensors in Monitoring and Control of Downstream Processing for Production of Biotherapeutic Products","volume":"12","author":"Rathore","year":"2022","journal-title":"Biosens. Bioelectron. X"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"102371","DOI":"10.1016\/j.flowmeasinst.2023.102371","article-title":"Critical Measurement Parameters Estimation in Liquid Rocket Engine Using LSTM-Based Soft Sensor","volume":"92","author":"Devakumar","year":"2023","journal-title":"Flow Meas. Instrum."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"110126","DOI":"10.1016\/j.compscitech.2023.110126","article-title":"3D Printing of Soft and Porous Composite Pressure Sensor with Monotonic and Positive Resistance Response","volume":"241","author":"Tang","year":"2023","journal-title":"Compos. Sci. Technol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"101877","DOI":"10.1016\/j.apmt.2023.101877","article-title":"Robotic E-Skin for High Performance Stretchable Acceleration Sensor via Combinations of Novel Soft and Functional Polymers","volume":"33","author":"Sekine","year":"2023","journal-title":"Appl. Mater. Today"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"113084","DOI":"10.1016\/j.sna.2021.113084","article-title":"An Intrinsically Embedded Pressure-Temperature Dual-Mode Soft Sensor towards Soft Robotics","volume":"332","author":"Zou","year":"2021","journal-title":"Sens. Actuators A Phys."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"102105","DOI":"10.1016\/j.flowmeasinst.2021.102105","article-title":"Recurrent Neural Network Based Soft Sensor for Flow Estimation in Liquid Rocket Engine Injector Calibration","volume":"83","author":"Vinoth","year":"2022","journal-title":"Flow Meas. Instrum."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"108128","DOI":"10.1016\/j.compeleceng.2022.108128","article-title":"Artificial Intelligence\u2014Enabled Soft Sensor and Internet of Things for Sustainable Agriculture Using Ensemble Deep Learning Architecture","volume":"102","author":"Wongchai","year":"2022","journal-title":"Comput. Electr. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"105447","DOI":"10.1016\/j.conengprac.2023.105447","article-title":"Edge-Computing Based Soft Sensors with Local Finite Impulse Response Models for Vehicle Wheel Center Loads Estimation under Multiple Working Conditions","volume":"133","author":"Wang","year":"2023","journal-title":"Control Eng. Pract."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"113036","DOI":"10.1016\/j.measurement.2023.113036","article-title":"Pseudo Label Estimation Based on Label Distribution Optimization for Industrial Semi-Supervised Soft Sensor","volume":"217","author":"Jin","year":"2023","journal-title":"Measurement"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"104895","DOI":"10.1016\/j.chemolab.2023.104895","article-title":"An Online Soft Sensor Based on Adaptive Double Gaussian Bayesian Network","volume":"240","author":"Dong","year":"2023","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"104678","DOI":"10.1016\/j.chemolab.2022.104678","article-title":"Correntropy Long Short Term Memory Soft Sensor for Quality Prediction in Industrial Polyethylene Process","volume":"231","author":"Liu","year":"2022","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/j.isatra.2022.03.013","article-title":"A Soft Sensor Model Based on Long&short-Term Memory Dual Pathways Convolutional Gated Recurrent Unit Network for Predicting Cement Specific Surface Area","volume":"130","author":"Sun","year":"2022","journal-title":"ISA Trans."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.jprocont.2022.09.008","article-title":"Flexible Clockwork Recurrent Neural Network for Multirate Industrial Soft Sensor","volume":"119","author":"Chang","year":"2022","journal-title":"J. Process Control"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"103661","DOI":"10.1016\/j.jwpe.2023.103661","article-title":"Development of Transparent High-Frequency Soft Sensor of Total Nitrogen and Total Phosphorus Concentrations in Rivers Using Stacked Convolutional Auto-Encoder and Explainable AI","volume":"53","author":"Heo","year":"2023","journal-title":"J. Water Process Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"722202","DOI":"10.3389\/fbioe.2021.722202","article-title":"Challenges in the Development of Soft Sensors for Bioprocesses: A Critical Review","volume":"9","author":"Brunner","year":"2021","journal-title":"Front. Bioeng. Biotechnol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"107756","DOI":"10.1016\/j.compchemeng.2022.107756","article-title":"Development of a Machine Learning-Based Soft Sensor for an Oil Refinery\u2019s Distillation Column","volume":"161","author":"Ferreira","year":"2022","journal-title":"Comput. Chem. Eng."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"107324","DOI":"10.1016\/j.compchemeng.2021.107324","article-title":"A Spectral AutoML Approach for Industrial Soft Sensor Development: Validation in an Oil Refinery Plant","volume":"150","author":"Cabrita","year":"2021","journal-title":"Comput. Chem. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"106722","DOI":"10.1016\/j.compchemeng.2020.106722","article-title":"Machine Learning Refinery Sensor Data to Predict Catalyst Saturation Levels","volume":"134","author":"Steurtewagen","year":"2020","journal-title":"Comput. Chem. Eng."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"104087","DOI":"10.1016\/j.chemolab.2020.104087","article-title":"Soft Sensor Modeling for Fraction Yield of Crude Oil Based on Ensemble Deep Learning","volume":"204","author":"Yi","year":"2020","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"108546","DOI":"10.1016\/j.asoc.2022.108546","article-title":"Adaptive Non-Linear Soft Sensor for Quality Monitoring in Refineries Using Just-in-Time Learning\u2014Generalized Regression Neural Network Approach","volume":"119","author":"Mohanta","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"107449","DOI":"10.1016\/j.compchemeng.2021.107449","article-title":"PAT Soft Sensors for Wide Range Prediction of Key Properties of Diesel Fuels and Blending Components for the Oil Industry","volume":"153","author":"Cabrita","year":"2021","journal-title":"Comput. Chem. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"5517","DOI":"10.1016\/j.aej.2021.10.060","article-title":"A Distributed Soft Sensors Model for Managing Vague and Uncertain Multimedia Communications Using Information Fusion Techniques","volume":"61","author":"Paggi","year":"2022","journal-title":"Alex. Eng. J."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"100858","DOI":"10.1016\/j.iot.2023.100858","article-title":"A Comprehensive Soft Security Model for Cognitive Internet of Things","volume":"23","author":"Abadi","year":"2023","journal-title":"Internet Things"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"104830","DOI":"10.1016\/j.micpro.2023.104830","article-title":"Intelligent Transportation System Based on Smart Soft-Sensors to Analyze Road Traffic and Assist Driver Behavior Applicable to Smart Cities","volume":"100","author":"Barodi","year":"2023","journal-title":"Microprocess. Microsyst."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1016\/j.isatra.2023.04.012","article-title":"A Nonlinear Industrial Soft Sensor Modeling Method Based on Locality Preserving Stochastic Configuration Network with Utilizing Unlabeled Samples","volume":"139","author":"Zhao","year":"2023","journal-title":"ISA Trans."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"105988","DOI":"10.1016\/j.engappai.2023.105988","article-title":"The Role of Artificial Intelligence-Driven Soft Sensors in Advanced Sustainable Process Industries: A Critical Review","volume":"121","author":"Perera","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"111897","DOI":"10.1016\/j.measurement.2022.111897","article-title":"Triple Attention-Based Deep Convolutional Recurrent Network for Soft Sensors","volume":"202","author":"Yao","year":"2022","journal-title":"Measurement"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1016\/j.cherd.2022.01.026","article-title":"Semi-Supervised Ensemble Support Vector Regression Based Soft Sensor for Key Quality Variable Estimation of Nonlinear Industrial Processes with Limited Labeled Data","volume":"179","author":"Li","year":"2022","journal-title":"Chem. Eng. Res. Des."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.chemolab.2017.01.004","article-title":"Data-Driven Soft Sensor Approach for Online Quality Prediction Using State Dependent Parameter Models","volume":"162","author":"Bidar","year":"2017","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1016\/S1570-7946(08)80166-6","article-title":"Practical Challenges in Developing Data-Driven Soft Sensors for Quality Prediction","volume":"25","author":"Liu","year":"2008","journal-title":"Comput. Aided Chem. Eng."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"118958","DOI":"10.1016\/j.ces.2023.118958","article-title":"Soft Sensor Modeling for Small Data Scenarios Based on Data Enhancement and Selective Ensemble","volume":"279","author":"Jin","year":"2023","journal-title":"Chem. Eng. Sci."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"106124","DOI":"10.1016\/j.engappai.2023.106124","article-title":"Deep Gaussian Mixture Adaptive Network for Robust Soft Sensor Modeling with a Closed-Loop Calibration Mechanism","volume":"122","author":"Zhang","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"102367","DOI":"10.1016\/j.jwpe.2021.102367","article-title":"Advances in Soft Sensors for Wastewater Treatment Plants: A Systematic Review","volume":"44","author":"Ching","year":"2021","journal-title":"J. Water Process Eng."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Sifakis, N., Savvakis, N., Daras, T., and Tsoutsos, T. (2019). Analysis of the Energy Consumption Behavior of European RES Cooperative Members. Energies, 12.","DOI":"10.3390\/en12060970"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Sifakis, N., Daras, T., and Tsoutsos, T. (2020). How Much Energy Efficient Are Renewable Energy Sources Cooperatives\u2019 Initiatives?. Energies, 13.","DOI":"10.3390\/en13051136"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Sifakis, N., Aryblia, M., Daras, T., Tournaki, S., and Tsoutsos, T. (2021). The Impact of COVID-19 Pandemic in Mediterranean Urban Air Pollution and Mobility. Energy Sources Part A Recovery Util. Environ. Eff., 1\u201316.","DOI":"10.1080\/15567036.2021.1895373"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1016\/j.procir.2020.04.009","article-title":"Streamlining the Development of Data-Driven Industrial Applications by Automated Machine Learning","volume":"93","author":"Mayr","year":"2020","journal-title":"Procedia CIRP"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/j.procir.2023.03.047","article-title":"Predictive Quality Modeling for Ultra-Short-Pulse Laser Structuring Utilizing Machine Learning","volume":"117","author":"Leyendecker","year":"2023","journal-title":"Procedia CIRP"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"11332","DOI":"10.1016\/j.ifacol.2020.12.541","article-title":"Platforms for Automatic PAT Soft Sensor Development and Analysis","volume":"53","author":"Reis","year":"2020","journal-title":"IFAC-PapersOnLine"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Bangert, P. (2021). Machine Learning and Data Science in the Oil and Gas Industry: Best Practices, Tools, and Case Studies, Elsevier.","DOI":"10.1016\/B978-0-12-820714-7.00004-2"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"100589","DOI":"10.1016\/j.measen.2022.100589","article-title":"Measurement of Oxygen Content in Water with Purity through Soft Sensor Model","volume":"24","author":"Thiruneelakandan","year":"2022","journal-title":"Meas. Sens."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"100168","DOI":"10.1016\/j.rico.2022.100168","article-title":"Distance to Empty Soft Sensor for Ford Escape Electric Vehicle","volume":"9","author":"Sekhar","year":"2022","journal-title":"Results Control Optim."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"46","DOI":"10.3182\/20080706-5-KR-1001.00007","article-title":"Fuzzy Soft Sensors for Chemical and Oil Refining Processes","volume":"41","author":"Bakhtadze","year":"2008","journal-title":"IFAC Proc. Vol."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Olaizola, I., Quartulli, M., Unzueta, E., Goicolea, J., and Fl\u00f3rez, J. (2022). Refinery 4.0, a Review of the Main Challenges of the Industry 4.0 Paradigm in Oil & Gas Downstream. Sensors, 22.","DOI":"10.3390\/s22239164"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Syafrudin, M., Alfian, G., Fitriyani, N.L., and Rhee, J. (2018). Performance Analysis of IoT-Based Sensor, Big Data Processing, and Machine Learning Model for Real-Time Monitoring System in Automotive Manufacturing. Sensors, 18.","DOI":"10.3390\/s18092946"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/j.ins.2019.11.039","article-title":"Deep Relevant Representation Learning for Soft Sensing","volume":"514","author":"Yan","year":"2020","journal-title":"Inf. Sci."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Rozanec, J.M., Trajkova, E., Onat, M.K., Sarantinoudis, N., Arampatzis, G., Fortuna, B., and Mladenic, D. (2022, January 20\u201322). Machine-Learning-Based Soft Sensors for Energy Efficient Operation of Crude Distillation Units. Proceedings of the International Conference on Electrical, Computer, and Energy Technologies (ICECET 2022), Prague, Czech Republic.","DOI":"10.1109\/ICECET55527.2022.9872983"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1016\/j.compchemeng.2008.12.012","article-title":"Data-Driven Soft Sensors in the Process Industry","volume":"33","author":"Kadlec","year":"2009","journal-title":"Comput. Chem. Eng."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/18\/7858\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T14:21:55Z","timestamp":1694701315000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/18\/7858"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,13]]},"references-count":54,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["s23187858"],"URL":"https:\/\/doi.org\/10.3390\/s23187858","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2023,9,13]]}}}