scholarly journals Machine Learning-Based Prediction of a BOS Reactor Performance from Operating Parameters

Processes ◽  
2020 ◽  
Vol 8 (3) ◽  
pp. 371
Author(s):  
Alireza Rahnama ◽  
Zushu Li ◽  
Seetharaman Sridhar
Keyword(s):  
Machine Learning ◽  
Pilot Plant ◽  
Oxygen Flow ◽  
Operating Parameters ◽  
Reactor Performance ◽  
Total Oxygen ◽  
Decarburization Rate ◽  
Lance Height ◽  
Positive Correlation ◽  
Waste Gas

A machine learning-based analysis was applied to process data obtained from a Basic Oxygen Steelmaking (BOS) pilot plant. The first purpose was to identify correlations between operating parameters and reactor performance, defined as rate of decarburization (dc/dt). Correlation analysis showed, as expected a strong positive correlation between the rate of decarburization (dc/dt) and total oxygen flow. On the other hand, the decarburization rate exhibited a negative correlation with lance height. Less obviously, the decarburization rate, also showed a positive correlation with temperature of the waste gas and CO2 content in the waste gas. The second purpose was to train the pilot-plant dataset and develop a neural network based regression to predict the decarburization rate. This was used to predict the decarburization rate in a BOS furnace in an actual manufacturing plant based on lance height and total oxygen flow. The performance was satisfactory with a coefficient of determination of 0.98, confirming that the trained model can adequately predict the variation in the decarburization rate (dc/dt) within BOS reactors.

scholarly journals MACHINE LEARNING METHODS IN MONITORING OPERATING BEHAVIOUR OF MARINE TWO-STROKE DIESEL ENGINE

Transport ◽  
2020 ◽  
Vol 35 (5) ◽  
pp. 462-473
Author(s):  
Aleksandar Vorkapić ◽  
Radoslav Radonja ◽  
Karlo Babić ◽  
Sanda Martinčić-Ipšić
Keyword(s):  
Machine Learning ◽  
Anomaly Detection ◽  
Fuel Consumption ◽  
Performance Monitoring ◽  
Absolute Error ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Operating Parameters ◽  
Detection Model ◽  
Modelling Framework

The aim of this article is to enhance performance monitoring of a two-stroke electronically controlled ship propulsion engine on the operating envelope. This is achieved by setting up a machine learning model capable of monitoring influential operating parameters and predicting the fuel consumption. Model is tested with different machine learning algorithms, namely linear regression, multilayer perceptron, Support Vector Machines (SVM) and Random Forests (RF). Upon verification of modelling framework and analysing the results in order to improve the prediction accuracy, the best algorithm is selected based on standard evaluation metrics, i.e. Root Mean Square Error (RMSE) and Relative Absolute Error (RAE). Experimental results show that, by taking an adequate combination and processing of relevant sensory data, SVM exhibit the lowest RMSE 7.1032 and RAE 0.5313%. RF achieve the lowest RMSE 22.6137 and RAE 3.8545% in a setting when minimal number of input variables is considered, i.e. cylinder indicated pressures and propulsion engine revolutions. Further, article deals with the detection of anomalies of operating parameters, which enables the evaluation of the propulsion engine condition and the early identification of failures and deterioration. Such a time-dependent, self-adopting anomaly detection model can be used for comparison with the initial condition recorded during the test and sea run or after survey and docking. Finally, we propose a unified model structure, incorporating fuel consumption prediction and anomaly detection model with on-board decision-making process regarding navigation and maintenance.

A Fuzzy Model with Thermodynamic Based Consequents and a Niching Swarm-Based Supervisor to Capture the Uncertainties of Damavand Power System

Fuzzy Systems ◽  
2017 ◽  
pp. 292-307
Author(s):  
Ahmad Mozaffari ◽  
Moein Mohammadpour ◽  
Alireza Fathi ◽  
Mofid Gorji-Bandpy
Keyword(s):  
Machine Learning ◽  
Power System ◽  
Intelligent System ◽  
Fuzzy Model ◽  
Operating Conditions ◽  
Operating Parameters ◽  
Fuzzy Approach ◽  
Swarm Optimization ◽  
Learning Mechanism ◽  
High Degree

In this investigation, a novel fuzzy mathematical program based on thermodynamic principles is implemented to capture the uncertainties of a practical power system, known as Damavand power plant. The proposed intelligent machine takes the advantages of a niching bio-inspired learning mechanism to be reconciled to the requirements of the problem at hand. The aim of the bio-inspired fuzzy based intelligent system is to yield a model capable of recognizing different operating parameters of Damavand power system under different operating conditions. To justify the privileges of using a niching metaheuristic over gradient descend methods, the authors use the data, derived through data acquisition, together with a machine learning based approach to estimate the multi-modality associated with the training of the proposed fuzzy model. Moreover, the niching bio-inspired metaheuristic, niching particle swarm optimization (NPSO), is compared to canonical PSO (CPSO), stochastic social PSO (SSPSO), unified PSO (UPSO), comprehensive learning PSO (CLPSO), PSO with constriction factor (PSOCF) and fully informed PSO (FIPSO). Through experiments and analysis of the characteristics of the problem being optimized, it is proved that NPSO is not only able to tackle the deficiencies of the learning process, but also can effectively adjust the fuzzy approach to conduct the identification process with a high degree of robustness and accuracy.

scholarly journals The influence of machine learning-based knowledge management model on enterprise organizational capability innovation and industrial development

PLoS ONE ◽  
2020 ◽  
Vol 15 (12) ◽  
pp. e0242253
Author(s):  
Zhigang Zhou ◽  
Yanyan Liu ◽  
Hao Yu ◽  
Lihua Ren
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Knowledge Management ◽  
Knowledge Acquisition ◽  
Industrial Development ◽  
Management Model ◽  
Data Mining Algorithm ◽  
Organizational Capability ◽  
Positive Correlation ◽  
Engineering Cost

The aims are to explore the construction of the knowledge management model for engineering cost consulting enterprises, and to expand the application of data mining techniques and machine learning methods in constructing knowledge management model. Through a questionnaire survey, the construction of the knowledge management model of construction-related enterprises and engineering cost consulting enterprises is discussed. First, through the analysis and discussion of ontology-based data mining (OBDM) algorithm and association analysis (Apriori) algorithm, a data mining algorithm (ML-AR algorithm) on account of ontology-based multilayer association and machine learning is proposed. The performance of the various algorithms is compared and analyzed. Second, based on the knowledge management level, analysis and statistics are conducted on the levels of knowledge acquisition, sharing, storage, and innovation. Finally, according to the foregoing, the knowledge management model based on engineering cost consulting enterprises is built and analyzed. The results show that the reliability coefficient of this questionnaire is above 0.8, and the average extracted value is above 0.7, verifying excellent reliability and validity. The efficiency of the ML-AR algorithm at both the number of transactions and the support level is better than the other two algorithms, which is expected to be applied to the enterprise knowledge management model. There is a positive correlation between each level of knowledge management; among them, the positive correlation between knowledge acquisition and knowledge sharing is the strongest. The enterprise knowledge management model has a positive impact on promoting organizational innovation capability and industrial development. The research work provides a direction for the development of enterprise knowledge management and the improvement of innovation ability.

scholarly journals Development of a Rapid Method to Assess Beer Foamability Based on Relative Protein Content Using RoboBEER and Machine Learning Modeling

Beverages ◽  
2020 ◽  
Vol 6 (2) ◽  
pp. 28 ◽  
Author(s):  
Claudia Gonzalez Viejo ◽  
Christopher H. Caboche ◽  
Edward D. Kerr ◽  
Cassandra L. Pegg ◽  
Benjamin L. Schulz ◽  
...  
Keyword(s):  
Machine Learning ◽  
Molecular Weight ◽  
Protein Content ◽  
Rapid Method ◽  
Near Infrared ◽  
Physical Parameters ◽  
Relative Quantification ◽  
Maximum Volume ◽  
Positive Correlation ◽  
Total Lifetime

Foam-related parameters are associated with beer quality and dependent, among others, on the protein content. This study aimed to develop a machine learning (ML) model to predict the pattern and presence of 54 proteins. Triplicates of 24 beer samples were analyzed through proteomics. Furthermore, samples were analyzed using the RoboBEER to evaluate 15 physical parameters (color, foam, and bubbles), and a portable near-infrared (NIR) device. Proteins were grouped according to their molecular weight (MW), and a matrix was developed to assess only the significant correlations (p < 0.05) with the physical parameters. Two ML models were developed using the NIR (Model 1), and RoboBEER (Model 2) data as inputs to predict the relative quantification of 54 proteins. Proteins in the 0–20 kDa group were negatively correlated with the maximum volume of foam (MaxVol; r = −0.57) and total lifetime of foam (TLTF; r = −0.58), while those within 20–40 kDa had a positive correlation with MaxVol (r = 0.47) and TLTF (r = 0.47). Model 1 was not as accurate (testing r = 0.68; overall r = 0.89) as Model 2 (testing r = 0.90; overall r = 0.93), which may serve as a reliable and affordable method to incorporate the relative quantification of important proteins to explain beer quality.

A Hydroprocessing Multicatalyst Deactivation and Reactor Performance Model−Pilot-Plant Life Test Applications

2005 ◽  
Vol 19 (3) ◽  
pp. 753-764 ◽  
Author(s):  
E. K. T. Kam ◽  
M. Al-Shamali ◽  
M. Juraidan ◽  
H. Qabazard
Keyword(s):  
Pilot Plant ◽  
Performance Model ◽  
Reactor Performance ◽  
Life Test ◽  
Plant Life

Preliminary Results of Laboratory Studies of Repository Chemistry for the Waste Isolation Pilot Plant

1990 ◽  
Vol 212 ◽  
Author(s):  
L. H. Brush ◽  
D. Grbic-Galic ◽  
D. T. Reed ◽  
X. Tong ◽  
R. H. Vreeland ◽  
...  
Keyword(s):  
Microbial Activity ◽  
Microbial Degradation ◽  
Pilot Plant ◽  
Gas Production ◽  
Lithostatic Pressure ◽  
Laboratory Studies ◽  
Waste Isolation Pilot Plant ◽  
Waste Gas ◽  
Preliminary Results ◽  
Design Basis

ABSTRACTThe design-basis, defense-related, transuranic (TRU) waste to be emplaced in the Waste Isolation Pilot Plant (WIPP) could, if sufficient H2O and nutrients were present, produce as much as 1,500 moles of gas per drum of waste. Gas production could pressurize the repository to lithostatic pressure (150 atm) and perhaps higher.Anoxic corrosion of Fe and Fe-base alloys and microbial degradation of cellulosics are the processes of greatest concern, but radiolysis of brine could also be important. The proposed backfill additives CaC03, CaO, CuSO4, KOH, and NaOH may remove or prevent the production of some of the expected gases. We describe these processes and present preliminary results of laboratory studies of anoxic corrosion and microbial activity.

scholarly journals Characterizing snow surface properties using airborne hyperspectral imagery for autonomous winter mobility

2021 ◽  
Author(s):  
Taylor Hodgdon ◽  
Anthony Fuentes ◽  
Brian Quinn ◽  
Bruce Elder ◽  
Sally Shoop
Keyword(s):  
Machine Learning ◽  
Grain Size ◽  
Surface Properties ◽  
Hyperspectral Imagery ◽  
Pearson Correlation ◽  
The United States ◽  
Snow Surface ◽  
Positive Correlation ◽  
Snow Properties ◽  
Vehicle Mobility

With changing conditions in northern climates it is crucial for the United States to have assured mobility in these high-latitude regions. Winter terrain conditions adversely affect vehicle mobility and, as such, they must be accurately characterized to ensure mission success. Previous studies have attempted to remotely characterize snow properties using varied sensors. However, these studies have primarily used satellite-based products that provide coarse spatial and temporal resolution, which is unsuitable for autonomous mobility. Our work employs the use of an Unmanned Aeriel Vehicle (UAV) mounted hyperspectral camera in tandem with machine learning frameworks to predict snow surface properties at finer scales. Several machine learning models were trained using hyperspectral imagery in tandem with in-situ snow measurements. The results indicate that random forest and k-nearest neighbors models had the lowest Mean Absolute Error for all surface snow properties. A pearson correlation matrix showed that density, grain size, and moisture content all had a significant positive correlation to one another. Mechanically, density and grain size had a slightly positive correlation to compressive strength, while moisture had a much weaker negative correlation. This work provides preliminary insight into the efficacy of using hyperspectral imagery for characterizing snow properties for autonomous vehicle mobility.

Experience with UASB reactor start-up under different operating conditions

1996 ◽  
Vol 34 (5-6) ◽  
pp. 421-428 ◽  
Author(s):  
M. M. Ghangrekar ◽  
S. R. Asolekar ◽  
K. R. Ranganathan ◽  
S. G. Joshi
Keyword(s):  
Steady State ◽  
Operating Conditions ◽  
Cod Removal ◽  
Upflow Anaerobic Sludge Blanket ◽  
Anaerobic Sludge ◽  
Operating Parameters ◽  
Reactor Performance ◽  
Loading Rates ◽  
Start Up ◽  
Sludge Production

Four laboratory upflow anaerobic sludge blanket (UASB) reactors were operated at different operating parameters viz., hydraulic retention time (HRT), upflow velocity, organic concentration, and Ca2+ concentration in the wastewater. These operating parameters gave different values of organic loading rates (OLRs) and sludge loading rates (SLRs). The reactor performance during start-up was evaluated at different values of the above listed parameters. Also, the effects of these parameters on the granule characteristics were investigated. It was observed that COD removal efficiency at steady state was profoundly influenced by SLR. The reactor started with SLR of 0.6 kgCOD/ kg VSS.d could result in about 50% COD removal at steady state. The reactor performance could not improve even after three months of operation. Up to 0.3 kgCOD/ kgVSS.d the reactor performance was good with more than 90% COD removal at steady state. The OLD and SLR also determine time required for the reactor to achieve steady state. Different operating conditions also have the bearing on the strength of the granules cultivated. The methanogenic activity measured on acetate for each reactor was observed between 0.259 and 0.909 kg CH4 COD/ kgVSS.d. The sludge production in all the reactors was between 0.087 and 0.13 kgVSS/ kgCODin. The mathematical model was developed in order to predict sludge production.

Sign in / Sign up

Export Citation Format

Share Document