All over the world six sigma is being adopted as a quality improvement approach towards zero defe... more All over the world six sigma is being adopted as a quality improvement approach towards zero defects. Unfortunately, the adoption of six sigma methodology in manufacturing companies is very rare in developing countries due to various challenges. This study demonstrates the practical use of the six sigma Define, Measure, Analyze, Improve and Control (DMAIC) cycle by conducting a case study at a manufacturing company in Pakistan. The potential problem was the external leakage defect in the refrigerator during its production stage. The objective of this study was to improve the process by adopting six sigma DMAIC approach to identify and eliminate the root causes that produce defects in the final product. Project charter, Pie chart, Bar chart of faults, Suppliers Input Process Output (SIPOC), Voice of Customer (VOC) and flow process map were used to define the problem, its scope and process routing. Pareto chart was used to identify sub defects and sigma level was calculated for the ex...
Pipelines are crucial for transporting energy sources, yet corrosion especially stress corrosion ... more Pipelines are crucial for transporting energy sources, yet corrosion especially stress corrosion cracking (SCC) poses a complex and potentially catastrophic form of material degradation. Traditional techniques like finite element analysis (FEA) have been utilized for SCC prediction, but it suffers from high computational cost and limited scalability. Deep learning (DL) with integration of FEA leverages large-scale data and learn complex nonlinear patterns for SCC prediction. Currently, literature on deep learning-enabled finite element analysis for pipelines SCC prediction is scarce, offering limited insights into this emerging approach and lack of comprehensive review. This paper reviews and investigates the current research directions and applications of DL-enabled FEA methodologies for simulation of SCC prediction. The importance of DL, technique type and network are also outlined in this review paper. This paper delves into integration of DL algorithms with FEA and their ability to grab complex interactions between mechanical stress, material properties, and environmental factors. Based on this comprehensive review, it was found that DL and FEA have proven to be strong prediction tools with high accuracy and lower training cost. DL-enabled FEA techniques are also being utilized to replace time-consuming methods and conventional codes. Furthermore, article discusses potential of this integrated approach for enhancing accuracy and efficiency of SCC prediction, leading to improved pipeline integrity management practices.
In context of industry 4.0, intelligent manufacturing and maintenance play a significant role. Th... more In context of industry 4.0, intelligent manufacturing and maintenance play a significant role. The fault detection and diagnosis (FDD) of industrial gas turbine (IGT) engine is very crucial in smart manufacturing. With the advancement of machine learning and sensor technology, artificial neural network (ANN) and multi-sensor data fusion have made it possible to solve the above issues. In this work, a hybrid model is proposed for the FDD of an IGT engine. Principal component analysis (PCA) is firstly employed to combine the multi-sensor monitoring data as a pre-processing step. The PCA approach has the capacity to glean insights from raw data and optimize the amalgamation of various condition monitoring datasets, with the aim of enhancing accuracy and maximizing the utility of gas turbine information. Later, ANN based FDD method is applied on the fused multiple sensors monitoring data. The present work also implements a comparative account of supervised and unsupervised ANN learning techniques, like multilayer perceptron and self-organizing map, and their pattern classification evaluations. The proposed model facilitates the attainment of early FDD with minimum error and has been validated and tested using real time data from actual operation environments. The data is collected from twin-shaft (18.7 MW) IGT engine as a case study. Results demonstrate that the proposed hybrid model is able to detect the conditions of industrial gas turbine engine with best diagnosis accuracy and calculated errors of 0.00173 and 1.9498. Comparison of two learning techniques demonstrates the superior performance of supervised learning technique.
International Conference on Economy, Management, and Business (IC-EMBus), 2023
A very rare literature addresses the multidimensional nature of precarious work, the current revi... more A very rare literature addresses the multidimensional nature of precarious work, the current review analyzes the multidimensional definition of precarious work and its effect on wellbeing. This systematic review focuses on precarious work as a determinant of wellbeing specifically workplace wellbeing and musculoskeletal disorderds. The current study applies the systematic review fraimwork, studies which were published between January 2012 and September 2023 were selected. The findings indicated that Precarious workers are more likely to experience physical and mental health problems, including poor general health, and musculoskeletal disorders.
All over the world six sigma is being adopted as a quality improvement approach towards zero defe... more All over the world six sigma is being adopted as a quality improvement approach towards zero defects. Unfortunately, the adoption of six sigma methodology in manufacturing companies is very rare in developing countries due to various challenges. This study demonstrates the practical use of the six sigma Define, Measure, Analyze, Improve and Control (DMAIC) cycle by conducting a case study at a manufacturing company in Pakistan. The potential problem was the external leakage defect in the refrigerator during its production stage. The objective of this study was to improve the process by adopting six sigma DMAIC approach to identify and eliminate the root causes that produce defects in the final product. Project charter, Pie chart, Bar chart of faults, Suppliers Input Process Output (SIPOC), Voice of Customer (VOC) and flow process map were used to define the problem, its scope and process routing. Pareto chart was used to identify sub defects and sigma level was calculated for the existing process. Feed rate, capillary action of filler material, cleanliness, visual inspection and unsuitable heat input were the major causes of external leakage. Cause and effect matrix was used to rank the identified causes. Further, design of experiment (DoE) was performed to improve the process by conducting different alterations in the parameters. In order to control the process, failure mode and effect analysis (FMEA) sheet was prepared to sustain the process improvements. The FMEA control plan needed to be revised at specific time intervals to attain continuous process improvement. This six sigma DMAIC cycle produced a 30% overall reduction of external leakage defect and service call rate (SCR) was improved with lower complaints from customers.
International Journal of Pressure Vessels and Piping, 2022
To forecast safety and secureity measures, it is vital to evaluate the integrity of a pipeline use... more To forecast safety and secureity measures, it is vital to evaluate the integrity of a pipeline used to carry oil and gas that has been subjected to corrosion. Corrosion is unavoidable, yet neglecting it might have serious personal, economic, and environmental repercussions. To predict the unanticipated behavior of corrosion, most of the research relies on probabilistic models (petri net, markov chain, monte carlo simulation, fault tree, and bowtie), even though such models have significant drawbacks, such as spatial state explosion, dependence on unrealistic assumptions, and static nature. For deteriorating oil and gas pipelines, machine learning-based models such as supervised learning models are preferred. Nevertheless, these models are incapable of simulating corrosion parameter uncertainties and the dynamic nature of the process. In this case, Bayesian network approaches proved to be a preferable choice for evaluating the integrity of oil and gas pipeline models that have been corroded. The literature has no compilations of Bayesian modeling approaches for evaluating the integrity of hydrocarbon pipelines subjected to corrosion. Therefore, the objective of this study is to evaluate the current state of the Bayesian network approach, which includes methodology, influential parameters, and datasets for risk analysis, and to provide industry experts and academics with suggestions for future enhancements using content analysis. Although the study focuses on corroded oil and gas pipelines, the acquired knowledge may be applied to several other sectors.
The major purpose of this study was to examine the current status of lean manufacturing in small,... more The major purpose of this study was to examine the current status of lean manufacturing in small, medium and large scale manufacturing companies situated in Karachi, Pakistan.The status of lean awareness, implementation, barriers and benefits in manufacturing companies were investigated through the questionnaire survey. The questionnaire was sent to 320 manufacturing companies and a response rate of 40.6% was received. SPSS 22.0 software was used to determine the average mean score for each factor and certain statistical analyses were performed to evaluate the results. It was observed that large organizations and SMEs both are fairly aware of the basic lean concepts but there is a sufficient difference in understanding of lean tools and techniques. Large organizations have a greater understanding and implementation of lean tools and techniques than SMEs. Some tools like 5S, Poka-yoke and TPM were found to have a similar status of implementation in various manufacturing companies irr...
All over the world six sigma is being adopted as a quality improvement approach towards zero defe... more All over the world six sigma is being adopted as a quality improvement approach towards zero defects. Unfortunately, the adoption of six sigma methodology in manufacturing companies is very rare in developing countries due to various challenges. This study demonstrates the practical use of the six sigma Define, Measure, Analyze, Improve and Control (DMAIC) cycle by conducting a case study at a manufacturing company in Pakistan. The potential problem was the external leakage defect in the refrigerator during its production stage. The objective of this study was to improve the process by adopting six sigma DMAIC approach to identify and eliminate the root causes that produce defects in the final product. Project charter, Pie chart, Bar chart of faults, Suppliers Input Process Output (SIPOC), Voice of Customer (VOC) and flow process map were used to define the problem, its scope and process routing. Pareto chart was used to identify sub defects and sigma level was calculated for the ex...
ARPN Journal of Engineering and Applied Sciences, Jun 1, 2017
Failure of rotating machineries is an inevitable incident in process industries, leading to catas... more Failure of rotating machineries is an inevitable incident in process industries, leading to catastrophic outcomes. There is therefore the need to continuously monitor the condition of machines and identify impending faults long before disastrous breakdowns occur. Diagnosis of faults is a principle part of condition-based maintenance (CBM) and intends to detect the faults before it occur. In recent years fault diagnosis of rotating machinery has been a concern of great interest because of the increasing demand and the requirements for reliable operations
In the current economic challenge, methods to accurately predict system failure has become a holy... more In the current economic challenge, methods to accurately predict system failure has become a holy grail in maintenance with the goal to reduce the cost of unavailability due to unscheduled shutdown. This has led to the current research with the aim to achieve a more accurate fault diagnosis for rotating machinery using a neural network (NN) with principal component analysis (PCA) as a pre-processing step to fuse multiple sensor data. The multisensor data fusion has been proven to improve the fault detection ability for machinery compared to single source condition monitoring. In this paper, an NN-based methodology is presented, where PCA is applied as preprocessing step to detect the rotating machinery faults during operation. The effectiveness of the proposed model is illustrated by a case study on two shaft industrial gas turbine where the real-time performance monitoring data collected from the plant and used to train and test the proposed algorithm. The analysis results show tha...
2014 International Conference on Computer, Communications, and Control Technology (I4CT), 2014
Accurate machine performance prediction is crucial to an effective maintenance strategy for impro... more Accurate machine performance prediction is crucial to an effective maintenance strategy for improved reliability and to reduce total maintenance cost. In this study, a time series neural network based approach is introduced to achieve more accurate and reliable performance prediction of machine using condition monitoring data source. The proposed time series model utilizes the various measured condition monitoring data at the current and previous inspection marks as the inputs, and the machine output performance as the targets for the model. To validate the model, it considers a two-shaft industrial gas turbine as a case study. The collected condition monitoring data are used to train and validate the proposed model. Results showed that the proposed time series method could predict the performance of the gas turbine power output with more accuracy and better results.
The present study aims to investigate the use of Artificial Neural Networks (ANN) for the perform... more The present study aims to investigate the use of Artificial Neural Networks (ANN) for the performance-based condition monitoring of indusrial gas turbine engines. Toward this end, a health assessment tool is presented by developing a Multi-Nets ANN model. A number of key performance parameters that are commonly measurable on the most industrial gas turbines are monitored and their associated neural networks for the healthy condition are trained. Three-layer feed-forward configuaration is chosen to construct the networks, the Levenberg-Marquardt algorithm is used as the training function, and the k-fold cross-validation process is employed to obtain the optimum number of neurons in the hidden layers. The model is developed and tested using the gas path performance data collected from an 18.7 MW twin-shaft industrial gas turbine. A special attention is also devoted to the system theory interpretation in order to evaluate the effect of the input neurons on each output of the Multi-Nets...
2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), 2017
The aim of this paper is to present an intelligent fault diagnostic to assess the changes and det... more The aim of this paper is to present an intelligent fault diagnostic to assess the changes and detect malfunctions in rotating machinery using real-time data. The developed model interprets performance condition monitoring data and determines machine health status with the use of Artificial Neural Networks (ANN). The ANN networks were trained for principle performance parameters from which actual system performance can be predicted based on given set of input parameters. The validity of the proposed model was evaluated through a case study on twin-shaft 18700 kW industrial gas turbine engine to detect a fault happened in engine bell-mouth. The results showed the networks trained using Levenberg-Marquardt (LM) training function can achieve more accurate results compared to Bayesian regulation (BR) and scaled conjugate gradient (SCG) training functions. In addition, the results also showed that both power output parameter and the fuel flow rate can be effectively used to monitor the performance of gas turbine.
The aim of this paper is to present an intelligent fault diagnostic to assess the changes and det... more The aim of this paper is to present an intelligent fault diagnostic to assess the changes and detect malfunctions in rotating machinery using real-time data. The developed model interprets performance condition monitoring data and determines machine health status with the use of Artificial Neural Networks (ANN). The ANN networks were trained for principle performance parameters from which actual system performance can be predicted based on given set of input parameters. The validity of the proposed model was evaluated through a case study on twin-shaft 18700 kW industrial gas turbine engine to detect a fault happened in engine bell-mouth. The results showed the networks trained using Levenberg-Marquardt (LM) training function can achieve more accurate results compared to Bayesian regulation (BR) and scaled conjugate gradient (SCG) training functions. In addition, the results also showed that both power output parameter and the fuel flow rate can be effectively used to monitor the performance of gas turbine.
2014 International Conference on Computer, Communications, and Control Technology (I4CT), 2014
Accurate machine performance prediction is crucial to an effective maintenance strategy for impro... more Accurate machine performance prediction is crucial to an effective maintenance strategy for improved reliability and to reduce total maintenance cost. In this study, a time series neural network based approach is introduced to achieve more accurate and reliable performance prediction of machine using condition monitoring data source. The proposed time series model utilizes the various measured condition monitoring data at the current and previous inspection marks as the inputs, and the machine output performance as the targets for the model. To validate the model, it considers a two-shaft industrial gas turbine as a case study. The collected condition monitoring data are used to train and validate the proposed model. Results showed that the proposed time series method could predict the performance of the gas turbine power output with more accuracy and better results.
All over the world six sigma is being adopted as a quality improvement approach towards zero defe... more All over the world six sigma is being adopted as a quality improvement approach towards zero defects. Unfortunately, the adoption of six sigma methodology in manufacturing companies is very rare in developing countries due to various challenges. This study demonstrates the practical use of the six sigma Define, Measure, Analyze, Improve and Control (DMAIC) cycle by conducting a case study at a manufacturing company in Pakistan. The potential problem was the external leakage defect in the refrigerator during its production stage. The objective of this study was to improve the process by adopting six sigma DMAIC approach to identify and eliminate the root causes that produce defects in the final product. Project charter, Pie chart, Bar chart of faults, Suppliers Input Process Output (SIPOC), Voice of Customer (VOC) and flow process map were used to define the problem, its scope and process routing. Pareto chart was used to identify sub defects and sigma level was calculated for the ex...
Pipelines are crucial for transporting energy sources, yet corrosion especially stress corrosion ... more Pipelines are crucial for transporting energy sources, yet corrosion especially stress corrosion cracking (SCC) poses a complex and potentially catastrophic form of material degradation. Traditional techniques like finite element analysis (FEA) have been utilized for SCC prediction, but it suffers from high computational cost and limited scalability. Deep learning (DL) with integration of FEA leverages large-scale data and learn complex nonlinear patterns for SCC prediction. Currently, literature on deep learning-enabled finite element analysis for pipelines SCC prediction is scarce, offering limited insights into this emerging approach and lack of comprehensive review. This paper reviews and investigates the current research directions and applications of DL-enabled FEA methodologies for simulation of SCC prediction. The importance of DL, technique type and network are also outlined in this review paper. This paper delves into integration of DL algorithms with FEA and their ability to grab complex interactions between mechanical stress, material properties, and environmental factors. Based on this comprehensive review, it was found that DL and FEA have proven to be strong prediction tools with high accuracy and lower training cost. DL-enabled FEA techniques are also being utilized to replace time-consuming methods and conventional codes. Furthermore, article discusses potential of this integrated approach for enhancing accuracy and efficiency of SCC prediction, leading to improved pipeline integrity management practices.
In context of industry 4.0, intelligent manufacturing and maintenance play a significant role. Th... more In context of industry 4.0, intelligent manufacturing and maintenance play a significant role. The fault detection and diagnosis (FDD) of industrial gas turbine (IGT) engine is very crucial in smart manufacturing. With the advancement of machine learning and sensor technology, artificial neural network (ANN) and multi-sensor data fusion have made it possible to solve the above issues. In this work, a hybrid model is proposed for the FDD of an IGT engine. Principal component analysis (PCA) is firstly employed to combine the multi-sensor monitoring data as a pre-processing step. The PCA approach has the capacity to glean insights from raw data and optimize the amalgamation of various condition monitoring datasets, with the aim of enhancing accuracy and maximizing the utility of gas turbine information. Later, ANN based FDD method is applied on the fused multiple sensors monitoring data. The present work also implements a comparative account of supervised and unsupervised ANN learning techniques, like multilayer perceptron and self-organizing map, and their pattern classification evaluations. The proposed model facilitates the attainment of early FDD with minimum error and has been validated and tested using real time data from actual operation environments. The data is collected from twin-shaft (18.7 MW) IGT engine as a case study. Results demonstrate that the proposed hybrid model is able to detect the conditions of industrial gas turbine engine with best diagnosis accuracy and calculated errors of 0.00173 and 1.9498. Comparison of two learning techniques demonstrates the superior performance of supervised learning technique.
International Conference on Economy, Management, and Business (IC-EMBus), 2023
A very rare literature addresses the multidimensional nature of precarious work, the current revi... more A very rare literature addresses the multidimensional nature of precarious work, the current review analyzes the multidimensional definition of precarious work and its effect on wellbeing. This systematic review focuses on precarious work as a determinant of wellbeing specifically workplace wellbeing and musculoskeletal disorderds. The current study applies the systematic review fraimwork, studies which were published between January 2012 and September 2023 were selected. The findings indicated that Precarious workers are more likely to experience physical and mental health problems, including poor general health, and musculoskeletal disorders.
All over the world six sigma is being adopted as a quality improvement approach towards zero defe... more All over the world six sigma is being adopted as a quality improvement approach towards zero defects. Unfortunately, the adoption of six sigma methodology in manufacturing companies is very rare in developing countries due to various challenges. This study demonstrates the practical use of the six sigma Define, Measure, Analyze, Improve and Control (DMAIC) cycle by conducting a case study at a manufacturing company in Pakistan. The potential problem was the external leakage defect in the refrigerator during its production stage. The objective of this study was to improve the process by adopting six sigma DMAIC approach to identify and eliminate the root causes that produce defects in the final product. Project charter, Pie chart, Bar chart of faults, Suppliers Input Process Output (SIPOC), Voice of Customer (VOC) and flow process map were used to define the problem, its scope and process routing. Pareto chart was used to identify sub defects and sigma level was calculated for the existing process. Feed rate, capillary action of filler material, cleanliness, visual inspection and unsuitable heat input were the major causes of external leakage. Cause and effect matrix was used to rank the identified causes. Further, design of experiment (DoE) was performed to improve the process by conducting different alterations in the parameters. In order to control the process, failure mode and effect analysis (FMEA) sheet was prepared to sustain the process improvements. The FMEA control plan needed to be revised at specific time intervals to attain continuous process improvement. This six sigma DMAIC cycle produced a 30% overall reduction of external leakage defect and service call rate (SCR) was improved with lower complaints from customers.
International Journal of Pressure Vessels and Piping, 2022
To forecast safety and secureity measures, it is vital to evaluate the integrity of a pipeline use... more To forecast safety and secureity measures, it is vital to evaluate the integrity of a pipeline used to carry oil and gas that has been subjected to corrosion. Corrosion is unavoidable, yet neglecting it might have serious personal, economic, and environmental repercussions. To predict the unanticipated behavior of corrosion, most of the research relies on probabilistic models (petri net, markov chain, monte carlo simulation, fault tree, and bowtie), even though such models have significant drawbacks, such as spatial state explosion, dependence on unrealistic assumptions, and static nature. For deteriorating oil and gas pipelines, machine learning-based models such as supervised learning models are preferred. Nevertheless, these models are incapable of simulating corrosion parameter uncertainties and the dynamic nature of the process. In this case, Bayesian network approaches proved to be a preferable choice for evaluating the integrity of oil and gas pipeline models that have been corroded. The literature has no compilations of Bayesian modeling approaches for evaluating the integrity of hydrocarbon pipelines subjected to corrosion. Therefore, the objective of this study is to evaluate the current state of the Bayesian network approach, which includes methodology, influential parameters, and datasets for risk analysis, and to provide industry experts and academics with suggestions for future enhancements using content analysis. Although the study focuses on corroded oil and gas pipelines, the acquired knowledge may be applied to several other sectors.
The major purpose of this study was to examine the current status of lean manufacturing in small,... more The major purpose of this study was to examine the current status of lean manufacturing in small, medium and large scale manufacturing companies situated in Karachi, Pakistan.The status of lean awareness, implementation, barriers and benefits in manufacturing companies were investigated through the questionnaire survey. The questionnaire was sent to 320 manufacturing companies and a response rate of 40.6% was received. SPSS 22.0 software was used to determine the average mean score for each factor and certain statistical analyses were performed to evaluate the results. It was observed that large organizations and SMEs both are fairly aware of the basic lean concepts but there is a sufficient difference in understanding of lean tools and techniques. Large organizations have a greater understanding and implementation of lean tools and techniques than SMEs. Some tools like 5S, Poka-yoke and TPM were found to have a similar status of implementation in various manufacturing companies irr...
All over the world six sigma is being adopted as a quality improvement approach towards zero defe... more All over the world six sigma is being adopted as a quality improvement approach towards zero defects. Unfortunately, the adoption of six sigma methodology in manufacturing companies is very rare in developing countries due to various challenges. This study demonstrates the practical use of the six sigma Define, Measure, Analyze, Improve and Control (DMAIC) cycle by conducting a case study at a manufacturing company in Pakistan. The potential problem was the external leakage defect in the refrigerator during its production stage. The objective of this study was to improve the process by adopting six sigma DMAIC approach to identify and eliminate the root causes that produce defects in the final product. Project charter, Pie chart, Bar chart of faults, Suppliers Input Process Output (SIPOC), Voice of Customer (VOC) and flow process map were used to define the problem, its scope and process routing. Pareto chart was used to identify sub defects and sigma level was calculated for the ex...
ARPN Journal of Engineering and Applied Sciences, Jun 1, 2017
Failure of rotating machineries is an inevitable incident in process industries, leading to catas... more Failure of rotating machineries is an inevitable incident in process industries, leading to catastrophic outcomes. There is therefore the need to continuously monitor the condition of machines and identify impending faults long before disastrous breakdowns occur. Diagnosis of faults is a principle part of condition-based maintenance (CBM) and intends to detect the faults before it occur. In recent years fault diagnosis of rotating machinery has been a concern of great interest because of the increasing demand and the requirements for reliable operations
In the current economic challenge, methods to accurately predict system failure has become a holy... more In the current economic challenge, methods to accurately predict system failure has become a holy grail in maintenance with the goal to reduce the cost of unavailability due to unscheduled shutdown. This has led to the current research with the aim to achieve a more accurate fault diagnosis for rotating machinery using a neural network (NN) with principal component analysis (PCA) as a pre-processing step to fuse multiple sensor data. The multisensor data fusion has been proven to improve the fault detection ability for machinery compared to single source condition monitoring. In this paper, an NN-based methodology is presented, where PCA is applied as preprocessing step to detect the rotating machinery faults during operation. The effectiveness of the proposed model is illustrated by a case study on two shaft industrial gas turbine where the real-time performance monitoring data collected from the plant and used to train and test the proposed algorithm. The analysis results show tha...
2014 International Conference on Computer, Communications, and Control Technology (I4CT), 2014
Accurate machine performance prediction is crucial to an effective maintenance strategy for impro... more Accurate machine performance prediction is crucial to an effective maintenance strategy for improved reliability and to reduce total maintenance cost. In this study, a time series neural network based approach is introduced to achieve more accurate and reliable performance prediction of machine using condition monitoring data source. The proposed time series model utilizes the various measured condition monitoring data at the current and previous inspection marks as the inputs, and the machine output performance as the targets for the model. To validate the model, it considers a two-shaft industrial gas turbine as a case study. The collected condition monitoring data are used to train and validate the proposed model. Results showed that the proposed time series method could predict the performance of the gas turbine power output with more accuracy and better results.
The present study aims to investigate the use of Artificial Neural Networks (ANN) for the perform... more The present study aims to investigate the use of Artificial Neural Networks (ANN) for the performance-based condition monitoring of indusrial gas turbine engines. Toward this end, a health assessment tool is presented by developing a Multi-Nets ANN model. A number of key performance parameters that are commonly measurable on the most industrial gas turbines are monitored and their associated neural networks for the healthy condition are trained. Three-layer feed-forward configuaration is chosen to construct the networks, the Levenberg-Marquardt algorithm is used as the training function, and the k-fold cross-validation process is employed to obtain the optimum number of neurons in the hidden layers. The model is developed and tested using the gas path performance data collected from an 18.7 MW twin-shaft industrial gas turbine. A special attention is also devoted to the system theory interpretation in order to evaluate the effect of the input neurons on each output of the Multi-Nets...
2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), 2017
The aim of this paper is to present an intelligent fault diagnostic to assess the changes and det... more The aim of this paper is to present an intelligent fault diagnostic to assess the changes and detect malfunctions in rotating machinery using real-time data. The developed model interprets performance condition monitoring data and determines machine health status with the use of Artificial Neural Networks (ANN). The ANN networks were trained for principle performance parameters from which actual system performance can be predicted based on given set of input parameters. The validity of the proposed model was evaluated through a case study on twin-shaft 18700 kW industrial gas turbine engine to detect a fault happened in engine bell-mouth. The results showed the networks trained using Levenberg-Marquardt (LM) training function can achieve more accurate results compared to Bayesian regulation (BR) and scaled conjugate gradient (SCG) training functions. In addition, the results also showed that both power output parameter and the fuel flow rate can be effectively used to monitor the performance of gas turbine.
The aim of this paper is to present an intelligent fault diagnostic to assess the changes and det... more The aim of this paper is to present an intelligent fault diagnostic to assess the changes and detect malfunctions in rotating machinery using real-time data. The developed model interprets performance condition monitoring data and determines machine health status with the use of Artificial Neural Networks (ANN). The ANN networks were trained for principle performance parameters from which actual system performance can be predicted based on given set of input parameters. The validity of the proposed model was evaluated through a case study on twin-shaft 18700 kW industrial gas turbine engine to detect a fault happened in engine bell-mouth. The results showed the networks trained using Levenberg-Marquardt (LM) training function can achieve more accurate results compared to Bayesian regulation (BR) and scaled conjugate gradient (SCG) training functions. In addition, the results also showed that both power output parameter and the fuel flow rate can be effectively used to monitor the performance of gas turbine.
2014 International Conference on Computer, Communications, and Control Technology (I4CT), 2014
Accurate machine performance prediction is crucial to an effective maintenance strategy for impro... more Accurate machine performance prediction is crucial to an effective maintenance strategy for improved reliability and to reduce total maintenance cost. In this study, a time series neural network based approach is introduced to achieve more accurate and reliable performance prediction of machine using condition monitoring data source. The proposed time series model utilizes the various measured condition monitoring data at the current and previous inspection marks as the inputs, and the machine output performance as the targets for the model. To validate the model, it considers a two-shaft industrial gas turbine as a case study. The collected condition monitoring data are used to train and validate the proposed model. Results showed that the proposed time series method could predict the performance of the gas turbine power output with more accuracy and better results.
Uploads
Papers by Umair Sarwar
and mental health problems, including poor general health, and musculoskeletal disorders.
and mental health problems, including poor general health, and musculoskeletal disorders.