Multivariate statistical process monitoring and control (MSPM&C) methods for chemical process monitoring with statistical projection techniques such as principal component analysis (PCA) and partial least squares ...Multivariate statistical process monitoring and control (MSPM&C) methods for chemical process monitoring with statistical projection techniques such as principal component analysis (PCA) and partial least squares (PLS) are surveyed in this paper. The four-step procedure of performing MSPM&C for chemical process, modeling of processes, detecting abnormal events or faults, identifying the variable(s) responsible for the faults and diagnosing the source cause for the abnormal behavior, is analyzed. Several main research directions of MSPM&C reported in the literature are discussed, such as multi-way principal component analysis (MPCA) for batch process, statistical monitoring and control for nonlinear process, dynamic PCA and dynamic PLS, and on-line quality control by inferential models. Industrial applications of MSPM&C to several typical chemical processes, such as chemical reactor, distillation column, polymerization process, petroleum refinery units, are summarized. Finally, some concluding remarks and future considerations are made.展开更多
In recent years there have been considerable new legislation and efforts by vehicle manufactures aimed at reducing pollutant emission to improve air quality in urban areas. Carbon monoxide is a major pollutant in urba...In recent years there have been considerable new legislation and efforts by vehicle manufactures aimed at reducing pollutant emission to improve air quality in urban areas. Carbon monoxide is a major pollutant in urban areas, and in this study we analyze monthly carbon monoxide (CO) data from Valencia City, a representative Mediterranean city in terms of its structure and climatology. Temporal and spatial trends in pollution were recorded from a monitoring net- work that consisted of five monitoring sites. A multiple linear model, incorporating meteorological parameters, annual cycles, and random error due to serial correlation, was used to estimate the temporal changes in pollution. An analysis performed on the meteorologically adjusted data reveals a significant decreasing trend in CO concentrations and an annual seasonal cycle. The model parameters are estimated by applying the least-squares method. The standard error of the parameters is determined while taking into account the serial correlation in the residuals. The decreasing trend im- plies to a certain extent an improvement in the air quality of the study area. The seasonal cycle shows variations that are mainly associated with traffic and meteorological patterns. Analysis of the stochastic spatial component shows that most of the intersite covariances can be analyzed using an exponential variogram model.展开更多
Clutch is one of the most significant components in automobiles.To improve passenger safety,reliability and economy of automobiles,advanced supervision and fault diagnostics are required.Condition Monitoring is one of...Clutch is one of the most significant components in automobiles.To improve passenger safety,reliability and economy of automobiles,advanced supervision and fault diagnostics are required.Condition Monitoring is one of the key divisions that can be used to track the reliability of clutch and allied components.The state of the clutch elements can be monitored with the help of vibration signals which contain valuable information required for classification.Specific drawbacks of traditional fault diagnosis techniques like high reliability on human intelligence and the requirement of profes-sional expertise,have made researchers look for intelligent fault diagnosis techniques.In this article,the classification performance of the deep learning technique(employing images plotted from vibration signals)is compared with the machine learning technique(using features extracted from vibration signals)to identify the most viable solution for condition monitoring of the clutch system.The overall experimentation is carried out in two phases,namely the deep learning phase and the machine learning phase.Overall,the effectiveness of the pre-trained networks was assessed and compared with machine learning algorithms.Based on the comparative study,the best-performing technique is recommended for real-time application.展开更多
Environmental sustainability is the rate of renewable resourceharvesting, pollution control, and non-renewable resource exhaustion. Airpollution is a significant issue confronted by the environment particularlyby high...Environmental sustainability is the rate of renewable resourceharvesting, pollution control, and non-renewable resource exhaustion. Airpollution is a significant issue confronted by the environment particularlyby highly populated countries like India. Due to increased population, thenumber of vehicles also continues to increase. Each vehicle has its individualemission rate;however, the issue arises when the emission rate crosses thestandard value and the quality of the air gets degraded. Owing to the technological advances in machine learning (ML), it is possible to develop predictionapproaches to monitor and control pollution using real time data. With thedevelopment of the Internet of Things (IoT) and Big Data Analytics (BDA),there is a huge paradigm shift in how environmental data are employed forsustainable cities and societies, especially by applying intelligent algorithms.In this view, this study develops an optimal AI based air quality prediction andclassification (OAI-AQPC) model in big data environment. For handling bigdata from environmental monitoring, Hadoop MapReduce tool is employed.In addition, a predictive model is built using the hybridization of ARIMAand neural network (NN) called ARIMA-NN to predict the pollution level.For improving the performance of the ARIMA-NN algorithm, the parametertuning process takes place using oppositional swallow swarm optimization(OSSO) algorithm. Finally, Adaptive neuro-fuzzy inference system (ANFIS)classifier is used to classify the air quality into pollutant and non-pollutant.A detailed experimental analysis is performed for highlighting the betterprediction performance of the proposed ARIMA-NN method. The obtainedoutcomes pointed out the enhanced outcomes of the proposed OAI-AQPCtechnique over the recent state of art techniques.展开更多
基金Supported by the National High-Tech Development Program of China(No.863-511-920-011,2001AA411230).
文摘Multivariate statistical process monitoring and control (MSPM&C) methods for chemical process monitoring with statistical projection techniques such as principal component analysis (PCA) and partial least squares (PLS) are surveyed in this paper. The four-step procedure of performing MSPM&C for chemical process, modeling of processes, detecting abnormal events or faults, identifying the variable(s) responsible for the faults and diagnosing the source cause for the abnormal behavior, is analyzed. Several main research directions of MSPM&C reported in the literature are discussed, such as multi-way principal component analysis (MPCA) for batch process, statistical monitoring and control for nonlinear process, dynamic PCA and dynamic PLS, and on-line quality control by inferential models. Industrial applications of MSPM&C to several typical chemical processes, such as chemical reactor, distillation column, polymerization process, petroleum refinery units, are summarized. Finally, some concluding remarks and future considerations are made.
文摘In recent years there have been considerable new legislation and efforts by vehicle manufactures aimed at reducing pollutant emission to improve air quality in urban areas. Carbon monoxide is a major pollutant in urban areas, and in this study we analyze monthly carbon monoxide (CO) data from Valencia City, a representative Mediterranean city in terms of its structure and climatology. Temporal and spatial trends in pollution were recorded from a monitoring net- work that consisted of five monitoring sites. A multiple linear model, incorporating meteorological parameters, annual cycles, and random error due to serial correlation, was used to estimate the temporal changes in pollution. An analysis performed on the meteorologically adjusted data reveals a significant decreasing trend in CO concentrations and an annual seasonal cycle. The model parameters are estimated by applying the least-squares method. The standard error of the parameters is determined while taking into account the serial correlation in the residuals. The decreasing trend im- plies to a certain extent an improvement in the air quality of the study area. The seasonal cycle shows variations that are mainly associated with traffic and meteorological patterns. Analysis of the stochastic spatial component shows that most of the intersite covariances can be analyzed using an exponential variogram model.
文摘Clutch is one of the most significant components in automobiles.To improve passenger safety,reliability and economy of automobiles,advanced supervision and fault diagnostics are required.Condition Monitoring is one of the key divisions that can be used to track the reliability of clutch and allied components.The state of the clutch elements can be monitored with the help of vibration signals which contain valuable information required for classification.Specific drawbacks of traditional fault diagnosis techniques like high reliability on human intelligence and the requirement of profes-sional expertise,have made researchers look for intelligent fault diagnosis techniques.In this article,the classification performance of the deep learning technique(employing images plotted from vibration signals)is compared with the machine learning technique(using features extracted from vibration signals)to identify the most viable solution for condition monitoring of the clutch system.The overall experimentation is carried out in two phases,namely the deep learning phase and the machine learning phase.Overall,the effectiveness of the pre-trained networks was assessed and compared with machine learning algorithms.Based on the comparative study,the best-performing technique is recommended for real-time application.
基金The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work under grant number(RGP2/45/43)Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R135)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.The authors would like to thank the Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:(22UQU4270206DSR02).
文摘Environmental sustainability is the rate of renewable resourceharvesting, pollution control, and non-renewable resource exhaustion. Airpollution is a significant issue confronted by the environment particularlyby highly populated countries like India. Due to increased population, thenumber of vehicles also continues to increase. Each vehicle has its individualemission rate;however, the issue arises when the emission rate crosses thestandard value and the quality of the air gets degraded. Owing to the technological advances in machine learning (ML), it is possible to develop predictionapproaches to monitor and control pollution using real time data. With thedevelopment of the Internet of Things (IoT) and Big Data Analytics (BDA),there is a huge paradigm shift in how environmental data are employed forsustainable cities and societies, especially by applying intelligent algorithms.In this view, this study develops an optimal AI based air quality prediction andclassification (OAI-AQPC) model in big data environment. For handling bigdata from environmental monitoring, Hadoop MapReduce tool is employed.In addition, a predictive model is built using the hybridization of ARIMAand neural network (NN) called ARIMA-NN to predict the pollution level.For improving the performance of the ARIMA-NN algorithm, the parametertuning process takes place using oppositional swallow swarm optimization(OSSO) algorithm. Finally, Adaptive neuro-fuzzy inference system (ANFIS)classifier is used to classify the air quality into pollutant and non-pollutant.A detailed experimental analysis is performed for highlighting the betterprediction performance of the proposed ARIMA-NN method. The obtainedoutcomes pointed out the enhanced outcomes of the proposed OAI-AQPCtechnique over the recent state of art techniques.
