Statistical Process Control based Energy Monitoring of Chemical Processes

Kulcsár, Tibor; Koncz, P.; Balaton, Miklós; Nagy, László; Abonyi, János

doi:10.1016/b978-0-444-63456-6.50067-3

Cited by 5 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The PMML represents not only a wide range of statistical techniques, but also the data transformations needed to turn input data and raw data into meaningful functions [44]. The performance of the models can be measured by various tools such as lean six sigma (LSS) and statistical process control (SPC) [45]. Improving the efficiency of processes is essential for environmental and economic reasons.…”

Section: Implementation Of Software Sensor and Machine-learning Model...mentioning

confidence: 99%

See 1 more Smart Citation

Edge-Computing and Machine-Learning-Based Framework for Software Sensor Development

Hanzelik

Kummer

Abonyi

2022

Sensors

View full text Add to dashboard Cite

The present research presents a framework that supports the development and operation of machine-learning (ML) algorithms to develop, maintain and manage the whole lifecycle of modeling software sensors related to complex chemical processes. Our motivation is to take advantage of ML and edge computing and offer innovative solutions to the chemical industry for difficult-to-measure laboratory variables. The purpose of software sensor models is to continuously forecast the quality of products to achieve effective quality control, maintain the stable production condition of plants, and support efficient, environmentally friendly, and harmless laboratory work. As a result of the literature review, quite a few ML models have been developed in recent years that support the quality assurance of different types of materials. However, the problems of continuous operation, maintenance and version control of these models have not yet been solved. The method uses ML algorithms and takes advantage of cloud services in an enterprise environment. Industrial 4.0 devices such as the Internet of Things (IoT), edge computing, cloud computing, ML, and artificial intelligence (AI) are core techniques. The article outlines an information system structure and the related methodology based on data from a quality-assurance laboratory. During the development, we encountered several challenges resulting from the continuous development of ML models and the tuning of their parameters. The article discusses the development, version control, validation, lifecycle, and maintenance of ML models and a case study. The developed framework can continuously monitor the performance of the models and increase the amount of data that make up the models. As a result, the most accurate, data-driven and up-to-date models are always available to quality-assurance engineers with this solution.

show abstract

Section: Implementation Of Software Sensor and Machine-learning Model...mentioning

confidence: 99%

“…These three metrics are key indicators of each laboratory measurement where the standards are provided. These numbers also affect the goodness of the models, as the reference data pertain to these numbers [45]. An essential tool in enterprise quality management is SPC [47].…”

Section: Implementation Of Software Sensor and Machine-learning Model...mentioning

confidence: 99%

Edge-Computing and Machine-Learning-Based Framework for Software Sensor Development

Hanzelik

Kummer

Abonyi

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…O trabalho de Oliveira et al (2013) é a atividade que é fundamental para o funcionamento de um laboratório de Química de rotina, em que se pode determinar resultados tendenciosos e, dessa forma, realizar o estudo dos dados avaliando possíveis problemas na execução diária do método de análise. Kulcsar et al (2014), apresentou uma pesquisa utilizando o CEP no monitoramento estatístico de processos químicos, no consumo de energia visado e o medido. Res., Soc.…”

Section: Laboratório De Químicaunclassified

Utilização de controle estatístico de processo em uma atividade experimental no Instituto Federal do Ceará

Nojosa

Sampaio

Firmino

et al. 2019

RSD

View full text Add to dashboard Cite

As technology advances, chemical analysis laboratories use statistical techniques to demonstrate the accuracy and precision of analytical methods. To make comparisons between the data obtained from an analysis, Statistical Process Control (CEP) can be used, which is a technique widely used in industry to understand and improve process performance through statistical data processing. Control charts are CEP graphic methods that enable continuous control of analytical processes and allow evaluations and possible optimization of assays. The objective of this study is to use the Statistical Process Control (CEP), the control chart, to evaluate the statistical stability of the spectrophotometer used in the application of the Nimodipino analytical methodology validation technique, using data from the absorbance study of this drug, being the tests performed by students contributing to a learning of work activities. With this study it can be verified that the use of the control chart generates an adequate monitoring to evaluate data fluctuations and to carry out studies of the same, being able to be taught to the students and applied in practical classes accompaniments. It can also be demonstrated that the Minitab 17 program assists quickly in the construction of control charts, obtaining real-time analysis results. This program can be used in other laboratories of the Federal Institute of Ceará for statistical control of analyzes with support for student learning.

show abstract

“…As well as technological developments brought them, increased interests on monitoring system exist. Energy monitoring interfaces that are able to calculate the estimated energy consumption [13] can also calculate the instantaneous energy requirement [14]. The monitoring systems can be easily integrated to low-cost and low power conversion system [15].…”

Section: Introductionmentioning

confidence: 99%

Dual DC-DC converter and monitoring interface for asymmetrical string inverters

Kabalcı

Bayındır

Gökkuş

et al. 2015

2015 International Conference on Renewable Energy Research and Applications (ICRERA)

View full text Add to dashboard Cite

This paper proposes monitoring of the dual dc-dc converters that independently operate of each other in the same topology (Buck-Boost). The dual converter structure is proposed to implement asymmetrical string inverter that is intended to be used variously arranged PV strings. The converters are operated by independently running MPPT algorithms. The converters are supplied by programmed dc sources emulating freely arranged solar arrays, and different loads are connected to each converter output. The converters allow using independent power sources like hybrid power techniques owing to these features. Current and voltage sensors measure the output powers of each converter, where the obtained values are evaluated by P&O algorithm on MCU and the PWM signals are generated. At the same time, obtained values are transmitted to computer by a microcontroller on optically isolated UART to USB unit. The received values are saved in a database to enable historical and instant analyse capability of the converters.

show abstract

Statistical Process Control based Energy Monitoring of Chemical Processes

Cited by 5 publications

References 9 publications

Edge-Computing and Machine-Learning-Based Framework for Software Sensor Development

Edge-Computing and Machine-Learning-Based Framework for Software Sensor Development

Utilização de controle estatístico de processo em uma atividade experimental no Instituto Federal do Ceará

Dual DC-DC converter and monitoring interface for asymmetrical string inverters

Contact Info

Product

Resources

About