Water Desalination Plant Fault Detection using Artificial Neural NetworkView Crossref metadata(active tab) <div id="edit-xml" class="form-item form-type-item"> <?xml version="1.0"?> <doi_batch version="4.4.1" xmlns="http://www.crossref.org/schema/4.4.1" xmlns:jats="http://www.ncbi.nlm.nih.gov/JATS1" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.crossref.org/schema/4.4.1 http://www.crossref.org/schemas/crossref4.4.1.xsd"><head><doi_batch_id>000690</doi_batch_id><timestamp>1713607039</timestamp><depositor><depositor_name>University of the Aegean</depositor_name><email_address>uoa@university.com</email_address></depositor><registrant>Global NEST Journal</registrant></head><body><journal><journal_metadata><full_title>Global NEST Journal</full_title><full_title>Global NEST: the international Journal</full_title><issn media_type="print">1790-7632</issn><issn media_type="electronic">2241-777X</issn></journal_metadata><journal_issue><titles><title>Issue 1</title></titles><publication_date><month>01</month><year>2024</year></publication_date><journal_volume><volume>25</volume></journal_volume><issue>1</issue></journal_issue><journal_article><titles><title>Water Desalination Plant Fault Detection using Artificial Neural Network</title></titles><abstract xmlns="http://www.ncbi.nlm.nih.gov/JATS1"><p><p>Water famine is very cruel. The desalination plant was brought in to alleviate the water shortage. A desalination plant has been set up in many places around the world. In the view of expanding worldwide need of fresh water, the usage of desalination plant becomes more common. There are more than twenty-five thousand desalination plants around the world. Many industries require treated water for production, water treatment, and other functions. Water quality is occasionally insufficient or does not satisfy the quality criteria for manufacturing causes. So, the enterprises utilize desalination systems to purify water for their own usage. It makes the water safe to drink as well as suitable for a variety of industrial applications. The fault occurring in the desalination plant, it slows down the processing the speed and reduce the output rate. In this study, focuses on the faults like not under system control, electrical fault, pump fault, control valve fault, inaccurate signal, old data fault, derived fault and transmitter fault. The proposed artificial neural network with the single and double component fault (ANN S-DCF) is introduced to detect the faults occurring in the desalination plant. The faults are splitted into two catagories and characteristics of each fault are trained in the artificial neural network. The result of this work achieves the best accuracy comparing to the existing techniques of SVR (support vector regression), PCA (principal component analysis) and DPLS (dynamic partial least square) method. This study achieves the accuracy rate of 96%, precision rate of 93% and sensitivity rate of 95% respectively with low complexity and high operational speed.</p> </p></abstract><publication_date><month>11</month><day>25</day><year>2022</year></publication_date><pages><first_page>127</first_page><last_page>133</last_page></pages><publisher_item><identifier id_type="pii">gnest_04503</identifier></publisher_item><doi_data><doi>10.30955/gnj.004503</doi><timestamp>1713607039</timestamp><resource>https://journal.gnest.org/publication/gnest_04503</resource></doi_data></journal_article></journal></body></doi_batch> </div>
