Machine Learning-Based Condition Monitoring for PV Systems: State of the Art and Future Prospects
Authors
Berghout, Tarek; email: t.berghout@univ-batna2.dzBenbouzid, Mohamed; orcid: 0000-0002-4844-508X; email: Mohamed.Benbouzid@univ-brest.fr
Bentrcia, Toufik; email: t.bentrcia@univ-batna2.dz
Ma, Xiandong; email: xiandong.ma@lancaster.ac.uk
Djurović, Siniša; orcid: 0000-0001-7700-6492; email: Sinisa.Durovic@manchester.ac.uk
Mouss, Leïla-Hayet; email: h.mouss@univ-batna2.dz
Publication Date
2021-10-03
Metadata
Show full item recordAbstract
To ensure the continuity of electric power generation for photovoltaic systems, condition monitoring frameworks are subject to major enhancements. The continuous uniform delivery of electric power depends entirely on a well-designed condition maintenance program. A just-in-time task to deal with several naturally occurring faults can be correctly undertaken via the cooperation of effective detection, diagnosis, and prognostic analyses. Therefore, the present review first outlines different failure modes to which all photovoltaic systems are subjected, in addition to the essential integrated detection methods and technologies. Then, data-driven paradigms, and their contribution to solving this prediction problem, are also explored. Accordingly, this review primarily investigates the different learning architectures used (i.e., ordinary, hybrid, and ensemble) in relation to their learning frameworks (i.e., traditional and deep learning). It also discusses the extension of machine learning to knowledge-driven approaches, including generative models such as adversarial networks and transfer learning. Finally, this review provides insights into different works to highlight various operating conditions and different numbers and types of failures, and provides links to some publicly available datasets in the field. The clear organization of the abundant information on this subject may result in rigorous guidelines for the trends adopted in the future.Citation
Energies, volume 14, issue 19, page e6316Publisher
MDPIType
articleDescription
From MDPI via Jisc Publications RouterHistory: accepted 2021-09-30, pub-electronic 2021-10-03
Publication status: Published
Collections
Related items
Showing items related by title, author, creator and subject.
-
Is the Morphological Subtype of Extra-Pulmonary Neuroendocrine Carcinoma Clinically Relevant?Frizziero, Melissa; email: melissa.frizziero@cruk.manchester.ac.uk; Durand, Alice; orcid: 0000-0002-0193-9058; email: alice.durand@chu-lyon.fr; Taboada, Rodrigo G.; orcid: 0000-0001-5674-2669; email: gomes.taboada@gmail.com; Zaninotto, Elisa; email: elisa.zaninotto@gmail.com; Luchini, Claudio; orcid: 0000-0003-4901-4908; email: claudio.luchini@univr.it; Chakrabarty, Bipasha; email: bipasha.chakrabarty@nhs.net; Hervieu, Valérie; email: valerie.hervieu@chu-lyon.fr; Claro, Laura C. L.; email: laura.claro@accamargo.org.br; Zhou, Cong; orcid: 0000-0002-6938-4685; email: cong.zhou@cruk.manchester.ac.uk; Cingarlini, Sara; email: cingarlini@icloud.com; et al. (MDPI, 2021-08-18)Extra-pulmonary neuroendocrine carcinomas (EP-NECs) are lethal cancers with limited treatment options. Identification of contributing factors to the observed heterogeneity of clinical outcomes within the EP-NEC family is warranted, to enable identification of effective treatments. A multicentre retrospective study investigated potential differences in “real-world” treatment/survival outcomes between small-cell (SC) versus (vs.) non-SC EP-NECs. One-hundred and seventy patients were included: 77 (45.3%) had SC EP-NECs and 93 (54.7%) had non-SC EP-NECs. Compared to the SC subgroup, the non-SC subgroup had the following features: (1) a lower mean Ki-67 index (69.3% vs. 78.7%; p = 0.002); (2) a lower proportion of cases with a Ki-67 index of ≥55% (73.9% vs. 88.7%; p = 0.025); (3) reduced sensitivity to first-line platinum/etoposide (objective response rate: 31.6% vs. 55.1%, p = 0.015; and disease control rate; 59.7% vs. 79.6%, p = 0.027); (4) worse progression-free survival (PFS) (adjusted-HR = 1.615, p = 0.016) and overall survival (OS) (adjusted-HR = 1.640, p = 0.015) in the advanced setting. Within the advanced EP-NEC cohort, subgroups according to morphological subtype and Ki-67 index (55% vs. ≥55%) had significantly different PFS (adjusted-p = 0.021) and OS (adjusted-p = 0.051), with the non-SC subgroup with a Ki-67 index of 55% and non-SC subgroup with a Ki-67 index of ≥55% showing the best and worst outcomes, respectively. To conclude, the morphological subtype of EP-NEC provides complementary information to the Ki-67 index and may aid identification of patients who could benefit from alternative first-line treatment strategies to platinum/etoposide.
-
Elevated Circulating and Placental SPINT2 Is Associated with Placental DysfunctionMurphy, Ciara N.; orcid: 0000-0001-6996-7250; email: ciaram1@student.unimelb.edu.au; Walker, Susan P.; email: spwalker@unimelb.edu.au; MacDonald, Teresa M.; email: teresa.mary.macdonald@gmail.com; Keenan, Emerson; orcid: 0000-0003-1966-2293; email: emerson.keenan@unimelb.edu.au; Hannan, Natalie J.; email: nhannan@unimelb.edu.au; Wlodek, Mary E.; orcid: 0000-0002-8490-9099; email: m.wlodek@unimelb.edu.au; Myers, Jenny; email: Jenny.Myers@manchester.ac.uk; Briffa, Jessica F.; email: jessica.briffa@unimelb.edu.au; Romano, Tania; orcid: 0000-0002-8581-2256; email: t.romano@latrobe.edu.au; Roddy Mitchell, Alexandra; email: aroddymitchell@gmail.com; et al. (MDPI, 2021-07-12)Biomarkers for placental dysfunction are currently lacking. We recently identified SPINT1 as a novel biomarker; SPINT2 is a functionally related placental protease inhibitor. This study aimed to characterise SPINT2 expression in placental insufficiency. Circulating SPINT2 was assessed in three prospective cohorts, collected at the following: (1) term delivery (n = 227), (2) 36 weeks (n = 364), and (3) 24–34 weeks’ (n = 294) gestation. SPINT2 was also measured in the plasma and placentas of women with established placental disease at preterm (34 weeks) delivery. Using first-trimester human trophoblast stem cells, SPINT2 expression was assessed in hypoxia/normoxia (1% vs. 8% O2), and following inflammatory cytokine treatment (TNFα, IL-6). Placental SPINT2 mRNA was measured in a rat model of late-gestational foetal growth restriction. At 36 weeks, circulating SPINT2 was elevated in patients who later developed preeclampsia (p = 0.028; median = 2233 pg/mL vs. controls, median = 1644 pg/mL), or delivered a small-for-gestational-age infant (p = 0.002; median = 2109 pg/mL vs. controls, median = 1614 pg/mL). SPINT2 was elevated in the placentas of patients who required delivery for preterm preeclampsia (p = 0.025). Though inflammatory cytokines had no effect, hypoxia increased SPINT2 in cytotrophoblast stem cells, and its expression was elevated in the placental labyrinth of growth-restricted rats. These findings suggest elevated SPINT2 is associated with placental insufficiency.
-
Climate Change Adaptation on Small Island States: An Assessment of Limits and ConstraintsLeal Filho, Walter; orcid: 0000-0002-1241-5225; email: walter.leal2@haw-hamburg.de; Krishnapillai, Murukesan; orcid: 0000-0002-3237-3149; email: muru@comfsm.fm; Sidsaph, Henry; orcid: 0000-0003-0538-0906; email: h.sidsaph@chester.ac.uk; Nagy, Gustavo J.; email: gnagy@fcien.edu.uy; Luetz, Johannes M.; orcid: 0000-0002-9017-4471; email: j.luetz@unsw.edu.au; Dyer, Jack; email: Jack.Dyer@utas.edu.au; Otoara Ha’apio, Michael; email: mhaapio@gmail.com; Havea, Peni Hausia; orcid: 0000-0002-5411-0358; email: ilaisiaimoana@yahoo.com; Raj, Kushaal; email: kushaal_raj@hotmail.com; Singh, Priyatma; email: priyatmas@unifiji.ac.fj; et al. (MDPI, 2021-05-31)Small Island States (SIDS) are among the nations most exposed to climate change (CC) and are characterised by a high degree of vulnerability. Their unique nature means there is a need for more studies focused on the limits to CC adaptation on such fragile nations, particularly regarding their problems and constraints. This paper addressed a perceived need for research into the limitations of adaptation on SIDS, focusing on the many unique restrictions. To this end, the study identified and described the adaptation limits they have by using a review of the literature and an analysis of case studies from a sample of five SIDS in the Caribbean and Pacific regions (Barbados, Trinidad and Tobago, Cook Islands, Fiji, Solomon Islands and Tonga). This research’s findings showed that an adaptable SIDS is characterised by awareness of various values, appreciation and understanding of a diversity of impacts and vulnerabilities, and acceptance of certain losses through change. The implications of this paper are two-fold. It explains why island nations continue to suffer from the impacts of CC and suggest some of the means via which adequate policies may support SIDS in their efforts to cope with the threats associated with a changing climate. This study concluded that, despite the technological and ecological limits (hard limits) affecting natural systems, adaptation to CC is limited by such complex forces and societal factors (soft limits) that more adequate adaptation strategies could overcome.