General Performance Score for classification problems

Applied Intelligence, Год журнала: 2022, Номер 52(10), С. 12049 - 12063

Опубликована: Янв. 31, 2022

Abstract Several performance metrics are currently available to evaluate the of Machine Learning (ML) models in classification problems. ML usually assessed using a single measure because it facilitates comparison between several models. However, there is no silver bullet since each metric emphasizes different aspect classification. Thus, choice depends on particular requirements and characteristics problem. An additional problem arises multi-class problems, most well-known only directly applicable binary In this paper, we propose General Performance Score (GPS) , methodological approach build for The basic idea behind GPS combine set individual metrics, penalising low values any them. users can that relevant based their preferences obtaining conservative combination. Different -based compared with alternatives problems real simulated datasets. built proposed method improve stability explainability usual metrics. Finally, brings benefits both new research lines practical usage, where tailored considered.

Язык: Английский

---

Convolutional neural network based on attention mechanism and Bi-LSTM for bearing remaining life prediction

Applied Intelligence, Год журнала: 2021, Номер 52(1), С. 1076 - 1091

Опубликована: Май 16, 2021

Язык: Английский

---

Semi-supervised multi-sensor information fusion tailored graph embedded low-rank tensor learning machine under extremely low labeled rate

Information Fusion, Год журнала: 2023, Номер 105, С. 102222 - 102222

Опубликована: Дек. 30, 2023

Язык: Английский

---

Diagnostic of Combined Mechanical and Electrical Faults in ASD-Powered Induction Motor Using MODWT and a Lightweight 1-D CNN

IEEE Transactions on Industrial Informatics, Год журнала: 2021, Номер 18(7), С. 4688 - 4697

Опубликована: Окт. 20, 2021

The early fault detection in the rotary electrical machines,such as induction motors (IMs), has been growing modern industry. IMs have widely used industrial applications due to its easy installation, reliability, and low cost. However, increasing usage of also increases need for timely maintenance order ensure their operation a longer service life. This article proposes new diagnosis methodology based on maximal overlap discrete wavelet transform lightweight 1-D convolutional neural network (CNN) architecture, detect mechanical faults combination, adjustable speed drive (ASD)-powered IMs. Specifically, single combined were studied from next: Outer raceway bearing (mechanical), turn-to-turn short-circuit, phase-to-ground short circuit (electrical). presented study was developed using current signals acquired stators 1 hp. are measured at powered conditions introduced by power grid with constant frequency 60 Hz, an ASD three different frequencies. proposed diagnostic reaches more than 99% accuracy.

Язык: Английский

---

Solar Radiation Forecasting by Pearson Correlation Using LSTM Neural Network and ANFIS Method: Application in the West-Central Jordan

Future Internet, Год журнала: 2022, Номер 14(3), С. 79 - 79

Опубликована: Март 5, 2022

Solar energy is one of the most important renewable energies, with many advantages over other sources. Many parameters affect electricity generation from solar plants. This paper aims to study influence these on predicting radiation and electric produced in Salt-Jordan region (Middle East) using long short-term memory (LSTM) Adaptive Network-based Fuzzy Inference System (ANFIS) models. The data relating 24 meteorological for nearly past five years were downloaded MeteoBleu database. results show that varies according season. forecasting ANFIS provides better when parameter correlation high (i.e., Pearson Correlation Coefficient PCC between 0.95 1). In comparison, LSTM neural network shows low (PCC range 0.5–0.8). obtained RMSE 0.04 0.8 depending season used parameters; new influencing are also investigated.

Язык: Английский

---

Multi-channel sensor fusion for real-time bearing fault diagnosis by frequency-domain multilinear principal component analysis

The International Journal of Advanced Manufacturing Technology, Год журнала: 2022, Номер 124(3-4), С. 1321 - 1334

Опубликована: Ноя. 30, 2022

Язык: Английский

---

Wasserstein distance based multi-scale adversarial domain adaptation method for remaining useful life prediction

Applied Intelligence, Год журнала: 2022, Номер 53(3), С. 3622 - 3637

Опубликована: Июнь 1, 2022

Язык: Английский

---

A transformer model with enhanced feature learning and its application in rotating machinery diagnosis

ISA Transactions, Год журнала: 2022, Номер 133, С. 1 - 12

Опубликована: Июль 23, 2022

Язык: Английский

---

Continual learning classification method and its application to equipment fault diagnosis

Applied Intelligence, Год журнала: 2021, Номер 52(1), С. 858 - 874

Опубликована: Май 12, 2021

Язык: Английский

---

A Multi-Input Convolutional Neural Network Model for Electric Motor Mechanical Fault Classification Using Multiple Image Transformation and Merging Methods

Machines, Год журнала: 2024, Номер 12(2), С. 105 - 105

Опубликована: Фев. 2, 2024

This paper addresses the critical issue of fault detection and prediction in electric motor machinery, a prevalent challenge industrial applications. Faults these machines, stemming from mechanical or electrical issues, often lead to performance degradation malfunctions, manifesting as abnormal signals vibrations currents. Our research focuses on enhancing accuracy classification facilities, employing innovative image transformation methods—recurrence plots (RPs), Gramian angular summation field (GASF), difference (GADF)—in conjunction with multi-input convolutional neural network (CNN) model. We conducted comprehensive experiments using datasets encompassing four types machinery components: bearings, belts, shafts, rotors. The results reveal that our CNN model exhibits exceptional across all types, significantly outperforming traditional single-input models. study not only demonstrates efficacy advanced techniques but also underscores potential models diagnosis, paving way for more reliable efficient monitoring machinery.

Язык: Английский

---