Fault Diagnosis Using Cascaded Adaptive Second-Order Tristable Stochastic Resonance and Empirical Mode Decomposition

Applied Sciences, Год журнала: 2021, Номер 11(23), С. 11480 - 11480

Опубликована: Дек. 3, 2021

Aiming at the problems of poor decomposition quality and extraction effect a weak signal with strong noise by empirical mode (EMD), novel fault diagnosis method based on cascaded adaptive second-order tristable stochastic resonance (CASTSR) EMD is proposed in this paper. In method, low-frequency interference components are filtered using high-pass filtering, restriction conditions theory solved an ordinary variable-scale method. Then, chaotic ant colony optimization algorithm global ability employed to adaptively adjust parameters system obtain optimal resonance, reduction pretreatment technology CASTSR developed enhance characteristics low frequency. Next, decompose denoising extract characteristic frequency from intrinsic function (IMF), so as realize rolling bearings. Finally, numerical simulation actual bearing data selected prove validity The experiment results indicate that can EMD, effectively features signals, improve accuracy diagnosis. Therefore, effective for rotating machinery.

Язык: Английский

---

Optimality conditions for nonlinear optimization problems with interval-valued objective function in admissible orders

Fuzzy Optimization and Decision Making, Год журнала: 2022, Номер 22(2), С. 247 - 265

Опубликована: Май 21, 2022

Язык: Английский

---

An Enhanced Artificial Electric Field Algorithm with Sine Cosine Mechanism for Logistics Distribution Vehicle Routing

Applied Sciences, Год журнала: 2022, Номер 12(12), С. 6240 - 6240

Опубликована: Июнь 19, 2022

Aiming at the scheduling problem of logistics distribution vehicles, an enhanced artificial electric field algorithm (SC-AEFA) based on sine cosine mechanism is proposed. The development SC-AEFA was as follows. First, a map grid model for enterprise vehicle path planning established. Then, with developed to simulate scheduling, establish movement law model, and plan path. Finally, business named fresh A in Fuzhou Strait Agricultural Sideline Products Trading Market selected test effectiveness method theoretical proof simulation results show that has good optimization ability strong which can improve efficiency vehicles save transportation costs.

Язык: Английский

---

An Improved Hierarchical Clustering Algorithm Based on the Idea of Population Reproduction and Fusion

Electronics, Год журнала: 2022, Номер 11(17), С. 2735 - 2735

Опубликована: Авг. 30, 2022

Aiming to resolve the problems of traditional hierarchical clustering algorithm that cannot find clusters with uneven density, requires a large amount calculation, and has low efficiency, this paper proposes an improved (referred as PRI-MFC) based on idea population reproduction fusion. It is divided into two stages: fuzzy pre-clustering Jaccard fusion clustering. In stage, it determines center point, uses product neighborhood radius eps dispersion degree fog benchmark divide data, Euclidean distance determine similarity data points, membership grade record information common points in each cluster. are be fused, whose coefficient between fused greater than parameter jac fused. The less cluster largest grade. A variety experiments designed from multiple perspectives artificial datasets real demonstrate superiority PRI-MFC terms effect, quality, time consumption. Experiments carried out Chinese household financial survey results conform actual situation households obtained, which shows practicability algorithm.

Язык: Английский

---

An Intelligent Identification Approach Using VMD-CMDE and PSO-DBN for Bearing Faults

Electronics, Год журнала: 2022, Номер 11(16), С. 2582 - 2582

Опубликована: Авг. 18, 2022

In order to improve the fault diagnosis accuracy of bearings, an intelligent method based on Variational Mode Decomposition (VMD), Composite Multi-scale Dispersion Entropy (CMDE), and Deep Belief Network (DBN) with Particle Swarm Optimization (PSO) algorithm—namely VMD-CMDE-PSO-DBN—is proposed in this paper. The number modal components decomposed by VMD is determined observation center frequency, reconstructed according kurtosis, composite multi-scale dispersion entropy signal calculated form training samples test pattern recognition. Considering that artificial setting DBN node parameters cannot achieve best recognition rate, PSO used optimize model, optimized model identify faults. Through experimental comparison analysis, we propose VMD-CMDE-PSO-DBN has certain application value diagnosis.

Язык: Английский

---

Event-Triggered Adaptive Fuzzy Control for Strict-Feedback Nonlinear FOSs Subjected to Finite-Time Full-State Constraints

Fractal and Fractional, Год журнала: 2024, Номер 8(3), С. 160 - 160

Опубликована: Март 12, 2024

In this article, an event-triggered adaptive fuzzy finite-time dynamic surface control (DSC) is presented for a class of strict-feedback nonlinear fractional-order systems (FOSs) with full-state constraints. The logic (FLSs) are employed to approximate uncertain functions in the backstepping process, method applied overcome inherent computational complexity from virtual controller and its derivative, barrier Lyapunov function (BLF) used handle By introducing stability criteria method, it verified that tracking error converges small neighborhood near zero constraints satisfied within predetermined finite time. Moreover, reducing communication burden can be guaranteed without occurrence Zeno behavior, example given demonstrate effectiveness proposed controller.

Язык: Английский

---

Research on Fractional Order Controller of Three-Phase Photovoltaic Inverter System Based on Improved Oustaloup Algorithm

IEEE Access, Год журнала: 2024, Номер 12, С. 39770 - 39782

Опубликована: Янв. 1, 2024

As the core component of photovoltaic grid-connected system, performance improvement inverter is an important means to improve system. key components capacitors and inductors play role energy storage filtering in their electrical characteristics will directly affect dynamic static The existing research showed that should be fractional nature, modeling, analysis control systems were carried out on theoretical basis integer calculus, which inevitably produce some errors. Therefore, controller three-phase system based improved Oustaloup algorithm introduced into this paper for control, can provide a model simulation power electronic systems. practical operation Jining PV generation base (installed capacity 560MW) Shandong Province, China, fractional-order PI $^{\mathrm {\lambda }}$ had good effect quality was also improved.

Язык: Английский

---

Using an open source and resilient technology framework to generate and execute prescription maps for site-specific manure application

Smart Agricultural Technology, Год журнала: 2023, Номер 5, С. 100272 - 100272

Опубликована: Июнь 16, 2023

The development of precision farming solutions and the required network infrastructure appear to be progressing at different speeds levels deployment. In most world's rural areas, where takes place, coverage is a basic level. However, digital are applied, internet-dependent applications need backup enable same or comparable performance towards maintaining functionality specific practice ultimately food production. aim avoid regressing practices waiving advantages established technologies. Based on conceptual framework, defined by authors in previous work, site-specific slurry application was chosen as concrete use case implement demonstrate fallback options maintain efficient reliable even during internet outages. Initially, differences between conventional resilient IT were contrasted investigated. generation prescription map (PM) based fusion multiple parameters, clustered domains soil, yield, remote sensing, performed utilizing open-source offline usable software. For seamless transmission generated PMs, new innovative hardware platform integrated into machinery fleet working process ring (MR), which acting service contractor inter-farm application. Interoperability considered enabling executing software accept PMs altering origin. on- off-line including data fusion, also compared. Here multi-parametric approach corresponded ground truth data, whereas an online farm management information system (FMIS), using only one source, showed deviations zone patterns relative dose rates. addition, impact lack accessible delineation zones investigated resulted switch from medium high rate (DR) level 9.1% field's area.

Язык: Английский

---

Early warning model based on support vector machine ensemble algorithm

Journal of the Operational Research Society, Год журнала: 2024, Номер unknown, С. 1 - 15

Опубликована: Июнь 3, 2024

Язык: Английский

---

Multiclass recognition of AD neurological diseases using a bag of deep reduced features coupled with gradient descent optimized twin support vector machine classifier for early diagnosis

Concurrency and Computation Practice and Experience, Год журнала: 2022, Номер 34(21)

Опубликована: Июнь 17, 2022

Summary Alzheimer's disease (AD) is an advanced neurodegenerative of the brain that affects nerve system brain. Previously, several feature extraction and classification methods were discussed, but provide high over fitting problem, which leads to minimization detection accuracy. To overcome these issues, multi class AD diseases using bag deep reduction technique twin support vector machine classifier (TSVM) optimized with gradient decent optimizer proposed in this manuscript for classifying as severe AD, mild cognitive impairment, healthy control. At first, input EEG signals are pre‐processed. decrease execution time processing size, a features used. The reduced classified by TSVM. simulation process implemented MATLAB environment. model achieves higher accuracy 33.84%, 28.93%, 33.03%, 27.93%, precision 22.87%, 16.97%, 36.97%, compared existing methods, such piecewise aggregate approximation (MCC‐EEG‐PAA‐SVM), convolutional neural network (MCC‐EEG‐CNN), conformal kernel‐based fuzzy (MCC‐EEG‐CKF‐SVM), Pearson correlation coefficient‐based selection strategy linear discriminant analysis (MCC‐EEG‐ PCC‐LDA).

Язык: Английский

---