Denoising Fault-Aware Wavelet Network:A Signal Processing Informed Neural Network for Fault Diagnosis

Deep learning(DL) is progressively popular as a viable alternative to traditional signal processing(SP) based methods for fault diagnosis. However, the lack of explainability makes DL-based fault diagnosis methods difficult to be trusted and understood by industrial users. In addition, the extraction of weak fault features from signals with heavy noise is imperative in industrial applications. To address these limitations, inspired by the Filterbank-Feature-Decision methodology, we propose a new Signal Processing Informed Neural Network(SPINN) framework by embedding SP knowledge into the DL model. As one of the practical implementations for SPINN, a denoising fault-aware wavelet network(DFAWNet) is developed, which consists of fused wavelet convolution(FWConv), dynamic hard thresholding(DHT),index-based soft filtering(ISF), and a classifier. Taking advantage of wavelet transform, FWConv extracts multiscale features while learning wavelet scales and selecting important wavelet bases automatically;DHT dynamically eliminates noise-related components via point-wise hard thresholding;inspired by index-based filtering, ISF optimizes and selects optimal filters for diagnostic feature extraction. It’s worth noting that SPINN may be readily applied to different deep learning networks by simply adding filterbank and feature modules in front. Experiments results demonstrate a significant diagnostic performance improvement over other explainable or denoising deep learning networks. The corresponding code is available at https://github. com/alber tszg/DFAWn et.

The Additive Manufacturing Process of Electric Power Fittings Fabricated by Metal Droplet Deposition

Metal droplet deposition is a kind of additive manufacturing(3D Printing)technique that fabricates near-net part through droplets deposition with lower cost and higher efficiency.This paper proposed a solution to problems of electric power fittings that large inventories,high procurement costs,low manufacturing efficiency and transportation cost.Using additive Manufacturing technique-metal droplet deposition,electric power fittings fabricated on power construction site.This paper describes the manufacturing process of typical thin-walled samples(the structure optimized based on additive manufacturing principle)and ball head rings of electric power fittings.Aiming at the integral AM forming for ball and ball socket electric power fitting workpiece,a novel easy removal forming support material(ceramics and gypsum mixed with UV cured resin)have been developed.Here this support material was used to fabricate nested integral workpieces.Dimensional accuracy and microstructure of the test pieces were analyzed.The error of the height and width of the forming workpiece is within 5%.No obvious overlap trace(such as overlap line and cracks)observed,and the internal microstructure is equiaxial crystal.The average density of the component is 99.51%,which measured by drainage method and 13.39%higher than the cast raw material.

THE CONSTRUCTION OF WAVELET-BASED TRUNCATED CONICAL SHELL ELEMENT USING B-SPLINE WAVELET ON THE INTERVAL

Based on B-spline wavelet on the interval （BSWI）, two classes of truncated conical shell elements were constructed to solve axisymmetric problems, i.e. BSWI thin truncated conical shell element and BSWI moderately thick truncated conical shell element with independent slopedeformation interpolation. In the construction of wavelet-based element, instead of traditional polynomial interpolation, the scaling functions of BSWI were employed to form the shape functions through the constructed elemental transformation matrix, and then construct BSWI element via the variational principle. Unlike the process of direct wavelets adding in the wavelet Galerkin method, the elemental displacement field represented by the coefficients of wavelets expansion was transformed into edges and internal modes via the constructed transformation matrix. BSWI element combines the accuracy of B-spline function approximation and various wavelet-based elements for structural analysis. Some static and dynamic numerical examples of conical shells were studied to demonstrate the present element with higher efficiency and precision than the traditional element.

Steam turbine rotor crack detection using sifting process of EMD and B-spline wavelet on the interval element model

A high-precision identification method for steam turbine rotor crack is presented. By providing the first three measured natural frequencies,contours for the specified natural frequency are plotted in the same coordinate,and the intersection of the three curves predicts the crack location and size. The cracked rotor system is modeled using Bspline wavelet on the interval(BSWI)finite element method,and a method based on empirical mode decomposition(EMD)and Laplace wavelet is implemented to improve the identification precision of the first three measured natural frequencies. Compared with the classical nondestructive testing,the presented method shows its effectiveness and reliability. It is feasible to apply this method to the online health monitoring for rotor structure.

Study on the Consultation Mechanism of an Internet-Based Remote Fault Diagnosis System

Aimed at the deficiency of the mechanism of management and consultation, an idea of an internet-based Virtual Diagnosis Center （VDC） for machine fault is proposed, and the key elements of remote consultation are abstracted. Around the key elements, the construct scheme and cooperative mechanism among experts of VDC are designed. According to the diagnosed object, the context knowledge of a fault machine, fault cases and ActiveX-based analysis tools are integrated into a multimedia consultation environment in VDC to enhance the efficiency of expert consultation. Simultaneously, the technique of push subscription in a SQL Server is utilized to collect machine condition data in an enter- prise machine condition database, which ensures the security of the database. The VDC system in Xi＇an Jiaotong University has been applied to remote diagnosis of a blower in Wuhan Iron and Steel Corporation and the system construction reasonableness and the running stability are verified.

Challenges and Opportunities of AI-Enabled Monitoring, Diagnosis & Prognosis: A Review

Prognostics and Health Management(PHM),including monitoring,diagnosis,prognosis,and health management,occupies an increasingly important position in reducing costly breakdowns and avoiding catastrophic accidents in modern industry.With the development of artificial intelligence(AI),especially deep learning(DL)approaches,the application of AI-enabled methods to monitor,diagnose and predict potential equipment malfunctions has gone through tremendous progress with verified success in both academia and industry.However,there is still a gap to cover monitoring,diagnosis,and prognosis based on AI-enabled methods,simultaneously,and the importance of an open source community,including open source datasets and codes,has not been fully emphasized.To fill this gap,this paper provides a systematic overview of the current development,common technologies,open source datasets,codes,and challenges of AI-enabled PHM methods from three aspects of monitoring,diagnosis,and prognosis.

Immune clonal selection optimization method with combining mutation strategies

In artificial immune optimization algorithm, the mutation of immune cells has been considered as the key operator that determines the algorithm performance. Traditional immune optimization algorithms have used a single mutation operator, typically a Gaussian. Using a variety of mutation operators that can be combined during evolution to generate different probability density function could hold the potential for producing better solutions with less computational effort. In view of this, a linear combination mutation operator of Gaussian and Cauchy mutation is presented in this paper, and a novel clonal selection optimization method based on clonal selection principle is proposed also. The simulation results show the combining mutation strategy can obtain the same performance as the best of pure strategies or even better in some cases.

Structural Design of a Bionic Anti-Clogging Drip Irrigation Emitter Based on Shark Dorsal Fin

Due to the poor anti-clogging performance of the common drip irrigation emitters, this paper designed a new bionic flow channel in the emitter based on the shape of shark dorsal fin. After preliminary structural design, the computational fluid dynamics (CFD) simulation showed that the bionic emitter exhibited superior anti-clogging performance and reasonable hydraulic performance. The passage rate of particles of the bionic emitter in simulation reached 96.3% which was 37.6% higher than 70% of traditional emitter, and the discharge exponent reached 0.4995 which was close to traditional emitter. Physical experiments were consistent with the CFD results, which confirmed the correctness of simulation. After a short cycle anti-clogging performance experiment, the bionic emitter still maintained 96.09% of the initial flow rate.

Fitting of Water Requirement and Yield of Winter Wheat in North China Plain Based on Artificial Neural Network

The fitting of water requirement and yield during the growth period of winter wheat can improve yield effectively and improve irrigation water use efficiency with a certain amount of resource input. This paper selects the irrigation amount, precipitation and yield of winter wheat at the Wuqiao Scientific Observation and Experimental Station. Fitting the water requirement and yield of winter wheat based on three types of artificial neural networks. This paper uses support vector machine (SVM), thought evolution algorithm to optimize BP neural network (MAE-BP) and generalized regression neural network (GRNN) to fit the water requirement and yield of two crops. The SVM is the model with the highest fitting accuracy among the three models, the RMSE, MAE, NS and R2 between predictive value and true value are 7.45 kg/hectares, 213.64 kg/hectares, 0.8086, 0.9409 respectively.

A Study on a Remote Monitoring and Diagnosis System and Its Application

Remote monitoring and diagnosis （RMD） is a new kind of monitoring and diagnosis technology that combines computer science, communication technology and fault diagnosis technology. Via the Internet a remote monitoring and diagnosis system can be established. In this paper, the model of an Internet based remote monitoring and diagnosis system is presented; the function of every part of the RMD system is discussed. Then, we introduce a practical example of a remote monitoring and diagnosis system that we established in a factory; its traits and functions are described.

Bipartite Graphs with the Maximum Sum of Squares of Degrees

In this paper we determine all the bipartite graphs with the maximum sum of squares of degrees among the ones with a given number of vertices and edges.

Enhanced comprehensive properties of directed energy deposited Inconel 718 by a novel integrated deposition strategy

Nickel-based superalloys fabricated by wire-arc directed energy deposition,also known as wire arc ad-ditive manufacturing(WAAM),usually exhibit inherent columnar grain structure,micro-segregation,and rough surface.A novel deposition strategy,integrating an oscillating arc and forced interlayer cooling,was developed in WAAM of Inconel(IN)718 components.The influences of deposition modes on geometrical characteristics,defects,microstructure,and mechanical properties were systematically evaluated.The re-sults showed that the oscillation mode,compared to the standard parallel mode,can effectively promote the molten pool’s spread and wettability,as well as prevent overflow,finally resulting in high geometric accuracy.In addition,the voids-like defects were reduced by 77.78%,while most common crack defects were not observed.Meanwhile,the forced interlayer cooling process further increased the cooling rate,leading to the reduction of the element segregation as well as the proportion of long-chain-like Laves phases.After a short-process modified heat treatment,the anisotropic mechanical behaviors of the as-deposited samples were almost eliminated.Compared with the parallel mode samples,the yield strength and ultimate tensile strength of the oscillation path samples increased by 5.75%and 9.25%,respectively,while the elongation increased significantly by 51.20%.This signifies that their strength and ductility were simultaneously improved.The strengthening mechanisms were further analyzed based on the distribution of the strengthening phases,as well as the residual Laves phases and porosity.

Full-field dynamic strain reconstruction of an aero-engine blade from limited displacement responses

Blade strain distribution and its change with time are crucial for reliability analysis and residual life evaluation in blade vibration tests.Traditional strain measurements are achieved by strain gauges(SGs)in a contact manner at discrete positions on the blades.This study proposes a method of full-field and real-time strain reconstruction of an aero-engine blade based on limited displacement responses.Limited optical measured displacement responses are utilized to reconstruct the full-field strain.The full-field strain distribution is in-time visualized.A displacement-to-strain transformation matrix is derived on the basis of the blade mode shapes in the modal coordinate.The proposed method is validated on an aero-engine blade in numerical and experimental cases.Three discrete vibrational displacement responses measured by laser triangulation sensors are used to reconstruct the full-field strain over the whole operating time.The reconstructed strain responses are compared with the results measured by SGs and numerical simulation.The high consistency between the reconstructed and measured results demonstrates the accurate strain reconstructed by the method.This paper provides a low-cost,real-time,and visualized measurement of blade full-field dynamic strain using displacement response,where the traditional SGs would fail.

简谐力激励下结构的生长式拓扑优化方法（英文）

目的:振动在机械结构的工作中难以避免,且会显著降低机械结构的工作性能。因此,结构动力响应优化设计就显得尤为重要。本文旨在提出一种有效的简谐力激励下的结构拓扑优化方法,通过合理设计结构内加强筋的布局,减小结构特定位置处的位移响应幅值,提高结构的固有频率。概要:植物叶脉可以有效地支撑叶片以抵抗自然界中的风载。本文将植物叶脉分叉构型的最优性用于简谐力激励下结构的加强筋布局设计。首先对简谐力激励下结构的位移响应进行分析。在此基础上,构建以最小化结构特定位置处位移响应幅值为目标的生长式拓扑优化模型。然后,从数学优化的角度,分析加强筋的生长应遵循的规律,提出生长式拓扑优化的数值实现算法。最后通过数值算例证明了本文所提方法的有效性。

Nonlinear dynamic behavior of rotating blade with breathing crack

This study aims at investigating the nonlinear dynamic behavior of rotating blade with transverse crack.A novel nonlinear rotating cracked blade model(NRCBM),which contains the spinning softening,centrifugal stiffening,Coriolis force,and crack closing effects,is developed based on continuous beam theory and strain energy release rate method.The rotating blade is considered as a cantilever beam fixed on the rigid hub with high rotating speed,and the crack is deemed to be open and close continuously in a trigonometric function way with the blade vibration.It is verified by the comparison with a finite element-based contact crack model and bilinear model that the proposed NRCBM can well capture the dynamic characteristics of the rotating blade with breathing crack.The dynamic behavior of rotating cracked blade is then investigated with NRCBM,and the nonlinear damage indicator(NDI)is introduced to characterize the nonlinearity caused by blade crack.The results show that NDI is a distinguishable indicator for the severity level estimation of the crack in rotating blade.It is found that severe crack(i.e.,a closer crack position to blade root as well as larger crack depth)is expected to heavily reduce the stiffness of rotating blade and apparently result in a lower resonant frequency.Meanwhile,the super-harmonic resonances are verified to be distinguishable indicators for diagnosing the crack existence,and the third-order super-harmonic resonances can serve as an indicator for the presence of severe crack since it only distinctly appears when the crack is severe.