Research on Rotating Machinery Fault Diagnosis Based on Improved Multi-target Domain Adversarial Network

Aiming at the problems of low efficiency,poor anti-noise and robustness of transfer learning model in intelligent fault diagnosis of rotating machinery,a new method of intelligent fault diagnosis of rotating machinery based on single source and multi-target domain adversarial network model(WDMACN)and Gram Angle Product field(GAPF)was proposed.Firstly,the original one-dimensional vibration signal is preprocessed using GAPF to generate the image data including all time series.Secondly,the residual network is used to extract data features,and the features of the target domain without labels are pseudo-labeled,and the transferable features among the feature extractors are shared through the depth parameter,and the feature extractors of the multi-target domain are updated anatomically to generate the features that the discriminator cannot distinguish.The modelt through adversarial domain adaptation,thus achieving fault classification.Finally,a large number of validations were carried out on the bearing data set of Case Western Reserve University(CWRU)and the gear data.The results show that the proposed method can greatly improve the diagnostic efficiency of the model,and has good noise resistance and generalization.

Optimal Design and Experimental Study of Tightly Coupled SCR Mixers for Diesel Engines

Two types of tightly coupled Selective Catalytic Reduction(SCR)mixers were designed in this study,namely Mixer 1 integrated with an SCR catalyst and Mixer 2 arranged separately.Computational Fluid Dynamics(CFD)software was utilized to model the gas flow,spraying,and pyrolysis reaction of the aqueous urea solution in the tightly coupled SCR system.The parameters of gas flow velocity uniformity and ammonia distribution uniformity were simulated and calculated for both Mixer 1 and Mixer 2 in the tightly coupled SCR system to compare their advantages and disadvantages.The simulation results indicated that Mixer 1 exhibited a gas velocity uniformity of 0.972 and an ammonia distribution uniformity of 0.817,whereas Mixer 2 demonstrated a gas velocity uniformity of 0.988 and an ammonia distribution uniformity of 0.964.Mixer 2 performed better in the simulation analysis.Furthermore,a 3D-printed prototype of Mixer 2 was manufactured and installed on an engine test bench to investigate ammonia distribution uniformity and NOX conversion efficiency.The experimental investigations yielded the following findings:1)The ammonia distribution uniformity of Mixer 2 was measured as 0.976,which closely aligned with the simulation result of 0.964,with a deviation of 1.2%from the model calculations;2)As exhaust temperature increased,the ammonia distribution uniformity gradually improved,while an increase in exhaust flow rate resulted in a decrease in ammonia distribution uniformity;3)When utilizing Mixer 2,the NOX conversion efficiency reached 84.7%at an exhaust temperature of 200°C and 97.4%at 250°C.Within the exhaust temperature range of 300°C to 450°C,the NOX conversion efficiency remained above 98%.This study proposed two innovative mixer structures,conducted simulation analysis,and performed performance testing.The research outcomes indicated that the separately arranged Mixer 2 exhibited superior performance.The tightly coupled SCR systemequippedwith Mixer 2 achieved excellent levels of gas velocity uniformity,ammonia distribution uniformity,and NOX conversion efficiency.These findings can serve as valuable references for the design and development of ultra-low emission after-treatment systems for diesel engines in the field of diesel engine aftertreatment.

Fuzzy Comprehensive Analysis of Static Mixers Used for Selective Catalytic Reduction in Diesel Engines

The proper selection of a relevant mixer generally requires an effective assessment of several models against theapplication requirements. This is a complex task, as traditional evaluation methods generally focus only on a single aspect of performance, such as pressure loss, mixing characteristics, or heat transfer. This study assesses aurea-based selective catalytic reduction (SCR) system installed on a ship, where the installation space is limitedand the distance between the urea aqueous solution injection position and the reactor is low;therefore, the staticmixer installed in this pipeline has special performance requirements. In particular, four evaluation indices areused in this study: The B value, C value, pressure loss correction factor (Z′), and the ratio of the required distanceto the equivalent diameter of the pipe (LV/D) when the velocity field after the mixer attains uniformity. Six typesof static mixers were simulated with varying concentrations, flow speeds, and positions. A fuzzy comprehensiveevaluation method was introduced to evaluate and compare the related advantages and disadvantages. The resultsshowed that 1) mixing performance was related to the shape of the mixer and had no direct relationship with flowvelocity. 2) For the same mixer position, the lower the urea concentration, the greater the difficulty of evenly mixing the solution. 3) At a constant urea concentration, the mixing performance improved when the mixer was closer to the injection inlet. 4) The installation of a GK mixer in the SCR system of a 9L20C diesel engine was best.

Weak Fault Feature Extraction of the Rotating Machinery Using Flexible Analytic Wavelet Transform and Nonlinear Quantum Permutation Entropy

Addressing the challenges posed by the nonlinear and non-stationary vibrations in rotating machinery,where weak fault characteristic signals hinder accurate fault state representation,we propose a novel feature extraction method that combines the Flexible Analytic Wavelet Transform(FAWT)with Nonlinear Quantum Permutation Entropy.FAWT,leveraging fractional orders and arbitrary scaling and translation factors,exhibits superior translational invariance and adjustable fundamental oscillatory characteristics.This flexibility enables FAWT to provide well-suited wavelet shapes,effectively matching subtle fault components and avoiding performance degradation associated with fixed frequency partitioning and low-oscillation bases in detecting weak faults.In our approach,gearbox vibration signals undergo FAWT to obtain sub-bands.Quantum theory is then introduced into permutation entropy to propose Nonlinear Quantum Permutation Entropy,a feature that more accurately characterizes the operational state of vibration simulation signals.The nonlinear quantum permutation entropy extracted from sub-bands is utilized to characterize the operating state of rotating machinery.A comprehensive analysis of vibration signals from rolling bearings and gearboxes validates the feasibility of the proposed method.Comparative assessments with parameters derived from traditional permutation entropy,sample entropy,wavelet transform(WT),and empirical mode decomposition(EMD)underscore the superior effectiveness of this approach in fault detection and classification for rotating machinery.

Experimental and numerical investigations on micromixing performance of multi-orifice cross-flow jet mixers

Multi-orifice cross-flow jet mixers(MOCJMs)are used in various industrial applications due to their excellent mixing efficiency,but few studies have focused on the micromixing performance of MOCJMs.Herein,the flow characteristics and micromixing performance inside the MOCJM were investigated using experiments and computational fluid dynamics(CFD)simulations based on the Villermaux/Dushman system and the finite-rate/modified eddy-dissipation model.The optimal A value was correlated with the characteristic parameters of MOCJMs to develop a CFD calculation method applicable to the study of the micromixing performance of the MOCJMs.Then the micromixing efficiency was evaluated using the segregation index XS,and the effects of operational and geometric parameters such as mixing flow Reynolds number(ReM),flow ratio(RF),total jet area(ST),the number of jet orifices(n),and outlet configuration on the micromixing efficiency were investigated.It was found that the intensive turbulent region generated by interactions between jets,as well as between jets and crossflows,facilitated rapid reactions.XS decreased with increasing ReM and decreasing RF.Furthermore,MOCJMs with lower ST,four jet orifices,and the narrower outlet configuration demonstrated a better micromixing efficiency.This study contributes to a deeper understanding of the micromixing performance of MOCJMs and provides valuable guidance for their design,optimization,and industrial application.

Exploration of Teaching Reform of Food Machinery and Equipment Course Based on New Engineering Concept

The new engineering concept aims to train high-quality engineering talents to meet the needs of future science and technology and industrial development through the reform of education and teaching.Under the background of"new engineering",by introducing cutting-edge knowledge of the industry and interdisciplinary integration,adopting innovative teaching methods such as project-driven teaching and flipped classroom,strengthening experimental teaching and school-enterprise cooperation,and establishing comprehensive evaluation and feedback mechanism,Food Machinery and Equipment course is reformed to improve the teaching quality and train high-quality engineering talents to meet the needs of modern food processing industry.

Italian textile machinery orders remain stable in Q1 2024

For Italian textile machinery sector,2024 has begun without anything seemingly special.The first quarter has seen the orders index,as reported by the Economics Department of ACIMIT-the Association of Italian Textile Machinery Manufacturers-remain stationary compared to the same period the previous year.In absolute terms,the index came in at 61.2 points(basis:2021=100).

基于电子商务环境的农机管理系统设计

介绍了电子商务环境的背景和现状,详细描述了农机管理系统的实际需求和业务流程,并根据系统设计原则设计了系统总体架构,最后从人机管理、作业管理及综合信息等3个方面实现了农机管理系统。系统在测试过程中取得了较好的应用效果,是一种具有广泛应用前景的高效农机管理系统。

Low Voltage CMOS Gilbert Mixers for Bluetooth Transceiver

Based on the analyses of the reported Gilbert mixers operating at low supply vol tage,a down-conversion mixer and an up-conversion mixer for 2.4GHz bluetooth transceiver are presented with the modified low voltage design techniques,respe ctively.Feedback and current mirror techniques suitable for low voltage operatio n are used to improve the linearity of the up-conversion mixer,and folded-casc ode output stage is adopted to optimize the noise and conversion gain of the dow n-conversion mixer operating at low voltage.Based on 0.35μm CMOS technology,s imulations are performed with 2V supply voltage.The results show that 20dBm thir d-order intercept point (IIP3),87mV output signal amplitude are achieved for up -conversion mixer with about 3mA current;while 20dB conversion gain (CG),6.5nV /Hz input-referred noise,4.4dBm IIP3 are obtained for down-conversion mixer with about 3.5mA current.

CMOS Mixers for 2.4GHz WLAN Transceivers

A down-conversion mixer and an up-conversion mixer for 2.4GHz WLAN transceivers are presented.The down-conversion mixer uses a class-AB input stage to get high linearity and to realize input impedance matching and single-ended to differential conversion.The mixers are implemented in 0.18μm CMOS process.The measured results are given to show their performance.

Summary and Improvement Measures for Soil Compaction Caused by Machinery

As agricultural mechanization is becoming more and more popular, soil compaction, on basis of agricultural machinery, has become a serious problem that can not be ignored. Soil compaction, which is caused by frequent til age and large load in the field, may have different effects on various properties of soil. Soil com-paction may result in different conditions, such as increased soil density and the mechanical resistance, and decreased soil ventilation and the capacity of water holding and storage, but uptaking capacity of chemical elements is restricted. There-fore, soil compaction has some negative impacts on soil properties, physical y, chemical y, or biological y, as wel as plant growth. This research analyzed the cause and the harm of soil compaction in recent years, and some effective mea-sures were proposed to improve soil compaction, in order to reduce the extent of soil compaction caused by agricultural machinery.

Technical Regulation of Foxtail Millet Production by Combining Machinery and Agronomy

In order to solve the problems of low production efficiency,great loss and low yield,Millet Research Institute of Hebei Academy of Agriculture and Forestry Sciences integrated the plastic film mulching technique and mechanized production technique,forming a foxtail millet production technique combining machinery and agronomy.The foxtail millet production technique combining machinery and agronomy regulates millet production from the links of soil preparation,fertilization,variety selection,seeding,intertillage and fertilization and harvest,so as to achieve the effects of promoting the matching between agro-machinery and agronomy,improving the level of millet production mechanization,realizing light simplified production and saving labor cost.This technical regulation has a broad application prospect.

水稻软盘毯状苗分离机设计与试验

目前,水稻种植环节中育秧环节与移栽环节之间的水稻苗盘分离环节的机械化程度相较于其他环节较为薄弱。为提高水稻全程机械化作业水平,降低生产成本,设计了一种适用于水稻毯状苗与塑料软盘分离的机械装置,主要由输送机构、分离机构、扶苗机构、集苗机构、动力系统和机架组成。对装置的结构及工作原理进行了描述,分析确定各个机构的结构参数。以分离率、茎叶损伤率、基质损伤率为试验指标进行苗盘分离试验,结果表明:水稻软盘毯状苗分离机作业效果较好,分离成功率在95%以上,能够降低生产成本,提高生产效率;茎叶损伤率及基质损伤率均在3%以下,保证后续水稻毯状苗移栽工作的顺利进行,较小的茎叶损伤与基质损伤也保证了后续水稻生长过程中不会受到较大的影响,满足水稻育秧农艺要求和水稻工厂化技术规范要求。

大田水肥一体化混肥器设计与试验研究

由于当前市场上没有既适合大田大面积灌溉、混肥精度又高的水肥一体化系统,故在旁路式结构设计中增加静态混合器替换主管道,以提高混肥均匀性为重点进行研究,对混肥部件进行了优化改进。利用混合器自身结构,在不需要外接能源的条件下,使得水肥充分混合,不仅能够满足大面积灌溉要求,而且可以保证混肥精度。基于流体力学及CFD基本原理,通过Fluent软件分析水肥混合过程中SK型静态混合器混合单元数,以及长径比对水肥混合性能和压降的影响,以此找出混合器的最佳结构参数,并对其结构做了改进,设计出了开沟式静态混合器。

肉苁蓉种子离散元仿真参数标定

为寻求肉苁蓉种子离散元模型的物料特性参数,采用物理和仿真试验相结合的方法,以不同物性参数组合下肉苁蓉种子休止角为响应值,采用Plackett-Burman试验对参数进行筛选,获取显著性参数,即肉苁蓉种间静摩擦因数、肉苁蓉种间动摩擦因数、肉苁蓉种子-钢板静摩擦因数、肉苁蓉种子-钢板恢复系数。通过Box-Behnken试验建立休止角与显著性参数回归模型并优化,获取接触参数最优值,即肉苁蓉种间静摩擦因数为0.65、肉苁蓉种间动摩擦因数为0.07、肉苁蓉种子-钢板恢复因数为0.54、肉苁蓉种子-钢板静摩擦因数为0.43。通过仿真与物理试验对比验证,得到二者相对误差为2.05%,表明标定参数可为肉苁蓉种子播种机械仿真提供数据依据。

HIGHER ORDER SPECTRA AND ITS APPLICATION IN MACHINERY FAULT DIAGNOSIS

The application of higher order spectra to machinery faults diagnosis is studied in this paper.A brief review of bispectra is presented,and more emphasis is placed on the ability of higher order spectra to extract diagnostic information from fault signals.Furthermore,by use of the algorithm of higher order spectra,two kinds of typical mechanical faults are analyzed.Results show that the high order spectra analysis is a more efficient method in machinery diagnosis compared with the FFT based spectral analysis.

具有避障功能的农机自动作业全覆盖路径规划方法

针对不同尺寸和类型障碍物条件下的农机车辆自动作业全覆盖路径规划问题,提出了静态全覆盖路径规划方法和路径优化方案。根据矩形田块信息、障碍物信息、农机最小转弯半径和机具宽度,自动选定作业方向、作业行距、地头转弯区域和转弯模式等参数;根据障碍物形状、高覆盖率高作业路径比的需求,对算法进行优化调整,以达到更好的作业效果。软件仿真测试结果表明:对有小矩形障碍物的田块,改进后的算法覆盖率提升了0.11%,重复率降低了0.71%;对大矩形障碍物的田块,两种分区路径的覆盖率分别为89.24%和98.08%,重复率分别为3.53%和2.84%。研究结果表明:算法提高了田块的利用率,降低了作业成本,能够有效避开大小障碍物,同时满足高覆盖率和低重复率的田间作业要求。

云控制水肥药械智能监控平台的设计与实现

随着我国农业现代化水平的提高,以水肥药械为核心的现代农业服务体系成为未来行业发展的方向。为此,采用B/S结构模式,使用Django框架,选用MySQL数据库,设计并实现了一种云控制水肥药械智能监控平台。平台拥有完善的机构、数据交互、用户和权限等管理功能,可实现水肥药械的数字化管理;嵌入了基于Bi-LSTM与LightGBM融合的参考作物蒸散量预测方法,可实现对作物灌溉的实时预测;增加了作物施肥计算公式以及施肥用药数据库,可为用户对肥、药的施用提供科学的参考依据。实际运行及性能测试结果表明:平台的架构和模块设计合理,功能较全面和灵活,可有效满足设施园区对于水肥药械的管理需求,推动现代化农业发展。

Particle Swarm Optimization-Support Vector Machine Model for Machinery Fault Diagnoses in High-Voltage Circuit Breakers

According to statistic data,machinery faults contribute to largest proportion of High-voltage circuit breaker failures,and traditional maintenance methods exist some disadvantages for that issue.Therefore,based on the wavelet packet decomposition approach and support vector machines,a new diagnosis model is proposed for such fault diagnoses in this study.The vibration eigenvalue extraction is analyzed through wavelet packet decomposition,and a four-layer support vector machine is constituted as a fault classifier.The Gaussian radial basis function is employed as the kernel function for the classifier.The penalty parameter c and kernel parameterδof the support vector machine are vital for the diagnostic accuracy,and these parameters must be carefully predetermined.Thus,a particle swarm optimizationsupport vector machine model is developed in which the optimal parameters c andδfor the support vector machine in each layer are determined by the particle swarm algorithm.The validity of this fault diagnosis model is determined with a real dataset from the operation experiment.Moreover,comparative investigations of fault diagnosis experiments with a normal support vector machine and a particle swarm optimization back-propagation neural network are also implemented.The results indicate that the proposed fault diagnosis model yields better accuracy and e-ciency than these other models.

The application on order analysis for the rotating machinery with LabVIEW

Order analysis is regarded as one of the most significant method for monitoring and analyzing rotational machinery for the phenomenon of " frequency smear".However,the order analysis based on resampling is a signal processingwhich converts the constant time interval sampling into constant angle interval sampling,while with the variety of the rotational speed.The superiority of the order analysis is investigatedon implement of order analysis.Andthrough comparing the advantage and disadvantage between spectrum and order analysis,the paper will discuss the order analysis form a deep perspective.