基于音频特征的交流接触器电寿命预测方法

该文基于音频特征的交流接触器电寿命预测方法,采用快速傅里叶变换法分析交流接触器线圈工作电压异常、触头磨损和壳体松动三种状态下接触器合闸时的音频特征,分别与正常的交流接触器音频特征进行对比。对比结果发现,非正常状态的交流接触器合闸时其音频特征与正常状态时明显不同。为进一步研究接触器合闸时的振动发声机理,基于振动方程和声压波动方程建立接触器合闸时的声场模型,仿真结果表明,该声场模型产生的音频频谱幅值随线圈工作电压的增大而变大、频谱分布随触头形貌改变而变化。分别运用BP神经网络和卷积神经网络(CNN)构建交流接触器合闸音频特征与电寿命的关联模型,对比了L-M算法、拟牛顿法、动量BP法和自适应梯度下降法四种BP网络学习算法,建立电寿命验证平台。实验结果表明,L-M算法性能最优,预测误差小于10%;CNN可以在线学习和提取音频特征,但其预测误差超过20%。

基于卡尔曼滤波的锂离子电池荷电寿命预测研究——锂离子电池管理研究之四

文章主要对锂离子电池荷电寿命的预测问题进行了简单的分析,基于卡尔曼滤波为基础,探究了锂离子电池荷电寿命,论述了扩展卡尔曼滤波及预测实验,仅供参考。

基于残差网络回归的直流断路器电寿命预测方法

针对直流电弧分断特性,提出一种预测直流断路器电寿命预测方法。根据GB/T 14048.2—2020进行测试,并获取分断过程中的电压波形。将断弧发生一段时间内的电压信号经过CEEMDAN滤波后,作为网络训练样本。采用触头质量表示电寿命状况,利用线性插值得到触头质量下降曲线,并将其作为网络训练标签。采用Pytorch框架搭建一种残差网络(ResNet)的一维卷积结构预测模型。实验结果表明,所提方法对于触头质量的预测误差<10%,证明了所提方法可以用于预测GB/T 14048.2—2020标准下的电寿命。

基于RVM联合SVR的低压开关电寿命预测方法

继电器等低压开关的电寿命是其可靠性的重要指标,对电寿命进行准确预测对于整个电网系统的安全稳定运行至关重要。传统基于反向传播(BP)神经网络的电寿命预测方法精度低且泛化能力弱,限制了其在实际生活中的推广应用。针对该问题,提出一种基于相关向量机(RVM)联合支持向量回归(SVR)的组合模型实现继电器电寿命的高精度预测。分析接触电阻、线圈电感、吸合时间等10维特征参数与继电器电寿命之间的关系,建立RVM模型对10维特征参数进行特征选择,自动获得与电寿命相关性最高的3维特征参数构成最优特征集合,并将其作为SVR模型的输入从而建立电寿命预测模型,实现对继电器电寿命的高精度预测。针对SVR模型参数选择难题,提出改进的水循环优化算法(IWCA)对其全局寻优,提升预测性能。试验结果表明,相对于BP神经网络预测模型和单一SVR预测模型,所提组合模型预测精度分别提升11.5%和6.3%,实时性分别提升0.64 s和0.32 s,并且在小样本条件下表现出了更强的泛化能力,具有较好的应用前景。

电磁继电器剩余电寿命智能预测研究

针对以往继电器剩余电寿命实际预测方法存在的不足,建立一种用于电磁继电器剩余电寿命预测的BP神经网络模型,该模型采取继电器的吸合时间和超程时间作为输入量,继电器剩余电寿命作为输出量,通过粒子群-蛙跳算法优化网络结构初始参数,利用改进BP算法训练BP神经网络,并加以测试验证。实验结果表明,经过粒子群-蛙跳算法优化的BP神经网络模型能快速、准确地实现电磁继电器剩余电寿命预测。

用于预测交流接触器电寿命的音频特征分析方法

本文提出了一种使用交流接触器电寿命试验过程中的音频信号特征去预测电寿命的方法.该方法首先获取在AC-4条件下的电寿命试验的交流接触器的音频信号;其次在MATLAB平台上对这些音频信号进行分帧处理,再对数据进行滤波处理,得到滤波后的音频信号;然后使用双门限法对音频信号进行端点检测;接下来用MFCC音频特征提取方法对音频进行特征提取,提取出能够反映交流接触器电寿命特征的参数;最后把交流接触器吸合音频特征作为输入量,已进行电寿命次数作为输出量,建立了基于BP神经网络交流接触器电寿命预测模型,并验证了该方法的可行性.

基于动态电阻测量的SF_6断路器触头烧蚀特性

为研究SF_6断路器在开断过程的触头烧蚀特性,对被试断路器进行了开断30 k A短路电流的烧蚀试验,通过动态电阻测量得到了触头在不同烧蚀程度下的动态电阻–行程曲线,并从曲线中提取了触头状态参数。根据这些参数在触头电寿命过程的变化规律,可以得到：1）动静触头运动存在最小有效接触行程,即14.2 mm;2）触头电阻值存在正常范围,主触头为50-150mW,弧触头为200-400mW;3）每次烧蚀试验中触头烧蚀量不变,为0.318 mm。根据以上结果,分析了断路器在开断电流过程中触头材料损失过程及其对断路器性能的影响,并计算出每次烧蚀试验中触头烧蚀量为0.268 mm,与测量值0.318 mm数量相当,最后初步得出了SF_6断路器触头电寿命的预测方法。

Cycle life prediction and match detection in retired electric vehicle batteries

The lifespan models of commercial 18650-type lithium ion batteries （nominal capacity of 1150 mA-h） were presented. The lifespan was extrapolated based on this model. The results indicate that the relationship of capacity retention and cycle number can be expressed by Gaussian function. The selecting function and optimal precision were verified through actual match detection and a range of alternating current impedance testing. The cycle life model with high precision （〉99%） is beneficial to shortening the orediction time and cutting the prediction cost.

Life prediction of Ni-Cd battery based on linearWiener process

Predicting the life of Ni-Cd battery for electric multiple units(EMU)can not only improve the safety and reliability of battery,but also reduce the operating costs of EMU.For this reason,a life prediction method based on linear Wiener process is proposed,which is suitable for both monotonic and non-monotonic degraded systems with accurate results.Firstly,a unary linear Wiener degradation model is established,and the parameters of the model are estimated by using the expectation-maximization algorithm(EM).With the established model,the remaining useful life(RUL)of Ni Cd battery and its distribution are obtained.Then based on the unary Wiener process degradation model,the correlation between capacity and energy is analyzed through Copula function to build a binary linear Wiener degradation model,where its parameters are estimated using Markov Chain Monte Carlo(MCMC)method.Finally,according to the binary Wiener process model,the battery RUL and its distribution are acquired.The experimental results show that the binary linear Wiener degradation model based on capacity and energy possesses higher accuracy than the unary linear wiener process degradation model.

Stress relaxation behavior and life prediction of gasket materials used in proton exchange membrane fuel cells

Silicone rubber gaskets are employed to keep fuel gases and oxidation in their own zones. Due to the viscosity and elasticity, the assembly force could relax when the silicone rubber is compressed in a proton exchange membrane fuel cell. In this work, the stress relaxation behavior of silicone rubber samples is studied under different temperatures and simulated operating conditions. The results show that the stress relaxes exponentially with time at 25% strain level, especially at higher temperature or with higher acid concentration solution. The three-term Prony series can simulate the viscoelastic behavior well, and the Master curves are established by applying a time–temperature superposition method to estimate the life of the samples. It can save approximately 50% and 78% of the test time when an operating temperature and acid solution are chosen appropriately.

Cycle life prediction of traction battery based on degradation data

The traction battery cycle life prediction method using performance degradation data was proposed. The example battery was a commercialized lithium-ion cell with LiMn2O4/Graphite cell system. The capacity faded with cycle number follows a traction function path. Two cycle life predicting models were established. The possible cycle life was extrapolated, which follows normal distribution well. The distribution parameters were estimated and the battery reliability was evaluated. The models＇ precision was validated and the effect of the cycle number on the predicting precision was analysed. The cycle life models and reliability evaluation method resolved the difficulty of battery life appraisal, such as long period and high cost.

Life prediction of ZPW-2000A track circuit equipment based on SVDD and gray prediction

Evaluation of the health state and prediction of the remaining life of the track circuit are important for the safe operation of the equipment of railway signal system.Based on support vector data description(SVDD)and gray prediction,this paper illustrates a method of life prediction for ZPW-2000A track circuit,which combines entropy weight method,SVDD,Mahalanobis distance and negative conversion function to set up a health state assessment model.The model transforms multiple factors affecting the health state into a health index named H to reflect the health state of the equipment.According to H,the life prediction model of ZPW-2000A track circuit equipment is established by means of gray prediction so as to predict the trend of health state of the equipment.The certification of the example shows that the method can visually reflect the health state and effectively predict the remaining life of the equipment.It also provides a theoretical basis to further improve the maintenance and management for ZPW-2000A track circuit.

Lifetime prediction for tantalum capacitors with multiple degradation measures and particle swarm optimization based grey model

A lifetime prediction method for high-reliability tantalum （Ta） capacitors was proposed, based on multiple degradation measures and grey model （GM）. For analyzing performance degradation data, a two-parameter model based on GM was developed. In order to improve the prediction accuracy of the two-parameter model, parameter selection based on particle swarm optimization （PSO） was used. Then, the new PSO-GM（1, 2, co） optimization model was constructed, which was validated experimentally by conducting an accelerated testing on the Ta capacitors. The experiments were conducted at three different stress levels of 85, 120, and 145℃. The results of two experiments were used in estimating the parameters. And the reliability of the Ta capacitors was estimated at the same stress conditions of the third experiment. The results indicate that the proposed method is valid and accurate.

Fatigue Life Prediction of Mooring Chains for a Floating Tidal Current Power Station

As a kind of clean and renewable energy,tidal current energy is becoming increasingly popular all over the world with the shortage of energy and environmental problems becoming more and more severe.A floating tidal current power station is a typical type of tidal current power transformers which can sustain the loads of wind,waves,and current,and even the extreme situation of a typhoon.Therefore,the mooring system must be reliable enough to keep the station operating normally and to survive in extreme situations.The power station examined in this paper was installed at a depth of 40 m.A 44 mm-diameter R4-RQ4 chain was chosen,with a 2 147 kN minimum break strength and 50 kN pretension.Common studless link chain was used in this paper.Based on the Miner fatigue cumulative damage rule,S-N curves of chains,and MOSES software,a highly reliable mooring system was designed and analyzed.The calculation results show that the mooring system designed is reliable throughout a 10-year period.It can completely meet the design requirements of American Petroleum institution（API）.Therefore,the presented research is significant for advancing the design of this kind of power station.

Establishment of wear model and life prediction of drum of hot rolling coiler

For the drum of hot rolling coiler is prone to be easily destroyed, the type of MMU-5G abrasion tester was applied to revealing the friction and wear behavior. The morphology observation by scanning electron microscope (SEM) demonstrates the wear mechanism of the drum, and the test data of the influence coefficient of the normal pressure, relative sliding speed and surface lubrication conditions acted on the linear rate of the wear could be obtained by the regression method. A calculation model, which considers the factors of the structure of the drum, coiling tension and coiling strip specifications, was established by the combination method to predict the wear life of the drum. Then the practical production data was applied into this model and the analysis result was in good accordance with that of actual production.