Dianci bileiqi, 2022 通过输电线路接地网腐蚀试验获得44样本数据,对样本数据进行主成分分析,根据计算结果确定pH值、Cl-含量和NO3-含水量为输电线路接地网腐蚀预测模型的输入量。针对狼群算法存在的缺陷,对探狼游走行为和猛狼运动步长进行改进,得到改进狼群算法。利用改进狼群算法对最小二乘支持向量机进行优化,建立基于IWPA-LSSVM的输电线路接地网腐蚀预测模型。采用IWPA-LSSVM预测模型对线路接地网腐蚀程度进行预测,结果表明,IWPA-LSSVM预测模型的平均相对误差、全局最大相对误差和均方根误差分别为3.47%、4 ...
林肖斐 +4 more
doaj
Research on Compensation Technology of Pressure Sensor Based on Machine Learning and Intelligent Optimization Algorithm [PDF]
, 2017 微机电系统（MicroElectroMechanicalSystem，MEMS）拥有功耗低、灵敏度高、体积小、制造标准化程度高以及性价比高等突出优势，基于MEMS制造工艺的压阻式压力传感器被广泛应用于汽车、航空、石油石化及消费电子的压力测量环节。伴随社会工业化水平的不断发展，对相应工业过程的压力测量性能也日趋严格。环境温度和静压压力作为全面影响高精度MEMS压力传感器整体测量特性的两个关键因素，已然成为压阻式压力传感器在高精度测量领域更进一步的瓶颈。 针对上述问题 ...
李冀
core
Rice fatty acid detection method combining hyperspectral technology with improved LSSVM [PDF]
Objective: To solve the problems of low accuracy and poor efficiency in the existing rice quality testing methods of food enterprises. Methods: Based on a hyperspectral data acquisition system, a fast and non-destructive detection method for stored rice ...
CHEN Chunru +3 more
core +1 more source
基于ILPSO-LSSVM的GIS设备隔离开关机械异响振动识别方法研究
Gaoya dianqi, 2023 隔离开关正常运行对保证气体绝缘开关GIS(gas insulated equipment)设备安全极为重要。文中针对GIS设备隔离开关机械异响振动识别方法开展研究，采用真型GIS设备平台模拟了隔离开关触头接触不良的5个典型状态：正常接触（148μΩ）、轻微接触不良（221、298μΩ）、严重接触不良（433、550μΩ），检测并分析了GIS设备隔离开关机械振动特性，发现GIS设备正常振动的主频率为100 Hz，振动幅值随电流增大而增大；当隔离开关存在接触不良缺陷时，振动频谱100 Hz振动分量幅值增加 ...
王旭鹏 +5 more
doaj
Key Compounds Mining Related to Aroma Richness of Cabernet Sauvignon Dry Red Wine Integrated with Machine Learning(融合机器学习的赤霞珠干红葡萄酒香气浓郁度关键化合物挖掘) [PDF]
Shipin kexue jishu xuebaoTo establish an objective evaluation method for the aroma richness of Cabernet Sauvignon dry red wine integrated with machine learning and identify the key aroma compounds influencing wine aroma richness, volatile compounds in 14 Cabernet Sauvignon dry ...
ZHU Jiaqi(朱佳祺) +3 more
doaj +1 more source
Hydraulic valve fault signal detection based on AR parameter [PDF]
, 2011 本文提出了一种使用最小支持向量机检测溢流阀故障信号的方法。通过提取溢流阀振动时的正常信号和故障信号,在此基础上进行了Ar建模,并由建立的模型获取了信号的Ar参数,之后利用这些参数作为最小支持向量机的输入进行故障辨识,取得了令人满意的结果。The paper presents the method to adopt least squares support vector machine to detect the overflow valve fault signal,and shows AR ...
吴文兵, 黄宜坚
core
Research on Energy Efficiency Optimization Algorithm for Copper Flash Smelting Process Based on Data-driven [PDF]
, 2016 铜闪速熔炼工序具有多变量、非线性、大时滞、强耦合、生产波动大的特点，传统的基于机理模型的优化控制系统很难适应多变的运行条件，预测结果偏差较大，影响最终的控制效果。随着计算机技术的发展，复杂工业过程中积累了大量生产数据，为我们从人工智能的角度进行建模与优化控制提供了数据基础。 本论文以某大型闪速炼铜企业的闪速熔炼生产过程为研究对象。为了实现铜闪速熔炼工序中的节能减耗，本文提出了一种满足三大工艺指标（冰铜品位，冰铜温度，渣中铁硅比）约束的能效优化模型：首先 ...
董云成
core
Comprehensive quality detection method for tomatoes combining machine vision and spectral techniques [PDF]
ObjectiveTo realize rapid and accurate measurement of both internal and external quality of tomatoes, and improve the efficiency and quality of tomato grading.MethodsBased on machine vision and spectroscopy technology, proposed a tomato comprehensive ...
GUO Dechao +4 more
core +1 more source
Gaoya dianqi, 2018 为了更准确、快速地对高压断路器故障进行分类、诊断,提出一种基于混合布谷鸟算法优化的最小二乘支持向量机（LSSVM）的故障诊断方法。首先提取分合闸线圈的时间和电流特征量得到特征向量,再利用模拟退火算法（SA）与布谷鸟算法（CS）结合形成的混合布谷鸟算法（CS-SA）,对支持向量机进行寻优,旨在得到具有最优参数支持向量机分类模型,提高诊断结果的准确性。最后,利用收集到的数据对该算法进行诊断验证,结果表明利用混合布谷鸟算法优化后的LS-SVM得到的分类模型比常用的粒子群算法、遗传算法 ...
徐其丹 +3 more
doaj
Extraction and identification of wear features on grinding roller surface of grinding mill [PDF]
Objective: To achieve surface wear life prediction of abrasive blast rollers of grinding machines. Methods: The wear images of the grinding roller surface were acquired by the built image acquisition system, and the texture parameters such as second ...
JIA Huapo +3 more
core +1 more source