基于工况识别的XGBoost算法在水泥熟料质量预测中的应用

采用数据驱动方法,基于ResNet50深度学习模型和XGBoost算法,实现对水泥熟料中fCaO含量的预测。利用ResNet50模型对篦冷机落料位置图像进行识别,判断区分回转窑的正常与异常工况。通过训练ResNet50模型,对回转窑的实时图像进行分类,可以及时发现潜在问题和异常情况,提高生产过程的稳定性和安全性。基于XGBoost算法,对正常工况下熟料fCaO含量进行预测,并将回转窑的工况和熟料fCaO含量进行关联,可以实现对熟料生产过程的监测和控制,提高熟料品质和生产效率。研究结果表明,基于深度学习的图像识别和基于XGBoost算法的质量预测方法,可以有效地预测熟料fCaO的含量,并为熟料生产提供指导和优化策略。     

基于遗传算法和长短记忆神经网络组合模型的加油站销量预测

针对加油站销量波动大且非线性特征明显,使用传统时间序列的预测模型无法满足实际预测需求的情况,提出基于遗传算法(GA)和长短记忆神经网络(LSTM)的销量组合预测模型,在原始数据的基础上加入温度、天气、油价、星期、节假日特征进行辅助预测,对文本类数据使用One-hot编码并使用Embedding降维,采用遗传算法求得LS...     

基于Voting和Stacking集成算法的岩爆倾向性预测

岩爆是矿山深部开采中常见的地质灾害,准确预测岩爆可降低矿山生产安全风险。将机器学习应用于岩爆预测是切实可行的,但仅用一种方法或将几种方法简单结合对于提高岩爆预测的准确性或泛化性作用十分有限。基于此,将最大切向应力、应力集中系数、脆性系数、弹性能量指数等作为指标,利用231组有效岩爆数据,基于Voting和Stacking集成算法,融合精确率较高的6种基础分类器(LR、RF、SVM、DT、KNN、GNB),建立了4个集成分类器V₁、V₂、S₁和S₂。根据预测结果的混淆矩阵计算了精确率、准确率、召回率及F₁分数,对各分类器性能进行了评估,结果表明：基础分类器中SVM、RF对Ⅰ级、Ⅱ级样本较敏感,KNN对Ⅲ级、Ⅳ级样本更敏感;RF、SVM整体预测效果最好,精确率分别为0.93、0.94;集成分类器相对于基础分类器性能均有不同程度的提升,但受性能较差的基础分类器及投票机制影响,Voting集成分类器整体性能弱于Stacking集成分类器;4个集成分类器中S₁性能提...     

基于Spark框架的电商实时推荐系统的设计与实现

大数据时代背景下,基于Hadoop平台构建的电商推荐系统面临数据处理效率低下、难以根据用户实时行为进行推荐的问题.针对Hadoop平台存在的问题,本文提出了基于Spark框架构建的电商实时推荐系统,通过借助Spark框架平台及其组件采集用户行为日志数据,并进行用户隐性行为分析和离线推荐系统训练,提高了离线推荐系统效率....     

基于机器学习的塑料分类回收预测系统

塑料分类回收预测系统主要由垃圾接收装置、垃圾预测分类装置、垃圾压缩装置和垃圾回收储存装置4部分组成,其中垃圾预测分类装置凭借提出的塑料预测分类模型执行塑料分类工作。塑料预测分类模型应用深层次的Inception卷积神经网络,提取高度抽象的关键塑料特征。实验结果表明:塑料分类回收预测系统的预测分类准确率高于传统的预测分类模型约2%。     

基于集成学习算法的水平气井积液状态预测

随着气藏能量衰竭,苏里格气田水平井积液情况日益严重,传统气井携液临界流量预测模型难以全面考虑水平井复杂的井身结构及多相流的耦合作用,导致判断气井积液状态时误差较大。为了克服上述局限性,本文提出一种纯现场数据挖掘的气井积液状态预测模型,实例分析表明,与现有临界携液流量模型相比,集成学习算法建立的气井积液状态预测准确率较高,可有效指导苏里格水平气井积液判断与排采工艺选择。     

考虑多影响因素的加油站销量预测研究

加油站销量预测是成品油二次物流中不可或缺的一部分,有利于推进油品主动配送,帮助二次物流运输精确调度,提升企业整体运行效率。通过历史数据及模型结果分析得出,加油站销量与特殊日期、长短时等多因素有关,文章在长短期记忆网络（LSTM）基础上引入多因素特征构建预测模型,并以某市加油站真实销量数据为实例进行检验。经验证,模型在汽油预测方面的平均误差小于15%,柴油预测的平均误差小于18%,能够满足应用需求。     

美国橡胶制造商会修正国内轮胎销量的预测

美国橡胶制造商会（RMA）最近预测,由于国内经济不断恶化,2008年美国轮胎的销售量可能下滑4％,降至2亿9800万条。2009年由于美国经济仍将继续处于低谷,国内对轮胎的需求可能不旺。     

基于邻域-克隆选择学习算法的分馏装置负荷优化

在免疫克隆选择和人工免疫网络算法基础上,采用了Agent的思想,提出了一种邻域-克隆选择学习全局优化算法(N-Clonalg)。不同于其他人工免疫算法,N-Clonalg定义了网格化的邻域操作环境,其主要搜索算子有N-克隆选择、N-竞争和自学习算子,能有机结合全局与局部搜索,多峰测试函数表明能较好地克服克隆选择算法(Clonalg)的早熟及人工免疫网络算法(Opt-aiNet)收敛速度慢问题。分馏装置负荷优化实例应用表明,算法具有较好的最优解搜索性能,能较好地实现化工中的寻优问题。     

A new estimation algorithm of physical properties based on a group contribution and support vector machine

There are two ways to evaluate the properties of unknown chemical compounds. One is by traditional approaches, which measure the desired data from the experiments and the other is by predicting them in the theoretical approaches using a kind of prediction model. The latter are considered to be more effective because they are less time consuming and cost efficient, and there is less risk in conducting the experiments. Besides, it is inconvenient to conduct experiments to obtain experimental data, especially for new materials or high molecular substances. Several methods using regression model and neural network for predicting the physical properties have been suggested so far. However, the existing methods have many problems in terms of accuracy and applicability. Therefore, an improved method for predicting the properties is needed. A new method for predicting the physical property was proposed to predict 15 physical properties for the chemicals which consist of C, H, N, O, S and Halogens. This method was based on the group contribution method that was oriented from the assumption that each fragment of a molecule contributes a certain amount to the value of its physical property. In order to improve the accuracy of the prediction of the physical properties and the applicability, we extended the database, significantly modifying the existing group contribution methods, and then established a new method for predicting the physical properties using support vector machine (SVM) which is a statistical theory that has never been used for predicting the physical properties. The SVM-based approach can develop nonlinear structure property correlations more accurately and easily in comparison with other conventional approaches. The results from the new estimation method are found to be more reliable, accurate and applicable. The newly proposed method can play a crucial role in the estimation of new compounds in terms of the expense and time.     

Modeling of oil near-infrared spectroscopy based on similarity and transfer learning algorithm

Near-infrared spectroscopy mainly reflects the frequency-doubled and total-frequency absorption information of hydrogen-containing groups (0 -H, C-H, N-H, S-H) in organic molecules for near-infrared lights with different wavelengths, so it is applicable to testing of most raw materials and products in the field of petrochemicals. However, the modeling process needs to collect a large number of laboratory analysis data. There are many oil sources in China, and oil properties change frequently. Modeling of each raw material is not only unfeasible but also will affect its engineering application efficiency. In order to achieve rapid modeling of near-infrared spectroscopy and based on historical data of different crude oils under different detection conditions, this paper discusses about the feasibility of the application of transfer learning algorithm and makes it possible that transfer learning can assist in rapid modeling using certain historical data under similar distributions under a small quantity of new data. In consideration of the requirement of transfer learning for certain similarity of different datasets, a transfer learning method based on local similarity feature selection is proposed. The simulation verification of spectral data of 13 crude oils measured by three different probe detection methods is performed. The effectiveness and application scope of the transfer modeling method under different similarity conditions are analyzed.     

A new forecasting method for system marginal prices based on power supply and demand

A new forecasting scheme is presented of short-term system marginal price (SMP) using past data on power supply and demand as well as past cost data. The forecasting of SMP is one of the most significant factors in an electricity market in which power is produced by generators, transmitted by transmission companies, and distributed by suppliers according to new trading agreements. The accurate forecasting of SMP can significantly influence the profit of market participants. In this paper, a new methodology for day-ahead SMP forecasting is proposed using the law of supply and demand on power. The salient feature of the proposed approach is that it exhibits excellent predicting performance in short-term forecasting.     

基于鲸鱼优化算法的汽轮机热耗率模型预测

为了准确地建立汽轮机热耗率预测模型,提出了一种基于反向学习自适应的鲸鱼优化算法（AWOA）和快速学习网（FLN）综合建模的方法。首先将改进后的鲸鱼算法与经典改进的粒子群、差分进化算法和基本鲸鱼算法进行比较,结果证明其具有更高的收敛精度和更快的收敛速度;然后采用某热电厂600 MW超临界汽轮机组现场收集的运行数据建立汽轮机热耗率预测模型,并将改进后的鲸鱼算法优化的快速学习网模型的预测结果与基本快速学习网及经典改进的粒子群、差分进化算法和基本鲸鱼算法优化的快速学习网模型预测结果相比较。结果表明,AWOA-FLN预测模型具有更高的预测精度和更强的泛化能力,更能准确地预测汽轮机的热耗率。     

基于遗传算法和粒子群优化算法的电力系统无功优化

从数学的角度分析,电力系统无功优化是一个多变量、多约束、非连续性的混合非线性规划问题,因此,优化过程十分复杂.以减少有功网损为目标函数建立电力系统无功优化计算的数学模型,基于遗传算法和粒子群优化算法,提出一种新颖的混合策略来求解无功优化问题.IEEE 6和IEEE 14节点系统的仿真计算结果表明:与单一的遗传算法或粒子群优化算法相比,该混合策略在优化效果方面具有明显的优势.     

A new method to forecast multi-time scale load of natural gas based on augmentation data-machine learning model

Gas load forecasting is important for the economic and reliable operation of the city gas transmission and distribution system. In this paper, a nonlinear autoregressive model (NARX) with exogenous inputs, support vector machine (SVM), Gaussian process regression (GPR) and ensemble tree model (ETREE) were used to predict and compare the gas load based on the gas load data in a certain region for past 3?years. The results showed that the prediction errors for most of days were higher than 10%. Further, simulation data were generated by considering the gas load variation trend, which was then combined with historical data to form the augmentation data set to train the model. The test results indicated that the prediction error of daily gas load in one year reduced to below 7% with a machine learning prediction method based on augmentation data. In addition, the model based on augmentation data set still performed better than original data in predicting the monthly gas load in last year as well as daily gas load in last month and week. Therefore, the method based on augmentation data proposed in this paper is a potentially good tool to forecast natural gas load.     

基于改进扩张搜索聚类算法的多流形软测量建模

针对化工生产过程工况复杂多变，单一的软测量模型难以满足系统对估计精度的要求，提出了一种基于改进的扩张搜索聚类算法的多流形软测量建模的方法。该算法采用流形距离来代替欧氏距离，自适应地确定邻域半径，并引入局部密度用于确定聚类中心，对聚类后得到的各个子流形分别采用流形学习中的核等距映射法进行特征提取，建立基于高斯过程回归的子模型。将该方法应用于某双酚A生产装置的软测量建模，仿真结果验证了该方法的有效性。     

Chemometric Studies on zNose™ and Machine Vision Technologies for Discrimination of Commercial Extra Virgin Olive Oils

The aim of this study was to classify Turkish commercial extra virgin olive oil (EVOO) samples according to geographical origins by using surface acoustic wave sensing electronic nose (zNose?) and machine vision system (MVS) analyses in combination with chemometric approaches. EVOO samples obtained from north and south Aegean region were used in the study. The data analyses were performed with principal component analysis class models, partial least squares‐discriminant analysis (PLS‐DA) and hierarchical cluster analysis (HCA). Based on the zNose? analysis, it was found that EVOO aroma profiles could be discriminated successfully according to geographical origin of the samples with the aid of the PLS‐DA method. Color analysis was conducted as an additional sensory quality parameter that is preferred by the consumers. The results of HCA and PLS‐DA methods demonstrated that color measurement alone was not an effective discriminative factor for classification of EVOO. However, PLS‐DA and HCA methods provided clear differentiation among the EVOO samples in terms of electronic nose and color measurements. This study is significant from the point of evaluating the potential of zNose? in combination with MVS as a rapid method for the classification of geographically different EVOO produced in industry.     

基于递推PLS核算法的软测量在线学习方法

针对过程的动态时变特性,提出一种基于PLS核算法的软测量在线学习方法。该方法利用PLS核算法,通过递推学习具有代表性的新样本来改善模型的适应能力,较NIPALS算法具有更高的计算效率;并采用一种同时考虑输入和输出信息的相似度准则,有选择地删除一个或多个冗余样本,更有效地构建了训练样本集。工业聚丙烯熔融指数的软测量建模研究表明,本文提出的方法能够快速有效地跟踪牌号切换中熔融指数的变化。