基于critic组合预测方法的共享单车故障预测

针对无桩式共享单车系统缺少故障预测方法的研究及预测准确率低不稳定等问题,在挖掘预测因素和故障单车之间的信息特征上,提出改进熵权法对预测因素分权,并采用BP神经网络、径向基函数和ELMAN神经网络3种单一预测模型建立基于critic权重的组合预测模型,在Matlab上进行实例求解。结果表明,相比单一预测方法,该组合预测方法提高了预测准确率5%左右,且能够降低预测风险,减少预测的系统误差,具有较好的实用价值。     

基于结核病预测模型的比较研究

随随结核病预防体系的不断发展和完善,各种关于结核病各个方面的预测模型也不短兴起。预测对结核病的防治的重要性开始显现。针对在建立预测模型时不能准确判别使用合适的神经网络,归纳几种常用于预测的神经网络:ARIMA模型PSO算法预测模型、RBF神经网络、组合预测模型ARIMA-BPNN模型、ARIMA-GRNN模型,并总结相应的优缺点,及其适用的预测范围。通过对各种预测模型的预测结果进行比较分析。预测结果显示,用单一预测模型进行预测时,因自身的局限,使其预测精度和稳定性不高。而将两种或两种以上的预测模型进行组合预测更能有效提高预测精度,充分的降低预测风险,保证预测结果的稳定性。     

基于组合预测模型的铁路集装箱运量预测

为了克服单项预测模型的单一性和片面性等缺点,本文应用组合预测模型对铁路集装箱运量进行预测,以提高预测的准确性。通过对运量的历史数据分别采用多项式曲线模型和灰色预测模型建立单项预测模型,再利用径向基神经网络对两个单项预测模型的结果进行组合预测。研究结果表明,相比于两单项预测方法,组合预测方法所得运量的相对误差分别提高了3.19%和12.76%。最后,应用马尔科夫链模型对组合预测的结果进行分析和修正,增加预测结果的可靠性。     

基于GMDH—GM（1，N）的模型对工业增加值预测

工业增加值的准确预测对于政府部制定工业发展政策有重要的作用。本文分别建立了四川省工业增加值的GMDH模型和GM（1,N）模型,并把两者结合起来建立基于GMDH—GM（1,N）的组合预测模型。将组合预测的结果与实际值以及单一的GMDH模型、GM（1,N）模型的结果进行了分析和比较,实证分析结果表明组合预测模型能够提高预测精度,从而为宏观经济预测提供了参考。     

基于ARIMA-OSELM的火电厂SCR入口NOx浓度预测建模研究

针对火力发电厂燃烧系统运行工况复杂、迟延较大，导致选择性催化还原烟气脱硝系统(SCR)中入口NO_x质量浓度难以准确测量的问题，提出了一种基于ARIMA-OSELM神经网络组合模型的火电厂SCR入口NO_x浓度预测方法，分别从最优权重和残差优化2个组合角度进行对比研究。将该方法应用于某火力发电厂SCR入口浓度预测中，结果表明：基于ARIMA-OSELM残差优化的组合模型预测精度最高，其效果优于ARIMA-OSELM最优权重的组合预测模型以及单一ARIMA和OSELM神经网络预测模型，评价指标F_MAPE、M_RMSE和R²分别为0.190、1.364和0.978。     

区域物流需求预测方法比较分析

用组合预测法对区域物流需求进行预测,各单项预测方法组合前需进行有效性分析.定性分析后选择回归分析、灰色预测、指数平滑法,定量计算验证时以1991～2004年综合货运量的预测为例,求出三种单项预测方法的预测精度序列值及相对误差值,依据组合预测的有效性对计算结果进行比较分析,经计算本文最终选定回归分析、指数平滑和灰色模型作为非线性组合预测模型的输入方法.     

基于线性趋势与神经网络的校准间隔组合预测

为了实现对测量仪器校准间隔的优化,对其校准数据进行建模,用滑动平均建模法建立线性趋势模型,预测参数的总体趋势,在此基础上利用动态神经网络对预测残差序列进行补偿,从而得到校准数据的预测值。给出基于线性趋势与神经网络的组合预测模型,通过实验对预测模型进行了验证和对比分析,并以此为根据对校准间隔进行优化。结果表明,该组合模型比单一模型预测精度高,既能预测总体趋势也能适应随机波动,并且简单易行,具有较强的普适性。     

海水腐蚀速率的不等时距灰色模型与BP神经网络模型组合预测

金属在海水中的腐蚀机理及变化规律十分复杂,且采集腐蚀数据存在时间间隔不均匀、数据量小等问题,难以获取准确数据.基于灰色系统理论,提出运用能够适应具有无规律的采集时序数据的不等时距GM(1,1)模型对金属海水腐蚀速率进行建模,并引入了BP人工神经网络模型对预测结果进行残差修正,以提高预测精度.以A3钢与15MnMoVN钢腐蚀行为作为实例,进行预测和分析.结果显示:不等时距GM(1,1)与BP神经网络组合预测模型的预测效果明显优于单一预测模型,能更真实地反映海水腐蚀的变化趋势,因而具有较高应用价值.     

基于BP-RBF组合神经网络的废气监测盲区SO_2浓度预测

工业园区大气管理中,监测盲区的废气浓度分析是现有监测系统需要解决的难点问题.本文提出一种组合神经网络,利用已知监测点信息对监测盲区的废气浓度进行预测.首先,根据BP与RBF神经网络的特点,提出二者组合的神经网络结构;其次,分析监测盲区废气浓度预测问题,并提出基于BP-RBF组合网络的预测模型算法;最后,运用工业园区SO_2实际监测数据对所提组合网络预测方法进行实验验证.实验结果表明:本文所提BP-RBF组合网络预测方法具有良好的性能,适用于监测盲区废气浓度预测问题.     

基于CEEMDAN-SVM-LSTM的高炉煤气利用率组合预测

煤气利用率是高炉炉况稳定和耗能的重要指标之一。为提高煤气利用率的预测精度,提出一种基于CEEMDAN-SVM-LSTM的组合模型对其进行预测。首先利用CEEMDAN(自适应噪声完备集合经验模态分解)将煤气利用率时间序列分解成6个模态量和一个趋势分量,对煤气流利用率的发展进行解耦;然后用LSTM(长短时间记忆人工神经网络)和SVM(支持向量机)分别对分解的高频模态和低频模态进行预测,最后将模型组合建立原始煤气利用率的组合预测模型。结果表明该组合模型的MAE(平均绝对误差)、MAPE(平均绝对百分比误差)、RMSE(均方根误差)和MSE(均方误差)分别为0.14、3.5%、0.18、0.032。与单一的SVM模型和LSTM预测模型对比,组合模型的精度更高。     

An innovative air-conditioning load forecasting model based on RBF neural network and combined residual error correction

Accurate air-conditioning load forecasting is the precondition for the optimal control and energy saving operation of HVAC systems. They have developed many forecasting methods, such as multiple linear regression (MLR), autoregressive integrated moving average (ARIMA), grey model (GM) and artificial neural network (ANN), in the field of air-conditioning load prediction. However, none of them has enough accuracy to satisfy the practical demand. On the basis of these models existed, a novel forecasting method, called ‘RBF neural network (RBFNN) with combined residual error correction’, is developed in this paper. The new model adopts the advanced algorithm of neural network based on radial basis functions for the air-conditioning load forecasting, and uses the combined forecasting model, which is the combination of MLR, ARIMA and GM, to estimate the residual errors and correct the ultimate foresting results. A study case indicates that RBFNN with combined residual error correction has a much better forecasting accuracy than RBFNN itself and RBFNN with single-model correction.     

A combined usage of stochastic and quantitative risk assessment methods in the worksites: Application on an electric power provider

An individual method cannot build either a realistic forecasting model or a risk assessment process in the worksites, and future perspectives should focus on the combined forecasting/estimation approach. The main purpose of this paper is to gain insight into a risk prediction and estimation methodological framework, using the combination of three different methods, including the proportional quantitative-risk-assessment technique (PRAT), the time-series stochastic process (TSP), and the method of estimating the societal-risk (SRE) by F-N curves. In order to prove the usefulness of the combined usage of stochastic and quantitative risk assessment methods, an application on an electric power provider industry is presented to, using empirical data.     

疲劳裂纹扩展预测模型及其应用

在分析了灰色预测方法和支持向量机各自的优缺点基础上,提出了将二者相结合的一种新的预测模型———灰色支持向量机裂纹扩展预测模型.新模型发挥了灰色预测方法中"累加生成"的优点,弱化了原始序列中随机扰动因素的影响,增强了数据的规律性,同时避免了灰色预测方法及模型存在的理论缺陷.工程实例表明,文章所提出的裂纹扩展预测模型较传统的GM(1,1)模型、等维GM(1,1)模型精度都有所提高,为预测疲劳裂纹扩展提供了一种新的方法.     

组合模型对我国软件人才预测的应用实例

随着软件行业的快速发展,软件人才已经成为该行业重要的战略资源.研究目的便是通过对软件人才预测进行研究,使政府部门以及软件企业更好地了解和管理软件人才.根据人才预测的特点,引用灰色GM(1,1)模型预测法和线性回归预测法,利用组合模型技术建立了需求预测综合模型.应用此模型对我国未来5年软件人才需求进行了预测.     

Application of an EWMA combining technique to the prediction of currency exchange rates

Financial forecasting is an important and challenging task for both academic researchers and business practitioners. The recent trend to improve the prediction accuracy is to combine individual forecasts using a simple average or weighted average where the weight reflects the inverse of the prediction error. In the existing combining methods, however, the errors between actual and predicted values are equally reflected in the weights regardless of the time order in a forecasting horizon. In this paper, we propose a new approach where the forecasting results of Generalized AutoRegressive Conditional Heteroskedastic (GARCH), neural network, and random walk models are combined based on a weight that reflects the inverse of the exponentially weighted moving average of the Mean Absolute Percentage Error (MAPE) of each individual prediction model. The results of an empirical study indicate that the proposed method has a better accuracy than the GARCH, neural network, and random walk models, and also combining methods based on using the MAPE for the weight.     

物资招标采购中组合预测的线性规划方法

结合企业在物资招标采购中大批量订货时,对物资采购量的供应商合理分配及采购费用问题,利用灰色预测法、自适应滤波法及线性回归预测法进行组合预测确定物资采购量,运用层次分析法确定供应商相应权重的基础上建立线性规划模型,力图达到采购的合理分配和采购费用最低的目的.因此,对于解决企业大批量物资采购招标中供应商的合理分配及供应量的确定,以达到企业采购成本最小化的问题,提出了一种有效的方法.     

Deep learning with long short-term memory networks and random forests for demand forecasting in multi-channel retail

This paper proposes a novel forecasting method that combines the deep learning method – long short-term memory (LSTM) networks and random forest (RF). The proposed method can model complex relationships of both temporal and regression type which gives it an edge in accuracy over other forecasting methods. We evaluated the new method on a real-world multivariate dataset from a multi-channel retailer. We benchmark the forecasting performance of the new proposition against neural networks, multiple regression, ARIMAX, LSTM networks, and RF. We employed forecasting performance metrics to measure bias, accuracy, and variance, and the empirical evidence suggests that the new proposition is (statistically) significantly better. Furthermore, our method ranks the explanatory variables in terms of their relative importance. The empirical evaluations are replicated for longer forecasting horizons, and online and offline channels and the same conclusions hold; thus, advocating for the robustness of our forecasting proposition as well as the suitability in multi-channel retail demand forecasting.     

智能预报模式与水文中长期智能预报方法

建立了以模糊优选、BP神经网络及遗传算法有机结合的智能预报模式与方法。在应用该方法进行中长期水文智能预报时，首先选取训练样本的数量，根据预报因子与预报对象的相关关系得到相对隶属度矩阵;再将其作为BP神经网络输入值以训练连接权重；最后将得到的连接权重值用于预报检验。计算结果表明，智能预报模式与方法的运行速度、精度及稳定性都达到了实际应用的要求。     

Matching of technological forecasting technique to a technology using fuzzy multi-attribute decision-making methods: Case study from the aerospace industry

Given the accelerating pace of technological advances and environmental changes, technology-based companies are required to predict and understand future events in their environments. However, there is a wide range of forecasting methods creating confusion on which method to use. This paper demonstrates the selection of an appropriate technique for technology forecasting in the Iran Aviation Industries Organization (IAIO). To this end, a review of the literature was first reviewed to extract the proper criteria for selecting a forecasting method. Next, the SWARA and fuzzy MUTLIMOORA methods were used to evaluate and prioritize a total of twelve forecasting methods proposed for the case study. The results suggested that the Delphi method for technology forecasting in the IAIO. Scenario writing and the relevance tree are the next proper alternatives that can be used.     

试论工程爆破中的安全评估

本文结合工程爆破中安全评估工作的实践经验，分析讨论了工程爆破中安全评估的方法、组织形式、步骤、要求及注意事项，从而揭示了工程爆破中安全评估的重要性、必要性和科学性。