岩溶塌陷倾向性等级的KPCA-SVM预测模型

为了快速、有效地预测岩溶塌陷倾向性等级,在统计分析大量观测实例的基础上,选取岩性系数、岩体结构系数、地下水系数、覆盖层系数、地形地貌系数和环境条件系数作为特征指标。利用核主成分分析(KPCA)方法在高维空间提取岩溶塌陷影响因子的主成分,将获取的主成分作为支持向量机(SVM)的特征向量,建立基于KPCA的岩溶塌陷倾向性等级的SVM预测模型。将12组观测数据作为学习样本对模型进行训练。采用回代估计法进行回检,误判率为0。利用训练好的模型对2组待判样本进行预测。结果表明:经KPCA后指标个数减少,相关性降低,SVM运算的复杂度降低。用该模型所得预测结果的准确率为100%。     

Modelling and Prediction of Diesel Engine Performance using Relevance Vector Machine

Diesel engines are being increasingly adopted by many car manufacturers today, yet no exact mathematical diesel engine model exists due to its highly nonlinear nature. In the current literature, black-box identification has been widely used for diesel engine modelling and many artificial neural network (ANN) based models have been developed. However, ANN has many drawbacks such as multiple local minima, user burden on selection of optimal network structure, large training data size, and over-fitting risk. To overcome these drawbacks, this article proposes to apply an emerging machine learning technique, relevance vector machine (RVM), to model and predict the diesel engine performance. The property of global optimal solution of RVM allows the model to be trained using only a few experimental data sets. In this study, the inputs of the model are engine speed, load, and cooling water temperature, while the output parameters are the brake-specific fuel consumption and the amount of exhaust emissions like nitrogen oxides and carbon dioxide. Experimental results show that the model accuracy is satisfactory even the training data is scarce. Moreover, the model accuracy is compared with that using typical ANN. Evaluation results also show that RVM is superior to typical ANN approach.     

Prediction of effluent concentration in a wastewater treatment plant using machine learning models

Of growing amount of food waste, the integrated food waste and waste water treatment was regarded as one of the efficient modeling method. However, the load of food waste to the conventional waste treatment process might lead to the high concentration of total nitrogen(T-N) impact on the effluent water quality. The objective of this study is to establish two machine learning models—artificial neural networks(ANNs) and support vector machines(SVMs), in order to predict 1-day interval T-N concentration of effluent from a wastewater treatment plant in Ulsan, Korea. Daily water quality data and meteorological data were used and the performance of both models was evaluated in terms of the coefficient of determination(R~2), Nash–Sutcliff efficiency(NSE), relative efficiency criteria(d rel). Additionally, Latin-Hypercube one-factor-at-a-time(LH-OAT) and a pattern search algorithm were applied to sensitivity analysis and model parameter optimization, respectively. Results showed that both models could be effectively applied to the 1-day interval prediction of T-N concentration of effluent. SVM model showed a higher prediction accuracy in the training stage and similar result in the validation stage.However, the sensitivity analysis demonstrated that the ANN model was a superior model for 1-day interval T-N concentration prediction in terms of the cause-and-effect relationship between T-N concentration and modeling input values to integrated food waste and waste water treatment. This study suggested the efficient and robust nonlinear time-series modeling method for an early prediction of the water quality of integrated food waste and waste water treatment process.     

有机化学品不同温度下(过冷)液体蒸气压预测模型的建立与评价

(过冷)液体蒸气压(PL)是评价化学品在环境中分配、迁移和归趋行为的重要参数。PL具有较强的温度依附性。发展一种能够精确预测不同环境温度下化学品PL的方法,有助于填补化学品生态风险评估的大量数据缺失。本研究收集整理了661种有机化合物在不同温度下(200~830 K)共计10 478个log PL值。在此基础上,采用偏最小二乘(PLS)回归和支持向量机(SVM)方法,构建了PL的线性和非线性预测模型。结果表明:2种模型均具有良好的拟合度、稳健性及预测能力,SVM模型的预测性能略高于PLS模型(PLS:R2adj.tra=0.912,RMSEtra=0.477,Q2ext=0.910;SVM:R2adj.tra=0.997,RMSEtra=0.092,Q2ext=0.967)。机理分析表明,温度是影响PL的主要因素,温度越高,蒸气压越大;其次,X1sol也影响PL大小,X1sol用来描述分子间的色散作用,分子间色散力越小,蒸气压越大;此外,化合物的氢键个数、极性和分子构型等因素也影响PL大小。采用Wiliams plot方法表征了PLS模型应用域。所建立的模型可用来预测烷烃、烯烃、醇、酮、羧酸、苯、酚、联苯、卤代芳香烃、含N化合物及含S化合物在不同温度下的PL数据。     

基于分解模型与VEC模型的沈阳经济区经济与环境时空关系研究

选择GDP、工业废水排放量、工业废气排放量、工业废物产生量4个指标,从横向的空间作用关系及纵向的时间作用关系对沈阳经济区经济增长与环境演化关系进行了动态综合分析.对于空间作用关系,采用完全分解模型,利用沈阳经济区内8个城市的面板数据,将经济与环境关系分解为经济规模效应、空间结构效应和技术效应,判定了由于经济增长造成的工业废物排放的增减变化而带来的区域环境压力扰动程度.对于时间作用关系,选择协整与向量误差修正模型(VEC),依次对指标序列进行了单位根检验、VAR估计、Johansen协整检验及向量自回归的VEC修正,进而对沈阳经济区经济与环境指标前期与当期作用关系进行了长期修正与短期校正.结果表明:对于工业废物排放,技术效应发挥了最突出的减量作用,经济效应的增量效应凸显,而空间结构效应的作用不明显;GDP与工业废水排放量、工业废气排放量、工业废物产生量之间的作用关系均经历了由波动到平稳的过程,但在研究期内GDP与工业废水排放之间的稳定性相对较弱,保持GDP与工业废气排放、工业废物产生各自的均衡关系,对各变量的优化有促进作用,而保持GDP与工业废水排放的均衡关系,则对各变量的优化有抑制作用.     

基于支持向量机的湖泊生态系统健康评价研究

利用支持向量机在处理分类问题、小样本问题和泛化推广方面的优势,构建了基于支持向量机的湖泊生态系统健康评价模型.同时,对广州市最大的人工湖——白云湖的水质及生物群落情况进行了监测,最后运用该模型对白云湖生态系统健康状况进行了评价.评价结果表明,白云湖生态系统处于病态状态,不能达到其净化水质的设计作用.建议从提高进水水质、实施湖区截污和丰富生物量3方面改善白云湖生态系统健康水平.与传统熵权综合健康指数法和熵权模糊综合评价法相比,所建模型更加客观、科学地评价了湖泊生态系统健康状况,能够为湖泊生态系统健康管理提供一定依据,具有广阔的应用前景.     

泰安市冬季一次严重空气污染过程分析

为揭示泰安市空气污染形成原因,选取泰安市2016年12月一次严重空气污染过程,利用泰安市2016年12月地面和探空资料及NCEP/NCAR（美国国家环境预报中心/美国国家大气研究中心）提供的FNL资料,对泰安市严重污染期间大气环流形势、边界层条件、污染源及传输路径进行分析.结果表明:在泰安市霾污染期间,500 hPa大气环流形势呈"两槽一脊"的特征,850 hPa泰安市处于南支槽前,受西南暖湿气流影响,为ρ（PM_2.5）的升高提供了有利条件;泰安市近地面处于高压控制下的弱风区（平均风速约为1.2 m/s）且边界层有逆温层存在,阻碍了PM_2.5的垂直输送,造成近地面ρ（PM_2.5）急剧升高.此外,泰安市及周边地区污染严重,聚类分析结果表明此次过程本地输送占比约为34%,其余均为外来传输,即污染物主要通过外来源传输,本地污染源贡献比率较小.污染物的高、低空传输路径不一致,低空污染物主要从安徽省水平输送至泰安市,高空污染物则先由河北省、河南省向南传输至安徽省、湖北省等地,再随南风气流向北输送至泰安市.研究显示,外来污染源传输作用配合本地静稳天气形势是造成此次泰安市空气污染的主要原因.      

区域生态环境评价的灰色关联投影模型

区域生态环境评价是实现全面环境管理，协调区域经济发展与生态环境保护．实现区域可持续发展的重要手段。由于评价所涉及的地域复杂性和因素多样性，许多评价方法和体系都处于不断探索和发展之中。区域生态环境系统是一个灰色系统，包括了自然、经济和社会等方面具有信息不确知性和不完全性的因素。基于灰色系统理论和矢量投影原理，建立了区域生态环境评价的灰色关联投影模型。该模型将评价样本及各级质量标准视为矢量．分别向同一矢量(理想样本)进行投影。根据投影值的大小，确定样本所属的生态环境质量级别及样本间的优劣排序。以巢湖流域为个案，在建立生态环境评价指标体系和标准的基础上，运用所建模型对其生态环境质量现状进行了评价，结果与实际情况相吻合。即巢湖流域总体以及分区合肥市、六安市的生态环境质量为4级，分区巢湖市为5级。研究表明，灰色关联投影模型对于多指标的区域生态环境质量评价是科学的、有效的，具有一定的推广和实用价值。     

Pipeline leakage detection and isolation: An integrated approach of statistical and wavelet feature extraction with multi-layer perceptron neural network (MLPNN)

Leakage diagnosis of hydrocarbon pipelines can prevent environmental and financial losses. This work proposes a novel method that not only detects the occurrence of a leakage fault, but also suggests its location and severity. The OLGA software is employed to provide the pipeline inlet pressure and outlet flow rates as the training data for the Fault Detection and Isolation (FDI) system. The FDI system is comprised of a Multi-Layer Perceptron Neural Network (MLPNN) classifier with various feature extraction methods including the statistical techniques, wavelet transform, and a fusion of both methods. Once different leakage scenarios are considered and the preprocessing methods are done, the proposed FDI system is applied to a 20-km pipeline in southern Iran (Goldkari-Binak pipeline) and a promising severity and location detectability (a correct classification rate of 92%) and a low False Alarm Rate (FAR) were achieved.