基于PSO-BP神经网络的山西省碳排放预测

山西作为能源使用和碳排放大省,推动“双碳”战略对全国具有重要示范意义。基于IPCC（政府间气候变化专门委员会）排放系数法测算山西省2000—2020年的碳排放量,运用Tapio脱钩模型分析碳排放与经济发展之间的脱钩关系,利用LMDI法对影响碳排放变化的因素进行分解,采用PSO-BP神经网络模型对山西省的碳排放量进行模拟和预测。结果表明：2000—2020年山西省碳排放量呈增长趋势,碳排放强度呈下降趋势,脱钩系数为0.585,整体处于弱脱钩状态。经济增长是碳排放量增长的决定因素,而产业结构与能源强度的优化调整是抑制碳排放的主导因素。引入PSO（粒子群优化算法）有效提高了BP神经网络的预测精度。预测结果显示,在基准情景、低碳情景和强化低碳情景下,山西省碳排放分别于2032年、2029年和2027年达峰。针对预测结果,提出了相关政策建议。

     

引信步进应力加速试验贮存寿命预测研究

目的 针对某机电引信加速寿命试验数据,采用传统统计分析方法存在计算量大、寿命预测精度难以保证的问题,开展与智能算法相结合的引信贮存寿命预测研究。方法 针对步进应力加速寿命试验数据,采用贝叶斯理论的环境因子法,对各级应力下的贮存时间进行折合计算。利用进化策略对粒子群算法进行改进,进而对所建立的BP神经网络预测模型的全局参数进行调整和优化,突破传统方法的局限。将折合后的试验时间、样本量、应力水平作为网络输入,失效数作为输出,来预测引信贮存寿命。结果 利用训练好的 BP神经网络预测引信在正常应力水平下的失效数,计算其贮存可靠度。在迭代402次后,模型找到最优解,且预测误差在1%以内。结论 步进应力加速寿命试验与智能算法相结合的方法计算过程简单,预测精度较高,可有效提高引信贮存寿命的预测精度。     

基于GIS的城市生活垃圾规划管理智能决策方法

对城市生活垃圾治理系统进行规划管理是克服治理过程中混乱不协调所带来的问题、提高治理决策有效性的根本方法.提出了基于GIS的城市生活垃圾规划管理智能决策方法.将"城市生活垃圾治理系统"的决策划分为3个层次,在此基础上构建总体规划方案,并将人工智能技术和GIS与总体规划中的模型相集成,给出了该方法的一般性决策模型,对该方法的决策过程和主要创新也进行了详细描述,为构建基于GIS的城市生活垃圾规划管理智能决策系统提供了依据.     

智力因素在城市生态环境中的作用

本文从城市生态学的角度出发，充实了城市生态环境系统以人为主体的观点，分析人的因素对城市生态的作用和影响，全面论述人与城市生态之间既适应又冲突的关系，强调人在城市生态调控中的主体作用，提出在城市生态化过程中，只有充分重视智力因素，加强智力建设，才能建设健康、财富和文明的社会，实现城市的可持续发展的观点。     

改进的粒子群算法及其在土坡临界滑动面搜索中的应用

首先,提出了一种新型的模拟任意滑动面的方法,该法能自动产生运动许可的滑动面。同时,针对基本粒子群优化算法存在计算量大的缺点,提出了一种改进的,即不连续飞行粒子群优化算法。利用Spencer法计算滑动面的安全系数,对几个复杂土坡的最小安全系数及其对应的滑动面进行了分析,并与国内外已有结果进行了比较,证明了改进粒子群优化算法和模拟滑动面的新方法是合理、有效的,可用于复杂优化问题的研究。     

Parametric study along with selection of optimal solutions in dry wire cut machining of cemented tungsten carbide (WC-Co)

This work deals with parametric study of dry wire EDM (WEDM) process of cemented tungsten carbide. Experiments have been conducted using air as dielectric medium to investigate effects of pulse on time, pulse off time, gap set voltage, discharge current and wire tension on cutting velocity (CV) surface roughness (SR) and oversize (OS). Firstly, a series of exploratory experiments were carried out to identify appropriate gas and its pressure. Afterward, preliminary experiments were conducted to investigate effects of process parameters on dry WEDM characteristics and find appropriate ranges for each factor. Then a central composite rotatable method was employed to design experiments based on response surface methodology (RSM). Empirical models were developed to create relationships between process factors and responses by considering to analysis of variances (ANOVA). To increase the predictability of the process, intelligent models have been developed based on back-propagation neural network (BPNN) and accuracy of these models was compared with mathematical models based on root mean square error (RMSE) and prediction error percent (PEP). In order to select optimal solutions in the cases of single-objective and multi-objectives optimization problems, optimization includes two main approaches. First approach was based on mathematical model and desirability function. Also second approach was designed based on neural network and particle swarm optimization. These approaches were applied in both cases of single-objective and multi-objectives optimization problems and their results were compared with together. Results indicated that selection of air at inlet pressure of 1.5 bar is really appropriate for conducting experiments of next stages. Also, the BPNN creates more accurate prediction rather than mathematical model. Moreover, the BPNN-PSO approach was more efficient in optimization of process rather than mathematical model-desirability function in respect with validation tests.     

草酸、壳聚糖与CaO联合调理对污泥脱水性能的影响

为提高剩余污泥脱水性能,本文采用单因素实验确定草酸、壳聚糖和CaO各因素的影响水平范围,基于响应曲面优化法建立了污泥滤饼含水率预测模型,通过粒子群算法计算污泥滤饼含水率预测模型,优化草酸、壳聚糖与CaO联合调理污泥脱水的最佳配比,并分析了污泥调理过程中胞外聚合物（EPS）的变化特性,深入解析了污泥脱水的关键机制.结果表明,草酸、壳聚糖与CaO联合调理污泥能明显提高污泥脱水性能,调理后的污泥滤饼含水率为64.017%,最佳投加量分别为0.377,0.029,0.040g/g;模型拟合度良好（R²=0.9651）,方差分析表明草酸对于污泥滤饼含水率的影响为主要因素;草酸投加量与溶解型EPS（SL-EPS）呈显著正相关关系,而与紧密型EPS（TB-EPS）呈显著负相关关系.该研究成果可为剩余污泥脱水性能的提高提供技术与方法参考.     

Organizing knowledge for tutoring fire loss prevention

The San Bernardino National Forest in southern California has recently developed a systematic approach to wildfire prevention planning. However, a comprehensive document or other mechanism for teaching this process to other prevention personnel does not exist. Anintelligent tutorial expert system is being constructed to provide a means for learning the process and to assist in the creation of specific prevention plans. An intelligent tutoring system (ITS) contains two types of knowledge—domain and tutoring. The domain knowledge for wildfire prevention is structured around several foci: (1) individual concepts used in prevention planning; (2) explicitly specified interrelationships between concepts; (3) deductive methods that contain subjective judgment normally unavailable to less-experienced users; (4) analytical models of fire behavior used for identification of hazard areas; (5) how-to guidance needed for performance of planning tasks; and (6) expository information that provides a rationale for planning steps and ideas. Combining analytical, procedure, inferential, conceptual, and expositional knowledge into a tutoring environment provides the student and/or user with a multiple perspective of the subject matter. Aconcept network provides a unifying framework for structuring and utilizing these diverse forms of prevention planning knowledge. This network structure borrows from and combines semantic networks and frame-based knowledge representations. The flexibility of this organization facilitates an effective synthesis and organization of multiple knowledge forms.     

灾后应急资源配送的LRP模型与算法研究

针对灾后应急资源配送的优化问题,考虑配送中心定位和配送路径方案的相互影响,建立应急资源配送的“定位-路径安排问题”优化模型,给出应急配送中心定位和配送可靠路径的全局优化方案。根据该模型的特点,设计多吸引子的离散粒子群优化算法,并结合仿真与分析,验证模型和算法的有效性。模型与算法的研究,对于突发事件下不确定交通路网应急资源配送决策具有一定指导意义。