Leak location of pipelines based on transient model and PSO-SVM

An improved and integrated approach of support vector machine and particle swarm optimization theory (PSO-SVM) is first used to detect the leak location of pipelines and overcome the problem of multiple leaks. The calibration and predictive ability of improved PSO-SVM is investigated and compared with that of other common method, back-propagation neural network (BPNN). Two conditions are evaluated. One with a leak involves a set of 20 samples, while another with two leaks has 127 samples. Both internal and external validations are performed to validate the performance of the resulting models. The results show that, for the two conditions, the values calculated by improved PSO-SVM are in good agreement with those simulated by transient model, and the performances of improved PSO-SVM models are superior to those of BPNN. This paper provides a new and effective method to inspect the multiple leak locations, and also reveals that improved PSO-SVM can be used as a powerful tool for studying the leak of pipeline.     

基于支持向量机的洪水灾情综合评价模型

在阐述支持向量机的基本原理、二值分类和多值分类技术及各自特性的基础上，结合洪水灾情综合评价中受自然环境、社会经济等诸多因素的影响且实测样本资料较少的特点，以及目前已有评价模型不能或难以解决的小样本、“过学习”、局部最小等实际难题，提出了基于支持向量机的洪水灾情综合评价模型，并应用实例进行了验证。研究结果表明，此模型和传统的灾情评估法、人工神经网络评价模型一样有效合理，并且模型运算时间比人工神经网络模型要短。因此，不仅为洪水灾情综合评估提供了一种新的模型，而且由于支持向量机遵循统计学习理论中结构风险最小化的原理，具有解决有限样本、非线性及高维识别中的优势，必将比其他传统的评价模型得到更广泛的应用和发展。〖     

选矿浮选电机烧坏原因分析

分析了浮选电机烧坏的原因,提出了防止电机烧坏的措施。     

烧结机烟气选择性脱硫技术的研发与应用

介绍了钢铁工业烧结烟气选择性脱硫技术及循环流化床半干法脱硫工艺的原理、系统运行效．果及在应用中存在的问题，并对其发展提出了建议。     

基于决策树支持向量机算法的船用设备故障诊断

目的 提高船用设备的智能化水平,增强船舶的安全性、可靠性,对船上设备进行状态监测,并基于监测数据对设备健康状况进行评估,对可能存在的故障工况进行识别.方法 通过采集机舱内的振动数据,对数据进行预处理、快速傅里叶变换,提取1/3倍频带特征,将倍频带谱信号作为特征向量,利用支持向量机算法进行模型训练及分类.对于船上多种工况及可能存在的多种故障类别,采用决策二叉树方法,提出一种快速、准确的状态监测及故障诊断策略.结果 在实验室工况下识别准确率接近100％.结论 该方法能够对船用设备进行状态监控、故障诊断、健康评估等提供支持,为设备检修、传感器布置等决策提供依据.     

烧结烟气中CO对SO2监测的干扰分析

通过承钢烧结机脱硫出口SO2的比对监测,发现在线及手持监测设备正常但监测数据仍比对不合格。进行CO干扰实验,得出CO对采用＂定电位电解法＂的手持SO2分析仪有正干扰,并得出了干扰系数。现场实地测试后,利用干扰系数对监测数据进行人工修正,对比结果合格。应用＂定点位电解法＂监测烧结机烟气中低浓度SO2时,应人工修正或加装剔除CO影响的元件。     

基于差异进化支持向量机的坑外土体沉降预测

就用支持向量机(SVM)预测基坑外土体沉降而言,通过差异进化(DE)算法构造适合的决策函数十分重要。在确定坑外土体沉降函数的基本形式下,进行参数反演。后将得到的解析式作为SVM的决策函数,再进行核函数转换,从而使SVM的曲线拟合更加快速,预测更加准确。对大连地铁湾家车站基坑坑外土体的沉降数据的分析及预测的结果表明,使用SVM-DE算法在计算数据量、计算消耗时间和预测精度方面优于2种方法单独使用。     

Comparison of Four Machine Learning Methods for Predicting PM10 Concentrations in Helsinki, Finland

Machine learning methods can offer a practicalalternative to deterministic and statistical methods forpredicting air pollution concentrations. However, for agiven data set, it is often not clear beforehand whichmachine learning method will yield the best predictionperformance. This study compares the variable selection andprediction performance of four machine-learning methods ofdifferent complexity: logistic regression, decision tree,multivariate adaptive regression splines and neuralnetwork. The methods are applied to the task of predictingthe exceedance of the European PM₁₀ daily averageobjective of 50 g m^-3 for a station in Helsinki,Finland. Our study shows that some predictors were selectedby all models but that the different models also pickeddifferent variables. The performance of three of the fourmethods investigated was very similar, however, performanceof the decision tree method was significantly inferior.Performance was sensitive to the learning sample size andtime period used.     

某卷烟厂卷接机组集中风力与除尘系统的应用

结合贵州某卷烟厂技术改造实践，采用集中工艺风力和除尘技术，对PASSIM和SUPER9卷接机组的工艺风力供给方式和除尘系统进行了改进。对于系统的结构、可靠性、调节性、稳定性进行了分析，改造后集中风力系统较常规风力系统在经济效益和工作环境上具有显著优势，降低了运行成本。     

Computer simulations help determine safe vertical boom speeds for roof bolting in underground coal mines

PROBLEM: Incident investigation reports do not usually contain enough information to aid in studying boom arm vertical speed for roof bolting machines to determine the impact that appendage speed had on an operator's risk of experiencing a contact. Laboratory experiments with human subjects are also not feasible because of safety and ethical issues. METHOD: Researchers successfully developed a three-dimensional computer model that uses virtual human simulation software as the primary means to gather contact data when the boom arm touches the operator's hand, arm, head, or leg. RESULTS: Data analysis of roof bolter simulations shows that the speed of the boom arm is the most important factor in determining the risk of an operator making contact. Regardless of other variables, contact incidents were always greater when the bolter arm was moving up, greater on the hand, and greater for the boom arm part of the machine. The reason why the subject experiences more contacts when the boom arm is moving up rather than down is that more risky behaviors occur during drilling and bolting when the boom arm is ascending. Based on the data collected, boom speeds greater than 13 in/sec result in a substantial increase in risk to the roof bolter operator of making contact. Speeds less than or equal to 13 in/sec are associated with a more modest relative risk of making contact, which represents a decrease in potential hazard. IMPACT ON INDUSTRY: The use of such information can be quite helpful in making recommendations to machine design and task procedures to reduce the likelihood that roof bolter operators will experience injury due to contact with a moving roof bolting machine's boom arm.