Application of fuzzy analytic hierarchy process and neural network in power transformer risk assessment

In operation,risk arising from power transformer faults is of much uncertainty and complicacy.To timely and objectively control the risks,a transformer risk assessment method based on fuzzy analytic hierarchy process(FAHP) and artificial neural network(ANN) from the perspective of accuracy and quickness is proposed.An analytic hierarchy process model for the transformer risk assessment is built by analysis of the risk factors affecting the transformer risk level and the weight relation of each risk factor in transformer risk calculation is analyzed by application of fuzzy consistency judgment matrix;with utilization of adaptive ability and nonlinear mapping ability of the ANN,the risk factors with large weights are used as input of neutral network,and thus intelligent quantitative assessment of transformer risk is realized.The simulation result shows that the proposed method increases the speed and accuracy of the risk assessment and can provide feasible decision basis for the transformer risk management and maintenance decisions.

Using analytic network process to analyze problems for implementing turn-key construction projects in Taiwan

The turn-key construction project is implemented in Taiwan not by a single company but by a make-shift group of several companies. Hence,problems to coordinate the professional construction management (PCM) and the supervising architectural company often occur for the lack of long-term experience to work together. The various factors that affect the implementation of turn-key projects currently practiced in Taiwan are analyzed using the analytic network process (ANP). The objective is to study how the twelve key factors in the four layers of "Role assignment","Signing contract","Operational procedures" and "Losing capital investment" affect the progress of implementing the turn-key project in Taiwan. The results reveal that "Delay in payment" has the most negative influence with 15.62% weighing factor; "Latent risk" comes next with 11.14% weighing factor,and "Responsibility of construction company for project quality" is the third with 10.79% weighing factor.

Using Extension Theory and Fuzzy Analytic Hierarchy Process on Heterogeneous Wireless Network Selection Algorithm

In order to solve the problem that determining decision factors weights is of subjectivity in heterogeneous wireless network selection algorithm, a network selection algorithm based on extension theory and fuzzy analytic hierarchy process (FAHP) is proposed in this paper. In addition, user and operator codetermine the optimal network using the proposed algorithm, which can give consideration to user and operator benefits. The fuzzy judgment matrix is constructed by membership degree of decision factors which is calculated according to extension theory. The comprehensive weight of each decision factor is obtained using FAHP. Finally, the optimal network is selected through total property value ranking of each candidate network under user preference and operator preference. The simulation results show that the proposed algorithm can select the optimal network efficiently and accurately, satisfy user preference, and implement load balance between networks.

Concurrent Material Selection of Natural Fibre Filament for Fused Deposition Modeling Using Integration of Analytic Hierarchy Process/Analytic Network Process

The employment of natural fibres in fused deposition modeling has raised much attention from researchers in finding a suitable formulation for the natural fibre composite filaments.Moreover,selection of suitable natural fibres for fused deposition modeling should be performed before the development of the composites.It could not be performed without identifying selection criteria that comprehend both materials and fused deposition modeling process requirements.Therefore,in this study,integration of the Analytic Hierarchy Process(AHP)/Analytic Network Process(ANP)has been introduced in selecting the natural fibres based in different clusters of selection concurrently.The selection process has been performed based on the interdependency among the selection criteria.Pairwise comparison matrices are constructed based on AHP’s hierarchical model and super matrices are constructed based on the ANP’s network model.As a result,flax fibre has ranked at the top of the selection by scored 19.5%from the overall evaluation.Flax fibre has excellent material properties and been found in various natural fibre composite applications.Further investigation is needed to study the compatibility of this fibre to be reinforced with a thermoplastic polymer matrix to develop a resultant natural fibre composite filament for fused deposition modeling.

The Selection of Dry Port Location by Analytic Network Process Model: A Case Study of Dosso-Niger

The aim of this paper is to select the best location for the construction of a dry port in Niger which is a land locked country (LLC). Niger is located in the Sahel and has a land area of 1,267,000 square kilometers [1], with the closest port being port of Cotonou in Benin. The transport corridor from Niamey to Cotonou is approximately 1036 km long [2]. It is estimated that this corridor carries about 40 percent of Niger’s overseas trade traffic [3]. In this work, the Analytic Network Process (ANP) model is used to determine the optimal location of the dry port, among three major cities: Niamey (capital city), Dosso and Gaya. From the application of this selection model, Dosso was selected as the best location for the location of the dry port, while Gaya and Niamey were placed second and third respectively. The results obtained in this work strongly confirm the decision of the government of Niger to construct a dry port in Dosso, a project that commenced in 2010 and is still in progress.

IoT data analytic algorithms on edge-cloud infrastructure:A review

The adoption of Internet of Things(IoT)sensing devices is growing rapidly due to their ability to provide realtime services.However,it is constrained by limited data storage and processing power.It offloads its massive data stream to edge devices and the cloud for adequate storage and processing.This further leads to the challenges of data outliers,data redundancies,and cloud resource load balancing that would affect the execution and outcome of data streams.This paper presents a review of existing analytics algorithms deployed on IoT-enabled edge cloud infrastructure that resolved the challenges of data outliers,data redundancies,and cloud resource load balancing.The review highlights the problems solved,the results,the weaknesses of the existing algorithms,and the physical and virtual cloud storage servers for resource load balancing.In addition,it discusses the adoption of network protocols that govern the interaction between the three-layer architecture of IoT sensing devices enabled edge cloud and its prevailing challenges.A total of 72 algorithms covering the categories of classification,regression,clustering,deep learning,and optimization have been reviewed.The classification approach has been widely adopted to solve the problem of redundant data,while clustering and optimization approaches are more used for outlier detection and cloud resource allocation.

Visual analytics tool for the interpretation of hidden states in recurrent neural networks

In this paper,we introduce a visual analytics approach aimed at helping machine learning experts analyze the hidden states of layers in recurrent neural networks.Our technique allows the user to interactively inspect how hidden states store and process information throughout the feeding of an input sequence into the network.The technique can help answer questions,such as which parts of the input data have a higher impact on the prediction and how the model correlates each hidden state configuration with a certain output.Our visual analytics approach comprises several components:First,our input visualization shows the input sequence and how it relates to the output(using color coding).In addition,hidden states are visualized through a nonlinear projection into a 2-D visualization space using t-distributed stochastic neighbor embedding to understand the shape of the space of the hidden states.Trajectories are also employed to show the details of the evolution of the hidden state configurations.Finally,a time-multi-class heatmap matrix visualizes the evolution of the expected predictions for multi-class classifiers,and a histogram indicates the distances between the hidden states within the original space.The different visualizations are shown simultaneously in multiple views and support brushing-and-linking to facilitate the analysis of the classifications and debugging for misclassified input sequences.To demonstrate the capability of our approach,we discuss two typical use cases for long short-term memory models applied to two widely used natural language processing datasets.

Analytical solutions for the slow neutron capture process of heavy element nucleosynthesis

In this paper, the network equation for the slow neutron capture process （s-process） of heavy element nucleosynthesis is investigated. Dividing the s-process network reaction chains into two standard forms and using the technique of matrix decomposition, a group of analytical solutions for the network equation are obtained. With the analytical solutions, a calculation for heavy element abundance of the solar system is carried out and the results are in good agreement with the astrophysical measurements.

正交实验结合AHP和GA-BP神经网络优化益黄散醇提工艺

目的 优化益黄散的醇提工艺。方法 采用回流提取法,以乙醇体积分数、液料比、提取时间为考察因素设计正交实验,以橙皮苷、川陈皮素、橘皮素、没食子酸、诃黎勒酸、诃子酸、甘草苷、甘草酸、丁香酚含量和干浸膏得率为指标,采用层次分析法(AHP)进行赋权并计算综合评分。通过验证正交实验和遗传算法(GA)-反向传播神经网络(BP神经网络)所预测的结果确定益黄散最佳醇提工艺参数。结果 正交实验优选的最佳醇提工艺参数为乙醇体积分数60%、液料比14∶1(mL/g)、提取时间90 min、提取2次,验证所得综合评分为79.19分;GA-BP神经网络优选的最佳醇提工艺参数为乙醇体积分数65%、液料比14∶1(mL/g)、提取时间60 min、提取2次,验证所得综合评分为85.30分,高于正交实验所得结果。结论 采用正交实验结合GA-BP神经网络的寻优方法较传统的正交实验寻优方法效果更佳,其优选出的益黄散最佳醇提工艺稳定可靠。

基于GA-BP神经网络的多层多道焊工艺预测及优化

针对目前多层多道焊工艺参数的选择问题,利用遗传算法(genetic algorithm, GA)对BP神经网络(back propagation neural network, BPNN)进行优化,提出多层多道焊成形预测及焊接工艺参数优化方法,旨在为工艺参数选取提供有效指导,提高焊接生产效率及焊接质量.首先通过分析多层多道焊图像,提出采用三次样条插值法与自适应分段法进行特征点识别,然后根据焊接顺序、焊道工艺建立焊接过程各焊道横截面积形状预测模型,运用解析法进行焊接工艺参数预测,进一步结合不同焊道工艺参数优选原则,采用改进神经网络进行焊接工艺参数优化,从而建立具有实时性的焊接工艺参数与焊缝轮廓关系模型.结果表明,该方法对多层多道焊中各焊道焊接工艺参数提供有效预测,试验结果满足实际需求,对提高焊接产品质量、简化焊接工艺参数选取具有实际意义.

海南省波浪能开发智能化适宜性分析模型研究

针对目前波浪能开发适宜性分析方法存在的问题及工作量大、成本高的特点,基于地理信息系统(Geographic information system, GIS)、改进的多准则决策方法(Multi-criteria decision making, MCDM)和人工神经网络(Artificial neural network, ANN)提出海南省波浪能开发智能化适宜性分析模型。对于该模型:首先,使用模糊层次分析(Fuzzy analytic hierarchy process, FAHP)法计算评价指标权重,降低专家主观偏差,更好地描述信息的不确定性;其次,提出灰色关联分析-折衷优化(Grey relation analysis-vlse kriterijumska optimizacijaⅠkompromisno resenje, GRA-VIKOR)法计算开发适宜性指数,解决评价过程中部分信息丢失、评价结果不准确的问题;最后依托反向传播(Back propagation, BP)神经网络进行模型训练并进行验证,实现海南省波浪能开发适宜性分析的智能化,不仅提高工作效率,而且降低计算成本。通过模型得到海南省波浪能可开发区域和开发适宜性等级,为海南省波浪能选址决策奠定基础,同时可填补海南省波浪能开发适宜性分析在智能化领域的空白。

双循环背景下石化企业供应链韧性评价研究——基于AHP-BP方法

随着环境不确定性的提高,中国石化企业供应链稳定性需求日渐攀升,供应链韧性评价已经成为判断石化企业风险应对能力的重要手段。基于双循环背景,通过构建石化企业供应链韧性评估指标体系,利用层次分析法和BP神经网络,对石化企业供应链韧性强度进行评估,确定了供应链韧性水平。结果表明,各石化企业的供应链韧性强度存在较大差异,供应链韧性整体水平偏低。在研究结果的基础上,对韧性供应链锻造提出了切实可行的建议。

基于组合赋权云模型的塔台管制系统运行安全评估

随着我国民航业的迅猛发展,空中交通流量不断攀升,机场塔台管制系统的运行安全面临严峻考验,因此,正确识别和评估风险成为有效提高塔台管制系统运行安全水平的重要前提。为精准且有效地完成对塔台管制系统运行的安全评估,构建了基于模糊决策实验室分析法(Decision-Making Trial and Evaluation Laboratory,DEMATEL)网络层次分析法(Analytic Network Process,ANP)熵权法云模型的塔台管制系统运行安全评估模型。首先,通过流程图法并结合人机环管的思想建立塔台管制系统运行安全评估指标体系,并采用模糊DEMATEL法确定评估指标间的相互影响关系,绘制评估指标之间的网络结构图;然后,通过ANP法确定各评估指标的主观权重,采用熵权法确定各评估指标的客观权重,并通过博弈论方法计算评估指标的综合权重;最后,将权重结果与评语层云模型结合使用对各级安全评估指标进行安全评估,通过MATLAB软件完成算例的仿真分析。结果表明:该塔台管制系统运行安全等级在一般和良好之间,仍需采取有效措施对某些风险因素进行控制;同时验证了该模型在塔台管制系统运行安全评估中具有可行性和准确性,对塔台管制系统安全评估具有指导意义。

鲁南地区流体监测台网优化与监测效能评估

结合鲁南地区地质构造背景,通过自主研发的高精度水位水温实时监测仪器,对地下流体监测站点软硬件设施进行升级改造,建设鲁南地区地下流体数字化监测台网。同时,构建基于层次分析法的鲁南地区地下流体监测效能评价体系,利用模糊综合评价法对各观测站点进行量化的效能评估,为进一步提升该地区地下流体监测台网监测能力提供参考意见。

基于概率神经网络和层次分析法的硐室群施工风险评估

地下硐室群施工风险研究尚处于起步阶段,为快速准确评判风险因素,预防施工安全事故,利用概率神经网络(PNN)和层次分析法(AHP)建立风险评估模型,并研发硐室群施工风险评估软件。通过统计分析硐室群施工风险因素,设置工程地质、自然、设计施工和管理4个一级风险因素,23个风险控制指标,建立针对硐室群施工的风险指标体系。收集典型样本数据后,基于PNN对施工风险等级进行评判,同时采用AHP定量分析风险因素权重,迅速捕捉风险点,采取风险控制措施并优化施工方案。运用研发软件对重庆轨道交通18号线歇台子站硐室群施工进行风险评价,得到风险概率等级为Ⅳ,在施工过程中需要重点监测和控制地下水、围岩等级和支护及时性等带来的影响,实例评价结果与现场情况相吻合,验证了该评估软件的有效性和实用性。研究表明:针对硐室群施工建立的指标体系和评估方法能有效预测风险级别,实时指导施工过程,确保地下硐室群施工安全。

基于BN-AHP的装甲车辆动力系统故障状态评估

装甲车辆复杂传统部件的损伤能否及时被发现,这关系到整车战备或作战能力,系统的故障状态评估是至关重要的。将贝叶斯网络模型结合云模型理论,建立云贝叶斯网络模型,针对4个不同工况的装甲车辆进行故障状态评估。在获取贝叶斯网络初始节点时更多是依靠专家经验,往往会带来很大的误差,导致条件概率偏差过大,采用证据理论/层次分析法来优化专家经验,确定各个节点的条件概率;将层次分析法转化所得的条件概率值代入到云贝叶斯网络模型中,经过计算可以得到不同损毁等级的概率。将云贝叶斯网络模型计算结果与其他状态评估方法结果进行对比分析,结果表明,所采用的计算方法较其他方法在可靠性和准确性方面有所提高。

基于Box-Behnken响应面法与BP神经网络优化雪莲药渣化学成分提取工艺

目的 优化雪莲药渣提取工艺。方法 在测得提取液中绿原酸、芦丁和多糖含量的基础上采用层次分析法(AHP)赋权得到综合评分。以料液比、提取时间和提取次数为考察因素,以综合评分为优选指标,运用Box-Behnken响应面设计和BP神经网络优化雪莲药渣化学成分的提取工艺。结果 Box-Behnken响应面法优化的提取工艺为加9倍量水回流提取3次,每次提取42 min。选择响应面试验中的17组数据作为训练数据和验证数据,BP神经网络预测的优选的提取工艺为加6倍量水回流提取3次,每次煎煮30 min。验证试验结果表明,BP神经网络优化工艺实际综合评分高于响应面法实际综合评分,提示BP神经网络预测的优选的提取工艺更为合理。结论 BP神经网络预测的优选的提取工艺合理、稳定、可行,可为雪莲药渣的二次开发利用提供参考。

基于改进LSTM神经网络的电动汽车充电负荷预测

当前对电动汽车(EV)充电负荷预测的研究缺少真实的数据支撑,并且模型考虑场景过于简单,影响因素考虑不到位,预测结果缺乏说服力。基于此,提出一种考虑多种电动汽车充电负荷影响因素的电动汽车充电负荷预测方法。首先,考虑天气、季节、温度、工作日、节假日等因素对电动汽车充电负荷的影响,采用三标度层次分析法分析各影响因素权重;其次,建立LSTM神经网络预测模型,通过真实数据训练得到用于预测的LSTM神经网络模型,结合影响因素权重分析结果对预测模型进行修正,得到最终的改进LSTM神经网络负荷预测模型;最后,采用常州某小区的真实数据对所提预测方法进行试验验证。结果表明,所提方法可以实现电动汽车充电负荷的精确预测,且负荷预测结果可为有序充电策略研究提供参考。

社交网络用户属性的隐私度量与决策分析方法

提出一种基于模糊层次分析和逼近理想解排序法的隐私决策优化方法,为用户在社交网络场景中实施隐私决策时提供可靠的隐私建议。首先,将社交属性的敏感度、独特性效用和普遍性效用作为价值评价指标,给出相应的量化方法,评价指标的权重计算过程是根据评价指标重要性的评价规则,采用模糊层次分析法构造模糊判断矩阵。然后,采用逼近理想解排序法对社交属性进行综合评估分析和排序,通过实验分析比较3种评价规则的个性化评估结果,实验结果表明该方法在满足个性化隐私需求的前提下能指导用户优化个人信息配置。