Multiple attribute decision making (MADM) problems often consist of various types of quantitative and qualitative attributes. Quantitative attributes can be assessed by accurate numerical values, interval values or fuzzy numbers, while qualitative attributes can be evaluated by belief distributions, linguistic variables or intuitionistic fuzzy sets. However, the determination of attribute weights is still an open issue in MADM problems until now. In the traditional objective weight assignment method, attributes are usually assessed by accurate values. In this paper, an entropy weight assignment method is proposed to dealing with the situation where the assessment of attributes can contain uncertainties, e.g., interval values, or contain both uncertainties and incompleteness, e.g., belief distributions. The advantage of the proposed method lies in that uncertainties and incompleteness contained in the interval numerical values or belief distributions can be preserved in the generated weights. Specifically, several pairs of programming models to generate the weights of attributes are constructed in three different circumstances: (1) quantitative attribute expressed by interval values; (2) incomplete belief distribution with accurate belief degrees; and (3) belief distribution constituted by interval belief degrees. The evidential reasoning approach is then utilized to aggregate the distributions of attributes based on the generated attribute weights. The normalized interval weight vector is defined, and the characteristics of the weight assignment method are discussed. The proposed method has been experimented with real data to illustrate its advantages and the potential in supporting MADM with uncertain and incomplete information. (C) 2019 Elsevier B.V. All rights reserved.

A novel convolutional neural network namely the modified CNN-GAP model is proposed for fast fault diagnosis of the DC-DC inverter. This method improves the model structure of the traditional CNN by using a global average pooling layer to replace the fully connected layer of 23 layers. The improved CNN-GAP method mainly contains an input layer, a feature extraction layer, a global average pooling (GAP) layer, and a Softmax output layer. Firstly, the raw 1-D time-series data directly input into the input layer of the established CNN-GAP diagnosis model. The 2-D feature maps are reconstructed in the input layer. Secondly, the representative features are automatically extracted from the 2-D feature maps by using multiple convolutional layers and pooling layers. Thirdly, the dimension transformation and size compression of the output image of the feature extraction layer is completed by the GAP layer. Finally, the fault diagnosis result of the DC-DC inverter is automatically output in the Softmax output layer. The proposed method is used for diagnosing the open-circuit fault of the IGBT in the isolated DC-DC inverter. The proposed method is more accurate and effective than other mainstream intelligent diagnosis methods including the SVM, KNN, DNN, and traditional CNN. The experiment results show that the diagnostic accuracy is up to 99.95%, and the testing time can reduce by more than 15%. The improved CNN-GAP method could greatly reduce the model parameter quantity of the traditional CNN more than 80%, which is more suitable for rapid fault diagnosis in electronic devices. © 2013 IEEE.

Remanufacturing has become one of the most important research topics in the manufacturing industry as it can effectively save costs, reduce environmental pollution and extend the lifecycle of products. The correct selection of remanufacturing mode is the key for enterprise. Previous studies usually constructed game models from the dynamic changes of single influencing factors, which may ignore the influence of interests among decision makers (DMs) and DMs' non-cooperative behavior under group decision-making circumstances. The non-cooperative behavior processing method that comprehensively considers multiple-attribute and group consensus to help enterprise to select the correct remanufacturing mode is a subject worthy of study. In this paper, we first propose the concept of fuzzy distributed preference relation. It combines the fuzzy set theory and DPR, which is more suitable to express fuzzy and uncertain assessments in complex decision situations. Then, a consensus reaching model to analyze non-cooperative behaviors is proposed. The non-cooperative degrees on attribute, alternative and individual levels are constructed to identify and manage non-cooperative behaviors of DMs. Thirdly, DM's reliability measurement method is proposed based on the consensus reaching model, and a suitable decision support procedure of remanufacturing mode selection is constructed. Finally, a case study of remanufacturing mode selection is provided to illustrate the effectiveness and validity of the proposed method.

Marine high-end equipment reflects a country's comprehensive national strength. The safety assessment of it is very important to avoid accident either from human or facility factors. Attribute structure and assessment approach are two key points in the safety assessment of marine high-end equipment. In this paper, we construct a hierarchical attribute structure based on literature review and text mining of reports and news. The hierarchical attribute structure includes human, equipment, environment and management level. The correlations among these attributes are analyzed. The assessment standards of attributes are described in details. Different evaluation grades associated with attributes are transformed to a unified one by the given rules. As for the assessment approach, the evidential reasoning approach is applied for uncertain information fusion. Group analytical hierarchical process is used to generate attribute weights from a group of experts, where process aggregation method and result aggregation method are combined in a comprehensive way. The importance of expert is computed by the uncertainty measure of expert's subjective judgment. A drilling platform is finally assessed by the proposed attribute structure and assessment approach to illustrate the effectiveness of the assessment framework. © 2024 - IOS Press. All rights reserved.

The different preferences of experts in fuzzy group decision-making problems will lead to conflict, which hinders the reaching of consensus. In present conflict management techniques, local conflict among individual experts or the overall level of conflict is often concerned. This paper deals with conflict relations by opinion dynamics to resolve the whole and local conflicts among experts. This paper proposes a conflict resolution method based on opinion dynamics, which mainly includes three parts: (1) trust propagation: taking the consistency index into account in the propagation of trust, aiming at making as objective an assessment as possible of the competence and social status of experts; (2) conflict detection and elimination: reducing conflicts to an acceptable level through multiple rounds of preference adjustment according to the harmony degree; (3) alternatives selection: proposing a scoring function combining extent superiority with number superiority to score and rank the alternatives. Finally, a numerical example is given to illustrate the feasibility of the proposed method. © 2024 Elsevier Ltd

The cylinder liner-piston ring (CL-PR) that worked under harsh conditions is extremely susceptible to wear, and its friction loss is the primary source of mechanical loss of engines, affecting its equipment reliability and energy consumption. Recently, the use of low sulfur fuel oils (LSFO) aggravated the wear of the CL-PR, further increasing friction loss. Furthermore, the emissions of diesel engines also affect the environment and human health. In this study, the graphene-attapulgite (G-ATP) additive was prepared and applied to engines in response to these challenges. The prepared G-ATP additive was dispersed into 5040 lubricating oil with a 0.25 wt% concentration, then the effects of the additive on engines were investigated under hot test conditions with a speed of 1750 rpm. It was found that the G-ATP additive displayed excellent tribological properties, the wear mass loss of the piston ring was reduced by 64.5% with the addition of the G-ATP additive, and the wear of the cylinder liner was significantly reduced. Meanwhile, owing to the excellent tribological properties and thermal conductivity of the G-ATP additive, the HC and NOx emissions of the engine were reduced by 3.0% and 6.1%, respectively. Additionally, the vibration performances of the engine were improved by 42.1% in the final stage. These findings revealed the potential mechanism of the G-ATP additive for performance enhancements of diesel engines, as well as the relationships between the emission and vibration of engines and tribological properties of CL-PRs, which promote the energy saving and emission reduction of engines. © 2023 Elsevier Ltd

针对深度学习面对不平衡训练数据时所面临的故障特征提取不准确、诊断效果较差的问题，提出了一种新的柴油机故障诊断方法。该方法将集成学习理论与深度置信网络相结合。具体而言，首先采用Adaboost-M2算法作为集成学习生成方法，然后使用麻雀搜索算法确定不同终止适应度下的不同初始化超参数分布的深度置信网络模型。最终将上述不同的深度置信网络模型作为基分类器进行集成学习，得到集成Ada-DBN模型。此外，实验分析了分类器数量对集成学习后的模型诊断性能的影响。实验结果表明，集成Ada-DBN模型不仅能够保证在平衡数据下的诊断能力，还能提高在不平衡数据下的泛化能力，是一种适用于实际柴油机故障诊断的有效方法。

Large-scale group decision making (LSGDM) is very common in real world, and especially how to reach a relatively consensus status in a social network is a hot topic. In this paper, we propose a concept of two-tuple linguistic trust/distrust relationship (LTR) which could present both trust and distrust degrees by semantics. The trust/distrust representation scheme can unburden individuals from providing numerical trust or distrust degree to just presenting linguistic variables. Transformation rule from two-tuple LTR to numerical trust degree is then analyzed, followed by the propagation operator of indirect trust/distrust relationships. The advantage of the propagation operator lies in that ignorance in trust/distrust relationships can be tackled rationally. As for the consensus reaching process (CRP), three-level identification and adjustment mechanisms are proposed under the condition that individuals express their preferences in an uncertain distribution form. Trust relationship, consensus degree and reliability of individuals’ judgments are all addressed comprehensively to narrow the opinion divergence. Self-confidence extent is utilized as a factor to adjust the opinions of non-consensus experts. The proposed method is further implemented in life cycle sustainability assessment to demonstrate the validity and effectiveness in dealing with realistic GDM problems. © 2023 Elsevier B.V.

针对某大型养殖工船所装备的养殖水泵采用恒速运行会造成大量电能浪费和养殖成本增加的问题,设计了一种基于鲸鱼算法优化的养殖水泵模糊PID控制器。通过鲸鱼算法对模糊PID控制器中的量化因子和比例因子进行优化,使得控制器能够针对换水、投饲、清洗、水面泡沫排出的复杂多变工况,对养殖水泵的转速进行动态调节,从而实现海水流量的调节。仿真结果显示,与PID控制器和模糊PID控制器相比,超调量和稳态误差更小。调节时间相较PID控制器缩短了71.11%,相较模糊PID控制器缩短了44.29%,能够更好地满足养殖水泵的控制要求,又能够实现节能的目标。

This article investigates how to make use of imperfect data gathered from different sources for inference and decision making. Based on Bayesian inference and the principle of likelihood, a likelihood analysis method is proposed for acquisition of evidence from imperfect data to enable likelihood inference within the framework of the evidential reasoning (ER). The nature of this inference process is underpinned by the new necessary and sufficient conditions that when a piece of evidence is acquired from a data source it should be represented as a normalized likelihood distribution to capture the essential evidential meanings of data. While the explanation of sufficiency of the conditions is straightforward based on the principle of likelihood, their necessity needs to be established by following the principle of Bayesian inference. It is also revealed that the inference process enabled by the ER rule under the new conditions constitutes a likelihood inference process, which becomes equivalent to Bayesian inference when there is no ambiguity in data and a prior distribution can be obtained as a piece of independent evidence. Two examples in decision analysis under uncertainty and a case study about fault diagnosis for railway track maintenance management are examined to demonstrate the steps of implementation and potential applications of the likelihood inference process.