Mechanical Reliability Analysis and Optimization Design Method Based on Evidence Theory

With the complexity of mechanical manufacturing system design increasing, the traditional single-objective optimization method can no longer meet the needs of multi-objective optimization, such as lightweight, high efficiency, low energy consumption and long life. Multi-objective optimization algorithm is widely used in mechanical design and manufacturing process planning because of its good convergence and diversity. Taking robot motion planning as an example, this paper analyzes the application methods of multi-objective optimization algorithm in mechanical structure design in detail, including problem description, multi-objective optimization model construction, algorithm application and performance analysis. Through the application of Genetic Algorithm (GA), this paper shows how the multi-objective optimization algorithm can balance multiple objectives such as path length, energy consumption and obstacle avoidance effect, and realize more intelligent and efficient solutions in robot motion planning. Performance analysis shows that GA is superior to single-objective optimization and random search algorithm in optimization effect, computational efficiency and stability. In addition, this paper also discusses the influence of the change of target weight and algorithm parameters on the optimization results, which provides valuable reference for future algorithm optimization and practical application. Multi-objective optimization algorithm shows obvious advantages in mechanical manufacturing system, which provides new ideas and methods for realizing more efficient, more environmentally friendly and more intelligent mechanical manufacturing design.

An Evidence theory and data fusion based classification method for decision making

In actual life, uncertain and inconsistent information exists widely. How to deal with the information so that it can be better applied is a problem that has to be solved. Neutrosophic soft sets can process uncertain and inconsistent information. Also, Dempster-Shafer evidence theory has the advantage of dealing with uncertain information, and it can synthesize uncertain information and deal with subjective judgments effectively. Therefore, this paper creatively combines the Dempster-Shafer evidence theory with the neutrosophic soft sets, and proposes a cosine similarity measure for multi-criteria group decision making. Different from the previous studies, the proposed similarity measure is utilized to measure the similarity between two objects in the structure of neutrosophic soft set, rather than two neutrosophic soft sets. We also propose the objective degree and credibility degree which reflect the decision makers’ subjective preference based on the similarity measure. Then parameter weights are calculated by the objective degree. Additionally, based on credibility degree and parameter weights, we propose the modified score function, modified accuracy function, and modified certainty function, which can be employed to obtain partial order relation and make decisions. Later, we construct an aggregation algorithm for multi-criteria group decision making based on Dempster’s rule of combination and apply the algorithm to a case of medical diagnosis. Finally, by testing and comparing the algorithm, the results demonstrate that the proposed algorithm can solve the multi-criteria group decision making problems effectively.

Interpreting uncertain information, a fundamental requirement of many computer vision and pattern recognition systems is commonly supported by models of the uncertainty. Evidence theory, also called Dempster-Shafer theory, is particularly useful for representing and combining uncertain information when a single precise uncertainty model is unavailable. A framework is presented for deriving and transforming evidence-theoretic belief representations of uncertain variables that denote numerical quantities. Belief is derived from probabilistic models using relationships between probability bounds and the support and plausibility functions used in evidence theory. This model-based approach to belief representation is illustrated by an algorithm currently used in a vision system to label anomalous high-intensity pixels in imagery. As the uncertain variables are manipulated to form features and object discriminants, the belief representation of the uncertain variables must be transformed accordingly. Belief transformations, analogous to the transformation of probability-density functions in mappings of random variables, are derived to maintain the same rigorous belief representation for computed quantities. The results demonstrate novel ways to address uncertainty in the use of sensor information, and contribute to understanding of the similarities and distinctions of probability theory and evidence theory.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Situation estimation and threat assessment in air combat are crucial issues. Due to the limitations of the sensor’s precision, terrible battlefield environment and the deliberately interfere of the enemy, the information of threat assessment is often ambiguous and uncertain. Belief function theory has unique and significant advantages in uncertain information processing and fusion, so it is suitable for threat assessment. Our proposed approach handles information begins with feature extraction using fuzzy sets, then interspecific fusion and time domain fusion are carried out by belief function theory and evidence discount. Finally, the data is processed into a definite number to measure the threat index of the target. In the fusion process, evidence discount improves the quality and accuracy of convergence. The simulation example verifies that our proposed method is not only able to accurately analyze and convey the sensor information, but also has better real-time performance and the ability to process uncertain information.

Parallelotope-formed evidence theory model for quantifying uncertainties with correlation

In this paper, we propose a Credal EM (CrEM) approach for partially supervised learning. The uncertainty is represented by belief functions as understood in the transferable belief model (TBM). This model relies on a non probabilistic formalism for representing and manipulating imprecise and uncertain information. We show how the EM algorithm can be applied within the TBM framework when applied for the classification of objects and when the learning set is imprecise (the actual class of each object is only known as belonging to a subset of classes), and/or uncertain (the knowledge about the actual class is represented by a probability function or by a belief function).KeywordsLearningbelief functionsEMtransferable belief model

An approach based on D-S theory of evidence and entropy-weighted grey correlation analysis is proposed as means to evaluating lightning risk of transmission lines. The correlation between environmental factors (altitude, slope position, aspect, slope, river network density, population density, Land-use types and surface types) and the lightning accidents of transmission lines are discussed based on the data of lightning trip-out. Based on the Information Entropy Theory, the entropy weight of the environmental factors of the line to be evaluated is determined, and the Probability Mass Function of environmental factors are obtained by the grey relational analysis. Then, the Evidence Theory is adopted to realize multi-source environmental information fusion. Finally, mapping the confidence value of lightning strike to the risk probability of lightning strike. Based on the proposed method and the lightning trip-out information of 35–500kV 623 transmission lines from 2003 to 2015, the lightning strike probability of different transmission lines are calculated. Compared the operational data for 2016 years to the evaluation results, the proposed method is credible.

Spatial pattern of critical wetland patches and its influencing factors in a coastal area, North China.

In addition to the news content, most news web pages also contain various noises, such as advertisements, recommendations, and navigation panels. These noises may hamper the studies and applications which require pre-processing to extract the news content accurately. Existing methods of news content extraction mostly rely on non-content features, such as tag path, text layout, and DOM structure. However, without considering topics of the news content, these methods are difficult to recognize noises whose external characteristics are similar to those of the news content. In this paper, we propose a method that combines non-content features and a topic feature based on Dempster-Shafer (DS) theory to increase the recognition accuracy. We use maximal compatibility blocks to generate topics from text nodes and then obtain feature values of topics. Each feature is converted into evidence for the DS theory which can be utilized in the uncertain information fusion. Experimental results on English and Chinese web pages show that combining the topic feature by DS theory can improve the extraction performance obviously.

Structural topology optimization based on deep learning

Based on the analysis of condensate and feed water system, a fault knowledge repository is established considering operation experience. The D-S inference of Information Fusion theory has the ability of dealing with uncertain information and Artificial Neural Network (ANN) has the advantage of high tolerance and robust. In this paper, a model for fault diagnosis utilizing D-S theory of evidence together with BP network is presented and introduced to the diagnosis of condensate and feed water system. The simulation experiment proves that the system is able to improve the reliability of the diagnosis and decrease the uncertainty markedly.

International audience

This work focuses on the proof-mass mechanical structural design improvement of a tri-axial piezoresistive accelerometer specifically designed for head injuries monitoring where medium-G impacts are common; for example, in sports such as racing cars or American Football. The device requires the highest sensitivity achievable with a single proof-mass approach, and a very low error (<1%) as the accuracy for these types of applications is paramount. The optimization method differs from previous work as it is based on the progressive increment of the sensor proof-mass mass moment of inertia (MMI) in all three axes. Three different designs are presented in this study, where at each step of design evolution, the MMI of the sensor proof-mass gradually increases in all axes. The work numerically demonstrates that an increment of MMI determines an increment of device sensitivity with a simultaneous reduction of cross-axis sensitivity in the particular axis under study. This is due to the linkage between the external applied stress and the distribution of mass (of the proof-mass), and therefore of its mass moment of inertia. Progressively concentrating the mass on the axes where the piezoresistors are located (i.e., x- and y-axis) by increasing the MMI in the x- and y-axis, will undoubtedly increase the longitudinal stresses applied in that areas for a given external acceleration, therefore increasing the piezoresistors fractional resistance change and eventually positively affecting the sensor sensitivity. The final device shows a sensitivity increase of about 80% in the z-axis and a reduction of cross-axis sensitivity of 18% respect to state-of-art sensors available in the literature from a previous work of the authors. Sensor design, modelling, and optimization are presented, concluding the work with results, discussion, and conclusion.

In Vehicular Cyber-Physical Systems (VCPS), the collected sensor data are always uncertain and conflicting. Dempster-Shafer (DS) evidence theory can effectively deal with uncertain information, but the Dempster's rule may produce counter-intuitive results when the information is conflicting. This paper proposed an improved approach for combining conflicting evidence with different weighting factors based on a novel dissimilarity measure. Firstly, a new dissimilarity measure mixing fuzzy nearness with the introduced correlation coefficient is proposed to characterize the divergence degree between two basic probability assignments (BPAs). Then, the weighting factors are developed by using the proposed dissimilarity measure. Finally, the Dempster's rule is chose to combine the revised sources. Simulation experiment shows that the improved method can effectively solve the problem of sensor data fusion in VCPS with better convergence performance.