It is vital to establish an interpretable fault diagnosis model for critical equipment. Belief Rule Base (BRB) expert system gradually applied in diagnosis. However, the knowledge cannot be utilized initial BRB accurately if there are multiple referential grades different features. In addition, interpretability of BRB-based destroyed optimization process, which reflects two aspects: deviation from judgment and over-optimization parameters. To solve these problems, a new based on probability...

Sensor disturbance has a significant impact on the performance state of complex systems in engineering. In this article, new evaluation model for considering sensor is proposed. First, belief rule base (BRB) used as white-box to establish transparent model. To evaluate influence state, described an interval and added input. The fluctuation range disturbed calculated. Then, assist diminish damage robustness analyzed two types tasks with different requirements. general tasks, antidisturbance...

Fault diagnosis plays an irreplaceable role in the normal operation of equipment. A fault model is often required to be interpretable for increasing trust between humans and model. Due understandable knowledge expression transparent reasoning process, belief rule base (BRB) has extensive applications as expert system diagnosis. Optimization effective means weaken subjectivity experts BRB, where interpretability BRB may weakened. Hence, obtain a credible result, weakening factors BRB-based...

The evidential reasoning (ER) rule, with its strict probabilistic and superior uncertainty handling ability, has been widely used in the evaluation, diagnosis, decision-making. Recently, a modeling approach based on ER rule that combines evidence constituted by single attribute (SA_ER) gradually attracted scholars' attention due to good scalability flexibility. However, SA_ER, frame of discernment (FoD) is composed series singleton propositions universal set these propositions. Since SA_ER...

In aerospace engineering, medical diagnosis and other fields, the implementation of interpretable fault (IFD) technology is critical for improving credibility results ensuring reliability complex electromechanical systems. As a typical modeling method, belief rule base (BRB) approach still has two problems that must be solved application to IFD: 1) structures increase cost model interpretability, 2) over-optimization parameters diminishes interpretability. To solve these problems, this paper...

In order to improve the reliability and accuracy of inertial navigation system, multi-meter redundant Laser measurement unit emerged under this demand. This type has more components, complex structure simpler criteria. To adapt quality evaluation laser units redundancy design, article constructs a index system that meets practical requirements through known data forms. Adopting bias as health indicator adding resume information an availability makes scientific complete. premise, multi-index...

The laser inertial measurement unit is a precision device widely used in rocket navigation system and other equipment, its quality directly related to accuracy.In the evaluation of unit, there inevitably uncertainty index input information.First, numerical information interval form.Second, grade result are given according different national standards.So, it key step transform by into data form consistent with grade.In case uncertain input, this paper puts forward method based on probability...

The fault diagnosis of aerospace relays plays a key role in the service aircraft by virtue essentiality them. requirement transparency is paramount to model. Belief rule base (BRB) introduced establish model for an easy-to-understand way this paper. To fully embed expert knowledge, mechanism relay analyzed generate failure mode and effects analysis (FMEA). Fault features, modes belief rules are extracted from FMEA experts BRB. projection covariance matrix adaption evolution strategy...

As a power element of the hydraulic system, health state plunger pump affected working condition and it is necessary to predict state. In this paper, belief rule base (BRB) used fuse multi-source information develop prediction model pump. Forecasting values indicators are obtained by introducing Long Short-Term Memory (LSTM) provide input for BRB. The experts construct indicator system establish BRB based on mechanism knowledge. projection covariance matrix adaption evolution strategy...

In the settlement safety assessment of liquefied natural gas (LNG) tank, there are some problems, such as lack high-value samples and uncertainty parameters. Compared with traditional method, belief rule base (BRB) model is an effective modeling tool by using qualitative knowledge quantitative information to solve describe uncertainties. Therefore, a method LNG tanks based on BRB proposed in this paper. Firstly, key factors established calculated through mechanism analysis new Fourier series...