Method for optimal maintenance decision-making of hydraulic equipment with risk control
A kind of equipment and optimal technology, applied in the direction of calculation, complex mathematical operations, special data processing applications, etc., can solve the problems of different status, achieve the effect of improving accuracy, speeding up diagnosis, improving accuracy and algorithm efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0134] Example 1: Calculate the probability value of the corresponding potential fault by using the variable weight association rule algorithm DVWAR
[0135] This embodiment uses two methods for analysis, one is the weighted association rule algorithm, and the other is the variable weight association rule algorithm. The same set of data is used in the example, and the final result is obtained through calculation and compared. .
example
[0136] Example: Device M consists of 5 kinds of components, and there are 7 kinds of possible failures. Table 1 is the initial weight of each component, and Table 2 is each fault database, indicating the components that can be traced when a certain fault occurs. Set the minimum support threshold wminsup to 1.
[0137] Table 1. Initial weights of components of equipment M. Table 2. Each fault database of equipment M.
[0138]
[0139]
[0140] 1. Mining using weighted association rules algorithm
[0141] Since the weighted association rule algorithm is only given the weight of each component once in the entire life cycle of the device, the initial weight of each component of device M is constant, that is, the weight of component A is 0.2, and the weight of component B is 0.2. The weight is 0.1, the weight of component C is 0.3, the weight of component D is 0.4, and the weight of component E is 0.8. According to the mining method of weighted association rules, mining is...
Embodiment 2
[0152] Example 2: Obtaining the Consequence Value of Corresponding Faults Using Neural Network Modeling
[0153] In order to illustrate the application of BP neural network in the prediction of failure consequence value, five items of equipment risk value, personal risk value, environmental risk value, social risk value and system risk value are selected as input items, and the output item is the comprehensive evaluation of potential failure consequences. value. Due to the large data, Table 6 lists the learning samples for the prediction of the comprehensive evaluation value of some fault consequences.
[0154] Table 6. Learning samples for the prediction of the comprehensive evaluation value of some fault consequences
[0155]
[0156] In the design of BP neural network, if the number of nodes in the hidden layer of the network is too small, the nonlinear mapping function and fault tolerance of the network will be poor, and the selection of too many nodes will increase th...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com