Method of vehicle remote diagnosis and spare parts retrieval based on fp-tree sequence pattern mining and fault code classification
A technology of sequential pattern mining and remote diagnosis, applied in the field of information retrieval, it can solve problems such as maintenance labor costs for detailed solutions to failures, and achieve the effect of high accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0019] Example 1: A method for vehicle remote diagnosis and spare parts retrieval based on FP-Tree sequence pattern mining and fault code classification, including
[0020] Step 1. Collect vehicle information data;
[0021] Step 2. Identify and classify the fault codes;
[0022] Step 3. Analyze the vehicle VIN code to obtain variables, and the variables include the engine displacement, body type, and engine gearbox type analyzed by the VIN code;
[0023] Step 4. Perform a decision tree analysis on the spare part codes corresponding to the variables, complete the classification of variable data to form spare part information, and establish an index to form a diagnostic knowledge base;
[0024] Step 5. According to the transaction database, create a frequent item set of the corresponding relationship between the fault code and the replacement spare part through the FP-Tree algorithm; use the topology relationship between the position of the spare part and the ECU where the fa...
Embodiment 2
[0027] Example 2: Have the same technical scheme as embodiment 1, more specifically, for step 4 of embodiment 1,
[0028] In the step 4, the historical records of the maintenance spare parts table are used as the data basis, and the spare parts are classified through the decision tree model. The maintenance spare parts table sample is shown in Table 1:
[0029] Table I
[0030] VIN123 VIN4 VIN6 VIN78 BJDM LFV 5 1 4B 06J 115 403J LFV 3 2 8K LN 052 167 A21 LFV 4 2 4F LN 052 167 A24
[0031] The basic principles of the decision tree model are as follows:
[0032] First: Determine the entropy of different categories of spare parts in each dimension. Taking VIN4 as an example, the entropy is defined as
[0033] E=sum(-p(I)*log(p(I)))
[0034] Wherein I=1:N (N category results, such as this example 1, that is, the spare part belongs to this model, so the probability P(I)=1)
[0035] Then E(5)=-(1 / 1) Log2(1 / 1)-(0 / 1) Log2(0 / 1)=...
Embodiment 3
[0055] Example 3: Have the same technical scheme as embodiment 1 or 2, more specifically, for step five of embodiment 1,
[0056] In said step 5, according to the transaction database, the step of creating a frequent itemset of the corresponding relationship between the fault code and the replacement spare part through the FP-Tree algorithm includes
[0057]S1.1 Input the transaction database and the minimum support threshold minσ, scan the transaction database, delete items whose frequency is less than the minimum support, and obtain all frequent itemsets F1, and arrange the frequent items in F1 in descending order of their support to obtain L;
[0058] S1.2 Create the root node of FP-Tree, mark it with "null", scan the transaction database again, arrange each record in the transaction database according to the order in L, and generate FP-Tree;
[0059] S1.3 Find all frequent patterns from FP-Tree.
[0060] In the fifth step, using the topological relationship between the ...
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