CN113761225A - Automobile engine fault prediction method fusing knowledge graph and multivariate neural network model - Google Patents
Automobile engine fault prediction method fusing knowledge graph and multivariate neural network model Download PDFInfo
- Publication number
- CN113761225A CN113761225A CN202111054560.1A CN202111054560A CN113761225A CN 113761225 A CN113761225 A CN 113761225A CN 202111054560 A CN202111054560 A CN 202111054560A CN 113761225 A CN113761225 A CN 113761225A
- Authority
- CN
- China
- Prior art keywords
- fault
- automobile engine
- neural network
- knowledge graph
- knowledge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000003062 neural network model Methods 0.000 title claims abstract description 19
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 238000012423 maintenance Methods 0.000 claims abstract description 14
- 238000006243 chemical reaction Methods 0.000 claims abstract description 13
- 230000007246 mechanism Effects 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims abstract description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 11
- 125000004122 cyclic group Chemical group 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 230000000306 recurrent effect Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000002457 bidirectional effect Effects 0.000 claims description 2
- 238000003745 diagnosis Methods 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 239000003607 modifier Substances 0.000 claims 1
- 238000013507 mapping Methods 0.000 abstract description 4
- 230000009466 transformation Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an automobile engine fault prediction method fusing a knowledge graph and a polynary neural network model, and belongs to the field of automobile engine fault prediction. By taking the running state, the fault phenomenon, the fault reason and the maintenance record of the automobile engine as input information, a structural knowledge network which can be represented and inferred is formed by knowledge extraction, disambiguation and processing, and feature vector conversion is carried out; secondly, a multi-element neural network path comprising a fault record embedding layer, a convolution layer, a GRU gate control layer and an attention mechanism is established, an engine fault prediction model is formed through feature vector training, and qualitative fault phenomena of an engine can be converted into quantitative fault reasoning and then mapping transformation to qualitative fault prediction output is carried out. The invention improves the prediction rate of the engine fault.
Description
Technical Field
The invention belongs to the field of automobile engine fault prediction, and relates to an automobile engine fault prediction method fusing a knowledge map and a polynary neural network model.
Background
The automobile engine is a very complex nonlinear system, not only has a complex structure, but also is repeatedly in a working state of high temperature, high pressure, vibration and high-speed operation for a long time, has high engine fault probability and multiple fault types, forms a many-to-many complex coupling relation between fault symptoms and faults, is difficult to establish an accurate mechanism model of the engine, has high engine fault prediction difficulty, and has a main problem of how to perform efficient and accurate traceability analysis and intelligent prediction of engine faults.
Disclosure of Invention
The invention aims to provide an intelligent automobile engine fault prediction method fusing a knowledge graph and a polynary neural network, aiming at the problems that the automobile engine has high fault rate and multiple types, many-to-many complex coupling relations exist between fault symptoms and faults, the fault tracing difficulty is high, the accuracy is low and the like. The engine fault prediction model is formed through the feature vector training after the knowledge map conversion, the mapping transformation from the qualitative fault phenomenon of the engine to the quantitative fault reasoning and then to the qualitative fault prediction output is realized, and a new thought and means are provided for the efficient and accurate prediction of the automobile engine fault.
The technical scheme for realizing the aim is mainly to establish an automobile engine fault prediction model fusing a knowledge graph and a polynary neural network, and the main method is as follows:
step (1): and aiming at the particularity of the fault data of the automobile engine, performing feature extraction and storage on the fault data in a form of a triple (entity-relation-entity) to construct an automobile engine fault knowledge map.
Step (2): and performing word vector conversion on the constructed knowledge graph, converting unstructured and semi-structured data into structured data, and applying the structured data as a word embedding layer to subsequent deep learning.
And (3): and constructing a multilayer mixed neural network model integrating a Convolutional Neural Network (CNN), a double-gate-controlled recurrent neural network (GRU), an Attention mechanism (Attention) and the like by taking the word vector embedded layer after the conversion of the knowledge graph as an initial input layer.
And (4): and constructing a knowledge graph after coding by using related words and sentences in more than 1000 maintenance cases as experimental data sources. And (3) dividing the data into a training set and a testing set according to the ratio of 2:8 to predict and compare the faults of the automobile engine.
Further, the main steps of constructing the automobile engine fault knowledge map in the step (1) are as follows:
step (1.1): and extracting related language materials, record entities and attributes of the automobile engine faults.
Step (1.2): and carrying out coreference resolution on words and sentences in the automobile engine fault record expectation.
Step (1.3): and processing the knowledge of the formed relevant knowledge.
Step (1.4): and carrying out data integration on the network triple structures of the fault entity, the attribute and the relationship.
Further, the vectorization representation of the knowledge graph ontology data in the step (2) mainly comprises the following steps:
step (2.1): and performing word vector conversion on the established knowledge graph by using word vector processing tools word2vec, jieba word segmentation and other tools.
Further, the multilayer hybrid neural network model in the step (3) is constructed by the following main steps:
step (3.1): and extracting the word vector characteristics after the knowledge graph is converted by the convolutional neural network layer.
Step (3.2): and forming an automobile engine fault prediction path by using the bidirectional gated cyclic neural network.
Step (3.3): text semantic information is better utilized by adding weights through an attention mechanism layer, and more important parts in the fault diagnosis knowledge entity are captured.
Further, the case prediction comparison in the step (4) mainly comprises the following steps:
step (4.1): the experimental data mainly comprises automobile engine fault maintenance cases, maintenance records, and relevant operation specifications and manuals. And constructing a knowledge graph after coding by using related words and sentences in more than 1000 maintenance cases as experimental data sources. And (3) dividing the data into a training set and a testing set according to the ratio of 2:8 to predict the automobile engine faults.
The invention has the beneficial effects that:
1. automobile engine fault prediction method fusing knowledge graph and multivariate neural network model
2. The engine fault prediction model is formed through the feature vector training after the knowledge map conversion, and mapping transformation from qualitative fault phenomena of the engine to quantitative fault reasoning and then to qualitative fault prediction output is realized.
3. A new idea and means are provided for the efficient and accurate prediction of the engine fault.
Drawings
FIG. 1 is a block diagram of an engine fault intelligent prediction framework;
FIG. 2 is a flow chart of engine fault knowledge map construction;
FIG. 3 is a diagram of a multivariate hybrid neural network model;
FIG. 4 is a diagram of a GRU neural network architecture;
FIG. 5 is a diagram of the attention mechanism operating mechanism;
FIG. 6 is a comparison graph of prediction effect of different model fusion knowledge maps.
Detailed Description
The invention will be further illustrated with reference to the following figures and examples, without however restricting the scope of the invention thereto.
Example 1: as shown in fig. 1, a method for predicting a failure of an automobile engine based on a fusion knowledge graph and a multivariate neural network model mainly includes the following steps:
step (1): and aiming at the particularity of the fault data of the automobile engine, the fault data is subjected to feature extraction and storage in a form of a triple (entity-relation-entity) to form a basic unit of the automobile engine fault knowledge map.
Step (2): and performing word vector conversion on the constructed knowledge graph, converting unstructured and semi-structured data into structured data, and applying the structured data as a word embedding layer to subsequent deep learning.
And (3): and constructing a multilayer mixed neural network model integrating a Convolutional Neural Network (CNN), a double-gate-controlled recurrent neural network (GRU), an Attention mechanism (Attention) and the like by taking the word vector embedded layer after the conversion of the knowledge graph as an initial input layer.
And (4): the invention uses the automobile engine fault maintenance case, the maintenance record, the relevant operation standard and the manual as the data source to analyze the model case.
Example 2: as shown in fig. 2, the method for predicting the failure of the automobile engine by fusing the knowledge graph and the polynary neural network model, in the step (1) of the embodiment 1, the construction of the knowledge graph mainly comprises the following steps:
step (1.1): and extracting related language materials, record entities and attributes of the automobile engine faults.
Step (1.2): and carrying out coreference resolution on words and sentences in the automobile engine fault record expectation.
Step (1.3): and processing the knowledge of the formed relevant knowledge.
Step (1.4): and carrying out data integration on the network triple structures of the fault entity, the attribute and the relationship.
Example 3: as shown in fig. 3, a method for predicting a failure of an automobile engine by fusing a knowledge graph and a multivariate neural network model, in step (3) of embodiment 1, the construction of the multivariate neural network mainly includes the following steps:
step (3.1): and extracting the word vector characteristics after the knowledge graph is converted by the convolutional neural network layer.
Step (3.2): as shown in FIG. 4, a two-way gated cyclic neural network is used to form a failure prediction path of an automobile engine.
Step (3.3): as shown in fig. 5, text semantic information is better utilized by the attention mechanism layer to add weights, capturing the more important parts of the troubleshooting knowledge entity. The relevant calculation formula for the attention mechanism is as follows:
example 4: as shown in fig. 6, in the comparison of prediction effects of fusion knowledge maps of different models, it can be seen that, under the operating environment with the same data set and parameter settings, the prediction effect of the KG-CNN model is poor, and the accuracy of KG-LSTM in the prediction effect is improved by 1.63% compared with KG-CNN, the recall rate is improved by 2.29%, and the score rate is improved by 2.0%. The long-time memory neural network has a cyclic characteristic when the characteristic is analyzed by using the automobile fault text, so that the condition that the prediction effect is not ideal due to the omission of related information can be effectively avoided. Compared with other models, the KG-CNN-GRU-ATT model provided by the method has greater improvement in accuracy, recall rate and score rate, and fully shows the high reliability and accuracy of the model for the automobile engine fault prediction. Compared with a KG-CNN-LSTM model, the head-tail relation of fault information can be better utilized by replacing the LSTM neural network with the double-gated cyclic neural network, and the influence of related interference words in fault prediction can be reduced by introducing an attention mechanism, so that the prediction effect of the model is greatly improved.
The working principle of the invention is as follows: the running state, fault phenomenon, fault reason and maintenance record of the automobile engine are used as input information, a structural knowledge network which can be represented and inferred is formed through knowledge extraction, disambiguation and processing, and feature vector conversion is carried out; secondly, a multi-element neural network path comprising a fault record embedding layer, a convolution layer, a GRU gate control layer and an attention mechanism is established, an engine fault prediction model is formed through feature vector training, and mapping transformation from qualitative fault phenomena of an engine to quantitative fault reasoning and then to qualitative fault prediction output is realized; finally, the feasibility and the effectiveness of the KG-CNN-GRU-ATT method are verified through actual maintenance cases.
What has been described above are merely some embodiments of the present invention. It will be apparent to those skilled in the art that various changes and modifications can be made without departing from the inventive concept thereof, and these changes and modifications can be made without departing from the spirit and scope of the invention.
Claims (6)
1. A method for predicting the failure of an automobile engine by fusing a knowledge map and a polynary neural network model is characterized in that the knowledge map and the polynary neural network are fused, multi-source heterogeneous data are fully utilized, and the method belongs to the field of automobile engine failure prediction.
2. The method for predicting the failure of the automobile engine based on the fusion knowledge graph and the polynary neural network model as claimed in claim 1, wherein: the method comprises the following steps:
step (1): and aiming at the particularity of the fault data of the automobile engine, the fault data is subjected to feature extraction and storage in a form of a triple (entity-relation-entity) to form a basic unit of the automobile engine fault knowledge map.
Step (2): and performing word vector conversion on the constructed knowledge graph, converting unstructured and semi-structured data into structured data, and applying the structured data as a word embedding layer to subsequent deep learning.
And (3): and constructing a multilayer mixed neural network model integrating a Convolutional Neural Network (CNN), a double-gate-controlled recurrent neural network (GRU), an Attention mechanism (Attention) and the like by taking the word vector embedded layer after the conversion of the knowledge graph as an initial input layer.
And (4): the invention uses the automobile engine fault maintenance case, the maintenance record, and the relevant operation standard and manual as the data source to analyze and compare the model case.
3. The automobile engine fault prediction method fusing the knowledge graph and the multivariate neural network model according to claim 2, characterized in that: the step of constructing the automobile engine fault knowledge map in the step (1) comprises the following steps:
step (1.1): and extracting related language materials, record entities and attributes of the automobile engine faults.
Step (1.2): and carrying out coreference resolution on words and sentences in the automobile engine fault record expectation.
Step (1.3): and processing the knowledge of the formed relevant knowledge.
Step (1.4): and carrying out data integration on the network triple structures of the fault entity, the attribute and the relationship.
4. The automobile engine fault prediction method fusing the knowledge graph and the multivariate neural network model according to claim 2, characterized in that: the main steps of performing word vector conversion on the constructed knowledge graph in the step (2) are as follows:
step (2.1): and performing word vector conversion on the established knowledge graph by using word vector processing tools word2vec, jieba word segmentation and other tools.
5. The automobile engine fault prediction method fusing the knowledge graph and the multivariate neural network model according to claim 2, characterized in that: the step (3) comprises the following steps:
step (3.1): and extracting the word vector characteristics after the knowledge graph is converted by the convolutional neural network layer.
Step (3.2): and forming an automobile engine fault prediction path by using the bidirectional gated cyclic neural network.
Step (3.3): text semantic information is better utilized by adding weights through an attention mechanism layer, a more important part in a fault diagnosis knowledge entity is captured, and the problem of noise caused by irrelevant modifiers existing in the fault text entity is reduced.
6. The automobile engine fault prediction method fusing the knowledge graph and the multivariate neural network model according to claim 2, characterized in that: the step (4) comprises the following steps:
step (4.1): the experimental data mainly comprises automobile engine fault maintenance cases, maintenance records, and relevant operation specifications and manuals. And constructing a knowledge graph after coding by using related words and sentences in more than 1000 maintenance cases as experimental data sources. And (3) dividing the data into a training set and a testing set according to the ratio of 2:8 to predict the automobile engine faults.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111054560.1A CN113761225A (en) | 2021-09-09 | 2021-09-09 | Automobile engine fault prediction method fusing knowledge graph and multivariate neural network model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111054560.1A CN113761225A (en) | 2021-09-09 | 2021-09-09 | Automobile engine fault prediction method fusing knowledge graph and multivariate neural network model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113761225A true CN113761225A (en) | 2021-12-07 |
Family
ID=78794232
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111054560.1A Pending CN113761225A (en) | 2021-09-09 | 2021-09-09 | Automobile engine fault prediction method fusing knowledge graph and multivariate neural network model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113761225A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115077906A (en) * | 2022-06-10 | 2022-09-20 | 潍柴动力股份有限公司 | Engine high-occurrence fault cause determination method, engine high-occurrence fault cause determination device, electronic equipment and medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190391574A1 (en) * | 2018-06-25 | 2019-12-26 | Nec Laboratories America, Inc. | Early anomaly prediction on multi-variate time series data |
CN110647867A (en) * | 2019-10-09 | 2020-01-03 | 中国科学技术大学 | Bearing fault diagnosis method and system based on self-adaptive anti-noise neural network |
CN111400505A (en) * | 2020-03-13 | 2020-07-10 | 国家电网有限公司 | Method and system for matching fault elimination scheme of power consumption information acquisition system |
CN112034789A (en) * | 2020-08-25 | 2020-12-04 | 国家机床质量监督检验中心 | Health assessment method, system and assessment terminal for key parts and complete machine of numerical control machine tool |
CN112906892A (en) * | 2021-03-08 | 2021-06-04 | 南京航空航天大学 | Intelligent equipment fault diagnosis method based on deep learning and knowledge graph |
CN113283027A (en) * | 2021-05-20 | 2021-08-20 | 南京航空航天大学 | Mechanical fault diagnosis method based on knowledge graph and graph neural network |
-
2021
- 2021-09-09 CN CN202111054560.1A patent/CN113761225A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190391574A1 (en) * | 2018-06-25 | 2019-12-26 | Nec Laboratories America, Inc. | Early anomaly prediction on multi-variate time series data |
CN110647867A (en) * | 2019-10-09 | 2020-01-03 | 中国科学技术大学 | Bearing fault diagnosis method and system based on self-adaptive anti-noise neural network |
CN111400505A (en) * | 2020-03-13 | 2020-07-10 | 国家电网有限公司 | Method and system for matching fault elimination scheme of power consumption information acquisition system |
CN112034789A (en) * | 2020-08-25 | 2020-12-04 | 国家机床质量监督检验中心 | Health assessment method, system and assessment terminal for key parts and complete machine of numerical control machine tool |
CN112906892A (en) * | 2021-03-08 | 2021-06-04 | 南京航空航天大学 | Intelligent equipment fault diagnosis method based on deep learning and knowledge graph |
CN113283027A (en) * | 2021-05-20 | 2021-08-20 | 南京航空航天大学 | Mechanical fault diagnosis method based on knowledge graph and graph neural network |
Non-Patent Citations (2)
Title |
---|
XIAOCHEN ZHANG ET AL: "Early Fault Detection Method of Rolling Bearing Based on MCNN and GRU Network with an Attention Mechanism", 《HINDAWI: SHOCK AND VIBRATION》, vol. 2021, pages 1 - 13 * |
张善文 等: "结合知识图谱与双向长短时记忆网络的小麦条锈病预测", 《农业工程学报》, vol. 36, no. 12, pages 172 - 178 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115077906A (en) * | 2022-06-10 | 2022-09-20 | 潍柴动力股份有限公司 | Engine high-occurrence fault cause determination method, engine high-occurrence fault cause determination device, electronic equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021000556A1 (en) | Method and system for predicting remaining useful life of industrial equipment, and electronic device | |
US9348815B1 (en) | Systems and methods for construction, maintenance, and improvement of knowledge representations | |
US20230169309A1 (en) | Knowledge graph construction method for ethylene oxide derivatives production process | |
Li et al. | Fault diagnosis expert system of semiconductor manufacturing equipment using a Bayesian network | |
CN106383916B (en) | Data processing method based on predictive maintenance of industrial equipment | |
Yakymets et al. | Model-based system engineering for fault tree generation and analysis | |
CN113342842A (en) | Semantic query method and device based on metering knowledge and computer equipment | |
CN104899291A (en) | Method and device for multidimensional analysis of relational database | |
US11443168B2 (en) | Log analysis system employing long short-term memory recurrent neural net works | |
CN107103363A (en) | A kind of construction method of the software fault expert system based on LDA | |
CN117035073B (en) | Future meteorological event prediction method based on hierarchical event development mode induction | |
CN111930912A (en) | Dialogue management method, system, device and storage medium | |
CN113761225A (en) | Automobile engine fault prediction method fusing knowledge graph and multivariate neural network model | |
CN116362245A (en) | OPC UA information model construction method based on unstructured text data | |
CN116010619A (en) | Knowledge extraction method in complex equipment knowledge graph construction process | |
CN103679484A (en) | Novel method for analyzing E-commerce consistency based on behavior Petri network | |
US20230037297A1 (en) | Robotics Process Automation Automatic Enhancement System | |
CN114492460A (en) | Event causal relationship extraction method based on derivative prompt learning | |
Luo et al. | A survey: complex knowledge base question answering | |
CN112818678B (en) | Dependency relationship graph-based relationship reasoning method and system | |
CN113379214A (en) | Method for automatically filling and assisting decision of power grid accident information based on affair map | |
CN117251581A (en) | Equipment fault information diagnosis method based on text analysis | |
CN117056226A (en) | Cross-project software defect number prediction method based on transfer learning | |
CN116108053A (en) | Question and answer processing method and device based on form | |
CN115756610A (en) | Method, device, equipment and medium for processing natural language instruction information |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |