CN118296370A - Train fault prediction method and system based on neural network - Google Patents
Train fault prediction method and system based on neural network Download PDFInfo
- Publication number
- CN118296370A CN118296370A CN202410282017.4A CN202410282017A CN118296370A CN 118296370 A CN118296370 A CN 118296370A CN 202410282017 A CN202410282017 A CN 202410282017A CN 118296370 A CN118296370 A CN 118296370A
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- neural network
- model
- train
- 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 41
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 27
- 238000003062 neural network model Methods 0.000 claims abstract description 21
- 230000008859 change Effects 0.000 claims abstract description 15
- 238000003745 diagnosis Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000001816 cooling Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000000498 cooling water Substances 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a train fault prediction method and a train fault prediction system based on a neural network, wherein the train fault prediction method comprises the following steps: acquiring the data change rate before the occurrence time of the historical fault of the vehicle, the occurrence times of the historical fault and other fault judgment conditions; training the neural network model by taking the acquired data as input data to obtain a trained model; and acquiring real-time running data of the vehicle, and inputting the real-time running data into the trained model for real-time fault prediction. The invention carries out intelligent prediction on train faults, so that the train can work more stably and safely.
Description
Technical Field
The invention belongs to the technical field of fault prediction, and particularly relates to a train fault prediction method and system based on a neural network.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The reliability and the safety of the high-speed motor train unit train in the running process have great significance for rail transit, and each train fault is related to the traveling of passengers.
The current fault diagnosis is fixed judgment logic and fixed threshold value is set, when the fault condition is met, fault alarm is carried out, a driver is prompted to carry out related operation, and a method and a mechanism for predicting the fault are lacked.
Especially, under the condition that the unmanned train becomes an industry development trend, if intelligent prediction on train faults cannot be realized, stable and safe work cannot be realized by the train.
Disclosure of Invention
In order to solve the problems, the invention provides a train fault prediction method based on a neural network, which intelligently predicts train faults and enables the trains to work more stably and safely.
According to some embodiments, the present invention employs the following technical solutions:
In a first aspect, a neural network-based train fault prediction method is disclosed, comprising:
acquiring the data change rate before the occurrence time of the historical fault of the vehicle, the occurrence times of the historical fault and other fault judgment conditions;
training the neural network model by taking the acquired data as input data to obtain a trained model;
and acquiring real-time running data of the vehicle, and inputting the real-time running data into the trained model for real-time fault prediction.
As a further technical scheme, before the data change rate before the occurrence time of the historical fault of the vehicle, the occurrence times of the historical fault and other fault judging conditions are obtained, data recorded by the train subsystem equipment and the network control system equipment are collected and cleaned, the recorded data are time series data, and each time series data comprises sensor data and operation record information in a period of time.
As a further technical solution, the predicted fault type is a fault diagnosis logic having an analog quantity as a judgment condition.
As a further technical solution, the process of obtaining data is: diagnostic logic for determining a fault and extracting data for a fault condition from the recorded data.
As a further technical scheme, the extracted data is normalized, the data set is divided into a training set, a verification set and a test set, the cross verification method is used for training and verification, and in the training process, a counter propagation algorithm and an optimizer are required to be used for optimizing and adjusting the model, meanwhile, network super parameters are required to be adjusted, and then a preliminary artificial neural network model is established.
As a further technical scheme, the neural network model adopts an RNN model, and the RNN is a model applicable to sequence data;
the network structure of the neural network model comprises an input layer, a hidden layer and an output layer;
in the RNN model, the output of the hidden layer will be used as input for the next time step to build the dependency of the sequence data;
And according to the specific fault logic of the single fault, determining fixed fault parameters and thresholds corresponding to each fault, and using different types of RNN models to meet different data characteristics and prediction targets.
As a further technical scheme, the neural network model is deployed in a train network control system to predict faults, and is updated continuously.
In a second aspect, a neural network-based train fault prediction system is disclosed, comprising:
a data acquisition module configured to: acquiring the data change rate before the occurrence time of the historical fault of the vehicle, the occurrence times of the historical fault and other fault judgment conditions;
a model training module configured to: training the neural network model by taking the acquired data as input data to obtain a trained model;
A real-time prediction module configured to: and acquiring real-time running data of the vehicle, and inputting the real-time running data into the trained model for real-time fault prediction.
Compared with the prior art, the invention has the beneficial effects that:
According to the invention, aiming at the diagnosis logic of the train faults, the artificial neural network is selected to predict the faults by combining with the actually recorded train sample data, and the method has the self-adaption and self-learning capabilities and has the advantages in large-scale operation and processing. By the method, a fault prediction model can be accurately established, so that a train fault diagnosis mode is more intelligent, and the safety and reliability of the train are improved.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a schematic diagram of model training for an example of the present disclosure;
fig. 2 is a schematic diagram of real-time prediction according to an embodiment of the present disclosure.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Embodiment one:
In this embodiment, a train fault prediction method based on a neural network is disclosed, including:
acquiring the data change rate before the occurrence time of the historical fault of the vehicle, the occurrence times of the historical fault and other fault judgment conditions;
training the neural network model by taking the acquired data as input data to obtain a trained model;
and acquiring real-time running data of the vehicle, and inputting the real-time running data into the trained model for real-time fault prediction.
Referring to fig. 1 and 2, the model is trained and predicted, wherein the diagnosis logic of faults is determined first, the basic diagnosis logic condition of each fault is determined, and the data required by the diagnosis conditions is extracted from the real-time train data recorded by the wireless transmission device. And carrying out normalization processing on the extracted data, and establishing a preliminary artificial neural network model after selecting a proper neural network model according to different diagnostic logics. And aiming at the data in the fault diagnosis logic conditions, establishing an artificial neural network model by taking the occurrence times of the faults, the related data change rate at the moment of the faults and other fault judgment conditions as inputs, and simultaneously forming a training data set. And (3) carrying out weight correction on the neural network by combining with the training data set, carrying out weight adjustment according to errors calculated by the neural network, and finally obtaining an accurate fault prediction model.
The processing process of the trained model on the data is as follows: the real-time running data of the vehicle can be subjected to corresponding data change calculation, and the calculated result is input as a model to participate in model prediction. In addition, the model is a neural network model, the neural network model can be considered as a black box (function), a plurality of trained parameters are arranged in the neural network model, data are input through the input end of the model, and the model analyzes and calculates the data by utilizing the trained parameters, so that a prediction result is obtained.
In determining diagnostic logic for a fault, for example: taking a cooling fault of the traction transformer as an example, the fault diagnosis logic judges the equipment fault when the temperature of an oil outlet or an oil inlet of the traction transformer exceeds a certain set threshold value.
And (3) carrying out weight correction on the neural network by combining with the training data set, and carrying out loss value calculation (calculation error) by using a predicted result and a set real result in the training process, and optimizing and adjusting parameters or weights in the neural network by using a back propagation algorithm and an optimizer.
The predicted faults in this embodiment are faults diagnosed by the network control system, and mainly include faults of high voltage, traction, assistance, and the like.
The obtained samples are mainly analog data acquired by the network control system through the input and output module, such as the temperature of an oil outlet of a traction transformer of a train, the temperature of an oil inlet of the traction transformer, the temperature of cooling water, motor current and the like.
Most of traditional fault diagnosis logics carry out fault alarm and follow-up automatic processing measures after the monitoring value exceeds a certain set threshold value, and the influence on equipment in the running process is large. Taking a cooling fault of the traction transformer as an example, the traditional fault logic is that if the temperature of an oil outlet or an oil inlet of the traction transformer exceeds a certain set threshold value, the equipment is judged to be faulty, so that the traction transformer is blocked to cause corresponding power loss of the motor train unit. If the probability of failure occurrence can be predicted before failure occurrence, the network control system sends operation instructions to the traction transformation cooling system again or reduces the operation power of the traction transformer, so that the safety of equipment and the operation efficiency of the motor train unit are protected to a certain extent.
According to the technical scheme, on the basis of an existing fault logic model, related data before the historical fault moment is subjected to learning analysis through a neural network, the data change rate is increased to serve as a condition for judging the occurrence probability of faults, the data change rate serves as input (characteristic parameters) of the neural network model, and training and prediction of the model are participated.
The related data before the historical fault moment is subjected to learning analysis through a neural network, and the method specifically comprises the following steps: the neural network model is used as a black box model (function), and contains a large number of neurons and parameters, and the trained neural network model can automatically learn and analyze the related data before the historical fault moment.
In the technical scheme of the disclosure, the artificial neural network adopts RNN, which is a neural network suitable for time series data, and future faults can be predicted by analyzing and predicting historical data. RNNs have advantages in handling long-term dependencies and sequence data and are often used to handle continuous time series data.
Firstly, collecting and cleaning data recorded by train subsystem equipment and network control system equipment. RNN is a model applicable to sequence data, and train record data is time-series data as well. Each time series data contains information such as sensor data and operation records for a period of time. At the same time, these data need to be preprocessed, e.g., normalized, etc., for subsequent training and prediction.
Establishing an RNN model requires defining a network structure and superparameters, the network structure typically including an input layer, a hidden layer and an output layer. In RNN, the output of the hidden layer will be used as input for the next time step to establish the dependency of the sequence data. The fixed fault parameters and thresholds corresponding to each fault are determined according to the specific fault logic of the single fault, and the extraction and selection of the characteristics are carried out by the model, so that different types of RNN models are used to meet different data characteristics and prediction targets.
Before training the RNN model, the data set needs to be divided into three parts, a training set, a validation set and a test set. The training and verification may be performed using methods such as cross-validation to avoid over-fitting and under-fitting. During training, the model needs to be optimized and adjusted using a back-propagation algorithm and an optimizer. Meanwhile, network super parameters such as learning rate, network layer number, hidden layer dimension and the like need to be adjusted so as to obtain better prediction performance.
The model is deployed and maintained, the model can be deployed in a train network control system for fault prediction, and the accuracy and reliability of the model are ensured by continuously updating the model and the data.
The above-described fault prediction involves multiple faults of multiple systems, and the fault logic requires specific analysis. The fault diagnosis is calculated in real time with the operation of the train. The plurality of logics are associated.
The method is characterized in that a neural network technology is applied to a predictive fault diagnosis method, traditional fault diagnosis logic is taken as a prototype, analog quantity data in the fault logic is predicted through a mature algorithm, historical operation data of equipment such as a transformer, a converter and the like, train load and operation environment data are taken as bases, proper state variables are selected as model inputs according to the influence on the operation state of the equipment, an association relation between multiple influence factors and analog quantity is established through a corresponding analog quantity prediction model, a proper RNN architecture such as a long-short-term memory network (LSTM) is selected, the method is widely applied in time sequence data processing, and time dependence and dynamic change in analog quantity signals are captured through the network structures. And predicting the new analog quantity signal by using the trained RNN model. And (5) combining the prediction data, the real acquisition data and expert knowledge to establish a predictive fault diagnosis model. According to the possibility of the predicted faults, the optimal fault decision meeting the operation requirements, such as equipment load shedding, automatic equipment restarting and the like, is provided, and the direct triggering faults are avoided to enable the train to be in an abnormal operation state. And analyzing the relation between the real-time data and the running state of the equipment, in particular the change rule of analog quantity data related to the fault diagnosis condition before the occurrence of the historical fault, and continuously learning and updating model parameters to form a new fault diagnosis model.
Embodiment two:
based on the method of the first embodiment, a train fault prediction system based on a neural network is disclosed, comprising:
a data acquisition module configured to: acquiring the data change rate before the occurrence time of the historical fault of the vehicle, the occurrence times of the historical fault and other fault judgment conditions;
a model training module configured to: training the neural network model by taking the acquired data as input data to obtain a trained model;
A real-time prediction module configured to: and acquiring real-time running data of the vehicle, and inputting the real-time running data into the trained model for real-time fault prediction.
Embodiment III:
It is an object of the present embodiment to provide a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, which processor implements the steps of the above method when executing the program.
Example IV
An object of the present embodiment is to provide a computer-readable storage medium.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (10)
1. The train fault prediction method based on the neural network is characterized by comprising the following steps of:
acquiring the data change rate before the occurrence time of the historical fault of the vehicle, the occurrence times of the historical fault and other fault judgment conditions;
training the neural network model by taking the acquired data as input data to obtain a trained model;
and acquiring real-time running data of the vehicle, and inputting the real-time running data into the trained model for real-time fault prediction.
2. The neural network-based train fault prediction method of claim 1, wherein the data recorded by the train subsystem device and the network control system device are collected and cleaned before the data change rate before the occurrence time of the historical fault of the vehicle, the occurrence times of the historical fault and other fault judgment conditions are obtained, the recorded data are time series data, and each time series data comprises sensor data and operation record information in a period of time.
3. The neural network-based train fault prediction method of claim 1, wherein the predicted fault type is fault diagnosis logic having an analog quantity as a judgment condition.
4. The neural network-based train fault prediction method as claimed in claim 1, wherein the process of acquiring data is: diagnostic logic for determining a fault and extracting data for a fault condition from the recorded data.
5. The neural network-based train fault prediction method of claim 4, wherein the extracted data is normalized, the data set is divided into a training set, a verification set and a test set, the training and verification are performed by using a cross verification method, and during the training process, the model is required to be optimized and adjusted by using a back propagation algorithm and an optimizer, and meanwhile, network superparameters are required to be adjusted, and then a preliminary artificial neural network model is established.
6. The neural network-based train fault prediction method according to any one of claims 1 to 5, wherein the neural network model adopts an RNN model, which is a model suitable for sequence data;
the network structure of the neural network model comprises an input layer, a hidden layer and an output layer;
in the RNN model, the output of the hidden layer will be used as input for the next time step to build the dependency of the sequence data;
And according to the specific fault logic of the single fault, determining fixed fault parameters and thresholds corresponding to each fault, and using different types of RNN models to meet different data characteristics and prediction targets.
7. The neural network-based train fault prediction method of claim 6, wherein the neural network model is deployed in a train network control system to predict faults, and the neural network model is updated continuously.
8. Train fault prediction system based on neural network, characterized by includes:
a data acquisition module configured to: acquiring the data change rate before the occurrence time of the historical fault of the vehicle, the occurrence times of the historical fault and other fault judgment conditions;
a model training module configured to: training the neural network model by taking the acquired data as input data to obtain a trained model;
A real-time prediction module configured to: and acquiring real-time running data of the vehicle, and inputting the real-time running data into the trained model for real-time fault prediction.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any of the preceding claims 1-7 when the program is executed by the processor.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, performs the steps of the method of any of the preceding claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410282017.4A CN118296370A (en) | 2024-03-12 | 2024-03-12 | Train fault prediction method and system based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410282017.4A CN118296370A (en) | 2024-03-12 | 2024-03-12 | Train fault prediction method and system based on neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118296370A true CN118296370A (en) | 2024-07-05 |
Family
ID=91686740
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410282017.4A Pending CN118296370A (en) | 2024-03-12 | 2024-03-12 | Train fault prediction method and system based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118296370A (en) |
-
2024
- 2024-03-12 CN CN202410282017.4A patent/CN118296370A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107194053B (en) | Intelligent elevator control system operation fault prediction method | |
| CN111178553A (en) | Industrial equipment health trend analysis method and system based on ARIMA and LSTM algorithms | |
| CN114048600A (en) | Digital twin-driven multi-model fusion industrial system anomaly detection method | |
| JP3651693B2 (en) | Plant monitoring diagnosis apparatus and method | |
| Mathew et al. | Regression kernel for prognostics with support vector machines | |
| CN113888353A (en) | Energy efficiency diagnosis method, system and medium for distributed photovoltaic power generation equipment | |
| TWI794907B (en) | Prognostic and health management system for system management and method thereof | |
| KR20230050812A (en) | Remaining useful life prediction method of fuel cell system and digital twin device performing the same | |
| CN118154174A (en) | Intelligent operation and maintenance cloud platform for industrial equipment | |
| CN111860839A (en) | Shore bridge fault monitoring method based on multi-signal fusion and Adam optimization algorithm | |
| CN110597235A (en) | Universal intelligent fault diagnosis method | |
| CN113505535A (en) | Motor life prediction method based on gate control self-adaptive hierarchical attention unit network | |
| CN114925718A (en) | Transformer core grounding current online prediction method and device, storage medium and fault diagnosis method | |
| CN111241629B (en) | Intelligent prediction method for performance change trend of hydraulic pump of airplane based on data driving | |
| CN117471346A (en) | Method and system for determining remaining life and health status of retired battery module | |
| CN117312972A (en) | Method for identifying health state of scraper conveyor speed reducer | |
| CN117743961A (en) | Cable joint fault detection method and system based on long-short-term memory LSTM | |
| CN118296370A (en) | Train fault prediction method and system based on neural network | |
| CN114386603B (en) | Thermal power plant generator fault early warning method based on time sequence causal network | |
| Niu et al. | A hybrid bearing prognostic method with fault diagnosis and model fusion | |
| CN116933003A (en) | Remaining service life prediction method of unmanned aerial vehicle engine based on DaNet | |
| Virk et al. | Fault prediction using artificial neural network and fuzzy logic | |
| KR20230106778A (en) | Apparatus for optimizing chemical dosing in water treatment plants and method therefor | |
| RU2735296C1 (en) | Method for multi-parameter monitoring of complex electrotechnical objects state | |
| Chen et al. | EPBS_FIDMV: A fault injection and diagnosis methods validation benchmark for EPBS of EMU |
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 |