JP4886460B2 - Abnormality monitoring device - Google Patents

Abnormality monitoring device Download PDF

Info

Publication number
JP4886460B2
JP4886460B2 JP2006278976A JP2006278976A JP4886460B2 JP 4886460 B2 JP4886460 B2 JP 4886460B2 JP 2006278976 A JP2006278976 A JP 2006278976A JP 2006278976 A JP2006278976 A JP 2006278976A JP 4886460 B2 JP4886460 B2 JP 4886460B2
Authority
JP
Japan
Prior art keywords
target
vector
unit
category
signal
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.)
Expired - Fee Related
Application number
JP2006278976A
Other languages
Japanese (ja)
Other versions
JP2008097360A (en
Inventor
秀和 姫澤
良仁 橋本
Original Assignee
パナソニック電工Sunx株式会社
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by パナソニック電工Sunx株式会社 filed Critical パナソニック電工Sunx株式会社
Priority to JP2006278976A priority Critical patent/JP4886460B2/en
Publication of JP2008097360A publication Critical patent/JP2008097360A/en
Application granted granted Critical
Publication of JP4886460B2 publication Critical patent/JP4886460B2/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Description

  The present invention relates to an abnormality monitoring apparatus that classifies electrical signals reflecting the operation of an inspection target by a competitive learning type neural network to determine whether the operation of the inspection target is abnormal.

  2. Description of the Related Art Conventionally, a technique for classifying a target signal obtained from a test object by using a classification function of a neural network (neurocomputer) is known. This type of technology is used in an abnormality monitoring apparatus that recognizes voice and determines whether an apparatus is operating normally or whether an apparatus has an abnormality. For example, in an abnormality monitoring apparatus that employs this type of technology, the operation sound of the device or the vibration of the device is converted into an electrical signal by a sensor unit (transducer), and the output of the sensor unit is used as the target signal. Various techniques for extracting feature vectors composed of a plurality of elements to be represented and classifying the feature vectors using a neural network have been proposed.

  Various configurations are known for neural networks. For example, it has been proposed to classify feature vector categories using a competitive learning type neural network (self-organizing map = SOM). The competitive learning type neural network is a neural network including two layers of an input layer and an output layer, and performs two operations of a learning mode and an inspection mode.

  In the learning mode, learning data is given without using a teacher signal. If a category is given to learning data, a category can be associated with a neuron in the output layer, and a cluster of neurons belonging to the same category can be formed. Accordingly, in the learning mode, a clustering map indicating a category can be associated with a cluster of neurons in the output layer.

In the inspection mode, the feature vector (input data) to be classified is given to the learned competitive learning type neural network, and the category of the cluster to which the fired neuron belongs in the clustering map is checked against the clustering map. Can be classified (see, for example, Patent Document 1).
JP 2004-354111 A

  By the way, in the structure described in patent document 1, since one kind of target signal is taken out from the inspection target, an abnormality at one place can be detected, but the inspection target includes a plurality of elements as in the equipment device. When configured in combination, the location where the target signal is extracted often operates in cooperation with other locations, so before an abnormality is detected at the location where the target signal is extracted There may be signs of abnormality elsewhere. In addition, when the operations at a plurality of places are combined, a sign of abnormality may be seen. Alternatively, it may be possible to detect a sign of abnormality by extracting a plurality of types of information even with one target signal.

  However, in the technique described in Patent Document 1, only the features obtained for one type of target signal are classified by the competitive learning type neural network, and even if a plurality of types of target signals are extracted from the inspection target, the presence or absence of abnormality is detected. Cannot be judged properly.

  In addition, it is possible to increase the number of neurons in the input layer in a competitive learning type neural network and enable input of multiple types of target signals, but if this configuration is adopted, the size of the competitive learning type neural network will increase. The problem arises. Moreover, since the categories set in the competitive learning neural network are a combination of categories for each target signal, the number of combinations increases as the number of target signals increases. It takes a lot of time to learn.

  The present invention has been made in view of the above-mentioned reasons, and its purpose is to enable early detection of an abnormality sign of a test object by extracting a plurality of types of target signals from the test object, and a competitive learning type An object of the present invention is to provide an anomaly monitoring apparatus that does not require an increase in the scale of a neural network and does not increase the time required for learning in combination even if the types of target signals increase.

The invention according to claim 1 is characterized in that a signal input unit that takes in a plurality of types of target signals from an inspection target using an electrical signal that reflects the operation of the inspection target as a target signal, and a feature vector that represents a feature for each target signal, respectively. An extraction unit and each feature signal extracted by the feature extraction unit as input data and the feature vector obtained for each target signal when the inspection target is operating normally as learning data. As a category classification unit consisting of a competitive learning type neural network in which the weight vector corresponding to the category of the learning data is set in each neuron of the output layer by learning in advance, and multiple types of target signals obtained by the operation of the inspection target each, a feature vector of the target signal, the neurons of the output layer in the category classification unit Chi, a deviation calculation unit for determining the magnitude of the deviation degree, the deviance deviance calculation unit is determined for each target signal component of the difference vector between weight vector set to neurons ignite by the input of the target signal And a discriminating unit that discriminates whether or not there is an abnormality to be inspected based on the existence area of the multidimensional divergence vector.

According to a second aspect of the present invention, in the first aspect of the invention, the determination unit includes a competitive learning type neural network that is learned by using a deviation vector when the inspection target is operating normally as learning data. Features.

According to a third aspect of the present invention, in the first or second aspect of the present invention, the category classification unit includes a competitive learning type neural network for each inspection signal .

According to the configuration of the invention according to claim 1, capable of integrating the information of a plurality of types of target signals by stroke rate vector. That is, it is possible to detect a sign of an abnormality to be inspected early using a plurality of types of target signals. In addition, the category classification unit does not need to classify multiple types of target signals in a comprehensive manner, and comprehensive determination based on multiple types of target signals is performed by the determination unit, so a category that combines the categories of each type of target signal is set. As a result, as a category classification unit, it is possible to comprehensively determine information on a plurality of types of target signals without using a large-scale competitive learning type neural network. That is, there is an advantage that the time required for learning does not increase in combination even if the types of target signals increase. Here, increasing in combination means increasing in relations such as a power and factorial larger than the proportional relation.

Furthermore, since the feature vector when the inspection target is operating normally is used as the learning data, a normal state category is set for each target signal in the competitive learning type neural network as the category classification unit. Become. In other words, each target signal when the inspection target is normal is set as a category in the category classification unit. Therefore, the learning data only needs to have a feature vector corresponding to each target signal while the inspection target is operating normally, and the number of learning data sets should be the same as the type of the target signal. That is, even if the types of target signals increase, the increase in the set of learning data is proportional, and does not increase in combination.

According to the configuration of the second aspect of the present invention, since the competitive learning type neural network is used as the discriminating unit, the discriminating unit is made to learn by using the deviation vector when the inspection target is operating normally as learning data. The test result corresponding to the existence area of the divergence vector in the multidimensional space can be obtained by the difference between the divergence vector generated in the category classification unit and the weight vector of the neuron in the output layer in the determination unit. That is, the presence or absence of an abnormality to be examined can be known from the firing state of the neurons in the output layer in the competitive learning type neural network as the discriminating unit.

According to the configuration of the invention of claim 3 , since the competitive learning type neural network for each target signal is used in the category classification unit, a plurality of competitive learning type neural networks are required, but one neuron in the output layer is different from each other. Since the categories of a plurality of types of target signals are not set redundantly, the detection accuracy of the presence / absence of abnormality is increased.

  In the embodiment described below, an example in which the technique of the present invention is employed in an abnormality monitoring device that determines whether the operation of the inspection target is normal or abnormal based on the feature vector of the target signal generated by the operation of the inspection target will be described. Moreover, although the installation apparatus provided with motive power sources like a motor is assumed as a test object, the kind of test object is not ask | required in particular.

  As shown in FIG. 1, the abnormality monitoring apparatus described in the present embodiment uses a category classification unit 1 composed of an unsupervised competitive learning type neural network (hereinafter simply referred to as “neural network”). As shown in FIG. 2, the neural network as the category classification unit 1 includes two layers of an input layer 11 and an output layer 12, and each neuron N <b> 2 of the output layer 12 is connected to all the neurons N <b> 1 of the input layer 11. It has a combined configuration. The neural network as the category classification unit 1 is assumed to be realized by executing an appropriate application program on a sequential processing type computer, but a dedicated neurocomputer can also be used.

  The operation of the neural network as the category classification unit 1 includes a learning mode and an inspection mode. After learning using appropriate learning data in the learning mode, a plurality of elements generated from actual target signals in the inspection mode are used. The feature vector (input data) category is classified.

  The degree of connection (weighting coefficient) between the neuron N1 of the input layer 11 and the neuron N2 of the output layer 12 is variable, and in the learning mode, the category classification unit 1 is made to learn by inputting learning data to the category classification unit 1. The weighting coefficient for each neuron N1 in the input layer 11 and each neuron N2 in the output layer 12 is determined. In other words, each neuron N2 in the output layer 12 is associated with a weight vector whose element is a weight coefficient between each neuron N1 in the input layer 11. Therefore, the weight vector has the same number of elements as the neuron N1 of the input layer 11, and the number of elements of the feature vector input to the input layer 11 matches the number of elements of the weight vector.

  On the other hand, in the inspection mode, when input data whose category is to be determined is given to the input layer 11 of the learned category classification unit 1, the Euclidean distance between the weight vector and the input data among the neurons N2 of the output layer 12 is the smallest. A neuron N2 fires. If a category is associated with the neuron N2 of the output layer 12 in the learning mode, the category of the input data can be known from the category of the position of the fired neuron N2.

  A category is associated with each neuron N2 of the output layer 12 in the neural network that is the category classification unit 1 in the procedure described later. In this embodiment, the category classification unit 1 classifies two categories, normal and abnormal, and inputs only learning data of normal categories in the learning mode. That is, when the input data given in the inspection mode does not belong to the normal category set in the category classification unit 1, the input data is regarded as abnormal.

  The category of learning data is reflected in the category of each neuron N2 in the output layer 12, and when a large number (for example, 150) of learning data is given, the learning data among the neurons N2 in the output layer 12 in the category classification unit 1 A weight vector having a small Euclidean distance from the learning data is set in the neuron N2 corresponding to the category. That is, the neuron N2 is fired by giving the learning data after learning. The learning data given to the category classification unit 1 in the learning mode is stored in the learning data storage unit 7 and is read from the learning data storage unit 7 and given to the category classification unit 1 as necessary.

  By the way, the target signal classified by the category classification unit 1 is an electrical signal obtained in accordance with the operation of the equipment device (hereinafter simply referred to as “device”) X, and detects, for example, vibration generated during the operation of the device X. The output of the signal input unit 2 composed of a vibration sensor is used. As the vibration sensor, an acceleration pickup that detects acceleration in three axes (that is, three directions orthogonal to each other) is used.

  However, the configuration of the signal input unit 2 can be appropriately selected according to the type of the device X, and various sensors such as a microphone, a TV camera, and an odor sensor that detect the operation sound of the device X are used alone or in combination. be able to. Alternatively, a signal generated by the device X can be taken out and used as a target signal. In the above example, a configuration in which three types of target signals are obtained from the vibration sensor provided in one place is adopted, but a configuration in which the target signals are extracted from a plurality of places of the device X to be inspected is adopted. Also good.

  The target signal, which is an electrical signal obtained by the signal input unit 2, is given to the feature extraction unit 4, and a feature vector representing the feature of the target signal is extracted. The feature extraction unit 4 extracts feature vectors for each of the three types of target signals. Therefore, the multiplexer 3 is provided between the signal input unit 2 and the feature extraction unit 4, and three types of target signals are sequentially input to the feature extraction unit 4. When the types of target signals are small, feature vectors of each target signal may be extracted by providing a plurality of feature extraction units 4.

  In addition, in order to extract a feature vector under the same conditions from the target signal generated by the device X in the feature extraction unit 4, the signal input unit 2 temporarily stores a buffer memory (first-in first-out memory) for each type of target signal. It is desirable to match the timings of extracting feature vectors for each target signal selected by the multiplexer 3. In addition, since each target signal needs to extract a target signal during the period in which the device X is operating, a timing signal (trigger signal) synchronized with the operation of the device X is used, or the waveform characteristics ( For example, the timing of segmenting the target signal from the output of the signal input unit 2 is determined by using a group of target signals. The target signal output from the device X is assumed to have periodicity, and segmentation is divided for each period, and a feature vector for each period is extracted. Further, the feature extraction unit 4 performs preprocessing for reducing noise by limiting the frequency band as necessary. Furthermore, the feature extraction unit 4 also has a function of converting the target signal into a digital signal.

  In order to simplify the explanation, here, a plurality of frequency components (power for each frequency band) are extracted from the target signal after segmentation, and a vector having each frequency component as an element is used as a feature vector. To do. For the extraction of frequency components, an FFT (Fast Fourier Transform) technique or a filter bank made up of a large number of bandpass filters is used. Which frequency power is used as an element of the feature vector is appropriately selected according to the target device X and the abnormality to be extracted.

  The feature vector obtained for each period from the feature extraction unit 4 is given to the category classification unit 1 every time the feature vector is extracted. The feature vector is also stored in the learning data storage unit 7 for use as learning data. The learning data storage unit 7 has a capacity for holding, for example, 150 feature vectors as learning data.

  Here, a set of data stored in the learning data storage unit 7 is called a data set, and each data constituting the data set corresponds to a specific category (that is, a normal category for each target signal). It shall be attached. Since the feature vectors in the normal state are extracted for the three types of target signals as described above, there are three categories.

  In order to be able to use the category classification unit 1 formed of a neural network, first, the category classification unit 1 is set to the learning mode, and the category classification unit 1 is trained using the learning data stored in the learning data storage unit 7. When learning by the category classification unit 1 is performed, a weight vector is set for each neuron N2 in the output layer 12 of the category classification unit 1. Here, since there are three categories, when the feature vectors of the three types of target signals have a sufficient difference, three regions are also formed in the neuron N2 of the output layer 12.

  After the weight vector is set for each neuron N2 of the output layer 12 in the category classification unit 1, when the learning data is re-input using the category classification unit 1 formed of a neural network as the inspection mode, the neuron N2 corresponding to the category of the learning data is displayed. set a fire. Since the firing neuron N2 is the neuron N2 having the minimum Euclidean distance between the weight vector and the input data, the feature vector of each target signal is given to the learned category classifying unit 1 and the Euclidean distance (difference between the weight vector and the input vector). When an evaluation value corresponding to the magnitude of the vector is obtained, the degree of belonging to each category can be evaluated.

As this evaluation value, the degree of divergence is used. The degree of divergence is a value obtained by normalizing the magnitude of the difference vector between the weight vector and the feature vector. If the feature vector is [X] and the weight vector of the neuron N2 associated with the category is [Wwin] ([a ] Means that a is a vector), and the divergence degree Y is defined by the following equation.
Y = ([X] / X- [Wwin] / Wwin) T ([X] / X- [Wwin] / Wwin)
Here, T represents transposition, and X and Wwin without a square bracket indicate the norm of each vector. Normalized by dividing each vector element by the norm.

The divergence degree is obtained by the divergence degree calculation unit 5 using the weight vector set in the category classification unit 1 and the input data (feature vector) to the category classification unit 1. When the divergence degrees of the respective target signals are obtained, three divergence degrees are obtained, so that a divergence degree vector having the divergence degree as an element can be defined. As is apparent from the definition of the divergence degree, if each target signal is normal, each element of the divergence degree vector is substantially zero, and thus the magnitude of the divergence degree vector is substantially zero.

  Therefore, if a multidimensional vector space having the divergence degree of each target signal as an axis is set, and the existence area of the divergence degree vector in this multidimensional space is determined, it is determined whether or not the operation of the device X is normal. Can do. In this embodiment, since there are three types of target signals, a three-dimensional vector space can be set as shown in FIG. In this vector space, if a spherical area centered on the origin is set as the normal area D, it is determined that the operation of the device X is normal when the divergence vector V is within the area D. Can do.

  A determination unit 6 is provided to determine whether there is an abnormality in the operation of the device X based on the degree of deviation. The discriminant obtained by the discrepancy calculator 5 is input to the discriminator 6. Here, as described above, the multiplexer 3 is provided and the respective target signals are sequentially input to the feature extraction unit 4, so the divergence degree calculation unit 5 sequentially obtains the divergence degrees. Accordingly, the determination unit 6 is provided with a register in which the divergence degrees sequentially obtained by the divergence degree calculation unit 5 are sequentially input, and the divergence degree vector is transferred to the next stage by reading data from the registers in parallel.

  The discriminating unit 6 obtains the norm of the deviation degree vector having the deviation degree for each target signal as an element, and compares it with a threshold value (corresponding to the radius of the spherical region D) defined by the obtained norm. If the norm is less than or equal to the threshold, it can be determined that the device X is normal, and if the norm exceeds the threshold, it can be determined that the device X is abnormal or has a sign of abnormality. Further, if the region D is set to an appropriate shape instead of a spherical shape, early detection for a specific abnormality can be performed.

  The discriminator 6 has a configuration in which the norm of the divergence degree vector is compared with a threshold, and a competitive learning type neural network (hereinafter referred to as “ A neural network ") may be used. If a neural network is used for the discriminating unit 6, a normally corresponding category is set. If the divergence vector input to the discriminating unit 6 does not belong to the normal category, is there an abnormality in the device X? It can be determined that there is a sign of abnormality.

  In the above configuration example, since the category classification unit 1 employs a configuration in which a plurality of types of target signals are classified by a neural network, if the characteristics of the target signals are similar, the categories are different (the target signal The same neuron N2 may fire regardless of the type. Since the feature vector corresponding to each target signal is input to the category classification unit 1 at different times, there is no problem if different categories are set in the same neuron N2, but a neural network is set for each target signal. Such a duplication can be avoided if the provided configuration is adopted.

  When the same number of neural networks as the types of target signals are provided, the same number of feature extraction units 4 are provided, so that the multiplexer 3 and the register in the determination unit 6 become unnecessary. However, since a plurality of feature extraction units 4, neural networks, and divergence degree calculation units 5 are required, the scale increases.

  In the above operation example, the divergence degree is obtained every time during the operation of the device X, and the presence or absence of an abnormality or a sign of abnormality is determined at each time point. It can be expected that signs of abnormality will be detected even earlier due to the change tendency of the degree vector. In the above example, the category is only normal, but another category may be used.

It is a block diagram which shows embodiment of this invention. It is a schematic block diagram of the neural network used for the same as the above. It is a figure which shows the principle of the discrimination | determination part used for the same as the above.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Category classification | category part 2 Signal input part 3 Multiplexer 4 Feature extraction part 5 Deviation degree calculation part 6 Discrimination part 7 Learning data memory | storage part 11 Input layer 12 Output layer N1 neuron N2 neuron X apparatus

Claims (3)

  1. A signal input unit that captures a plurality of types of target signals from the inspection target using an electrical signal that reflects the operation of the inspection target as a target signal, a feature extraction unit that extracts a feature vector representing each feature signal, and a feature extraction unit Each feature vector extracted in step 1 is used as input data when the test target is operating normally, and the feature vector obtained for each target signal is used as learning data, and each target signal is output by learning in advance as one category. A category classification unit consisting of a competitive learning type neural network in which a weight vector corresponding to the category of learning data is set for each neuron of the layer, and for each of a plurality of types of target signals obtained by the operation of the inspection target , Among the feature vectors and neurons in the output layer of the category classification unit, the target signal Multidimensional deviation to the deviation calculation unit for determining the magnitude of the difference vector as a deviance, and the deviance deviance calculation unit is determined for each target signal component of the weight vector set to neurons ignite by the input An abnormality monitoring apparatus comprising: a determination unit configured to determine presence or absence of an abnormality to be inspected based on a presence area of a degree vector.
  2. 2. The abnormality monitoring apparatus according to claim 1 , wherein the discriminating unit includes a competitive learning type neural network learned by using a deviation vector when the inspection target is operating normally as learning data .
  3. The categorization unit, the abnormality monitoring equipment according to claim 1 or claim 2, characterized in that it comprises a competitive learning neural network for each target signal.
JP2006278976A 2006-10-12 2006-10-12 Abnormality monitoring device Expired - Fee Related JP4886460B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2006278976A JP4886460B2 (en) 2006-10-12 2006-10-12 Abnormality monitoring device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2006278976A JP4886460B2 (en) 2006-10-12 2006-10-12 Abnormality monitoring device

Publications (2)

Publication Number Publication Date
JP2008097360A JP2008097360A (en) 2008-04-24
JP4886460B2 true JP4886460B2 (en) 2012-02-29

Family

ID=39380132

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2006278976A Expired - Fee Related JP4886460B2 (en) 2006-10-12 2006-10-12 Abnormality monitoring device

Country Status (1)

Country Link
JP (1) JP4886460B2 (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6226463B2 (en) * 2013-09-30 2017-11-08 Kddi株式会社 Network management system, network device and control device
FR3012897A1 (en) * 2013-11-07 2015-05-08 Snecma Method and device for characterizing a signal
WO2016151708A1 (en) * 2015-03-20 2016-09-29 株式会社日立製作所 Breakdown detection device and breakdown detection method for electrical appliance
EP3098681B1 (en) * 2015-05-27 2020-08-26 Tata Consultancy Services Limited Artificial intelligence based health management of host system
JP2018147172A (en) * 2017-03-03 2018-09-20 日本電信電話株式会社 Abnormality detection device, abnormality detection method and program

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11338848A (en) * 1998-05-26 1999-12-10 Ffc:Kk Data abnormality detector
JP2002188411A (en) * 2000-12-22 2002-07-05 Mitsubishi Heavy Ind Ltd Abnormality diagnosing apparatus
JP4032045B2 (en) * 2004-08-13 2008-01-16 新キャタピラー三菱株式会社 Data processing method, data processing device, diagnosis method, and diagnosis device

Also Published As

Publication number Publication date
JP2008097360A (en) 2008-04-24

Similar Documents

Publication Publication Date Title
Verstraete et al. Deep learning enabled fault diagnosis using time-frequency image analysis of rolling element bearings
Zhao et al. Machine health monitoring with LSTM networks
Lu et al. Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification
Kang et al. Reliable fault diagnosis for incipient low-speed bearings using fault feature analysis based on a binary bat algorithm
US8630962B2 (en) Error detection method and its system for early detection of errors in a planar or facilities
KR101711936B1 (en) Generalized pattern recognition for fault diagnosis in machine condition monitoring
Lu et al. Dominant feature selection for the fault diagnosis of rotary machines using modified genetic algorithm and empirical mode decomposition
US7181365B2 (en) Diagnostic data detection and control
CN101907088B (en) Fault diagnosis method based on one-class support vector machines
KR20160083127A (en) Method and system for face image recognition
CN101271515B (en) Image detection device capable of recognizing multi-angle objective
Lee et al. Ensemble of convolutional neural networks for weakly-supervised sound event detection using multiple scale input
US5361628A (en) System and method for processing test measurements collected from an internal combustion engine for diagnostic purposes
Wong et al. Modified self-organising map for automated novelty detection applied to vibration signal monitoring
JP2976053B2 (en) Pattern classification and identification system
US10444032B2 (en) Sensor output change detection
WO2015099964A1 (en) Systems and methods for event detection and diagnosis
US20120310597A1 (en) Failure cause diagnosis system and method
Batista et al. A classifier fusion system for bearing fault diagnosis
Tibaduiza et al. Damage classification in structural health monitoring using principal component analysis and self‐organizing maps
JP4321581B2 (en) Machine tool comprehensive monitoring device
US8655571B2 (en) MFCC and CELP to detect turbine engine faults
Wang et al. A novel method for intelligent fault diagnosis of bearing based on capsule neural network
Han et al. An adaptive spatiotemporal feature learning approach for fault diagnosis in complex systems
US20100312502A1 (en) System for detecting leaks in single phase and multiphase fluid transport pipelines

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20080205

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20110524

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20110725

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20110816

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A821

Effective date: 20110902

RD02 Notification of acceptance of power of attorney

Free format text: JAPANESE INTERMEDIATE CODE: A7422

Effective date: 20110902

A711 Notification of change in applicant

Free format text: JAPANESE INTERMEDIATE CODE: A712

Effective date: 20110901

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20111017

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20111129

A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20111209

R150 Certificate of patent or registration of utility model

Free format text: JAPANESE INTERMEDIATE CODE: R150

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20141216

Year of fee payment: 3

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20141216

Year of fee payment: 3

S533 Written request for registration of change of name

Free format text: JAPANESE INTERMEDIATE CODE: R313533

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20141216

Year of fee payment: 3

R350 Written notification of registration of transfer

Free format text: JAPANESE INTERMEDIATE CODE: R350

LAPS Cancellation because of no payment of annual fees