CN112598666B - Cable tunnel anomaly detection method based on convolutional neural network - Google Patents
Cable tunnel anomaly detection method based on convolutional neural network Download PDFInfo
- Publication number
- CN112598666B CN112598666B CN202110011709.1A CN202110011709A CN112598666B CN 112598666 B CN112598666 B CN 112598666B CN 202110011709 A CN202110011709 A CN 202110011709A CN 112598666 B CN112598666 B CN 112598666B
- Authority
- CN
- China
- Prior art keywords
- image
- neural network
- convolutional neural
- layer
- training
- 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.)
- Active
Links
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 41
- 238000001514 detection method Methods 0.000 title claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 36
- 238000007689 inspection Methods 0.000 claims abstract description 16
- 230000002159 abnormal effect Effects 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims abstract description 8
- 238000011176 pooling Methods 0.000 claims description 17
- 230000005856 abnormality Effects 0.000 claims description 11
- 238000000034 method Methods 0.000 claims description 10
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a cable tunnel anomaly detection method based on a convolutional neural network, which comprises a training stage and a testing stage, wherein a standard image a can be input into the convolutional neural network for training in the training stage to obtain a model A; in the test stage, a model A is input by using a daily inspection image sample b, a standard image a corresponding to the model A is obtained, if the image b is the same as or close to the image a, normal data are obtained, and otherwise abnormal data are obtained; the detection method is more accurate, convenient and fast, and is suitable for popularization.
Description
Technical Field
The invention relates to the field of cable tunnel anomaly detection methods, in particular to a cable tunnel anomaly detection method based on a convolutional neural network.
Background
When the tunnel anomaly detection is performed at present, the inspection robot needs to shoot at the same angle at the first position of the image, then the image characteristics are extracted, and whether the current inspection shooting image is an anomaly image or not is judged according to the difference degree of the corresponding characteristics of the two images; the length of the high-voltage cable tunnel is generally 5-10 km, the running speed of the inspection robot is generally 1 m/s, running is completed in a period of hours, the whole tunnel is monitored in a photographing mode, the running speed is greatly reduced, the timeliness of tunnel monitoring is greatly affected, and the main mode of collecting visible light data of the inspection robot is video recording at present, so that the analysis and the processing of the video can be most ideal if the video can be directly analyzed.
Disclosure of Invention
In order to solve the problems, the invention provides a cable tunnel abnormality detection method based on a convolutional neural network, which can convert recorded video into images and then use the convolutional neural network technology to perform abnormality analysis detection.
In order to solve the technical problems, the embodiment of the invention provides a cable tunnel anomaly detection method based on a convolutional neural network, which comprises a training stage and a testing stage, wherein a standard image a can be input into the convolutional neural network for training in the training stage to obtain a model A; in the test stage, a model A is input by using a daily inspection image sample b, a standard image a corresponding to the model A is obtained, if the image b is identical to or close to the image a, normal data are obtained, otherwise abnormal data are obtained, and the steps are as follows:
Converting standard video into an image: extracting an image sequence from a standard video, classifying according to a fixed time period, wherein each image corresponds to a time point, taking any image from a patrol video, determining the corresponding relation between the patrol image and the standard image, and converting the video into an image;
inputting the segmented standard images into a convolutional neural network for training: the convolutional neural network comprises an input layer, a convolutional layer, a pooling layer, a full-connection layer and an output layer, wherein the convolutional layer and the pooling layer form a plurality of convolutional groups, the characteristics are extracted layer by layer, and classification is completed through a plurality of full-connection layers;
The training process is as follows:
1) Inputting a standard image into the convolution set;
2) Updating training parameters;
3) Obtaining training samples needed to be used for each iteration from the standard image data, preprocessing the training samples, and inputting the training samples as a model A;
4) Alternately optimizing by adopting a random gradient descent method, and updating the weight of each part until iteration is finished;
5) Obtaining an abnormality discrimination threshold
Inputting the daily inspection image into a trained convolutional neural network: a patrol image which is the same as the divided standard image time period can be obtained;
(IV) comparing the two images and finding the difference: after finding the standard image corresponding to the inspection image, finding out the mapping relation of the two images through an image registration method, and then making a difference value, and if the difference value is larger than the abnormality judgment threshold value, treating the difference value as an abnormality.
Wherein the objective function/loss function of the convolutional neural network model in step (two) is as follows:
Wherein n is the number of samples, C is the number of classes, xi is the feature of the ith sample, yi is the class label corresponding to xi, and Wj and bj are the weight and bias of class j;
the loss function can measure the inconsistency degree of the predicted value and the true value of the model, and if the error between the classified data obtained by iterative operation of the standard image input network and the expected data is smaller than an abnormal judgment threshold value, the network training is successful;
the training parameters in the step (two) include a minimum batch value N batch, a maximum iteration number M, the number of layers of the convolution and deconvolution network, and the number of feature graphs of each layer of the network.
Preferably, the convolutional neural network is a three-dimensional convolutional neural network, and an input layer of the three-dimensional convolutional neural network receives a four-dimensional array.
Wherein the weights corresponding to the neurons in the convolution layer in the step (two) are fixed.
Wherein, the pooling layer in the step (two) can perform maximum value pooling and average value pooling.
Preferably, the duration of the video slicing in the step (one) is 5 seconds.
The technical scheme of the invention has the following beneficial effects:
1. In the invention, as long as a new object or abnormal situation exists in the tunnel, the object can be identified, and the identification result is not affected by the position and angle deviation caused by shooting in the movement of the inspection robot, so that the detection is more intelligent and accurate;
2. according to the invention, the video can be converted into the image and then distinguished, namely, the inspection robot can complete real-time monitoring of the whole tunnel only by running at normal speed and shooting the video, so that the detection time is saved.
Drawings
Fig. 1 is a block diagram of a convolutional neural network.
Reference numerals illustrate:
01. an input layer; 02. a convolution layer; 03. pooling layers; 04. a full connection layer; 05. and an output layer.
Detailed Description
In order to make the technical problems, technical solutions and advantages to be solved by the present invention more apparent, the following detailed description will be given with reference to the accompanying drawings and specific embodiments, it being apparent that the described embodiments are only some of the embodiments of the present invention, but not all of the embodiments.
As shown in fig. 1, the invention provides a cable tunnel anomaly detection method based on a convolutional neural network, which comprises a training stage and a testing stage, wherein a standard image a can be input into the convolutional neural network for training in the training stage to obtain a model a; in the test stage, a model A is input by using a daily inspection image sample b, a standard image a corresponding to the model A is obtained, if the image b is identical to or close to the image a, normal data are obtained, otherwise abnormal data are obtained, and the steps are as follows:
Converting standard video into an image: extracting an image sequence from a standard video, classifying according to a fixed time period, wherein each image corresponds to a time point, taking any image from a patrol video, determining the corresponding relation between the patrol image and the standard image, and converting the video into an image;
Inputting the segmented standard images into a convolutional neural network for training: the convolutional neural network comprises an input layer 01, a convolutional layer 02, a pooling layer 03, a full connection layer 04 and an output layer 05, wherein the convolutional layer and the pooling layer form a plurality of convolutional groups, characteristics are extracted layer by layer, classification is completed through a plurality of full connection layers, namely the convolutional neural network simulates characteristic distinction through convolution, the magnitude order of network parameters is reduced through weight sharing and pooling of the convolution, and finally tasks such as classification and the like are completed through a traditional neural network;
The training process is as follows:
1) Inputting a standard image into the convolution set;
2) Updating training parameters;
3) Obtaining training samples needed to be used for each iteration from the standard image data, preprocessing the training samples, and inputting the training samples as a model A;
4) Alternately optimizing by adopting a random gradient descent method, and updating the weight of each part until iteration is finished;
5) Obtaining an abnormality discrimination threshold
Inputting the daily inspection image into a trained convolutional neural network: a patrol image which is the same as the divided standard image time period can be obtained;
(IV) comparing the two images and finding the difference: after finding the standard image corresponding to the inspection image, finding out the mapping relation of the two images through an image registration method, and then making a difference value, and if the difference value is larger than the abnormality judgment threshold value, treating the difference value as an abnormality.
Wherein the objective function/loss function of the convolutional neural network model in step (two) is as follows:
Wherein n is the number of samples, C is the number of classes, xi is the feature of the ith sample, yi is the class label corresponding to xi, and Wj and bj are the weight and bias of class j;
The loss function can estimate the degree of inconsistency between the predicted value and the true value of the model, and if the error between the classified data obtained by iterative operation of the standard image input network and the expected data is smaller than an abnormal judgment threshold value, the network training is successful;
The training parameters in the step (two) include a minimum batch value N batch, a maximum iteration number M, the number of layers of the convolution and deconvolution network, and the number of feature maps of each layer of the network.
Preferably, the convolutional neural network is a three-dimensional convolutional neural network, and an input layer of the three-dimensional convolutional neural network receives a four-dimensional array.
Wherein the weights corresponding to the neurons in the convolutional layer in step (two) are fixed.
Wherein, the pooling layer in the step (two) can perform maximum value pooling and average value pooling.
Preferably, the duration of the video slicing in step (one) is 5 seconds.
While the preferred embodiments of the present invention have been described, the scope of the present invention is not limited thereto, and any person skilled in the art, who is skilled in the art, should make equivalents and modifications within the scope of the present invention according to the technical scheme and the inventive concept thereof.
Claims (8)
1. The cable tunnel anomaly detection method based on the convolutional neural network is characterized by comprising a training stage and a testing stage, wherein a standard image a is input into the convolutional neural network for training in the training stage, and a model A is obtained; in the test stage, a model A is input by using a daily inspection image sample b, a standard image a corresponding to the model A is obtained, if the image b is identical to or close to the image a, normal data are obtained, otherwise abnormal data are obtained, and the steps are as follows:
Converting standard video into an image: extracting an image sequence from a standard video, classifying according to a fixed time period, wherein each image corresponds to a time point, taking any image from a patrol video, determining the corresponding relation between the patrol image and the standard image, and converting the video into an image;
inputting the segmented standard images into a convolutional neural network for training: the convolutional neural network comprises an input layer, a convolutional layer, a pooling layer, a full-connection layer and an output layer, wherein the convolutional layer and the pooling layer form a plurality of convolutional groups, the characteristics are extracted layer by layer, and classification is completed through a plurality of full-connection layers;
The training process is as follows:
inputting a standard image into the convolution set;
Updating training parameters;
Obtaining training samples needed to be used for each iteration from the standard image data, preprocessing the training samples, and inputting the training samples as a model A;
Alternately optimizing by adopting a random gradient descent method, and updating the weight of each part until iteration is finished;
obtaining an abnormality discrimination threshold
Inputting the daily inspection image into a trained convolutional neural network: a patrol image which is the same as the divided standard image time period can be obtained;
(IV) comparing the two images and finding the difference: after finding the standard image corresponding to the inspection image, finding out the mapping relation of the two images through an image registration method, and then making a difference value, and if the difference value is larger than the abnormality judgment threshold value, treating the difference value as an abnormality.
2. The method for detecting cable tunnel anomalies based on a convolutional neural network according to claim 1, wherein the objective function/loss function of the convolutional neural network model in the step (two) is as follows:
Where n is the number of samples, C is the number of classes, xi is the feature of the ith sample, yi is the class label corresponding to xi, and Wj and bj are the weights and offsets of class j.
3. The cable tunnel anomaly detection method based on the convolutional neural network according to claim 2, wherein the loss function can measure the degree of inconsistency between a predicted value and a true value of a model, and if the error between classified data obtained by iterative operation of a standard image input network and expected data is smaller than an anomaly discrimination threshold, the error represents that network training is successful.
4. The method of claim 1, wherein the training parameters in the step (two) include a minimum batch value N batch, a maximum number of iterations M, a number of layers of the convolutional and deconvolve network, and a number of feature maps of each layer of the network.
5. The cable tunnel anomaly detection method based on the convolutional neural network according to claim 1, wherein the convolutional neural network is a three-dimensional convolutional neural network, and an input layer of the three-dimensional convolutional neural network receives a four-dimensional array.
6. The method for detecting abnormal cable tunnel according to claim 1, wherein the weights corresponding to the neurons in the convolutional layer in the step (two) are fixed.
7. The cable tunnel anomaly detection method based on convolutional neural network according to claim 1, wherein the pooling layer in the step (two) can perform maximum pooling and average pooling.
8. The method for detecting cable tunnel anomalies based on convolutional neural network according to claim 1, wherein the duration of the video slicing in the step (one) is 5 seconds.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110011709.1A CN112598666B (en) | 2021-01-06 | 2021-01-06 | Cable tunnel anomaly detection method based on convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110011709.1A CN112598666B (en) | 2021-01-06 | 2021-01-06 | Cable tunnel anomaly detection method based on convolutional neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112598666A CN112598666A (en) | 2021-04-02 |
| CN112598666B true CN112598666B (en) | 2024-06-07 |
Family
ID=75207922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110011709.1A Active CN112598666B (en) | 2021-01-06 | 2021-01-06 | Cable tunnel anomaly detection method based on convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112598666B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113344037A (en) * | 2021-05-18 | 2021-09-03 | 国网江西省电力有限公司电力科学研究院 | Cable insulation layer and sheath parameter measuring method and measuring device |
| CN113284144B (en) * | 2021-07-22 | 2021-11-30 | 深圳大学 | Tunnel detection method and device based on unmanned aerial vehicle |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104284185A (en) * | 2014-10-24 | 2015-01-14 | 苏州科达科技股份有限公司 | Video image quality routing inspection method and system |
| CN106709511A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Urban rail transit panoramic monitoring video fault detection method based on depth learning |
| CN108615057A (en) * | 2018-04-28 | 2018-10-02 | 广东电网有限责任公司 | A kind of abnormality recognition method of the cable tunnel lighting apparatus based on CNN |
| CN108846418A (en) * | 2018-05-24 | 2018-11-20 | 广东电网有限责任公司 | A kind of positioning of cable machinery temperature anomaly and recognition methods |
| CN109558912A (en) * | 2019-01-21 | 2019-04-02 | 广西师范大学 | A kind of Alzheimer's disease classification method separating convolution based on depth |
| CN110598767A (en) * | 2019-08-29 | 2019-12-20 | 河南省收费还贷高速公路管理有限公司航空港分公司 | SSD convolutional neural network-based underground drainage pipeline defect identification method |
| CN111563557A (en) * | 2020-05-12 | 2020-08-21 | 山东科华电力技术有限公司 | Method for detecting target in power cable tunnel |
| CN112037219A (en) * | 2020-09-27 | 2020-12-04 | 上海电力大学 | Metal surface defect detection method based on two-stage convolution neural network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9633282B2 (en) * | 2015-07-30 | 2017-04-25 | Xerox Corporation | Cross-trained convolutional neural networks using multimodal images |
-
2021
- 2021-01-06 CN CN202110011709.1A patent/CN112598666B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104284185A (en) * | 2014-10-24 | 2015-01-14 | 苏州科达科技股份有限公司 | Video image quality routing inspection method and system |
| CN106709511A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Urban rail transit panoramic monitoring video fault detection method based on depth learning |
| CN108615057A (en) * | 2018-04-28 | 2018-10-02 | 广东电网有限责任公司 | A kind of abnormality recognition method of the cable tunnel lighting apparatus based on CNN |
| CN108846418A (en) * | 2018-05-24 | 2018-11-20 | 广东电网有限责任公司 | A kind of positioning of cable machinery temperature anomaly and recognition methods |
| CN109558912A (en) * | 2019-01-21 | 2019-04-02 | 广西师范大学 | A kind of Alzheimer's disease classification method separating convolution based on depth |
| CN110598767A (en) * | 2019-08-29 | 2019-12-20 | 河南省收费还贷高速公路管理有限公司航空港分公司 | SSD convolutional neural network-based underground drainage pipeline defect identification method |
| CN111563557A (en) * | 2020-05-12 | 2020-08-21 | 山东科华电力技术有限公司 | Method for detecting target in power cable tunnel |
| CN112037219A (en) * | 2020-09-27 | 2020-12-04 | 上海电力大学 | Metal surface defect detection method based on two-stage convolution neural network |
Non-Patent Citations (3)
| Title |
|---|
| 基于卷积神经网络的智能巡检机器人场景识别;王尤河;游日晴;郑力勇;文春华;;信息技术;20200220(第02期);全文 * |
| 基于卷积神经网络的电缆隧道异常识别;杨跞;中国优秀硕士学位论文全文数据库;20200215(第2期);全文 * |
| 基于改进卷积神经网络的恶意代码检测技术;唐永旺;王刚;魏晗;;信息工程大学学报;20190415(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112598666A (en) | 2021-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112380952B (en) | Power equipment infrared image real-time detection and identification method based on artificial intelligence | |
| CN111179251B (en) | Defect detection system and method based on twin neural network and by utilizing template comparison | |
| CN111914883B (en) | Spindle bearing state evaluation method and device based on deep fusion network | |
| CN113612733B (en) | Twin network-based few-sample false data injection attack detection method | |
| CN112598666B (en) | Cable tunnel anomaly detection method based on convolutional neural network | |
| CN108711148A (en) | A kind of wheel tyre defect intelligent detecting method based on deep learning | |
| CN116793682A (en) | Bearing fault diagnosis method based on iCORAL-MMD and anti-migration learning | |
| CN112229845A (en) | Unmanned aerial vehicle high-precision winding tower intelligent inspection method based on visual navigation technology | |
| CN111652835A (en) | Method for detecting insulator loss of power transmission line based on deep learning and clustering | |
| CN112365497A (en) | High-speed target detection method and system based on Trident Net and Cascade-RCNN structures | |
| CN111860277A (en) | Civil aviation aircraft airspeed pipe sleeve safety warning method based on color histogram features | |
| CN114359695A (en) | Insulator breakage identification method based on uncertainty estimation | |
| CN111862065A (en) | Power transmission line diagnosis method and system based on multitask deep convolutional neural network | |
| CN111768429A (en) | Pedestrian target tracking method in tunnel environment based on Kalman filtering and pedestrian re-identification algorithm | |
| CN114662594B (en) | Target feature recognition analysis system | |
| Chou et al. | SHM data anomaly classification using machine learning strategies: A comparative study | |
| CN116805051A (en) | Double convolution dynamic domain adaptive equipment fault diagnosis method based on attention mechanism | |
| CN114549414A (en) | Abnormal change detection method and system for track data | |
| CN112132088B (en) | Inspection point missing inspection identification method | |
| CN112508946B (en) | Cable tunnel anomaly detection method based on antagonistic neural network | |
| CN116150668B (en) | Rotating equipment fault diagnosis method based on double-stage alignment partial migration network | |
| CN114596244A (en) | Infrared image identification method and system based on visual processing and multi-feature fusion | |
| CN115661042A (en) | Hierarchical classification defect detection method based on attention mechanism guidance | |
| CN110070520B (en) | Pavement crack detection model construction and detection method based on deep neural network | |
| CN117346657B (en) | Event triggering method and system based on 5G camera |
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 | ||
| GR01 | Patent grant |