CN105204084B - Optical Fiber Intrusion Signal Recognition Method Based on LDA Algorithm Model - Google Patents
Optical Fiber Intrusion Signal Recognition Method Based on LDA Algorithm Model Download PDFInfo
- Publication number
- CN105204084B CN105204084B CN201510575833.5A CN201510575833A CN105204084B CN 105204084 B CN105204084 B CN 105204084B CN 201510575833 A CN201510575833 A CN 201510575833A CN 105204084 B CN105204084 B CN 105204084B
- Authority
- CN
- China
- Prior art keywords
- mrow
- wavelet
- msub
- power
- frequency
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 239000013307 optical fiber Substances 0.000 title claims abstract description 14
- 239000011159 matrix material Substances 0.000 claims abstract description 10
- 238000010276 construction Methods 0.000 claims abstract description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 abstract 1
- 238000012795 verification Methods 0.000 abstract 1
- 239000007789 gas Substances 0.000 description 11
- 238000001514 detection method Methods 0.000 description 4
- 230000006378 damage Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000006424 Flood reaction Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 239000003209 petroleum derivative Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 239000010913 used oil Substances 0.000 description 1
Landscapes
- Complex Calculations (AREA)
Abstract
本发明针对光纤入侵信号识别系统提出了一种基于LDA算法检验的方法，该方法包括：对采集的时域信号利用多孔算法对其进行多层分解，得到各频段小波概貌与细节系数；通过计算小波功率熵与信号的中心频率得到二维样本数据，将该样本数据输入到LDA算法检验模型，使投影后样本数据的类间散布矩阵最大，并且同时类内散布矩阵最小，最终达到较为理想的分类效果，即可判断施工信号为机械信号或者人工信号。该方法简单易行，计算效率高并且可以有效区分入侵信号性质。
The present invention proposes a method based on LDA algorithm verification for the optical fiber intrusion signal identification system. The method includes: using a porous algorithm to decompose the collected time domain signals into multiple layers to obtain the wavelet overview and detail coefficients of each frequency band; through calculation The wavelet power entropy and the center frequency of the signal are used to obtain two-dimensional sample data. The sample data is input into the LDA algorithm to test the model, so that the inter-class scatter matrix of the projected sample data is maximized, and at the same time the intra-class scatter matrix is minimized, ultimately achieving a more ideal The classification effect can determine whether the construction signal is a mechanical signal or a manual signal. This method is simple and easy to implement, has high computational efficiency and can effectively distinguish the nature of intrusion signals.
Description
技术领域technical field
本发明涉及一种基于LDA算法模型的光纤入侵信号识别方法。The invention relates to an optical fiber intrusion signal identification method based on an LDA algorithm model.
背景技术Background technique
石油、天然气主要靠管道进行运输，管道运输是一种比较经济、安全、可靠和便捷的运输方式，具有连续输送、平稳的特点，能很好地协调油气田和炼厂、石油化工厂的生产。与公路、铁路、水路等运输方式相比，管道输送具有输送量大、投资省、建设周期短、对生态环境影响小等优点。Petroleum and natural gas are mainly transported by pipelines. Pipeline transportation is a relatively economical, safe, reliable and convenient transportation mode, which has the characteristics of continuous and stable transportation, and can well coordinate the production of oil and gas fields, refineries, and petrochemical plants. Compared with transportation methods such as roads, railways, and waterways, pipeline transportation has the advantages of large transportation volume, low investment, short construction period, and small impact on the ecological environment.
我国目前现有油气管道3万多公里,“十一五”期间已建设3万多公里的油气管道，而如此之长的管道目前尚无有效的安全防护方式，在管道上打孔盗油、盗气事件十分频繁,对国家和人民生命财产造成了巨大损失。由于大气腐蚀、人为故意损坏等原因，管道泄漏事故经常发生，所铺设的油气管道沿途可能穿越人口密集的城镇、乡村、农田、沙漠、公路和铁路等各种复杂的环境，周围存在的施工、人为破坏以及自然灾害(如地震、洪水、泥石流以及山体滑坡)等诸多因素有可能造成管道泄漏，一旦发生事故将会造成巨大的生命财产损失和环境污染。因此建立有效地预测、检测机制对潜在的破坏事件作出预警，是减少恶性事件的很好手段，于是管道安全预警系统应运而生。常用的油气管道泄漏检测装置输送压力和流量等参数的变化来判断是否发生泄漏。该类方法受输送物质特性以及输送工况等因素影响，对微小泄漏检测灵敏度不高，目前的技术多数是在管道破坏以后的泄漏检测技术，经济损失较大。my country currently has more than 30,000 kilometers of oil and gas pipelines, and more than 30,000 kilometers of oil and gas pipelines have been built during the "Eleventh Five-Year Plan" period. However, there is currently no effective safety protection method for such long pipelines. Gas theft incidents are very frequent, causing huge losses to the country and people's lives and property. Due to atmospheric corrosion, man-made damage and other reasons, pipeline leakage accidents often occur, and the laid oil and gas pipelines may pass through various complex environments such as densely populated towns, villages, farmland, deserts, roads and railways. Many factors such as man-made sabotage and natural disasters (such as earthquakes, floods, mudslides, and landslides) may cause pipeline leakage. Once an accident occurs, it will cause huge loss of life and property and environmental pollution. Therefore, establishing an effective prediction and detection mechanism to give early warning to potential sabotage events is a good means to reduce vicious events, so the pipeline safety early warning system came into being. Commonly used oil and gas pipeline leak detection devices change the transmission pressure and flow parameters to determine whether a leak occurs. This type of method is affected by factors such as the characteristics of the transported material and the transporting conditions, and the sensitivity to micro-leakage detection is not high. Most of the current technologies are leak detection technologies after the pipeline is damaged, and the economic loss is relatively large.
光纤入侵信号识别系统利用与油气管道同沟敷设的普通通信光缆中的光纤作为传感器，长距离连续实时检测油气管道沿线的土壤振动情况，包括在油气管道附近施工、人为破坏油气管道等，来分析判断是否存在威胁油气管道安全的破坏事件，及时报警，起到安全预警的作用，并能够对这些事件进行准确的分析和定位，确定事件的性质，通过地理信息系统显示振动源所在地的具体位置和性质。The optical fiber intrusion signal recognition system uses the optical fiber in the ordinary communication cable laid in the same ditch as the oil and gas pipeline as a sensor to continuously detect the soil vibration along the oil and gas pipeline in real time over a long distance, including construction near the oil and gas pipeline, artificial destruction of the oil and gas pipeline, etc., to analyze Judging whether there is a sabotage event that threatens the safety of oil and gas pipelines, and calling the police in time, it plays the role of safety early warning, and can accurately analyze and locate these events, determine the nature of the event, and display the specific location and location of the vibration source through the geographic information system. nature.
综上所述，基于小波系数功率熵检验的光纤入侵信号识别方法具有极大的研究价值与使用价值。To sum up, the identification method of optical fiber intrusion signal based on wavelet coefficient power entropy test has great research value and application value.
发明内容Contents of the invention
根据本发明的一个方面，提供了一种基于LDA算法的光纤入侵信号识别方法，该方法能有效区分机械施工和人工作业，其特征在于包括：According to one aspect of the present invention, a method for identifying optical fiber intrusion signals based on the LDA algorithm is provided, the method can effectively distinguish between mechanical construction and manual work, and is characterized in that it includes:
对采集的数据利用多孔算法对其进行小波分解，得到各频段概貌系数与细节系数，其中所得到各频段的小波系数与未分解时原时域信号长度均保持一致；The collected data is decomposed by wavelet using porous algorithm to obtain the overview coefficient and detail coefficient of each frequency band, and the obtained wavelet coefficient of each frequency band is consistent with the length of the original time domain signal when it is not decomposed;
对各频段的小波系数(不包含最低频)计算小波系数功率，然后求得各系数功率占比；Calculate the wavelet coefficient power for the wavelet coefficients of each frequency band (excluding the lowest frequency), and then obtain the power ratio of each coefficient;
计算小波系数功率熵，得到关于小波系数功率熵的特征样本数据；Calculate the wavelet coefficient power entropy to obtain the feature sample data about the wavelet coefficient power entropy;
将各频段小波系数功率进行归一化，利用各频段与归一化的小波系数功率可求得信号频域中心，得到关于信号中心频率的特征样本数据；The wavelet coefficient power of each frequency band is normalized, and the signal frequency domain center can be obtained by using each frequency band and the normalized wavelet coefficient power, and the characteristic sample data about the signal center frequency can be obtained;
将以上所得到的二维特征数据输入到LDA算法分类器，对入侵信号性质进行识别。Input the two-dimensional feature data obtained above into the LDA algorithm classifier to identify the nature of the intrusion signal.
根据本发明的一个进一步的方面，上述光纤入侵信号识别方法进一步包括：According to a further aspect of the present invention, the above-mentioned optical fiber intrusion signal identification method further includes:
对所求得的各频段小波系数，分别计算不包含最低频的各频段的小波系数功率，继而求得小波系数功率熵，计算各频段小波系数功率：For the obtained wavelet coefficients of each frequency band, calculate the wavelet coefficient power of each frequency band not including the lowest frequency, and then obtain the wavelet coefficient power entropy, and calculate the wavelet coefficient power of each frequency band:
其中，s(i)代表第i个小波功率系数，N代表小波系数的长度，然后可以求得各频段小波系数功率占总功率的比例，即：Among them, s(i) represents the i-th wavelet power coefficient, N represents the length of the wavelet coefficient, and then the ratio of the wavelet coefficient power in each frequency band to the total power can be obtained, namely:
其中Pi分别代表各频段小波系数功率，继而可以求得小波系数功率熵，即：Among them, P i represent the wavelet coefficient power of each frequency band respectively, and then the wavelet coefficient power entropy can be obtained, namely:
其中，Ri代表各频段小波系数功率占总功率的比例，通过以上各式可求得小波系数功率熵。Among them, R i represents the proportion of the wavelet coefficient power in each frequency band to the total power, and the wavelet coefficient power entropy can be obtained through the above formulas.
根据本发明的一个进一步的方面，上述光纤入侵信号识别方法进一步包括：According to a further aspect of the present invention, the above-mentioned optical fiber intrusion signal identification method further includes:
对所求得的小波系数功率归一化，具体为：Normalize the obtained wavelet coefficient power, specifically:
其中s(i)代表第i个小波系数功率，P(i)为第i个小波系数功率占比；Where s(i) represents the power of the i-th wavelet coefficient, and P(i) is the power ratio of the i-th wavelet coefficient;
分别求取四个高频段的频率中心f，继而求得整个信号频率的期望值即中心频率：Find the frequency center f of the four high-frequency bands respectively, and then find the expected value of the entire signal frequency, that is, the center frequency:
其中，f(i)为第i频段的频率中心，fs为信号的中心频率，所求得中心频率作为样本数据。Among them, f(i) is the frequency center of the i-th frequency band, f s is the center frequency of the signal, and the obtained center frequency is used as sample data.
根据本发明的一个进一步的方面，上述光纤入侵信号识别方法进一步包括：According to a further aspect of the present invention, the above-mentioned optical fiber intrusion signal identification method further includes:
用LDA算法将中心频率、功率熵二维特征数据进行降维并投影到最佳鉴别矢量空间，投影后保证样本数据在新的子空间有最大的类间距离和最小的类内距离，从而使得样本数据在该空间中有最佳的可分离性，Use the LDA algorithm to reduce the dimensionality of the center frequency and power entropy two-dimensional feature data and project it into the best discriminant vector space. After projection, ensure that the sample data has the largest inter-class distance and the smallest intra-class distance in the new subspace, so that The sample data has the best separability in this space,
寻找使得支持矢量达到最大值继而可以求得最佳投影方向，即引入Fisher鉴别准则表达式:Find the support vector to reach the maximum value and then obtain the best projection direction, that is, introduce the Fisher discrimination criterion expression:
其中v为任一n维列矢量，T代表列矢量转置，Sb为类间散布矩阵，Sw为类内散布矩阵，Fisher线性鉴别分析就是选取使得Jfisher(v)达到最大值的矢量v作为投影方向，其物理意义就是投影后的样本具有最大的类间离散度和最小的类内离散度，从而使投影后样本数据的类间散布矩阵Sb最大，并且同时类内散布矩阵Sw最小，从而实现分类，并有效地识别振源类型。Where v is any n-dimensional column vector, T represents the column vector transpose, S b is the inter-class scatter matrix, S w is the intra-class scatter matrix, Fisher linear discriminant analysis is to select the vector that makes J fisher (v) reach the maximum value As the projection direction, the physical meaning of v is that the projected samples have the largest inter-class scatter and the smallest intra-class scatter, so that the inter-class scatter matrix S b of the projected sample data is the largest, and at the same time the intra-class scatter matrix S w is the smallest, so as to achieve classification and effectively identify the type of vibration source.
附图说明Description of drawings
图1是根据本发明的一个实施例的方法的整体流程。Fig. 1 is an overall flow of a method according to an embodiment of the present invention.
图2是根据本发明的一个实施例的多孔算法原理图。Fig. 2 is a schematic diagram of a porous algorithm according to an embodiment of the present invention.
图3是根据本发明的一个实施例的多孔算法分解结果。Fig. 3 is a decomposition result of a porous algorithm according to an embodiment of the present invention.
图4是根据本发明的一个实施例的振动信号二维特征分布图。Fig. 4 is a two-dimensional feature distribution diagram of a vibration signal according to an embodiment of the present invention.
图5是根据本发明的一个实施例的LDA分类器训练后的数据分布。Fig. 5 is the data distribution after training of the LDA classifier according to an embodiment of the present invention.
具体实施方案specific implementation plan
以下结合附图，对本发明实施例中的技术方案进行描述。显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部实施例。基于本发明中的实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他实施例，都属于本发明保护的范围。The technical solutions in the embodiments of the present invention are described below in conjunction with the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, those of ordinary skill in the art can obtain other embodiments according to these drawings without any creative effort, which all belong to the protection scope of the present invention.
请参见图1所示，图1是根据本发明的一个实施例的基于小波系数熵检验的光纤入侵信号识别方法的流程图。如图1所示，本实施例所揭示的基于LDA算法模型的光纤入侵信号识别方法包括：Please refer to FIG. 1 . FIG. 1 is a flow chart of an optical fiber intrusion signal identification method based on wavelet coefficient entropy test according to an embodiment of the present invention. As shown in Figure 1, the method for identifying optical fiber intrusion signals based on the LDA algorithm model disclosed in this embodiment includes:
S101：通过对采集数据利用小波多孔算法对其做四层分解，这样得到的小波系数的长度都与原时域信号的长度保持一致。S101: Decompose the collected data into four levels by using the wavelet porous algorithm, so that the lengths of the obtained wavelet coefficients are consistent with the lengths of the original time-domain signals.
S102：对各频段小波系数分别求得功率值，继而求得各频段小波系数功率占比，最后求得各频段小波系数功率熵值；S102: Obtain power values for the wavelet coefficients in each frequency band, and then obtain the power ratio of the wavelet coefficients in each frequency band, and finally obtain the power entropy value of the wavelet coefficients in each frequency band;
S103：将各频段小波系数功率归一化，求各频段中心值的期望即信号中心频率；S103: Normalize the wavelet coefficient power of each frequency band, and find the expectation of the center value of each frequency band, that is, the signal center frequency;
S104：将中心频率、小波系数功率熵结果输入到LDA算法模型，得到最佳鉴别矢量空间。S104: Input the center frequency and wavelet coefficient power entropy results into the LDA algorithm model to obtain the optimal discriminant vector space.
根据本发明的一个实施例的多孔算法分解流程如图2所示：The porous algorithm decomposition process according to an embodiment of the present invention is shown in Figure 2:
使用哈尔小波族中的db5小波，求得该小波分解时的低通滤波器系数h0(n)以及高通滤波器系数h1(n)，图2中，H1(z4)是将h1(n)每两个点之间插入三个零得到的新滤波器，同理，H0(z2)是将h0(n)每两个点插入一个零后所得到的新滤波器，↓2代表二抽取环节，即对信号每隔两个点进行抽取，这样就把每一级的抽取移到了最后，这样即可保证总的数据不会逐级减少，经过多孔算法分解后，可以得到一个低频段小波概貌系数和四个高频段小波细节系数。Use the db5 wavelet in the Haar wavelet family to obtain the low-pass filter coefficient h 0 (n) and high-pass filter coefficient h 1 (n) when the wavelet is decomposed. In Figure 2, H 1 (z 4 ) is the H 1 (n) is a new filter obtained by inserting three zeros between every two points. Similarly, H 0 (z 2 ) is a new filter obtained by inserting a zero between every two points of h 0 (n) ↓2 represents the second extraction link, that is, the signal is extracted every two points, so that the extraction of each level is moved to the end, so as to ensure that the total data will not decrease step by step. After decomposition by the porous algorithm , one low-frequency wavelet profile coefficient and four high-frequency wavelet detail coefficients can be obtained.
利用多孔算法对时域信号进行分解所得到小波系数的实例如图3所示：An example of the wavelet coefficients obtained by decomposing the time domain signal using the porous algorithm is shown in Figure 3:
图3中,a4表示四层小波概貌系数，d1～d4分别代表各频段小波细节系数，由图可以看出各频段小波系数长度均与原时域信号长度一致，分别对d1～d4求其功率值，然后求得每层小波系数功率在各频段中的占比，最后求得各层小波系数功率熵值，结果作为样本数据库。In Figure 3, a4 represents the four-layer wavelet overview coefficient, and d1~d4 represent the wavelet detail coefficients of each frequency band respectively. It can be seen from the figure that the length of the wavelet coefficients of each frequency band is consistent with the length of the original time domain signal, and its power is calculated for d1~d4 respectively. value, and then obtain the proportion of the wavelet coefficient power of each layer in each frequency band, and finally obtain the wavelet coefficient power entropy value of each layer, and the result is used as a sample database.
将二维样本数据输入到LDA分类器的实例如图4所示。图4中‘.’代表电钻信号数据，‘Δ’代表电钻信号均值，‘o’代表镐刨信号数据，‘+’代表镐刨信号均值，‘*’代表所有数据均值，从图4可以很明显看出电钻和镐刨信号的在坐标上着明显的界限。下面再将这些数据放入到LDA分类器中进一步分类。An example of inputting two-dimensional sample data to the LDA classifier is shown in Figure 4. In Figure 4, '.' represents the signal data of the electric drill, 'Δ' represents the average value of the electric drill signal, 'o' represents the signal data of the pickaxe planer, '+' represents the average value of the signal signal of the pickaxe planer, and '*' represents the average value of all data. It can be seen from Figure 4 It is obvious that there is a clear boundary in the coordinates of the electric drill and pick planer signals. Next, put these data into the LDA classifier for further classification.
图5所示为上述数据由LDA分类器分类后的数据，将这些数据更准确的进行分类；从图5中可以清楚地看出，由LDA分类器降维分类后，2种信号达到了分类的目的，从而有效的区分振动源信号类型。Figure 5 shows the data after the above data is classified by the LDA classifier, and these data are classified more accurately; it can be clearly seen from Figure 5 that after the dimensionality reduction classification by the LDA classifier, the two signals have reached the classification The purpose of this is to effectively distinguish the type of vibration source signal.
本发明与现有光纤入侵信号识别方法具有以下优点：The present invention and the existing optical fiber intrusion signal identification method have the following advantages:
(1)本发明的方法信号识别准确率较高，误差小；(1) The method signal recognition accuracy rate of the present invention is higher, and error is little;
(2)本发明的方法简单易行，并且执行效率高，耗时少，对于数据量较大的信号可以做到实时处理，保证执行效率；(2) The method of the present invention is simple and easy to implement, and has high execution efficiency and less time-consuming, and can achieve real-time processing for signals with a large amount of data to ensure execution efficiency;
(3)本发明的方法采用多孔算法对信号做多层分解，所得系数长度保持一致，便于求解小波系数功率熵，降低系统设计难度，易于实现。(3) The method of the present invention adopts a porous algorithm to perform multi-layer decomposition on the signal, and the length of the obtained coefficients remains consistent, which is convenient for solving the power entropy of wavelet coefficients, reduces the difficulty of system design, and is easy to implement.
Claims (5)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510575833.5A CN105204084B (en) | 2015-09-10 | 2015-09-10 | Optical Fiber Intrusion Signal Recognition Method Based on LDA Algorithm Model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510575833.5A CN105204084B (en) | 2015-09-10 | 2015-09-10 | Optical Fiber Intrusion Signal Recognition Method Based on LDA Algorithm Model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105204084A CN105204084A (en) | 2015-12-30 |
| CN105204084B true CN105204084B (en) | 2018-02-09 |
Family
ID=54951858
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510575833.5A Expired - Fee Related CN105204084B (en) | 2015-09-10 | 2015-09-10 | Optical Fiber Intrusion Signal Recognition Method Based on LDA Algorithm Model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105204084B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107809430B (en) * | 2017-10-31 | 2020-09-08 | 常州大学 | Network intrusion detection method based on extreme point classification |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5663559A (en) * | 1995-06-07 | 1997-09-02 | Schlumberger Technology Corporation | Microscopy imaging of earth formations |
| CN101556724A (en) * | 2008-04-09 | 2009-10-14 | 中国科学院半导体研究所 | Safety management system of optical fiber perimeter and pattern recognition method thereof |
| CN103134580A (en) * | 2011-11-22 | 2013-06-05 | 上海华魏光纤传感技术有限公司 | Signal processing method for distributed optical fiber vibration measurement system based on wavelet analysis |
| CN103345808A (en) * | 2013-06-26 | 2013-10-09 | 武汉理工光科股份有限公司 | Fiber Bragg grating perimeter intrusion pattern recognition method and system |
| CN103617684A (en) * | 2013-12-12 | 2014-03-05 | 威海北洋电气集团股份有限公司 | Interference type optical fiber perimeter vibration intrusion recognition algorithm |
| CN104240455A (en) * | 2014-08-07 | 2014-12-24 | 北京航天控制仪器研究所 | Method for identifying disturbance event in distributed type optical fiber pipeline security early-warning system |
-
2015
- 2015-09-10 CN CN201510575833.5A patent/CN105204084B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5663559A (en) * | 1995-06-07 | 1997-09-02 | Schlumberger Technology Corporation | Microscopy imaging of earth formations |
| CN101556724A (en) * | 2008-04-09 | 2009-10-14 | 中国科学院半导体研究所 | Safety management system of optical fiber perimeter and pattern recognition method thereof |
| CN103134580A (en) * | 2011-11-22 | 2013-06-05 | 上海华魏光纤传感技术有限公司 | Signal processing method for distributed optical fiber vibration measurement system based on wavelet analysis |
| CN103345808A (en) * | 2013-06-26 | 2013-10-09 | 武汉理工光科股份有限公司 | Fiber Bragg grating perimeter intrusion pattern recognition method and system |
| CN103617684A (en) * | 2013-12-12 | 2014-03-05 | 威海北洋电气集团股份有限公司 | Interference type optical fiber perimeter vibration intrusion recognition algorithm |
| CN104240455A (en) * | 2014-08-07 | 2014-12-24 | 北京航天控制仪器研究所 | Method for identifying disturbance event in distributed type optical fiber pipeline security early-warning system |
Non-Patent Citations (1)
| Title |
|---|
| 基于时频特征的光纤周界振动信号识别;朱程辉 等;《光电工程》;20140131;第41卷(第1期);第16-22页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105204084A (en) | 2015-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Coupling coordination and spatiotemporal dynamic evolution between urbanization and geological hazards–A case study from China | |
| US20200208786A1 (en) | Method for tracking and locating contamination sources in water distribution systems based on consumer complaints | |
| CN103617684B (en) | Interference-type optical fiber circumference vibrating intruding recognizer | |
| CN102722892B (en) | SAR (synthetic aperture radar) image change detection method based on low-rank matrix factorization | |
| Cao et al. | Excavation equipment classification based on improved MFCC features and ELM | |
| CN112836591B (en) | Method for extracting optical fiber early warning signal characteristics of oil gas long-distance pipeline | |
| CN113779888B (en) | Ground subsidence risk assessment method, device, equipment and storage medium | |
| CN106021842A (en) | Bridge monitoring abnormal trend data identification method based on wavelet low-frequency sub-band and correlation analysis | |
| Yanbin et al. | Research on optimization of crane fault predictive control system based on data mining | |
| Li et al. | Denoising of magnetotelluric data using K‐SVD dictionary training | |
| CN112488371B (en) | Pipeline intelligent early warning method and system based on big data | |
| CN104807589A (en) | Online identification method for gas-liquid two-phase-flow flow pattern in gathering and transportation-vertical pipe system | |
| CN103488971A (en) | Method for identifying geometrical morphology of organic reef storage layer | |
| CN103473445A (en) | Method for evaluating pollution flashover fault probabilities of power transmission lines in online manner | |
| CN105204084B (en) | Optical Fiber Intrusion Signal Recognition Method Based on LDA Algorithm Model | |
| Kalantari et al. | Evaluating traditional versus ensemble machine learning methods for predicting missing data of daily PM10 concentration | |
| CN105844051A (en) | Detection method of oil and gas pipeline slow leakage on basis of negative pressure wave signal sparse representation | |
| CN108037529B (en) | A fast identification method for seismic events based on initial vibration signals | |
| Liao et al. | Mapping global distributions of clay-size minerals via soil properties and machine learning techniques | |
| Zhang et al. | Leak localization of water supply network based on temporal convolutional network | |
| Liu et al. | Application of convolutional neural network to GIS and physics | |
| Entezari et al. | Classification map of the sensitivity of flooding using the method of assessment frequency and weight of evidence in the Kermanshah Province | |
| CN108711002B (en) | An oil and gas pipeline segment division method based on improved FPPC algorithm | |
| Liu | Research on feature fusion method of mine microseismic signal based on unsupervised learning | |
| Yousefi et al. | Application of Wavelet Decomposition and Phase Space Reconstruction in Urban Water Consumption Forecasting: Chaotic Approach (Case Study) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Qu Hongquan Inventor after: Qu Dandan Inventor after: Zhao Chao Inventor after: Tian Qing Inventor after: Wang Yanping Inventor before: Qu Hongquan Inventor before: Zhao Chao Inventor before: Cai Xichang Inventor before: Li Xuelian Inventor before: Lv Lei |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180209 |