CN112489330A - Warehouse anti-theft alarm method - Google Patents

Warehouse anti-theft alarm method Download PDF

Info

Publication number
CN112489330A
CN112489330A CN202011391597.9A CN202011391597A CN112489330A CN 112489330 A CN112489330 A CN 112489330A CN 202011391597 A CN202011391597 A CN 202011391597A CN 112489330 A CN112489330 A CN 112489330A
Authority
CN
China
Prior art keywords
wavelet packet
warehouse
original sound
sound signal
matrix
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.)
Granted
Application number
CN202011391597.9A
Other languages
Chinese (zh)
Other versions
CN112489330B (en
Inventor
方涛
聂春洪
李华辉
伍建炜
廖卫平
苏珏
苏海林
麦炳灿
黄练栋
温健锋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangmen Power Supply Bureau of Guangdong Power Grid Co Ltd
Original Assignee
Jiangmen Power Supply Bureau of Guangdong Power Grid Co Ltd
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 Jiangmen Power Supply Bureau of Guangdong Power Grid Co Ltd filed Critical Jiangmen Power Supply Bureau of Guangdong Power Grid Co Ltd
Priority to CN202011391597.9A priority Critical patent/CN112489330B/en
Publication of CN112489330A publication Critical patent/CN112489330A/en
Application granted granted Critical
Publication of CN112489330B publication Critical patent/CN112489330B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00—Burglar, theft or intruder alarms
    • G08B13/02—Mechanical actuation
    • G08B13/08—Mechanical actuation by opening, e.g. of door, of window, of drawer, of shutter, of curtain, of blind
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
    • G06F17/148—Wavelet transforms
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00—Burglar, theft or intruder alarms
    • G08B13/16—Actuation by interference with mechanical vibrations in air or other fluid
    • G08B13/1654—Actuation by interference with mechanical vibrations in air or other fluid using passive vibration detection systems
    • G08B13/1672—Actuation by interference with mechanical vibrations in air or other fluid using passive vibration detection systems using sonic detecting means, e.g. a microphone operating in the audio frequency range
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/18—Status alarms
    • G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/72—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for transmitting results of analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Multimedia (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Engineering & Computer Science (AREA)
  • Algebra (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Burglar Alarm Systems (AREA)
  • Alarm Systems (AREA)

Abstract

The invention relates to the field of anti-theft alarm of a distribution network equipment warehouse, in particular to an anti-theft alarm method for a warehousek *Calculating the energy of the historical relative wavelet packet coefficient by using a training set consisting of collected historical sound signals, and calculating a threshold value z according to a kernel Fisher analysis method0The relative wavelet packet systemThe number energy is classified by the kernel Fisher analysis method when z isk *≤z0The warehouse anti-theft alarm method can acquire warehouse door opening sound signals in real time, judge the sound signals and ensure the anti-theft alarm of the warehouse.

Description

Warehouse anti-theft alarm method
Technical Field
The invention relates to the field of anti-theft alarm of distribution network equipment warehouses, in particular to an anti-theft alarm method for a warehouse.
Background
Nowadays, companies pay more and more attention to the management of power distribution network equipment warehouses, and as an anti-theft alarm device is not arranged, the warehouses are stolen occasionally, so that great loss is caused to a power grid. At present, most of anti-theft modes adopted by other industries are based on voice recognition, such as a voice recognition anti-theft method based on a wavelet packet, a voice recognition anti-theft method based on a support vector machine and the like, but the methods either cannot well extract nonlinear signal characteristics or are too complex in algorithm, involve training and setting of various parameters, and seriously affect the judging efficiency. Therefore, in order to further ensure the safety of the warehouse, a new warehouse alarm system needs to be researched.
Chinese patent CN104900228B discloses a suspicious door opening sound recognition device and a suspicious door opening sound recognition method, wherein the recognition device comprises a sound trigger module, a sound acquisition module, a sound feature extraction processing module, a sound recognition module and an alarm module which are connected in sequence, and when the sound trigger module, the sound acquisition module, the sound feature extraction processing module, the sound recognition module and the alarm module are connected in sequence, the sound acquisition module acquires sound, preprocesses the acquired sound and converts the acquired sound into a digital signal; carrying out feature extraction on the digital signals to obtain feature parameters, and eliminating magnitude difference to obtain a feature vector Fi' to be recognized; calculating the similarity Si of the feature vector F 'i stored in the Fi' corresponding to the pre-stored door opening sound, and determining the type of a sample to be identified according to Si so as to judge whether the collected sound is suspicious door opening sound.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an anti-theft alarm method for a distribution network equipment warehouse, which can acquire warehouse door opening sound signals in real time, distinguish the sound signals and ensure anti-theft alarm for the warehouse.
In order to solve the technical problems, the invention adopts the technical scheme that: a warehouse anti-theft alarm method comprises the following steps:
acquiring real-time original sound signals of the opened door of the warehouse, carrying out wavelet packet analysis on the real-time original sound signals to obtain real-time relative wavelet packet coefficient energy, calculating a mapping value z according to a kernel Fisher analysis method by taking the real-time relative wavelet packet coefficient energy as characteristic quantityk *；
Collecting a training set E consisting of historical sound signals, carrying out wavelet packet analysis on the training set E to obtain historical relative wavelet packet coefficient energy, calculating a threshold value z according to a kernel Fisher analysis method by taking the historical relative wavelet packet coefficient energy as characteristic quantity0；
The z isk *And said z0Making a comparison when zk *＞z0When the original sound signal is normal, when z isk *≤z0When the original sound signal is abnormal, the system alarms.
According to the warehouse anti-theft alarm method, wavelet packet analysis is carried out on the original sound signals of the warehouse door opening collected in real time, the wavelet packet coefficient energy of the wavelet packet coefficient signals of each frequency band is calculated, then the relative wavelet packet coefficient energy is calculated, and the mapping value z is calculated according to a kernel Fisher analysis methodk *By means of collectionCalculating the energy of historical relative wavelet packet coefficient according to a training set consisting of historical sound signals, and calculating a threshold value z according to a kernel Fisher analysis method0Classifying the energy of the relative wavelet packet coefficient by a kernel Fisher analysis method when z isk *≤z0The warehouse anti-theft alarm method can acquire warehouse door opening sound signals in real time, judge the sound signals and ensure the anti-theft alarm of the warehouse.
Preferably, the real-time original sound signal is subjected to wavelet packet analysis, i.e. the original sound signal is decomposed and reconstructed by J-layer wavelet packet transform to obtain 2JWavelet packet coefficient signals of different frequency bands.
Preferably, the method for calculating the wavelet packet coefficient energy of the wavelet packet coefficient signal of each frequency band comprises:
Figure BDA0002813006280000021
where n is the total number of sample points of the acquired original sound signal, EJiFor the wavelet packet coefficient energy, x, of the node (J, i) after the wavelet packet transformationJi(k)Is the kth wavelet packet coefficient in node (J, i).
Preferably, the calculation method of the relative wavelet packet coefficient energy is as follows:
Figure BDA0002813006280000022
in the formula, eJiThe relative wavelet packet coefficient energy of the node (J, i) after wavelet packet transformation.
Preferably, the relative wavelet packet coefficient energy is taken as a characteristic quantity, and a training set E consisting of historical sound signals is a relative wavelet packet coefficient energy matrix consisting of n training samples, including a normal original sound signal relative wavelet packet coefficient energy matrix E1Energy matrix E of relative wavelet packet coefficient of abnormal original sound signal2Mapping the extracted nonlinear data to a high-dimensional space through a kernel functionObtaining a linear change matrix K, and then performing centralization processing on the change matrix K to obtain a centralized matrix
Figure BDA0002813006280000023
The calculation method is as follows:
Figure BDA0002813006280000024
in the formula, mun＝one(n)/n
Wherein one (n) is an n-dimensional identity matrix;
thus, the training covariance matrix based on the training samples
Figure BDA0002813006280000031
Preferably, the covariance matrix E is trainedxComprises n samples1And n2Normal original sound signal data matrix Ex1And an abnormal original sound signal data matrix Ex2Normal original sound signal data matrix Ex1And an abnormal original sound signal data matrix Ex2Respectively, are m1And m2The calculation method is as follows:
Figure BDA0002813006280000032
preferably, the internal parameters of the kernel Fisher analysis include Fisher criterion J (W), which is defined as follows:
Figure BDA0002813006280000033
in the formula, W is a weight vector in the Fisher criterion.
Preferably, the weight vector when J (W) is maximum is the optimal vector W*Wherein W is*The calculation method comprises the following steps:
Figure BDA0002813006280000034
preferably, the covariance matrix E is trainedxiIn 1 line niMapping Z under the column's mapping spaceiThe vectors are as follows:
Zi＝(W*)TExi，(i＝1，2)
threshold z of Fisher criterion0It can be calculated by the following formula:
Figure BDA0002813006280000035
Figure BDA0002813006280000036
the wavelet packet analysis is preferably performed on the original sound signal extracted in real time to obtain a relative wavelet packet coefficient E*Then vector Z is mapped*As follows:
Figure BDA0002813006280000037
when the k sample represents the mapping value zk *Satisfies zk *≤z0If the k sample is an abnormal sample, the system alarms.
Compared with the background technology, the warehouse anti-theft alarm method of the invention has the following technical effects:
the door opening sound signals of the warehouse are collected in real time, the sound signals are distinguished, and anti-theft alarm of the warehouse is guaranteed.
Drawings
FIG. 1 is a flow chart of a warehouse burglar alarm method according to an embodiment of the present invention;
fig. 2 is a diagram illustrating mapping values of the kernel Fisher mapping space in an embodiment of the present invention.
Detailed Description
The present invention will be further described with reference to the following embodiments.
Examples
A warehouse anti-theft alarm method, as shown in fig. 1, comprising the steps of:
acquiring real-time original sound signals of the opened door of the warehouse, carrying out wavelet packet analysis on the real-time original sound signals to obtain real-time relative wavelet packet coefficient energy, calculating a mapping value z according to a kernel Fisher analysis method by taking the real-time relative wavelet packet coefficient energy as characteristic quantityk *；
Collecting a training set E consisting of historical sound signals, carrying out wavelet packet analysis on the training set E to obtain historical relative wavelet packet coefficient energy, calculating a threshold value z according to a kernel Fisher analysis method by taking the historical relative wavelet packet coefficient energy as characteristic quantity0；
Will zk *And z0Making a comparison when zk *＞z0When the original sound signal is normal, when z isk *≤z0When the original sound signal is abnormal, the system alarms.
According to the warehouse anti-theft alarm method, wavelet packet analysis is carried out on the original sound signals collected in real time during opening the door of the warehouse, the wavelet packet coefficient energy of the wavelet packet coefficient signals of each frequency band is calculated, then the relative wavelet packet coefficient energy is calculated, and the mapping value z is calculated according to a kernel Fisher analysis methodk *Calculating the energy of the historical relative wavelet packet coefficient by using a training set consisting of collected historical sound signals, and calculating a threshold value z according to a kernel Fisher analysis method0Classifying the energy of the relative wavelet packet coefficient by a kernel Fisher analysis method when z isk *≤z0The warehouse anti-theft alarm method can acquire warehouse door opening sound signals in real time, judge the sound signals and ensure the anti-theft alarm of the warehouse.
Performing wavelet packet analysis on the real-time original sound signal, namely obtaining 2 after the original sound signal is decomposed and reconstructed through J-layer wavelet packet transformationJSmall of different frequency bandsThe method for calculating the wavelet packet coefficient energy of the wavelet packet coefficient signals of each frequency band comprises the following steps:
Figure BDA0002813006280000041
where n is the total number of sample points of the acquired original sound signal, EJiFor the wavelet packet coefficient energy, x, of the node (J, i) after the wavelet packet transformationJi(k)Is the kth wavelet packet coefficient in node (J, i).
The method for calculating the relative wavelet packet coefficient energy comprises the following steps:
Figure BDA0002813006280000051
in the formula, eJiThe relative wavelet packet coefficient energy of the node (J, i) after wavelet packet transformation.
Taking the relative wavelet packet coefficient energy as characteristic quantity, a training set E consisting of historical sound signals is a relative wavelet packet coefficient energy matrix consisting of n training samples, and the relative wavelet packet coefficient energy matrix E comprises normal original sound signals1Energy matrix E of relative wavelet packet coefficient of abnormal original sound signal2Mapping the extracted nonlinear data to a high-dimensional space through a kernel function to obtain a linear change matrix K, and then performing centralization processing on the change matrix K to obtain a centralized matrix
Figure BDA0002813006280000052
The calculation method is as follows:
Figure BDA0002813006280000053
in the formula, mun＝one(n)/n
Wherein one (n) is an n-dimensional identity matrix;
thus, the training covariance matrix based on the training samples
Figure BDA0002813006280000054
Training covariance matrix ExComprises n samples1And n2Normal original sound signal data matrix Ex1And an abnormal original sound signal data matrix Ex2Normal original sound signal data matrix Ex1And an abnormal original sound signal data matrix Ex2Respectively, are m1And m2The calculation method is as follows:
Figure BDA0002813006280000055
in one embodiment, in step (1), the internal parameters of the kernel Fisher analysis method include Fisher criteria j (w), and Fisher criteria j (w) are defined as follows:
Figure BDA0002813006280000056
in the formula, W is a weight vector in the Fisher criterion.
The weight vector when J (W) is maximum is the optimal vector W*Wherein W is*The calculation method comprises the following steps:
Figure BDA0002813006280000057
training covariance matrix ExiIn 1 line niMapping Z under the column's mapping spaceiThe vectors are as follows:
Zi＝(W*)TExi，(i＝1，2)
threshold z of Fisher criterion0It can be calculated by the following formula:
Figure BDA0002813006280000061
Figure BDA0002813006280000062
wavelet packet analysis is carried out on the original sound signals extracted in real time to obtain a relative wavelet packet coefficient E*Then vector Z is mapped*As follows:
Figure BDA0002813006280000063
when the k sample represents the mapping value zk *Satisfies zk *≤z0If the k sample is an abnormal sample, the system alarms.
The warehouse anti-theft alarm method is adopted for testing: firstly, sound signals when 39 groups of keys are opened, namely normal original sound signals, and sound signals when 40 groups of keys are opened, namely abnormal original sound signals, are collected from the electrical equipment warehouse site respectively to serve as original data. Then, wavelet packet analysis is performed, wherein the wavelet packet decomposition function used is a wpdec function, the wavelet base used is a db3 wavelet, the number of decomposition layers is 3, and the function reconstructed by the wavelet packet decomposition coefficients used is a wprcoef function, by which each sound signal can decompose the wavelet packet coefficients of 8 nodes in total, i.e., nodes (3, 0), (3, 1), (3, 2), (3, 3), (3, 4), (3, 5), (3, 6), (3, 7). The wavelet packet coefficient energy table 1 of each node of the 79 groups of signals can be obtained through a wavelet packet coefficient energy formula.
TABLE 179 relative wavelet packet coefficient energy of group signals
Figure BDA0002813006280000064
Figure BDA0002813006280000071
The kernel function is Sigmoid function, according toPerforming kernel function line processing on the energy matrix of the relative wavelet packet coefficient calculated by the matrix formed by the 79 pieces of data, and determining internal parameters in the kernel function, the optimal vector in the kernel Fisher analysis method and a threshold value by taking the finally obtained matrix as a training covariance matrix, wherein the threshold value z is0Is 0. The training covariance matrix composed of these 79 signals is used as the test covariance matrix to perform kernel Fisher analysis based on Sigmoid function, and the mapping values of the 79 signal data in Fisher mapping space can be calculated as shown in fig. 2.
Fig. 2 shows that the kernel Fisher analysis method based on the Sigmoid function is very suitable for structural data of a normal door opening sound signal and an abnormal sound signal, the accuracy is 100%, the intra-class dispersion of the normal door opening sound signal and the abnormal door opening sound signal is very small, and the inter-class dispersion is very large, that is, the difference between the mapping value of the normal door opening sound signal and the abnormal door opening sound signal in the Fisher space and the threshold value is very large, the criterion margin is very high, and no misjudgment exists. Therefore, whether the warehouse door and the warehouse window are prized or not can be well judged, and finally the warehouse anti-theft alarm function is realized.
In the detailed description of the embodiments, various technical features may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.

Claims (10)

1. An anti-theft alarm method for a warehouse is characterized by comprising the following steps:
acquiring real-time original sound signals of the opened door of the warehouse, carrying out wavelet packet analysis on the real-time original sound signals to obtain real-time relative wavelet packet coefficient energy, calculating a mapping value z according to a kernel Fisher analysis method by taking the real-time relative wavelet packet coefficient energy as characteristic quantityk *；
Collecting a training set E consisting of historical sound signals, carrying out wavelet packet analysis on the training set E to obtain historical relative wavelet packet coefficient energy, calculating a threshold value z according to a kernel Fisher analysis method by taking the historical relative wavelet packet coefficient energy as characteristic quantity0；
The z isk *And said z0Making a comparison when zk *＞z0When the original sound signal is normal, when z isk *≤z0When the original sound signal is abnormal, the system alarms.
2. The warehouse burglar alarm method according to claim 1, wherein the real-time original sound signal is subjected to wavelet packet analysis, i.e. the real-time original sound signal is decomposed and reconstructed by J-layer wavelet packet transformation to obtain 2JReal-time wavelet packet coefficient signals of different frequency bands.
3. The warehouse anti-theft alarm method according to claim 2, wherein the calculation method of the wavelet packet coefficient energy of the real-time wavelet packet coefficient signal of each frequency band is as follows:
Figure FDA0002813006270000011
where n is the total number of sample points of the acquired real-time original sound signal, EJiFor the wavelet packet coefficient energy, x, of the node (J, i) after the wavelet packet transformationJi(k)Is the kth wavelet packet coefficient in node (J, i).
4. The warehouse anti-theft alarm method according to claim 3, wherein the calculation method of the real-time relative wavelet packet coefficient energy is as follows:
Figure FDA0002813006270000012
in the formula, eJiThe relative wavelet packet coefficient energy of the node (J, i) after wavelet packet transformation.
5. The warehouse anti-theft alarm method according to any one of claims 1 to 4, wherein the historical relative wavelet packet coefficient energy is used as a characteristic quantity, and the training set E consisting of historical sound signals is a relative wavelet packet coefficient energy matrix consisting of n training samples, including a normal original sound signal relative wavelet packet coefficient energy matrix E1Energy matrix E of relative wavelet packet coefficient of abnormal original sound signal2Mapping the extracted nonlinear data to a high-dimensional space through a kernel function to obtain a linear change matrix K, and then performing centralization processing on the change matrix K to obtain a centralized matrix
Figure FDA0002813006270000021
The calculation method is as follows:
Figure FDA0002813006270000022
in the formula, mun＝one(n)/n
Wherein one (n) is an n-dimensional identity matrix;
thus, the training covariance matrix based on the training samples
Figure FDA0002813006270000023
6. The warehouse burglar alarm method according to claim 5, wherein a covariance matrix E is trainedxComprises n samples1And n2Is turning toConstant original sound signal data matrix Ex1And an abnormal original sound signal data matrix Ex2Normal original sound signal data matrix Ex1And an abnormal original sound signal data matrix Ex2Respectively, are m1And m2The calculation method is as follows:
Figure FDA0002813006270000024
7. the warehouse burglar alarm method according to claim 6, wherein the internal parameters of the kernel Fisher analysis method include Fisher criterion j (w), wherein Fisher criterion j (w) is defined as follows:
Figure FDA0002813006270000025
in the formula, W is a weight vector in the Fisher criterion.
8. The warehouse burglar alarm method according to claim 7, wherein the weight vector when j (W) is maximum is an optimal vector W*Wherein W is*The calculation method comprises the following steps:
Figure FDA0002813006270000026
9. the warehouse burglar alarm method according to claim 8, wherein a covariance matrix E is trainedxiIn 1 line niMapping Z under the column's mapping spaceiThe vectors are as follows:
Zi＝(W*)TExi，(i＝1，2)
threshold z of Fisher criterion0It can be calculated by the following formula:
Figure FDA0002813006270000027
Figure FDA0002813006270000028
10. the warehouse burglar alarm method according to claim 9, wherein the extracted real-time original sound signal is subjected to wavelet packet analysis to obtain a relative wavelet packet coefficient E*Then vector Z is mapped*As follows:
W*TE*＝(z1 *,z2 *,......zn *)＝Z*
when the k sample represents the mapping value zk *Satisfies zk *≤z0If the k sample is an abnormal sample, the system alarms.
CN202011391597.9A 2020-12-02 2020-12-02 Warehouse anti-theft alarm method Active CN112489330B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011391597.9A CN112489330B (en) 2020-12-02 2020-12-02 Warehouse anti-theft alarm method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011391597.9A CN112489330B (en) 2020-12-02 2020-12-02 Warehouse anti-theft alarm method

Publications (2)

Publication Number Publication Date
CN112489330A true CN112489330A (en) 2021-03-12
CN112489330B CN112489330B (en) 2022-02-11

Family

ID=74939076

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011391597.9A Active CN112489330B (en) 2020-12-02 2020-12-02 Warehouse anti-theft alarm method

Country Status (1)

Country Link
CN (1) CN112489330B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113671363A (en) * 2021-08-13 2021-11-19 华北电力大学（保定） High-voltage circuit breaker state identification system and method

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101017128A (en) * 2006-10-13 2007-08-15 华中科技大学 Analysis method for localized corroding based on electrochemistry noise
CN101773394A (en) * 2010-01-06 2010-07-14 中国航天员科研训练中心 Identification method and identification system using identification method
CN101877172A (en) * 2009-12-21 2010-11-03 金会庆 Impact sound-based automatic traffic accident detection method
CN101908138A (en) * 2010-06-30 2010-12-08 北京航空航天大学 Identification method of image target of synthetic aperture radar based on noise independent component analysis
CN102289568A (en) * 2011-07-18 2011-12-21 电子科技大学 Large emergent equipment fault prediction method based on offline time sequence data
CN102944435A (en) * 2012-10-25 2013-02-27 北京航空航天大学 Health assessment and fault diagnosis method for rotating machinery based on fisher discriminant analysis and mahalanobis distance
CN104900228A (en) * 2015-04-30 2015-09-09 重庆理工大学 Suspicious door opening sound identification apparatus and identification method
CN109326355A (en) * 2018-08-16 2019-02-12 浙江树人学院 A kind of fireman's Breathiness monitoring earphone and its physical condition appraisal procedure
KR20200043650A (en) * 2018-10-18 2020-04-28 황설리 Road facilities
KR20200069506A (en) * 2018-12-07 2020-06-17 이화여자대학교 산학협력단 Method of smart home alert service based on deep learning for hearing-impaired people, apparatus of sound analysis for performing the method and smart home alert system

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101017128A (en) * 2006-10-13 2007-08-15 华中科技大学 Analysis method for localized corroding based on electrochemistry noise
CN101877172A (en) * 2009-12-21 2010-11-03 金会庆 Impact sound-based automatic traffic accident detection method
CN101773394A (en) * 2010-01-06 2010-07-14 中国航天员科研训练中心 Identification method and identification system using identification method
CN101908138A (en) * 2010-06-30 2010-12-08 北京航空航天大学 Identification method of image target of synthetic aperture radar based on noise independent component analysis
CN102289568A (en) * 2011-07-18 2011-12-21 电子科技大学 Large emergent equipment fault prediction method based on offline time sequence data
CN102944435A (en) * 2012-10-25 2013-02-27 北京航空航天大学 Health assessment and fault diagnosis method for rotating machinery based on fisher discriminant analysis and mahalanobis distance
CN104900228A (en) * 2015-04-30 2015-09-09 重庆理工大学 Suspicious door opening sound identification apparatus and identification method
CN109326355A (en) * 2018-08-16 2019-02-12 浙江树人学院 A kind of fireman's Breathiness monitoring earphone and its physical condition appraisal procedure
KR20200043650A (en) * 2018-10-18 2020-04-28 황설리 Road facilities
KR20200069506A (en) * 2018-12-07 2020-06-17 이화여자대학교 산학협력단 Method of smart home alert service based on deep learning for hearing-impaired people, apparatus of sound analysis for performing the method and smart home alert system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113671363A (en) * 2021-08-13 2021-11-19 华北电力大学（保定） High-voltage circuit breaker state identification system and method

Also Published As

Publication number Publication date
CN112489330B (en) 2022-02-11

Similar Documents

Publication Publication Date Title
CN103968933B (en) Fiber-optic vibration signal recognition method based on fuzzy field feature
CN110213222A (en) Network inbreak detection method based on machine learning
CN109446804B (en) Intrusion detection method based on multi-scale feature connection convolutional neural network
CN112420055A (en) Substation state identification method and device based on voiceprint characteristics
CN111080105A (en) Transformer area user-to-user relationship identification method and system based on voltage time sequence data
CN109190598A (en) A kind of rotating machinery monitoring data noise detection method based on SES-LOF
KR100733145B1 (en) Fingerprint Producing Method and Audio Fingerprinting System Based on Normalized Spectral Subband Centroids
CN112637834B (en) Fingerprint fusion identification method and device for wireless communication equipment
CN115296853A (en) Network attack detection method based on network space-time characteristics
CN112489330B (en) Warehouse anti-theft alarm method
CN110702966A (en) Fault arc detection method, device and system based on probabilistic neural network
CN114371353A (en) Power equipment abnormity monitoring method and system based on voiceprint recognition
Wang et al. A novel underground pipeline surveillance system based on hybrid acoustic features
CN115510909A (en) Unsupervised algorithm for DBSCAN to perform abnormal sound features
CN111999591A (en) Method for identifying abnormal state of primary equipment of power distribution network
Tang et al. Classification for transient overvoltages in offshore wind farms based on sparse decomposition
CN109375041B (en) Single-phase grounding fault judgment method for small-current grounding system
CN116318877A (en) Method for defending countersamples by using intrusion detection system with various characteristic manifold vectors
CN116069607A (en) Mobile office user abnormal behavior detection method based on graph convolution neural network
CN113159181B (en) Industrial control system anomaly detection method and system based on improved deep forest
CN115410599A (en) Method and system for identifying running state of transformer based on voiceprint perception
CN114121025A (en) Voiceprint fault intelligent detection method and device for substation equipment
CN109935234B (en) Method for identifying source equipment of sound recording
Ghiurcau et al. A modified TESPAR algorithm for wildlife sound classification
CN112954689A (en) Lightweight network intrusion detection system and method for Bluetooth wireless transmission

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
GR01 Patent grant