CN117875053A - Sound sensor layout optimization method and system for equipment operation monitoring - Google Patents
Sound sensor layout optimization method and system for equipment operation monitoring Download PDFInfo
- Publication number
- CN117875053A CN117875053A CN202410035307.9A CN202410035307A CN117875053A CN 117875053 A CN117875053 A CN 117875053A CN 202410035307 A CN202410035307 A CN 202410035307A CN 117875053 A CN117875053 A CN 117875053A
- Authority
- CN
- China
- Prior art keywords
- sound
- sensor
- monitoring area
- monitoring
- determining
- 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
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 239
- 238000000034 method Methods 0.000 title claims abstract description 84
- 238000005457 optimization Methods 0.000 title claims abstract description 70
- 230000005236 sound signal Effects 0.000 claims abstract description 85
- 230000008859 change Effects 0.000 claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 35
- 239000011159 matrix material Substances 0.000 claims description 29
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000009826 distribution Methods 0.000 claims description 12
- 230000035772 mutation Effects 0.000 claims description 10
- 238000001228 spectrum Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000009286 beneficial effect Effects 0.000 description 14
- 238000004458 analytical method Methods 0.000 description 11
- 230000000694 effects Effects 0.000 description 7
- 239000013598 vector Substances 0.000 description 7
- 230000004044 response Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000004069 differentiation Effects 0.000 description 3
- 230000004807 localization Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- JJWKPURADFRFRB-UHFFFAOYSA-N carbonyl sulfide Chemical compound O=C=S JJWKPURADFRFRB-UHFFFAOYSA-N 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- 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
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The invention relates to a sound sensor layout optimization method for equipment operation monitoring, which comprises the following steps: determining a monitoring area of the device; uniformly distributing each sound sensor in a monitoring area; when the equipment is in operation, acquiring corresponding first sound signals based on each sound sensor, processing the first sound signals of each sound sensor, and determining first sound intensity changes; dividing the monitoring area according to the first sound intensity change to obtain a plurality of sub-monitoring areas; determining target sound sensor optimization schemes of all sub-monitoring areas, and determining the optimized layout of the monitoring areas of the equipment according to the target sound sensor optimization schemes of all the sub-monitoring areas; by adopting the scheme, the sensor can be better optimized in layout, and the sensor can play a better role.
Description
Technical Field
The invention relates to the technical field of sensor layout optimization, in particular to a sound sensor layout optimization method and system for equipment operation monitoring.
Background
Currently, sensors are devices for detecting and sensing physical quantities, chemical quantities or other types of information in the environment, and as the progress of science and technology and the demand for applications continue to increase, the sensors have been penetrated into extremely wide fields such as industrial production, cosmic development, ocean exploration, environmental protection, resource investigation, medical diagnosis, biological engineering, even cultural relics protection, and the like; it can be said without exaggeration that from the space in the vast area to the ocean in the vast area, to the complex engineering systems, almost every modern project is free from various sensors. With the development of the internet of things and intelligent technology, the number of sensors is rapidly increased, and the sensors themselves become more and more complex; the diversity and complexity of the sensors provide challenges for the layout, and the sound sensor is reasonably distributed in a specific working environment for detecting the positions of the sensors and the density distribution of the sensors in the sound event process, so that the maximum effect of the sensors becomes a problem to be solved currently.
Disclosure of Invention
The present invention aims to solve, at least to some extent, one of the technical problems in the above-described technology. Therefore, the invention aims to provide a sound sensor layout optimization method for equipment operation monitoring, which is used for solving the problem that the positions of the sound sensors and the number of the sensors are reasonably distributed in a specific working environment in the process of detecting sound events, so that the sensors exert the maximum effect.
To achieve the above objective, an embodiment of the present invention provides a method for optimizing a layout of a sound sensor for monitoring operation of a device, including:
determining a monitoring area of the device;
uniformly distributing each sound sensor in a monitoring area;
when the equipment is in operation, acquiring corresponding first sound signals based on each sound sensor, processing the first sound signals of each sound sensor, and determining first sound intensity changes;
dividing the monitoring area according to the first sound intensity change to obtain a plurality of sub-monitoring areas;
and determining the target sound sensor optimization schemes of all the sub-monitoring areas, and determining the optimized layout of the monitoring areas of the equipment according to the target sound sensor optimization schemes of all the sub-monitoring areas.
Preferably, the target sound sensor optimization scheme for determining the sub-monitoring area includes:
selecting one sub-monitoring area at will as a target sub-monitoring area;
when the equipment operates, closing the sound sensors in other sub-monitoring areas except the target sub-monitoring area;
determining the number and the position of sound sources in the target sub-monitoring area according to the second sound signals acquired by the sound sensors in the target sub-monitoring area;
And determining a sound sensor optimization scheme of the target sub-monitoring area according to the number of sound sources in the target sub-monitoring area, the positions of the sound sources and the second sound intensity change of the collected second sound signals.
Preferably, when the device is operated, the corresponding first sound signal is acquired based on each sound sensor, the first sound signal of each sound sensor is processed, and the first sound intensity change is determined, including:
analyzing and processing according to the first sound signals of each sound sensor, and determining a matrix of sound intensity as follows:
wherein S is m Is a matrix of sound intensities;representing the sound intensity of the ith sensor when the nth sound source in the monitoring area sounds in j grades; sound intensity level from 0 to l;
determining a first sound intensity variation from a matrix of sound intensities:
wherein Δs is a first sound intensity variation matrix;representing a preset sound intensity of a z-th sound sensor in the monitoring area; />
Preferably, the monitoring area is divided according to the first sound intensity change to obtain a plurality of sub-monitoring areas, including:
determining a sound intensity mutation value of the monitoring area according to the first sound intensity change;
and dividing the monitoring area by taking the sound source corresponding to the sound intensity mutation value as a center and taking the preset distance as a radius to obtain a plurality of sub-monitoring areas.
Preferably, determining the number of sound sources and the sound source position of the target sub-monitoring area according to the second sound signals collected by the sound sensors in the target sub-monitoring area includes:
performing short-time Fourier transform processing on the second sound signals collected by the sound sensors in the target sub-monitoring area to obtain time-frequency domain sound signals of the signals collected by the sensors;
setting first grid precision for the time-frequency domain sound signals, and constructing a first sparse dictionary based on a maximum directional beam former;
in the first sparse dictionary, a sparse Bayes learning method and a expectation maximization method are used for calculating to obtain a first sound source position of a target sub-monitoring area;
the number of sound sources is determined based on the first sound source position.
Preferably, the calculating to obtain the first sound source position of the target sub-monitoring area by using a sparse bayesian learning method and an expectation maximization method includes:
presetting a first parameter in a sparse Bayes learning method;
based on a first parameter of sparse Bayesian learning, calculating to obtain a first average value and a first variance of a sparse matrix;
determining a second parameter based on the expectation maximization method, the first average value of the sparse matrix and the first variance;
Based on a second parameter of sparse Bayesian learning, calculating to obtain a second average value and a second variance of the sparse matrix;
an iterative operation, wherein when the P-th variance is less than or equal to a preset variance threshold, the iterative operation is stopped; the highest peak of the energy spectrum of the P-th average is determined as grouping a number of first sound source positions.
Preferably, after the calculating to obtain the first sound source position of the target sub-monitoring area by using the sparse bayesian learning method and the expectation maximization method, the method further includes:
setting a second grid precision for the time-frequency domain sound signal;
acquiring a time-frequency domain sound signal of a signal acquired by a sensor in a preset range of any one first sound source position to obtain a target time-frequency domain sound signal;
determining a second sparse dictionary according to the weight of the maximum directional beam former and the second grid precision time-domain sound signals of the target; calculating a second sound source position in a preset range of the first sound source position based on a second sparse dictionary, a sparse Bayes learning method and a expectation maximization method;
repeating the iteration operation, and stopping iteration when the sum of the Euclidean distance between the nth sound source position and the previous n-1 sound source positions is less than or equal to a preset distance threshold value; the nth sound source position is determined as the final sound source position.
Preferably, the determining the sound sensor optimization scheme of the target sub-monitoring area according to the number of sound sources, the positions of the sound sources and the collected second sound intensity variation of the second sound signals includes:
acquiring the area of a target sub-monitoring area;
acquiring Euclidean distance between sound sensors in a target sub-monitoring area and Euclidean distance between each sensor and the sound source position;
determining a sensor optimization index based on a preset optimization index algorithm;
sequentially reducing the number of the sensors in the preset range of the target sound source position, repeatedly calculating the sensor optimization indexes when the number of the sensors in the preset range of the target sound source position is reduced, and stopping iterative calculation until the number of the sensors in the preset range is 1, so as to obtain a plurality of sensor optimization indexes;
searching an optimal allocation scheme by using a particle swarm optimization algorithm based on a plurality of sensor optimization indexes;
and determining a sound sensor optimization scheme of the target sub-monitoring area based on the optimal sensor scheme.
Preferably, the preset optimization index algorithm includes:
where Yh represents the sensor optimization index, min (D ij ) Representing the Euclidean distance between each sensor and the nearest sensor in the target sub-monitoring area; d (D) iz Representing the Euclidean distance from each sensor to the sound source position in the target sub-monitoring area; s is the area of the target sub-monitoring area; ΔS max Representing the maximum value of the change of the sound intensity received by the sensor in the target sub-monitoring area; ΔS min Representing the minimum value of the change of the intensity of the sound received by the sensor in the target sub-monitoring area; m is the number of sensors; e is a natural constant.
Preferably, a sound sensor layout optimization system for equipment operation monitoring, comprising:
a determining module for determining a monitoring area of the device;
the distribution module is used for uniformly distributing the sound sensors in the monitoring area;
the sound intensity module is used for acquiring corresponding first sound signals based on each sound sensor when the equipment is in operation, processing the first sound signals of each sound sensor and determining first sound intensity change;
dividing the monitoring area according to the first sound intensity change to obtain a plurality of sub-monitoring areas;
and the optimizing module is used for determining the target sound sensor optimizing schemes of all the sub-monitoring areas and determining the optimizing layout of the monitoring areas of the equipment according to the target sound sensor optimizing schemes of all the sub-monitoring areas.
The beneficial effects of the invention are as follows: by uniformly distributing each sound sensor in the monitoring area, the comprehensiveness and accuracy of monitoring can be increased; each sensor can be responsible for monitoring the sound change of a specific area, so that the monitoring effect of the whole system is improved; by processing the first sound signal of each sound sensor, a change in sound intensity between the sensors can be determined; this can help to further optimize the layout to minimize overlap areas or dead zones, improving the effectiveness of the layout; dividing a monitoring area into a plurality of sub-monitoring areas according to the first sound intensity change; this division allows better differentiation between different sound sources for more accurate monitoring and identification of the operating state of the device; determining a sound sensor optimization scheme of the target based on the characteristics and requirements of each sub-monitoring area; this may include strategies such as sensor position adjustment, increasing or decreasing the number of sensors to maximize monitoring; and determining the overall optimized layout of the equipment monitoring area according to the target sound sensor optimization scheme of each sub-monitoring area. This ensures the consistency and consistency of the overall layout to achieve optimal monitoring; the sound sensor layout can be more reasonable and efficient, and the accuracy and reliability of equipment operation monitoring can be improved; this helps to discover the abnormal state of the device in time, prevent potential failure, and improve maintenance and management efficiency of the device.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of a method of optimizing a sound sensor layout for device operational monitoring according to one embodiment of the invention;
FIG. 2 is a flow chart of a target sound sensor optimization scheme for determining a sub-monitoring area in accordance with one embodiment of the invention;
FIG. 3 is a block diagram of a sound sensor layout optimization system for device operation monitoring in accordance with one embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Example 1
As shown in fig. 1, a method for optimizing a sound sensor layout for monitoring operation of a device includes:
s1, determining a monitoring area of equipment;
s2, uniformly distributing each sound sensor in a monitoring area;
s3, when the equipment is operated, acquiring corresponding first sound signals based on each sound sensor, processing the first sound signals of each sound sensor, and determining first sound intensity change;
s4, dividing the monitoring area according to the first sound intensity change to obtain a plurality of sub-monitoring areas;
and S5, determining target sound sensor optimization schemes of all the sub-monitoring areas, and determining the optimized layout of the monitoring areas of the equipment according to the target sound sensor optimization schemes of all the sub-monitoring areas.
In this embodiment, the processing of the first sound signal of each sound sensor further comprises: noise reduction and enhancement are performed on the sound signal.
In this embodiment, the monitored area is divided according to the first sound intensity variation to obtain a plurality of sub-monitored areas, so as to more accurately locate and identify the sound source or the specific sound event; by subdividing the monitoring area into a plurality of sub-monitoring areas, the monitoring precision can be improved, and the positioning error can be reduced, so that the identification accuracy can be improved.
The beneficial effects of the technical scheme are that: by uniformly distributing each sound sensor in the monitoring area, the comprehensiveness and accuracy of monitoring can be increased; each sensor can be responsible for monitoring the sound change of a specific area, so that the monitoring effect of the whole system is improved; by processing the first sound signal of each sound sensor, a change in sound intensity between the sensors can be determined; this can help to further optimize the layout to minimize overlap areas or dead zones, improving the effectiveness of the layout; dividing a monitoring area into a plurality of sub-monitoring areas according to the first sound intensity change; this division allows better differentiation between different sound sources for more accurate monitoring and identification of the operating state of the device; determining a sound sensor optimization scheme of the target based on the characteristics and requirements of each sub-monitoring area; this may include strategies such as sensor position adjustment, increasing or decreasing the number of sensors to maximize monitoring; and determining the overall optimized layout of the equipment monitoring area according to the target sound sensor optimization scheme of each sub-monitoring area. This ensures the consistency and consistency of the overall layout to achieve optimal monitoring; the sound sensor layout can be more reasonable and efficient, and the accuracy and reliability of equipment operation monitoring can be improved; this helps to discover the abnormal state of the device in time, prevent potential failure, and improve maintenance and management efficiency of the device.
Example 2
As shown in fig. 2, the target sound sensor optimization scheme for determining the sub-monitoring area includes:
selecting one sub-monitoring area at will as a target sub-monitoring area;
when the equipment operates, closing the sound sensors in other sub-monitoring areas except the target sub-monitoring area;
determining the number and the position of sound sources in the target sub-monitoring area according to the second sound signals acquired by the sound sensors in the target sub-monitoring area;
and determining a sound sensor optimization scheme of the target sub-monitoring area according to the number of sound sources in the target sub-monitoring area, the positions of the sound sources and the second sound intensity change of the collected second sound signals.
In the embodiment, the purpose of closing the sound sensors in the other sub-monitoring areas except the target sub-monitoring area is to reduce noise interference in the other areas and improve the positioning accuracy of the sound sources in the target sub-monitoring area; only the sound sensor in the target sub-monitoring area participates in signal acquisition and processing, so that signal interference in other areas can be reduced, and the accuracy of a positioning result is improved.
The beneficial effects of the technical scheme are that: by determining the sound sensor optimization scheme of the target sub-monitoring area, the positioning accuracy can be improved, the power consumption and the resource occupation can be reduced, the system response speed can be improved, and a beneficial data basis is provided for further optimizing a sound positioning algorithm, so that the accuracy and the efficiency of sound monitoring and recognition can be improved; by closing the sound sensors except the target sub-monitoring area, noise interference of other areas can be reduced, and the positioning accuracy of sound sources in the target sub-monitoring area is improved; only the sound sensor in the target sub-monitoring area participates in signal acquisition and processing, so that signal interference in other areas can be reduced, and the accuracy of a positioning result is improved; by limiting the monitoring area and switching off the irrelevant sensors, the data volume and the computational complexity of the signal processing can be reduced, thereby improving the response speed of the system. Only relevant sound source data is processed in the target sub-monitoring area, so that the number and the position of the sound sources can be rapidly determined, and the recognition and the response of sound events are accelerated; according to the second sound signals collected by the sound sensors in the target sub-monitoring area, the number of sound sources and the positions of the sound sources can be more accurately determined; the method provides valuable data basis for further optimizing the sound positioning algorithm, can carry out parameter adjustment and algorithm improvement according to specific requirements of a target sub-monitoring area, and improves the accuracy and effect of sound positioning.
Example 3
When the device is running, acquiring corresponding first sound signals based on each sound sensor, processing the first sound signals of each sound sensor, and determining a first sound intensity change, wherein the method comprises the following steps:
analyzing and processing according to the first sound signals of each sound sensor, and determining a matrix of sound intensity as follows:
wherein S is m Is a matrix of sound intensities;representing the sound intensity of the ith sensor when the nth sound source in the monitoring area sounds in j grades; sound intensity level from 0 to l;
determining a first sound intensity variation from a matrix of sound intensities:
wherein Δs is a first sound intensity variation matrix;representing a preset sound intensity of a z-th sound sensor in the monitoring area; />
In this embodiment, the first sound signal of each sound sensor is analyzed, and specific embodiments of the matrix for determining the sound intensity include, but are not limited to: preprocessing the first sound signal acquired by each sound sensor, including filtering, denoising, gain and other operations; thus, the influence of noise can be reduced, and the quality of signals is improved; cutting the first sound signal of each sound sensor into a fixed-length time period to obtain continuous sound fragments; the length of the time period can be set according to the requirement, and is usually sound data in a short period of time; for sound segments within each time period, various feature extraction methods may be used to calculate sound features, such as short-time energy, zero-crossing rate, spectral features, etc.; these features may reflect the intensity and frequency distribution of the sound; normalizing the extracted sound features to eliminate dimension differences among different sound sensors; common normalization methods include amplitude normalization, etc.; the feature vector of each sound sensor is combined into a matrix, and the matrix of sound intensity can be obtained by carrying out statistical analysis and mathematical model establishment on the feature matrix.
In this embodiment, the preset sound intensity of the sensor in the monitoring area is specifically: an initial sensor is set up to be in contact with the object,
wherein,represents the preset sound intensity of the set initial sensor, e is a natural constant, delta represents the attenuation coefficient, and the value range (0, 1]L represents the distance between the other sensor and the set initial sensor.
The beneficial effects of the technical scheme are that: the occurrence of different sound events can be monitored and identified in real time by analyzing and processing the first sound signals of each sound sensor, and the change matrix of the sound intensity is determined; the method can be applied to the fields of safety monitoring, environmental protection and the like, and improves the perception and response capability to sound events; the first sound signals of all the sound sensors are analyzed and processed, so that a matrix of sound intensity can be determined, and the position of a sound source is calculated through a sound source positioning algorithm; by analyzing and processing the first sound signals of each sound sensor, characteristics can be extracted and a sound intensity matrix can be constructed, and then a sound recognition model is applied to judge sound types or recognize specific sounds; by analyzing and processing the first sound signals of the respective sound sensors, the change trend of the sound intensity can be determined; and the method is beneficial to improving the perceptibility, accuracy and response capability.
Example 4
Dividing the monitoring area according to the first sound intensity change to obtain a plurality of sub-monitoring areas, including:
determining a sound intensity mutation value of the monitoring area according to the first sound intensity change;
and dividing the monitoring area by taking the sound source corresponding to the sound intensity mutation value as a center and taking the preset distance as a radius to obtain a plurality of sub-monitoring areas.
In this embodiment, the specific implementation manner of determining the mutation value of the sound intensity of the monitoring area according to the first sound intensity change is as follows: according to the change trend of the sound intensity, different methods can be adopted to calculate the abrupt change value of the sound intensity; common methods include differential operation, sliding window averaging, differencing, and the like; according to the calculated abrupt change value of the sound intensity, a reasonable threshold value is set to judge whether the abrupt change of the sound intensity occurs or not; the appropriate threshold may be determined based on historical data or experience.
The beneficial effects of the technical scheme are that: by determining the sound intensity mutation value of the monitoring area according to the first sound intensity variation, the position of the sound source can be more accurately positioned; the sound source corresponding to the sound intensity mutation value is used as the center of the sub-monitoring area, so that the sound source positioning accuracy is improved; dividing the monitoring area according to the sound intensity mutation value, and subdividing the whole monitoring range into a plurality of sub-monitoring areas; this provides better regional management and monitoring analysis of the sound for targeted processing and control.
Example 5
According to the second sound signals collected by the sound sensors in the target sub-monitoring area, determining the sound source number and the sound source position of the target sub-monitoring area comprises the following steps:
performing short-time Fourier transform processing on the second sound signals collected by the sound sensors in the target sub-monitoring area to obtain time-frequency domain sound signals of the signals collected by the sensors;
setting first grid precision for the time-frequency domain sound signals, and constructing a first sparse dictionary based on a maximum directional beam former;
in the first sparse dictionary, a sparse Bayes learning method and a expectation maximization method are used for calculating to obtain a first sound source position of a target sub-monitoring area;
the number of sound sources is determined based on the first sound source position.
In this embodiment, the short-time fourier transform processing aims to divide a signal into a plurality of short-time windows, and perform fourier transform on the signal in each window to obtain spectrum information of the signal in the period; by decomposing the signal into a plurality of time-frequency spectral segments, frequency components of the signal over different time periods can be obtained.
In this embodiment, the first grid precision is set for the time-frequency domain sound signal, and the time-frequency domain analysis refers to a method for analyzing the signal in time and frequency at the same time, so that more detailed and comprehensive signal information can be provided; by setting the first grid precision, the resolution of time-frequency conversion can be controlled, so that the time-frequency characteristic of the signal can be described and analyzed more finely; as the accuracy of the first grid is increased, the resolution of the time domain is also improved, and the time-varying characteristics of the signals can be more accurately described; the higher first grid accuracy can improve the frequency domain resolution and can more accurately represent the energy distribution of the signal on different frequencies. For signals with faster frequency variation or signals with denser frequency components, the frequency characteristics of the signals can be better distinguished; by setting higher first grid precision, the time-frequency domain analysis can provide finer time-frequency characteristic information; the frequency spectrum change of the signal, the evolution trend of the frequency component and the time-frequency relation can be better analyzed.
In this embodiment, the first grid precision refers to the time and frequency resolution of the time-frequency transform; time resolution refers to the ability of a signal to be accurately represented in the time domain, i.e., the resolution on the time axis, typically expressed in terms of the length of a time window; a shorter time window may provide higher time resolution, enabling better capture of short-time varying signal characteristics, such as transient signals. However, the shorter the time window, the lower the frequency accuracy; frequency resolution refers to the ability of a signal to be represented accurately in the frequency domain, i.e., the resolution on the frequency axis, typically expressed in terms of the width of a frequency window; a narrower frequency window may provide higher frequency resolution, enabling better resolution of small differences between frequencies. However, the narrower the frequency window, the lower the time resolution; the first grid accuracy takes into account both time resolution and frequency resolution, which represent the minimum time and frequency separation in the time-frequency transform.
In this embodiment, the maximum directivity beamformer is a technique for array signal processing, aiming at forming the maximum directivity beam by reasonable weight adjustment; the goal of a maximum directional beamformer is to maximize the signal received power in a selected direction while minimizing the received power in the other directions under given constraints; in general, the constraint may be to control the total power of the array or to direct the array in a particular direction.
In the embodiment, the sound signal is subjected to time-frequency transformation, the time-frequency domain signal is divided into grids, and the time and frequency intervals of the grids are the first grid precision; selecting a proper grid precision according to specific requirements and computing resource availability; the maximum directional beam former is utilized, the signal gain amplification in a specific direction is realized by adjusting the weight distribution of each sensor in the array, and interference signals in other directions are restrained; based on the output of the maximum directivity beamformer, a first sparse dictionary may be constructed; the sparse dictionary is composed of a set of atomic (basis) vectors, each of which is the output of a corresponding sensor for representing the components of the original signal in different directions; the first sound position of the target sub-monitoring area can be calculated by using a sparse Bayesian learning method and an expectation maximization method; the principle of sparse representation and probability statistics is combined, so that the sparse representation of the original signal can be recovered from the sparse dictionary, and the position of the target sound source can be estimated.
In this embodiment, a specific implementation manner of constructing the first sparse dictionary is: setting a first grid precision, namely determining the interval between time and frequency; for example, the result of the time-frequency domain analysis may be divided into N time grid points and M frequency grid points, to obtain an n×m grid matrix; calculating the beam output on each grid point according to the position of the array sensor and the sound signal to be analyzed by using the maximum directivity beam former; the beam output indicates the signal strength in that direction; the beam output on each grid point is taken as an atomic vector, and the vectors are combined together according to the sequence of rows or columns to form a first sparse dictionary; this dictionary will be used in subsequent sparse representations for estimating the location of the target sound source; adopting sparse representation algorithms such as a sparse Bayesian learning method, a expectation maximization method and the like, and estimating the position of a target sound source by carrying out sparse representation on sound signals; the algorithms obtain sparse representation results by using a first sparse dictionary and in a mode of iteratively updating weight coefficients; calculating the position estimation of the target sound source according to the sparse representation result; according to the information of time delay, angle and the like of the sound signals, the coordinate position of the target sound source in the space can be calculated by combining the positions of the array sensors.
The beneficial effects of the technical scheme are as follows: performing short-time Fourier transform (STFT) processing on the second sound signals collected by the sound sensors in the target sub-monitoring area to obtain time-frequency domain sound signals of the signals collected by the sensors; the STFT can represent the signal on a time frequency domain to provide time frequency characteristic information; setting first grid precision for the time-frequency domain sound signal, and constructing a first sparse dictionary according to the method; the dictionary is composed of beam vectors output by the beam former and used for representing signal components in different directions; calculating to obtain a first sound source position of a target sub-monitoring area through sparse representation by using a sparse Bayesian learning method and a expectation maximization method; the method combines the principles of sparse representation and probability statistics, and can recover the sparse representation of the sound source from the first sparse dictionary so as to estimate the position of the sound source; according to the first sound source position, a similar method can be used for processing the sound signal again to obtain an estimation of the second sound source position; by analyzing and comparing the differences of the first sound source position and the second sound source position, the number of sound sources of the target sub-monitoring area can be determined based on the comparison; the sound source quantity estimation in the target sub-monitoring area can be obtained; this makes further sound analysis and processing more accurate and reliable; this is of great importance for sound source localization, analysis, target detection and other applications.
Example 6
The method for calculating the first sound source position of the target sub-monitoring area by using the sparse Bayesian learning method and the expectation maximization method comprises the following steps:
presetting a first parameter in a sparse Bayes learning method;
based on a first parameter of sparse Bayesian learning, calculating to obtain a first average value and a first variance of a sparse matrix;
determining a second parameter based on the expectation maximization method, the first average value of the sparse matrix and the first variance;
based on a second parameter of sparse Bayesian learning, calculating to obtain a second average value and a second variance of the sparse matrix;
an iterative operation, wherein when the P-th variance is less than or equal to a preset variance threshold, the iterative operation is stopped; the highest peak of the energy spectrum of the P-th average is determined as grouping a number of first sound source positions.
In the embodiment, the sparse Bayesian learning method is a probability modeling method for sparse representation problem; the method combines the ideas of Bayesian learning and sparse representation, and aims to estimate sparse representation of data and corresponding model parameters through observation data;
in this embodiment, the first parameter of sparse bayesian learning is to control the degree of sparseness.
In this embodiment, the sparse bayesian learning method is specifically implemented: selecting a suitable sparse prior distribution, such as a laplacian distribution or a gaussian distribution; the sparseness degree is controlled by setting parameters of prior distribution; constructing a probability model by utilizing the data samples of the sound intensity; representing the data samples as linear combinations of basis vectors according to the assumption of sparse representation, wherein coefficients of most of the basis vectors are 0; calculating posterior probability under given observation data according to a Bayesian formula; according to the sparse prior distribution and the likelihood function of the observation data, a posterior probability form can be obtained; parameters in the model are estimated by methods such as maximum a posteriori estimation or variance inference, including sparsely represented coefficients and other model parameters, such as a second parameter.
In the embodiment, the purpose of the iterative operation is to gradually approach the optimal solution through multiple iterations, so as to obtain a more accurate result; when the P-th variance is less than or equal to a preset variance threshold, the purpose of stopping the iterative operation is to control the iterative times, so that the algorithm is ensured to converge in a reasonable iterative time. And when the P-th variance is smaller than or equal to a preset variance threshold, the algorithm is indicated to reach a preset precision requirement, and iteration can be stopped.
In this embodiment, the purpose of determining the highest peak of the energy spectrum of the P-th average as grouping the number of first sound source positions is to determine the sound source positions based on the analysis of the energy spectrum; by calculating the energy spectrum of the P-th average value, the peak value with the highest energy can be found, and the frequency corresponding to the preset peak value is the first sound source position; with the position of the highest peak as an estimate of the first sound source position, the sound sources may be grouped for subsequent processing and analysis.
The beneficial effects of the technical scheme are that: the sparse Bayesian learning and expectation maximization method combines probability modeling and parameter estimation technologies, and can provide accurate sound source position estimation by modeling and optimizing observation data; the sparse Bayesian learning method considers the assumption of sparse representation when estimating the sound source position, can better describe the characteristics of signals and reduce the influence of redundant information on the result; through the expectation maximization method, parameters of the model can be automatically adjusted, so that the model is better adapted to observed data, and the accuracy and stability of sound source position estimation are improved; through iterative operation and setting the P-th variance less than or equal to a preset variance threshold as a stopping condition, the convergence of the algorithm can be effectively controlled, invalid calculation is avoided, and the calculation process is accelerated; the peak of the energy spectrum of the P-th average value is calculated, so that the positions of a plurality of first sound sources can be further determined, and finer analysis and processing of the sound sources are facilitated; the positioning accuracy and stability can be improved by utilizing a sparse Bayesian learning method and a expectation maximization method to carry out sound source position estimation, and further grouping of sound sources is realized through energy spectrum analysis, so that more beneficial information is provided for subsequent processing and analysis.
Example 7
After the first sound source position of the target sub-monitoring area is calculated by using the sparse Bayesian learning method and the expectation maximization method, the method further comprises the following steps:
setting a second grid precision for the time-frequency domain sound signal;
acquiring a time-frequency domain sound signal of a signal acquired by a sensor in a preset range of any one first sound source position to obtain a target time-frequency domain sound signal;
determining a second sparse dictionary according to the weight of the maximum directional beam former and the second grid precision time-domain sound signals of the target; calculating a second sound source position in a preset range of the first sound source position based on a second sparse dictionary, a sparse Bayes learning method and a expectation maximization method;
repeating the iteration operation, and stopping iteration when the sum of the Euclidean distance between the nth sound source position and the previous n-1 sound source positions is less than or equal to a preset distance threshold value; the nth sound source position is determined as the final sound source position.
The beneficial effects of the technical scheme are that: setting a second grid precision for the time-frequency domain of the sound signal, namely further subdividing the monitoring area in a time-frequency space, and positioning and analyzing the monitoring area with finer granularity; the method comprises the steps that in a preset range of a sound source position, a sensor collects time-frequency domain sound signals of signals; the purpose of this step is to acquire sound signals around the first sound source, providing a data basis for subsequent processing and analysis; determining a second sparse dictionary according to the weight of the maximum directional beam former, the second grid precision and the target time-frequency domain sound signal; the sparse dictionary is used for describing sparse representation of the sound signals in a time-frequency domain; by selecting proper dictionaries and weights, the characteristics of the sound signals can be better described, and the accuracy of sound source position estimation is improved; and calculating to obtain a second sound source in the preset range of the first sound source position based on the second sparse dictionary, the sparse Bayesian learning method and the expectation maximization method. The aim of this step is to further estimate the position of other sound sources in the target area by iterative computation, repeating the iterative operation: stopping iteration when the sum of Euclidean distances between the nth sound source position and the previous n-1 sound source positions is less than or equal to a preset distance threshold value; determining an additional sound source position by performing iterative operations and comparing the additional sound source position with the sound source position; the process can be used for preparing the iteration times and convergence accuracy by setting a preset distance threshold value; the nth sound source position is determined as the final sound source. Through iteration, all sound source positions are finally obtained, and comprehensive positioning is carried out by combining the previous sound source positions, so that the final sound source position is obtained; the accuracy and stability of sound source localization are further improved, and the discovery and localization capability of additional sound sources can be improved by setting grid precision with finer granularity, acquiring a target time-frequency domain signal and performing iterative operation.
Example 8
The sound sensor optimization scheme for determining the target sub-monitoring area according to the number of sound sources, the positions of the sound sources and the second sound intensity change of the collected second sound signals in the target sub-monitoring area comprises the following steps:
acquiring the area of a target sub-monitoring area;
acquiring Euclidean distance between sound sensors in a target sub-monitoring area and Euclidean distance between each sensor and the sound source position;
determining a sensor optimization index based on a preset optimization index algorithm;
sequentially reducing the number of the sensors in the preset range of the target sound source position, repeatedly calculating the sensor optimization indexes when the number of the sensors in the preset range of the target sound source position is reduced, and stopping iterative calculation until the number of the sensors in the preset range is 1, so as to obtain a plurality of sensor optimization indexes;
determining an optimal sensor scheme based on a plurality of sensor optimization indexes;
and determining a sound sensor optimization scheme of the target sub-monitoring area based on the optimal sensor scheme.
In this embodiment, the sensor optimization index is repeatedly calculated while reducing the number of sensors within the preset range of the target sound source position, for example: the target sound source position is provided with 5 sensors, when 1 sensor is taken out each time, according to the different positions of the sensors, 5 taking out modes are provided, and the corresponding 5 sensors optimize indexes; when 2 sensors are taken out each time, according to different sensor positions, 10 taking out modes exist, and 10 sensor optimization indexes are corresponding; and by analogy, after 4 sensors are taken out each time, 5 taking out modes exist, after 5 sensor optimization indexes are obtained through calculation, only 1 sensor is left at the moment, iteration is stopped, and an optimal allocation scheme is determined based on a plurality of sensor optimization indexes.
In this embodiment, the euclidean distance between the sensors and the euclidean distance between each sensor and the sound source position in the target sub-monitoring area are acquired, for example: assuming that the sensors in the target sub-detection area are A, B, C, D and the sound source position is S, the distance of AB, BC, AC, AD, BD, CD between the sensors in the target sub-detection area and the euclidean distance SA, SB, SC, SD between each sensor and the sound source position are acquired.
The beneficial effects of the technical scheme are that: the coverage range of the sensors to the target sub-monitoring area can be improved by reasonably optimizing the layout and the number of the sensors, so that the comprehensiveness and the accuracy of sound monitoring are improved; by optimizing the positions of the sensors, the interference among the sensors can be reduced, and the acquisition quality and accuracy of sound signals are improved; the Euclidean distance between the sensor and the sound source position is accurately calculated, so that the accuracy and stability of sound source positioning can be improved; the optimization scheme of the sound sensor can improve the sound monitoring and positioning effects and provide more accurate, comprehensive and reliable sound information.
Example 9
The preset optimization index algorithm comprises the following steps:
where Yh represents the sensor optimization index, min (D ij ) Representing the Euclidean distance between each sensor and the nearest sensor in the target sub-monitoring area; d (D) iz Representing the Euclidean distance from each sensor to the sound source position in the target sub-monitoring area; s is the area of the target sub-monitoring area; ΔS max Representing the maximum value of the change of the sound intensity received by the sensor in the target sub-monitoring area; ΔS min Representing the minimum value of the change of the intensity of the sound received by the sensor in the target sub-monitoring area; m is the number of sensors; e is a natural constant.
The beneficial effects of the technical scheme are as follows: by calculating the number of sensors around the sound source, the distance between the sensors, the sound intensity received by the sensors, the distance between the sensors and the sound source and other factors, the accuracy of the optimization index is increased, and a guarantee is provided for the follow-up optimization scheme.
Example 10
As shown in fig. 3, a sound sensor layout optimization system for equipment operation monitoring, comprising:
a determining module for determining a monitoring area of the device;
the distribution module is used for uniformly distributing the sound sensors in the monitoring area;
the sound intensity module is used for acquiring corresponding first sound signals based on each sound sensor when the equipment is in operation, processing the first sound signals of each sound sensor and determining first sound intensity change;
Dividing the monitoring area according to the first sound intensity change to obtain a plurality of sub-monitoring areas;
and the optimizing module is used for determining the target sound sensor optimizing schemes of all the sub-monitoring areas and determining the optimizing layout of the monitoring areas of the equipment according to the target sound sensor optimizing schemes of all the sub-monitoring areas.
The beneficial effects of the technical scheme are as follows: by uniformly distributing each sound sensor in the monitoring area, the comprehensiveness and accuracy of monitoring can be increased; each sensor can be responsible for monitoring the sound change of a specific area, so that the monitoring effect of the whole system is improved; by processing the first sound signal of each sound sensor, a change in sound intensity between the sensors can be determined; this can help to further optimize the layout to minimize overlap areas or dead zones, improving the effectiveness of the layout; dividing a monitoring area into a plurality of sub-monitoring areas according to the first sound intensity change; this division allows better differentiation between different sound sources for more accurate monitoring and identification of the operating state of the device; determining a sound sensor optimization scheme of the target based on the characteristics and requirements of each sub-monitoring area; this may include strategies such as sensor position adjustment, increasing or decreasing the number of sensors to maximize monitoring; and determining the overall optimized layout of the equipment monitoring area according to the target sound sensor optimization scheme of each sub-monitoring area. This ensures the consistency and consistency of the overall layout to achieve optimal monitoring; the sound sensor layout can be more reasonable and efficient, and the accuracy and reliability of equipment operation monitoring can be improved; this helps to discover the abnormal state of the device in time, prevent potential failure, and improve maintenance and management efficiency of the device.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. A method of optimizing a sound sensor layout for equipment operation monitoring, comprising:
determining a monitoring area of the device;
uniformly distributing each sound sensor in a monitoring area;
when the equipment is in operation, acquiring corresponding first sound signals based on each sound sensor, processing the first sound signals of each sound sensor, and determining first sound intensity changes;
dividing the monitoring area according to the first sound intensity change to obtain a plurality of sub-monitoring areas;
and determining the target sound sensor optimization schemes of all the sub-monitoring areas, and determining the optimized layout of the monitoring areas of the equipment according to the target sound sensor optimization schemes of all the sub-monitoring areas.
2. The sound sensor layout optimization method for equipment operation monitoring of claim 1, wherein the determining a target sound sensor optimization scheme for a sub-monitoring area comprises:
Selecting one sub-monitoring area at will as a target sub-monitoring area;
when the equipment operates, closing the sound sensors in other sub-monitoring areas except the target sub-monitoring area;
determining the number and the position of sound sources in the target sub-monitoring area according to the second sound signals acquired by the sound sensors in the target sub-monitoring area;
and determining a sound sensor optimization scheme of the target sub-monitoring area according to the number of sound sources in the target sub-monitoring area, the positions of the sound sources and the second sound intensity change of the collected second sound signals.
3. The method of optimizing a sound sensor layout for device operation monitoring of claim 1, wherein, while the device is in operation, the processing the first sound signals of each sound sensor based on the respective first sound signals acquired by each sound sensor to determine a first sound intensity variation comprises:
analyzing and processing according to the first sound signals of each sound sensor, and determining a matrix of sound intensity as follows:
wherein S is m Is strong in soundA matrix of degrees;representing the sound intensity of the ith sensor when the nth sound source in the monitoring area sounds in j grades; sound intensity level from 0 to l;
Determining a first sound intensity variation from a matrix of sound intensities:
wherein Δs is a first sound intensity variation matrix;representing a preset sound intensity of a z-th sound sensor in the monitoring area; />
4. The method for optimizing a layout of a sound sensor for monitoring operation of a device of claim 1, wherein dividing the monitored area according to the first sound intensity variation to obtain a plurality of sub-monitored areas comprises:
determining a sound intensity mutation value of the monitoring area according to the first sound intensity change;
and dividing the monitoring area by taking the sound source corresponding to the sound intensity mutation value as a center and taking the preset distance as a radius to obtain a plurality of sub-monitoring areas.
5. The method for optimizing sound sensor placement for equipment operation monitoring of claim 2, wherein determining the number of sound sources and the sound source location of the target sub-monitoring area based on the second sound signals collected by the sound sensors in the target sub-monitoring area comprises:
performing short-time Fourier transform processing on the second sound signals collected by the sound sensors in the target sub-monitoring area to obtain time-frequency domain sound signals of the signals collected by the sensors;
Setting first grid precision for the time-frequency domain sound signals, and constructing a first sparse dictionary based on a maximum directional beam former;
in the first sparse dictionary, a sparse Bayes learning method and a expectation maximization method are used for calculating to obtain a first sound source position of a target sub-monitoring area;
the number of sound sources is determined based on the first sound source position.
6. The method for optimizing a layout of a sound sensor for monitoring operation of a device according to claim 5, wherein the calculating a first sound source position of a target sub-monitoring area by using a sparse bayesian learning method and a expectation maximization method comprises:
presetting a first parameter in a sparse Bayes learning method;
based on a first parameter of sparse Bayesian learning, calculating to obtain a first average value and a first variance of a sparse matrix;
determining a second parameter based on the expectation maximization method, the first average value of the sparse matrix and the first variance;
based on a second parameter of sparse Bayesian learning, calculating to obtain a second average value and a second variance of the sparse matrix;
an iterative operation, wherein when the P-th variance is less than or equal to a preset variance threshold, the iterative operation is stopped; the highest peak of the energy spectrum of the P-th average is determined as grouping a number of first sound source positions.
7. The method for optimizing a layout of a sound sensor for monitoring operation of a device according to claim 5, further comprising, after the calculating the first sound source position of the target sub-monitoring area by using a sparse bayesian learning method and a expectation maximization method:
setting a second grid precision for the time-frequency domain sound signal;
acquiring a time-frequency domain sound signal of a signal acquired by a sensor in a preset range of any one first sound source position to obtain a target time-frequency domain sound signal;
determining a second sparse dictionary according to the weight of the maximum directional beam former and the second grid precision time-domain sound signals of the target; calculating a second sound source position in a preset range of the first sound source position based on a second sparse dictionary, a sparse Bayes learning method and a expectation maximization method;
repeating the iteration operation, and stopping iteration when the sum of the Euclidean distance between the nth sound source position and the previous n-1 sound source positions is less than or equal to a preset distance threshold value; the nth sound source position is determined as the final sound source position.
8. The method for optimizing a sound sensor layout for monitoring operation of a device according to claim 2, wherein the determining the sound sensor optimization scheme for the target sub-monitoring area according to the number of sound sources in the target sub-monitoring area, the positions of the sound sources, and the second sound intensity variation of the collected second sound signal comprises:
Acquiring the area of a target sub-monitoring area;
acquiring Euclidean distance between sound sensors in a target sub-monitoring area and Euclidean distance between each sensor and the sound source position;
determining a sensor optimization index based on a preset optimization index algorithm;
sequentially reducing the number of the sensors in the preset range of the target sound source position, repeatedly calculating the sensor optimization indexes when the number of the sensors in the preset range of the target sound source position is reduced, and stopping iterative calculation until the number of the sensors in the preset range is 1, so as to obtain a plurality of sensor optimization indexes;
determining an optimal sensor scheme based on a plurality of sensor optimization indexes;
and determining a sound sensor optimization scheme of the target sub-monitoring area based on the optimal sensor scheme.
9. The sound sensor layout optimization method for equipment operation monitoring of claim 8, wherein the preset optimization index algorithm comprises:
where Yh represents the sensor optimization index, min (D ij ) Representing the Euclidean distance between each sensor and the nearest sensor in the target sub-monitoring area; d (D) iz Representing the Euclidean distance from each sensor to the sound source position in the target sub-monitoring area; s is the area of the target sub-monitoring area; ΔS max Representing the maximum value of the change of the sound intensity received by the sensor in the target sub-monitoring area; ΔS min Representing the minimum value of the change of the intensity of the sound received by the sensor in the target sub-monitoring area; m is the number of sensors; e is a natural constant.
10. A sound sensor layout optimization system for equipment operation monitoring, comprising:
a determining module for determining a monitoring area of the device;
the distribution module is used for uniformly distributing the sound sensors in the monitoring area;
the sound intensity module is used for acquiring corresponding first sound signals based on each sound sensor when the equipment is in operation, processing the first sound signals of each sound sensor and determining first sound intensity change;
dividing the monitoring area according to the first sound intensity change to obtain a plurality of sub-monitoring areas;
the optimizing module is used for determining a sound sensor optimizing scheme of the target sub-monitoring area; and determining the optimized layout of the monitoring area of the equipment according to the target sound sensor optimization schemes of the sub-monitoring areas.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410035307.9A CN117875053B (en) | 2024-01-09 | 2024-01-09 | Sound sensor layout optimization method and system for equipment operation monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410035307.9A CN117875053B (en) | 2024-01-09 | 2024-01-09 | Sound sensor layout optimization method and system for equipment operation monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117875053A true CN117875053A (en) | 2024-04-12 |
| CN117875053B CN117875053B (en) | 2024-06-18 |
Family
ID=90576922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410035307.9A Active CN117875053B (en) | 2024-01-09 | 2024-01-09 | Sound sensor layout optimization method and system for equipment operation monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117875053B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105517147A (en) * | 2015-12-02 | 2016-04-20 | 浙江大学 | Block iteration based distributed target positioning method |
| CN106658920A (en) * | 2017-01-10 | 2017-05-10 | 齐鲁工业大学 | Intelligent control illumination method and device |
| CN107064872A (en) * | 2017-02-14 | 2017-08-18 | 天津大学 | A kind of passive type indoor orientation method and system based on intensity variation |
| CN107870204A (en) * | 2016-09-22 | 2018-04-03 | 淮阴师范学院 | A kind of high composite structure damage monitoring method of accuracy |
| CN110991821A (en) * | 2019-11-15 | 2020-04-10 | 国网安徽省电力有限公司黄山市黄山区供电公司 | Substation live operation and inspection auxiliary analysis method |
| CN111339651A (en) * | 2020-02-22 | 2020-06-26 | 西北工业大学 | Secondary sound source layout optimization method for decoupling error sensor layout information |
| WO2022247202A1 (en) * | 2021-05-24 | 2022-12-01 | 清华大学 | Sound source identification method and system based on array measurement and sparse prior information |
| CN117172135A (en) * | 2023-11-02 | 2023-12-05 | 山东省科霖检测有限公司 | Intelligent noise monitoring management method and system |
-
2024
- 2024-01-09 CN CN202410035307.9A patent/CN117875053B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105517147A (en) * | 2015-12-02 | 2016-04-20 | 浙江大学 | Block iteration based distributed target positioning method |
| CN107870204A (en) * | 2016-09-22 | 2018-04-03 | 淮阴师范学院 | A kind of high composite structure damage monitoring method of accuracy |
| CN106658920A (en) * | 2017-01-10 | 2017-05-10 | 齐鲁工业大学 | Intelligent control illumination method and device |
| CN107064872A (en) * | 2017-02-14 | 2017-08-18 | 天津大学 | A kind of passive type indoor orientation method and system based on intensity variation |
| CN110991821A (en) * | 2019-11-15 | 2020-04-10 | 国网安徽省电力有限公司黄山市黄山区供电公司 | Substation live operation and inspection auxiliary analysis method |
| CN111339651A (en) * | 2020-02-22 | 2020-06-26 | 西北工业大学 | Secondary sound source layout optimization method for decoupling error sensor layout information |
| WO2022247202A1 (en) * | 2021-05-24 | 2022-12-01 | 清华大学 | Sound source identification method and system based on array measurement and sparse prior information |
| CN117172135A (en) * | 2023-11-02 | 2023-12-05 | 山东省科霖检测有限公司 | Intelligent noise monitoring management method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117875053B (en) | 2024-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Qu et al. | Multi-step wind speed forecasting based on a hybrid decomposition technique and an improved back-propagation neural network | |
| Raymond et al. | Partial discharge classifications: Review of recent progress | |
| Buhan et al. | Wind pattern recognition and reference wind mast data correlations with NWP for improved wind-electric power forecasts | |
| Jia et al. | An optimized classification algorithm by BP neural network based on PLS and HCA | |
| Deng et al. | Modified kernel principal component analysis using double-weighted local outlier factor and its application to nonlinear process monitoring | |
| CN113255848B (en) | Water turbine cavitation sound signal identification method based on big data learning | |
| CN116380445B (en) | Equipment state diagnosis method and related device based on vibration waveform | |
| CN106933778A (en) | A kind of wind power combination forecasting method based on climbing affair character identification | |
| Wu et al. | A hybrid support vector regression approach for rainfall forecasting using particle swarm optimization and projection pursuit technology | |
| CN109145516B (en) | Analog circuit fault identification method based on improved extreme learning machine | |
| CN117458955A (en) | Operation control method and system of motor | |
| CN111447217A (en) | Method and system for detecting flow data abnormity based on HTM under sparse coding | |
| CN114964778A (en) | Bearing fault diagnosis method based on wavelet time-frequency graph and deep learning | |
| CN115600088A (en) | Distribution transformer fault diagnosis method based on vibration signals | |
| CN114812796A (en) | Equipment condition evaluation method and related equipment | |
| CN112014790A (en) | Near-field source positioning method based on factor analysis | |
| CN114372344B (en) | Quantitative identification method for subsynchronous oscillation damping characteristic influence factors | |
| Gao et al. | Underdetermined blind source separation method based on quantum Archimedes optimization algorithm | |
| CN117875053B (en) | Sound sensor layout optimization method and system for equipment operation monitoring | |
| CN117435969A (en) | Switch cabinet health state assessment method, device, equipment and storage medium | |
| Wang et al. | Hybrid learning based Gaussian ARTMAP network for tool condition monitoring using selected force harmonic features | |
| CN103020452A (en) | Method for judging threat level of radar radiation source | |
| Jiang et al. | Recurrence plot quantitative analysis-based fault recognition method of rolling bearing | |
| Shenbagalakshmi et al. | A Study on Monitoring an Air Conditioning (AC) system in a Home environment using Machine Learning Techniques | |
| CN117829822B (en) | Power transformer fault early warning method and system |
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 |