Noise traceability analysis system and method based on double-sensor rotation measurement

Abstract

The application relates to the technical field of missing data recovery, and provides a noise tracing analysis system and method based on double-sensor rotation measurement, which comprises a data acquisition module, an energy matrix corresponding to each rotation period is acquired, the energy matrix comprises energy data corresponding to each preset direction in the rotation period; a data calculation module is used for acquiring missing data in the energy matrix, and the missing data is calculated according to adjacent matrices of the energy matrix, so that a target matrix after recovery of the missing data is obtained; and an output drawing module is used for drawing and outputting corresponding prediction results according to energy data in the target matrix. Since the missing data is recovered through the data calculation module, the integrity of the energy matrix is avoided from being affected by data vacancy, and the robustness of the system is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of missing data recovery, in particular to a noise tracing analysis system and method based on double-sensor rotation measurement. BACKGROUND

[0002] With the improvement of people's living standards, the prediction and analysis of noise are paid more and more attention. For example, by predicting the noise in each direction, the noise can be traced. However, this method has high requirements for sensor accuracy. Once the data of the sensor drifts or is missing, it will affect the accuracy of noise tracing analysis. The requirement for sensor accuracy results in high hardware cost of noise tracing analysis. How to predict the missing data and improve the robustness of noise tracing analysis has become a problem to be solved. SUMMARY

[0003] The main purpose of the present application is to provide a noise tracing analysis system and method based on double-sensor rotation measurement, which aims to recover the missing data and improve the robustness of noise tracing.

[0004] In a first aspect, the present application provides a noise tracing analysis system based on double-sensor rotation measurement, which comprises:

[0005] A data acquisition module is configured to acquire an energy matrix corresponding to each rotation period, wherein the energy matrix comprises energy data corresponding to each preset direction within the rotation period.

[0006] A data calculation module is configured to acquire missing data in the energy matrix, and calculate the missing data according to adjacent matrices of the energy matrix, so as to obtain a target matrix after recovery of the missing data.

[0007] An output drawing module is configured to draw and output a corresponding prediction result according to the energy data in the target matrix.

[0008] In some embodiments, the data acquisition module comprises a first sensor, a second sensor and a rotating component, the rotating component has a geometric center as a rotation center, the first sensor and the second sensor are installed at different positions of the rotating component, and a first position where the first sensor is located and a second position where the second sensor is located are centrally symmetrically distributed about the geometric center. The data acquisition module is configured to detect energy data corresponding to each preset direction within each rotation period during rotation of the rotating component driving the first sensor and the second sensor, and obtain an energy matrix corresponding to each rotation period.

[0009] In some embodiments, the data acquisition module is further configured to: detect energy data corresponding to each preset direction in each rotation cycle during the process in which the rotating component drives the first sensor and the second sensor to rotate, and obtain an energy matrix corresponding to each rotation cycle;

[0010] During the rotation period, acquiring first noise energy data detected by the first sensor, second noise energy data detected by the second sensor at the same time, and position data detected by the position sensor at the same time;

[0011] determining, according to the position data, a first direction corresponding to the first noise energy data and a second direction corresponding to the second noise energy data;

[0012] Filling the first noise energy data into a first position corresponding to the first direction in the energy matrix, and filling the second noise energy data into a second position corresponding to the second direction in the energy matrix;

[0013] The rotation period is the duration of half a rotation of the first sensor or the second sensor.

[0014] In some embodiments, the data calculation module is used to obtain missing data in the energy matrix and calculate the missing data according to the adjacent matrix of the energy matrix to obtain the target matrix after the missing data is restored, and is also used to:

[0015] Obtaining adjacent matrices of the first n frames and adjacent matrices of the next n frames adjacent to the energy matrix, performing pattern recognition on the adjacent matrices to obtain a noise energy distribution pattern;

[0016] The missing data is restored according to the noise energy distribution pattern to obtain a target matrix after the missing data is restored.

[0017] In some embodiments, obtaining adjacent matrices of the first n frames and adjacent matrices of the next n frames adjacent to the energy matrix, and performing pattern recognition on the adjacent matrices to obtain a noise energy distribution pattern includes:

[0018] Eliminating the items at the positions corresponding to the missing data from the adjacent matrix to obtain a first adjacent matrix, and eliminating the missing data from the energy matrix to obtain a first energy matrix;

[0019] Calculating a similarity between the first adjacent matrix and the first energy matrix, and determining the first adjacent matrix having the similarity greater than a preset similarity as a second adjacent matrix;

[0020] Performing pattern recognition on the second adjacent matrix to obtain the noise energy distribution pattern.

[0021] In some embodiments, performing pattern recognition on the second adjacent matrix to obtain the noise energy distribution pattern includes:

[0022] performing pattern recognition on the second adjacent matrices to obtain energy distribution information corresponding to each second adjacent matrix;

[0023] Determining a weight corresponding to each piece of energy distribution information according to the similarity of each of the second adjacent matrices;

[0024] The energy distribution information is fused according to the weight to obtain the noise energy distribution pattern.

[0025] In some embodiments, the noise source tracing and analysis system based on dual-sensor rotation measurement further includes:

[0026] The abnormality prompt module is used to determine the missing value frequency according to the distribution of the missing data in each energy matrix, and output an abnormality prompt when the missing value frequency is greater than a preset frequency.

[0027] In some embodiments, determining the missing value frequency based on the distribution of the missing data in each of the energy matrices, and outputting an abnormal prompt when the missing value frequency is greater than a preset frequency, includes:

[0028] Calculating a first occurrence frequency of a first missing value of the first sensor within a preset time period, and a second occurrence frequency of a second missing value of the second sensor within a preset time period;

[0029] When the first occurrence frequency within M consecutive preset time periods is greater than N, it is determined that the first missing value frequency is greater than the above-mentioned preset frequency, and an abnormal output prompt is given for the first sensor; and / or,

[0030] When the second occurrence frequency within M consecutive preset time lengths is greater than N, it is determined that the second missing value frequency is greater than the above-mentioned preset frequency, and an abnormal output prompt is given for the second sensor.

[0031] In some embodiments, calculating the similarity between the first adjacency matrix and the first energy matrix includes:

[0032] Acquire a first frequency parameter during the first adjacent matrix measurement period and a second frequency parameter during the first energy matrix measurement period;

[0033] Performing feature extraction on the first frequency parameter to obtain a first frequency feature, and performing feature extraction on the second frequency parameter to obtain a second frequency feature;

[0034] Calculating feature similarity between the first frequency feature and the second frequency feature, and matrix similarity between the first adjacency matrix and the first energy matrix;

[0035] The similarity between the first adjacent matrix and the first energy matrix is ​​determined according to the feature similarity and the matrix similarity.

[0036] In a second aspect, the present application further provides a noise source tracing and analysis method based on dual-sensor rotation measurement, the method comprising:

[0037] Obtaining an energy matrix corresponding to each rotation period, wherein the energy matrix includes energy data corresponding to each preset direction within the rotation period;

[0038] Obtaining missing data in the energy matrix, and calculating the missing data according to an adjacent matrix of the energy matrix to obtain a target matrix after the missing data is restored;

[0039] The corresponding prediction results are drawn and output according to the energy data in the target matrix.

[0040] This application provides a noise source tracing and analysis system and method based on dual-sensor rotation measurement. This application utilizes a data acquisition module to obtain an energy matrix corresponding to each rotation cycle. The energy matrix includes energy data corresponding to each preset direction within the rotation cycle. A data calculation module is used to obtain missing data in the energy matrix and calculate the missing data based on adjacent matrices of the energy matrix to obtain a target matrix after the missing data has been recovered. An output drawing module is used to draw and output the corresponding prediction results based on the energy data in the target matrix. Because the data calculation module recovers missing data, data gaps are prevented from affecting the integrity of the energy matrix, improving the robustness of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0042] Figure 1 A schematic block diagram of a noise source tracing and analysis system based on dual-sensor rotation measurement provided in one embodiment of the present application;

[0043] Figure 2 A schematic flow chart of a noise source tracing and analysis method based on dual-sensor rotation measurement provided in one embodiment of the present application;

[0044] Figure 3 Fig. 1 is a structural schematic block diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0046] The flowchart shown in the drawings is only an example and does not necessarily include all the contents and operations / steps, nor does it necessarily be executed in the described order. For example, some operations / steps can be further decomposed, combined or partially merged, so that the actual execution order can be changed according to the actual situation.

[0047] The embodiments of the present application provide a noise traceability analysis system and method based on double-sensor rotation measurement.

[0048] Some embodiments of the present application will be described in detail below with reference to the drawings. The following embodiments and features in the embodiments can be combined with each other without conflict.

[0049] Please refer to Figure 1 , Figure 1 Fig. 1 is a structural schematic block diagram of a noise traceability analysis system based on double-sensor rotation measurement according to an embodiment of the present application. The system can be configured in a terminal or a server. The terminal can be an electronic device such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant and a wearable device. The server can be a stand-alone server, a server cluster, a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0050] As shown in Figure 1 , the noise traceability analysis system based on double-sensor rotation measurement includes a data acquisition module 110, a data calculation module 120 and an output drawing module 130.

[0051] The data acquisition module 110 is configured to acquire an energy matrix corresponding to each rotation period, wherein the energy matrix includes energy data corresponding to each preset direction within the rotation period.

[0052] A data calculation module 120 is configured to obtain missing data in the energy matrix and calculate the missing data according to an adjacent matrix of the energy matrix to obtain a target matrix after the missing data is restored;

[0053] The output drawing module 130 is used to draw and output the corresponding prediction result according to the energy data in the target matrix.

[0054] Exemplarily, the energy matrix is ​​a noise energy matrix, the energy data is noise energy data, and the noise energy data may be acquired through a noise energy sensor.

[0055] Exemplarily, the prediction result can be a rose diagram obtained by detecting the noise energy in various directions. The noise source tracing and analysis system based on dual-sensor rotation measurement provided in the embodiment of the present application can draw the noise energy data of each preset direction in each rotation cycle into a rose diagram, intuitively displaying the noise intensity in various directions on the circumference, so that the user has a clear understanding of the noise size in various directions.

[0056] In related technologies, various reasons may cause sensors to fail to acquire data at certain points in time, resulting in data gaps and, consequently, missing data in the noise energy matrix corresponding to some rotation periods. To avoid this, the noise source tracing and analysis system based on dual-sensor rotation measurement provided in the present application recovers the missing data through a data calculation module, thereby preventing data gaps from affecting the integrity of the energy matrix and improving the robustness of the system.

[0057] In some embodiments, the data acquisition module includes a first sensor, a second sensor, and a rotating component, the rotating component uses a geometric center as a rotation center, the first sensor and the second sensor are installed at different positions of the rotating component, and the first position where the first sensor is located and the second position where the second sensor is located are centrally symmetrically distributed about the geometric center. The data acquisition module is used to detect the energy data corresponding to each preset direction in each rotation cycle in the process of the rotating component driving the first sensor and the second sensor to rotate, and obtain the energy matrix corresponding to each rotation cycle.

[0058] Illustratively, in the noise source tracing and analysis system based on dual-sensor rotation measurement provided by an embodiment of the present application, a first sensor and a second sensor are used to simulate a person's ears. The ears can determine the direction of the sound source by the time difference and intensity difference of the sound. The first sensor and the second sensor can also trace the source of the noise based on the intensity difference and time difference of the detected noise. Specifically, when the sound source is on one side, the sound will first reach the sensor close to the sound source, and then reach the sensor on the other side. There will be a time difference in the sounds detected by the two sensors. The sound will attenuate as the distance increases during propagation. When the sound source is close to one side, the sound intensity received by the sensor close to the sound source will be higher than that of the sensor on the other side. There will be an intensity difference in the sounds detected by the two sensors.

[0059] Exemplarily, the first and second sensors may be acoustic energy sensors (AENS), devices that convert acoustic signals into electrical signals and are used to measure the magnitude and distribution of acoustic energy. The first and second sensors are positioned at different locations on a rotating component to simulate ears located on either side of the head. The rotating component drives the first and second sensors to rotate, allowing them to detect noise energy in various directions around the system during one rotation. For example, they detect noise energy in eight directions: east, south, west, north, southeast, southwest, northwest, and northeast, obtaining energy data for each preset direction.

[0060] Exemplarily, the rotating component rotates one circle, and the energy data in eight directions around the system within the rotation period are detected respectively to obtain the energy matrix corresponding to the rotation period. The acoustic energy matrix contains the energy data in eight directions around the system within the rotation period.

[0061] Exemplarily, the rotating component can be circular, such as a disk or a ring, and the rotating component rotates around the center of the circle. The first position of the first sensor and the second position of the second sensor are symmetrical about the center of the circle, so that the first sensor and the second sensor are located on opposite sides of the center of the circle and are equidistant from the center of the circle, thereby better simulating the distribution of the human ear.

[0062] Exemplarily, a sound insulation component may be provided between the first sensor and the second sensor in the rotating component to simulate the sound blocking effect of a human head and increase the sound intensity difference between the first sensor and the second sensor.

[0063] In some embodiments, the data acquisition module is further configured to: detect energy data corresponding to each preset direction in each rotation cycle during the process in which the rotating component drives the first sensor and the second sensor to rotate, and obtain an energy matrix corresponding to each rotation cycle;

[0064] During the rotation period, acquiring first noise energy data detected by the first sensor, second noise energy data detected by the second sensor at the same time, and position data detected by the position sensor at the same time;

[0065] determining, according to the position data, a first direction corresponding to the first noise energy data and a second direction corresponding to the second noise energy data;

[0066] Filling the first noise energy data into a first position corresponding to the first direction in the noise energy matrix, and filling the second noise energy data into a second position corresponding to the second direction in the noise energy matrix;

[0067] The rotation period is the duration of half a rotation of the first sensor or the second sensor.

[0068] For example, since the energy data is detected simultaneously by the first sensor and the second sensor, noise energy data in two opposite directions can be detected at one moment, and the data in each direction around can be detected every half rotation of the rotating component. Therefore, the time it takes for the rotating component to rotate half a circle is taken as the rotation period.

[0069] For example, in order to determine the direction of the noise energy data detected by the sensor, it is necessary to obtain the position data of the sensor at the same time as obtaining the noise energy data. The position data can be obtained through an encoder or a gyroscope, and is used to indicate the orientation of the first sensor and the second sensor relative to the geometric center of the rotating component, thereby determining the direction corresponding to the noise energy data based on the position data. The direction can be, for example, east, south, west, north, southeast, southwest, northwest, and northeast.

[0070] Exemplarily, the positions of the first noise energy data and the second noise energy data in the noise energy matrix are determined according to the first direction and the second direction. For example, the directions corresponding to each item in the noise energy matrix are as follows:

[0071]

[0072] For example, if the first direction corresponding to the first noise energy data is northwest, the first noise data is filled into the position corresponding to the northwest item in the above matrix, which will not be described in detail here.

[0073] For example, since there is no noise energy data in the center, a default value such as -1 is used as a placeholder. For example, the data corresponding to the northwest, north, northeast, and east in the above matrix are the first noise energy data detected by the first sensor, and the data corresponding to the southeast, south, southwest, and west in the opposite directions are the second noise energy data detected by the second sensor.

[0074] In some embodiments, the data calculation module is configured to acquire missing data in the energy matrix, and calculate the missing data according to adjacent matrices of the energy matrix to obtain a target matrix after the missing data is recovered, and is further configured to:

[0075] acquire n frames of adjacent matrices before and after the energy matrix, and perform pattern recognition on the adjacent matrices to obtain a noise energy distribution pattern;

[0076] recover the missing data according to the noise energy distribution pattern to obtain the target matrix after the missing data is recovered.

[0077] It can be understood that the distribution of noise energy data in the energy matrix has a similar pattern with n frames of noise energy matrices before and after the energy matrix, and therefore, the missing data in the noise energy matrix can be recovered according to the n frames of adjacent matrices before and after the energy matrix. The missing data in the noise energy matrix can be occupied by 0.

[0078] For example, the pattern recognition is performed on the adjacent matrices to obtain a noise energy distribution pattern of the adjacent matrices, and the noise energy distribution pattern is applied to the energy matrix to recover the missing data in the energy matrix.

[0079] For example, the pattern recognition of the adjacent matrices can determine the mutual relationship between each item in the adjacent matrices, such as that the sound in a certain direction is always small, or that there is a specific relationship between the sound size in a certain direction and the sound size in the surrounding directions, which is equivalent to training a prediction model by taking the adjacent matrices as samples, taking the non-missing data in the energy matrix as the input of the model, and predicting the missing data in the energy matrix by the model.

[0080] For example, the pattern recognition of the adjacent matrices can be implemented based on a Bayesian classifier, a support vector machine, and the like, which will not be described herein.

[0081] In some embodiments, the acquiring n frames of adjacent matrices before and after the energy matrix, and performing pattern recognition on the adjacent matrices to obtain a noise energy distribution pattern, comprises:

[0082] eliminating items at positions corresponding to the missing data from the adjacent matrices to obtain a first adjacent matrix, and eliminating the missing data from the energy matrix to obtain a first energy matrix;

[0083] calculating a similarity between the first adjacent matrix and the first energy matrix, and determining a first adjacent matrix with a similarity greater than a preset similarity as a second adjacent matrix;

[0084] performing pattern recognition on the second adjacent matrix to obtain the noise energy distribution pattern.

[0085] For example, in order to avoid the interference of some burst noise in the adjacent matrix, the similarity between the adjacent matrix and the energy matrix needs to be calculated. Since there is missing data in the energy matrix, the items corresponding to the missing data in the adjacent matrix are also removed to obtain the first adjacent matrix, which is convenient for calculating the similarity with the first energy matrix from which the missing data is removed.

[0086] For example, the similarity between the first adjacent matrix and the first energy matrix can be cosine similarity, but is not limited thereto. In the case where the similarity between the first adjacent matrix and the first energy matrix is greater than a preset similarity, the first adjacent matrix is taken as the second adjacent matrix for predicting the missing data.

[0087] In some embodiments, the performing pattern recognition on the second adjacent matrix to obtain the noise energy distribution pattern comprises:

[0088] performing pattern recognition on the second adjacent matrix to obtain energy distribution information corresponding to each second adjacent matrix;

[0089] determining a weight corresponding to each energy distribution information according to the similarity of each second adjacent matrix;

[0090] fusing each energy distribution information according to the weight to obtain the noise energy distribution pattern.

[0091] For example, in order to improve the accuracy of the noise energy distribution pattern, different weights can be assigned to second adjacent matrices with different similarities, and the higher the similarity of the second adjacent matrix, the higher the weight of the second adjacent matrix in the noise energy distribution pattern. Specifically, pattern recognition can be performed on each second adjacent matrix to obtain energy distribution information corresponding to each second adjacent matrix, and then the energy distribution information is fused into a noise energy distribution pattern according to the weight of each second adjacent matrix, for example, weighted average or weighted fusion of the energy distribution information.

[0092] In some embodiments, the noise source analysis system based on double-sensor rotation measurement further comprises:

[0093] an abnormality prompting module configured to determine a missing value frequency according to the distribution of the missing data in each energy matrix, and output an abnormality prompt in the case where the missing value frequency is greater than a preset frequency.

[0094] For example, if the missing values ​​of a sensor occur frequently, it means that the sensor may be abnormal or even damaged. At this time, it is necessary to output an abnormal prompt, such as a flashing fault indicator light, to prompt the user to maintain the sensor, thereby avoiding long-term operation of the system in a faulty state and improving the perceptibility of the fault.

[0095] In some embodiments, determining the missing value frequency based on the distribution of the missing data in each of the energy matrices, and outputting an abnormal prompt when the missing value frequency is greater than a preset frequency, includes:

[0096] Calculating a first occurrence frequency of a first missing value of the first sensor within a preset time period, and a second occurrence frequency of a second missing value of the second sensor within a preset time period;

[0097] When the first occurrence frequency within M consecutive preset time periods is greater than N, it is determined that the first missing value frequency is greater than the above-mentioned preset frequency, and an abnormal output prompt is given for the first sensor; and / or,

[0098] When the second occurrence frequency within M consecutive preset time lengths is greater than N, it is determined that the second missing value frequency is greater than the above-mentioned preset frequency, and an abnormal output prompt is given for the second sensor.

[0099] For example, the frequency of occurrence of missing values ​​is calculated for the first sensor and the second sensor respectively, so that abnormal prompts are output for the first sensor and the second sensor respectively. When one of the sensors fails, the user can only repair or replace the failed sensor, thereby reducing the coupling and maintenance costs of the system and increasing the service life of the system.

[0100] In some embodiments, calculating the similarity between the first adjacency matrix and the first energy matrix includes:

[0101] Acquire a first frequency parameter during the first adjacent matrix measurement period and a second frequency parameter during the first energy matrix measurement period;

[0102] Performing feature extraction on the first frequency parameter to obtain a first frequency feature, and performing feature extraction on the second frequency parameter to obtain a second frequency feature;

[0103] Calculating feature similarity between the first frequency feature and the second frequency feature, and matrix similarity between the first adjacency matrix and the first energy matrix;

[0104] The similarity between the first adjacent matrix and the first energy matrix is ​​determined according to the feature similarity and the matrix similarity.

[0105] For example, the propagation characteristics of noise are closely related to its frequency. Noise of different frequencies exhibits different attenuation and reflection characteristics during propagation, as well as different impacts on the environment and human perception. For example, high-frequency noise exhibits rapid attenuation, significant reflection, and weak diffraction, while low-frequency noise exhibits slow attenuation, weak reflection, and strong diffraction.

[0106] Exemplarily, adjacent matrices with similar frequency characteristics are preferentially selected as the basis for predicting missing values. The feature similarity between the first frequency feature and the second frequency feature can be calculated, and then the feature similarity is combined with the matrix similarity to determine the similarity between the first adjacent matrix and the target noise matrix. For example, the average value of the feature similarity and the matrix similarity is used as the similarity.

[0107] Exemplarily, the feature similarity may be the cosine similarity between the first frequency feature and the second frequency feature, but is certainly not limited thereto and is not limited here.

[0108] The noise source tracing and analysis system based on dual-sensor rotation measurement provided in the above embodiment uses a data acquisition module to obtain the energy matrix corresponding to each rotation cycle. The energy matrix includes energy data corresponding to each preset direction within the rotation cycle. A data calculation module is used to obtain missing data in the energy matrix and calculate the missing data based on the adjacent matrix of the energy matrix to obtain a target matrix after the missing data is recovered. An output drawing module is used to draw and output the corresponding prediction results based on the energy data in the target matrix. Since the data calculation module recovers the missing data, the integrity of the energy matrix is ​​prevented from being affected by data gaps, thereby improving the robustness of the system.

[0109] See also Figure 2 , Figure 2 A flow chart of a noise source tracing and analysis method based on dual-sensor rotation measurement provided in one embodiment of the present application is provided. The method can be used in a server or a terminal and is implemented by the aforementioned noise source tracing and analysis system based on dual-sensor rotation measurement.

[0110] like Figure 2 As shown, the noise source tracing and analysis method based on dual-sensor rotation measurement includes steps S101 to S103.

[0111] Step S101: Acquire an energy matrix corresponding to each rotation period, wherein the energy matrix includes energy data corresponding to each preset direction within the rotation period;

[0112] Step S102: Obtain missing data in the energy matrix, and calculate the missing data according to the adjacent matrix of the energy matrix to obtain a target matrix after the missing data is restored;

[0113] Step S103: Draw and output corresponding prediction results according to the energy data in the target matrix.

[0114] In some embodiments, the data acquisition module includes a first sensor, a second sensor, and a rotating component, wherein the rotating component uses a geometric center as a rotation center, the first sensor and the second sensor are installed at different positions of the rotating component, and the first position where the first sensor is located and the second position where the second sensor is located are centrally symmetrically distributed about the geometric center. The data acquisition module is used to detect energy data corresponding to each preset direction in each rotation cycle during the process of the rotating component driving the first sensor and the second sensor to rotate, and obtain an energy matrix corresponding to each rotation cycle.

[0115] In some embodiments, during the process of the rotating component driving the first sensor and the second sensor to rotate, detecting energy data corresponding to each preset direction in each rotation cycle to obtain an energy matrix corresponding to each rotation cycle includes:

[0116] During the rotation period, acquiring first noise energy data detected by the first sensor, second noise energy data detected by the second sensor at the same time, and position data detected by the position sensor at the same time;

[0117] determining, according to the position data, a first direction corresponding to the first noise energy data and a second direction corresponding to the second noise energy data;

[0118] Filling the first noise energy data into a first position corresponding to the first direction in the energy matrix, and filling the second noise energy data into a second position corresponding to the second direction in the energy matrix;

[0119] The rotation period is the duration of half a rotation of the first sensor or the second sensor.

[0120] In some embodiments, obtaining missing data in the energy matrix and calculating the missing data according to an adjacent matrix of the energy matrix to obtain a target matrix after the missing data is restored includes:

[0121] Obtaining adjacent matrices of the first n frames and adjacent matrices of the next n frames adjacent to the energy matrix, performing pattern recognition on the adjacent matrices to obtain a noise energy distribution pattern;

[0122] The missing data is restored according to the noise energy distribution pattern to obtain a target matrix after the missing data is restored.

[0123] In some embodiments, obtaining adjacent matrices of the first n frames and adjacent matrices of the next n frames adjacent to the energy matrix, and performing pattern recognition on the adjacent matrices to obtain a noise energy distribution pattern includes:

[0124] Eliminating the items at the positions corresponding to the missing data from the adjacent matrix to obtain a first adjacent matrix, and eliminating the missing data from the energy matrix to obtain a first energy matrix;

[0125] Calculating a similarity between the first adjacent matrix and the first energy matrix, and determining the first adjacent matrix having the similarity greater than a preset similarity as a second adjacent matrix;

[0126] Performing pattern recognition on the second adjacent matrix to obtain the noise energy distribution pattern.

[0127] In some embodiments, performing pattern recognition on the second adjacent matrix to obtain the noise energy distribution pattern includes:

[0128] performing pattern recognition on the second adjacent matrices to obtain energy distribution information corresponding to each second adjacent matrix;

[0129] Determining a weight corresponding to each piece of energy distribution information according to the similarity of each of the second adjacent matrices;

[0130] The energy distribution information is fused according to the weight to obtain the noise energy distribution pattern.

[0131] In some embodiments, the noise source tracing and analysis method based on dual-sensor rotation measurement further includes:

[0132] The missing value frequency is determined according to the distribution of the missing data in each of the energy matrices, and an abnormal prompt is output when the missing value frequency is greater than a preset frequency.

[0133] In some embodiments, determining the missing value frequency based on the distribution of the missing data in each of the energy matrices, and outputting an abnormal prompt when the missing value frequency is greater than a preset frequency, includes:

[0134] Calculating a first occurrence frequency of a first missing value of the first sensor within a preset time period, and a second occurrence frequency of a second missing value of the second sensor within a preset time period;

[0135] When the first occurrence frequency within M consecutive preset time periods is greater than N, it is determined that the first missing value frequency is greater than the above-mentioned preset frequency, and an abnormal output prompt is given for the first sensor; and / or,

[0136] When the second occurrence frequency within M consecutive preset time lengths is greater than N, it is determined that the second missing value frequency is greater than the above-mentioned preset frequency, and an abnormal output prompt is given for the second sensor.

[0137] In some embodiments, calculating the similarity between the first adjacency matrix and the first energy matrix includes:

[0138] Acquire a first frequency parameter during the first adjacent matrix measurement period and a second frequency parameter during the first energy matrix measurement period;

[0139] Performing feature extraction on the first frequency parameter to obtain a first frequency feature, and performing feature extraction on the second frequency parameter to obtain a second frequency feature;

[0140] Calculating feature similarity between the first frequency feature and the second frequency feature, and matrix similarity between the first adjacency matrix and the first energy matrix;

[0141] The similarity between the first adjacent matrix and the first energy matrix is ​​determined according to the feature similarity and the matrix similarity.

[0142] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described method and each step can refer to the corresponding process in the aforementioned system embodiment and will not be repeated here.

[0143] The systems and methods of the present application can be used in a wide range of general or special computing system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0144] For example, the above method and apparatus may be implemented in the form of a computer program. The computer program may be implemented in the form of a computer program. Figure 3 Runs on the computer device shown.

[0145] See also Figure 3 , Figure 3 This is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device can be a server or a terminal.

[0146] like Figure 3 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a storage medium and an internal memory.

[0147] The storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any noise source tracing and analysis method based on dual-sensor rotation measurement.

[0148] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0149] The internal memory provides an environment for the operation of the computer program in the storage medium. When the computer program is executed by the processor, the processor can execute any noise source tracing analysis method based on dual-sensor rotation measurement.

[0150] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0151] It should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0152] In one embodiment, the processor is configured to execute a computer program stored in the memory to implement the following steps:

[0153] Obtaining an energy matrix corresponding to each rotation period, wherein the energy matrix includes energy data corresponding to each preset direction within the rotation period;

[0154] Obtaining missing data in the energy matrix, and calculating the missing data according to an adjacent matrix of the energy matrix to obtain a target matrix after the missing data is restored;

[0155] The corresponding prediction results are drawn and output according to the energy data in the target matrix.

[0156] In some embodiments, the data acquisition module includes a first sensor, a second sensor, and a rotating component, wherein the rotating component uses a geometric center as a rotation center, the first sensor and the second sensor are installed at different positions of the rotating component, and the first position where the first sensor is located and the second position where the second sensor is located are centrally symmetrically distributed about the geometric center. The data acquisition module is used to detect energy data corresponding to each preset direction in each rotation cycle during the process of the rotating component driving the first sensor and the second sensor to rotate, and obtain an energy matrix corresponding to each rotation cycle.

[0157] In some embodiments, during the process of the rotating component driving the first sensor and the second sensor to rotate, the energy data corresponding to each preset direction in each rotation cycle is detected, and the energy matrix corresponding to each rotation cycle is obtained, which is further used to:

[0158] During the rotation period, acquiring first noise energy data detected by the first sensor, second noise energy data detected by the second sensor at the same time, and position data detected by the position sensor at the same time;

[0159] determining, according to the position data, a first direction corresponding to the first noise energy data and a second direction corresponding to the second noise energy data;

[0160] Filling the first noise energy data into a first position corresponding to the first direction in the energy matrix, and filling the second noise energy data into a second position corresponding to the second direction in the energy matrix;

[0161] The rotation period is the duration of half a rotation of the first sensor or the second sensor.

[0162] In some embodiments, the process of obtaining missing data in the energy matrix and calculating the missing data according to the adjacent matrix of the energy matrix to obtain the target matrix after the missing data is restored is further used to:

[0163] Obtaining adjacent matrices of the first n frames and adjacent matrices of the next n frames adjacent to the energy matrix, performing pattern recognition on the adjacent matrices to obtain a noise energy distribution pattern;

[0164] The missing data is restored according to the noise energy distribution pattern to obtain a target matrix after the missing data is restored.

[0165] In some embodiments, obtaining adjacent matrices of the first n frames and adjacent matrices of the next n frames adjacent to the energy matrix, and performing pattern recognition on the adjacent matrices to obtain a noise energy distribution pattern includes:

[0166] Eliminating the items at the positions corresponding to the missing data from the adjacent matrix to obtain a first adjacent matrix, and eliminating the missing data from the energy matrix to obtain a first energy matrix;

[0167] Calculating a similarity between the first adjacent matrix and the first energy matrix, and determining the first adjacent matrix having the similarity greater than a preset similarity as a second adjacent matrix;

[0168] Performing pattern recognition on the second adjacent matrix to obtain the noise energy distribution pattern.

[0169] In some embodiments, performing pattern recognition on the second adjacent matrix to obtain the noise energy distribution pattern includes:

[0170] performing pattern recognition on the second adjacent matrices to obtain energy distribution information corresponding to each second adjacent matrix;

[0171] Determining a weight corresponding to each piece of energy distribution information according to the similarity of each of the second adjacent matrices;

[0172] The energy distribution information is fused according to the weight to obtain the noise energy distribution pattern.

[0173] In some embodiments, the noise source tracing and analysis method based on dual-sensor rotation measurement further includes:

[0174] The missing value frequency is determined according to the distribution of the missing data in each of the energy matrices, and an abnormal prompt is output when the missing value frequency is greater than a preset frequency.

[0175] In some embodiments, determining the missing value frequency based on the distribution of the missing data in each of the energy matrices, and outputting an abnormal prompt when the missing value frequency is greater than a preset frequency, includes:

[0176] Calculating a first occurrence frequency of a first missing value of the first sensor within a preset time period, and a second occurrence frequency of a second missing value of the second sensor within a preset time period;

[0177] In a case where the first occurrence frequency in the continuous M preset time lengths is greater than N, it is determined that the first missing value frequency is greater than the preset frequency, and the output abnormality prompt is given for the first sensor; and / or,

[0178] In a case where the second occurrence frequency in the continuous M preset time lengths is greater than N, it is determined that the second missing value frequency is greater than the preset frequency, and the output abnormality prompt is given for the second sensor.

[0179] In some embodiments, the similarity of the first adjacent matrix and the first energy matrix is calculated, including:

[0180] obtaining a first frequency parameter during measurement of the first adjacent matrix and a second frequency parameter during measurement of the first energy matrix;

[0181] performing feature extraction on the first frequency parameter to obtain a first frequency feature, and performing feature extraction on the second frequency parameter to obtain a second frequency feature;

[0182] calculating a feature similarity of the first frequency feature and the second frequency feature, and a matrix similarity of the first adjacent matrix and the first energy matrix;

[0183] determining the similarity of the first adjacent matrix and the first energy matrix according to the feature similarity and the matrix similarity.

[0184] It should be noted that, for the convenience and brevity of description, the above description is based on the specific working process of the noise traceability analysis system of the double-sensor rotation measurement, and the corresponding process in the foregoing embodiments can be referred to, which will not be described here.

[0185] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the computer program includes program instructions. The method implemented by executing the program instructions can refer to each embodiment of the noise traceability analysis method based on double-sensor rotation measurement of the present application.

[0186] The computer readable storage medium can be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. The computer readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc.

[0187] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0188] It should also be understood that the term "and / or" used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements that are inherent to such process, method, article or system. In the absence of further limitations, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system that includes the element.

[0189] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments. The above description is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A noise source tracing and analysis system based on dual-sensor rotation measurement, characterized in that: The system comprises: A data acquisition module, configured to acquire an energy matrix corresponding to each rotation period, wherein the energy matrix includes energy data corresponding to each preset direction within the rotation period; a data calculation module, configured to obtain missing data in the energy matrix and calculate the missing data according to an adjacent matrix of the energy matrix to obtain a target matrix after the missing data is restored; An output drawing module, configured to draw and output corresponding prediction results according to the energy data in the target matrix; The data calculation module is used to obtain the missing data in the energy matrix, and calculate the missing data according to the adjacent matrix of the energy matrix to obtain the target matrix after the missing data is restored. It is also used to: Obtaining adjacent matrices of the first n frames and adjacent matrices of the next n frames adjacent to the energy matrix, performing pattern recognition on the adjacent matrices to obtain a noise energy distribution pattern; Restoring the missing data according to the noise energy distribution pattern to obtain a target matrix after the missing data is restored; The step of obtaining adjacent matrices of first n frames and adjacent matrices of next n frames adjacent to the energy matrix, and performing pattern recognition on the adjacent matrices to obtain a noise energy distribution pattern includes: Eliminating the items at the positions corresponding to the missing data from the adjacent matrix to obtain a first adjacent matrix, and eliminating the missing data from the energy matrix to obtain a first energy matrix; Calculating a similarity between the first adjacent matrix and the first energy matrix, and determining the first adjacent matrix having the similarity greater than a preset similarity as a second adjacent matrix; Performing pattern recognition on the second adjacent matrix to obtain the noise energy distribution pattern.

2. The noise source tracing and analysis system based on dual-sensor rotation measurement according to claim 1 is characterized in that: The data acquisition module includes a first sensor, a second sensor and a rotating component. The rotating component uses a geometric center as a rotation center. The first sensor and the second sensor are installed at different positions of the rotating component, and the first position where the first sensor is located and the second position where the second sensor is located are centrally symmetrically distributed about the geometric center. The data acquisition module is used to detect energy data corresponding to each preset direction in each rotation cycle during the process of the rotating component driving the first sensor and the second sensor to rotate, and obtain an energy matrix corresponding to each rotation cycle.

3. The noise source tracing and analysis system based on dual-sensor rotation measurement according to claim 2 is characterized in that: The data acquisition module is further configured to: detect energy data corresponding to each preset direction in each rotation cycle during the process in which the rotating component drives the first sensor and the second sensor to rotate, and obtain an energy matrix corresponding to each rotation cycle; During the rotation period, acquiring first noise energy data detected by the first sensor, second noise energy data detected by the second sensor at the same time, and position data detected by the position sensor at the same time; determining, according to the position data, a first direction corresponding to the first noise energy data and a second direction corresponding to the second noise energy data; Filling the first noise energy data into a first position corresponding to the first direction in the energy matrix, and filling the second noise energy data into a second position corresponding to the second direction in the energy matrix; The rotation period is the duration of half a rotation of the first sensor or the second sensor.

4. The noise source tracing and analysis system based on dual-sensor rotation measurement according to claim 1 is characterized in that: The performing pattern recognition on the second adjacent matrix to obtain the noise energy distribution pattern includes: performing pattern recognition on the second adjacent matrices to obtain energy distribution information corresponding to each second adjacent matrix; Determining a weight corresponding to each piece of energy distribution information according to the similarity of each of the second adjacent matrices; The energy distribution information is fused according to the weight to obtain the noise energy distribution pattern.

5. The noise source tracing and analysis system based on dual-sensor rotation measurement according to any one of claims 1 to 4, characterized in that: The noise source tracing and analysis system based on dual-sensor rotation measurement also includes: The abnormality prompt module is used to determine the missing value frequency according to the distribution of the missing data in each energy matrix, and output an abnormality prompt when the missing value frequency is greater than a preset frequency.

6. The noise source tracing and analysis system based on dual-sensor rotation measurement according to claim 5 is characterized in that: The determining of the missing value frequency according to the distribution of the missing data in each of the energy matrices, and outputting an abnormal prompt when the missing value frequency is greater than a preset frequency, includes: Calculating a first occurrence frequency of a first missing value of the first sensor within a preset time period, and a second occurrence frequency of a second missing value of the second sensor within a preset time period; When the first occurrence frequency within M consecutive preset time periods is greater than N, it is determined that the first missing value frequency is greater than the above-mentioned preset frequency, and an abnormal output prompt is given for the first sensor; and / or, When the second occurrence frequency within M consecutive preset time lengths is greater than N, it is determined that the second missing value frequency is greater than the above-mentioned preset frequency, and an abnormal output prompt is given for the second sensor.

7. The noise source tracing and analysis system based on dual-sensor rotation measurement according to claim 1 is characterized in that: The calculating the similarity between the first adjacent matrix and the first energy matrix includes: Acquire a first frequency parameter during the first adjacent matrix measurement period and a second frequency parameter during the first energy matrix measurement period; Performing feature extraction on the first frequency parameter to obtain a first frequency feature, and performing feature extraction on the second frequency parameter to obtain a second frequency feature; Calculating feature similarity between the first frequency feature and the second frequency feature, and matrix similarity between the first adjacency matrix and the first energy matrix; The similarity between the first adjacent matrix and the first energy matrix is ​​determined according to the feature similarity and the matrix similarity.

8. A noise source tracing and analysis method based on dual-sensor rotation measurement, characterized in that: The method comprises: Obtaining an energy matrix corresponding to each rotation period, wherein the energy matrix includes energy data corresponding to each preset direction within the rotation period; Obtaining missing data in the energy matrix, and calculating the missing data according to an adjacent matrix of the energy matrix to obtain a target matrix after the missing data is restored; Draw and output corresponding prediction results according to the energy data in the target matrix; The step of obtaining missing data in the energy matrix and calculating the missing data according to an adjacent matrix of the energy matrix to obtain a target matrix after the missing data is restored includes: Obtaining adjacent matrices of the first n frames and adjacent matrices of the next n frames adjacent to the energy matrix, performing pattern recognition on the adjacent matrices to obtain a noise energy distribution pattern; Restoring the missing data according to the noise energy distribution pattern to obtain a target matrix after the missing data is restored; The step of obtaining adjacent matrices of first n frames and adjacent matrices of next n frames adjacent to the energy matrix, and performing pattern recognition on the adjacent matrices to obtain a noise energy distribution pattern includes: Eliminating the items at the positions corresponding to the missing data from the adjacent matrix to obtain a first adjacent matrix, and eliminating the missing data from the energy matrix to obtain a first energy matrix; Calculating a similarity between the first adjacent matrix and the first energy matrix, and determining the first adjacent matrix having the similarity greater than a preset similarity as a second adjacent matrix; Performing pattern recognition on the second adjacent matrix to obtain the noise energy distribution pattern.

Images