Noise Sensor Operation Monitoring System and Method Based on Multivariate Data Fusion Processing

Abstract

The present invention discloses a noise sensor operation monitoring system and method based on multi-source data fusion processing, which relates to the technical field of data processing. It includes an information collection module: obtaining historical environmental data and historical noise data; an information processing module: exploring the influence relationship and corresponding information between the environment and noise through an exploration method to obtain a target relationship and reference information. By setting a compensation model in cooperation with a dynamic analysis method, according to real-time environmental data, it is analyzed whether the environment and noise have changed to obtain change data, and the change data is compensated through the compensation model to obtain corrected noise, so as to compensate and correct the monitored noise data with deviations in the noise sensor caused by environmental changes, so as to improve the accuracy of the monitored noise data. By setting a prediction matching method, according to the user's needs, the predicted noise is matched with the repository, so that it is convenient for the user to understand the future noise of the needs, so as to take corresponding measures to control the noise.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and specifically to a noise sensor operation monitoring system and method based on multi-source data fusion processing. Background Art

[0002] A noise sensor is a device used to measure the ambient noise level, which is widely used in industries, transportation, urban management and other fields to help monitor and control noise pollution. When the noise sensor is operating, it is vulnerable to the influence of the external environment, resulting in monitoring errors. In order to reduce the monitoring errors, it is often necessary to monitor and correct the operation of the noise sensor.

[0003] A locomotive noise intelligent monitoring system with the patent publication number of CN116124481A includes: a data acquisition module, which is used to set a sound sensor according to the locomotive track position to collect noise signals, form a noise difference vector data set, and form a non-linear model; a data analysis module, which is used to perform noise sample confirmation operations according to the track noise characteristics, and perform noise sample data marking after confirmation; a noise monitoring module, which is used to substitute the noise sample data into the non-linear model, and identify abnormal noises by judging the data distribution of the track noise through Bayesian, and discover abnormal contact states between the track and the vehicle.

[0004] Monitoring systems based on the above and similar principles mostly rely on noise sensors. In a dynamic environment where the environment is prone to change, it will cause an increase in the errors generated by the monitoring data of the noise sensor, and then lead to errors in the overall noise monitoring, which is not convenient for reflecting the accurate real-time noise situation. Noise pollution not only has a direct impact on personal health, but also affects multiple aspects such as psychological conditions, ecological environment and social economy. In order to reduce the harm caused by noise pollution, it is necessary to take effective noise control measures. In order to optimize the reduction of noise pollution, it is often necessary to carry out corresponding speed limits, traffic restrictions or traffic guidance on roads. In the prior art, when performing noise monitoring, it is not convenient to predict future noise situations based on historical noise situations, and then it is not convenient for the management department to take measures to reduce noise pollution while ensuring traffic to the greatest extent. Therefore, the present invention is proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide a noise sensor operation monitoring system and method based on multi-source data fusion processing to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solution: A noise sensor operation monitoring system based on multi-source data fusion processing, the system includes:

[0007] An information collection module: obtaining historical environmental data and historical noise data;

[0008] Information processing module: Explore the influence relationship between the environment and noise and corresponding information through an exploration method to obtain the target relationship and reference information, and establish a compensation model based on the target relationship and reference information;

[0009] Monitoring and compensation module: Obtain the monitoring data and environmental data of the noise sensor in real time to get the real-time noise data and real-time environmental data. Analyze whether the environment and noise have changed through a dynamic analysis method based on the real-time environmental data to obtain change data. Extract the real-time noise data from the change data to get the noise to be corrected. Compensate the noise to be corrected based on the change data through the compensation model to obtain the corrected noise;

[0010] Reference establishment module: Replace the noise to be corrected in the real-time noise data with the corrected noise to obtain the corrected real-time noise, and establish a repository for storing the corrected real-time noise, real-time environmental data, historical environmental data, and historical noise data;

[0011] Matching and output module: Obtain the prediction requirement and user address information, determine the target time point based on the prediction requirement, obtain the predicted noise through a prediction matching method based on the target time point and in cooperation with the repository, and feedback the predicted noise to the user based on the user address information;

[0012] The exploration method includes: Preset a standard environment and quantitative noise, monitor the quantitative noise in the standard environment by the noise sensor to obtain the reference noise, preset an addition parameter, adjust the standard environment based on the addition parameter to obtain an adjusted environment, monitor the quantitative noise in the adjusted environment by the noise sensor to obtain the comparison noise, integrate the reference noise, comparison noise, standard environment, and adjusted environment to obtain the reference information, and obtain the target relationship by obtaining the influence relationship between the environment and noise based on the reference information through a relationship acquisition method.

[0013] Furthermore, the process of presetting the addition parameter and adjusting the standard environment based on the addition parameter to obtain the adjusted environment is: Split the standard environment into several standard items, preset fixed parameters based on the standard items to obtain sub-parameters, integrate the sub-parameters of all standard items to obtain the addition parameter, preset an adjustment object, where the adjustment object includes adjusting a single standard item and adjusting multiple standard items, determine the adjustment object based on the standard items to obtain the target object, and perform incremental adjustment and decremental adjustment on the standard items in the target object based on the addition parameter to obtain the adjusted environment.

[0014] Further, the relationship acquisition method includes: classifying the reference information by environment and noise to obtain a noise information set and an environment information set, splitting the noise information set and the environment information set to obtain a number of noise information and a number of environment information, establishing the correlation between the noise information and the environment information, extracting the environment for single standard item adjustment from the environment information set to obtain a single-factor environment, extracting the environment for multiple standard item adjustments from the environment information set to obtain a multi-factor environment, correspondingly extracting the noise information of the single-factor environment and the multi-factor environment based on the correlation to obtain single-factor noise and multi-factor noise, sorting the single-factor environment and the multi-factor environment from small to large based on the parameters of the same standard item to obtain single-factor sorting information and multi-factor sorting information, correspondingly sorting the single-factor noise and the multi-factor noise in combination with the single-factor sorting information and the multi-factor sorting information based on the correlation to obtain single-factor sorted noise and multi-factor sorted noise, obtaining a single-factor difference set and a multi-factor difference set based on the differences between adjacent noises in the single-factor sorted noise and the multi-factor sorted noise, extracting the single-factor noise range and the multi-factor noise range with the same difference in the single-factor difference set and the multi-factor difference set to obtain a single-factor range and a multi-factor range, extracting the corresponding single-factor environment and multi-factor environment based on the single-factor range and the multi-factor range in combination with the correlation to obtain a linear relationship range, removing the single-factor range and the multi-factor range in the single-factor noise and the multi-factor noise and extracting the corresponding single-factor environment and multi-factor environment in combination with the correlation to obtain a non-linear relationship range, and integrating the linear relationship range and the non-linear relationship range to obtain the target relationship.

[0015] Further, the method for establishing a compensation model includes:

[0016] Data acquisition and processing: Based on the reference information and the target relationship, training data is derived through a data derivation method to obtain derived data, the reference information and the derived data are integrated to obtain preliminary data, the noise difference generated by adjacent environment data in the preliminary data is obtained to obtain the target difference, and the target difference is marked in the preliminary data to obtain training data;

[0017] Model selection and training: Select a deep learning model as the model matrix, and import the training data into the model matrix for the model matrix to be trained to obtain an initial model;

[0018] Model adjustment and output: Preset verification data and verification results, import the verification data into the initial model to obtain result information, compare the verification results and the result information to obtain comparison information, and adjust and optimize the initial model based on the comparison information to obtain a compensation model.

[0019] Further, the data derivation method includes: the target relationships are the linear relationship range and the non-linear relationship range. A preset addition value is set. For the environment in the linear relationship range, the addition value is incremented or decremented to obtain a linearly derived environment. Based on the relationship between the addition value and the addition parameter, the noise information of the environment is correspondingly reduced or increased to obtain linearly derived noise. For the environment in the non-linear relationship range, the addition value is incremented or decremented to obtain a non-linearly derived environment. Based on the non-linearly derived environment and quantitative noise, in cooperation with a noise sensor, non-linearly derived noise is obtained. The linearly derived environment, linearly derived noise, non-linearly derived environment, and non-linearly derived noise are integrated to obtain derived data.

[0020] Further, the dynamic analysis method includes: a preset interval time is set. The environmental data at the interval time before the real-time time point is obtained to obtain past environmental data. The noise information of the past environmental data and the real-time environmental data is obtained to obtain the first noise and the second noise. When the real-time environmental data changes and the second noise does not change, and when the real-time environmental data changes and the second noise changes, the past environmental data, the real-time environmental data, the first noise, and the second noise are integrated to obtain change data.

[0021] Further, the prediction matching method includes: the time features and holiday features of the historical noise data and the real-time noise data in the repository are extracted to obtain a reference feature set. The reference feature set includes a number of reference features corresponding to the historical noise data and the real-time noise data. The time feature and holiday at the target time point are obtained to obtain a target feature. A preset similarity value is set. Based on the target feature, the reference feature set is traversed to select the reference features whose similarity to the target feature exceeds the similarity value to obtain selected features. Based on the selected features, the noise data corresponding to the target feature is selected from the repository to obtain predicted noise.

[0022] A method for monitoring the operation of a noise sensor based on multi-source data fusion processing uses the above-mentioned system for monitoring the operation of a noise sensor based on multi-source data fusion processing.

[0023] Compared with the prior art, the beneficial effects of the present invention are:

[0024] For the system and method for monitoring the operation of a noise sensor based on multi-source data fusion processing, through the compensation model set in cooperation with the dynamic analysis method, according to the real-time environmental data, it is analyzed whether the environment and the noise change to obtain change data. According to the change data, the noise to be corrected is compensated by the compensation model to obtain corrected noise, so that the monitored noise data with deviation caused by environmental changes of the noise sensor can be compensated and corrected to improve the accuracy of the monitored noise data. Through the prediction matching method set, according to the user's needs, it is matched and output in cooperation with the repository to obtain predicted noise, so that it is convenient for the user to understand the future noise of the needs, so as to take corresponding measures to control the noise.

[0025] Meanwhile, data derivation is performed on the reference information according to the target relationship through the set data derivation method to enrich the quantity of data for training the model and diversify the data, so as to improve the accuracy of the model. The multiple relationship between the added value and the added parameter is recorded. By increasing or decreasing the added value in the environment within the linear relationship range, a linear derivative environment can be obtained. Through the multiple relationship, the linear derivative noise corresponding to the linear derivative environment can be calculated. By increasing and decreasing the added value in the environment within the non-linear relationship range, a non-linear derivative environment can be obtained. Create a non-linear derivative environment and add quantitative noise in combination with a noise sensor to obtain non-linear derivative noise. Through the prediction matching method, the features in the extracted historical noise data can be used, combined with the user's needs, to obtain the features at a future time point for similarity matching to obtain the predicted noise of the noise at the future time point, so that the user can know in advance the possible predicted noise at the future time point and apply it to different fields.

[0026] Meanwhile, through the set dynamic analysis method, it is judged whether the noise monitored in real time needs to be compensated to improve the smooth operation of the overall system and reduce the load of the system, which is beneficial for use. When the real-time environmental data changes and the second noise does not change, and when the real-time environmental data changes and the second noise changes, it proves that the real-time noise data monitored by the noise sensor needs to be compensated. At the same time, a threshold for the change of real-time environmental data can be set, that is, when the threshold is exceeded, the data monitored by the noise sensor needs to be compensated, and when the threshold is not exceeded, no compensation is required. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a schematic diagram of the main structure of the present invention;

[0028] Figure 2 is a schematic diagram of the reference establishment module structure of the present invention;

[0029] Figure 3 is a schematic diagram of the matching output module structure of the present invention;

[0030] Figure 4 is a schematic diagram of the process of establishing a compensation model of the present invention;

[0031] Figure 5 is a schematic diagram of the relationship acquisition method structure of the present invention.

[0032] BRIEF DESCRIPTION OF THE DRAWINGS: Figure 5 In (a), it is a schematic diagram of the linear relationship range and non-linear relationship range of single-factor sorted noise, Figure 5 In (b), it is a schematic diagram of the linear relationship range and non-linear relationship range of multi-factor sorted noise. DETAILED DESCRIPTION OF THE INVENTION

[0033] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0034] Multivariate data fusion processing refers to integrating, analyzing, and processing data from different sources, different formats, and different characteristics to extract more comprehensive and accurate information. Based on this, multivariate data fusion processing refers to integrating and processing data from different sources (such as noise data and environmental data) to improve the accuracy, reliability, and intelligence level of the monitoring system. By performing multivariate data fusion processing on the data collected by noise sensors, environmental interference can be eliminated and data accuracy can be improved. The corrected noise data is more accurate and reliable, and can support the intelligent operation and decision-making of the noise monitoring system.

[0035] As Figures 1 - 5 shown, the present invention provides a technical solution: a noise sensor operation monitoring system based on multivariate data fusion processing. The system includes:

[0036] An information collection module: obtaining historical environmental data and historical noise data; Embodiment

[0037] In the process of connecting a noise sensor to the operation monitoring system, it is first necessary to determine the noise sensor model and obtain the historical noise data of the noise sensor. For example, when connecting a noise sensor with the model Microphone(1 / 2"Prepolarized,40kHz)-Brüel&Kjær4135 to the operation monitoring system, the historical monitored noise data of this type of noise sensor and the environmental data where the noise sensor is located are obtained. The specific environmental data can be obtained through corresponding sensors. When adjusting this type of noise sensor, the historical noise data of the adjusted noise sensor needs to be obtained accordingly.

[0038] An information processing module: exploring the influence relationship between the environment and noise and corresponding information through exploration methods to obtain the target relationship and reference information, and establishing a compensation model based on the target relationship and reference information;

[0039] Real-time Example Two

[0040] Judge the influence relationship between the environment and noise based on the collected historical environment data and historical noise data. Specifically, it is necessary to first establish the time relationship between the historical environment data and the historical noise data to ensure the correspondence between the environment data and the noise data. When the collected historical environment data is the first environment data: temperature: 20°C, humidity: 50%, air pressure: 1010 hPa, wind speed: 5 km / h; the second environment data: temperature: 25°C, humidity: 55%, air pressure: 1030 hPa, wind speed: 7 km / h; the third environment data: temperature: 22°C, humidity: 50%, air pressure: 1010 hPa, wind speed: 8 km / h; the collected historical noise data is the first noise data of 70 dB; the second noise data of 60 dB; the third noise data of 65 dB; that is, it is necessary to pair the noise and the environment according to the time relationship, and match the generation time of the first environment data, the second environment data, and the third environment data with the generation time of the first noise data, the second noise data, and the third noise data to obtain the corresponding environment data and noise data. Then, extract multiple corresponding environment data and noise data and use the exploration method to explore the influence relationship and corresponding information between the noise and the environment.

[0041] Monitoring compensation module: Obtain the monitoring data of the noise sensor and the environment data in real time to obtain the real-time noise data and the real-time environment data. Analyze whether the environment and the noise have changed through the dynamic analysis method based on the real-time environment data to obtain the change data. Extract the real-time noise data from the change data to obtain the noise to be corrected. Compensate the noise to be corrected based on the change data through the compensation model to obtain the corrected noise.

[0042] Real-time example three

[0043] When the noise sensor is running in real time, by installing temperature and humidity sensors, barometric pressure sensors, and wind speed sensors around the working environment of the noise sensor, the data of temperature, humidity, barometric pressure, and wind speed can be obtained, that is, the real-time environmental data can be obtained. Then, based on the noise value monitored by the noise sensor, the real-time noise data can be obtained. During the process of information generation and output, it is ensured that the generation and output of the real-time environmental data and the real-time noise data are consistent. That is, when the noise sensor generates noise at 11:50, the above-mentioned monitored environmental sensors generate environmental data, that is, the data of temperature, humidity, barometric pressure, and wind speed, at 11:50. According to the collected real-time environmental data and real-time noise data, the change data is obtained by analyzing whether the environment and noise have changed through a dynamic analysis method. Specifically, it is judged whether the noise changes when the environment changes, and whether the noise changes when the environment does not change. When the environment changes, whether the noise changes or not may cause deviations in the monitored noise values. Therefore, the environmental change threshold can be set according to the applicable environment of the noise sensor. When the temperature is between -10°C and 35°C and the humidity is between 10% and 65%, it is determined that there will be no deviation in the noise sensor. That is, when the environmental change is within the environmental change threshold, no noise compensation is required.

[0044] Reference establishment module: Replace the noise to be corrected in the real-time noise data with the corrected noise to obtain the corrected real-time noise, and establish a repository for storing the corrected real-time noise, real-time environmental data, historical environmental data, and historical noise data;

[0045] Matching output module: Obtain the prediction requirement and user address information, determine the target time point based on the prediction requirement, obtain the predicted noise through the prediction matching method based on the target time point in cooperation with the repository, and feedback the predicted noise to the user based on the user address information; Embodiment

[0046] First, the user's prediction requirement and user address information are obtained through the user himself / herself. Specifically, the prediction requirement can be obtained by the user's own input or sending, and the user address information, that is, the phone number or email, can be obtained by recording the way of the user's input or sending. When the user has a prediction requirement, the predicted noise that meets the user's prediction requirement is predicted through the prediction matching method according to the prediction requirement. That is, the historical noise data corresponding to the prediction date is found by matching based on the previous noise data and date characteristics to obtain the predicted noise. When there are multiple predicted noises, the noise with the highest similarity during matching is selected as the predicted noise, and the predicted noise is sent to the user according to the user address information.

[0047] It should be noted that in the information collection module, the historical environmental data and historical noise data can be obtained from the work logs of this noise sensor or noise sensors of the same model. This noise sensor refers to the noise sensor to which this monitoring system needs to be applied. The historical environmental data is the environmental data of the working environment where the noise sensor is located, including temperature, humidity, air pressure, etc. The historical noise data is a collection of noise values monitored by the noise sensor in the past. In the information processing module, the influence relationship between the environment and noise and corresponding information are explored through the set exploration method to obtain the target relationship and reference information. A compensation model is established through the target relationship in cooperation with the reference information. Through the compensation model, it is convenient to compensate the noise data monitored by the noise sensor to improve the accuracy of noise monitoring by the noise sensor. In the monitoring compensation module, the real-time noise data can be directly obtained through the noise sensor, and the real-time environmental data can be obtained by installing corresponding environmental sensors around the noise sensor, such as temperature and humidity sensors and air pressure sensors, etc. Through the set dynamic analysis method, it is analyzed whether the environment and noise have changed according to the real-time environmental data to obtain change data. According to the change data, the noise to be corrected is compensated through the compensation model to obtain the corrected noise. The corrected noise is the combination of the compensation value obtained from the compensation model and the real-time noise data. In the reference establishment module, the noise to be corrected in the real-time noise data is replaced with the corrected noise to obtain the corrected real-time noise, and a repository is established to store the real-time and historical environmental data and noise data, so as to facilitate predicting future noise. In the matching output module, the prediction requirement is obtained from the user, specifically the user's prediction time requirement. The user address information is the address information for sending the information to the user, which may specifically include the IP address and email, etc. The target time point is the user's prediction requirement. Through the set prediction matching method, the predicted noise is obtained according to the target time point in cooperation with the repository, and then the predicted noise is fed back to the user according to the user address information, so that it is convenient for the user to understand the future noise of the requirement and take corresponding measures to control the noise.

[0048] As Figure 1 shown, the exploration method includes: presetting a standard environment and quantitative noise, obtaining a reference noise based on the noise sensor monitoring the quantitative noise in the standard environment, presetting an addition parameter, adjusting the standard environment based on the addition parameter to obtain an adjusted environment, obtaining a comparison noise based on the noise sensor monitoring the quantitative noise in the adjusted environment, integrating the reference noise, comparison noise, standard environment and adjusted environment to obtain reference information, and obtaining a target relationship based on the reference information through a relationship acquisition method to obtain the influence relationship between the environment and noise.

[0049] It should be noted that the standard environment and quantitative noise are formulated according to the actual usage situation. The reference noise is obtained by monitoring the quantitative noise in the set standard environment through a noise sensor. The addition parameters are preset according to the actual usage situation. The specific addition parameters are consistent with a single item in the standard environment. The standard environment is adjusted through the addition parameters to obtain the adjusted environment. The contrast noise is obtained by monitoring the quantitative noise in the set adjusted environment through a noise sensor. The influence relationship between the environment and the noise is obtained according to the set relationship acquisition method based on the reference information to obtain the target relationship.

[0050] In the specific implementation process, first, the standard environment, quantitative noise, and addition parameters need to be set. For example, the standard environment is temperature: 20°C, humidity: 50%, air pressure: 1010 hPa, wind speed: 5 km / h; the quantitative noise is 65 dB, and the addition parameters are temperature 1°C, humidity 1%, air pressure 10 hPa, wind speed 1 km / h. The adjusted environment can be obtained by adjusting the standard environment through the addition parameters. There are multiple adjusted environments. For example, the first adjusted environment is temperature: 21°C, humidity: 51%, air pressure: 1020 hPa, wind speed: 6 km / h; the second adjusted environment is temperature: 22°C, humidity: 52%, air pressure: 1030 hPa, wind speed: 7 km / h; the nth adjusted environment is temperature: 20 + (n * 1)°C, humidity: 50 + (n * 1)%, air pressure: 1010 + (n * 10) hPa, wind speed: 5 + (n * 1) km / h. The above shows that the adjusted environment is in an increasing state, and it can also be in a decreasing state. For example, the first adjusted environment is temperature: 19°C, humidity: 49%, air pressure: 1000 hPa, wind speed: 4 km / h; the second adjusted environment is temperature: 18°C, humidity: 48%, air pressure: 990 hPa, wind speed: 3 km / h; the nth adjusted environment is temperature: 20 - (n * 1)°C, humidity: 50 - (n * 1)%, air pressure: 1010 - (n * 10) hPa, wind speed: 5 - (n * 1) km / h. At the same time, the number of specific adjustment items can be single or multiple. The above is the adjustment of multiple items. For the adjustment of a single item, for example, temperature: 21°C, humidity: 50%, air pressure: 1010 hPa, wind speed: 5 km / h.

[0051] The process of presetting the addition parameters and adjusting the standard environment based on the addition parameters to obtain the adjusted environment is as follows: The standard environment is split into several standard items, fixed parameters are preset based on the standard items to obtain sub-parameters, the sub-parameters of all standard items are integrated to obtain the addition parameters, the adjustment object is preset, and the adjustment object includes adjusting a single standard item and adjusting multiple standard items. The target object is obtained based on the standard items to determine the adjustment object, and the standard items in the target object are adjusted incrementally and decrementally based on the addition parameters to obtain the adjusted environment.

[0052] It should be noted that the added parameters are formulated corresponding to the units of the standard items, that is, sub-parameters are obtained according to the preset fixed parameters of the standard items, and all the preset sub-parameters are integrated to obtain the added parameters. The added parameters include the adjustment parameters of all standard items in the standard environment. The adjustment object is selected according to the actual usage situation, and the selection method can be formulated by the user himself, including single selection or multiple selections. The upper limit of multiple selections is the number of standard items in the standard environment. Based on the added parameters, the standard items in the target object are adjusted incrementally and decrementally in sequence to obtain the adjustment environment.

[0053] In the specific implementation process, when the standard items in the standard environment include temperature, humidity, air pressure and wind speed, there are sub-parameters corresponding to temperature, humidity, air pressure and wind speed in the added parameters. At this time, the adjustment object can be single or multiple. When it is single, it can be one of temperature, humidity, air pressure and wind speed. When it is multiple, it can be two, three or all of humidity, humidity, air pressure and wind speed. Through the cooperation of the adjustment object and the added parameters, the standard items in the adjustment object are adjusted incrementally and decrementally. For example, the first adjustment is to increment the added parameter by 1 unit, and the second adjustment is to continue to increment the added parameter by 1 unit on the basis of the previous adjustment, and so on. The decrement is to decrement the added parameter by 1 unit in sequence.

[0054] Such as Figure 5As shown, the relationship acquisition method includes: classifying reference information into environmental information and noise information to obtain a noise information set and an environmental information set, splitting the noise information set and the environmental information set to obtain a number of noise information and a number of environmental information, establishing the correlation between the noise information and the environmental information, extracting the environment for single standard item adjustment from the environmental information set to obtain a single-factor environment, extracting the environment for multiple standard item adjustments from the environmental information set to obtain a multi-factor environment, extracting the noise information of the single-factor environment and the multi-factor environment based on the correlation to obtain single-factor noise and multi-factor noise, sorting the single-factor environment and the multi-factor environment in ascending order of parameters for the same standard item to obtain single-factor sorting information and multi-factor sorting information, sorting the single-factor noise and the multi-factor noise corresponding to the single-factor sorting information and the multi-factor sorting information based on the correlation to obtain single-factor sorted noise and multi-factor sorted noise, obtaining a single-factor difference set and a multi-factor difference set based on the differences between adjacent noises in the single-factor sorted noise and the multi-factor sorted noise, extracting the single-factor noise range and the multi-factor noise range with the same difference in the single-factor difference set and the multi-factor difference set to obtain a single-factor range and a multi-factor range, extracting the corresponding single-factor environment and multi-factor environment based on the single-factor range and the multi-factor range in combination with the correlation to obtain a linear relationship range, removing the single-factor range and the multi-factor range in the single-factor noise and the multi-factor noise and extracting the corresponding single-factor environment and multi-factor environment in combination with the correlation to obtain a non-linear relationship range, and integrating the linear relationship range and the non-linear relationship range to obtain the target relationship.

[0055] It should be noted that the process of classifying reference information into environmental information and noise information to obtain a noise information set and an environmental information set is to extract the noise in the reference information to obtain the noise information set and extract the environment in the reference information to obtain the environmental information set. By establishing the correlation between the noise information and the environmental information, it is convenient to search for other information based on one of them later. The single-factor environment is the environment in the environmental information set for single standard item adjustment, and the multi-factor environment is the environment in the environmental information for multiple standard item adjustments. Based on the correlation, the corresponding noise can be extracted according to the single-factor environment and the multi-factor environment to obtain single-factor noise and multi-factor noise. Then, by obtaining the differences between adjacent single-factor noise and multi-factor noise and judging whether there is a linear change, a linear relationship range and a non-linear relationship range can be obtained. By obtaining the linear relationship range and the non-linear relationship range, it is convenient to deeply obtain the relationship between the environment and the noise, so as to generate more data for model training based on the linear relationship range and the non-linear relationship range later, improve the richness of the data, and facilitate use. As Figure 5 shown in (a) and (b) below, where difference 1, difference 2, and difference 3 represent different differences, that is, difference 1 is only the same as difference 1, and difference 1 is different from difference 2 and difference 3.

[0056] In the specific implementation process: When it is necessary to obtain the relationship between the specific environment and noise, and the noise monitoring value has a linear relationship with a single environmental parameter, a model is established: , where is the noise monitoring value, is the slope (influence coefficient), is the change in the environmental parameter, is the reference noise value. In the specific use process, the least squares method is used to fit the data and solve the model parameters. When the noise monitoring value has a linear relationship with multiple environmental parameters, a model is established: , where are the changes in different environmental parameters, are the influence coefficients of each parameter, is the reference noise value. In the specific use process, the least squares method is used to fit the data. When it is necessary to obtain the relationship between the specific environment and noise, and the noise monitoring value has a non-linear relationship with the environmental parameter, a suitable non-linear regression model (such as polynomial regression, logarithmic regression, exponential regression, etc.) is selected for data fitting.

[0057] As Figure 4 shown, the method for establishing the compensation model includes:

[0058] Data acquisition and processing: Based on the reference information and the target relationship, training data is derived through data derivation methods to obtain derived data. The reference information and the derived data are integrated to obtain preliminary data. The noise difference generated by adjacent environmental data in the preliminary data is obtained to get the target difference, and the target difference is marked in the preliminary data to obtain the training data;

[0059] Model selection and training: Select a deep learning model as the model matrix, and import the training data into the model matrix for the model matrix to be trained to obtain the initial model;

[0060] Model adjustment and output: Preset the verification data and the verification result, import the verification data into the initial model to obtain the result information, compare the verification result and the result information to obtain the comparison information, and adjust and optimize the initial model based on the comparison information to obtain the compensation model.

[0061] It should be noted that in the data acquisition and processing stage, data derivation is performed on the reference information according to the target relationship through the set data derivation method to enrich the quantity of data for training the model and diversify the data, so as to improve the accuracy of the model. By marking the target difference, it is convenient for the model to judge whether it is a linear or non-linear relationship. At the same time, the linear relationship range and non-linear relationship range in the target relationship can also be imported into the model for the model to learn. In the model selection and training stage, a deep learning model can select a convolutional neural network, etc. as the model matrix, and import the training data and the target relationship into the model matrix for training to obtain an initial model. In the model adjustment and output stage, preset verification data and verification results are set. The verification data is the preset environmental information, and the verification result is the compensation value of the noise sensor under this environmental information. Import the environmental information into the initial model to obtain result information, compare the result information with the verification result to obtain comparison information, and adjust and optimize the initial model according to the comparison information to obtain the compensation model.

[0062] In the specific implementation process, a deep learning model is selected as the model matrix. For example, a feedforward neural network can be selected as the model matrix to create a compensation model. First, process the acquired training data, remove incomplete, duplicate or noisy data to ensure the quality of the data, and convert the data to a unified range (such as normalization, standardization) to ensure that different features will not affect model training due to different dimensions. Import the processed training data into the model matrix for training to obtain an initial model. Batch input the training data into the model for forward propagation, calculate the gradient (the partial derivative of the loss with respect to the model parameters), execute the backpropagation algorithm, and update the model parameters. In each training round, the model will traverse all the training data and update the parameters. After training, use the verification data to evaluate the generalization ability of the model, calculate the final accuracy, and adjust and optimize the model according to the accuracy or other metrics to obtain the compensation model.

[0063] The data derivation method includes: the target relationship is a linear relationship range and a non-linear relationship range. Preset an added value, increment or decrement the added value for the environment in the linear relationship range to obtain a linear derived environment, correspondingly reduce or increase the noise information of the environment based on the relationship between the added value and the added parameter to obtain linear derived noise, increment or decrement the added value for the environment in the non-linear relationship range to obtain a non-linear derived environment, and obtain non-linear derived noise based on the non-linear derived environment and quantitative noise in cooperation with the noise sensor. Integrate the linear derived environment, linear derived noise, non-linear derived environment and non-linear derived noise to obtain derived data.

[0064] It should be noted that the added value is formulated according to the actual usage. The added value is consistent with the definition of the added parameter, but the added value is less than the added parameter. Record the multiple relationship between the added value and the added parameter. By increasing or decreasing the added value in the environment within the linear relationship range, a linear derivative environment can be obtained. Through the multiple relationship, the linear derivative noise corresponding to the linear derivative environment can be calculated. By increasing and decreasing the added value in the environment within the non-linear relationship range, a non-linear derivative environment can be obtained. Create a non-linear derivative environment and add quantitative noise in combination with a noise sensor to obtain non-linear derivative noise. At the same time, the non-linear derivative environment can also be further segmented and analyzed to extract the paragraph linear derivative environment in the non-linear derivative environment. Whether to continue the analysis is specifically determined according to the actual usage situation.

[0065] In the specific implementation process, a preset added value is set. For example, when the added parameters are temperature 1°C, humidity 1%, air pressure 10 hPa, and wind speed 1 km / h, the added value can be 0.5 times the added parameter, that is, the added value is temperature 0.5°C, humidity 0.5%, air pressure 5 hPa, and wind speed 0.5 km / h; at the same time, the added value can also be temperature 0.5°C, humidity 1%, air pressure 10 hPa, and wind speed 1 km / h, that is, a single adjustment or multiple adjustments in the corresponding linear derivative environment.

[0066] As Figure 1 shown, the dynamic analysis method includes: presetting an interval time, obtaining historical environment data by acquiring the environment data at the interval time before the real-time time point, obtaining the noise information of the historical environment data and the real-time environment data to obtain the first noise and the second noise. When the real-time environment data changes and the second noise does not change, and when the real-time environment data changes and the second noise changes, integrate the historical environment data, the real-time environment data, the first noise, and the second noise to obtain the changed data.

[0067] It should be noted that the interval time is determined according to the actual usage requirements. Through the set dynamic analysis method, it is judged whether the noise monitored in real time needs to be compensated to improve the smooth operation of the overall system and reduce the load of the system, which is beneficial for use. When the real-time environment data changes and the second noise does not change, and when the real-time environment data changes and the second noise changes, it proves that the real-time noise data monitored by the noise sensor needs to be compensated. At the same time, a threshold for the change of the real-time environment data can be set, that is, when the threshold is exceeded, the data monitored by the noise sensor needs to be compensated, and when the threshold is not exceeded, no compensation is required.

[0068] In the specific implementation process, an environmental data change threshold is set. For example, the environmental data change threshold is: temperature 15°C - 25°C, humidity: 30% - 70%, air pressure 950 hPa - 1050 hPa, wind speed: 2 km / h - 10 km / h. The preset interval time can be 10 minutes. Every 10 minutes, the environmental data 10 minutes ago and the real-time environmental data are extracted for judgment. When the real-time environmental data is within this interval, no compensation is performed.

[0069] As Figure 3 shown, the prediction matching method includes: extracting the time features and holiday features of historical noise data and real-time noise data in the repository to obtain a reference feature set. The reference feature set includes a number of reference features corresponding to the historical noise data and real-time noise data. Obtain the time feature and holiday of the target time point to get the target feature, preset a similarity value, traverse the reference feature set based on the target feature to select the reference features whose similarity to the target feature exceeds the similarity value to obtain the selected features, and select the noise data corresponding to the target feature in the repository based on the selected features to obtain the predicted noise.

[0070] It should be noted that the reference feature set includes the time features and holiday features when a single historical noise data and real-time noise data occur. For example, the time feature is 8:00 in the morning, and the holiday feature is a working day. The size of the similarity value is determined according to the actual usage. The larger the similarity value, the more accurate the predicted noise selected. Through the prediction matching method, the features in the past historical noise data can be extracted, and combined with the user's needs, the features of the future time point can be obtained for similarity matching to obtain the predicted noise of the future time point, so that the user can know in advance the possible predicted noise at the future time point, which is convenient for application in different fields.

[0071] In the specific implementation process, the similarity value can be preset to 80%. When specifically selecting the predicted noise, an optimal selection is made. The time feature and holiday feature can be more accurate. For example, the time feature is 8:10 in the morning, and the holiday feature is Wednesday, being a working day, etc., to improve the accuracy of the predicted noise of the prediction matching method.

[0072] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirits of the present invention. The scope of the present invention is defined by the appended embodiments and their equivalents.

Claims

1. A noise sensor operation monitoring system based on multivariate data fusion processing, characterized in that: The system comprises: Information collection module: obtain historical environmental data and historical noise data; Information processing module: Use the exploration method to explore the influence relationship and corresponding information between the environment and noise to obtain the target relationship and reference information, and establish a compensation model based on the target relationship and reference information; Monitoring and compensation module: acquires the monitoring data and environmental data of the noise sensor in real time to obtain real-time noise data and real-time environmental data, analyzes whether the environment and noise have changed based on the real-time environmental data through a dynamic analysis method to obtain change data, extracts the real-time noise data from the change data to obtain the noise to be corrected, and compensates the noise to be corrected based on the change data through a compensation model to obtain the corrected noise; Reference establishment module: replacing the noise to be corrected in the real-time noise data with the corrected noise to obtain the corrected real-time noise, and establishing a repository for storing the corrected real-time noise, real-time environmental data, historical environmental data and historical noise data; Matching output module: obtains predicted demand and user address information, determines the target time point based on the predicted demand, obtains predicted noise through the prediction matching method based on the target time point and the repository, and feeds back the predicted noise to the user based on the user address information; The research method includes: presetting a standard environment and quantitative noise, obtaining a reference noise by monitoring the quantitative noise in the standard environment based on a noise sensor, presetting an added parameter, adjusting the standard environment based on the added parameter to obtain an adjusted environment, obtaining a comparative noise by monitoring the quantitative noise in the adjusted environment based on the noise sensor, integrating the reference noise, the comparative noise, the standard environment and the adjusted environment to obtain reference information, and obtaining the influence relationship between the environment and the noise through a relationship acquisition method based on the reference information to obtain a target relationship; The relationship acquisition method comprises: classifying the reference information into environment and noise to obtain a noise information set and an environment information set, splitting the noise information set and the environment information set to obtain a plurality of noise information and a plurality of environment information, establishing the correlation between the noise information and the environment information, extracting the environment in which a single standard item is adjusted from the environment information set to obtain a single-factor environment, extracting the environment in which multiple standard items are adjusted from the environment information set to obtain a multi-factor environment, extracting the noise information of the single-factor environment and the multi-factor environment based on the correlation to obtain single-factor noise and multi-factor noise, sorting the single-factor environment and the multi-factor environment from small to large based on the parameters of the same standard item to obtain single-factor sorting information and multi-factor sorting information, and matching the single-factor sorting information and the multi-factor sorting information based on the correlation. The single-factor noise and multi-factor noise are sorted corresponding to the sequence information to obtain the single-factor sorting noise and multi-factor sorting noise. The single-factor difference set and the multi-factor difference set are obtained based on the difference of adjacent noises in the single-factor sorting noise and the multi-factor sorting noise. The single-factor noise range and the multi-factor noise range with the same difference in the single-factor difference set and the multi-factor difference set are extracted to obtain the single-factor range and the multi-factor range. Based on the single-factor range and the multi-factor range, the corresponding single-factor environment and the multi-factor environment are extracted in conjunction with the correlation to obtain the linear relationship range. The single-factor range and the multi-factor range in the single-factor noise and the multi-factor noise are eliminated and the corresponding single-factor environment and the multi-factor environment are extracted in conjunction with the correlation to obtain the non-linear relationship range. The linear relationship range and the non-linear relationship range are integrated to obtain the target relationship.

2. The noise sensor operation monitoring system based on multivariate data fusion processing according to claim 1 is characterized in that: The process of presetting additional parameters and adjusting the standard environment based on the added parameters to obtain an adjusted environment is as follows: splitting the standard environment to obtain several standard projects, presetting fixed parameters based on the standard projects to obtain sub-parameters, integrating the sub-parameters of all standard projects to obtain added parameters, presetting adjustment objects, the adjustment objects include adjusting a single standard project and adjusting multiple standard projects, determining the adjustment objects based on the standard projects to obtain the target objects, and performing incremental and decremental adjustments on the standard projects in the target objects based on the added parameters to obtain the adjusted environment.

3. The noise sensor operation monitoring system based on multivariate data fusion processing according to claim 1 is characterized in that: Methods for building compensation models include: Data acquisition and processing: Based on the reference information and target relationship, the training data is derived through the data derivation method to obtain the derived data, the reference information and the derived data are integrated to obtain the preliminary data, the noise difference generated by the adjacent environmental data in the preliminary data is obtained to obtain the target difference, and the target difference is marked in the preliminary data to obtain the training data; Model selection and training: Select a deep learning model as the model matrix, import the training data into the model matrix for training to obtain the initial model; Model adjustment and output: preset verification data and verification results, import the verification data into the initial model to obtain result information, compare the verification results and result information to obtain comparison information, and adjust and optimize the initial model based on the comparison information to obtain a compensation model.

4. The noise sensor operation monitoring system based on multivariate data fusion processing according to claim 3 is characterized in that: The data derivation method includes: the target relationship is a linear relationship range and a nonlinear relationship range, an added value is preset, the added value is increased or decreased for the environment in the linear relationship range to obtain a linear derived environment, based on the relationship between the added value and the added parameter, the noise information of the environment is correspondingly reduced or increased to obtain a linear derived noise, the added value is increased or decreased for the environment in the nonlinear relationship range to obtain a nonlinear derived environment, nonlinear derived noise is obtained based on the nonlinear derived environment and quantitative noise in combination with a noise sensor, and the linear derived environment, linear derived noise, nonlinear derived environment and nonlinear derived noise are integrated to obtain derived data.

5. The noise sensor operation monitoring system based on multivariate data fusion processing according to claim 1 is characterized in that: The dynamic analysis method includes: presetting an interval time, obtaining environmental data of the interval time before the real-time time point to obtain past environmental data, obtaining noise information of the past environmental data and the real-time environmental data to obtain a first noise and a second noise, and when the real-time environmental data changes and the second noise does not change and when the real-time environmental data changes and the second noise changes, integrating the past environmental data, the real-time environmental data, the first noise and the second noise to obtain change data.

6. The noise sensor operation monitoring system based on multivariate data fusion processing according to claim 1 is characterized in that: The prediction and matching method comprises: extracting time features and holiday features of historical noise data and real-time noise data in a storage repository to obtain a reference feature set, the reference feature set comprising a plurality of reference features corresponding to the historical noise data and the real-time noise data, obtaining time features and holidays at a target time point to obtain a target feature, presetting a similarity value, traversing the reference feature set based on the target feature to select a reference feature whose similarity with the target feature exceeds the similarity value to obtain a selected feature, and selecting noise data corresponding to the target feature in the storage repository based on the selected feature to obtain predicted noise.

7. A noise sensor operation monitoring method based on multivariate data fusion processing, characterized in that: A noise sensor operation monitoring system based on multivariate data fusion processing as described in any one of claims 1 to 6 is used.

Images