Wireless tilt angle sensor adaptive acquisition real-time noise reduction method and system

Abstract

The invention discloses a self-adaptive acquisition real-time noise reduction method for a wireless tilt angle sensor, which comprises the following steps: S1, judging the working state of the wireless tilt angle sensor on the basis of analysis on tilt angle monitoring data acquired by the wireless tilt angle sensor, wherein the working state comprises a temporary disturbance state caused by the fact that the wireless tilt angle sensor passes by a train, data instability caused by damage of the wireless tilt angle sensor and other accidental factors or a normal non-vibration working state of the wireless tilt angle sensor; s2, according to the judgment result that the tilt angle sensor is in the non-vibration normal working state in the S1, sensor collection data noise reduction based on the standard deviation is carried out, the sensor collection data noise reduction based on the standard deviation is achieved based on a data noise reduction model, and the data noise reduction model is constructed based on a standard deviation comparison method. The invention further discloses a corresponding evaluation system, electronic equipment and a computer readable storage medium, on one hand, the working (vibration) state of the sensor can be analyzed and judged through data collected by the sensor, vibration interference abnormal data is abandoned during the vibration working state of the equipment, and the collection frequency is adjusted in a self-adaptive mode; and secondly, a data noise reduction model can be constructed based on a standard deviation comparison method.

Description

Technical Field

[0001] The invention relates to the technical field of railway and sensor data acquisition and noise reduction, and in particular to a method and system for self-adaptive acquisition and real-time noise reduction of a wireless tilt sensor. Background Art

[0002] With the rapid development of high-speed railways, in order to meet the needs of large space and unique building functions, high-speed railway passenger station buildings, waiting halls, and platform canopies mostly use large-volume, large-span, complex structural systems, grids, trusses, string and other steel structures. On the one hand, the main structural components are designed for a long life and cannot be replaced for a long time. On the other hand, most areas, especially coastal areas, are also affected by complex environments. Steel structures are prone to damage and various deformations, and their safety issues are particularly prominent. In view of the above two reasons, it is very necessary to implement sensor-based online health monitoring of the main structure.

[0003] However, the existing technology for implementing sensor-based online health monitoring technology solutions for structural entities has three technical defects, which can no longer meet the urgent needs of the rapid development of high-speed railways for all-round and efficient management of construction and operation safety. Specifically, it is reflected in:

[0004] 1. The current application and promotion of railway platform rain shelter structure health monitoring is not ideal. From the perspective of system equipment, it has long been constrained by the complex installation of monitoring equipment, the large number of cables for wired transmission, and the high cost of inspection and maintenance;

[0005] 2. The noise in the train passing vibration environment is large, the signal-to-noise ratio of the equipment data is not high, the stability is poor, the actual dynamic monitoring data has a low signal-to-noise ratio, and the false alarm rate is high, which cannot dynamically and accurately reflect the real structural status;

[0006] 3. The system’s adaptability and intelligence level is insufficient. Summary of the invention

[0007] The purpose of the present invention is to propose a simple, feasible and effective wireless tilt sensor adaptive acquisition real-time noise reduction method and system for the inclination monitoring of the steel structure of the high-speed railway platform canopy, based on the complex environment of vibration interference caused by the passage of high-speed railway trains, in view of the requirements of wireless transmission, low power consumption, high signal-to-noise ratio and reduction of false alarm rate in the inclination monitoring scenario of the high-speed railway platform canopy. On the one hand, it can analyze and judge the working (vibration) state of the sensor itself through the data collected by the sensor, so that the equipment can discard abnormal data of vibration interference during the vibration working state and adaptively adjust the acquisition frequency; on the other hand, it can construct a data noise reduction model based on the standard deviation comparison method.

[0008] The first aspect of the present invention is to provide a method for adaptively collecting and reducing noise in real time for a wireless tilt sensor, comprising:

[0009] S1, judging the working state of the wireless inclination sensor itself based on the analysis of the inclination monitoring data collected by the wireless inclination sensor, wherein the working state includes that the wireless inclination sensor is in a temporary disturbance state caused by the passing of a train, the wireless inclination sensor itself is damaged and the data is unstable due to other accidental factors, or the wireless inclination sensor is in a normal non-vibration working state;

[0010] S2, according to the determination result that the tilt sensor in S1 is in a non-vibrating normal working state, performing standard deviation-based sensor data denoising, wherein the standard deviation-based sensor data denoising is implemented based on a data denoising model, and the data denoising model is constructed based on a standard deviation comparison method.

[0011] Preferably, the S1 comprises:

[0012] S11, acquiring monitoring data of a wireless inclination sensor and an acoustic signal acquisition sensor, wherein the wireless inclination sensor is used to acquire and collect inclination monitoring data of a corresponding position in real time, and the acoustic signal acquisition sensor is used to monitor acoustic signals in an environment where the wireless inclination sensor is located;

[0013] S12, analyzing the high-frequency vibration interference characteristics of the inclination monitoring data based on the sensor vibration working status data analysis and discrimination method of mean comparison to obtain a first analysis result for the working status of the wireless inclination sensor itself; the first analysis result includes a first judgment result and a first processing behavior.

[0014] Preferably, the implementation process of S12 includes:

[0015] (1) calculating an average value of single-collection sample data according to a single-collection data sample of the wireless tilt sensor as a reference average value benchmark;

[0016] (2) determining a first analysis result based on a comparison between the reference average value benchmark and the data variable collected once; the first determination result includes that the tilt sensor is in a non-vibration normal working state or that the tilt sensor may be in a vibration abnormal working state; the first processing behavior includes directly entering S2 when the tilt sensor is in a non-vibration normal working state or waking up the acoustic signal collection sensor to collect the acoustic signal in the environment in real time when the tilt sensor may be in a vibration abnormal working state;

[0017] S13, processing and analyzing the sound data characteristics of the acoustic signal in the environment where the acoustic sensor is located based on the sensor vibration working state data analysis and discrimination method optimized by acoustic signals to obtain a second analysis result of the working state of the wireless tilt sensor itself, wherein the sound data characteristics include decibels and pitch;

[0018] S14, based on the first analysis result and the second analysis result, accurately judge the working state of the wireless inclination sensor, effectively distinguish the temporary disturbance caused by the passing of the train and the data instability caused by the damage of the sensor itself and other accidental factors, intelligently reduce the noise of the temporary disturbance caused by the passing of the train through adaptive state adjustment of the sensor equipment, and carry out targeted processing for the unstable data in other abnormal situations, so as to improve the robustness and accuracy of the sensor working state judgment and the entire measurement system.

[0019] Preferably, the implementation process of S13 includes:

[0020] (1) performing data processing on acoustic signals in the environment, wherein the data processing includes filtering and feature extraction;

[0021] (2) Analyzing and judging the working status of the wireless tilt sensor itself based on the sound data characteristics to obtain a second analysis result; the second analysis result includes determining whether a train is passing by based on decibel threshold comparison, tone pattern matching analysis, and duration matching analysis.

[0022] Preferably, the process of S14 includes:

[0023] (1) If the inclination sensor data |μ0-x i |>2σ, and the acoustic data analysis result shows that a train has passed, the sensor is in a temporary disturbance state caused by the train passing, and intelligent noise reduction processing is required at this time: remove the data sample A0 collected this time, and collect new sample data again according to the collection frequency interval for processing, and repeat the operation; where μ0 is the average value of the single collection data sample A0, x i is the data variable collected once, σ is the nominal measurement accuracy of the wireless tilt sensor;

[0024] (2) If the inclination sensor data |μ0-x i |>2σ, and the acoustic data analysis result shows that no train has passed, the sensor is in an unstable data working state caused by its own damage and other accidental factors. At this time, targeted processing is required in a timely manner.

[0025] Preferably, S2 includes:

[0026] S21, constructing the data denoising model based on the discrete characteristics of the data collected by the front end of the tilt sensor, discrete data variable analysis and Kalman filtering algorithm, and calculating based on the data denoising model; the data denoising model is used to implement denoising of the sensor collected data based on standard deviation;

[0027] S22, calculating the standard deviation reference value of the initial reference sample based on the data denoising model; S22 is specifically implemented as follows:

[0028] The initial reference standard deviation benchmark value is calculated based on the single data sample A0 collected in the non-vibration working state of the tilt sensor. Assuming that the average value of the single data sample A0 is μ0, the calculation formula for the initial reference sample standard deviation reference value is as follows:

[0029]

[0030] Among them, σ0 is the standard deviation reference value of the initial data sample A0, x i is the data variable collected once, μ0 is the average value of the data sample A0 collected once, and n is the number of sample data collected once;

[0031] S23, before the tilt sensor outputs data, continuously collect a group of collected data samples A1 of the tilt sensor in a non-vibration working state at a certain time T, and calculate an average value σ1 of the single collected data samples A1 corresponding to the time T;

[0032] S24, after comparing and analyzing the average value σ1 of the single-time collected data sample A1 with the standard deviation reference value σ0 of the initial data sample A0, the output data of the inclination sensor is determined according to the comparison and analysis result.

[0033] Preferably, the S24 includes:

[0034] (1) If σ1≤σ0, the average value of the single-collected data sample A1 is represented as μ1;

[0035] (2) If σ1>σ0, then collect a set of single-collection data samples A2 again, and compare the average value σ2 of the single-collection data samples A2 with the standard deviation reference value σ0 of the initial data sample A0:

[0036] ① If σ2≤σ0, the average value of the single-time collected data sample A2 is expressed as μ1;

[0037] ② If σ2>σ0, the average value of a group of data samples with smaller standard deviations σ1 and σ2 of single-time collected data samples A1 and A2 is represented as μ1;

[0038] (3) The current output value of the sensor P1 = (a·μ0+b·μ1) / (a+b); where a and b are weight coefficients, which can be adjusted according to the relative change value of μ0 and μ1 and the relative size of the sensor accuracy or warning value to improve the data signal-to-noise ratio.

[0039] The second aspect of the present invention also provides a wireless tilt sensor adaptive acquisition real-time noise reduction system, comprising:

[0040] A sensor working state determination module (101) is used to determine the working state of the wireless inclination sensor itself based on the analysis of the inclination monitoring data collected by the wireless inclination sensor, wherein the working state includes the wireless inclination sensor being in a temporary disturbance state caused by a train passing by, the wireless inclination sensor being damaged and data being unstable due to other accidental factors, or the wireless inclination sensor being in a normal non-vibration working state;

[0041] A real-time noise reduction module (102) is used to perform standard deviation-based noise reduction of sensor collected data according to a determination result that the tilt sensor is in a non-vibration normal working state, wherein the standard deviation-based noise reduction of sensor collected data is implemented based on a data noise reduction model, and the data noise reduction model is constructed based on a standard deviation comparison method.

[0042] A third aspect of the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores a plurality of instructions, and the processor is configured to read the instructions and execute the method described in the first aspect.

[0043] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a plurality of instructions, and the plurality of instructions can be read by a processor to execute the method described in the first aspect.

[0044] Beneficial effects of the method and system of the present invention:

[0045] (1) Effectively improve the signal-to-noise ratio of data collected at the front end of the equipment, reduce or even eliminate false alarms of system sensor data distortion, and provide important technical support for subsequent monitoring data mining, fusion analysis, and engineering solution decision-making.

[0046] (2) The method and system of the present invention can also be expanded and widely used in the fields of pattern recognition, classification and data mining in the engineering industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the related technologies, the drawings required for use in the specific embodiments or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 It is a flow chart of a method for adaptive acquisition and real-time noise reduction of a wireless tilt sensor according to an embodiment of the present invention;

[0049] Figure 2 This is a flow chart of step S1 of the method for adaptive acquisition and real-time noise reduction of a wireless tilt sensor provided according to an embodiment of the present invention;

[0050] Figure 3 This is a flow chart of step S2 of the method for adaptive acquisition and real-time noise reduction of a wireless tilt sensor provided in an embodiment of the present invention;

[0051] Figure 4 This is an architecture diagram of a wireless tilt sensor adaptive acquisition and real-time noise reduction system according to an embodiment of the present invention;

[0052] Figure 5 A structural diagram of an electronic device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0055] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0056] Embodiment 1

[0057] like Figure 1 As shown, this embodiment provides a method for adaptively collecting and reducing noise in real time for a wireless tilt sensor, comprising:

[0058] S1, judging the working state of the wireless inclination sensor itself based on the analysis of the inclination monitoring data collected by the wireless inclination sensor, wherein the working state includes that the wireless inclination sensor is in a temporary disturbance state caused by the passing of a train, the wireless inclination sensor itself is damaged and the data is unstable due to other accidental factors, or the wireless inclination sensor is in a normal non-vibration working state;

[0059] like Figure 2 As shown, as a preferred embodiment, the S1 includes:

[0060] S11, acquiring monitoring data of a wireless inclination sensor and an acoustic signal acquisition sensor, wherein the wireless inclination sensor is used to acquire and collect inclination monitoring data of a corresponding position in real time, and the acoustic signal acquisition sensor is used to monitor acoustic signals in an environment where the wireless inclination sensor is located;

[0061] S12, analyzing the high-frequency vibration interference characteristics of the tilt monitoring data based on the sensor vibration working state data analysis and discrimination method based on mean comparison to obtain a first analysis result of the working state of the wireless tilt sensor itself; the first analysis result includes a first determination result and a first processing behavior;

[0062] As a preferred implementation, the implementation process of S12 includes:

[0063] (1) calculating an average value of single-collection sample data according to a single-collection data sample of the wireless tilt sensor as a reference average value benchmark;

[0064] In the embodiment, it is assumed that the nominal measurement accuracy of the wireless tilt sensor is σ, which is a known parameter; the acquisition frequency of the wireless tilt sensor is f; the single acquisition data sample is A0, and the single acquisition data sample A0 average value is μ0, then the calculation formula for the single acquisition sample data average value is as follows:

[0065]

[0066] Among them, μ0 is the average value of single-time collected data sample A0, x i is the data variable collected once, and n is the number of sample data collected once.

[0067] (2) determining a first analysis result based on a comparison between the reference average value benchmark and the data variable collected once; the first determination result includes that the tilt sensor is in a non-vibration normal working state or that the tilt sensor may be in a vibration abnormal working state; the first processing behavior includes directly entering S2 when the tilt sensor is in a non-vibration normal working state or waking up the acoustic signal collection sensor to collect the acoustic signal in the environment in real time when the tilt sensor may be in a vibration abnormal working state;

[0068] In this embodiment, the specific implementation is: according to the single-collection sample data average value μ0 of the single-collection data sample A0 of the device sensor and the single-collection data variable x i Comparative analysis of (i=1,2,…,n):

[0069] (1) If A0 is "null" or an empty value, re-collect sample data;

[0070] (2) If A0 is not "null" or a non-empty value, then for

[0071] ①If |μ0-x i |≤2σ, the inclination sensor is considered to be in a non-vibration normal working state, that is, directly proceed to the next step (collection sample data noise reduction process);

[0072] ②If |μ0-x i |>2σ, it is considered that the tilt sensor may be in an abnormal vibration working state. At this time, the acoustic signal acquisition sensor is awakened to collect acoustic data in real time, including decibels and pitch.

[0073] S13, processing and analyzing the sound data characteristics of the acoustic signal in the environment where the acoustic sensor is located based on the sensor vibration working state data analysis and discrimination method optimized by acoustic signals to obtain a second analysis result of the working state of the wireless tilt sensor itself, wherein the sound data characteristics include decibels and pitch;

[0074] As a preferred implementation, the implementation process of S13 includes:

[0075] (1) performing data processing on acoustic signals in the environment, wherein the data processing includes filtering and feature extraction;

[0076] Filtering: Apply digital filters to reduce the impact of background noise and other interfering signals and highlight the characteristics of the train sound;

[0077] Feature extraction: Extract key features from the filtered acoustic signal in the environment as the sound data features. The key features include decibel peak, duration, and frequency components, etc., for analysis and judgment.

[0078] (2) analyzing and judging the working state of the wireless tilt sensor itself based on the sound data characteristics to obtain a second analysis result; the second analysis result includes determining whether a train is passing by based on decibel threshold comparison, tone pattern matching analysis, and duration matching analysis;

[0079] Decibel threshold comparison: According to the background noise baseline characteristics of the high-speed railway monitoring scene, taking into account the sensitivity impact, the decibel threshold is set. When the decibel peak exceeds the threshold, the tone pattern matching analysis and duration matching analysis are triggered; if the decibel peak does not exceed the threshold, it is judged that no train is passing;

[0080] Tone pattern matching analysis: Set the tone pattern matching threshold, extract the frequency characteristics such as peak frequency, frequency bandwidth, and frequency change rate in the frequency components of the acoustic sample, and analyze the matching degree with the unique tone pattern when the train passes. When the matching degree exceeds the threshold, it is judged that the probability of the train passing is high; otherwise, it is judged to be other noise other than the train or no train passing;

[0081] Duration matching analysis: Set the duration matching threshold. When both the decibel threshold and the tone pattern matching threshold are exceeded, obtain the duration of the decibel increase and the tone pattern matching state, and analyze their consistency with the time when the train passes. If the consistency exceeds the threshold, it is finally judged that a train has passed, otherwise it is judged that no train has passed.

[0082] S14, based on the first analysis result and the second analysis result, accurately judge the working state of the wireless inclination sensor, effectively distinguish the temporary disturbance caused by the passing of the train and the data instability caused by the damage of the sensor itself and other accidental factors, intelligently reduce the noise of the temporary disturbance caused by the passing of the train through adaptive state adjustment of the sensor equipment, and carry out targeted processing for the unstable data in other abnormal situations, so as to improve the robustness and accuracy of the sensor working state judgment and the entire measurement system.

[0083] As a preferred implementation, the implementation of S14 integrates the analysis results of the tilt sensor data and the acoustic data, and finally determines that the sensor is in a temporary disturbance state caused by the passing of a train, or the sensor is in an unstable data working state caused by its own damage and other accidental factors. The process of S14 includes:

[0084] (1) If the inclination sensor data |μ0-x i|>2σ, and the acoustic data analysis result shows that a train has passed, the sensor is in a temporary disturbance state caused by the train passing. At this time, intelligent noise reduction processing is required: the collected data sample A0 is eliminated, and new sample data is collected again according to the collection frequency interval for processing, and the operation is repeated;

[0085] (2) If the inclination sensor data |μ0-x i |>2σ, and the acoustic data analysis result shows that no train has passed, the sensor is in an unstable data working state caused by its own damage and other accidental factors. At this time, targeted processing is required in a timely manner.

[0086] like Figure 3 As shown, S2, according to the judgment result that the inclination sensor in S1 is in a non-vibrating normal working state, performs standard deviation-based sensor acquisition data denoising, and the standard deviation-based sensor acquisition data denoising is implemented based on a data denoising model, and the data denoising model is constructed based on a standard deviation comparison method.

[0087] As a preferred embodiment, the S2 includes:

[0088] S21, based on the discrete characteristics of the data collected by the front end of the tilt sensor, the discrete data variable analysis and Kalman filtering algorithm are used to construct the data denoising model, and the calculation is based on the data denoising model; the data denoising model is used to implement the sensor data denoising based on the standard deviation, which is a simple and efficient denoising data model, and can improve the signal-to-noise ratio of the data collected by the front end of the device. In probability statistics, the standard deviation can reflect the degree of discreteness of a data set and can be used to evaluate the possible changes or fluctuations in the data. The larger the standard deviation, the wider the range of data fluctuations, and vice versa, the more stable the data is. It is an important indicator of accuracy.

[0089] S22, calculating a standard deviation reference value of an initial reference sample based on the data denoising model;

[0090] In this embodiment, the S22 is specifically implemented as follows:

[0091] The initial reference standard deviation benchmark value is calculated based on the single data sample A0 collected in the non-vibration working state of the tilt sensor. Assuming that the average value of the single data sample A0 is μ0, the calculation formula for the initial reference sample standard deviation reference value is as follows:

[0092]

[0093] Among them, σ0 is the standard deviation reference value of the initial data sample A0, x i is the data variable collected once, μ0 is the average value of the data sample A0 collected once, and n is the number of sample data collected once.

[0094] S23, before the tilt sensor outputs data, continuously collect a group of collected data samples A1 of the tilt sensor in a non-vibration working state at a certain time T, and calculate an average value σ1 of the single collected data samples A1 corresponding to the time T;

[0095] S24, after comparing and analyzing the average value σ1 of the single-time collected data sample A1 with the standard deviation reference value σ0 of the initial data sample A0, determining the output data of the tilt sensor according to the comparison and analysis result, including:

[0096] (1) If σ1≤σ0, the average value of the single-collected data sample A1 is represented as μ1;

[0097] (2) If σ1>σ0, then a new set of single-collection data samples A2 is collected, and the average value σ2 of the single-collection data samples A2 is compared with the standard deviation reference value σ0 of the initial data sample A0:

[0098] ① If σ2≤σ0, the average value of the single-time collected data sample A2 is expressed as μ1;

[0099] ② If σ2>σ0, the average value of a group of data samples with smaller standard deviations σ1 and σ2 of single-time collected data samples A1 and A2 is represented as μ1;

[0100] (3) The current output value of the sensor P1 = (a·μ0+b·μ1) / (a+b); where a and b are weight coefficients, which can be adjusted according to the relative change value of μ0 and μ1 and the relative size of the sensor accuracy or warning value to improve the data signal-to-noise ratio.

[0101] Embodiment 2

[0102] like Figure 4 As shown, this embodiment provides a wireless tilt sensor adaptive acquisition real-time noise reduction system, including:

[0103] The sensor working state determination module 101 is used to determine the working state of the wireless inclination sensor itself based on the analysis of the inclination monitoring data collected by the wireless inclination sensor, wherein the working state includes that the wireless inclination sensor is in a temporary disturbance state caused by the passing of a train, the wireless inclination sensor is damaged and the data is unstable due to other accidental factors, or the wireless inclination sensor is in a normal non-vibration working state;

[0104] The real-time noise reduction module 102 is used to perform standard deviation-based sensor data noise reduction according to the determination result that the tilt sensor is in a non-vibration normal working state, wherein the standard deviation-based sensor data noise reduction is implemented based on a data noise reduction model, and the data noise reduction model is constructed based on a standard deviation comparison method.

[0105] The present invention also provides a memory storing a plurality of instructions, wherein the instructions are used to implement the method as in the first embodiment.

[0106] like Figure 5 As shown, the present invention also provides an electronic device, including a processor 301 and a memory 302 connected to the processor 301, the memory 302 stores a plurality of instructions, and the instructions can be loaded and executed by the processor so that the processor can execute the method as in the first embodiment.

[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for adaptively collecting and reducing noise in real time for a wireless tilt sensor, characterized in that: include: S1, judging the working state of the wireless inclination sensor itself based on the analysis of the inclination monitoring data collected by the wireless inclination sensor, wherein the working state includes that the wireless inclination sensor is in a temporary disturbance state caused by the passing of a train, the wireless inclination sensor itself is damaged and the data is unstable due to other accidental factors, or the wireless inclination sensor is in a normal non-vibration working state; S2, according to the determination result that the tilt sensor in S1 is in a non-vibrating normal working state, performing standard deviation-based sensor data denoising, wherein the standard deviation-based sensor data denoising is implemented based on a data denoising model, and the data denoising model is constructed based on a standard deviation comparison method.

2. A wireless tilt sensor adaptive acquisition real-time noise reduction method according to claim 1, characterized in that: The S1 includes: S11, acquiring monitoring data of a wireless inclination sensor and an acoustic signal acquisition sensor, wherein the wireless inclination sensor is used to acquire and collect inclination monitoring data of a corresponding position in real time, and the acoustic signal acquisition sensor is used to monitor acoustic signals in an environment where the wireless inclination sensor is located; S12, analyzing the high-frequency vibration interference characteristics of the inclination monitoring data based on the sensor vibration working status data analysis and discrimination method of mean comparison to obtain a first analysis result for the working status of the wireless inclination sensor itself; the first analysis result includes a first judgment result and a first processing behavior.

3. A wireless tilt sensor adaptive acquisition real-time noise reduction method according to claim 2, characterized in that: The implementation process of S12 includes: (1) calculating the average value of the single-collected sample data according to the single-collected data sample of the wireless tilt sensor as a reference average value benchmark; (2) determining a first analysis result based on a comparison between the reference average value benchmark and the data variable collected once; the first determination result includes that the tilt sensor is in a non-vibration normal working state or that the tilt sensor may be in a vibration abnormal working state; the first processing behavior includes directly entering S2 when the tilt sensor is in a non-vibration normal working state or waking up the acoustic signal collection sensor to collect the acoustic signal in the environment in real time when the tilt sensor may be in a vibration abnormal working state; S13, processing and analyzing the sound data characteristics of the acoustic signal in the environment where the acoustic sensor is located based on the sensor vibration working state data analysis and discrimination method optimized by acoustic signals to obtain a second analysis result of the working state of the wireless tilt sensor itself, wherein the sound data characteristics include decibels and pitch; S14, based on the first analysis result and the second analysis result, accurately judge the working state of the wireless inclination sensor, effectively distinguish the temporary disturbance caused by the passing of the train and the data instability caused by the damage of the sensor itself and other accidental factors, intelligently reduce the noise of the temporary disturbance caused by the passing of the train through adaptive state adjustment of the sensor equipment, and carry out targeted processing for the unstable data in other abnormal situations, so as to improve the robustness and accuracy of the sensor working state judgment and the entire measurement system.

4. A wireless tilt sensor adaptive acquisition real-time noise reduction method according to claim 3, characterized in that: The implementation process of S13 includes: (1) performing data processing on acoustic signals in the environment, wherein the data processing includes filtering and feature extraction; (2) Analyzing and judging the working status of the wireless tilt sensor itself based on the sound data characteristics to obtain a second analysis result; the second analysis result includes determining whether a train is passing by based on decibel threshold comparison, tone pattern matching analysis, and duration matching analysis.

5. A wireless tilt sensor adaptive acquisition real-time noise reduction method according to claim 4, characterized in that: The process of S14 includes: (1) If the inclination sensor data |μ0-x i |>2σ, and the acoustic data analysis result shows that a train has passed, the sensor is in a temporary disturbance state caused by the train passing, and intelligent noise reduction processing is required at this time: remove the data sample A0 collected this time, and collect new sample data again according to the collection frequency interval for processing, and repeat the operation; where μ0 is the average value of the single collection data sample A0, x i is the data variable collected once, σ is the nominal measurement accuracy of the wireless tilt sensor; (2) If the inclination sensor data |μ0-x i |>2σ, and the acoustic data analysis result shows that no train has passed, the sensor is in an unstable data working state caused by its own damage and other accidental factors. At this time, targeted processing is required in a timely manner.

6. A wireless tilt sensor adaptive acquisition real-time noise reduction method according to claim 5, characterized in that: The S2 includes: S21, constructing the data denoising model based on the discrete characteristics of the data collected by the front end of the tilt sensor, discrete data variable analysis and Kalman filtering algorithm, and calculating based on the data denoising model; the data denoising model is used to implement denoising of the sensor collected data based on standard deviation; S22, calculating the standard deviation reference value of the initial reference sample based on the data denoising model; S22 is specifically implemented as follows: The initial reference standard deviation benchmark value is calculated based on the single data sample A0 collected in the non-vibration working state of the tilt sensor. Assuming that the average value of the single data sample A0 is μ0, the calculation formula for the initial reference sample standard deviation reference value is as follows: Among them, σ0 is the standard deviation reference value of the initial data sample A0, x i is the data variable collected once, μ0 is the average value of the data sample A0 collected once, and n is the number of sample data collected once; S23, before the tilt sensor outputs data, continuously collect a group of collected data samples A1 of the tilt sensor in a non-vibration working state at a certain time T, and calculate an average value σ1 of the single collected data samples A1 corresponding to the time T; S24, after comparing and analyzing the average value σ1 of the single-time collected data sample A1 with the standard deviation reference value σ0 of the initial data sample A0, the output data of the inclination sensor is determined according to the comparison and analysis result.

7. A wireless tilt sensor adaptive acquisition real-time noise reduction method according to claim 6, characterized in that: The S24 includes: (1) If σ1≤σ0, the average value of the single-collected data sample A1 is represented as μ1; (2) If σ1>σ0, then a new set of single-collection data samples A2 is collected, and the average value σ2 of the single-collection data samples A2 is compared with the standard deviation reference value σ0 of the initial data sample A0: ① If σ2≤σ0, the average value of the single-time collected data sample A2 is expressed as μ1; ② If σ2>σ0, the average value of a group of data samples with smaller standard deviations σ1 and σ2 of single-time collected data samples A1 and A2 is represented as μ1; (3) The current output value of the sensor P1 = (a·μ0+b·μ1) / (a+b); where a and b are weight coefficients, which can be adjusted according to the relative change value of μ0 and μ1 and the relative size of the sensor accuracy or warning value to improve the data signal-to-noise ratio.

8. A wireless tilt sensor adaptive acquisition real-time noise reduction system, used to implement any method of claims 1-7, characterized in that: include: A sensor working state determination module (101) is used to determine the working state of the wireless inclination sensor itself based on the analysis of the inclination monitoring data collected by the wireless inclination sensor, wherein the working state includes the wireless inclination sensor being in a temporary disturbance state caused by a train passing by, the wireless inclination sensor being damaged and data being unstable due to other accidental factors, or the wireless inclination sensor being in a normal non-vibration working state; A real-time noise reduction module (102) is used to perform standard deviation-based noise reduction of sensor collected data according to a determination result that the tilt sensor is in a non-vibration normal working state, wherein the standard deviation-based noise reduction of sensor collected data is implemented based on a data noise reduction model, and the data noise reduction model is constructed based on a standard deviation comparison method.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a plurality of instructions, and the processor is used to read the instructions and execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the plurality of instructions can be read by a processor to execute the method according to any one of claims 1 to 7.

Images