Noise reduction device and noise reduction method for rock burst sensor

Abstract

The invention provides a rock burst sensor noise reduction device and a noise reduction method, the rock burst sensor noise reduction device comprises a sensor, a sensor signal line, an acquisition instrument, an acquisition instrument data line and a grounding signal line, the sensor is used for acquiring a vibration source signal in a mine environment; the acquisition instrument is connected with the sensor through a sensor signal line and is used for carrying out noise reduction processing on the vibration source signal to obtain a vibration signal after noise reduction; the acquisition instrument data line is connected with the acquisition instrument and is used for transmitting the vibration signals after noise reduction; one end of the grounding signal line is connected with the acquisition instrument, and the other end is connected with the ground for leading the noise signal into the ground. Therefore, noise reduction processing is carried out through the rock burst sensor noise reduction device and the target noise data model in the rock burst sensor noise reduction device, the noise reduction effect is achieved in various mine environments, the application range is wide, and therefore normal use of rock burst sensor collection equipment in a mine is guaranteed; and normal safety production of mine enterprises is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of noise reduction, and in particular to a noise reduction device and a noise reduction method for an impact ground pressure sensor. Background Art

[0002] Impact ground pressure sensor is a detection device that can sense the vibration information being measured and convert the sensed information into electrical signals or other required forms of information output according to certain rules to meet the requirements of information transmission, processing, storage, display, recording and control. At present, with the development of intelligent technology in all walks of life, sensors have been widely used.

[0003] At present, with the advancement of the prevention and control of rock burst in mines, the rock burst sensor can be used to obtain signals to achieve positioning and energy calculation, and then actively apply prevention and control measures to effectively avoid rock burst accidents. However, in the actual process, the strong power equipment running in the mining environment brings serious interference to the rock burst sensor collection, such as 50Hz power frequency interference and human interference caused by manual operations in the surrounding environment. The above interference can cause serious distortion of the signal and make it unusable. Based on this, it is necessary to perform noise reduction processing on the collected signals to ensure the normal use of rock burst sensor collection equipment in mines and ensure the normal safety production of mining enterprises.

[0004] In the prior art, filtering can be performed through software, but the above prior art can have a certain effect in situations where the noise interference is small or the interference environment is not serious, but it is difficult to achieve the noise reduction effect in relatively harsh situations, and the scope of application is relatively small. Summary of the invention

[0005] The present invention provides a noise reduction device and a noise reduction method for an impact ground pressure sensor, which are used to solve the technical problems arising in the above-mentioned related technologies.

[0006] To this end, the present invention proposes a rock burst sensor noise reduction device, which performs noise reduction processing on the vibration source signal through the rock burst sensor noise reduction device and the target noise data model in the rock burst sensor noise reduction device, so that the vibration source signal can be noise reduced through hardware and the target noise data model, and has a noise reduction effect in various mine environments and a wide range of applications, thereby ensuring the normal use of the rock burst sensor acquisition equipment in the mine and ensuring the normal safe production of the mining enterprise.

[0007] Another object of the present invention is to provide a noise reduction method based on the impact ground pressure sensor noise reduction device.

[0008] To achieve the above-mentioned purpose, the present invention provides a noise reduction device for an impact ground pressure sensor, comprising a sensor, a sensor signal line, a collector, a collector data line and a ground signal line, wherein:

[0009] The sensor is used to collect vibration source signals in a mine environment;

[0010] The collector is connected to the sensor via the sensor signal line, and is used to perform noise reduction processing on the vibration source signal to obtain a vibration signal after noise reduction;

[0011] The data line of the collector is connected to the collector and is used to transmit the vibration signal after noise reduction;

[0012] One end of the ground signal line is connected to the collector, and the other end is connected to the ground, so as to guide the noise signal into the ground.

[0013] The rock burst sensor noise reduction device of the embodiment of the present invention may also have the following additional technical features:

[0014] In one embodiment of the present invention, the sensor includes a sensor connector, a connector isolation layer, a sensor metal housing, a sensor metal housing isolation layer, a sensor transmitter, a sensor signal processing circuit and a sensor grounding point, wherein:

[0015] The sensor connector is a connecting joint, which is fixed by the connecting joint and other threaded rods;

[0016] The connector isolation layer is fixed by radial screws for axial rotation;

[0017] The sensor transmitter is a moving coil magnetoelectric sensor, which converts the vibration source signal into a voltage signal through electromagnetic induction;

[0018] The sensor grounding point is the shielding layer of the sensor signal processing circuit and is connected to the power ground, and the shielding layer is connected to the metal housing of the sensor;

[0019] The sensor metal housing isolation layer is the outer layer of the sensor metal housing.

[0020] In one embodiment of the present invention, the sensor signal line includes a sensor isolation protection layer, wherein:

[0021] The sensor isolation protection layer is connected to the sensor metal shell to form a signal protection layer.

[0022] In one embodiment of the present invention, the collector includes a collector grounding point, a collector front-end signal processing circuit, a collector central processing unit circuit, a collector signal transmission circuit module, a collector metal shell isolation layer and a collector isolation protection layer, wherein:

[0023] The collector grounding point is connected to the power ground of the collector front-end signal processing circuit, the collector central processing unit circuit and the collector signal transmission circuit module;

[0024] The collector grounding point is connected to the collector metal shell isolation layer, and the collector metal shell isolation layer is connected to the grounding signal line;

[0025] The front-end signal processing circuit of the acquisition instrument is a differential amplifier and filter circuit for the instrument, which is used to isolate and shield the common ground interference signal and filter out the interference signal;

[0026] The collector central processing unit circuit is used to perform noise reduction processing on the vibration source signal to obtain a vibration signal after noise reduction;

[0027] The collector signal transmission circuit module is connected to the collector data line and transmits data through the collector data line;

[0028] The collector metal shell isolation layer is connected to the sensor isolation protection layer to form a closed protection for the internal circuit structure of the collector;

[0029] The collector isolation protection layer is used to prevent the metal housing from directly contacting with external interference sources.

[0030] In one embodiment of the present invention, the step of performing noise reduction processing on the vibration source signal to obtain a noise-reduced vibration signal includes:

[0031] Inputting the vibration source signal into a target noise data model to obtain a target type of the vibration source signal;

[0032] The vibration source signal is filtered based on the target type to obtain a vibration signal after noise reduction.

[0033] In one embodiment of the present invention, before inputting the vibration source signal into the target noise data model to obtain the vibration signal after noise reduction, the method further includes:

[0034] Acquire noise source data, and preprocess the noise source data to obtain first training data;

[0035] Labeling the first training data to obtain second training data;

[0036] Based on the second training data, a training data set and a test data set corresponding to the initial noise data model are obtained;

[0037] Training the initial noise data model based on the training data set to obtain a trained noise data model;

[0038] The trained noise data model is tested using the test data set to obtain a target noise data model.

[0039] In one embodiment of the present invention, the training of the initial noise data model based on the training data set to obtain a trained noise data model includes:

[0040] Inputting the data in the training data set into the initial noise data model to obtain a prediction type;

[0041] Based on the predicted type and the true type, a corresponding loss value is obtained;

[0042] The network parameters in the initial noise data model are updated based on the loss value until the initial noise data model converges, or when the number of iterations of the network parameters reaches a preset number, a trained noise data model is obtained.

[0043] In one embodiment of the present invention, the initial noise data model includes a convolutional pooling layer, a Transformer layer, a fully connected layer and an output layer; the data in the training data set is input into the initial noise data model to obtain a prediction type, including:

[0044] The data in the training data set passes through the convolutional pooling layer to obtain the corresponding spatial feature vector;

[0045] Performing signal feature enhancement on the spatial feature vector through the Transformer layer to obtain a corresponding first feature vector;

[0046] Processing the first feature vector through the fully connected layer to obtain a corresponding second feature vector;

[0047] The output layer determines the category of the second feature vector through a classifier to obtain a predicted type.

[0048] In one embodiment of the present invention, the target type includes non-contact radiation noise data and contact electrical signal interference noise data; the impact ground pressure sensor noise reduction device also includes a grounding isolation device switch; the filtering process of the vibration source signal based on the target type to obtain a noise-reduced vibration signal includes:

[0049] If the target type is non-contact radiation noise data, the vibration source signal is filtered using a variety of eigenvalue filtering algorithms to obtain a vibration signal after noise reduction;

[0050] If the target type is contact-type electrical signal interference noise data, filtering processing is performed through the ground isolation device to obtain a vibration signal after noise reduction.

[0051] The second aspect of the present invention provides a noise reduction method based on a rock burst sensor noise reduction device, which is implemented by using the rock burst sensor noise reduction device described in any one of the first aspects, including:

[0052] Collect vibration source signals in mine environment;

[0053] Inputting the vibration source signal into the rock burst sensor noise reduction device, and obtaining the target type of the vibration source signal through the target noise data model in the rock burst sensor noise reduction device;

[0054] The vibration source signal is filtered based on the target type to obtain a vibration signal after noise reduction.

[0055] The computer device proposed in the embodiment of the third aspect of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method described in the first aspect above can be implemented.

[0056] The computer storage medium proposed in the fourth aspect of the embodiment of the present invention stores computer executable instructions; after the computer executable instructions are executed by the processor, the method described in the first aspect above can be implemented.

[0057] The rock burst sensor noise reduction device and noise reduction method provided by the present invention include a sensor, a sensor signal line, a collector, a collector data line and a ground signal line, wherein the sensor is used to collect vibration source signals in a mine environment; the collector is connected to the sensor through the sensor signal line, and is used to perform noise reduction processing on the vibration source signal to obtain the vibration signal after noise reduction; the collector data line is connected to the collector, and is used to transmit the vibration signal after noise reduction; one end of the ground signal line is connected to the collector, and the other end is connected to the ground, and is used to introduce the noise signal into the ground. It can be seen that the vibration source signal is subjected to noise reduction processing by the rock burst sensor noise reduction device and the target noise data model in the rock burst sensor noise reduction device, so that the vibration source signal can be subjected to noise reduction processing by hardware and the target noise data model, and has a noise reduction effect in various mine environments, and has a wide range of applications, thereby ensuring the normal use of the rock burst sensor acquisition equipment in the mine and ensuring the normal safety production of the mining enterprise.

[0058] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0060] Figure 1 is a schematic structural diagram of a noise reduction device for an impact ground pressure sensor provided according to an embodiment of the present invention;

[0061] Figure 2 is a schematic diagram of the structure of a sensor and a sensor signal line provided according to an embodiment of the present invention;

[0062] Figure 3 is a schematic diagram of the structure of a collector provided according to an embodiment of the present invention;

[0063] Figure 4 It is a flow chart of a noise reduction method based on an impact ground pressure sensor noise reduction device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0064] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0065] The following describes a noise reduction device and a noise reduction method for a rock burst sensor according to an embodiment of the present invention with reference to the accompanying drawings.

[0066] Figure 1 FIG. 1 is a schematic diagram of a structure of a noise reduction device for an impact ground pressure sensor according to an embodiment of the present invention. Figure 1 As shown, the above-mentioned impact ground pressure sensor noise reduction device may include a sensor (1), a sensor signal line (2), a collector (3), a collector data line (4) and a ground signal line (5), wherein:

[0067] The sensor (1) is used to collect vibration source signals in a mine environment;

[0068] The collector (3) is connected to the sensor (1) via the sensor signal line (2) and is used to perform noise reduction processing on the vibration source signal to obtain a vibration signal after noise reduction;

[0069] The data acquisition instrument data line (4) is connected to the acquisition instrument (3) and is used to transmit the vibration signal after noise reduction;

[0070] One end of the ground signal line (5) is connected to the collector (3), and the other end is connected to the ground, so as to guide the noise signal into the ground.

[0071] Figure 2FIG. 1 is a schematic diagram of the structure of a sensor and a sensor signal line provided according to an embodiment of the present invention. Figure 2 As shown, in one embodiment of the present invention, the sensor (1) may include a sensor connector (6), a connector isolation layer (7), a sensor metal housing (8), a sensor metal housing isolation layer (9), a sensor transmitter (10), a sensor signal processing circuit (11) and a sensor grounding point (12), wherein:

[0072] The sensor connector (6) is a connector, which is fixed by the connector and other threaded rods, wherein the sensor connector (6) is made of copper material and is not easy to rust;

[0073] The connector isolation layer (7) is fixed axially for rotation by a radial screw, wherein the connector isolation layer (7) is a resin sealant;

[0074] The sensor transmitter (10) is a moving coil magnetoelectric sensor, which converts the vibration source signal into a voltage signal through electromagnetic induction;

[0075] The sensor grounding point (12) is a shielding layer of the sensor signal processing circuit (11) and is connected to the power ground, and the shielding layer is connected to the sensor metal housing (8);

[0076] The sensor metal shell isolation layer (9) is the outer layer of the sensor metal shell, wherein the sensor metal shell isolation layer (9) can be made of nylon insulating flame-retardant material.

[0077] In one embodiment of the present invention, the sensor signal line (2) may be composed of a sensor wire (13), a sensor wire isolation layer (14) and a sensor isolation protection layer (15), wherein the sensor isolation protection layer (15) is connected to the sensor metal housing (8) to form a signal protection layer.

[0078] In one embodiment of the present invention, the signal frequency collected by the above-mentioned sensor may be in the range of 1 Hz to 2000 Hz, the duration of the rock burst signal does not exceed 5 s, and there is no specific periodicity.

[0079] Figure 3 Schematic diagram of the structure of a collector provided according to an embodiment of the present invention. Figure 3 As shown, in one embodiment of the present invention, the above-mentioned collector (3) includes a collector grounding point (16), a collector front-end signal processing circuit (17), a collector central processing unit circuit (18), a collector signal transmission circuit module (19), a collector metal shell isolation layer (20) and a collector isolation protection layer (21), wherein:

[0080] The collector grounding point (16) is connected to the power ground of the collector front-end signal processing circuit (17), the collector central processing unit circuit (18) and the collector signal transmission circuit module (19);

[0081] The collector grounding point (16) is connected to the collector metal shell isolation layer (20), and the collector metal shell isolation layer (20) is connected to the grounding signal line (5);

[0082] The front-end signal processing circuit (17) of the acquisition instrument is an instrument differential amplifier and filter circuit, which is used to isolate and shield the common ground interference signal and filter out the interference signal, wherein the instrument differential amplifier circuit can isolate and shield the common ground interference signal, and the filter circuit can be a trap circuit to filter out the 50Hz interference signal;

[0083] The collector central processing unit circuit (18) is used to perform noise reduction processing on the vibration source signal to obtain a vibration signal after noise reduction;

[0084] The data acquisition instrument signal transmission circuit module (19) is connected to the data acquisition instrument data line (4) and transmits data via the data acquisition instrument data line (4);

[0085] The collector metal shell isolation layer (20) is connected to the sensor isolation protection layer (15) to form a closed protection for the internal circuit structure of the collector;

[0086] The collector isolation protection layer (21) is used to prevent direct contact between the metal shell and external interference sources during the use of the collector (3), wherein the collector isolation protection layer can be made of nylon insulating flame-retardant material.

[0087] In one embodiment of the present invention, the grounding signal line (5) is connected to the earth, the grounding point conductor can penetrate 1.5 meters underground, and the grounding signal line (5) can be a copper tape conductor with a thickness greater than 5 mm and a resistance less than 0.5 ohms.

[0088] Furthermore, in one embodiment of the present invention, the metal shell isolation layer (20) of the collector is connected to the sensor isolation protection layer (15), and the metal shell isolation layer (20) of the collector forms a closed protection for the internal circuit structure of the collector (3), thereby avoiding interference from external electromagnetic signals.

[0089] In one embodiment of the present invention, the collector central processor circuit (18) may be an ARM processor, wherein the processor may apply the Linux operating system, and the collector central processor circuit (18) may further include a power supply circuit, an amplifier circuit, an AD acquisition circuit, a storage circuit and a clock circuit. The AD acquisition chip is a 32-bit integral acquisition chip. In one embodiment of the present invention, the vibration source signal may be subjected to noise reduction processing in the Linux operating system to obtain a vibration signal after noise reduction.

[0090] Specifically, in one embodiment of the present invention, the method for performing noise reduction processing on the vibration source signal in the Linux operating system to obtain the vibration signal after noise reduction may include: inputting the vibration source signal into the target noise data model to obtain the target type of the vibration source signal, and filtering the vibration source signal based on the target type to obtain the vibration signal after noise reduction.

[0091] In one embodiment of the present invention, before inputting the vibration source signal into the target noise data model to obtain the vibration signal after noise reduction, the method may further include the following steps:

[0092] Step 1: Acquire noise source data, and preprocess the noise source data to obtain first training data;

[0093] Step 2: label the first training data to obtain second training data;

[0094] Step 3: Based on the second training data, obtain a training data set and a test data set corresponding to the initial noise data model;

[0095] Step 4: Train the initial noise data model based on the training data set to obtain a trained noise data model;

[0096] Step 5: Use the test data set to test the trained noise data model to obtain the target noise data model.

[0097] Among them, in one embodiment of the present invention, the above-mentioned noise source data may include coal mining machine signals, tunneling machine signals, coal cannon signals, conveyor machine signals, underground drilling rig drilling signals, blasting signals, coal rock fracture and collapse signals, coal conveyor belt conveyor signals, transfer machine signals, coal mining machine front chute and rear chute operation start-up signals, and power supply frequency interference signals.

[0098] And, in one embodiment of the present invention, after obtaining the noise source data, it is necessary to perform a preprocessing operation of denoising and normalizing the noise source data to obtain the first training data. In one embodiment of the present invention, after obtaining the first training data through the above steps, the first training data can be labeled to obtain the second training data.

[0099] Among them, in one embodiment of the present invention, the first training data can be analyzed from the frequency domain, time domain and time-frequency domain, and the labels can be marked. Among them, according to the frequency components in the frequency domain analysis data, the typical characteristic frequencies are extracted and labeled; according to the time domain characteristics, the signal start time point, end time point, peak moment and maximum value can be analyzed, and the signal threshold label can be marked; the time-frequency domain can perform secondary data feature extraction and labeling according to the time domain label value and the frequency domain label value; and the type of the first training data is labeled to obtain the second training data. In one embodiment of the present invention, frequency domain analysis can be performed by wavelet analysis technology to extract the signal frequency components in layers, highlighting the role of wavelet magnifier.

[0100] And, in one embodiment of the present invention, the second training data can be divided into a training data set and a test data set corresponding to the initial noise data model according to a preset ratio. For example, assuming that the preset ratio is 8:2, that is, 80% of the data in the second training data is randomly divided into a training data set, and 20% of the data is divided into a test data set.

[0101] Furthermore, in one embodiment of the present invention, after obtaining the training data set through the above steps, the initial noise data model can be trained based on the training data set to obtain a trained noise data model.

[0102] Specifically, in one embodiment of the present invention, the method of training the initial noise data model based on the training data set to obtain the trained noise data model may include the following steps:

[0103] Step 41, input the data in the training data set into the initial noise data model to obtain the prediction type;

[0104] Step 42: Based on the predicted type and the true type, obtain the corresponding loss value;

[0105] Step 43: Update the network parameters in the initial noise data model based on the loss value until the initial noise data model converges, or when the number of iterations of the network parameters reaches a preset number, a trained noise data model is obtained.

[0106] In one embodiment of the present invention, the method for obtaining the corresponding loss value based on the predicted type and the true type may include: obtaining the corresponding loss value through a loss function based on the predicted type and the true type. The loss function is the same as that in the prior art, and the embodiment of the present disclosure will not be described in detail here.

[0107] And, in one embodiment of the present invention, the above-mentioned initial noise data model may include a convolutional pooling layer, a Transformer layer, a fully connected layer and an output layer. Among them, in one embodiment of the present invention, the above-mentioned method of inputting the data in the training data set into the initial noise data model to obtain the predicted type may include the following steps:

[0108] Step a: The data in the training data set is passed through a convolutional pooling layer to obtain the corresponding spatial feature vector;

[0109] Step b, performing signal feature enhancement on the spatial feature vector through the Transformer layer to obtain the corresponding first feature vector;

[0110] Step c: Processing the first eigenvector through a fully connected layer to obtain a corresponding second eigenvector;

[0111] Step d: The output layer uses a classifier to determine the category of the second feature vector to obtain a predicted type.

[0112] Among them, in one embodiment of the present invention, the above-mentioned initial noise data model can be a CNN-Transfromer, the input data is training data of marked time domain, frequency domain and time-frequency domain label data respectively selected, and the output is the corresponding prediction type.

[0113] Furthermore, in one embodiment of the present invention, when the classifier is used to determine the category of the second feature vector in the output layer, the softmax method can be used to determine the category of the second feature vector to obtain a predicted type.

[0114] Furthermore, in one embodiment of the present invention, the trained noise data model is obtained through the above steps, and the trained noise data model can be tested and tuned using a test data set to obtain the accuracy performance of the trained noise data model on the test data and evaluate the generalization ability of the model. Then, according to the evaluation results of the test data set, the trained noise data model is adjusted and optimized, for example, the network structure or hyperparameter settings are changed to improve the accuracy, robustness and performance of the model.

[0115] Wherein, in one embodiment of the present invention, the above-mentioned target type may include non-contact radiation noise data and contact electrical signal interference noise data. And, in one embodiment of the present invention, the above-mentioned impact ground pressure sensor noise reduction device also includes a grounding isolation device switch (25), and the above-mentioned grounding isolation device switch (25) includes a resistor and a capacitor combination, a trap circuit, and the resistor and capacitor realize the filtering of high-frequency pulses, and the trap circuit realizes the filtering of power frequency signals. In one embodiment of the present invention, the above-mentioned grounding isolation device switch (25) can realize the opening and closing of the grounding isolation device by the target type obtained by the target noise data model.

[0116] Furthermore, in one embodiment of the present invention, the above-mentioned method of filtering the vibration source signal based on the target type to obtain the vibration signal after noise reduction may include: if the target type is non-contact radiation noise data, then using multiple eigenvalue filtering algorithms to filter the vibration source signal to obtain the vibration signal after noise reduction; if the target type is contact electrical signal interference noise data, then filtering is performed through a grounding isolation device to obtain the vibration signal after noise reduction.

[0117] Specifically, in one embodiment of the present invention, the method of filtering the vibration source signal using multiple eigenvalue filtering algorithms to obtain a vibration signal after noise reduction may include: filtering the vibration source signal using a wavelet filtering algorithm to obtain a vibration signal after noise reduction.

[0118] Among them, in one embodiment of the present invention, the method of filtering the vibration source signal using a wavelet filtering algorithm to obtain a vibration signal after noise reduction may include: performing wavelet decomposition on the vibration source signal to obtain wavelet coefficients of multiple scales, performing threshold processing on the wavelet coefficients of each scale, setting coefficients less than a certain threshold to 0, retaining coefficients greater than or equal to the threshold, performing wavelet reconstruction on the processed wavelet coefficients to obtain a vibration signal after noise reduction, and repeating the above steps until a stopping criterion is met.

[0119] Furthermore, in one embodiment of the present invention, the method for obtaining a vibration signal after noise reduction by filtering through a ground isolation device may include:

[0120] Step 1: Open the ground isolation device through the processor of the sensor or collector to achieve isolation and shielding of contact-type electrical signals;

[0121] Step 2: If the noise in the collected vibration source signal still exists, turn off the sensor or the processor of the collector and turn on the ground isolation device;

[0122] Step 3: If the noise signal has not been removed through the above steps 1 and 2, the above non-contact radiation noise data processing method is applied to remove the noise.

[0123] Furthermore, in one embodiment of the present invention, the host computer can automatically increase type data and model training to make the target noise data model more generalized.

[0124] Furthermore, in one embodiment of the present invention, the data collector signal transmission circuit module (19) may include two input and output signals, one for an Ethernet interface and one for an optical fiber communication interface, and transmit the data collected by the AD through the data collector data line (4).

[0125] It should be noted that, in one embodiment of the present invention, the sensor, sensor signal line, collector and ground signal line are fully enclosed and isolated by a metal shielding layer, and the internal power ground is connected to the shielding layer and the noise signal is introduced into the ground through the ground signal line. At the same time, the environmental noise and other power interference sources are filtered out by the target noise data model, so that the noise reduction effect can be achieved in various mining environments, ensuring the normal operation of the impact ground pressure sensor measurement system, and the scope of application is wide.

[0126] The rock burst sensor noise reduction device and noise reduction method provided by the present invention include a sensor, a sensor signal line, a collector, a collector data line and a ground signal line, wherein the sensor is used to collect vibration source signals in a mine environment; the collector is connected to the sensor through the sensor signal line, and is used to perform noise reduction processing on the vibration source signal to obtain the vibration signal after noise reduction; the collector data line is connected to the collector, and is used to transmit the vibration signal after noise reduction; one end of the ground signal line is connected to the collector, and the other end is connected to the ground, and is used to introduce the noise signal into the ground. It can be seen that the vibration source signal is subjected to noise reduction processing by the rock burst sensor noise reduction device and the target noise data model in the rock burst sensor noise reduction device, so that the vibration source signal can be subjected to noise reduction processing by hardware and the target noise data model, and has a noise reduction effect in various mine environments, and has a wide range of applications, thereby ensuring the normal use of the rock burst sensor acquisition equipment in the mine and ensuring the normal safety production of the mining enterprise.

[0127] Figure 4 The flowchart of a noise reduction method based on a rock burst sensor noise reduction device according to the present invention is shown in FIG. Figure 4 As shown, it may include:

[0128] Step 401, collecting vibration source signals in a mine environment;

[0129] Step 402: input the vibration source signal into the rock burst sensor noise reduction device, and obtain the target type of the vibration source signal through the target noise data model in the rock burst sensor noise reduction device;

[0130] Step 403: filter the vibration source signal based on the target type to obtain a vibration signal after noise reduction.

[0131] Among them, in one embodiment of the present invention, after the vibration source signal is input into the impact ground pressure sensor noise reduction device, the sensor, sensor signal line, collector and ground signal line in the impact ground pressure sensor noise reduction device can be fully enclosed and isolated through a metal shielding layer, and the internal power ground is connected to the shielding layer and the noise signal is introduced into the earth through the grounding signal line. At the same time, the environmental noise and other power interference sources are filtered out through the target noise data model, and the noise reduction effect can be achieved in various mining environments to ensure the normal operation of the impact ground pressure sensor measurement system, which has a wide range of applications.

[0132] For the introduction of the above-mentioned impact ground pressure sensor noise reduction device and the target noise data model, reference can be made to the detailed introduction in the above-mentioned embodiments, and the embodiments of the present disclosure will not be elaborated here.

[0133] The rock burst sensor noise reduction device and noise reduction method provided by the present invention include a sensor, a sensor signal line, a collector, a collector data line and a ground signal line, wherein the sensor is used to collect vibration source signals in a mine environment; the collector is connected to the sensor through the sensor signal line, and is used to perform noise reduction processing on the vibration source signal to obtain the vibration signal after noise reduction; the collector data line is connected to the collector, and is used to transmit the vibration signal after noise reduction; one end of the ground signal line is connected to the collector, and the other end is connected to the ground, and is used to introduce the noise signal into the ground. It can be seen that the vibration source signal is subjected to noise reduction processing by the rock burst sensor noise reduction device and the target noise data model in the rock burst sensor noise reduction device, so that the vibration source signal can be subjected to noise reduction processing by hardware and the target noise data model, and has a noise reduction effect in various mine environments, and has a wide range of applications, thereby ensuring the normal use of the rock burst sensor acquisition equipment in the mine and ensuring the normal safety production of the mining enterprise.

[0134] In order to implement the above embodiment, the present invention also provides a computer device.

[0135] The computer device provided in the embodiment of the present invention includes a memory, a processor and a computer program stored in the memory and executable on the processor; when the processor executes the program, the following can be achieved: Figure 1 The method shown.

[0136] In order to implement the above embodiment, the present invention also provides a computer storage medium.

[0137] The computer storage medium provided in the embodiment of the present invention stores computer executable instructions; after the computer executable instructions are executed by the processor, the following can be achieved: Figure 1 The method shown.

[0138] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0139] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0140] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A noise reduction device for an impact ground pressure sensor, characterized in that: It includes a sensor, a sensor signal line, a collector, a collector data line and a ground signal line, wherein: The sensor is used to collect vibration source signals in a mine environment; The collector is connected to the sensor via the sensor signal line, and is used to perform noise reduction processing on the vibration source signal to obtain a vibration signal after noise reduction; The data line of the collector is connected to the collector and is used to transmit the vibration signal after noise reduction; One end of the ground signal line is connected to the collector, and the other end is connected to the ground, so as to guide the noise signal into the ground.

2. The noise reduction device for the impact ground pressure sensor according to claim 1, characterized in that: The sensor includes a sensor connector, a connector isolation layer, a sensor metal housing, a sensor metal housing isolation layer, a sensor transmitter, a sensor signal processing circuit and a sensor grounding point, wherein: The sensor connector is a connecting joint, which is fixed by the connecting joint and other threaded rods; The connector isolation layer is fixed by radial screws for axial rotation; The sensor transmitter is a moving coil magnetoelectric sensor, which converts the vibration source signal into a voltage signal through electromagnetic induction; The sensor grounding point is the shielding layer of the sensor signal processing circuit and is connected to the power ground, and the shielding layer is connected to the metal housing of the sensor; The sensor metal housing isolation layer is the outer layer of the sensor metal housing.

3. The noise reduction device for the impact ground pressure sensor according to claim 2, characterized in that: The sensor signal line includes a sensor isolation protection layer, wherein: The sensor isolation protection layer is connected to the sensor metal shell to form a signal protection layer.

4. The noise reduction device for the impact ground pressure sensor according to claim 3, characterized in that: The collector includes a collector grounding point, a collector front-end signal processing circuit, a collector central processing unit circuit, a collector signal transmission circuit module, a collector metal shell isolation layer and a collector isolation protection layer, wherein: The collector grounding point is connected to the power ground of the collector front-end signal processing circuit, the collector central processing unit circuit and the collector signal transmission circuit module; The collector grounding point is connected to the collector metal shell isolation layer, and the collector metal shell isolation layer is connected to the grounding signal line; The front-end signal processing circuit of the acquisition instrument is a differential amplifier and filter circuit for the instrument, which is used to isolate and shield the common ground interference signal and filter out the interference signal; The collector central processing unit circuit is used to perform noise reduction processing on the vibration source signal to obtain a vibration signal after noise reduction; The collector signal transmission circuit module is connected to the collector data line and transmits data through the collector data line; The collector metal shell isolation layer is connected to the sensor isolation protection layer to form a closed protection for the internal circuit structure of the collector; The collector isolation protection layer is used to prevent the metal housing from directly contacting with external interference sources.

5. The noise reduction device for the impact ground pressure sensor according to claim 4, characterized in that: The step of performing noise reduction processing on the vibration source signal to obtain a noise-reduced vibration signal includes: Inputting the vibration source signal into a target noise data model to obtain a target type of the vibration source signal; The vibration source signal is filtered based on the target type to obtain a vibration signal after noise reduction.

6. The noise reduction device for the impact ground pressure sensor according to claim 5, characterized in that: Before inputting the vibration source signal into the target noise data model to obtain the vibration signal after noise reduction, the method further includes: Acquire noise source data, and preprocess the noise source data to obtain first training data; Labeling the first training data to obtain second training data; Based on the second training data, a training data set and a test data set corresponding to the initial noise data model are obtained; Training the initial noise data model based on the training data set to obtain a trained noise data model; The trained noise data model is tested using the test data set to obtain a target noise data model.

7. The noise reduction device for the impact ground pressure sensor according to claim 6, characterized in that: The step of training the initial noise data model based on the training data set to obtain a trained noise data model includes: Inputting the data in the training data set into the initial noise data model to obtain a prediction type; Based on the predicted type and the true type, a corresponding loss value is obtained; The network parameters in the initial noise data model are updated based on the loss value until the initial noise data model converges, or when the number of iterations of the network parameters reaches a preset number, a trained noise data model is obtained.

8. The noise reduction device for the impact ground pressure sensor according to claim 7, characterized in that: The initial noise data model includes a convolutional pooling layer, a Transformer layer, a fully connected layer and an output layer; the data in the training data set is input into the initial noise data model to obtain a prediction type, including: The data in the training data set passes through the convolutional pooling layer to obtain the corresponding spatial feature vector; Performing signal feature enhancement on the spatial feature vector through the Transformer layer to obtain a corresponding first feature vector; Processing the first feature vector through the fully connected layer to obtain a corresponding second feature vector; The output layer determines the category of the second feature vector through a classifier to obtain a predicted type.

9. The noise reduction device for a rock burst sensor according to claim 5, characterized in that: The target type includes non-contact radiation noise data and contact electrical signal interference noise data; the impact ground pressure sensor noise reduction device also includes a grounding isolation device switch; the vibration source signal is filtered based on the target type to obtain a vibration signal after noise reduction, including: If the target type is non-contact radiation noise data, the vibration source signal is filtered using a variety of eigenvalue filtering algorithms to obtain a vibration signal after noise reduction; If the target type is contact-type electrical signal interference noise data, filtering is performed through the ground isolation device to obtain a vibration signal after noise reduction.

10. A noise reduction method based on a rock burst sensor noise reduction device, implemented by using the rock burst sensor noise reduction device according to any one of claims 1 to 9, characterized in that: include: Collect vibration source signals in mine environment; Inputting the vibration source signal into the rock burst sensor noise reduction device, and obtaining the target type of the vibration source signal through the target noise data model in the rock burst sensor noise reduction device; The vibration source signal is filtered based on the target type to obtain a vibration signal after noise reduction.

Images