A method for reducing noise of a wall breaker and a wall breaker

Abstract

The present invention discloses a noise reduction method for a wall breaker, which relates to the technical field of household appliances and includes: collecting noise signals generated during the operation of the wall breaker through a sound sensor, and preprocessing the noise signals to obtain standardized noise waveform data; using a time-frequency analysis method to convert the standardized noise waveform data from the time domain to the frequency domain, and extracting key frequency band features reflecting the noise characteristics; identifying the noise type by using a machine learning algorithm according to the key frequency band features, and matching the noise feature template to determine the noise category; retrieving corresponding cancellation signals from a preset cancellation signal template library according to the noise category, and performing parameter optimization to generate cancellation signals matching the original noise; playing the cancellation signals through a speaker to be superimposed with the original noise to achieve noise cancellation, and adaptively optimizing the cancellation signals to adapt to noise changes.

Description

Technical Field

[0001] The present invention relates to the technical field of household appliances, and in particular to a noise reduction method for a wall breaker and a wall breaker. Background Art

[0002] During the use of a wall breaker, the noise problem has always been an important factor affecting the user experience. Traditional noise reduction methods mainly rely on passive noise reduction technologies, such as adding sound insulation materials, etc., but these methods have limited effects in actual applications and cannot effectively solve the noise problems of wall breakers in different working states. In recent years, active noise reduction technologies have gradually attracted attention, and the noise reduction effect is achieved by generating a cancellation signal with a phase opposite to that of the noise. However, there are technical bottlenecks in the existing technology for real-time dynamic adjustment of the cancellation signal.

[0003] When the wall breaker is working, its noise frequency and intensity will change with factors such as time, working state, and materials. Simply using a fixed cancellation signal is difficult to effectively adapt to this dynamic change, resulting in poor noise cancellation effect. For example, the Chinese patent with the publication number (CN118942437A) discloses an open-type active noise reduction wall breaker. Although a noise reduction signal with a phase opposite to that of the noise is generated through methods such as fast Fourier transform, in actual applications, it is still impossible to real-time dynamically adjust the cancellation signal to adapt to the changing noise characteristics. Summary of the Invention

[0004] The present invention provides a noise reduction method for a wall breaker and a wall breaker to solve the above-mentioned existing technical problems.

[0005] The technical solution of the present invention is realized as follows:

[0006] A noise reduction method for a wall breaker includes the following steps:

[0007] S1. Collect the noise signal generated during the operation of the wall breaker through a sound sensor, and preprocess the noise signal to obtain standardized noise waveform data;

[0008] S2. Use the time-frequency analysis method to convert the standardized noise waveform data from the time domain to the frequency domain, and extract the key frequency band characteristics reflecting the noise characteristics;

[0009] S3. Identify the noise type using a machine learning algorithm according to the key frequency band characteristics, and match the noise feature template to determine the noise category;

[0010] S4. Retrieve the corresponding cancellation signal from the preset cancellation signal template library according to the noise category, and perform parameter optimization to generate a cancellation signal matching the original noise;

[0011] S5. Play the cancellation signal through a speaker and superimpose it on the original noise to achieve noise cancellation, and adaptively optimize the cancellation signal to adapt to noise changes;

[0012] S6. Calculate the difference degree between the residual noise after cancellation and the original noise to obtain the noise suppression amount, and perform iterative optimization of the cancellation signal according to the comparison result between the noise suppression amount and the target threshold.

[0013] Further, the process of extracting the key frequency band features reflecting the noise characteristics in step S2 is specifically as follows:

[0014] Use the short-time Fourier transform to convert the standardized noise waveform data from the time domain to the frequency domain, and obtain the energy distribution characteristics of the noise signal in different frequency bands;

[0015] According to the energy distribution characteristics of the noise signal in different frequency bands, extract the key frequency band features that can reflect the noise characteristics, including the mean and variance statistical characteristics of the energy in the low-frequency, middle-frequency, and high-frequency bands;

[0016] Construct a noise recognition model, and use the extracted key frequency band features as the input of the model.

[0017] Further, the process of matching the noise feature template to determine the noise category in step S3 is specifically as follows:

[0018] In the noise recognition process, if the key frequency band features of the current noise match the preset noise type feature template with a high degree of similarity, it is determined that the noise belongs to the corresponding type, and the category to which the noise belongs is obtained;

[0019] Specifically, according to the material properties and working status of the wall breaker, select the corresponding typical frequency domain feature template from the pre-established noise model library;

[0020] Use the dynamic time warping algorithm to match and compare the frequency domain feature data of the noise with the selected typical frequency domain feature template, and calculate the similarity between the two; if the similarity is greater than the preset threshold, it is determined that the current noise belongs to the noise category corresponding to the typical frequency domain feature template; if the similarity is less than the threshold, continue to match with other typical frequency domain feature templates;

[0021] Repeat the above process until a typical frequency domain feature template with the largest similarity and greater than the threshold is found to determine the category to which the noise belongs.

[0022] Further, step S3 also includes:

[0023] After determining the category to which the noise belongs, analyze the source and cause of the noise according to the category of the noise and the acoustic characteristic parameters of the noise of this category in the noise model library;

[0024] Specifically, the association rules between the working state parameters of the wall breaker and the feature vectors of the noise signal are mined through data mining algorithms, and a mapping model between the two is established;

[0025] According to the established mapping model, by monitoring the change of the noise signal in real time, it is judged whether the working state of the wall breaker is abnormal. If an abnormality is detected, a warning prompt is triggered, and the noise signal data in the abnormal state is recorded for subsequent fault diagnosis and model optimization.

[0026] Further, the process of generating the cancellation signal matching the original noise in step S4 is specifically as follows:

[0027] Adjust the parameters of the obtained cancellation signal template, match the frequency, amplitude, and phase parameters of the template with the actual characteristic parameters of the noise signal, and generate a cancellation signal matching the original noise signal;

[0028] Superimpose the generated cancellation signal on the original noise signal. Through the waveform cancellation principle, weaken or eliminate the intensity of the original noise signal to obtain the superimposed and cancelled signal.

[0029] Further, the process of adaptively optimizing the cancellation signal in step S5 is specifically as follows:

[0030] After obtaining the superimposed and cancelled signal, evaluate the effect of the superimposed and cancelled signal, extract the characteristic parameters of the residual noise, calculate the noise reduction amount, and judge whether the noise cancellation effect reaches the preset threshold; if the noise cancellation effect does not reach the preset threshold, further optimize the parameters of the cancellation signal until the noise cancellation effect reaches the preset threshold, and output the finally noise-reduced signal.

[0031] Further, the specific process of iterative optimization of the cancellation signal in step S6 is as follows:

[0032] Calculate the difference degree of the energy of the residual noise signal and the original noise signal in each frequency band to obtain the noise suppression amount in each frequency band;

[0033] Weight and average the noise suppression amounts in each frequency band to obtain the total noise suppression amount, which is used as an index to measure the noise suppression effect;

[0034] Compare the total noise suppression amount with the preset noise suppression target threshold. If the noise suppression amount is lower than the target threshold, it is judged that the noise suppression effect is not ideal;

[0035] If the noise suppression effect is not ideal, an adaptive filtering algorithm is used to optimize the cancellation signal, and by adjusting the amplitude and phase of the cancellation signal, the residual noise is minimized;

[0036] Repeat the above process according to the optimized cancellation signal until the total noise suppression amount is higher than or equal to the target threshold. If the total noise suppression amount is higher than or equal to the target threshold, it is determined that the noise suppression effect meets the expectation, and the current cancellation signal is maintained.

[0037] Further, the method further includes:

[0038] Real-time monitor the working state of the wall breaker and the changes in material properties, trigger the noise feature extraction and analysis process, dynamically adjust the noise recognition model and the cancellation signal template, and realize the adaptive optimization of the cancellation signal.

[0039] A wall breaker includes a main body, and a sound sensor for real-time collecting noise data generated during the working process of the wall breaker is installed on the main body. A noise reduction device for reducing the noise of the wall breaker is also provided on the main body. The noise reduction device includes a speaker, a signal processing module, a cancellation signal generation and adjustment module, and an adaptive filtering module;

[0040] The signal processing module includes an analog-to-digital converter, a digital signal processor, and a memory;

[0041] The cancellation signal generation and adjustment module includes an electrically tunable attenuator, a phase adjuster, and a power combiner.

[0042] Further, the analog-to-digital converter is used to convert the analog noise signal collected by the sound sensor into a digital signal for subsequent digital signal processing;

[0043] The digital signal processor is used to execute the time-frequency analysis method, convert the noise signal from the time domain to the frequency domain, and obtain the energy distribution characteristics of the noise in different frequency bands; it is also used to identify and classify the frequency domain characteristics of the noise according to the pre-established noise model library; and match the technology to retrieve the cancellation signal template and adjust the amplitude and phase of the template;

[0044] The electrically tunable attenuator and the phase adjuster are used to adjust the amplitude and phase of the cancellation signal template according to the actual frequency and intensity parameters of the noise, and generate a cancellation signal that matches the original noise;

[0045] The power combiner performs vector power combination on the adjusted cancellation signal and the reference signal, etc., to form the final cancellation signal;

[0046] The adaptive filtering module is used to implement an improved variable step size least mean square adaptive filtering algorithm based on a radial basis function neural network, optimize the cancellation signal in real time, and continuously correct the parameters of the cancellation signal to adapt to the dynamic changes of the noise.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The present invention collects the working noise of the wall breaker in real time, performs time-frequency analysis and feature recognition on it, retrieves a matching template from a preset cancellation signal library, and uses an improved adaptive filtering algorithm. The present invention can dynamically optimize the cancellation signal to make it precisely match the original noise, and play the optimized cancellation signal through a speaker to achieve active suppression of the wall breaker noise;

[0049] 2. The present invention also introduces a residual noise feedback mechanism. By comparing the noise suppression amount with the target threshold, the cancellation strategy is continuously adjusted. At the same time, when the working state or materials of the wall breaker change, the present invention can automatically repeat the suppression process to ensure continuous and effective noise suppression under different working conditions. This intelligent and adaptive noise suppression method significantly improves the comfort of using the wall breaker and the quality of the working environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flowchart of the steps of a wall breaker noise reduction method in Embodiment 1;

[0051] Figure 2 is a schematic structural diagram of the noise reduction device in Embodiment 2;

[0052] Figure 3 is a framework diagram of the signal processing module in Embodiment 2;

[0053] Figure 4 is a framework diagram of the cancellation signal generation and adjustment module in Embodiment 2. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] To make the objectives, features, and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described below are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0055] Embodiment 1

[0056] As Figure 1 shown, this embodiment provides a wall breaker noise reduction method, including the following steps:

[0057] S1. Collect the noise signal generated during the operation of the wall breaker through a sound sensor, and preprocess the noise signal to obtain standardized noise waveform data;

[0058] S2. Use a time-frequency analysis method to convert the standardized noise waveform data from the time domain to the frequency domain, and extract the key frequency band features reflecting the noise characteristics;

[0059] S3. Identify the noise type using a machine learning algorithm according to the key frequency band characteristics, and match the noise characteristic template to determine the noise category;

[0060] S4. Retrieve the corresponding cancellation signal from the preset cancellation signal template library according to the noise category, and perform parameter optimization to generate a cancellation signal that matches the original noise;

[0061] S5. Play the cancellation signal through a speaker to superimpose it with the original noise to achieve noise cancellation, and perform adaptive optimization on the cancellation signal to adapt to noise changes;

[0062] S6. Calculate the difference degree between the residual noise after cancellation and the original noise to obtain the noise suppression amount, and perform iterative optimization of the cancellation signal according to the comparison result between the noise suppression amount and the target threshold.

[0063] Further, the process of extracting the key frequency band characteristics reflecting the noise characteristics in step S2 is specifically as follows:

[0064] Adopt short-time Fourier transform to convert the standardized noise waveform data from the time domain to the frequency domain, and obtain the energy distribution characteristics of the noise signal in different frequency bands;

[0065] According to the energy distribution characteristics of the noise signal in different frequency bands, extract the key frequency band characteristics that can reflect the noise characteristics, including the energy mean and variance statistical characteristics of the low-frequency, medium-frequency, and high-frequency bands;

[0066] Construct a noise recognition model, and use the extracted key frequency band characteristics as the input of the model;

[0067] Specifically, as described below, arrange 8 sound sensors around the wall breaker, with a sampling frequency of 44.1 kHz, and collect the noise data generated during the operation of the wall breaker in real time to obtain the original waveform of the noise signal. Use the wavelet analysis method to extract the characteristics of the original noise waveform data, extract 12 characteristic parameters such as the mean, variance, and energy of the wavelet coefficients, and form the characteristic vector of the noise signal. Input the extracted characteristic vector into the noise classification model based on the convolutional neural network;

[0068] For the preprocessing of the original noise data, the median filtering method can be used to remove outliers, and then the normalization method is used to map the noise amplitude to the interval [0, 1] to obtain the standardized noise waveform data. Then, perform short-time Fourier transform on the standardized noise waveform using a Hamming window with a window length of 10 ms and a frame shift of 5 ms to obtain the energy distribution characteristics of the noise signal in the 0 - 8 kHz frequency band. According to the energy distribution characteristics, extract the energy mean and variance of the low-frequency (0 - 2 kHz), medium-frequency (2 - 5 kHz), and high-frequency (5 - 8 kHz) bands as the key frequency band characteristics;

[0069] Next, a noise recognition model based on support vector machine is constructed. The key frequency band features are used as the input, and the discriminant function of the noise type is obtained through training. During the recognition process, if the Euclidean distance between the key frequency band features of the current noise and the preset feature templates of 5 noise types is less than the threshold of 0.1, it is determined that the noise belongs to the corresponding type.

[0070] According to the recognized noise category, in the pre-established library of 100 cancellation signal templates, a convolutional neural network algorithm is used for template matching to select the cancellation signal template that best matches the current noise category.

[0071] For the selected cancellation signal template, the parameters such as the frequency, amplitude, and phase of the noise signal are fitted by the least squares method to generate a cancellation signal that matches the original noise signal.

[0072] Finally, the generated cancellation signal is superimposed on the original noise signal, and the noise intensity is weakened through the waveform cancellation principle. The effect of the superimposed and cancelled signal is evaluated, the frequency domain energy characteristics of the residual noise are extracted, and the noise reduction amount is calculated. If the noise reduction amount is less than 20 dB, return to the cancellation signal generation step, and further optimize the cancellation signal parameters by the gradient descent method until the noise reduction amount reaches 20 dB, and output the final noise reduction signal.

[0073] Furthermore, the process of determining the noise category by matching the noise feature template in step S3 is specifically as follows:

[0074] During the noise recognition process, if the key frequency band features of the current noise have a high degree of matching with the preset noise type feature template, it is determined that the noise belongs to the corresponding type, and the category to which the noise belongs is obtained.

[0075] Specifically, according to the material properties and working status of the wall breaker, the corresponding typical frequency domain feature template is selected from the pre-established noise model library.

[0076] The dynamic time warping algorithm is used to match and compare the frequency domain feature data of the noise with the selected typical frequency domain feature template, and calculate the similarity between the two; if the similarity is greater than the preset threshold, it is determined that the current noise belongs to the noise category corresponding to the typical frequency domain feature template; if the similarity is less than the threshold, continue to match with other typical frequency domain feature templates.

[0077] Repeat the above process until a typical frequency domain feature template with the largest similarity and greater than the threshold is found to determine the category to which the noise belongs.

[0078] Furthermore, step S3 also includes:

[0079] After determining the category to which the noise belongs, based on the category of the noise and combining the acoustic characteristic parameters of the noise of this category in the noise model library, analyze the source and cause of the noise;

[0080] Specifically, use a data mining algorithm to mine the association rules between the working state parameters of the wall breaker and the feature vectors of the noise signal, and establish a mapping model between the two;

[0081] According to the established mapping model, by real-time monitoring the change of the noise signal, judge whether the working state of the wall breaker is abnormal. If an abnormality is detected, trigger a warning prompt and record the noise signal data in the abnormal state for subsequent fault diagnosis and model optimization;

[0082] Specifically, it can be described as follows. According to the material properties (such as stainless steel, glass, etc.) and working states (such as no-load, load, etc.) of the wall breaker, select the corresponding typical frequency domain feature templates from the pre-established noise model library containing 500 samples. Adopt the dynamic time warping algorithm, with a 10 ms time window, calculate the Euclidean distance between the noise frequency domain feature data and the typical frequency domain feature templates, and obtain the similarity between the two. If the similarity is greater than 0.85, it is judged that the current noise belongs to the noise category corresponding to the typical frequency domain feature template; if the similarity is less than 0.85, continue to match with other typical frequency domain feature templates until a template with the largest similarity and greater than 0.85 is found to determine the noise category;

[0083] According to the noise category, combine the acoustic characteristic parameters such as the sound pressure level and frequency range of the noise of this category in the noise model library, and use the logistic regression algorithm to analyze the source (such as mechanical failure, environmental noise, etc.) and cause (such as bearing wear, rotor imbalance, etc.) of the noise;

[0084] Through the Apriori association rule mining algorithm, with the thresholds of minimum support of 0.05 and minimum confidence of 0.8, mine the association rules between the working state parameters such as the rotation speed and vibration of the wall breaker and the feature vectors of the noise signal frequency domain, and establish a non-linear mapping model between the two;

[0085] Based on this model, real-time monitor the change of the noise signal frequency domain characteristics. When the deviation between the feature vector and the model prediction value exceeds 10%, judge that the working state of the wall breaker is abnormal, trigger a warning prompt, and record the noise signal data in the abnormal state for subsequent fault diagnosis and model parameter optimization.

[0086] Furthermore, the process of generating the cancellation signal that matches the original noise in step S4 is specifically as follows:

[0087] Adjust the parameters of the obtained cancellation signal template, match the frequency, amplitude, and phase parameters of the template with the actual characteristic parameters of the noise signal, and generate a cancellation signal that matches the original noise signal;

[0088] Superimpose the generated cancellation signal on the original noise signal. According to the waveform cancellation principle, weaken or eliminate the intensity of the original noise signal to obtain the signal after superimposed cancellation;

[0089] Specifically, as described below, according to the identified noise category, use a convolutional neural network to perform template matching in the cancellation signal template library, find the cancellation signal template that is most similar to the current noise category, and then optimize the parameters such as the frequency, amplitude, and phase of the matched cancellation signal template to match the characteristic parameters of the original noise signal, and generate a targeted cancellation signal;

[0090] Superimpose the generated cancellation signal on the original noise signal. Utilize the acoustic wave interference principle to make the waveforms of the two signals cancel each other, thereby weakening the noise intensity. Perform spectral analysis on the cancelled signal, calculate the noise reduction amount. If the reduction amount does not reach the preset -20dB threshold, return to the cancellation signal optimization step, and further adjust the cancellation signal parameters through the gradient descent algorithm until the noise reduction amount meets the requirements;

[0091] Finally, play the optimized cancellation signal in real time through the speaker on the wall breaker, superimpose it on the original noise to achieve active noise reduction. At the same time, adopt an adaptive filtering algorithm based on a radial basis function neural network, and dynamically adjust the amplitude and phase parameters of the cancellation signal according to the correlation between the residual noise and the cancellation signal to adapt to the real-time changes of the noise and maintain a stable noise reduction effect.

[0092] Furthermore, the specific process of adaptively optimizing the cancellation signal in step S5 is as follows:

[0093] After obtaining the signal after superimposed cancellation, evaluate the effect of the signal after superimposed cancellation, extract the characteristic parameters of the residual noise, calculate the noise reduction amount, and judge whether the noise cancellation effect reaches the preset threshold; if the noise cancellation effect does not reach the preset threshold, further optimize the parameters of the cancellation signal until the noise cancellation effect reaches the preset threshold, and output the finally noise-reduced signal.

[0094] Furthermore, the specific process of iteratively optimizing the cancellation signal in step S6 is as follows:

[0095] Calculate the difference degree of the energy of the residual noise signal and the original noise signal in each frequency band to obtain the noise suppression amount in each frequency band;

[0096] Weighted average the noise suppression amounts in each frequency band to obtain the total noise suppression amount, which is used as an index to measure the noise suppression effect;

[0097] Compare the total noise suppression amount with a preset noise suppression target threshold. If the noise suppression amount is lower than the target threshold, it is determined that the noise suppression effect is not ideal.

[0098] If the noise suppression effect is not ideal, an adaptive filtering algorithm is used to optimize the cancellation signal. By adjusting the amplitude and phase of the cancellation signal, the residual noise is minimized.

[0099] According to the optimized cancellation signal, repeat the above process until the total noise suppression amount is higher than or equal to the target threshold. If the total noise suppression amount is higher than or equal to the target threshold, it is determined that the noise suppression effect meets the expectation, and the current cancellation signal is maintained.

[0100] Specifically, as described below, by performing a fast Fourier transform (FFT) analysis on the noise signal collected during the operation of the wall breaker, characteristic parameters such as the main noise frequency of 1.5 kHz, amplitude of -20 dB, and phase of 45° are extracted. The extracted characteristic parameters are input into a pre-trained support vector machine (SVM) model for noise category recognition. The recognition result shows that the noise belongs to the motor noise category with a confidence level of 95%.

[0101] According to the recognized motor noise category, use a convolutional neural network (CNN) algorithm to search for the cancellation signal template with the highest matching degree in the cancellation signal template library. The matching degree reaches 98%. Fine-tune the parameters of the matched cancellation signal template, adjust the frequency of the template to 1.5 kHz, the amplitude to 20 dB, and the phase to 225° to generate a cancellation signal that matches the original noise signal.

[0102] Adopt an improved variable step-size least mean square (LMS) adaptive filtering algorithm based on a radial basis function neural network (RBFNN) to optimize the cancellation signal in real time with an initial step size of 0.01. After 100 iterations, the mean square error converges to less than 0.001, realizing the dynamic correction of the cancellation signal parameters.

[0103] Play the optimized cancellation signal through the speaker on the wall breaker and superimpose it with the original noise signal. According to the waveform cancellation principle, the intensity of the noise signal is reduced by 20 dB.

[0104] Evaluate the effect of the superimposed cancellation signal. The frequency of the residual noise is 1.8 kHz, the amplitude is -40 dB, and the phase is 60°. Calculate that the noise reduction amount is 20 dB, reaching the preset 18 dB noise cancellation threshold. Output the finally noise-reduced signal, completing the active cancellation process of the wall breaker noise.

[0105] Furthermore, this method also includes:

[0106] Monitor the working state of the wall breaker and the changes in material properties in real time, trigger the noise feature extraction and analysis process, dynamically adjust the noise recognition model and the cancellation signal template, and realize the adaptive optimization of the cancellation signal;

[0107] Specifically, as described below, obtain the original noise waveform data generated by the wall breaker during operation through sensors, and convert the noise signal into a digital signal for processing;

[0108] According to the pre-established noise signal feature model of the wall breaker, extract the features of the obtained original noise waveform data to obtain the feature vector of the noise signal;

[0109] Input the extracted feature vector of the noise signal into an adaptive filter. The adaptive filter dynamically adjusts the weight coefficients of the filter according to the features of the noise signal and generates a cancellation signal with a high correlation with the noise signal;

[0110] Conduct a correlation analysis on the generated cancellation signal and the original noise signal, calculate the correlation coefficient between the two. If the correlation is higher than the preset threshold, output the cancellation signal to the speaker of the wall breaker for playback;

[0111] Obtain the residual noise after the speaker plays the cancellation signal through sensors, and feedback the residual noise signal to the adaptive filter. The adaptive filter optimizes the weight coefficients of the filter in real time according to the residual noise signal, and continuously corrects the parameters of the cancellation signal to adapt to the dynamic changes of the noise;

[0112] Repeat the above process until the residual noise is less than the preset threshold or the set number of iterations is reached, and complete the active cancellation process of the wall breaker noise; conduct a correlation analysis on the working state parameters of the wall breaker and the feature vector of the noise signal, and mine the association rules between the two through data mining algorithms to judge the relationship between the noise and the working state of the wall breaker;

[0113] According to the results of the correlation analysis, establish a mapping model between the working state of the wall breaker and the noise signal, and monitor the working state of the wall breaker in real time through the changes in the noise signal. When it is detected that the working state of the wall breaker is abnormal, trigger a warning prompt in time, and record the noise signal data in the abnormal state for subsequent fault diagnosis and model optimization. When the working state of the wall breaker changes or the used material changes, repeat step 6 above to realize the dynamic adjustment of the cancellation signal and ensure effective noise suppression under different working conditions.

[0114] Exemplarily, the original noise waveform data during the operation of the wall breaker is acquired by a sensor at a sampling rate of 44.1 kHz. The short-time Fourier transform is performed on the noise signal to extract 12 MFCC feature vectors. The feature vectors are input into an adaptive LMS filter, and 32 weight coefficients of the filter are dynamically adjusted according to the least mean square error criterion to generate a cancellation signal;

[0115] Calculate the Pearson correlation coefficient between the cancellation signal and the original noise. If it is higher than 0.8, the cancellation signal is output to the speaker for playback. The residual noise is obtained and fed back into the filter, and the weights are optimized in real time at a learning rate of 0.01, and iterated 50 times until the residual noise is lower than 30 dB;

[0116] The Apriori algorithm is used to mine the association rules between noise features and operating condition parameters such as the rotation speed and material viscosity of the wall breaker, with a support of 0.5 and a confidence of 0.8;

[0117] Based on the association rules, a BP neural network mapping model is established to monitor the operating conditions of the wall breaker in real time according to the changes in noise features. If the noise energy exceeds 20% of the normal value, an alarm is triggered and the abnormal data is recorded.

[0118] In this embodiment, multiple sound sensors are arranged around the wall breaker to collect noise signals in real time, and the preprocessing is performed to obtain standardized noise waveform data. Then, time-frequency analysis methods such as short-time Fourier transform are used to convert the noise signal from the time domain to the frequency domain, extract the key frequency band features, and construct a noise recognition model;

[0119] The machine learning algorithm is used to identify the noise type, and the noise feature template is matched to determine the noise category. According to the recognition result, the corresponding cancellation signal is retrieved from the preset cancellation signal template library, and the parameters are optimized to generate a cancellation signal that matches the original noise;

[0120] The cancellation signal is played through the speaker to be superimposed on the original noise to achieve noise reduction, and the adaptive filtering algorithm is used to optimize the cancellation signal in real time to adapt to the dynamic changes of the noise. At the same time, the difference between the residual noise after cancellation and the original noise is calculated to obtain the noise suppression amount, and iterative optimization is performed according to the comparison result with the target threshold;

[0121] In addition, the present invention also monitors the changes in the working state of the wall breaker and the material properties in real time, dynamically adjusts the noise recognition model and the cancellation signal template, ensures that the noise can be effectively suppressed under different working conditions, and significantly improves the noise reduction effect of the wall breaker and the user experience.

[0122] Embodiment 2

[0123] Such as Figures 2-4As shown in the figure, this embodiment provides a wall breaker for implementing the above-mentioned noise reduction method for a wall breaker, including a main body. A sound sensor for real-time collection of noise data generated during the operation of the wall breaker is installed on the main body. A noise reduction device for reducing the noise of the wall breaker is also provided on the main body. The noise reduction device includes a loudspeaker, a signal processing module, a cancellation signal generation and adjustment module, and an adaptive filtering module;

[0124] The signal processing module includes an analog-to-digital converter, a digital signal processor, and a memory;

[0125] The cancellation signal generation and adjustment module includes an electrically tunable attenuator, a phase adjuster, and a power combiner.

[0126] Further, the analog-to-digital converter is used to convert the analog noise signal collected by the sound sensor into a digital signal for subsequent digital signal processing;

[0127] The digital signal processor is used to execute a time-frequency analysis method to convert the noise signal from the time domain to the frequency domain, obtain the energy distribution characteristics of the noise in different frequency bands; it is also used to identify and classify the frequency domain characteristics of the noise according to a pre-established noise model library; and to retrieve a cancellation signal template by matching technology and adjust the amplitude and phase of the template;

[0128] The electrically tunable attenuator and the phase adjuster are used to adjust the amplitude and phase of the cancellation signal template according to the actual frequency and intensity parameters of the noise to generate a cancellation signal that matches the original noise;

[0129] The power combiner performs vector power combination on the adjusted cancellation signal and a reference signal, etc., to form a final cancellation signal;

[0130] The adaptive filtering module is used to implement an improved variable step-size least mean square adaptive filtering algorithm based on a radial basis function neural network to optimize the cancellation signal in real time and continuously correct the parameters of the cancellation signal to adapt to the dynamic changes of the noise.

[0131] This embodiment provides a wall breaker with a noise reduction function. A sound sensor is installed on the main body for real-time collection of noise data during operation. The noise reduction device includes a loudspeaker, a signal processing module, a cancellation signal generation and adjustment module, and an adaptive filtering module;

[0132] The analog-to-digital converter in the signal processing module converts the analog noise signal into a digital signal. The digital signal processor performs time-frequency analysis, identifies the noise characteristics, and retrieves the cancellation signal template. The electrically tunable attenuator and the phase adjuster adjust the cancellation signal according to the noise parameters, and the power combiner combines the final cancellation signal;

[0133] The adaptive filtering module uses an improved algorithm based on a radial basis function neural network to optimize and cancel signals in real time, adapt to noise changes, thereby effectively reducing the noise during the operation of the wall breaker and enhancing the user experience.

[0134] The specific embodiments of the invention have been described in detail above, but they are only examples. The invention is not limited to the specific embodiments described above. Those skilled in the art should understand that the above embodiments and the descriptions in the specification only illustrate the principles of the invention. Without departing from the spirit and scope of the invention, the invention will have various changes and improvements, and these changes and improvements fall within the scope of the claimed invention. The scope of protection of the invention is defined by the appended claims and their equivalents.

Claims

1. A noise reduction method for a wall breaking machine, characterized in that: The following steps are involved: S1. Collecting the noise signal generated during the working process of the wall breaking machine through a sound sensor, and preprocessing the noise signal to obtain standardized noise waveform data; S2. Converting the standardized noise waveform data from the time domain to the frequency domain using a time-frequency analysis method to extract key frequency band features reflecting noise characteristics; S3, using a machine learning algorithm to identify the noise type according to the key frequency band characteristics, and matching the noise feature template to determine the noise category; S4, retrieving a corresponding cancellation signal from a preset cancellation signal template library according to the noise category, and performing parameter optimization to generate a cancellation signal that matches the original noise; S5, playing the cancellation signal through a loudspeaker to superimpose it with the original noise to achieve noise cancellation, and adaptively optimizing the cancellation signal to adapt to noise changes; S6, calculating the difference between the residual noise after cancellation and the original noise to obtain a noise suppression amount, and performing iterative optimization of the cancellation signal according to a comparison result between the noise suppression amount and the target threshold; Real-time monitoring of the working status of the wall-breaking machine and changes in material properties, triggering the noise feature extraction and analysis process, dynamically adjusting the noise recognition model and the cancellation signal template, and achieving adaptive optimization of the cancellation signal; The working state parameters of the wall-breaking machine are correlated with the characteristic vectors of the noise signal, and the correlation rules between the two are mined through data mining algorithms to determine the relationship between the noise and the working state of the wall-breaking machine. According to the results of correlation analysis, a mapping model between the working state of the wall-breaking machine and the noise signal is established. The working state of the wall-breaking machine is monitored in real time through the changes in the noise signal. When the working state of the wall-breaking machine is detected to be abnormal, an early warning prompt is triggered in time. At the same time, the noise signal data under abnormal state is recorded for subsequent fault diagnosis and model optimization. When the working state of the wall-breaking machine changes or the material used changes, the above step S6 is repeated to achieve dynamic adjustment of the offset signal to ensure that noise can be effectively suppressed under different working conditions.

2. A wall breaking machine noise reduction method according to claim 1, characterized in that: The process of extracting the key frequency band features reflecting the noise characteristics in step S2 is specifically as follows: Short-time Fourier transform is used to convert the standardized noise waveform data from the time domain to the frequency domain to obtain the energy distribution characteristics of the noise signal in different frequency bands; According to the energy distribution characteristics of the noise signal in different frequency bands, the key frequency band characteristics that can reflect the noise characteristics are extracted, including the energy mean and variance statistical characteristics of the low-frequency, medium-frequency and high-frequency bands; Build a noise recognition model and use the extracted key frequency band features as the input of the model.

3. A wall breaking machine noise reduction method according to claim 1, characterized in that: The process of matching the noise feature template to determine the noise category in step S3 is specifically as follows: In the noise recognition process, if the key frequency band characteristics of the current noise have a high matching degree with the preset noise type feature template, the noise is judged to belong to the corresponding type and the category to which the noise belongs is obtained; Specifically, Sa1. According to the material properties and working state of the wall-breaking machine, a corresponding typical frequency domain feature template is selected from a pre-established noise model library; Sa2, using the dynamic time warping algorithm, the frequency domain feature data of the noise is matched and compared with the selected typical frequency domain feature template, and the similarity between the two is calculated; Sa3. If the similarity is greater than a preset threshold, the current noise is judged to belong to the noise category corresponding to the typical frequency domain feature template; if the similarity is less than the threshold, the current noise is matched with other typical frequency domain feature templates; The above process Sa1 to Sa3 is repeated until a typical frequency domain feature template with the largest similarity and greater than the threshold is found, and the category to which the noise belongs is determined.

4. A wall breaking machine noise reduction method according to claim 3, characterized in that: The step S3 further comprises: After determining the category to which the noise belongs, analyze the source and cause of the noise based on the category of the noise and the acoustic characteristic parameters of the noise in the noise model library.

5. A wall breaking machine noise reduction method according to claim 1, characterized in that: The process of generating the cancellation signal matching the original noise in step S4 is specifically as follows: Adjust the parameters of the obtained cancellation signal template, match the frequency, amplitude, and phase parameters of the template with the actual characteristic parameters of the noise signal, and generate a cancellation signal that matches the original noise signal; The generated cancellation signal is superimposed on the original noise signal, and the strength of the original noise signal is weakened or eliminated through the waveform cancellation principle to obtain a superimposed and cancelled signal.

6. A wall breaking machine noise reduction method according to claim 1, characterized in that: The process of adaptively optimizing the cancellation signal in step S5 is specifically as follows: After obtaining the signal after superposition and cancellation, the effect of the signal after superposition and cancellation is evaluated, the characteristic parameters of the residual noise are extracted, the noise reduction amount is calculated, and it is determined whether the noise cancellation effect reaches a preset threshold; If the noise cancellation effect does not reach the preset threshold, the parameters of the cancellation signal are further optimized until the noise cancellation effect reaches the preset threshold, and the final noise-reduced signal is output.

7. A wall breaking machine noise reduction method according to claim 1, characterized in that: The specific process of iterative optimization of the cancellation signal in step S6 is: Calculate the difference in energy between the residual noise signal and the original noise signal in each frequency band to obtain the noise suppression amount in each frequency band; The noise suppression amount in each frequency band is weighted averaged to obtain the total noise suppression amount, which is used as an indicator to measure the noise suppression effect; The total noise suppression amount is compared with a preset noise suppression target threshold value, and if the noise suppression amount is lower than the target threshold value, it is determined that the noise suppression effect is not ideal; If the noise suppression effect is not ideal, an adaptive filtering algorithm is used to optimize the cancellation signal, and the residual noise is minimized by adjusting the amplitude and phase of the cancellation signal; According to the optimized cancellation signal, the above process is repeated until the total noise suppression amount is higher than or equal to the target threshold. If the total noise suppression amount is higher than or equal to the target threshold, it is judged that the noise suppression effect reaches the expectation and the current cancellation signal is maintained.

8. A wall-breaking machine, used to implement the wall-breaking machine noise reduction method according to any one of claims 1 to 7, characterized in that: The invention comprises a main body, on which a sound sensor for real-time acquisition of noise data generated during the working process of the wall-breaking machine is installed, and a noise reduction device for reducing the noise of the wall-breaking machine is also arranged on the main body, and the noise reduction device comprises a speaker, a signal processing module, a cancellation signal generation and adjustment module and an adaptive filtering module; The signal processing module includes an analog-to-digital converter, a digital signal processor and a memory; The cancellation signal generation and adjustment module includes an electrically adjustable attenuator, a phase adjuster and a power synthesizer; The analog-to-digital converter is used to convert the analog noise signal collected by the sound sensor into a digital signal for subsequent digital signal processing; The digital signal processor is used to perform a time-frequency analysis method to convert the noise signal from the time domain to the frequency domain, and obtain the energy distribution characteristics of the noise in different frequency bands; it is also used to identify and classify the frequency domain characteristics of the noise according to a pre-established noise model library; and the matching technology is used to retrieve the cancellation signal template and adjust the amplitude and phase of the template; The electrically adjustable attenuator and phase adjuster are used to adjust the amplitude and phase of the cancellation signal template according to the actual frequency and intensity parameters of the noise, so as to generate a cancellation signal matching the original noise; The power synthesizer performs vector power synthesis on the adjusted cancellation signal and the reference signal to form a final cancellation signal; The adaptive filtering module is used to implement an improved variable step size minimum mean square adaptive filtering algorithm based on radial basis function neural network, optimize the cancellation signal in real time, and continuously correct the parameters of the cancellation signal to adapt to the dynamic changes of noise; The adaptive filtering module monitors the working state of the wall-breaking machine and the changes in material properties in real time, triggers the noise feature extraction and analysis process, dynamically adjusts the noise recognition model and the cancellation signal template, and realizes the adaptive optimization of the cancellation signal; The working state parameters of the wall-breaking machine are correlated with the characteristic vectors of the noise signal, and the correlation rules between the two are mined through data mining algorithms to determine the relationship between the noise and the working state of the wall-breaking machine. According to the results of correlation analysis, a mapping model between the working state of the wall-breaking machine and the noise signal is established. The working state of the wall-breaking machine is monitored in real time through the changes in the noise signal. When the working state of the wall-breaking machine is detected to be abnormal, an early warning prompt is triggered in time. At the same time, the noise signal data under abnormal state is recorded for subsequent fault diagnosis and model optimization. When the working state of the wall-breaking machine changes or the material used changes, the above step S6 is repeated to achieve dynamic adjustment of the offset signal to ensure that noise can be effectively suppressed under different working conditions.

Images