Intelligent control system and method for rapping hammer

Abstract

The invention provides an intelligent control system and method for a rapping hammer, and the system comprises a detection module which is used for detecting the working state of the rapping hammer to generate an analog electric signal; the analog-to-digital converter is used for converting the analog electric signal into a digital signal; the intelligent control module is deployed on the background server and is used for executing the following steps to remotely and intelligently control the rapping hammer: preprocessing the digital signal to obtain a to-be-analyzed signal, the preprocessing at least comprising filtering and denoising; performing statistical analysis on the to-be-analyzed signal to obtain a statistical analysis result; judging the working state of the rapping hammer according to the statistical analysis result; and according to the working state, generating an intelligent instruction for controlling the rapping hammer so as to control the working state of the rapping hammer. Therefore, the real-time performance and the continuity of monitoring are at least improved, and when a fault or an abnormal condition is found, the system can also trigger an alarm or maintenance process in time, so that the normal operation of equipment is further guaranteed.

Description

Technical Field

[0001] The present application relates to the field of intelligent control technology, and in particular to an intelligent control system and method for a rapping hammer. Background Art

[0002] As a dust removal tool widely used in industrial equipment, the vibrating hammer removes dust accumulation on the surface of the equipment through periodic knocking action, thereby ensuring the normal operation of the equipment and extending its service life. To this end, during the working process of the vibrating hammer, its working status must be monitored and controlled in real time to ensure the normal operation and maintenance management of the cleaning equipment. However, under the existing technical conditions, the monitoring and control of the vibrating hammer mostly rely on manual operation, which not only leads to a lag in reaction speed, but also has many deficiencies in accuracy. Summary of the invention

[0003] The purpose of this application is to propose an intelligent control system and method for a rapping hammer, so as to solve or alleviate the technical problems existing in the prior art.

[0004] The embodiment of the present application provides an intelligent control system for a rapping hammer, which includes:

[0005] A detection module, used for detecting the working state of the rapping hammer to generate an analog electrical signal;

[0006] An analog-to-digital converter, used for converting the analog electrical signal into a digital signal;

[0007] The intelligent control module is deployed on the background server and is used to perform the following steps to remotely and intelligently control the rapping hammer:

[0008] Preprocessing the digital signal to obtain a signal to be analyzed, wherein the preprocessing includes at least filtering and denoising;

[0009] Performing statistical analysis on the signal to be analyzed to obtain statistical analysis results;

[0010] Determine the working state of the rapping hammer according to the statistical analysis result;

[0011] According to the working state, an intelligent instruction for controlling the rapping hammer is generated to control the working state of the rapping hammer.

[0012] The embodiment of the present application provides an intelligent control method for a rapping hammer, which includes:

[0013] Detecting the working state of the rapping hammer to generate an analog electrical signal;

[0014] Converting the analog electrical signal into a digital signal;

[0015] Preprocessing the digital signal to obtain a signal to be analyzed, wherein the preprocessing includes at least filtering and denoising;

[0016] Performing statistical analysis on the signal to be analyzed to obtain statistical analysis results;

[0017] Determine the working state of the rapping hammer according to the statistical analysis result;

[0018] According to the working state, an intelligent instruction for controlling the rapping hammer is generated to control the working state of the rapping hammer.

[0019] The rapping hammer intelligent control system provided by the embodiment of the present application can detect the working state of the rapping hammer in real time based on the detection module in the system and generate an analog electrical signal. This step automates the monitoring work that originally needed to be performed manually, greatly improving the real-time and continuity of monitoring. Through real-time monitoring, the system can promptly detect abnormal changes in the working state of the rapping hammer, thereby avoiding the lag that may be caused by manual monitoring. In addition, the analog-to-digital converter converts the analog electrical signal into a digital signal, providing a basis for subsequent intelligent processing. The processing of digital signals is more accurate and flexible, which is convenient for the computer system to perform in-depth analysis and processing. Furthermore, the intelligent control module pre-processes the digital signal, including steps such as filtering and denoising, effectively removing interference and noise in the signal, and improving the purity and accuracy of the signal. This step is crucial to ensure the reliability of subsequent statistical analysis results. Finally, the intelligent control module performs statistical analysis on the pre-processed signal, and extracts key information reflecting the working state of the rapping hammer through complex algorithms and models. This process is more objective and accurate than manual judgment, and can capture subtle changes that are difficult to detect manually. Further based on the statistical analysis results, the system can intelligently judge the working status of the vibrating hammer, including normal, abnormal, faulty and other different situations. This intelligent judgment is not only fast but also accurate, providing strong support for the subsequent generation of control instructions. Moreover, the intelligent control module is deployed on the background server, which can realize remote intelligent control of the vibrating hammer. This feature makes the system free from geographical restrictions and can monitor and control the vibrating hammer anytime and anywhere. At the same time, remote intelligent control also reduces the risk and cost of on-site operations and improves work efficiency. According to the determined working status of the vibrating hammer, the system can automatically generate corresponding intelligent instructions and send them to the control system of the vibrating hammer. These instructions can accurately adjust the operating parameters of the vibrating hammer, such as vibration frequency, amplitude, etc., to ensure that it is in the best working state. When a fault or abnormal situation is found, the system can also trigger an alarm or maintenance process in time to further ensure the normal operation of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Hereinafter, some specific embodiments of the present application will be described in detail in an exemplary and non-limiting manner with reference to the accompanying drawings. The same reference numerals in the accompanying drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the accompanying drawings:

[0021] Figure 1 This is a flow chart of an intelligent control system for a rapping hammer according to an embodiment of the present application.

[0022] Figure 2 A schematic flow chart of an intelligent control method for a rapping hammer according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the embodiments of the present application should fall within the scope of protection of the embodiments of the present application.

[0024] Figure 1 This is a flow chart of an intelligent control system for a rapping hammer according to an embodiment of the present application. Figure 1 As shown, it includes:

[0025] A detection module, used for detecting the working state of the rapping hammer to generate an analog electrical signal;

[0026] An analog-to-digital converter, used for converting the analog electrical signal into a digital signal;

[0027] The intelligent control module is deployed on the background server and is used to perform the following steps to remotely and intelligently control the rapping hammer:

[0028] Preprocessing the digital signal to obtain a signal to be analyzed, wherein the preprocessing includes at least filtering and denoising;

[0029] Performing statistical analysis on the signal to be analyzed to obtain statistical analysis results;

[0030] Determine the working state of the rapping hammer according to the statistical analysis result;

[0031] According to the working state, an intelligent instruction for controlling the rapping hammer is generated to control the working state of the rapping hammer.

[0032] The rapping hammer intelligent control system provided by the embodiment of the present application can detect the working state of the rapping hammer in real time based on the detection module in the system and generate an analog electrical signal. This step automates the monitoring work that originally needed to be performed manually, greatly improving the real-time and continuity of monitoring. Through real-time monitoring, the system can promptly detect abnormal changes in the working state of the rapping hammer, thereby avoiding the lag that may be caused by manual monitoring. In addition, the analog-to-digital converter converts the analog electrical signal into a digital signal, providing a basis for subsequent intelligent processing. The processing of digital signals is more accurate and flexible, which is convenient for the computer system to perform in-depth analysis and processing. Furthermore, the intelligent control module pre-processes the digital signal, including steps such as filtering and denoising, effectively removing interference and noise in the signal, and improving the purity and accuracy of the signal. This step is crucial to ensure the reliability of subsequent statistical analysis results. Finally, the intelligent control module performs statistical analysis on the pre-processed signal, and extracts key information reflecting the working state of the rapping hammer through complex algorithms and models. This process is more objective and accurate than manual judgment, and can capture subtle changes that are difficult to detect manually. Further based on the statistical analysis results, the system can intelligently judge the working status of the vibrating hammer, including normal, abnormal, faulty and other different situations. This intelligent judgment is not only fast but also accurate, providing strong support for the subsequent generation of control instructions. Moreover, the intelligent control module is deployed on the background server, which can realize remote intelligent control of the vibrating hammer. This feature makes the system free from geographical restrictions and can monitor and control the vibrating hammer anytime and anywhere. At the same time, remote intelligent control also reduces the risk and cost of on-site operations and improves work efficiency. According to the determined working status of the vibrating hammer, the system can automatically generate corresponding intelligent instructions and send them to the control system of the vibrating hammer. These instructions can accurately adjust the operating parameters of the vibrating hammer, such as vibration frequency, amplitude, etc., to ensure that it is in the best working state. When a fault or abnormal situation is found, the system can also trigger an alarm or maintenance process in time to further ensure the normal operation of the equipment.

[0033] Optionally, the detection module includes a current sensor, a voltage sensor, and a power sensor. The current sensor is used to detect the output current of the rapping hammer when it is working to generate a first current signal. The voltage sensor is used to detect the output voltage of the rapping hammer when it is working to generate a first voltage signal. The power sensor is used to detect the output power of the rapping hammer when it is working to generate a first power signal.

[0034] To this end, the above detection module includes current sensors, voltage sensors, and power sensors. The application of these sensors brings the following technical benefits to the rapping hammer intelligent control system:

[0035] (1) By simultaneously monitoring the output current (first current signal), output voltage (first voltage signal) and output power (first power signal) of the rapping hammer, the system can obtain multiple key parameters of the rapping hammer's working state. This multi-dimensional monitoring can more comprehensively reflect the actual working conditions of the rapping hammer and provide richer data support for subsequent intelligent analysis and judgment.

[0036] (2) Current, voltage and power are important indicators of the working performance of the rapping hammer. Their changes can directly reflect the working status of the rapping hammer. Through the detection of high-precision current sensors, voltage sensors and power sensors, it can be ensured that the acquired data is accurate and reliable, thereby improving the accuracy and reliability of the entire intelligent control system.

[0037] Optionally, the detection module also includes: a signal conditioning circuit for conditioning the first current signal, the first voltage signal, and the first power signal to generate a second current signal, a second voltage signal, and a second power signal, respectively, and the analog electrical signal includes the second current signal, the second voltage signal, and the second power signal.

[0038] Optionally, the output power is at least one of active power and reactive power.

[0039] Optionally, the detection sensor is mounted on a fixed base or a motor output end of the rapping hammer.

[0040] Optionally, the analog-to-digital converter includes an anti-aliasing filter, a sampling module, and a quantization module. The anti-aliasing filter is used to filter the analog electrical signal at half of a set sampling frequency to obtain a signal to be sampled. The sampling module is used to sample the signal to be sampled based on the set sampling frequency to obtain a sampling signal. The quantization module is used to map the sampling signal into a discrete sequence to convert the analog electrical signal into a digital signal.

[0041] To this end, in the rapping hammer intelligent control system, the analog-to-digital converter (ADC) is designed to include a combination of an anti-aliasing filter, a sampling module, and a quantization module, which has the following technical benefits:

[0042] (1) The introduction of the anti-aliasing filter effectively prevents the occurrence of aliasing by filtering out all frequency components higher than half of the set sampling frequency. Aliasing is a phenomenon in which high-frequency components are mistakenly interpreted as low-frequency components when an analog signal is converted to a digital signal, resulting in signal distortion. The use of the anti-aliasing filter ensures that the signal input to the sampling module is clean and meets the requirements, thereby improving the overall signal quality.

[0043] (2) The sampling module accurately samples the filtered signal based on the set sampling frequency. The selection of sampling frequency is directly related to the accuracy and resolution of the converted digital signal. By setting a suitable sampling frequency, it can ensure that the sampling process can accurately capture the changes in the signal and provide a reliable data basis for subsequent statistical analysis.

[0044] (3) The quantization module maps the sampled continuous signal into a discrete sequence, which is the core step of analog-to-digital conversion. The quantization process determines the accuracy and range of the digital signal. Through a sophisticated quantization strategy, the quantization error can be minimized, more signal details can be retained, and the converted digital signal can be closer to the original analog signal, improving the accuracy and reliability of the system.

[0045] (4) The entire analog-to-digital conversion process effectively reduces the impact of noise and interference on the signal through the synergistic effect of the three steps of filtering, sampling and quantization. The anti-aliasing filter removes high-frequency noise, and the sampling and quantization process further reduces the error and noise in the signal through precise operations, improves the signal-to-noise ratio, and provides a clearer and more accurate signal source for subsequent intelligent analysis and judgment.

[0046] Optionally, a metal shielding cover is provided around the analog-to-digital converter, and a shielding wire is used for the signal wire of the analog-to-digital converter, and the shielding wire at the signal input side and the signal output side of the analog-to-digital converter is suspended.

[0047] To this end, a metal shield is provided around the analog-to-digital converter, and a shielded wire is used for the signal line of the analog-to-digital converter. At the same time, the shielded wire on the signal input side and the signal output side of the analog-to-digital converter is ensured to be suspended, which has the following technical benefits:

[0048] (1) The metal shield can effectively isolate the interference of external electromagnetic fields on the internal circuit of the analog-to-digital converter. In the scenario of the rapping hammer, there are a large number of electromagnetic radiation sources, such as motors, transformers, etc. These radiation sources may generate electromagnetic interference and affect the normal operation of the analog-to-digital converter. The metal shield guides the external electromagnetic field to the ground through its conductivity and grounding, thereby protecting the analog-to-digital converter from interference.

[0049] Shielded cables further reduce electromagnetic radiation and crosstalk during signal transmission. The shielding layer can absorb or reflect electromagnetic waves, preventing the signal line from becoming a source of electromagnetic radiation or a source of reception. This is critical to maintaining signal integrity and accuracy.

[0050] (2) By reducing electromagnetic interference, the analog-to-digital converter can more accurately convert analog electrical signals into digital signals. Electromagnetic interference may cause problems such as signal distortion and increased noise, thereby affecting the accuracy of the conversion results. After using metal shielding covers and shielded cables, these problems are effectively alleviated and the signal quality is improved.

[0051] (3) Electromagnetic interference not only affects the accuracy of the signal, but also threatens the stability of the system. For example, strong electromagnetic interference may cause system malfunctions, freezes, and other failures. By taking the above shielding measures, the system's anti-interference ability is enhanced, thereby improving the system's stability and reliability.

[0052] (4) The metal shield and shielded wire also have certain lightning protection and anti-static functions. In thunderstorms or static electricity environments, these measures can protect the analog-to-digital converter from damage by lightning and static electricity discharge, ensuring the safe operation of the equipment.

[0053] Optionally, the intelligent control module includes a digital filtering unit, the digital filtering unit has an initial filter coefficient vector and an initialized covariance matrix, and the digital filtering unit performs the following steps to filter the digital signal:

[0054] Calculating a gain vector according to the digital signal and an initial covariance matrix;

[0055] Based on the gain vector, calculating a filter coefficient;

[0056] Based on the filter coefficient, filtering the digital signal to obtain a predicted output;

[0057] Calculating the error between the predicted output and the expected output;

[0058] The covariance matrix is ​​updated according to the error, and the gain vector is recalculated to update the filter coefficient, so as to re-filter the digital signal to obtain a new predicted output, and so on until the error is less than a set threshold, and the predicted output is used as the output of the filtering process.

[0059] To this end, an intelligent control module including a digital filtering unit is introduced into the intelligent control system of the rapping hammer, and filtering of digital signals is performed, which has the following technical benefits:

[0060] (1) The digital filter unit can effectively remove noise and interference components in the digital signal by adaptively adjusting the filter coefficients, thereby improving the signal-to-noise ratio and clarity of the signal. This is crucial for subsequent signal analysis and control decisions, because high-quality signals can more accurately reflect the working status of the rapping hammer.

[0061] (2) The adaptive filtering algorithm can automatically adjust the filtering parameters according to the characteristics of the input signal, which enables the system to adapt to different working environments and working conditions. For example, when the noise level in the working environment of the rapping hammer changes, the digital filtering unit can respond quickly and adjust the filtering strategy to maintain the stability of the signal quality. This adaptability enhances the robustness and adaptability of the system.

[0062] (3) By accurately filtering the digital signal, the intelligent control module can more accurately determine the working status of the rapping hammer and generate corresponding control instructions. This helps to achieve more precise control and adjustment, improve the working efficiency and cleaning effect of the rapping hammer. At the same time, since the filtering process reduces the influence of noise and interference, the generation of control instructions is also more stable and reliable.

[0063] (4) The above filtering algorithm can update the filter coefficients in real time at each sampling moment, which enables the system to respond quickly to changes in the input signal. In the intelligent control system of the vibrating hammer, this real-time and dynamic response capability is crucial for timely detection and handling of abnormal situations. For example, when the vibrating hammer is stuck or fails, the system can quickly identify and take corresponding control measures to prevent the situation from escalating.

[0064] (5) Traditional filtering methods often require manual setting of filtering parameters or complex debugging. The above filtering algorithm reduces the need for manual intervention by automatically adjusting the filtering coefficients, thereby reducing the complexity and maintenance cost of the system. At the same time, since the algorithm itself has self-learning and adaptive capabilities, it can maintain a high filtering effect for a long time without frequent adjustments.

[0065] Optionally, the intelligent control module includes a digital denoising unit, and the digital denoising unit performs the following steps to denoise the digital signal:

[0066] Based on a set sliding window, the output of the filtering process is sequentially intercepted according to a set step size to obtain a signal segment;

[0067] Based on the set denoising model, the signal segment is denoised in real time to obtain the signal to be analyzed.

[0068] Optionally, the digital denoising unit performs the following steps when denoising the signal segment in real time based on a set denoising model to obtain a signal to be analyzed:

[0069] Performing screening processing on the signal segment to decompose the signal segment into a plurality of intrinsic mode functions and residual signals;

[0070] Mapping the plurality of modal functions into a modal matrix, and performing singular value decomposition on the modal matrix to obtain a plurality of singular value matrices;

[0071] Calculating the energy of all singular value matrices to compare with a set energy threshold to determine the noise component signal and the dominant component signal in the signal;

[0072] The signal is reconstructed based on the dominant component and the residual signal to obtain the signal to be analyzed.

[0073] To this end, an intelligent control module including a digital denoising unit is introduced into the intelligent control system of the vibrating hammer, and a denoising method based on intrinsic mode function decomposition and singular value decomposition is used to further denoise the digital signal after filtering, which has the following technical benefits:

[0074] (1) By decomposing the signal segment into several intrinsic mode functions and residual signals, this method can analyze the components in the signal in more detail. Each mode function represents an inherent oscillation mode in the signal, while the residual signal contains non-oscillatory components such as the trend term or noise of the signal. This decomposition method makes the denoising process more accurate and can more effectively remove the noise components in the signal.

[0075] (2) After performing singular value decomposition on the modal matrix, the energy of each singular value matrix is ​​calculated and compared with the set energy threshold, so that the noise component and the dominant component in the signal can be automatically identified. This adaptive noise identification mechanism makes the denoising process more intelligent and can adapt to changes in different signal characteristics and noise levels.

[0076] (3) In the denoising process, only the noise component signal is removed, while the dominant component signal and the residual signal are retained for signal reconstruction. This method ensures that the denoised signal retains the effective information of the original signal as much as possible while removing the noise, thereby improving the fidelity and usability of the signal.

[0077] (4) The sliding window-based moving interception and real-time denoising process enable the system to immediately perform denoising after receiving the new filter processing output to obtain the signal to be analyzed. This real-time processing method improves the response speed and efficiency of the system, allowing the system to adapt to signal changes more quickly and make corresponding control decisions.

[0078] (5) After deep denoising, the signal to be analyzed is purer and more accurate, which enables the intelligent control module to more accurately judge the working state of the rapping hammer and generate more precise control instructions in the subsequent signal analysis and control decision-making process, thereby improving the control accuracy and stability of the system.

[0079] (6) This denoising method can not only effectively remove the noise components in the signal, but also adapt to the changes in different signal characteristics and noise levels. This enables the system to maintain high stability and reliability in a complex and changing working environment, and enhances the robustness of the system.

[0080] Optionally, the intelligent control module includes a statistical analysis model, and the statistical analysis model is used to perform the following steps to perform statistical analysis on the signal to be analyzed to obtain a statistical analysis result:

[0081] Extracting features from the signal to be analyzed to obtain time domain features;

[0082] Calculating statistics based on the time domain features;

[0083] Autocorrelation analysis is performed on the statistics to estimate the correlation between signal segments at different time intervals to obtain statistical analysis results.

[0084] To this end, an intelligent control module containing a statistical analysis model is introduced into the intelligent control system of the vibrating hammer, and the statistical analysis results are obtained by performing feature extraction, statistical calculation and autocorrelation analysis on the signal to be analyzed, which has the following technical benefits:

[0085] (1) The statistical analysis model first extracts features from the signal to be analyzed, especially the time domain features, which enables the system to have a deeper understanding of the basic properties and changing patterns of the signal. Time domain features such as mean, variance, kurtosis, skewness, etc. can reflect the statistical characteristics of the signal in the time dimension and provide a basis for subsequent analysis.

[0086] (2) Based on the extracted time domain features, the statistical analysis model further calculates statistics, such as mean and standard deviation, which can quantify the degree of change and stability of the signal. Through the calculation of statistics, the system can more accurately evaluate the change trend and fluctuation range of the signal, providing a basis for subsequent control decisions.

[0087] (3) Autocorrelation analysis of statistics is one of the important steps in the statistical analysis model. Autocorrelation analysis can estimate the correlation between signal segments at different time intervals and reveal the time dependence and periodicity of the signal. This is crucial for understanding the dynamic characteristics and stability of the vibrating hammer during operation. Through autocorrelation analysis, the system can identify the periodic components and trend changes in the signal, providing strong support for prediction and control.

[0088] (4) The statistical analysis results can be directly applied to the intelligent control of the vibration hammer. Through in-depth understanding and quantitative analysis of signal characteristics, the system can more accurately judge the working status and performance changes of the vibration hammer, thereby generating more precise control instructions. In addition, since the statistical analysis process has a fast calculation speed and real-time performance, the system can quickly respond to signal changes and make corresponding adjustments, thereby improving the response speed and accuracy of the control.

[0089] (5) The introduction of statistical analysis models enables the vibrating hammer intelligent control system to have stronger data processing and analysis capabilities. Through comprehensive analysis and in-depth understanding of the signal, the system can better adapt to changes in different working environments and working conditions, optimize control strategies and improve system performance. At the same time, the statistical analysis results can also be used for system fault diagnosis and predictive maintenance, further improving the system reliability and maintenance efficiency.

[0090] Optionally, when the intelligent control module judges the working status of the rapping hammer according to the statistical analysis results, a mapping relationship between the statistical analysis results and the working status table of the rapping hammer is established, and the working status of the rapping hammer is judged based on the mapping relationship, and the working status table includes the statistical characteristic range of normal operation, minor fault, major fault, maintenance, and overload.

[0091] To this end, in the rapping hammer intelligent control system, by establishing a mapping relationship between the statistical analysis results and the rapping hammer working state table, and judging the working state of the rapping hammer based on this mapping relationship, it has the following technical benefits:

[0092] (1) The working status table sets clear statistical feature ranges for different working states of the rapping hammer (such as normal operation, minor fault, major fault, maintenance, and overload). This enables the system to quickly and accurately determine the current working state of the rapping hammer based on the statistical analysis results and directly compare the working status table. This clear definition method reduces the subjectivity and uncertainty of human judgment and improves the accuracy and reliability of judgment.

[0093] (2) By establishing a mapping relationship, the system can monitor the statistical characteristics of the signal to be analyzed in real time and compare them with the statistical characteristic range in the working status table. Once the statistical characteristics are found to be out of the normal range, the system can immediately identify potential faults or abnormal conditions, thereby quickly starting the fault detection and diagnosis process. This efficient fault detection and diagnosis mechanism helps to find and solve problems in a timely manner, avoiding the expansion of faults and the aggravation of damage.

[0094] (3) Based on the judgment results of the working status table, the system can formulate corresponding maintenance strategies for different working conditions. For example, in normal working conditions, the system may take routine monitoring measures; in a minor fault state, the system may trigger an early warning and prompt the operator to check; in a serious fault or overload state, the system may immediately take shutdown protection measures to prevent further damage. This targeted maintenance strategy helps to optimize resource allocation and reduce unnecessary downtime and maintenance costs.

[0095] (4) The statistical analysis results are combined with the working status table of the vibrating hammer to achieve intelligent judgment and decision-making based on data. This intelligent processing method not only improves the automation level of the system, but also enables the system to respond more flexibly to changes in different working environments and working conditions. At the same time, with the accumulation of data and the deepening of analysis, the system can also continuously optimize the mapping relationship and judgment logic to improve the accuracy and intelligence level of judgment.

[0096] Optionally, the rapping hammer intelligent control system also includes: a rapping behavior detection module to detect the rapping behavior of the rapping hammer to generate rapping behavior detection data and send it to the intelligent control module, so that the intelligent control module merges the rapping behavior detection data with the statistical analysis results to determine the working status of the rapping hammer.

[0097] Optionally, the rapping behavior detection module includes at least one of a proximity sensor and a pressure sensor; wherein the proximity sensor is installed at a predetermined position on the path passed by the rapping hammer during rapping, so as to detect whether the rapping hammer performs at least one of a lifting action and a releasing action, so as to generate first rapping behavior detection data and send it to the intelligent control module; the pressure sensor is installed on the hammer head end face of the rapping hammer, so as to detect the pressure of the rapping hammer when the rapping hammer performs a hammering action and generate second pressure detection data to send to the intelligent control module.

[0098] The proximity sensor is, for example, installed in a lower box housing the rapping hammer and located where the hammer head of the rapping hammer passes, thereby achieving non-contact detection and avoiding influence on the rapping hammer.

[0099] Optionally, the intelligent control module performs the following steps to fuse the rapping behavior detection data with the statistical analysis results to determine the working state of the rapping hammer, including:

[0100] Based on principal component analysis, feature extraction is performed on the rapping behavior detection data to obtain rapping behavior characteristics, wherein the rapping behavior characteristics include rapping frequency, duration of lifting action, and acceleration data of releasing action;

[0101] Extracting vibration operation status characteristics from the statistical analysis results;

[0102] The rapping behavior feature and the rapping operation state feature are normalized and then spliced ​​to form a rapping fusion feature vector;

[0103] Based on the set modal number and penalty factor, performing variational modal decomposition on the vibration fusion eigenvector to obtain a variational modal function;

[0104] The variational modal function is matched with the working state table of the rapping hammer to determine the working state of the rapping hammer.

[0105] To this end, through the rapping behavior detection module (including proximity sensors and pressure sensors), the system can monitor the rapping behavior of the rapping hammer in real time, including key parameters such as lifting action, release action, and pressure during rapping. This real-time monitoring ensures the timeliness and accuracy of the data, providing a reliable basis for subsequent work status judgment.

[0106] The intelligent control module uses principal component analysis and other methods to extract features from the detection data, and extracts key features such as vibration frequency, duration, acceleration, and vibration force. These features can fully reflect the working status of the vibration hammer.

[0107] The system not only considers the statistical analysis results, but also combines the vibration behavior detection data, and fuses the data from different sources and dimensions into a unified vibration fusion feature vector through normalization processing. This data fusion method can make full use of the information from various data sources and improve the accuracy and comprehensiveness of state judgment.

[0108] The application of variational mode decomposition further enhances the system's analytical capabilities. Variational mode decomposition decomposes the fused eigenvectors into multiple variational mode functions, each of which represents a specific mode or stage of the vibrating hammer's working state. This method can reveal the internal structure and change law of the vibrating hammer's working state, providing more refined and in-depth information for state judgment.

[0109] The establishment of the working state table is based on a large amount of experimental data and accumulated experience, which can cover all possible working states of the rapping hammer. Therefore, the system can accurately identify the normal working state, abnormal state and fault state of the rapping hammer, and provide timely guidance for the maintenance and maintenance of the equipment.

[0110] The entire system realizes intelligent monitoring and judgment of the working status of the vibrating hammer, and can complete complex data processing and analysis without human intervention. This intelligent and automated design improves work efficiency, reduces labor costs, and improves the reliability and stability of the system.

[0111] Optionally, the rapping operation state characteristics may include frequency components and distribution of the rapping hammer during vibration.

[0112] The frequency components include the main frequency: the main frequency is the frequency component with the most concentrated energy in the vibration signal of the rapping hammer, which reflects the main vibration mode and operating frequency of the rapping hammer. The stability of the main frequency can indicate whether the rapping hammer is in a stable operating state.

[0113] The frequency distribution includes:

[0114] Frequency distribution range: The frequency distribution range indicates the extensiveness of the frequency components in the vibration signal of the rapping hammer. A wider frequency distribution range may mean that the vibration mode of the rapping hammer is more complex or there are multiple vibration sources. This may be related to the design, working state or environmental factors of the rapping hammer.

[0115] Spectral energy distribution: Spectral energy distribution shows the energy distribution of the vibration signal of the rapping hammer at different frequencies. By observing the spectral energy distribution, we can determine which frequency components contribute more to the vibration of the rapping hammer, and then analyze the vibration characteristics of the rapping hammer.

[0116] Sidebands: Sidebands refer to additional frequency components on both sides of the main frequency. The presence of sidebands may indicate the presence of nonlinear factors or interference in the vibration process of the rapping hammer. By analyzing the characteristics of the sidebands, we can further understand the vibration characteristics of the rapping hammer and potential sources of failure.

[0117] Optionally, when the rapping behavior detection data includes first rapping behavior detection data and second rapping behavior detection data, based on principal component analysis, feature extraction is performed on the first rapping behavior detection data and the second rapping behavior detection data, respectively, to obtain a first rapping behavior feature and a second rapping behavior feature, wherein the first rapping behavior feature includes rapping frequency, duration of a lifting action, and acceleration data of a releasing action, and the second rapping behavior feature includes rapping force, knocking displacement, and continuous knocking interval time data;

[0118] The first rapping behavior feature and the second rapping behavior feature are fused to obtain a global rapping behavior comprehensive feature, and the global rapping behavior comprehensive feature and the rapping operation state feature are normalized and then spliced ​​to form a rapping fusion feature vector.

[0119] Therefore, when extracting features through principal component analysis, the dimensionality reduction of the rapping behavior detection data can also be achieved to extract the main features (such as rapping frequency, duration of lifting action, acceleration data of release action). These features can represent the main information of rapping behavior, while removing redundancy and noise, which is helpful for subsequent analysis and processing.

[0120] The extracted rapping behavior features and rapping operation status features are normalized to eliminate the influence of different feature dimensions and numerical ranges, and then the normalized features are spliced ​​into a rapping fusion feature vector.

[0121] Furthermore, the input signal is decomposed into multiple variational mode functions through variational mode decomposition, each of which fluctuates around its center frequency and has a limited bandwidth. Variational mode functions can characterize different modes or components in the input signal. To this end, the vibration fusion eigenvector is decomposed into multiple mode functions with clear physical meanings, which represent different aspects or stages of the working state of the vibration hammer. Through variational mode decomposition, the internal structure and change law of the working state of the vibration hammer can be seen more clearly. Each variational mode function represents a specific mode or stage in the working state of the vibration hammer, which may correspond to different states such as normal operation, abnormality, and failure.

[0122] The variational modal function is matched with a predefined rapping hammer working state table, which is a database or lookup table containing different working states and their corresponding characteristics (such as statistics based on the variational modal function).

[0123] During matching, the similarity or distance between the variational mode function and each state in the working state table is calculated to find the best matching state as the current working state of the rapping hammer.

[0124] Optionally, when the intelligent control module generates an intelligent instruction to control the rapping hammer according to the working state to control the working state of the rapping hammer, the working state is converted into a feature vector, and an inner product operation is performed on the feature vector based on a set kernel function to increase the dimension of the feature vector, and a linear separation hyperplane is determined based on this, and the classification label of the working state is based on the linear separation hyperplane, and intelligent control instructions are generated based on this to adjust the operating parameters of the rapping hammer, or trigger a maintenance or fault handling process.

[0125] Therefore, in the intelligent control system of the vibrating hammer, the working state is converted into a feature vector, and the kernel function is used to perform inner product operation to achieve feature dimension increase, and then the linear separation hyperplane is determined as the classification label of the working state, and the intelligent control instructions are generated accordingly, which has the following technical benefits:

[0126] (1) By converting the working state into a feature vector and using the kernel function to perform dimensionality increase processing, the system can find the best classification boundary in a higher-dimensional space. This dimensionality increase processing can make different working states that were originally difficult to distinguish in low-dimensional space more separable in high-dimensional space, thereby improving the precision and accuracy of classification. This is crucial for accurately judging the working state of the rapping hammer and generating corresponding control instructions.

[0127] (2) The selection and use of kernel functions enables the system to learn complex relationships between data, rather than simple linear relationships. This nonlinear processing capability enables the system to better adapt to changes in different working environments and working conditions, and improves the system's generalization ability. Even when faced with unknown or new working conditions, the system can make reasonable classifications and judgments through similarity measurements.

[0128] (3) Based on the linearly separable hyperplane as the classification label of the working state, the system can quickly identify the current working state and generate intelligent control instructions accordingly. This intelligent decision-making mechanism enables the system to automatically adjust the operating parameters of the vibrating hammer according to different working states, or trigger corresponding maintenance or fault handling processes. This not only improves the automation level of the system, but also reduces the need for human intervention and the error rate.

[0129] (4) By real-time monitoring and analysis of the working status of the rapping hammer, the system can dynamically adjust the control strategy to adapt to the current working requirements. For example, under normal working conditions, the system may adopt energy-saving control strategies to reduce energy consumption; under mild fault conditions, the system may take early warning and preventive maintenance measures to prevent the fault from expanding; under severe fault or overload conditions, the system may immediately take shutdown protection measures to prevent further damage. This optimized control strategy helps to extend the service life of the rapping hammer and improve production efficiency.

[0130] (5) The intelligent control module can ensure that the rapping hammer can maintain a stable operating state under different working conditions through precise classification and intelligent decision-making mechanism. Even in the event of a fault or abnormal situation, the system can respond in time and take appropriate measures to deal with it, thus avoiding the risk of fault expansion and damage aggravation. This stability and reliability is one of the important advantages of the rapping hammer intelligent control system.

[0131] Figure 2 This is a flow chart of an intelligent control method for a rapping hammer according to an embodiment of the present application. Figure 2 As shown, it includes:

[0132] Detecting the working state of the rapping hammer to generate an analog electrical signal;

[0133] Converting the analog electrical signal into a digital signal;

[0134] Preprocessing the digital signal to obtain a signal to be analyzed, wherein the preprocessing includes at least filtering and denoising;

[0135] Performing statistical analysis on the signal to be analyzed to obtain statistical analysis results;

[0136] Determine the working state of the rapping hammer according to the statistical analysis result;

[0137] According to the working state, an intelligent instruction for controlling the rapping hammer is generated to control the working state of the rapping hammer.

[0138] Above Figure 2 For an exemplary explanation of each step, see the above Figure 1 Description.

[0139] The expressions "first", "second", "the first" or "the second" used in various embodiments of the present disclosure may modify various components regardless of order and / or importance, but these expressions do not limit the corresponding components. The above expressions are only configured for the purpose of distinguishing an element from other elements. For example, a first user device and a second user device represent different user devices, although both are user devices. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element without departing from the scope of the present disclosure.

[0140] When one element (e.g., a first element) is referred to as being "(operably or communicatively) coupled" or "(operably or communicatively) coupled to" or "connected to" another element (e.g., a second element), it is understood that the one element is directly connected to the other element or the one element is indirectly connected to the other element via yet another element (e.g., a third element). Conversely, it is understood that when an element (e.g., a first element) is referred to as being "directly connected" or "directly coupled" to another element (the second element), no element (e.g., a third element) is interposed between the two.

[0141] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. An intelligent control system for a rapping hammer, characterized in that: include: A detection module, used for detecting the working state of the rapping hammer to generate an analog electrical signal; An analog-to-digital converter, used for converting the analog electrical signal into a digital signal; The intelligent control module is deployed on the background server and is used to perform the following steps to remotely and intelligently control the rapping hammer: Preprocessing the digital signal to obtain a signal to be analyzed, wherein the preprocessing includes at least filtering and denoising; Performing statistical analysis on the signal to be analyzed to obtain statistical analysis results; Determine the working state of the rapping hammer according to the statistical analysis result; According to the working state, an intelligent instruction for controlling the rapping hammer is generated to control the working state of the rapping hammer.

2. The intelligent control system of a rapping hammer according to claim 1 is characterized in that: The detection module includes a current sensor, a voltage sensor, and a power sensor. The current sensor is used to detect the output current of the rapping hammer when it is working to generate a first current signal. The voltage sensor is used to detect the output voltage of the rapping hammer when it is working to generate a first voltage signal. The power sensor is used to detect the output power of the rapping hammer when it is working to generate a first power signal.

3. The intelligent control system of a rapping hammer according to claim 1 is characterized in that: The detection module also includes: a signal conditioning circuit for conditioning the first current signal, the first voltage signal, and the first power signal to generate a second current signal, a second voltage signal, and a second power signal, respectively, and the analog electrical signal includes the second current signal, the second voltage signal, and the second power signal.

4. The intelligent control system of a rapping hammer according to claim 1, characterized in that: The analog-to-digital converter includes an anti-aliasing filter, a sampling module, and a quantization module. The anti-aliasing filter is used to filter the analog electrical signal according to half of the set sampling frequency to obtain a signal to be sampled. The sampling module is used to sample the signal to be sampled based on the set sampling frequency to obtain a sampled signal. The quantization module is used to map the sampled signal into a discrete sequence to convert the analog electrical signal into a digital signal.

5. The intelligent control system for a rapping hammer according to claim 1 is characterized in that: The intelligent control module includes a digital filtering unit, the digital filtering unit has an initial filter coefficient vector and an initialized covariance matrix, and the digital filtering unit performs the following steps to filter the digital signal: Calculating a gain vector according to the digital signal and an initial covariance matrix; Based on the gain vector, calculating a filter coefficient; Based on the filter coefficient, filtering the digital signal to obtain a predicted output; Calculating the error between the predicted output and the expected output; The covariance matrix is ​​updated according to the error, and the gain vector is recalculated to update the filter coefficient, so as to re-filter the digital signal to obtain a new predicted output, and so on until the error is less than a set threshold, and the predicted output is used as the output of the filtering process.

6. The intelligent control system for a rapping hammer according to claim 5, characterized in that: The intelligent control module includes a digital denoising unit, which performs the following steps to denoise the digital signal: Based on a set sliding window, the output of the filtering process is sequentially moved and intercepted according to a set step size to obtain a signal segment; Based on the set denoising model, the signal segment is denoised in real time to obtain the signal to be analyzed.

7. The intelligent control system for a rapping hammer according to claim 6, characterized in that: The digital denoising unit performs denoising on the signal segment in real time based on the set denoising model to obtain the signal to be analyzed, and executes the following steps: Performing screening processing on the signal segment to decompose the signal segment into a plurality of intrinsic mode functions and residual signals; Mapping the plurality of modal functions into a modal matrix, and performing singular value decomposition on the modal matrix to obtain a plurality of singular value matrices; Calculating the energy of all singular value matrices to compare with a set energy threshold to determine the noise component signal and the dominant component signal in the signal; The signal is reconstructed based on the dominant component and the residual signal to obtain the signal to be analyzed.

8. The intelligent control system for a rapping hammer according to claim 1, characterized in that: The rapping hammer intelligent control system also includes: a rapping behavior detection module for detecting the rapping behavior of the rapping hammer, so as to generate rapping behavior detection data and send it to the intelligent control module, so that the intelligent control module integrates the rapping behavior detection data with the statistical analysis results to determine the working status of the rapping hammer.

9. The intelligent control system for a rapping hammer according to claim 1, characterized in that: The intelligent control module performs the following steps to fuse the rapping behavior detection data with the statistical analysis results to determine the working state of the rapping hammer, including: Based on principal component analysis, feature extraction is performed on the rapping behavior detection data to obtain rapping behavior characteristics, wherein the rapping behavior characteristics include rapping frequency, duration of lifting action, and acceleration data of releasing action; Extracting vibration operation status characteristics from the statistical analysis results; The rapping behavior characteristics and the rapping operation state characteristics are normalized and then spliced ​​to form a rapping fusion feature vector; based on the set modal number and penalty factor, the rapping fusion feature vector is subjected to variational modal decomposition to obtain a variational modal function; The variational modal function is matched with the working state table of the rapping hammer to determine the working state of the rapping hammer.

10. A rapping hammer intelligent control method, characterized in that: include: Detecting the working state of the rapping hammer to generate an analog electrical signal; Converting the analog electrical signal into a digital signal; Preprocessing the digital signal to obtain a signal to be analyzed, wherein the preprocessing includes at least filtering and denoising; Performing statistical analysis on the signal to be analyzed to obtain statistical analysis results; Determine the working state of the rapping hammer according to the statistical analysis result; According to the working state, an intelligent instruction for controlling the rapping hammer is generated to control the working state of the rapping hammer.

Images