Thermal power plant coal conveying process control system and method with anti-interference capability

Abstract

The embodiment of the invention provides a thermal power plant coal conveying process control system and method with anti-interference capability, the motor rotating speed signal of a belt conveyor is filtered by establishing a signal filter so as to reduce the influence of external interference on the signal, and meanwhile, a magnetic field intensity detector is arranged on the belt conveyor so as to reduce the interference of the magnetic field intensity detector on the belt conveyor. When it is detected that the mean value of the magnetic field intensity in the preset period is larger than a preset threshold value, the signal processing technology based on deep learning is further adopted to conduct frequency domain feature analysis on the magnetic field intensity signals, filtering parameters of a signal filter are updated in a self-adaptive mode, and therefore more accurate filtering processing is conducted on the motor rotating speed signals; and therefore, the accuracy and the stability of controlling the running speed of the belt conveyor are improved. In this way, different electromagnetic interference environments can be dynamically adapted, it is ensured that the signal can still keep a high signal-to-noise ratio under the complex working condition, and therefore the anti-interference capacity and the operation efficiency of the whole coal conveying process are improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of coal conveying process control, and more specifically, to a coal conveying process control system and method for a thermal power plant with anti-interference ability. Background Art

[0002] In the daily operation of a thermal power plant, the coal conveying system, as a key link in the entire power generation process, is responsible for transporting coal from the storage area to the power generation boiler. Its operating efficiency and stability are directly related to the production capacity and economic benefits of the entire power plant. Among them, the belt conveyor, as the main transmission equipment of the coal conveying system, the control and management of its operating state directly affect the power generation efficiency of the entire power plant. Traditionally, the PID control algorithm is usually used to adjust the motor speed of the belt conveyor to achieve stable control of the coal conveying flow. However, in the actual operation process, the motor speed signal of the belt conveyor is often affected by various electromagnetic interferences from the external environment, such as magnetic field changes generated by other electrical equipment, radio waves, and other forms of electromagnetic noise, resulting in fluctuations in the motor speed signal, and further affecting the precise control of the operating speed of the belt conveyor.

[0003] In order to improve the anti-interference ability of the motor speed signal of the belt conveyor, in the prior art, a hardware filter or a software algorithm is usually used to filter out unnecessary noise in the signal. However, this traditional signal filtering method is often difficult to completely eliminate complex dynamic interferences. Especially in the case where the interference sources are variable, fixed filtering parameters may not be able to adapt to different interference conditions, resulting in poor filtering effects and being more powerless in the face of strong or sudden electromagnetic interferences.

[0004] Therefore, an optimized coal conveying process control system and method for a thermal power plant with anti-interference ability are expected. Summary of the Invention

[0005] The present invention aims to at least solve one of the technical problems existing in the prior art, and provides a coal conveying process control system and method for a thermal power plant with anti-interference ability.

[0006] In a first aspect, the embodiments of the present invention provide a coal conveying process control method for a thermal power plant with anti-interference ability, including:

[0007] Obtain the motor speed signal of the belt conveyor;

[0008] Establish a signal filter, the signal filter having initial filtering parameters, the initial filtering parameters including an initial bandwidth and an initial center frequency;

[0009] Obtain the magnetic field intensity signal collected by a magnetic field intensity detector deployed on the belt conveyor;

[0010] In response to the average magnetic field intensity of the magnetic field intensity signal within a preset period being greater than a preset threshold, based on the spectral characteristics of the magnetic field intensity signal, update the initial filtering parameters of the signal filter to obtain an updated signal filter;

[0011] Use the updated signal filter to perform filtering processing on the motor speed signal to obtain a filtered motor speed signal;

[0012] Input the filtered motor speed signal into a PID controller to control the running speed of the belt conveyor.

[0013] In some possible embodiments, based on the spectral characteristics of the magnetic field intensity signal, updating the initial filtering parameters of the signal filter to obtain an updated signal filter includes:

[0014] Perform frequency-domain feature analysis on the magnetic field intensity signal to obtain a magnetic field intensity signal spectral feature map;

[0015] Perform feature selection based on the activity of the feature neighborhood on the magnetic field intensity signal spectral feature map to obtain a sparsified magnetic field intensity signal spectral feature map;

[0016] Generate optimized filtering parameters based on the sparsified magnetic field intensity signal spectral feature map;

[0017] Update the initial filtering parameters of the signal filter with the optimized filtering parameters to obtain the updated signal filter.

[0018] In some possible embodiments, performing frequency-domain feature analysis on the magnetic field intensity signal to obtain a magnetic field intensity signal spectral feature map includes:

[0019] Perform a fast Fourier transform on the magnetic field intensity signal to obtain a magnetic field intensity signal spectrum;

[0020] Extract spectral features from the magnetic field intensity signal spectrum to obtain the magnetic field intensity signal spectral feature map.

[0021] In some possible embodiments, extracting spectral features from the magnetic field intensity signal spectrum to obtain the magnetic field intensity signal spectral feature map includes:

[0022] Input the magnetic field intensity signal spectrum into a spectral feature extractor based on a dilated convolutional neural network model to obtain the magnetic field intensity signal spectral feature map.

[0023] In some possible embodiments, performing feature selection based on the activity of the feature neighborhood on the magnetic field intensity signal spectral feature map to obtain a sparsified magnetic field intensity signal spectral feature map includes:

[0024] Perform feature decoupling and feature flattening on the spectral feature map of the magnetic field intensity signal to obtain a set of local spectral feature vectors of the magnetic field intensity signal;

[0025] Based on the feature importance of each local spectral feature vector of the magnetic field intensity signal in the set of local spectral feature vectors of the magnetic field intensity signal, perform serial rearrangement on the set of local spectral feature vectors of the magnetic field intensity signal to obtain a descending sequence of local spectral feature vectors of the magnetic field intensity signal;

[0026] Based on the neighborhood feature activity of each local spectral feature vector of the magnetic field intensity signal in the descending sequence of local spectral feature vectors of the magnetic field intensity signal, perform feature selection sparse aggregation on the descending sequence of local spectral feature vectors of the magnetic field intensity signal to obtain the sparse spectral feature map of the magnetic field intensity signal.

[0027] In some possible embodiments, based on the feature importance of each local spectral feature vector of the magnetic field intensity signal in the set of local spectral feature vectors of the magnetic field intensity signal, performing serial rearrangement on the set of local spectral feature vectors of the magnetic field intensity signal to obtain a descending sequence of local spectral feature vectors of the magnetic field intensity signal includes:

[0028] Input each local spectral feature vector of the magnetic field intensity signal in the set of local spectral feature vectors of the magnetic field intensity signal into an importance measurement module to obtain a set of local spectral feature importance score values of the magnetic field intensity signal;

[0029] Based on the set of local spectral feature importance score values of the magnetic field intensity signal, perform descending sorting on the set of local spectral feature vectors of the magnetic field intensity signal to obtain the descending sequence of local spectral feature vectors of the magnetic field intensity signal.

[0030] In some possible embodiments, based on the neighborhood feature activity of each local spectral feature vector of the magnetic field intensity signal in the descending sequence of local spectral feature vectors of the magnetic field intensity signal, performing feature selection sparse aggregation on the descending sequence of local spectral feature vectors of the magnetic field intensity signal to obtain the sparse spectral feature map of the magnetic field intensity signal includes:

[0031] Based on the neighborhood features of each local spectral feature vector of the magnetic field intensity signal in the descending sequence of local spectral feature vectors of the magnetic field intensity signal, calculate the feature neighborhood activity of each local spectral feature vector of the magnetic field intensity signal to obtain a sequence of local spectral feature neighborhood activities of the magnetic field intensity signal;

[0032] Based on the sequence of the neighborhood activity of the local spectral features of the magnetic field strength signal, perform feature selection on the descending sequence of the local spectral feature vectors of the magnetic field strength signal to obtain the descending sequence of the selected local spectral feature vectors of the magnetic field strength signal;

[0033] Perform feature shape reshaping on the descending sequence of the selected local spectral feature vectors of the magnetic field strength signal to obtain the sparse magnetic field strength signal spectral feature map.

[0034] In some possible embodiments, based on the sparse magnetic field strength signal spectral feature map, generate optimized filtering parameters, including:

[0035] Input the sparse magnetic field strength signal spectral feature map into a filtering parameter optimization module based on a decoder to obtain the decoded value of the optimized filtering parameters.

[0036] In a second aspect, an embodiment of the present invention provides a coal conveying process control system for a thermal power plant with anti-interference ability, including:

[0037] A motor speed signal acquisition module for acquiring the motor speed signal of the belt conveyor;

[0038] A signal filter establishment module for establishing a signal filter, the signal filter having initial filtering parameters, the initial filtering parameters including an initial bandwidth and an initial center frequency;

[0039] A magnetic field strength signal acquisition module for acquiring the magnetic field strength signal collected by a magnetic field strength detector deployed on the belt conveyor;

[0040] A filtering parameter adjustment module for, in response to the average magnetic field strength of the magnetic field strength signal within a preset period being greater than a preset threshold, updating the initial filtering parameters of the signal filter based on the spectral characteristics of the magnetic field strength signal to obtain an updated signal filter;

[0041] A signal filtering processing module for filtering the motor speed signal using the updated signal filter to obtain a filtered motor speed signal;

[0042] An operating speed control module for inputting the filtered motor speed signal into a PID controller to control the operating speed of the belt conveyor.

[0043] In some possible embodiments, the filtering parameter adjustment module is specifically further configured to:

[0044] Perform frequency domain feature analysis on the magnetic field strength signal to obtain a magnetic field strength signal spectral feature map;

[0045] Perform feature selection based on the activity of the feature neighborhood on the spectrum feature map of the magnetic field intensity signal to obtain a sparsified spectrum feature map of the magnetic field intensity signal;

[0046] Generate optimized filtering parameters based on the sparsified spectrum feature map of the magnetic field intensity signal;

[0047] Update the initial filtering parameters of the signal filter with the optimized filtering parameters to obtain the updated signal filter.

[0048] Compared with the prior art, the coal conveying process control system and method for a thermal power plant with anti-interference ability provided by the embodiments of the present invention establish a signal filter to filter the motor speed signal of the belt conveyor to reduce the influence of external interference on the signal. At the same time, a magnetic field intensity detector is deployed on the belt conveyor. When it is detected that the average magnetic field intensity within a preset period is greater than a preset threshold, a signal processing technology based on deep learning is further used to perform frequency-domain feature analysis on the magnetic field intensity signal. Thus, based on the spectrum characteristics of the magnetic field intensity signal, the filtering parameters of the signal filter are adaptively updated to perform more accurate filtering on the motor speed signal, thereby improving the accuracy and stability of the control of the running speed of the belt conveyor. In this way, it can dynamically adapt to different electromagnetic interference environments, ensure that the signal can still maintain a high signal-to-noise ratio under complex working conditions, and thus improve the anti-interference ability and operating efficiency of the entire coal conveying process. Description of the Drawings

[0049] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0050] Figure 1 It is a flowchart of a coal conveying process control method for a thermal power plant with anti-interference ability according to an embodiment of the present invention;

[0051] Figure 2 It is a flowchart of sub-step S4 of a coal conveying process control method for a thermal power plant with anti-interference ability according to an embodiment of the present invention;

[0052] Figure 3 It is a data flow diagram of sub-step S4 of a coal conveying process control method for a thermal power plant with anti-interference ability according to an embodiment of the present invention;

[0053] Figure 4 It is a flowchart of sub-step S41 of a coal conveying process control method for a thermal power plant with anti-interference ability according to an embodiment of the present invention;

[0054] Figure 5 It is a flowchart of sub-step S42 of the coal conveying process control method for a thermal power plant with anti-interference ability according to an embodiment of the present invention;

[0055] Figure 6 It is a block diagram of the coal conveying process control system for a thermal power plant with anti-interference ability according to an embodiment of the present invention. Detailed implementation manners

[0056] To enable those skilled in the art to better understand the technical solutions of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the described embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention.

[0057] Unless otherwise specifically stated, the technical terms or scientific terms used in the embodiments of the present invention should be the ordinary meanings understood by those with ordinary skills in the field to which the present invention belongs. The "including" or "comprising" used in the embodiments of the present invention neither limits the mentioned shapes, numbers, steps, actions, operations, components, originals and / or their groups, nor excludes the appearance or addition of one or more other different shapes, numbers, steps, actions, operations, components, originals and / or their groups, or the addition of these. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity and order of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present invention, the meaning of "a plurality" is two or more, unless otherwise clearly and specifically defined.

[0058] Unless otherwise specifically stated, the relative settings, numerical expressions and values of the components and steps described in these embodiments do not limit the scope of the present invention. At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship. For technologies, methods and devices known to those of ordinary skill in the relevant fields, they may not be discussed in detail, but in appropriate cases, the shown technologies, methods and devices should be regarded as part of the authorization specification. In all the examples shown and discussed here, any specific other example may have different values. It should be noted that similar symbols and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0059] In the description of the embodiments of the present invention, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In the embodiments of the present invention, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in the embodiments of the present invention and the features of different embodiments or examples.

[0060] In the present invention, flowcharts are used to illustrate the operations performed by the system according to the embodiments of the present invention. It should be understood that the operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, as needed, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0061] Next, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited by the exemplary embodiments described herein.

[0062] As mentioned in the above background art, in order to enhance the anti-noise performance of the motor speed signal of the belt conveyor, in the prior art, a hardware filtering device or a programming algorithm is usually used to eliminate the useless noise in the signal. However, this traditional signal filtering method often fails to completely eliminate complex dynamic interference. Especially when the interference source is unstable, the preset filtering settings may not be adjusted flexibly to match the changing interference situation, resulting in poor purification effect. In the case of strong or sudden electromagnetic interference, the limitations of the traditional method are more obvious.

[0063] In view of the above technical problems, the present invention proposes an optimized coal conveying process control method for thermal power plants with anti-interference ability. By establishing a signal filter to filter the motor speed signal of the belt conveyor, the influence of external interference on the signal is reduced. At the same time, a magnetic field intensity detector is deployed on the belt conveyor. When the average magnetic field intensity within a preset period is detected to be greater than a preset threshold, a signal processing technology based on deep learning is further used to perform frequency-domain feature analysis on the magnetic field intensity signal. Then, based on the spectral characteristics of the magnetic field intensity signal, the filtering parameters of the signal filter are adaptively updated to perform more accurate filtering on the motor speed signal, thereby improving the accuracy and stability of the control of the running speed of the belt conveyor. In this way, it can dynamically adapt to different electromagnetic interference environments, ensure that the signal can still maintain a high signal-to-noise ratio under complex working conditions, and thus improve the anti-interference ability and operating efficiency of the entire coal conveying process.

[0064] Figure 1 FIG. is a flowchart of a coal conveying process control method for a thermal power plant with anti-interference ability according to an embodiment of the present invention. As Figure 1 shown, the coal conveying process control method for a thermal power plant with anti-interference ability includes the steps of: S1, obtaining the motor speed signal of the belt conveyor; S2, establishing a signal filter, the signal filter having initial filtering parameters, the initial filtering parameters including an initial bandwidth and an initial center frequency; S3, obtaining the magnetic field intensity signal collected by a magnetic field intensity detector deployed on the belt conveyor; S4, in response to the average magnetic field intensity of the magnetic field intensity signal within a preset period being greater than a preset threshold, updating the initial filtering parameters of the signal filter based on the spectral characteristics of the magnetic field intensity signal to obtain an updated signal filter; S5, using the updated signal filter to filter the motor speed signal to obtain a filtered motor speed signal; S6, inputting the filtered motor speed signal into a PID controller to control the running speed of the belt conveyor.

[0065] In the above coal conveying process control method for a thermal power plant with anti-interference ability, in step S1, the motor speed signal of the belt conveyor is obtained. It should be understood that the motor speed signal is the key basis for controlling the running speed of the belt conveyor. By accurately obtaining the motor speed signal, the actual running state of the belt conveyor can be understood in real time, which helps to achieve precise regulation of the running speed of the belt conveyor and ensure the smooth progress of the coal conveying process.

[0066] To ensure that the acquired motor speed signal can accurately reflect the actual working conditions of the motor and provide reliable data support for subsequent filtering and PID control, it is first necessary to select a suitable sensor or encoder to detect the motor speed. This usually involves the selection of the installation location and the type of sensor. For belt conveyors, common detection methods include, but are not limited to, Hall effect sensors, incremental encoders, or absolute encoders. These sensors can directly or indirectly measure the number of rotations of the motor shaft, and then calculate the speed. For example, a Hall effect sensor can sense the magnetic field change generated each time a magnet fixed on the motor shaft passes by, and determine the speed by counting the number of such changes per unit time; while an encoder can convert the accurately measured rotation angle of the motor shaft into speed information.

[0067] After selecting the appropriate sensor and completing the installation, the next step is to set up the signal acquisition device. In modern industrial environments, data acquisition is usually completed by a PLC (programmable logic controller), DCS (distributed control system), or other dedicated data acquisition devices. These devices not only need to be able to receive analog or digital signals from the sensors, but also need to have certain data processing capabilities, such as signal amplification, analog-to-digital conversion (A / D conversion), and preliminary data filtering. This is because the original sensor output often contains some unwanted information or noise, and preliminary filtering can help reduce the burden of subsequent processing.

[0068] After setting up the data acquisition device, the next step is to establish a communication link. This step aims to ensure that the acquired motor speed signal can be smoothly transmitted to the central control system or other computer systems responsible for further processing. According to specific application scenarios and technical requirements, different communication protocols and network structures can be selected, such as Ethernet, MODBUS, PROFIBUS, etc. Ensuring the security and stability of the communication link is crucial, because any interruption or delay may affect the final control effect.

[0069] When all the hardware is ready, it enters the actual signal acquisition stage. At this time, the operator needs to start the data acquisition system and confirm that it correctly records the motor speed signal. During this period, the operating status of the system should be closely monitored, and the parameter settings should be adjusted in a timely manner to ensure that the acquired data has sufficient resolution and accuracy. To verify the validity of the data, short-term on-site tests can be carried out to evaluate the accuracy of the system by comparing the results of manual measurements with the data provided by the automated system.

[0070] In the above coal conveying process control method for thermal power plants with anti-interference ability, in step S2, a signal filter is established. The signal filter has initial filtering parameters, and the initial filtering parameters include an initial bandwidth and an initial center frequency. It should be understood that the present invention takes into account that the motor speed signal is prone to being affected by various external interferences during transmission, resulting in noise being mixed in the signal, thereby reducing the signal quality and affecting the accurate judgment of the motor speed. Therefore, the present invention filters the motor speed signal by establishing a signal filter to remove noise and improve the signal purity. In an embodiment of the invention, the signal filter is a band-pass filter, whose center frequency determines the main frequency range of the signal allowed to pass through the filter, and the bandwidth determines the frequency width of the passed signal. By reasonably setting the initial bandwidth and the initial center frequency, the filter can effectively filter the motor speed signal under the basic working conditions and reduce unnecessary noise interference.

[0071] Specifically, before establishing the filter, it is first necessary to conduct an in-depth analysis of the motor speed signal. Considering that different application scenarios and devices may generate signals with different characteristics. For a belt conveyor, the motor speed signal usually exhibits a periodic waveform, and its frequency is directly related to the actual speed of the motor. In addition, due to factors such as mechanical vibration and load changes, the signal may also contain a certain amount of random noise or harmonic components. Therefore, when designing the filter, it is necessary to fully understand these signal characteristics and determine the basic performance indicators of the filter accordingly, such as the passband range, stopband attenuation, etc.

[0072] Based on the above analysis results, the next step is to select a suitable filter type. In the field of industrial automation, common filter types include low-pass filters, high-pass filters, band-pass filters, and band-stop filters. For the motor speed signal, considering that the effective information within a specific frequency range needs to be retained while removing the interference components outside this range, the band-pass filter is a relatively ideal choice. It can effectively suppress the unwanted high-frequency noise and low-frequency drift while ensuring the passage of the useful signal.

[0073] After determining the filter type, it enters the specific parameter setting stage. The initial filtering parameters refer to a set of parameters preset according to the inherent characteristics of the motor speed signal without the influence of external interference sources, mainly including the initial bandwidth and the initial center frequency. Among them, the initial bandwidth defines the width of the frequency range allowed to pass through the filter, that is, the interval between the lower cut-off frequency and the upper cut-off frequency; while the initial center frequency refers to the frequency point where the effective signal is most likely to appear within this frequency range, usually corresponding to the frequency value corresponding to the rated speed of the motor. In order to reasonably set these two parameters, on the one hand, it is necessary to refer to the technical specification of the motor to understand the variation range of the speed under its normal operating conditions, and then deduce the corresponding frequency range; on the other hand, the motor speed signal samples during actual operation can be obtained through experimental means, and they can be processed using spectrum analysis tools to find out which frequency band the signal energy is mainly concentrated in. For example, the fast Fourier transform (FFT) algorithm can be used to calculate the frequency-domain representation of the signal, observe the position and distribution of the peaks in the spectrum diagram, and use this as an important basis for setting the initial center frequency.

[0074] However, relying solely on static data analysis is not enough because there are various unforeseen factors in the actual operating environment that may cause changes in signal characteristics. This requires leaving some leeway when setting the initial filtering parameters to make the filter have a certain degree of adaptability. For example, considering that the speed may fluctuate greatly during motor startup, stop, or load mutation, the initial bandwidth can be appropriately widened to ensure that even under extreme conditions, as many effective signals as possible can be retained. At the same time, attention should also be paid to avoiding too wide a bandwidth from introducing too much noise and affecting the final filtering effect.

[0075] In addition, the selection of the filter order also needs to be considered. The filter order determines the steepness of its frequency response curve. The higher the order of the filter, the faster the conversion between the passband and the stopband, but it also means a more complex structure and a higher implementation cost. Therefore, on the premise of meeting the filtering requirements, a lower-order filter should be selected as much as possible to ensure good filtering performance and simplify the system design.

[0076] In the above-mentioned coal transportation process control method of a thermal power plant with anti-interference ability, the step S3 obtains the magnetic field strength signal collected by the magnetic field strength detector deployed on the belt conveyor. It should be understood that the present invention takes into account that in actual applications, the electromagnetic environment of the thermal power plant is relatively complex, and there may be various electromagnetic field sources around the belt conveyor. The changes in the magnetic field strength generated by these electromagnetic field sources may interfere with the spectrum characteristics of the motor speed signal, thereby affecting the filtering effect of the filter. Therefore, in order to further improve the anti-interference ability of the system, the present invention deploys a magnetic field strength detector on the belt conveyor to collect the magnetic field strength signal, and monitors the changes in the electromagnetic environment around the belt conveyor in real time, so as to take corresponding countermeasures for different electromagnetic interference conditions, thereby ensuring the stability of the filtering effect.

[0077] In order to ensure that the obtained magnetic field strength signal can accurately reflect the electromagnetic interference in the actual environment and provide a reliable basis for the dynamic adjustment of subsequent filtering parameters, it is necessary to first select a suitable magnetic field strength detector. In industrial environments, common magnetic field strength detectors include Hall effect sensors, magnetoresistive sensors (MR), giant magnetoresistive (GMR) sensors, etc. These sensors have their own characteristics and are suitable for different application scenarios. For example, Hall effect sensors have been widely used in many occasions due to their low cost, high sensitivity and easy integration; magnetoresistive sensors are known for their high linearity and temperature stability; and giant magnetoresistive sensors are particularly suitable for detecting weak magnetic field changes due to their excellent sensitivity and resolution. For specific application scenarios such as belt conveyors, it is necessary to comprehensively consider factors such as the cost, size, power consumption, and measurement range of the detector to select the most suitable type.

[0078] After selecting the sensor, the next thing to consider is the installation location of the sensor. The ideal installation location should cover the main areas of the motor and its surroundings where electromagnetic interference may occur, and should not be affected by other irrelevant factors. Usually, the sensor is installed close to the motor to directly monitor the changes in the magnetic field from the motor itself. In addition, additional sensors should be arranged at key nodes of the belt conveyor, such as near the drive roller, around conductive parts, etc., to fully capture electromagnetic interference information from different sources. It is worth noting that the installation of the sensor should try to avoid blocking or changing the original mechanical structure to avoid affecting the normal operation of the equipment. The setting of the signal acquisition device can adopt the equipment configuration of the motor speed signal acquisition device in step S1.

[0079] In the above coal conveying process control method for thermal power plants with anti-interference ability, in step S4, in response to the average magnetic field intensity of the magnetic field intensity signal being greater than a preset threshold within a preset period, based on the spectral characteristics of the magnetic field intensity signal, the initial filtering parameters of the signal filter are updated to obtain an updated signal filter. Specifically, when it is detected that the average magnetic field intensity of the magnetic field intensity signal is greater than the preset threshold within the preset period, it indicates that there is strong electromagnetic interference around the belt conveyor. At this time, the original initial filtering parameters may not be able to effectively filter the motor speed signal. Therefore, the present invention further analyzes the spectral characteristics of the magnetic field intensity signal to dynamically update the parameters of the filter, enabling the filter to better adapt to the changing electromagnetic environment, improving the filtering effect on the motor speed signal, thereby more accurately obtaining the actual speed of the motor and ensuring the accuracy of the belt conveyor running speed control. Among them, Figure 2 FIG. Figure 2 is a flowchart of sub-step S4 of the coal conveying process control method for thermal power plants with anti-interference ability according to an embodiment of the present invention. Figure 3 FIG. Figure 3 is a schematic diagram of data flow of sub-step S4 of the coal conveying process control method for thermal power plants with anti-interference ability according to an embodiment of the present invention. As Figure 2 and Figure 3 shown, step S4 includes the steps of: S41, performing frequency-domain feature analysis on the magnetic field intensity signal to obtain a magnetic field intensity signal spectral feature map; S42, performing feature selection based on the activity of the feature neighborhood on the magnetic field intensity signal spectral feature map to obtain a sparsified magnetic field intensity signal spectral feature map; S43, generating optimized filtering parameters based on the sparsified magnetic field intensity signal spectral feature map; and S44, updating the initial filtering parameters of the signal filter with the optimized filtering parameters to obtain the updated signal filter.

[0080] Specifically, in step S41, frequency-domain feature analysis is performed on the magnetic field intensity signal to obtain a magnetic field intensity signal spectral feature map. Among them, Figure 4 FIG. Figure 4 is a flowchart of sub-step S41 of the coal conveying process control method for thermal power plants with anti-interference ability according to an embodiment of the present invention. As Figure 4 shown, step S41 includes the steps of: S411, performing a fast Fourier transform on the magnetic field intensity signal to obtain a magnetic field intensity signal spectrogram; and S412, extracting spectral features from the magnetic field intensity signal spectrogram to obtain the magnetic field intensity signal spectral feature map.

[0081] More specifically, in step S411, a fast Fourier transform is performed on the magnetic field intensity signal to obtain a magnetic field intensity signal spectrogram. It should be understood that in the present invention, considering that the magnetic field intensity signal presents amplitude values that change over time in the time domain and it is difficult to intuitively analyze its frequency components. In the complex electromagnetic environment of a thermal power plant, interference signals often have specific frequency characteristics. Therefore, in the present invention, a fast Fourier transform is further performed on the magnetic field intensity signal to convert the magnetic field intensity signal from the time domain to the frequency domain, generating a magnetic field intensity signal spectrogram. Among them, the abscissa of the magnetic field intensity signal spectrogram is frequency, and the ordinate is amplitude, thus clearly showing the distribution of each frequency component in the signal and the energy intensity, providing an intuitive and crucial basis for the subsequent parameter adjustment of the signal filter, and helping to improve the targeted filtering ability of the filter for interference signals.

[0082] More specifically, in a specific example of the present invention, step S412 includes: inputting the magnetic field intensity signal spectrogram into a spectral feature extractor based on a dilated convolutional neural network model to obtain a magnetic field intensity signal spectral feature map. Specifically, in order to more deeply explore the spectral features of the magnetic field intensity signal, such as the amplitude change pattern within a specific frequency range, the relative relationship between frequency components, etc., the present invention uses a dilated convolutional neural network model to construct a spectral feature extractor, and through a sliding convolutional operation on the magnetic field intensity signal spectrogram, to learn the key spectral features of the magnetic field intensity signal spectrogram, such as the main interference frequency, frequency distribution range, energy concentration degree, etc., to obtain a more representative magnetic field intensity signal spectral feature map. It should be understood that by introducing the dilated convolution operation, the dilated convolutional neural network model can increase the receptive field of the convolutional kernel without increasing the computational complexity, thereby capturing a wider range of spectral feature information and improving the accuracy and efficiency of feature extraction.

[0083] Specifically, in step S42, feature selection based on the activity of the feature neighborhood is performed on the magnetic field intensity signal spectral feature map to obtain a sparsified magnetic field intensity signal spectral feature map. It should be understood that in the present invention, considering that although the magnetic field intensity signal spectral feature map contains key spectral feature information, there are also some redundant or irrelevant noise interferences. Therefore, in order to further improve the quality of feature information and reduce the computational burden, the present invention adopts a feature selection method based on the activity of the feature neighborhood, and by analyzing the activity of the neighborhood of each feature point in the magnetic field intensity signal spectral feature map, that is, the information richness and change intensity of the area around the feature point, to perform feature screening, realizing the sparsification process of features, thereby reducing the subsequent computational amount, improving the computational efficiency, and at the same time avoiding the interference of redundant features on the filter parameter optimization process. Among them, Figure 5It is a flowchart of sub-step S42 of the coal conveying process control method for thermal power plants with anti-interference ability according to an embodiment of the present invention. As Figure 5 shown, the step S42 includes steps: S421, performing feature decoupling and feature flattening on the magnetic field intensity signal spectrum feature map to obtain a set of local spectrum feature vectors of the magnetic field intensity signal; S422, based on the feature importance of each local spectrum feature vector in the set of local spectrum feature vectors of the magnetic field intensity signal, performing serial rearrangement on the set of local spectrum feature vectors of the magnetic field intensity signal to obtain a descending order sequence of local spectrum feature vectors of the magnetic field intensity signal; S423, based on the neighborhood feature activity of each local spectrum feature vector in the descending order sequence of local spectrum feature vectors of the magnetic field intensity signal, performing feature selection sparse aggregation on the descending order sequence of local spectrum feature vectors of the magnetic field intensity signal to obtain the sparse magnetic field intensity signal spectrum feature map.

[0084] More specifically, the step S421 is expressed by the formula:

[0085] Decuple(F)={M1,M2,...,M i ,...,M n}

[0086] Flatten{M1,M2,...,M i ,...,M n}={x1,x2,...,x i ,...,x n}

[0087] where F represents the magnetic field intensity signal spectrum feature map, Decouple(·) represents feature decoupling, M1, M2, M i and M n respectively represent the first, second, i-th and n-th local spectrum feature matrices of the magnetic field intensity signal along the channel dimension of the magnetic field intensity signal spectrum feature map, n is the number of channels of the magnetic field intensity signal spectrum feature map, Flatten{·} represents feature flattening processing, x1, x2, x i and x n respectively represent the local spectrum feature vectors of the magnetic field intensity corresponding to the M1, the M2, the M i and the M n .

[0088] That is, for fine-grained feature selection, the spectral feature map of the magnetic field intensity signal is subjected to feature decoupling and feature flattening along the channel dimension to decompose it into a set of local spectral feature vectors of the magnetic field intensity signal, ensuring that each local spectral feature vector captures unique spectral feature information. In this way, a detailed data basis is prepared for the subsequent feature selection step, ensuring the diversity and representativeness of the selected features.

[0089] More specifically, in a specific example of the present invention, the step S422 includes: First, each local spectral feature vector of the magnetic field intensity signal in the set of local spectral feature vectors of the magnetic field intensity signal is input into the importance measurement module to obtain a set of importance score values of the local spectral feature of the magnetic field intensity signal, which is expressed by the formula:

[0090]

[0091] where W i and b i respectively represent the weight parameter matrix and the bias term, represents the importance scoring reference vector, represents the matrix multiplication operation, s i represents the importance score value of the local spectral feature of the magnetic field intensity signal of the said x i ;

[0092] Then, based on the set of importance score values of the local spectral feature of the magnetic field intensity signal, the set of local spectral feature vectors of the magnetic field intensity signal is sorted in descending order to obtain the descending order sequence of the local spectral feature vectors of the magnetic field intensity signal, which is expressed by the formula:

[0093]

[0094] where Rank{·} represents the sorting operation, and v1, v2, v k and v n represent the 1st, 2nd, kth, and nth local spectral feature vectors of the magnetic field intensity signal in the descending order sequence of the local spectral feature vectors of the magnetic field intensity signal.

[0095] That is, through neural network analysis, the local spectral feature vectors of each decomposed magnetic field intensity signal are evaluated for feature importance to determine the influence of each local spectral feature on the interference degree of the motor speed signal, thereby helping to identify the significant features that have the greatest influence on the filtering effect. Furthermore, according to the obtained local spectral feature importance score values, the local spectral feature vectors of each magnetic field intensity signal are sorted in descending order of their importance to construct a descending sequence of the local spectral feature vectors of the magnetic field intensity signal. In this way, without changing the feature content, a clear view of the relative importance of the features is provided, thus optimizing the subsequent feature selection process.

[0096] More specifically, in a specific example of the present invention, the step S423 includes: First, based on the neighborhood features of each local spectral feature vector of the magnetic field intensity signal in the descending sequence, the feature neighborhood activity of each local spectral feature vector of the magnetic field intensity signal is calculated to obtain a sequence of the local spectral feature neighborhood activity of the magnetic field intensity signal, which is expressed by the formula:

[0097]

[0098] where L represents the characteristic scale value of v k and represents the feature value at the j-th position in v k , u k and u k+1 respectively represent the internal feature attenuation factors of the k-th and k + 1-th local spectral feature vectors of the magnetic field intensity signal in the descending sequence of the local spectral feature vectors of the magnetic field intensity signal, and t k represents the local spectral feature neighborhood activity of the magnetic field intensity signal corresponding to v k .

[0099] Specifically, the present invention takes into account the limitation of the information amount of a single feature point in the magnetic field intensity signal spectral feature map and the importance of the context correlation information provided by the surrounding feature points. Therefore, the present invention further introduces an evaluation method based on feature neighborhood activity, and obtains its feature neighborhood activity by calculating the interaction degree between each local spectral feature vector of the magnetic field intensity signal and adjacent features to reveal the correlation strength between the two. In this way, by considering the interaction between local spectral features, a more comprehensive perspective is provided to select the most effective feature representation.

[0100] Then, based on the sequence of the local spectral feature neighborhood activity of the magnetic field intensity signal, feature selection is performed on the descending sequence of the local spectral feature vectors of the magnetic field intensity signal to obtain a descending sequence of the selected local spectral feature vectors of the magnetic field intensity signal, which is expressed by the formula:

[0101] Select({v1, v2, ..., v k , ..., v n ) = {v1’, v2’, ..., v k ’, ..., v m ’}

[0102]

[0103] where Select(·) represents the feature selection operation, τ is a preset threshold, v1’, v2’, v k ’ and v m ’ respectively represent the 1st, 2nd, kth, and mth selected local spectral feature vectors of the magnetic field intensity signal in the descending order of the selected local spectral feature vectors of the magnetic field intensity signal, and m is the number of feature vectors in the descending order of the selected local spectral feature vectors of the magnetic field intensity signal;

[0104] Finally, reshape the descending order sequence of the selected local spectral feature vectors of the magnetic field intensity signal to obtain the sparse magnetic field intensity signal spectral feature map, which is expressed by the formula:

[0105] F s = reshape{v1’, v2’, ..., v k ’, ..., v m ’}

[0106] where reshape{·} represents feature shape reshaping, and F s represents the sparse magnetic field intensity signal spectral feature map.

[0107] That is, according to the evaluation result of the feature neighborhood activity, further screen out the most valuable local spectral feature vectors of the magnetic field intensity signal, perform feature shape reshaping on them, and re-integrate them into the original spatial structure to form a sparse magnetic field intensity signal spectral feature map, which retains the spatial relationship of the original magnetic field intensity signal spectral feature and provides more accurate feature information for the parameter adjustment of the subsequent filter. In this way, feature selection not only focuses on the importance scores of independent local spectral features but also comprehensively considers the association between features and their adjacent features, which helps to more accurately capture the key features that have a significant impact on signal interference, thereby improving the pertinence and accuracy of filter parameter adjustment.

[0108] Specifically, in a specific example of the present invention, the step S43 includes: inputting the sparsified magnetic field intensity signal spectrum feature map into a decoder-based filtering parameter optimization module to obtain the decoded value of the optimized filtering parameter. Specifically, the decoder establishes a mapping relationship between the magnetic field intensity signal spectrum feature and the filtering parameter through a training process, so that in practical applications, through a series of neural network layers inside it, the input sparsified magnetic field intensity signal spectrum feature map can be subjected to feature decoding and conversion to inversely map the sparsified magnetic field intensity signal spectrum feature map into the decoded value of the optimized filtering parameter. It should be understood that the optimized filtering parameter includes an optimized bandwidth parameter and an optimized center frequency parameter, which is the best filtering parameter configuration under the current electromagnetic interference condition and can effectively suppress the electromagnetic interference signal, thereby realizing effective filtering of the motor speed signal.

[0109] Specifically, in the step S44, the initial filtering parameter of the signal filter is updated with the optimized filtering parameter to obtain the updated signal filter. That is, by applying the optimized filtering parameter to the signal filter, its initial filtering parameter is updated, so that the signal filter can better adapt to the changing electromagnetic environment and improve the filtering ability of the motor speed signal.

[0110] In the above coal conveying process control method for thermal power plants with anti-interference ability, in the step S5, the updated signal filter is used to filter the motor speed signal to obtain the filtered motor speed signal. That is, the updated signal filter is used to filter the motor speed signal. Based on the optimized filtering parameter, different frequency components in the input motor speed signal are attenuated or amplified to different degrees, so as to achieve precise filtering of the interference components in the motor speed signal, while retaining useful speed information and providing high-quality data support for subsequent control links.

[0111] To verify the effect of the filtering process, a complete performance evaluation system also needs to be established. This includes, but is not limited to, the following aspects: signal-to-noise ratio (SNR), that is, the ratio of the useful signal to the noise; total harmonic distortion (THD), which is used to measure the purity of the signal after filtering; and the comparison of the frequency-domain and time-domain analysis results, which is used to check whether the signal characteristics have changed as expected before and after filtering. By continuously monitoring these indicators, the working state of the filter can be comprehensively understood, and necessary adjustments can be made accordingly. In addition, on-site tests can be regularly carried out to evaluate the accuracy of the entire system by comparing with the manual measurement results.

[0112] In the above coal conveying process control method for thermal power plants with anti-interference ability, in step S6, the filtered motor speed signal is input into a PID controller to control the running speed of the belt conveyor. It should be understood that a PID controller is a commonly used feedback control algorithm. It can generate a control signal through the operations of three links: proportional (P), integral (I), and derivative (D) according to the deviation between the actual output and the set value of the system, and adjust the system to make the system output as close to the set value as possible. Among them, the role of the proportional link is to output a control signal proportionally according to the size of the deviation. The larger the deviation, the stronger the control effect. The integral link is used to eliminate the steady-state error of the system. By integrating the deviation, the deviation is continuously accumulated, so that the control signal can be continuously adjusted until the steady-state error is zero. The derivative link outputs a control signal according to the change rate of the deviation, can predict the change trend of the system in advance, adjust the dynamic response of the system, and improve the stability of the system. In the present invention, the filtered motor speed signal is used as the input of the PID controller. The PID controller calculates the deviation between the actual speed and the set speed of the motor to adjust the running state of the motor in real time, so as to achieve precise control of the running speed of the belt conveyor.

[0113] In summary, the coal conveying process control method for thermal power plants with anti-interference ability based on the embodiments of the present invention is elucidated. It filters the motor speed signal of the belt conveyor by establishing a signal filter to reduce the influence of external interference on the signal. At the same time, a magnetic field intensity detector is deployed on the belt conveyor. When it is detected that the average value of the magnetic field intensity within a preset period is greater than a preset threshold, a signal processing technology based on deep learning is further used to perform frequency-domain feature analysis on the magnetic field intensity signal. Then, based on the spectral characteristics of the magnetic field intensity signal, the filtering parameters of the signal filter are adaptively updated to make it perform more accurate filtering on the motor speed signal, thereby improving the accuracy and stability of the control of the running speed of the belt conveyor. In this way, it can dynamically adapt to different electromagnetic interference environments, ensure that the signal can still maintain a high signal-to-noise ratio under complex working conditions, and thus enhance the anti-interference ability and operating efficiency of the entire coal conveying process.

[0114] Furthermore, a coal conveying process control system for thermal power plants with anti-interference ability is also provided.

[0115] Figure 6 is a block diagram of a coal conveying process control system for thermal power plants with anti-interference ability according to an embodiment of the present invention. As Figure 6As shown, the coal conveying process control system 100 of a thermal power plant with anti-interference ability according to an embodiment of the present invention includes: a motor speed signal acquisition module 110 for acquiring the motor speed signal of a belt conveyor; a signal filter establishment module 120 for establishing a signal filter, the signal filter having initial filtering parameters, the initial filtering parameters including an initial bandwidth and an initial center frequency; a magnetic field intensity signal acquisition module 130 for acquiring a magnetic field intensity signal collected by a magnetic field intensity detector deployed on the belt conveyor; a filtering parameter adjustment module 140 for updating the initial filtering parameters of the signal filter based on the spectral characteristics of the magnetic field intensity signal in response to the average magnetic field intensity of the magnetic field intensity signal within a preset period being greater than a preset threshold to obtain an updated signal filter; a signal filtering and processing module 150 for filtering the motor speed signal using the updated signal filter to obtain a filtered motor speed signal; and an operating speed control module 160 for inputting the filtered motor speed signal into a PID controller to control the operating speed of the belt conveyor.

[0116] Here, those skilled in the art can understand that the specific operations of the various modules in the above coal conveying process control system of a thermal power plant with anti-interference ability have been introduced in detail in the description of the Figures 1 to 5 coal conveying process control method of a thermal power plant with anti-interference ability above, and therefore, the repeated description thereof will be omitted.

[0117] It can be understood that the above embodiments are merely exemplary embodiments adopted to illustrate the principle of the present invention, and however, the present invention is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also regarded as the protection scope of the present invention.

Claims

1. A method for controlling coal transportation process in a thermal power plant with anti-interference capability, characterized in that: include: Get the motor speed signal of the belt conveyor; Establishing a signal filter, wherein the signal filter has initial filtering parameters, and the initial filtering parameters include an initial bandwidth and an initial center frequency; Acquiring a magnetic field strength signal collected by a magnetic field strength detector deployed on the belt conveyor; In response to the average magnetic field strength of the magnetic field strength signal within a preset period being greater than a preset threshold, based on the frequency spectrum characteristics of the magnetic field strength signal, updating the initial filtering parameters of the signal filter to obtain an updated signal filter; Using the updated signal filter to filter the motor speed signal to obtain a filtered motor speed signal; The filtered motor speed signal is input into a PID controller to control the running speed of the belt conveyor.

2. The method for controlling the coal transportation process of a thermal power plant with anti-interference capability according to claim 1, characterized in that: Based on the frequency spectrum characteristics of the magnetic field intensity signal, updating the initial filtering parameters of the signal filter to obtain an updated signal filter includes: Performing frequency domain characteristic analysis on the magnetic field strength signal to obtain a frequency spectrum characteristic diagram of the magnetic field strength signal; Performing feature selection based on feature neighborhood activity on the magnetic field strength signal spectrum feature graph to obtain a sparse magnetic field strength signal spectrum feature graph; Based on the sparse magnetic field intensity signal frequency spectrum characteristic graph, generating optimized filtering parameters; The initial filtering parameters of the signal filter are updated with the optimized filtering parameters to obtain the updated signal filter.

3. The method for controlling the coal transportation process of a thermal power plant with anti-interference capability according to claim 2 is characterized in that: Performing frequency domain characteristic analysis on the magnetic field strength signal to obtain a frequency spectrum characteristic diagram of the magnetic field strength signal includes: Performing a fast Fourier transform on the magnetic field strength signal to obtain a magnetic field strength signal spectrum diagram; The spectrum feature extraction is performed on the magnetic field strength signal spectrum diagram to obtain the magnetic field strength signal spectrum feature diagram.

4. The method for controlling the coal transportation process of a thermal power plant with anti-interference capability according to claim 3 is characterized in that: Extracting spectrum features from the magnetic field strength signal spectrum diagram to obtain the magnetic field strength signal spectrum feature diagram includes: The magnetic field strength signal spectrum diagram is input into a spectrum feature extractor based on a hole convolutional neural network model to obtain the magnetic field strength signal spectrum feature diagram.

5. The method for controlling the coal transportation process of a thermal power plant with anti-interference capability according to claim 4 is characterized in that: Performing feature selection based on feature neighborhood activity on the magnetic field strength signal spectrum feature graph to obtain a sparse magnetic field strength signal spectrum feature graph, including: Performing feature decoupling and feature flattening on the frequency spectrum feature graph of the magnetic field strength signal to obtain a set of local frequency spectrum feature vectors of the magnetic field strength signal; Based on the characteristic importance of each local spectrum feature vector of the magnetic field strength signal in the set of local spectrum feature vectors of the magnetic field strength signal, the set of local spectrum feature vectors of the magnetic field strength signal is serialized and rearranged to obtain a descending sequence of local spectrum feature vectors of the magnetic field strength signal; Based on the neighborhood feature activity of each local spectrum feature vector of the magnetic field strength signal in the descending sequence of the local spectrum feature vector of the magnetic field strength signal, feature selection and sparse aggregation are performed on the descending sequence of the local spectrum feature vector of the magnetic field strength signal to obtain the sparse magnetic field strength signal spectrum feature graph.

6. The method for controlling the coal transportation process of a thermal power plant with anti-interference capability according to claim 5, characterized in that: Based on the characteristic importance of each local spectrum feature vector of the magnetic field strength signal in the set of local spectrum feature vectors of the magnetic field strength signal, the set of local spectrum feature vectors of the magnetic field strength signal is serialized and rearranged to obtain a descending sequence of local spectrum feature vectors of the magnetic field strength signal, including: Inputting each local frequency spectrum feature vector of the magnetic field strength signal in the set of local frequency spectrum feature vectors of the magnetic field strength signal into an importance measurement module to obtain a set of importance score values ​​of local frequency spectrum features of the magnetic field strength signal; Based on the set of importance score values ​​of the local spectrum characteristics of the magnetic field strength signal, the set of local spectrum characteristic vectors of the magnetic field strength signal is arranged in descending order to obtain a descending sequence of the local spectrum characteristic vectors of the magnetic field strength signal.

7. The method for real-time feedback of drone application data according to claim 6, characterized in that: Based on the neighborhood feature activity of each local spectrum feature vector of the magnetic field strength signal in the descending sequence of the local spectrum feature vector of the magnetic field strength signal, feature selection and sparse aggregation are performed on the descending sequence of the local spectrum feature vector of the magnetic field strength signal to obtain the sparse magnetic field strength signal spectrum feature graph, including: Based on the neighborhood characteristics of each local spectrum feature vector of the magnetic field strength signal in the descending sequence of the local spectrum feature vector of the magnetic field strength signal, calculating the characteristic neighborhood activity of each local spectrum feature vector of the magnetic field strength signal to obtain a sequence of the local spectrum feature neighborhood activity of the magnetic field strength signal; Based on the sequence of neighborhood activity of the local spectrum feature of the magnetic field strength signal, feature selection is performed on the descending sequence of the local spectrum feature vectors of the magnetic field strength signal to obtain a descending sequence of the local spectrum feature vectors of the magnetic field strength signal after selection; The descending sequence of the selected local frequency spectrum feature vectors of the magnetic field intensity signal is reshaped to obtain the sparse magnetic field intensity signal frequency spectrum feature graph.

8. The method for controlling the coal transportation process of a thermal power plant with anti-interference capability according to claim 7, characterized in that: Based on the sparse magnetic field intensity signal spectrum characteristic diagram, generating optimized filtering parameters includes: The sparse magnetic field intensity signal spectrum characteristic diagram is input into a decoder-based filter parameter optimization module to obtain a decoded value of the optimized filter parameter.

9. A coal handling process control system for a thermal power plant with anti-interference capability, characterized in that: include: The motor speed signal acquisition module is used to obtain the motor speed signal of the belt conveyor; A signal filter establishment module, used for establishing a signal filter, wherein the signal filter has initial filter parameters, and the initial filter parameters include an initial bandwidth and an initial center frequency; A magnetic field strength signal acquisition module, used to acquire a magnetic field strength signal collected by a magnetic field strength detector deployed on the belt conveyor; A filtering parameter adjustment module, configured to update the initial filtering parameters of the signal filter to obtain an updated signal filter based on the spectrum characteristics of the magnetic field intensity signal in response to the average magnetic field intensity of the magnetic field intensity signal within a preset period being greater than a preset threshold; A signal filtering processing module, used for filtering the motor speed signal using the updated signal filter to obtain a filtered motor speed signal; The running speed control module is used to input the filtered motor speed signal into a PID controller to control the running speed of the belt conveyor.

10. The coal handling process control system with anti-interference capability for a thermal power plant according to claim 9, characterized in that: The filtering parameter adjustment module is further specifically used for: Performing frequency domain characteristic analysis on the magnetic field strength signal to obtain a frequency spectrum characteristic diagram of the magnetic field strength signal; Performing feature selection based on feature neighborhood activity on the magnetic field strength signal spectrum feature graph to obtain a sparse magnetic field strength signal spectrum feature graph; Based on the sparse magnetic field intensity signal frequency spectrum characteristic graph, generating optimized filtering parameters; The initial filtering parameters of the signal filter are updated with the optimized filtering parameters to obtain the updated signal filter.

Images