Method, device and equipment for configuring damper for vibrating screen

Abstract

The embodiment of the invention provides a method, device and equipment for configuring a damper for a vibrating screen. The method comprises the following steps: in response to an obtained vibration signal of a target vibration screen, carrying out preprocessing and feature fusion on the vibration signal, and generating a dimensionality reduction feature matrix; inputting the dimension reduction characteristic matrix into a vibration path identification model, and outputting contribution proportions of a plurality of vibration transmission paths associated with the target vibration screen by the vibration path identification model; wherein the vibration path identification model is obtained by pre-training based on a transfer learning framework; a main transmission path is screened from the multiple vibration transmission paths according to the contribution proportion, and a parameter configuration instruction of the particle damper is generated based on the vibration frequency domain characteristics of the main transmission path; controlling an execution mechanism to deploy a particle damper at a specified position of the main transmission path; wherein the particle damper is matched with a parameter configuration instruction corresponding to the main transmission path. By means of the method, targeted deployment of the damper can be achieved for the target vibrating screen.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of mechanical vibration suppression and structural dynamics, and in particular to a method, device and equipment for configuring a damper for a vibrating screen. BACKGROUND

[0002] Coal, as a key component of China's energy structure, its secondary processing link after mining highly depends on the core equipment of vibrating screen - the equipment realizes efficient screening of materials through vibration motor drive, but the strong vibration and noise generated during its working process not only accelerates the structural loss of the equipment, but also seriously threatens the health of operating personnel and the safety of the production environment.

[0003] In order to implement targeted vibration reduction measures, the traditional method uses OTPA (operating transfer path analysis) technology to identify the main vibration transmission path and lay out the damper, but there are significant defects in the actual application of coal mine engineering: first, the data dependency is strong, and it is necessary to collect a large amount of vibration data under multiple working conditions to construct the transfer function matrix, resulting in long experimental period and high cost, which is difficult to meet the rapid deployment needs of coal mine site; second, the calculation complexity is high, and the matrix decomposition and path contribution quantification involve high-dimensional operation, which is low in real-time analysis efficiency; third, it is difficult to analyze coupled vibration, and the resonance phenomenon of vibrating screen-steel frame structure caused by the coexistence of multiple equipment in coal mine workshop makes the traditional method unable to accurately separate the contribution of each path, resulting in insufficient targeting of the vibration reduction scheme. These bottlenecks seriously restrict the engineering applicability and economy of the vibration screen vibration reduction technology, and it is urgent to develop a transfer path identification and vibration reduction optimization method with lower data requirement, higher calculation efficiency and self-adaptive multi-frequency vibration characteristics, to fundamentally improve the reliability and environmental friendliness of key equipment in coal industry. SUMMARY

[0004] In order to solve the above technical problems, the scheme of the present disclosure is proposed. The embodiments of the present disclosure provide a method, device and equipment for configuring a damper for a vibrating screen.

[0005] According to a first aspect of the embodiments of the present disclosure, a method for configuring a damper for a vibrating screen is provided, wherein the method comprises: In response to obtaining a vibration signal of a target vibrating screen, pre-processing and feature fusion are performed on the vibration signal to generate a dimension-reduced feature matrix; The dimension-reduced feature matrix is input into a vibration path identification model, and the contribution ratio of a plurality of vibration transmission paths associated with the target vibrating screen is output by the vibration path identification model; wherein the vibration path identification model is pre-trained based on a transfer learning framework; According to the contribution ratio, a main transmission path is selected from the plurality of vibration transmission paths, and a parameter configuration instruction of a particle damper is generated based on the vibration frequency domain characteristics of the main transmission path; controlling an execution mechanism to deploy a particle damper at a specified position of the main transmission path; wherein the particle damper matches the parameter configuration instruction corresponding to the main transmission path.

[0006] According to a second aspect of the embodiments of the present disclosure, an apparatus for configuring a damper for a vibrating screen is provided, wherein the apparatus comprises: a preprocessing and fusion unit configured to, in response to obtaining a vibration signal of a target vibrating screen, pre-process and feature fuse the vibration signal to generate a dimension-reduced feature matrix; a vibration path identification unit configured to input the dimension-reduced feature matrix to a vibration path identification model, and output a contribution proportion of a plurality of vibration transmission paths associated with the target vibrating screen from the vibration path identification model; wherein the vibration path identification model is pre-trained based on a transfer learning framework; a main transmission path screening unit configured to screen a main transmission path from the plurality of vibration transmission paths according to the contribution proportion, and generate a parameter configuration instruction of a particle damper based on a vibration frequency domain characteristic of the main transmission path; a control execution unit configured to control an execution mechanism to deploy a particle damper at a specified position of the main transmission path; wherein the particle damper matches the parameter configuration instruction corresponding to the main transmission path.

[0007] According to a third aspect of the embodiments of the present disclosure, an electronic device is provided, comprising: a processor; a memory for storing executable instructions of the processor; and the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method for configuring a damper for a vibrating screen according to the present disclosure.

[0008] According to a fourth aspect of the embodiments of the present disclosure, a computer readable storage medium is provided, which stores a computer program for executing the method for configuring a damper for a vibrating screen according to the present disclosure.

[0009] According to a fifth aspect of the embodiments of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program is executed by a processor to implement the method for configuring a damper for a vibrating screen according to the present disclosure.

[0010] In summary, the method for configuring a damper for a vibrating screen provided by the embodiments of the present disclosure breaks through the data dependence, coupling vibration analysis difficulty, and insufficient vibration suppression targeting of the traditional vibration screen vibration reduction scheme, and realizes significant vibration energy attenuation, thereby providing a universal solution for precise suppression of low-frequency and high-frequency composite vibration of mine equipment. BRIEF DESCRIPTION OF DRAWINGS

[0011] The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which like reference characters refer to like elements throughout. The accompanying drawings are intended to provide a further understanding of the embodiments of the present disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the present disclosure and serve to explain the present disclosure, and do not constitute a limitation of the present disclosure. In the drawings, like reference numerals refer to like elements throughout.

[0012] Figure 1 is a flowchart of a method for configuring a damper for a vibrating screen provided by an exemplary embodiment of the present disclosure; Figure 2 is a flowchart of a method for configuring a damper for a vibrating screen provided by an exemplary embodiment of the present disclosure; Figure 1 is a flowchart of a method for configuring a damper for a vibrating screen provided by an exemplary embodiment of the present disclosure; Figure 3 is a flowchart of a method for configuring a damper for a vibrating screen provided by an exemplary embodiment of the present disclosure; Figure 1 is a flowchart of a method for configuring a damper for a vibrating screen provided by an exemplary embodiment of the present disclosure; Figure 4 is a flowchart of a method for configuring a damper for a vibrating screen provided by an exemplary embodiment of the present disclosure; Figure 1 is a flowchart of a method for configuring a damper for a vibrating screen provided by an exemplary embodiment of the present disclosure; Figure 5 is a structural schematic diagram of a device for configuring a damper for a vibrating screen provided by an exemplary embodiment of the present disclosure; Figure 6 is a structural schematic diagram of an electronic device according to an application embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] The present disclosure will be further described below with reference to the embodiments shown in the drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the example embodiments described herein.

[0014] It should be noted that the relative arrangement, numerical expressions, and numerical values of the components and steps set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.

[0015] Those skilled in the art can understand that the terms "first", "second" and the like in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, and do not represent any specific technical meaning, nor indicate their logical order.

[0016] It should also be understood that in the embodiments of the present disclosure, "multiple" can mean two or more, and "at least one" can mean one, two or more.

[0017] It should also be understood that for any component, data or structure mentioned in the embodiments of the present disclosure, it can be understood as one or more in general, without explicit limitation or in the context of the opposite indication.

[0018] In addition, the term "and / or" in the present disclosure is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. In addition, the character " / " in the present disclosure generally represents an "or" relationship between the front and rear associated objects.

[0019] It should also be understood that the description of the embodiments of the present disclosure emphasizes the differences between the embodiments, and the same or similar parts can be referred to each other, and for the sake of brevity, will not be repeated.

[0020] At the same time, it should be understood that for the convenience of description, the size of each part shown in the drawings is not drawn according to the actual proportional relationship.

[0021] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application or uses.

[0022] Techniques, methods, and devices known to those of ordinary skill in the relevant art can not be discussed in detail, but should be considered part of the specification where appropriate.

[0023] It should be noted that similar reference numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be discussed further in subsequent drawings.

[0024] Example 1 Figure 1is a flowchart of a method for configuring a damper for a vibrating screen according to an example embodiment of the present disclosure. The method can be executed on a server or an edge computing terminal, wherein the server can include but is not limited to a server, a cloud computing platform.

[0025] In particular, with reference to Figure 1 , the method for configuring a damper for a vibrating screen comprises: S110, in response to obtaining the vibration signal of the target vibrating screen, pre-processing and feature fusion are performed on the vibration signal to generate a dimension-reduced feature matrix.

[0026] The vibrating screen is a core device in the secondary processing link after coal mining, which can realize material screening through a vibrating motor drive.

[0027] The vibration signal can be a vibration acceleration signal.

[0028] Optionally, the vibration signal is obtained as follows: first, arrange acceleration sensors at key positions of the vibrating screen steel frame, such as the vibrating motor mounting point, the foot, and the screen body connection point; then collect the acceleration sensor return signal at a preset sampling frequency under different working conditions and different load conditions of the target vibrating screen. The sampling frequency is set according to the device characteristic frequency and the sampling law to ensure that all characteristic frequency bands (for example, the base frequency 14~15.75 Hz and its multiple frequencies of the vibrating screen) are covered. Different working conditions can include start-up, steady-state operation, and shutdown; different load conditions can include empty load, half load, and full load.

[0029] Optionally, with reference to Figure 2 , the step S110 of "pre-processing and feature fusion on the vibration signal to generate a dimension-reduced feature matrix" can be implemented as follows: S1110, use a multi-scale decomposition algorithm to process the vibration signal to output a denoised vibration component.

[0030] Optionally, use discrete wavelet transform for multi-scale decomposition (set the number of decomposition layers to 5 layers), use Stein unbiased risk estimation criterion to dynamically adjust the threshold, and improve the signal-to-noise ratio ≥8 dB; thereby realizing noise suppression.

[0031] S1120, perform band-pass filtering of a preset frequency band on the vibration component to output a frequency-band-focused filtered signal.

[0032] Optionally, for low-frequency vibration (for example, base frequency 14~15.75 Hz), design a finite impulse response band-pass filter, use a Hamming window function to set the cutoff frequency (low-pass 14 Hz, high-pass 200 Hz), cover more than 99% of the vibration energy frequency band, and use zero-phase filtering to avoid phase distortion; thereby realizing signal filtering.

[0033] Accordingly, after step S1120, time synchronization may also be included. Specifically, multiple accelerometers are synchronized through hardware trigger signals (error ≤ 0.1 ms); asynchronous data are compensated for phase consistency through cross-correlation algorithms.

[0034] S1130. The filtered signal is standardized to output a dimensionless standard vibration sequence.

[0035] Optionally, the filtered signal (i.e., the filtered acceleration signal) is Z-score normalized to eliminate sensor sensitivity differences.

[0036] in, The mean of the signal. Standard deviation The amplitude of the filtered signal. This is a standard vibration signal amplitude sequence.

[0037] S1140. Extract time-domain statistics, frequency-domain energy distribution, and time-frequency sub-band energy concentration from the standard vibration sequence to generate a multi-dimensional original feature matrix.

[0038] Optionally, time-domain statistics (i.e., time-domain features) may include root mean square (RMS), kurtosis, and crescendo factor, as shown in the following formula:

[0039] in, This is a standard vibration signal amplitude sequence; N This represents the number of sampling points; for The Middle i The amplitude of a standard vibration signal; The mean of the signal; The standard deviation is denoted as .

[0040] Optionally, the frequency domain energy distribution (i.e., frequency domain characteristics) can be extracted by using a Hanning window to reduce spectral leakage through Fast Fourier Transform (FFT) analysis. The fundamental frequency and harmonic component amplitudes are calculated, and the power spectral density (PSD) (segment length 512 points, overlap rate 50%) is calculated using the Welch method, dividing the frequency bands into low-frequency (14~50 Hz) and mid-frequency (50~200 Hz) integral energy bands.

[0041] Optionally, the time-frequency domain sub-band energy concentration degree (i.e., time-frequency domain feature) can be extracted in the following manner. Specifically, the wavelet packet transform (WPT) is used to extract (Db4 wavelet basis, 4-layer decomposition to generate 16 sub-bands), and the energy entropy of each sub-band is calculated (the entropy value reflects the energy concentration degree and is used to identify the resonance characteristics):

[0042]

[0043] wherein, represents the energy entropy of the jth sub-band; represents the energy proportion probability of the sub-band j in the time window k; represents the wavelet packet coefficient of the sub-band j in the time window k; represents the signal energy corresponding to the frequency band-time window.

[0044] Optionally, the extracted original features include 5 dimensions in the time domain (RMS, peak value, kurtosis, pulse factor, and waveform factor), 8 dimensions in the frequency domain (fundamental frequency amplitude, harmonic energy proportion, and PSD integral), and 16 dimensions in the time-frequency domain (sub-band energy entropy), totaling 29 dimensions. Based on this, a high-dimensional feature matrix (29 dimensions: 5 dimensions in the time domain, 8 dimensions in the frequency domain, and 16 dimensions in the time-frequency domain) can be constructed and stored as an N x 29 matrix (N is the number of samples).

[0045] S1150, dimension reduction processing is performed on the multi-dimensional original feature matrix using a feature compression algorithm to obtain the dimension-reduced feature matrix.

[0046] Optionally, a pre-trained autoencoder is used for dimension reduction. Specifically, the multi-dimensional original feature matrix is input into the pre-trained autoencoder to obtain a dimension-reduced feature matrix output by the pre-trained autoencoder.

[0047] wherein the output dimension-reduced feature matrix retains more than 90% of the information (verified by variance contribution rate), the reconstruction error is less than or equal to 3%, and the separability is verified by t-SNE visualization.

[0048] wherein the pre-trained autoencoder network structure includes an input layer (29 nodes), an encoding layer (50 nodes, ReLU activation), and a decoding layer (29 nodes, linear activation).

[0049] The loss function in the training stage is mean square error (MSE), the optimizer is Adam, the training period is 200 epochs, and the early stopping method (patience = 10) is used to prevent overfitting.

[0050] S120, input the dimension-reduced feature matrix into a vibration path identification model, and output a contribution ratio of a plurality of vibration transmission paths associated with the target vibrating screen.

[0051] The vibration path identification model is pre-trained based on a transfer learning framework.

[0052] Optionally, the vibration path identification model is a fully connected neural network. The fully connected neural network can include, but is not limited to, a convolutional neural network (CNN) or a Transformer network.

[0053] Optionally, the fully connected neural network can include a cascaded input layer, a hidden layer, and an output layer.

[0054] The input layer includes a plurality of nodes matching the dimension-reduced feature matrix. For example, the input layer can include 50 nodes.

[0055] The hidden layer includes a first fully connected layer and a second fully connected layer. The first fully connected layer includes 128 nodes, and the second fully connected layer includes 64 nodes. In addition, a ReLU activation function can also be included.

[0056] The output layer includes a plurality of nodes and an activation function. Each node corresponds to one of the vibration transmission paths, and the activation function is Softmax. For example, the output layer can include 5 nodes.

[0057] Optionally, the pre-training based on the transfer learning framework includes a source domain training phase and a target domain fine-tuning phase.

[0058] In a specific example, referring to Figure 3 , the source domain training phase includes: S310, obtaining at least one set of source domain training data pairs.

[0059] Each set of source domain training data pairs includes first vibration data simulating target vibrating screen vibration data and first contribution ratio sample true values of vibration transmission paths corresponding to the first vibration data.

[0060] The data source of the first vibration data can include two paths. 1) Obtain vibration data from similar industrial equipment (such as a crusher, a fan) that is similar to the structure of the target vibrating screen, to ensure structural similarity (such as a welded steel beam structure); 2) generate vibration response data through finite element analysis (FEA) or multi-body dynamics simulation to simulate different excitation sources (such as motor eccentricity, material impact). The first contribution ratio sample true values can be adaptively determined based on the above two paths.

[0061] The first vibration data in each source domain training data pair may be, for example, a 50-dimensional feature matrix.

[0062] S320, input the first vibration data in each training data pair into a vibration path identification model to be trained, and output a corresponding first contribution ratio prediction value through the vibration path identification model to be trained.

[0063] The model architecture of the vibration path identification model to be trained may be: an input layer (50 nodes), a hidden layer (two fully connected layers: 128 nodes + 64 nodes, ReLU activation), and an output layer (5 nodes, Softmax activation).

[0064] Based on this architecture, the model output is the contribution ratio of each transmission path (for example, Path 1 contributes 30%, Path 2 contributes 25%, etc.); that is, the weight coefficients of Path 1 to Path 5.

[0065] S330, using a first preset comprehensive loss function, based on the first contribution ratio sample true value in each source domain training data pair and the corresponding first contribution ratio prediction value, obtaining a function value of the first preset comprehensive loss function.

[0066] The first preset comprehensive loss function is a mean square error (MSE) function constructed using the first contribution ratio sample true value and the corresponding first contribution ratio prediction value.

[0067] S340, based on the function value of the first preset comprehensive loss function, training the vibration path identification model to be trained until the first preset training completion condition of the source domain training phase is met, and obtaining a primary vibration path identification model from the vibration path identification model to be trained.

[0068] The training strategy may be: the initial value of the learning rate is set to 0.001, the model parameters are dynamically adjusted using cosine annealing scheduling (CosineAnnealing), and L2 regularization (weight decay coefficient 0.001) is used to prevent overfitting.

[0069] In a specific example, referring to Figure 4 , the target domain fine-tuning stage includes: S410, obtaining at least one target domain training data pair.

[0070] Each target domain training data pair includes second vibration data of the target vibration screen itself and second contribution ratio sample true values of vibration transmission paths corresponding to the second vibration data.

[0071] Here, the second vibration data and the second contribution ratio sample true value are measured data about the target vibration screen itself. Moreover, the data in the target domain training data pair can cover different operating conditions and no-load conditions of the target vibration screen.

[0072] The second vibration data in each group of target domain training data pairs may be, for example, a 50-dimensional feature matrix.

[0073] S420, input the second vibration data in each group of training data pairs into a primary vibration path identification model respectively, and output corresponding second contribution ratio predicted values through the primary vibration path identification model.

[0074] The model structure of the primary vibration path identification model is the same as the model architecture of the vibration path identification model to be trained described above; the difference lies in the difference in model parameters before and after the foregoing source domain training stage.

[0075] Based on this architecture, the model output is the contribution ratio of each transmission path (for example, Path 1 contributes 30%, Path 2 contributes 25%, etc.); that is, the weight coefficients of Path 1 to Path 5.

[0076] S430, using a second preset comprehensive loss function, based on the second contribution ratio sample true value in each group of target domain training data pairs and the corresponding second contribution ratio predicted value, obtaining the function value of the second preset comprehensive loss function.

[0077] The second preset comprehensive loss function is a mean square error (MSE) function constructed using the second contribution ratio sample true value and the corresponding second contribution ratio predicted value.

[0078] S440, based on the function value of the second preset comprehensive loss function, training the primary vibration path identification model until the second preset training completion condition of the target domain fine-tuning stage is met, and obtaining the vibration path identification model from the primary vibration path identification model.

[0079] Optionally, in the target domain training stage, the first several layers of the primary vibration path identification model can be frozen (to retain the general feature extraction capability), and only the parameters of the fully connected layer can be fine-tuned. Thus, the small amount of target domain training data pairs (for example, 20 groups of operating conditions) of the target vibration screen can be fully utilized for training to learn the system-specific vibration transmission rule.

[0080] The training strategy can be: the initial value of the learning rate is set to 0.001, the model parameters are dynamically adjusted by using cosine annealing scheduling (CosineAnnealing), and L2 regularization (weight decay coefficient 0.001) is used to prevent overfitting.

[0081] S130, screen a main transmission path from the multiple vibration transmission paths according to the contribution ratio, and generate a parameter configuration instruction of a particle damper based on vibration frequency domain characteristics of the main transmission path.

[0082] Optionally, the step S130 of "screening a main transmission path from the multiple vibration transmission paths according to the contribution ratio" can include: from the multiple vibration transmission paths, identifying a vibration transmission path with a contribution ratio greater than a preset contribution ratio threshold as the main transmission path.

[0083] Wherein, the preset contribution ratio threshold is not limited by the present disclosure, and can be set according to actual needs. For example, it can be 20%.

[0084] Optionally, the step S130 of "generating a parameter configuration instruction of a particle damper based on vibration frequency domain characteristics of the main transmission path" can include: In response to the main transmission path vibration frequency being in a first frequency band, configuring a particle damper with a first density and a first particle size for the main transmission path.

[0085] In response to the main transmission path vibration frequency being in a second frequency band, configuring a particle damper with a second density and a second particle size for the main transmission path.

[0086] Wherein, the upper limit of the first frequency band is less than the lower limit of the second frequency band; the first density is greater than the second density; and the first particle size is greater than the second particle size.

[0087] In a specific example, the first frequency band can be a 10-315Hz frequency band, the first density can be between 7.81~7.85 , and the first particle size can be 3~5mm. For example, a particle damper of carbon steel material and 4mm in diameter meets the conditions of this example.

[0088] The second frequency band can be a 500-2000Hz frequency band, the second density can be between 2.4~6.2 , and the second particle size can be 1~2mm. For example, a particle damper of ceramic material and 2mm in diameter meets the conditions of this example.

[0089] S140, control an execution mechanism to deploy a particle damper at a specified position of the main transmission path.

[0090] Wherein, the particle damper matches the parameter configuration instruction corresponding to the main transmission path.

[0091] Optionally, the specified position includes a node position in the main transmission path. In particular, the node position is a critical position of the vibrating screen steel frame (for example, a vibrating motor mounting point, a foot, and a screen body connection point).

[0092] The execution mechanism can include, but is not limited to, a humanoid robot, a mechanical arm, and the like, which can receive control instructions issued by the server and execute the control instructions.

[0093] In summary, the method for configuring a damper for a vibrating screen provided by the embodiments of the present disclosure is based on the innovative path of "multi-source data fusion-migration learning prediction-targeted vibration suppression decision". First, a dimension reduction feature matrix representing vibration transmission characteristics is constructed through discrete wavelet denoising and frequency band focusing preprocessing. Then, the migration learning model is used to analyze the contribution distribution of the main transmission path to accurately identify high-energy efficiency nodes. Finally, the particle size and material configuration instructions of the particle damper are generated based on the frequency domain characteristics, and the execution mechanism is driven to realize the targeted deployment of the particle damper, breaking through the data dependence, coupled vibration analysis difficulty, and insufficient vibration suppression of traditional vibration screen vibration reduction schemes. The method realizes significant attenuation of vibration energy and provides a universal solution for precise suppression of low-frequency and high-frequency composite vibration of mine equipment.

[0094] Embodiment 2 It should be understood that the foregoing embodiments of the method for configuring a damper for a vibrating screen can also be similarly applied to the following device for configuring a damper for a vibrating screen for similar expansion. For the sake of simplicity, they are not described in detail.

[0095] Figure 5 is a device structure schematic diagram for configuring a damper for a vibrating screen provided by an exemplary embodiment of the present disclosure. Referring to Figure 5 , the device comprises: The preprocessing and fusion unit 510 is configured to, in response to obtaining the vibration signal of the target vibrating screen, pre-process and feature fuse the vibration signal to generate a dimension reduction feature matrix; The vibration path identification unit 520 is configured to input the dimension reduction feature matrix into a vibration path identification model, and output the contribution proportion of a plurality of vibration transmission paths associated with the target vibrating screen from the vibration path identification model; wherein the vibration path identification model is pre-trained based on a migration learning framework; The main transmission path screening unit 530 is configured to screen the main transmission path from the plurality of vibration transmission paths according to the contribution proportion, and generate parameter configuration instructions of the particle damper based on the vibration frequency domain characteristics of the main transmission path; The control execution unit 540 is configured to control the execution mechanism to deploy the particle damper at a specified position of the main transmission path; wherein the parameter configuration instructions of the particle damper corresponding to the main transmission path are matched.

[0096] In summary, the device for configuring a damper for a vibrating screen provided by the embodiments of the present disclosure breaks through the data dependence, coupling vibration analysis difficulty, and insufficient vibration suppression targeting of the traditional vibration screen vibration reduction scheme, and realizes significant vibration energy attenuation, thereby providing a universal solution for precise suppression of low-frequency and high-frequency composite vibration of mine equipment.

[0097] Embodiment 3 In addition, the embodiments of the present disclosure also provide an electronic device, including a memory for storing a computer program, and a processor for executing the computer program stored in the memory, and when the computer program is executed, the method for configuring a damper for a vibrating screen described in any of the embodiments of the present disclosure is implemented.

[0098] Figure 6 is a structural schematic diagram of an application embodiment of the electronic device of the present disclosure. Next, the electronic device according to the embodiments of the present disclosure will be described with reference to Figure 6 The electronic device can be any one or both of the first device and the second device, or a single device independent of them, which can communicate with the first device and the second device to receive the collected input signals therefrom.

[0099] As shown in Figure 6 The electronic device includes one or more processors and a memory. The processor can be a central processing unit (CPU) or other form of processing unit having data processing and / or instruction execution capabilities, and can control other components in the electronic device to perform desired functions. The memory can include one or more computer program products, which can include various forms of computer readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory, etc. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions can be stored on the computer readable storage medium, and the processor can run the program instructions to implement the method for configuring a damper for a vibrating screen of the embodiments of the present disclosure described above and / or other desired functions.

[0100] In one example, the electronic device can further include an input device and an output device, which components are interconnected through a bus system and / or other forms of connection mechanism (not shown). In addition, the input device can include, for example, a keyboard, a mouse, and the like. The output device can output various information, including determined distance information, direction information, and the like, to the outside. The output device can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0101] Of course, in order to simplify, Figure 6 In the electronic device, only some of the components related to the present disclosure are shown, and components such as buses, input / output interfaces, and the like are omitted. In addition, the electronic device can further include any other appropriate components according to a specific application.

[0102] In addition to the above-described method and device, an embodiment of the present disclosure can be a computer program product including computer program instructions that, when executed by a processor, cause the processor to perform the steps of the method for configuring a damper for a vibrating screen according to various embodiments of the present disclosure described in the above parts of the specification.

[0103] The computer program product can be written in any combination of one or more programming languages, including an object-oriented programming language such as Java, C++, and the like, and conventional procedural programming languages, such as the "C" programming language, or the like. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.

[0104] In addition, an embodiment of the present disclosure can also be a computer readable storage medium having stored thereon computer program instructions, which, when executed by a processor, cause the processor to perform the steps of the method for configuring a damper for a vibrating screen according to various embodiments of the present disclosure described in the above parts of the specification.

[0105] The computer readable storage medium can be a combination of one or more computer readable media. The computer readable media can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include the following: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0106] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware, and the foregoing program can be stored in a computer readable storage medium. When the program is executed, the steps of the method embodiments are executed; and the foregoing storage medium includes ROM, RAM, magnetic disk or optical disk and various storage media that can store program codes.

[0107] The above describes the basic principles of the present disclosure in combination with specific embodiments. However, it should be noted that the advantages, advantages, effects and the like mentioned in the present disclosure are only examples and are not limiting. These advantages, advantages, effects and the like cannot be considered as necessary for each embodiment of the present disclosure. In addition, the above specific details are only for the purpose of example and for the purpose of understanding, and the above details do not limit the present disclosure to the above specific details.

[0108] Each embodiment in the specification is described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same or similar parts between each embodiment can be referred to each other. For system embodiments, since they basically correspond to method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0109] The block diagrams of the devices, apparatuses, equipment, systems involved in the present disclosure are only illustrative examples and are not intended to require or imply the connection, arrangement, configuration shown in the block diagram. As those skilled in the art will recognize, these devices, apparatuses, equipment, systems can be connected, arranged, configured in any way. Words such as "include", "contain", "have" and the like are open-ended words, which mean "include but not limited to", and can be used interchangeably. The words "or" and "and" used herein mean the word "and / or", and can be used interchangeably unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably.

[0110] The methods and apparatus of this disclosure can be implemented in a number of ways. For example, the methods and apparatus of this disclosure can be implemented using software, hardware, firmware, or any combination of these methods. The order of any steps described above is merely exemplary and the steps of the methods of this disclosure need not be performed in the order described unless otherwise specified. Furthermore, any steps described above can be combined, reordered, or otherwise altered unless otherwise specified. Moreover, in some embodiments, the disclosure can also be implemented as a program for running on a computer or other programmable apparatus to implement the methods as described above. Thus, the disclosure also covers record mediums storing programs for implementing the methods of this disclosure.

[0111] It is also noted that the methods of this disclosure can be implemented by way of machine, programs, or specifically programmed computers or processors, programmable logic devices, application-specific integrated circuits, or the like. In this context, a "processor" can be a hardware device.

[0112] The above description is provided for the purpose of illustrating and describing the disclosed aspects. It is not intended to be limiting. Numerous modifications and variations are possible in light of the above teachings without departing from the scope of the disclosure. It is also intended that the disclosure be construed to encompass each alternate aspect and permutation of the disclosure. Accordingly, the disclosure is intended to embrace all such alterations, modifications, and permutations of the various aspects disclosed herein. Additionally, although some aspects and embodiments of the disclosure have been described above with particular emphasis, it should be understood that any feature, structure, or characteristic described in connection with one aspect or embodiment can be included in or applied to another aspect or embodiment. Further, it should be understood that features, structures, or characteristics described in connection with one aspect or embodiment can be combined in any manner with one or more other aspects or embodiments.

[0113] The above description has been presented for the purpose of illustration and description. It is not intended to be limiting. Although various examples and embodiments have been discussed above, those skilled in the art will recognize that certain modifications, permutations, additions and sub-combinations of the above-disclosed aspects and / or embodiments can be made without departing from the scope of the disclosure.

Claims

1. A method for configuring a damper for a vibrating screen, characterized in that, The method includes: In response to the acquisition of the vibration signal of the target vibrating screen, the vibration signal is preprocessed and feature fusion is performed to generate a dimension-reduced feature matrix; The reduced feature matrix is ​​input into the vibration path recognition model, which outputs the contribution percentage of multiple vibration transmission paths associated with the target vibrating screen; wherein, the vibration path recognition model is pre-trained based on a transfer learning framework. Based on the contribution ratio, the main transmission path is selected from the multiple vibration transmission paths, and the parameter configuration instructions for the particle damper are generated based on the vibration frequency domain characteristics of the main transmission path. The control actuator deploys a particle damper at a designated location on the main transmission path; wherein the particle damper is matched with the parameter configuration command corresponding to the main transmission path.

2. The method according to claim 1, characterized in that, In response to acquiring the vibration signal of the target vibrating screen, the vibration signal is preprocessed and feature fusion is performed to generate a dimension-reduced feature matrix, including: The vibration signal is processed using a multi-scale decomposition algorithm, and the denoised vibration component is output. The vibration component is subjected to a preset frequency band bandpass filter, and the output frequency band focused filtered signal is generated. The filtered signal is standardized to output a dimensionless standard vibration sequence; Time-domain statistics, frequency-domain energy distribution, and time-frequency sub-band energy concentration are extracted from the standard vibration sequence to generate a multi-dimensional original feature matrix. The multidimensional original feature matrix is ​​reduced in dimensionality using a feature compression algorithm to obtain the reduced-dimensional feature matrix.

3. The method according to claim 1, characterized in that, The vibration path recognition model is a fully connected neural network.

4. The method according to claim 3, characterized in that, The fully connected neural network includes cascaded input layers, hidden layers, and output layers; The input layer includes multiple nodes that match the reduced-dimensional feature matrix; The hidden layer includes a first fully connected layer and a second fully connected layer; wherein the first fully connected layer includes 128 nodes and the second fully connected layer includes 64 nodes; The output layer includes multiple nodes and activation functions; each node corresponds to a vibration transmission path, and the activation function is Softmax.

5. The method according to claim 1, characterized in that, The pre-training based on the transfer learning framework includes a source domain training phase and a target domain fine-tuning phase. The source domain training phase includes: Obtain the at least one set of source domain training data pairs; wherein each set of source domain training data pairs includes first vibration data for simulating the vibration data of the target vibrating screen, and the true value of the first contribution percentage sample of the vibration transmission path corresponding to the first vibration data; The first vibration data in each training data pair is input into the vibration path recognition model to be trained, and the vibration path recognition model to be trained outputs the corresponding first contribution ratio prediction value. Using the first preset comprehensive loss function, based on the true value of the first contribution percentage sample and the corresponding predicted value of the first contribution percentage in each pair of source domain training data, the function value of the first preset comprehensive loss function is obtained; Based on the function value of the first preset comprehensive loss function, the vibration path recognition model to be trained is trained until the first preset training completion condition of the source domain training stage is met, and an initial vibration path recognition model is obtained from the vibration path recognition model to be trained. The target domain fine-tuning stage includes: Acquire at least one set of target domain training data pairs; wherein each set of target domain training data pairs includes the second vibration data of the target vibrating screen itself, and the true value of the sample of the second contribution of the vibration transmission path corresponding to the second vibration data. The second vibration data in each training data pair is input into the primary vibration path recognition model, and the primary vibration path recognition model outputs the corresponding predicted value of the second contribution ratio. Using the second preset comprehensive loss function, based on the true value of the second contribution proportion sample in each target domain training data pair and the corresponding predicted value of the second contribution proportion, the function value of the second preset comprehensive loss function is obtained; Based on the function value of the second preset comprehensive loss function, the initial vibration path recognition model is trained until the second preset training completion condition of the target domain fine-tuning stage is met, and the vibration path recognition model is obtained from the initial vibration path recognition model.

6. The method according to claim 1, characterized in that, The step of selecting the main transmission path from the multiple vibration transmission paths based on the contribution ratio includes: From the multiple vibration transmission paths, the vibration transmission path whose contribution percentage is greater than a preset contribution percentage threshold is identified as the main transmission path.

7. The method according to claim 1, characterized in that, The parameter configuration instructions for generating the particle damper based on the vibration frequency domain characteristics of the main transmission path include: In response to the vibration frequency of the main transmission path being within a first frequency band, a particle damper conforming to a first density and a first particle size is configured for the main transmission path. In response to the vibration frequency of the main transmission path being between the second frequency band, a particle damper conforming to the second density and the second particle size is configured for the main transmission path; in, The upper limit of the first frequency band is less than the lower limit of the second frequency band; The first density is greater than the second density; The first particle size is larger than the second particle size.

8. The method according to claim 1, characterized in that, The specified location includes the node location in the main transmission path.

9. A device for configuring a damper for a vibrating screen, characterized in that, The device includes: The preprocessing and fusion unit is configured to: in response to acquiring the vibration signal of the target vibrating screen, preprocess and fuse the vibration signal to generate a dimension-reduced feature matrix; The vibration path identification unit is configured to: input the dimensionality-reduced feature matrix into the vibration path identification model, and have the vibration path identification model output the contribution ratio of multiple vibration transmission paths associated with the target vibrating screen; wherein, the vibration path identification model is pre-trained based on a transfer learning framework; The main transmission path filtering unit is configured to: filter the main transmission path from the multiple vibration transmission paths according to the contribution ratio, and generate parameter configuration instructions for the particle damper based on the vibration frequency domain characteristics of the main transmission path. The control execution unit is configured such that: the control execution mechanism deploys a particle damper at a designated location on the main transmission path; wherein the particle damper is matched with the parameter configuration command corresponding to the main transmission path.

10. An electronic device, the electronic device comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method for configuring a damper for a vibrating screen as described in claims 1 to 8.

Images