Method, device and equipment for detecting height of coal cake on tamping machine and medium

Abstract

The invention relates to the technical field of tamping machine detection, in particular to a method, device and equipment for detecting the height of a coal cake on a tamping machine and a medium. Analyzing the operation vibration data to generate a vibration compensation model; correcting the height of the coal cake based on the vibration compensation model; and outputting the corrected coal cake height measurement value. The method has the effect of improving the accuracy of coal cake detection of the tamping machine.

Description

Technical Field

[0001] The present application relates to the technical field of tamping machine detection, and in particular to a method, device, equipment and medium for detecting the height of coal cakes on a tamping machine. Background Art

[0002] A method for detecting the height of coal cakes on a tamping machine is mainly used in the coal cake tamping process in coking production. A non-contact sensor (such as a laser ranging sensor or an ultrasonic sensor, etc.) is used to measure the vertical distance from the top of the coal cake entering the barrel of the tamping machine to the bottom of the barrel in real time, thereby obtaining the compaction height data of the coal cake.

[0003] One challenge faced by this method is that during the coal cake height detection process, the continuous vibration generated by the tamping machine will directly have an adverse effect on the detection accuracy. The vibration will cause the relative position between the sensor and the surface to be detected to change, thereby introducing additional errors and reducing the accuracy of the detection. Summary of the invention In order to improve the accuracy of coal cake detection on a tamping machine, the present application provides a method, device, equipment and medium for detecting the height of coal cakes on a tamping machine.

[0004] In the first aspect, the present application provides a method for detecting the height of coal cakes on a tamping machine, which adopts the following technical solution: A method for detecting the height of coal cakes on a tamping machine, Obtain the operating vibration data of the tamping machine; Analyzing the operation vibration data to generate a vibration compensation model; Correcting the coal cake height based on the vibration compensation model; Outputs the corrected briquette height measurement.

[0005] By adopting the above technical solution, the operating vibration data of the tamping machine is obtained. By analyzing the operating vibration data, the relationship between vibration and coal cake height can be revealed, and then a vibration compensation model can be established. It helps to reduce the coal cake height measurement error caused by vibration and can more accurately reflect the actual height of the coal cake. In the process of coal cake height detection, the vibration compensation model is applied in real time to correct the measured value, which can immediately eliminate or reduce the impact of vibration on the measurement result. After the correction is completed, the corrected Meibin height measurement value is output, so that the staff can intuitively see the coal cake height.

[0006] In another possible implementation manner, analyzing the vibration data to generate a vibration compensation model includes: Using fast Fourier transform to obtain frequency spectrum characteristics of the vibration data; The principal component analysis is used to extract characteristic parameters representing the vibration state from the spectrum characteristics; Based on the characteristic parameters and the corresponding coal cake height detection results, association training is performed with a multivariate statistical model; The multivariate statistical model is adjusted by cross validation to obtain the vibration compensation model.

[0007] In another possible implementation, the briquettes height is corrected based on the vibration compensation model, including: Get current vibration data; Inputting the current vibration data into the vibration compensation model to obtain a compensation coefficient; Correcting the operating vibration data according to the compensation coefficient to determine the compensated operating vibration data; Analyzing the compensated operating vibration data to determine an actual coal cake contour curve; The coordinates of each detection point on the actual coal cake contour curve are converted to calculate the height change trend; The coal cake height is corrected according to the height variation trend.

[0008] In another possible implementation, the correcting the coal cake height based on the vibration compensation model further includes: Acquiring vibration deviation parameters based on the vibration compensation model; Performing filtering processing on the vibration deviation parameter to obtain a filtering result; Calculate the compensation amount C based on the filtering result, C=K×(AF), where A represents the filtering result, F is the reference amplitude, and K is the coefficient; The compensation amount is added to the coal cake height detection result to correct the coal cake height.

[0009] In another possible implementation manner, the obtaining the vibration deviation parameter based on the vibration compensation model includes: Call the latest state model M; Execute a simulation process based on the state model M to generate a simulation deviation Δ; Compare the simulation results with the actual test results to obtain the measured deviation Δm; The vibration deviation parameter S is calculated based on the simulated deviation Δ and the measured deviation Δm, wherein S=|Δ-Δm|, S is the vibration deviation parameter, Δ is the simulated deviation, and Δm is the measured deviation.

[0010] In another possible implementation manner, comparing the simulation result with the actual detection result includes: Compare the time series results Ts obtained from the simulation with the actual on-site detection results Ta; Compare the numerical differences of the same timestamp points in the two sequences and calculate the overall difference D, that is, D=S×τ, where τ is the time step; If D>δ, the vibration compensation model is updated to obtain an updated vibration compensation model, where the formula for updating the equipment vibration compensation model is M=M+μ×(D / λ), where M represents the model parameter group of the new version, D is the cumulative deviation sum calculated above, μ is the adjustment coefficient, λ represents the vibration intensity level value, and δ represents the preset error threshold.

[0011] In another possible implementation manner, the obtaining of the measured results based on the updated vibration compensation model includes: Predicting the on-site vibration amplitude H based on the updated vibration compensation model, where H=G×M, G is a conversion matrix of the inherent characteristics of the equipment; Correct the theoretical prediction value H′ based on the actual sensor reading N; Calculate the actual coal cake position error ε=(H′–N); Determine whether the condition ε<η is true, η is the acceptable error limit, and if the condition is true, output the correction instruction.

[0012] In the second aspect, the present application provides a coal cake height detection device on a tamping machine, which adopts the following technical solution: A coal cake height detection device on a tamping machine, comprising: A data acquisition module, used for acquiring the operation vibration data of the tamping machine; A model generation module, used for analyzing the operation vibration data and generating a vibration compensation model; A height correction module, used for correcting the height of the coal cake based on the vibration compensation model; The measurement output module is used to output the corrected coal cake height measurement value.

[0013] By adopting the above technical solution, the data acquisition module obtains the operating vibration data of the tamping machine, and the model generation module analyzes the operating vibration data to reveal the relationship between vibration and coal cake height, and then establishes a vibration compensation model. It helps to reduce the coal cake height measurement error caused by vibration and can more accurately reflect the actual height of the coal cake. During the coal cake height detection process, the height correction module applies the vibration compensation model in real time to correct the measured value, which can immediately eliminate or reduce the impact of vibration on the measurement result. After the correction is completed, the measurement output module outputs the corrected Meibin height measurement value, so that the staff can intuitively see the coal cake height.

[0014] In another possible implementation, when the model generation module analyzes the vibration data to generate the vibration compensation model, it is specifically used to: Using fast Fourier transform to obtain frequency spectrum characteristics of the vibration data; The principal component analysis is used to extract characteristic parameters representing the vibration state from the spectrum characteristics; Based on the characteristic parameters and the corresponding coal cake height detection results, association training is performed with a multivariate statistical model; The multivariate statistical model is adjusted by cross validation to obtain the vibration compensation model.

[0015] In another possible implementation, when the height correction module corrects the coal cake height based on the vibration compensation model, it is specifically used to: Get current vibration data; Inputting the current vibration data into the vibration compensation model to obtain a compensation coefficient; Correcting the operating vibration data according to the compensation coefficient to determine the compensated operating vibration data; Analyzing the compensated operating vibration data to determine an actual coal cake contour curve; The coordinates of each detection point on the actual coal cake contour curve are converted to calculate the height change trend; The coal cake height is corrected according to the height variation trend.

[0016] In another possible implementation, the device further includes: A deviation parameter acquisition module, used for acquiring vibration deviation parameters based on the vibration compensation model; A filtering result determination module, used for filtering the vibration deviation parameter to obtain a filtering result; A compensation amount calculation module, used for calculating a compensation amount C based on the filtering result, C=K×(AF), where A represents the filtering result, F is the reference amplitude, and K is the coefficient; The compensation adding module is used to add the compensation amount to the coal cake height detection result to correct the coal cake height.

[0017] In another possible implementation, when the deviation parameter acquisition module acquires the vibration deviation parameter based on the vibration compensation model, it is specifically used to: Call the latest state model M; Execute a simulation process based on the state model M to generate a simulation deviation Δ; Compare the simulation results with the actual test results to obtain the measured deviation Δm; The vibration deviation parameter S is calculated based on the simulated deviation Δ and the measured deviation Δm, wherein S=|Δ-Δm|, S is the vibration deviation parameter, Δ is the simulated deviation, and Δm is the measured deviation.

[0018] In another possible implementation, when comparing the simulation result with the actual detection result, the deviation parameter acquisition module is specifically used to: Compare the time series results Ts obtained from the simulation with the actual on-site detection results Ta; Compare the numerical differences of the same timestamp points in the two sequences and calculate the overall difference D, that is, D=S×τ, where τ is the time step; If D>δ, the vibration compensation model is updated to obtain an updated vibration compensation model, where the formula for updating the equipment vibration compensation model is M=M+μ×(D / λ), where M represents the model parameter group of the new version, D is the cumulative deviation sum calculated above, μ is the adjustment coefficient, λ represents the vibration intensity level value, and δ represents the preset error threshold.

[0019] In another possible implementation, the device includes: A vibration amplitude prediction module, used to predict the on-site vibration amplitude H based on the updated vibration compensation model, where H=G×M, G is a conversion matrix of the inherent characteristics of the equipment; A theoretical prediction value correction module, used to correct the theoretical prediction value H′ based on the actual sensor reading N; Error calculation module, used to calculate the actual coal cake position error ε=(H′–N); The condition judgment module is used to judge whether the condition ε<η is true, η is the acceptable error limit, and outputs a correction instruction if the judgment condition is true.

[0020] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device, comprising: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and at least one is configured to: execute a method for detecting the height of coal cakes on a tamping machine as shown in any possible implementation of the first aspect.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium, when the computer program is executed in a computer, enables the computer to execute a coal cake height detection method on a tamping machine as described in any one of the first aspects.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: 1. Obtain the operating vibration data of the tamping machine. By analyzing the operating vibration data, the relationship between vibration and coal cake height can be revealed, and then a vibration compensation model can be established. It helps to reduce the coal cake height measurement error caused by vibration and can more accurately reflect the actual height of the coal cake. During the coal cake height detection process, the vibration compensation model is applied in real time to correct the measured value, which can immediately eliminate or reduce the impact of vibration on the measurement result. After the correction is completed, the corrected Meibin height measurement value is output, so that the staff can intuitively see the coal cake height. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of a method for detecting the height of coal cakes on a tamping machine in an embodiment of the present application.

[0024] Figure 2 It is a flow chart of analyzing vibration data and generating a vibration compensation model according to an embodiment of the present application.

[0025] Figure 3 It is a schematic diagram of the process of correcting the coal cake height based on the vibration compensation model in an embodiment of the present application.

[0026] Figure 4 It is a flow chart of a coal cake height detection device on a tamping machine in an embodiment of the present application.

[0027] Figure 5 It is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] The following is combined with Figure 1-5 This application is described in further detail.

[0029] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0030] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0032] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0033] The embodiment of the present application provides a method for detecting the height of coal cakes on a tamping machine, which is performed by an electronic device, and the electronic device can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and the embodiment of the present application does not limit this. Figure 1 As shown, the method includes: step S101, step S102, step S103, step S104, wherein: Step S101, obtaining the operation vibration data of the tamping machine.

[0034] In the embodiment of the present application, vibration sensors are installed at key parts of the tamping machine (such as tamping arms, tamping picks, etc.) to collect vibration data during the tamping process in real time, including parameters such as vibration frequency, amplitude, acceleration, etc. These data are transmitted to the data processing center via a data acquisition card. A high-definition camera combined with digital image processing technology is used to perform real-time detection of the height of the coal cake during the tamping process. The camera is installed above the tamping station, which can clearly capture the outline of the coal cake and calculate the actual height of the coal cake through an image processing algorithm.

[0035] Step S102: analyzing the operation vibration data to generate a vibration compensation model.

[0036] In an embodiment of the present application, key features are extracted from the vibration data, such as the fluctuation range of the vibration frequency, the changing trend of the amplitude, etc., and these features will be used for subsequent model training. Using machine learning or deep learning algorithms (such as neural networks, support vector machines, etc.), with vibration data as input and coal cake height detection error as output, the vibration compensation model is trained. The goal of the model is to learn the influence of vibration on coal cake height detection and predict the coal cake height detection error under given vibration conditions. Use historical data or experimental data to verify the model and evaluate its prediction accuracy and generalization ability. According to the verification results, the model is tuned to improve its accuracy and stability.

[0037] Step S103, correcting the coal cake height based on the vibration compensation model.

[0038] In the embodiment of the present application, during the tamping process, vibration data is collected in real time and input into the vibration compensation model, and the model predicts the detection error of the coal cake height according to the current vibration state. The predicted detection error is added to the original coal cake height detection value to obtain the corrected coal cake height measurement value.

[0039] Step S104, outputting the corrected coal cake height measurement value.

[0040] In the embodiment of the present application, the corrected coal cake height measurement value is displayed in real time on the operation interface for reference by the operator. At the same time, the data can be recorded in the database for subsequent analysis and tracing.

[0041] Assume that during a tamping process, the vibration frequency collected by the vibration sensor is 60Hz and the amplitude is 0.5mm. At the same time, the coal cake height detected by the high-definition camera is 2.5m. The vibration data is input into the vibration compensation model, and the model predicts that the detection error of the coal cake height under the current vibration conditions is -0.05m (that is, the actual height may be 0.05m lower than the detected value). Therefore, the corrected coal cake height measurement value is 2.5m+0.05m=2.55m. This corrected value will be output to the operator as the final coal cake height measurement result.

[0042] The introduction of the vibration compensation model can effectively eliminate or reduce the impact of vibration on coal cake height detection. The real-time vibration data collection and analysis enables the system to respond to vibration changes during the tamping process in a timely manner, and avoid operational errors or equipment failures caused by vibration by correcting the coal cake height, thereby enhancing the stability and reliability of the entire system and further improving the accuracy of coal cake height measurement.

[0043] A possible implementation method of the embodiment of the present application is as follows: Figure 2 As shown, analyzing the vibration data and generating a vibration compensation model includes: step S105, step S106, step S107, step S108, wherein: Step S105, using fast Fourier transform to obtain frequency spectrum characteristics of the vibration data.

[0044] In the embodiment of the present application, the vibration data collected from the tamping machine is ensured to be continuous and time-synchronized. These data usually include signals such as acceleration, velocity or displacement. Fast Fourier transform (FFT) is applied to the vibration data to convert the time domain signal into a frequency domain signal. FFT can reveal the frequency components in the vibration signal and their corresponding amplitudes, thereby obtaining the spectral characteristics. The results of FFT are displayed in the form of a spectrum diagram to facilitate the observation of the main frequency components and energy distribution of the vibration signal.

[0045] Assuming that the collected vibration data appears as a series of fluctuations in the time domain, after FFT transformation, it is found that the vibration signals are mainly concentrated at three frequencies of 50 Hz, 100 Hz and 150 Hz, and the amplitudes corresponding to these three frequencies are relatively large, indicating that the vibration of the tamping machine is mainly composed of these three frequency components.

[0046] Step S106: extracting characteristic parameters representing the vibration state from the frequency spectrum characteristics by using principal component analysis.

[0047] In an embodiment of the present application, the spectrum characteristic data (such as the amplitude of each frequency point) obtained by FFT is used as the input data of PCA. The principal component analysis (PCA) algorithm is applied to perform dimension reduction processing on the spectrum characteristic data. PCA can identify the main change patterns (i.e., principal components) in the data and extract characteristic parameters (i.e., principal component scores) that can characterize these patterns. According to the results of PCA, the principal component with a larger contribution rate is selected as the characteristic parameter characterizing the vibration state. These characteristic parameters will be used for subsequent model training.

[0048] Assume that after PCA analysis, it is found that the cumulative contribution rate of the first two principal components (PC1 and PC2) reaches more than 90%, indicating that these two principal components can well characterize the vibration state. Therefore, the scores of PC1 and PC2 are selected as the input feature parameters of the subsequent model.

[0049] Step S107, the characteristic parameters and the corresponding coal cake height detection results are associated with the multivariate statistical model for training.

[0050] In an embodiment of the present application, the extracted characteristic parameters are matched with the corresponding coal cake height detection results to ensure that each characteristic parameter has a corresponding coal cake height value. According to the nature of the problem and the characteristics of the data, a suitable multivariate statistical model is selected, such as a linear regression model, a multivariate nonlinear regression model or a machine learning model (such as a support vector machine, a neural network, etc.). The selected model is trained using the matched data. During the training process, the model will learn the correlation between the characteristic parameters and the coal cake height, and try to find the best fitting method.

[0051] Assume that a linear regression model is selected as the association model and the least squares method is used for parameter estimation. During the training process, the model learns the linear relationship between PC1 and PC2 scores and the briquette height and outputs a regression equation for predicting the briquette height under a given vibration state.

[0052] Step S108: cross-validation is used to adjust the multivariate statistical model to obtain a vibration compensation model.

[0053] In an embodiment of the present application, the data set is divided into a training set and a validation set (or a more complex cross-validation strategy, such as K-fold cross-validation, is used). The trained model is evaluated using the validation set to calculate the model's prediction accuracy, error and other indicators. The model is adjusted according to the evaluation results, including adjusting model parameters, changing model types or adding new feature parameters. The adjusted model is retrained, and evaluated and adjusted again until satisfactory performance is achieved. After multiple iterations, the final vibration compensation model is obtained. The model can predict a relatively accurate coal cake height based on given vibration state characteristic parameters.

[0054] Assume that a 5-fold cross-validation strategy is used to evaluate and adjust the linear regression model. In each cross-validation, the data set is divided into 5 subsets, and one of the subsets is selected as the validation set in turn, and the remaining subsets are used as the training set for training. After 5 iterations, the average performance indicators of the model on different validation sets are obtained. According to these indicators, the model is adjusted (such as adjusting the regression coefficient, adding regularization terms, etc.) until the performance of the model on the validation set reaches a stable and good level. The final linear regression model is the vibration compensation model.

[0055] A possible implementation method of the embodiment of the present application is as follows: Figure 3 As shown, the coal cake height is corrected based on the vibration compensation model, including: step S109, step S110, step S111, step S112, step S113, step S114, wherein: Step S109, obtaining current vibration data.

[0056] In the embodiment of the present application, vibration sensors are installed on the briquette forming machine or related equipment, and these sensors can capture the vibration data of the equipment in real time during operation. The output data of the vibration sensors are collected regularly or continuously through the data acquisition system, and these data include parameters such as amplitude, frequency, and phase.

[0057] Step S110: input the current vibration data into a vibration compensation model to obtain a compensation coefficient.

[0058] In the embodiment of the present application, a mathematical model (i.e., a vibration compensation model) between vibration and briquette height change is established in advance by machine learning or physical modeling methods. The model should be able to predict the potential change in briquette height based on the input vibration data. The real-time collected vibration data is used as input and sent to the vibration compensation model. The model calculates the corresponding compensation coefficients based on the input data, and these coefficients reflect the degree of influence of vibration on the briquette height measurement.

[0059] Assume that the model is a prediction model based on a neural network, with amplitude and frequency as input and height compensation coefficient k as output. When the current amplitude is 0.5 mm and the frequency is 50 Hz, the model outputs compensation coefficient k=0.98, indicating that the actual coal cake height may be 2% lower than the measured value due to vibration.

[0060] Step S111, correcting the operating vibration data according to the compensation coefficient to determine the compensated operating vibration data.

[0061] In the embodiment of the present application, the calculated compensation coefficient is used to correct the original vibration data to eliminate the influence of vibration on the measurement of coal cake height. Assuming that the original measured coal cake height is 100mm, according to the compensation coefficient k=0.98, the corrected height is 1000×98=98mm.

[0062] Step S112, analyzing the compensated operating vibration data to determine the actual coal cake contour curve.

[0063] In the embodiment of the present application, the corrected vibration data is further analyzed, such as using image processing technology (if the vibration data is converted into an image in some way) or mathematical methods (such as curve fitting) to depict the contour curve of the coal cake.

[0064] Step S113, converting the coordinates of each detection point on the actual coal cake contour curve and calculating the height change trend.

[0065] 1. In the embodiment of the present application, the coordinate points on the contour curve are converted from one coordinate system to another coordinate system (such as from the device coordinate system to the world coordinate system). Assume that the slope of the contour curve at different positions is calculated and it is found that the slope gradually increases from the center to the edge, indicating that the height of the edge of the briquettes decreases rapidly.

[0066] Step S114, correcting the coal cake height according to the height change trend.

[0067] In the embodiment of the present application, a correction strategy is formulated according to the height change trend, such as adjusting the pressure distribution of the press, and the briquette forming process is adjusted according to the correction strategy to achieve the desired briquette height and shape. For example, according to the height change trend, it is decided to increase the pressure of the edge area during the pressing process to reduce the drop in the edge height, thereby correcting the overall height distribution of the briquette.

[0068] A possible implementation of the embodiment of the present application is to correct the coal cake height based on the vibration compensation model, and further includes: The vibration deviation parameters are obtained based on the vibration compensation model.

[0069] 1. In an embodiment of the present application, the real-time collected vibration data (such as acceleration, velocity or displacement signal) is input into a pre-trained vibration compensation model. The vibration compensation model outputs a vibration deviation parameter related to the briquette height deviation based on the input vibration data. This parameter may be a value directly representing the height deviation, or it may be a quantity that is proportional to or correlated with the height deviation. It is assumed that the vibration compensation model outputs a vibration deviation index (VDI), which is proportional to the actual deviation of the briquette height.

[0070] The vibration deviation parameters are filtered to obtain a filtering result.

[0071] In the embodiment of the present application, according to the characteristics and noise level of the vibration data, a suitable filter (such as a low-pass filter, a band-pass filter, a Kalman filter, etc.) is selected to filter the vibration deviation parameters. The vibration deviation parameters are input into the selected filter and filtered to remove noise and unnecessary high-frequency components to obtain a smooth filtering result. Assume that a low-pass filter is used to filter the VDI, and the cutoff frequency is set to 10Hz to remove noise and vibration fluctuations above 10Hz.

[0072] The compensation amount C is calculated based on the filtering result, C=K×(AF).

[0073] In the embodiment of the present application, A represents the filtering result, F is the reference amplitude, and K is the coefficient. According to the characteristics of the coal cake forming machine and the requirements of the vibration compensation model, the reference amplitude F and the coefficient K in the formula are determined. The reference amplitude F can be the amplitude of the coal cake forming machine under ideal conditions, and the coefficient K is a proportional factor obtained based on experiments or data analysis. Substitute the filtering result A into the formula C=K×(AF) to calculate the compensation amount C. Assume that the reference amplitude F is 0.5mm and the coefficient K is 2. The deviation A after filtering is 0.1mm (indicating that the actual amplitude is 0.1mm higher than the reference, which may cause the coal cake height to be low). Then the compensation amount C=2×(0.1-0.5)=-0.8mm (a negative value indicates that the coal cake height needs to be increased).

[0074] The compensation amount is added to the coal cake height detection result to correct the coal cake height.

[0075] In the embodiment of the present application, a coal cake height detection device (such as a laser rangefinder, an ultrasonic sensor, etc.) is used to obtain the original height detection result of the coal cake. The calculated compensation amount C is added to the original height detection result to obtain the corrected coal cake height. Assuming that the original height detection result is 100mm, the compensation amount C is -0.8mm. Then the corrected coal cake height is 100mm+(-0.8mm)=99.2mm.

[0076] The present application implements real-time correction of vibration deviation through a vibration compensation model, thereby reducing measurement errors caused by vibration interference, making the measurement results closer to the true value, and thus improving the accuracy of coal cake height measurement.

[0077] A possible implementation of the embodiment of the present application is to obtain a vibration deviation parameter based on a vibration compensation model, including: Call the latest state model M.

[0078] In an embodiment of the present application, it is ensured that the latest state model M is stored in the vibration compensation system. This model may contain information such as structural parameters, material properties, working environment conditions, and historical vibration data of the equipment. When it is necessary to obtain vibration deviation parameters, this latest state model M is called through an electronic device. Assume that the state model M is a neural network-based model that has been trained with a large amount of historical data and updated in real time to reflect the latest state of the equipment. Before obtaining the vibration deviation parameters, the system calls this neural network model through an API interface.

[0079] A simulation process is performed based on the state model M to generate a simulation deviation Δ.

[0080] In an embodiment of the present application, the current operating conditions, such as speed, load, temperature, etc., are input to the state model M. Model M performs simulation according to the input conditions to simulate the vibration behavior of the device under given conditions. After the simulation, the model outputs a simulated vibration deviation Δ, which is the vibration deviation that the model predicts may occur under the current conditions. Assume that, under the conditions of inputting a current speed of 1200rpm and a load of 80%, the state model M performs simulation and outputs a simulated vibration deviation Δ of 0.05mm.

[0081] The simulation results are compared with the actual test results to obtain the measured deviation Δm.

[0082] In the embodiment of the present application, a detection device such as a vibration sensor is used to collect vibration data of the device in real time. The collected vibration data is processed to extract the vibration deviation Δm corresponding to the simulation result. Assume that the vibration data collected in real time by the vibration sensor shows that the actual vibration deviation Δm of the device under the current conditions is 0.06mm.

[0083] The vibration deviation parameter S is calculated based on the simulation deviation Δ and the measured deviation Δm.

[0084] In the embodiment of the present application, S=|Δ-Δm|, S is the vibration deviation parameter, Δ is the simulation deviation, and Δm is the measured deviation. Substituting the simulation deviation Δ=0.05mm and the measured deviation Δm=0.06mm into the formula, the vibration deviation parameter S=[0.05-0.06]=0.01mm is calculated.

[0085] In the embodiment of the present application, by calling the latest state model M for simulation, the vibration behavior of the device under specific conditions can be predicted more accurately. The vibration data of the device is collected in real time and compared with the simulation results, and the measured deviation Δm can be quickly obtained. This real-time performance enables the system to respond quickly to vibration changes. The vibration deviation parameter S calculated based on the simulated deviation Δ and the measured deviation Δm provides an accurate reference for vibration compensation.

[0086] A possible implementation of the embodiment of the present application is to compare the simulation result with the actual detection result, including: The time series results Ts obtained by simulation are compared with the actual on-site detection results Ta.

[0087] In the embodiment of the present application, the existing vibration simulation model M is used to run the simulation under specific working conditions to obtain the time series result Ts. Ts contains the vibration data at each time point during the simulation process. Under the same or similar working conditions, a detection device such as a vibration sensor is used to perform real-time vibration detection on the field equipment to obtain the time series result Ta. Ta contains the vibration data at each time point during the actual operation process.

[0088] Compare the numerical differences of the same timestamp points in the two sequences and calculate the overall difference D, that is, D=S×τ.

[0089] In the embodiment of the present application, τ is the time step. The timestamps in Ts and Ta are aligned to ensure that the two sequences are compared on the same time scale. For each aligned timestamp point, the numerical difference between Ts and Ta at that point is calculated to obtain a series of differences. The numerical differences of all timestamp points are accumulated (or accumulated according to a certain weight) to obtain the overall difference D. According to the given formula D=S×τ, S is the sum of the cumulative deviations (that is, the sum of all differences divided by the number of time steps τ), but in this scenario, we directly calculate D as a measure of the cumulative deviation.

[0090] If D>δ, the vibration compensation model is updated to obtain an updated vibration compensation model.

[0091] In the embodiment of the present application, the formula for updating the vibration compensation model of the device is M=M+μ×(D / λ), where M represents the model parameter group of the new version, D is the cumulative deviation sum calculated above, μ is the adjustment coefficient, λ represents the vibration intensity level value, and δ represents the preset error threshold. The calculated overall difference D is compared with the preset error threshold δ. If D>δ, it indicates that there is a large deviation between the simulation model and the actual situation, and the vibration compensation model needs to be updated.

[0092] For example, simulation result Ts: within 10 time steps, the vibration data of each time step are [1, 2, 3, 4, 5, 4, 3, 2, 1, 0]. Actual detection result Ta: within the same time step, the vibration data of each time step are [1.1, 2.2, 2.9, 4.1, 5.2, 4.0, 3.1, 2.0, 0.9, 0.1]. The time step τ is 1 second. The preset error threshold δ is 0.5. The adjustment coefficient μ is 0.1. The vibration intensity level value λ is 5.

[0093] Numeric difference sequence: [0.1, 0.2, -0.1, 0.1, 0.2, 0.0, -0.1, 0.0, -0.1, -0.1].

[0094] Overall difference D: D=0.1+0.2+(−0.1)+0.1+0.2+0.0+(−0.1)+0.0+(−0.1)+(−0.1)=0.2.

[0095] Since D=0.2>δ=0.5, the updated model parameter group M (assuming the original model parameter group is Mold) is: M=Mold+0.1×(0.2 / 5)=Mold+0.004.

[0096] A possible implementation of the embodiment of the present application is to obtain the measured results based on the updated vibration compensation model, including: The on-site vibration amplitude H is predicted based on the updated vibration compensation model.

[0097] In the embodiment of the present application, H=G×M, where G is the conversion matrix of the inherent characteristics of the equipment. The updated vibration compensation model M is used for vibration prediction. This model has been adjusted based on the comparison between the previous simulation results and the actual test results to more accurately reflect the vibration characteristics of the equipment. The conversion matrix G of the inherent characteristics of the equipment is multiplied by the updated model parameters M to obtain the predicted on-site vibration amplitude H. That is, H=C×M. Here, G contains information such as the physical characteristics and structural parameters of the equipment, which is used to convert the model parameters into actual vibration amplitudes.

[0098] The theoretical prediction value H' is corrected based on the actual sensor reading N.

[0099] In the embodiment of the present application, a vibration sensor installed on the equipment is used to detect vibration data in real time to obtain a sensor reading N. Due to various interference factors in the actual environment, the theoretical predicted value H may deviate from the actual reading N. Therefore, it is necessary to correct H according to N to obtain a corrected predicted value H′. The correction method may include simple addition and subtraction operations, proportional adjustment, or more complex algorithms.

[0100] Calculate the actual coal cake position error ε=(H′–N).

[0101] In the embodiment of the present application, the coal cake position error ε refers to the difference between the predicted coal cake position (indirectly reflected by the vibration amplitude) and the actual coal cake position.

[0102] Determine whether the condition ε<η is true, η is the acceptable error limit, and if the condition is true, output the correction instruction.

[0103] In the embodiment of the present application, the calculated error ε is compared with the preset acceptable error limit η. If ε<η, the error is considered to be within the acceptable range and no further correction is required. If ε≥η, it indicates that there is a large deviation between the predicted coal cake position and the actual position, and a correction instruction needs to be output to adjust the equipment or control parameters to return the coal cake position to the expected range.

[0104] In the embodiment of the present application, the model is updated regularly and the predicted value is corrected in real time, which helps to reduce the long-term deviation caused by error accumulation, making it closer to the actual working conditions, thereby improving the accuracy of vibration prediction.

[0105] Assume that the updated vibration compensation model M is adjusted to more accurately predict the vibration amplitude of the equipment. The transformation matrix G of the inherent characteristics of the equipment is known, and the predicted vibration amplitude H is calculated. The real-time sensor reading N is 2.5mm. After correction, the predicted value H′ is 2.6mm. The preset acceptable error limit η is 0.1mm.

[0106] The actual coal cake position error ε = (2.6-2.5) = 0.1mm Since ε=0.1mm is equal to η, according to the actual application, the error may be considered within the acceptable range, or slightly exceeded, depending on the error handling strategy. If the system is set to be strictly less than η to be acceptable, no correction command will be output at this time; if the system is set to be less than or equal to η to be acceptable, it may choose not to output or output a fine-tuning command.

[0107] The above embodiment introduces a method for detecting the height of coal cakes on a tamping machine from the perspective of a method flow, and the following embodiment introduces a device 20 for detecting the height of coal cakes on a tamping machine from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiment.

[0108] The embodiment of the present application provides a coal cake height detection device 20 on a tamping machine, such as Figure 4 As shown, the coal cake height detection device 20 on the tamping machine may specifically include: A coal cake height detection device 20 on a tamping machine, comprising: The data acquisition module 201 is used to acquire the operation vibration data of the tamping machine; A model generation module 202 is used to analyze the operation vibration data and generate a vibration compensation model; A height correction module 203, used to correct the height of the coal cake based on a vibration compensation model; The measurement output module 204 is used to output the corrected coal cake height measurement value.

[0109] By adopting the above technical solution, the data acquisition module 201 obtains the operating vibration data of the tamping machine, and the model generation module 202 can reveal the relationship between vibration and coal cake height by analyzing the operating vibration data, and then establish a vibration compensation model. It helps to reduce the coal cake height measurement error caused by vibration and can more accurately reflect the actual height of the coal cake. During the coal cake height detection process, the height correction module 203 applies the vibration compensation model in real time to correct the measured value, which can immediately eliminate or reduce the impact of vibration on the measurement result. After the correction is completed, the measurement output module 204 outputs the corrected Meibin height measurement value, so that the staff can intuitively see the coal cake height.

[0110] In a possible implementation of the embodiment of the present application, when the model generation module 202 analyzes the vibration data and generates the vibration compensation model, it is specifically used to: Fast Fourier transform is used to obtain the spectrum characteristics of vibration data; The principal component analysis is used to extract characteristic parameters representing the vibration state from the spectrum characteristics; Based on the characteristic parameters and the corresponding coal cake height detection results, the multivariate statistical model is trained; Cross-validation was used to adjust the multivariate statistical model and obtain the vibration compensation model.

[0111] In a possible implementation of the embodiment of the present application, when the height correction module 203 corrects the coal cake height based on the vibration compensation model, it is specifically used to: Get current vibration data; Input the current vibration data into the vibration compensation model to obtain the compensation coefficient; Correcting the operating vibration data according to the compensation coefficient to determine the compensated operating vibration data; Analyze the compensated operating vibration data to determine the actual coal cake profile curve; The coordinates of each detection point on the actual coal cake contour curve are converted to calculate the height change trend; The coal cake height is corrected according to the height change trend.

[0112] In a possible implementation of the embodiment of the present application, the device 20 further includes: A deviation parameter acquisition module, used for acquiring vibration deviation parameters based on a vibration compensation model; A filtering result determination module is used to filter the vibration deviation parameters to obtain a filtering result; A compensation amount calculation module is used to calculate the compensation amount C based on the filtering result, C=K×(AF), where A represents the filtering result, F is the reference amplitude, and K is the coefficient; The compensation adding module is used to add the compensation amount to the coal cake height detection result to correct the coal cake height.

[0113] In a possible implementation manner of the embodiment of the present application, when the deviation parameter acquisition module acquires the vibration deviation parameter based on the vibration compensation model, it is specifically used to: Call the latest state model M; Execute a simulation process based on the state model M to generate a simulation deviation Δ; Compare the simulation results with the actual test results to obtain the measured deviation Δm; The vibration deviation parameter S is calculated based on the simulated deviation Δ and the measured deviation Δm, where S=|Δ-Δm|, S is the vibration deviation parameter, Δ is the simulated deviation, and Δm is the measured deviation.

[0114] In a possible implementation of the embodiment of the present application, when the deviation parameter acquisition module compares the simulation result with the actual detection result, it is specifically used to: Compare the time series results Ts obtained from the simulation with the actual on-site detection results Ta; Compare the numerical differences of the same timestamp points in the two sequences and calculate the overall difference D, that is, D=S×τ, where τ is the time step; If D>δ, the vibration compensation model is updated to obtain an updated vibration compensation model, where the formula for updating the equipment vibration compensation model is M=M+μ×(D / λ), where M represents the model parameter group of the new version, D is the cumulative deviation sum calculated above, μ is the adjustment coefficient, λ represents the vibration intensity level value, and δ represents the preset error threshold.

[0115] In a possible implementation manner of the embodiment of the present application, the device 20 includes: A vibration amplitude prediction module is used to predict the on-site vibration amplitude H based on the updated vibration compensation model, where H=G×M, and G is a conversion matrix of the inherent characteristics of the equipment; A theoretical prediction value correction module, used to correct the theoretical prediction value H′ based on the actual sensor reading N; Error calculation module, used to calculate the actual coal cake position error ε=(H′–N); The condition judgment module is used to judge whether the condition ε<η is true, η is the acceptable error limit, and outputs a correction instruction if the judgment condition is true.

[0116] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0117] An electronic device is provided in an embodiment of the present application, such as Figure 5 As shown, Figure 5 The electronic device 30 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 does not constitute a limitation on the embodiments of the present application.

[0118] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0119] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0120] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0121] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0122] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 5 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0123] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment. Compared with the related art, the operating vibration data of the tamping machine is obtained in the embodiment of the present application. By analyzing the operating vibration data, the relationship between vibration and coal cake height can be revealed, and then a vibration compensation model can be established. It helps to reduce the coal cake height measurement error caused by vibration, and can more accurately reflect the actual height of the coal cake. In the process of coal cake height detection, the vibration compensation model is applied in real time to correct the measured value, which can immediately eliminate or reduce the impact of vibration on the measurement result. After the correction is completed, the corrected Mei Bin height measurement value is output, so that the staff can intuitively see the coal cake height.

[0124] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0125] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for detecting the height of coal cakes on a tamping machine, characterized in that: include: Obtain the operating vibration data of the tamping machine; Analyzing the operation vibration data to generate a vibration compensation model; Correcting the coal cake height based on the vibration compensation model; Outputs the corrected briquette height measurement.

2. A method for detecting the height of coal cakes on a tamping machine according to claim 1, characterized in that: The analyzing the vibration data to generate a vibration compensation model comprises: Using fast Fourier transform to obtain frequency spectrum characteristics of the vibration data; The principal component analysis is used to extract characteristic parameters representing the vibration state from the spectrum characteristics; Based on the characteristic parameters and the corresponding coal cake height detection results, association training is performed with a multivariate statistical model; The multivariate statistical model is adjusted by cross validation to obtain the vibration compensation model.

3. A method for detecting the height of coal cakes on a tamping machine according to claim 2, characterized in that: The method of correcting the coal cake height based on the vibration compensation model comprises: Get current vibration data; Inputting the current vibration data into the vibration compensation model to obtain a compensation coefficient; Correcting the operating vibration data according to the compensation coefficient to determine the compensated operating vibration data; Analyzing the compensated operating vibration data to determine an actual coal cake contour curve; The coordinates of each detection point on the actual coal cake contour curve are converted to calculate the height change trend; The coal cake height is corrected according to the height variation trend.

4. A method for detecting the height of coal cakes on a tamping machine according to claim 1, characterized in that: The correction of the coal cake height based on the vibration compensation model also includes: Acquiring vibration deviation parameters based on the vibration compensation model; Performing filtering processing on the vibration deviation parameter to obtain a filtering result; Calculate the compensation amount C based on the filtering result, C=K×(AF), where A represents the filtering result, F is the reference amplitude, and K is the coefficient; The compensation amount is added to the coal cake height detection result to correct the coal cake height.

5. A method for detecting the height of coal cakes on a tamping machine according to claim 4, characterized in that: The obtaining of vibration deviation parameters based on the vibration compensation model includes: Call the latest state model M; Execute a simulation process based on the state model M to generate a simulation deviation Δ; Compare the simulation results with the actual test results to obtain the measured deviation Δm; The vibration deviation parameter S is calculated based on the simulated deviation Δ and the measured deviation Δm, wherein S=|Δ-Δm|, S is the vibration deviation parameter, Δ is the simulated deviation, and Δm is the measured deviation.

6. A method for detecting the height of coal cakes on a tamping machine according to claim 5, characterized in that: The comparing of the simulation results with the actual detection results includes: Compare the time series results Ts obtained from the simulation with the actual on-site detection results Ta; Compare the numerical differences of the same timestamp points in the two sequences and calculate the overall difference D, that is, D=S×τ, where τ is the time step; If D>δ, the vibration compensation model is updated to obtain an updated vibration compensation model, where the formula for updating the equipment vibration compensation model is M=M+μ×(D / λ), where M represents the model parameter group of the new version, D is the cumulative deviation sum calculated above, μ is the adjustment coefficient, λ represents the vibration intensity level value, and δ represents the preset error threshold.

7. A method for detecting the height of coal cakes on a tamping machine according to claim 6, characterized in that: The obtaining of the measured results based on the updated vibration compensation model includes: Predicting the on-site vibration amplitude H based on the updated vibration compensation model, where H=G×M, G is a conversion matrix of the inherent characteristics of the equipment; Correct the theoretical prediction value H′ based on the actual sensor reading N; Calculate the actual coal cake position error ε=(H′–N); Determine whether the condition ε<η is true, η is the acceptable error limit, and if the condition is true, output the correction instruction.

8. A coal cake height detection device on a tamping machine, characterized in that: include: A data acquisition module, used for acquiring the operation vibration data of the tamping machine; A model generation module, used for analyzing the operation vibration data and generating a vibration compensation model; A height correction module, used for correcting the height of the coal cake based on the vibration compensation model; The measurement output module is used to output the corrected coal cake height measurement value.

9. An electronic device, characterized in that: It includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and is configured to be executed by the at least one processor, and the at least one application is used to execute a coal cake height detection method on a tamping machine according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the method for detecting the height of coal cakes on a tamping machine as described in any one of claims 1 to 7.

Images