Self-adaptive wind pressure regulation and control system of quartz sand unpowered powder selecting equipment

Abstract

The invention discloses a self-adaptive air pressure regulation and control system of quartz sand unpowered powder selecting equipment, and relates to the technical field of automatic control. According to the method, wind pressure and airflow disturbance signals are collected, a high-resolution map is generated through Hampel filtering and noise reduction, features are extracted through the convolutional neural network, key influence areas are identified, the problem of unstable wind pressure caused by airflow disturbance in a mountainous area is solved, and the particle separation precision is improved; a natural potential energy distribution matrix is constructed based on building floor height difference, velocity field reconstruction and airflow channel optimization are driven, technological parameters are adjusted in combination with a gradient descent algorithm, precise utilization of natural potential energy is achieved, energy consumption is reduced, uneven efficiency is improved, airflow distribution is simulated through a fluid dynamic model, and sedimentation behaviors are analyzed and predicted through particle trajectory. A support vector machine is used for classifying tracks and generating regulation and control instructions, PID control is used for stabilizing air pressure to form a closed loop, the problems that fine powder is mixed with coarse powder, coarse particles are left and the like are avoided, the equipment blockage risk is reduced, and the product purity stability is improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of automatic control, and particularly relates to an adaptive air pressure regulation system of a quartz sand non-powered powder separation device. BACKGROUND

[0002] The field of mountainous quartz sand mining and processing faces unique environmental challenges, and the efficient use of mineral resources is crucial in this field, because quartz sand, as an industrial base material, is widely used in glass manufacturing and electronic products, and its powder separation process directly affects product quality and resource recovery rate. Traditional powder separation methods rely on fixed air pressure settings or external power equipment. In mountainous terrain, these schemes have practical defects: on the one hand, the equipment cannot cope with the continuous airflow disturbance caused by the terrain, resulting in unstable air pressure and affecting particle separation accuracy; on the other hand, power-dependent systems increase additional energy consumption and maintenance burden in non-powered scenarios, and cannot fully utilize natural potential energy, resulting in uneven overall efficiency and resource waste.

[0003] The core technical difficulty lies in real-time capture and dynamic regulation of air pressure fluctuations in complex mountainous environments. The fluctuation characteristics of air pressure in the airflow channel are first caused by the uneven distribution of natural airflow due to terrain elevation. This unevenness further amplifies the local deviation of the airflow velocity field in the powder separation chamber, making it difficult to predict particle settling behavior. For example, in actual powder separation operations, when the airflow on the upstream hillside suddenly increases, the air pressure in the chamber rises sharply, and fine powder particles are accidentally lifted and mixed into the coarse powder output, resulting in a decrease in product purity of more than 15%. The airflow in the downstream valley is weakened, causing insufficient settling and increasing the risk of coarse particle residue clogging the equipment. These interrelated air pressure fluctuations and airflow velocity field deviations form a chain of interference, hindering the stable operation of the powder separation process. SUMMARY

[0004] The purpose of the present application is to provide an adaptive air pressure regulation system for a quartz sand non-powered powder separation device, which solves the core problems of unstable air pressure, high energy consumption, insufficient potential energy utilization, and difficult prediction of particle settling, and achieves the operation goals of accurate, stable, energy-saving and efficient powder separation.

[0005] The purpose of the present application can be achieved by the following technical solutions: The present application provides an adaptive air pressure regulation system for a quartz sand non-powered powder separation device, comprising: An air pressure data acquisition and preprocessing module acquires real-time air pressure fluctuation data and airflow disturbance signals from the mountainous terrain environment through a sensor network deployed at multiple positions in the powder separation chamber, and obtains an initial air pressure distribution map; An air pressure fluctuation pattern recognition module processes the airflow disturbance signals using a convolutional neural network algorithm based on the initial air pressure distribution map to determine the air pressure fluctuation pattern and the particle separation accuracy influence area; The airflow velocity field optimization module adjusts the airflow velocity field deviation through the natural elevation potential energy utilization model if the wind pressure fluctuation mode exceeds the preset threshold, to obtain optimized airflow channel parameters. The particle sedimentation behavior prediction module obtains particle sedimentation behavior prediction data from the optimized airflow channel parameters, to determine whether the separation precision reaches the target level. The particle trajectory classification and regulation module classifies the coarse and fine powder particle trajectories by using a support vector machine algorithm according to the particle sedimentation behavior prediction data, to obtain a dynamic regulation instruction sequence. The wind pressure stability and efficiency correction module drives the unpowered regulating valve through the dynamic regulation instruction sequence, obtains real-time feedback of the wind pressure stability index, and determines an efficiency uneven correction scheme. The potential energy utilization path optimization module optimizes the potential energy utilization path by using a gradient descent algorithm if the efficiency uneven correction scheme shows a resource waste risk, to obtain a final powder selection process control sequence. The system adaptability evaluation module extracts a product purity improvement index from the final powder selection process control sequence, to determine whether the overall system response meets the mountainous environment adaptation requirements.

[0006] The present application has the following advantages: Through the cooperative operation of the wind pressure data acquisition and preprocessing module and the wind pressure fluctuation mode recognition module, the problem of wind pressure instability caused by airflow disturbance in mountainous terrain is solved. The wind pressure fluctuation and airflow disturbance signals are collected by a multi-position sensor network in the powder selection cavity, high-resolution wind pressure maps are generated through data processing, and disturbance features are extracted and key influence areas are recognized through a convolutional neural network to accurately capture the wind pressure dynamic mode. This breaks the limitations of traditional fixed wind pressure settings in dealing with terrain airflow interference, and significantly improves the stability of particle separation precision. Through the airflow velocity field optimization module and the potential energy utilization path optimization module, the problems of high energy consumption of traditional power-dependent systems and insufficient utilization of natural elevation potential energy are solved. When the wind pressure fluctuation exceeds the threshold, a natural potential energy distribution matrix is constructed based on the building height difference to drive the velocity field reconstruction and optimize the airflow channel configuration. At the same time, the process parameter ratio is dynamically adjusted through the gradient descent algorithm to realize the accurate utilization of natural potential energy, get rid of the dependence on external power equipment, effectively reduce the system energy consumption, improve the efficiency uneven condition, and reduce resource waste. Through the closed-loop regulation of the particle sedimentation behavior prediction module, the particle trajectory classification and regulation module and the wind pressure stability and efficiency correction module, the problem that the particle sedimentation is difficult to predict due to the chain interference caused by the wind pressure fluctuation and the airflow velocity field deviation is solved, the airflow distribution is simulated based on the optimized airflow parameters, the sedimentation behavior is predicted by combining the particle trajectory analysis, the trajectory is classified by the support vector machine and the regulation instruction is generated, and then the wind pressure is stabilized by the PID control, so that the problems such as the fine powder mixed into the coarse powder and the coarse particle residue are effectively avoided, the device blockage risk is reduced, the product purity stability is improved, and the powder selection process is ensured to continuously and stably operate. BRIEF DESCRIPTION OF DRAWINGS

[0007] In order to better understand and implement, the technical solutions of the present application are described in detail below in combination with the drawings.

[0008] Fig. 1 A structure schematic diagram of the self-adaptive wind pressure regulation system of the quartz sand non-powered powder selection device provided for Embodiment 1 of the present application; Fig. 2 A flowchart of the airflow velocity field optimization module in the self-adaptive wind pressure regulation system of the quartz sand non-powered powder selection device provided for Embodiment 1 of the present application; Fig. 3 A flowchart of the particle trajectory classification and regulation module in the self-adaptive wind pressure regulation system of the quartz sand non-powered powder selection device provided for Embodiment 1 of the present application. DETAILED DESCRIPTION

[0009] In order to better understand and implement, the technical solutions of the present application are described in detail below in combination with the drawings.

[0010] The terms used in the present application are merely for the purpose of describing specific embodiments and are not intended to limit the present application. The singular forms "a", "an" and "the" used in the present application are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein means and includes any or all possible combinations of one or more associated listed items.

[0011] The specific embodiments, features and effects according to the present application are described in detail below in combination with the drawings and preferred embodiments.

[0012] Embodiment 1

[0013] Please refer to Figs. 1-3The embodiment provides a self-adaptive wind pressure regulation system of a quartz sand non-powered powder separation device. The wind pressure data acquisition and preprocessing module acquires real-time wind pressure fluctuation data and airflow disturbance signals from the mountainous terrain environment through a sensor network arranged at multiple positions of the powder separation cavity, and obtains an initial wind pressure distribution atlas.

[0014] Further, the wind pressure data acquisition and preprocessing module comprises: The time series analysis is adopted to extract periodic change characteristics from the acquired real-time wind pressure fluctuation data, and a wind pressure dynamic mode is obtained. The time series analysis method is adopted to capture the dynamic change law of the wind pressure with time based on the real-time wind pressure fluctuation data collected by the multi-position sensor network of the powder separation cavity in the mountainous terrain environment, and the wind pressure dynamic mode that can accurately reflect the wind pressure change trend in the powder separation process is constructed by mining the periodically repeating fluctuation period, amplitude change and other periodic characteristics in the data. For the wind pressure fluctuation data collected by the sensor of the powder separation cavity in the mountainous terrain environment, the Hampel filter with strong robustness to abnormal values is used for smoothing processing. First, a sliding window adaptive to the time sequence characteristics of the wind pressure data is set, and the median of the data in the window is taken as the reference value. The absolute deviation of each data point in the window from the median is calculated, and the absolute deviation median is obtained. Then, the abnormal value judgment threshold is determined based on the deviation median. The abnormal data points exceeding the threshold in the window are replaced by the window median, and the complete wind pressure fluctuation data set is traversed window by window. Finally, the random noise and extreme interference caused by the complex airflow and terrain disturbance in the mountainous area are removed, and the smoothed wind pressure data that can accurately reflect the real change trend of the wind pressure in the powder separation cavity is obtained. The Hampel filter is an abnormal processing method for the initial collected data.

[0015] The Pearson correlation coefficient of the smoothed wind pressure data and the airflow disturbance data is calculated to determine the correlation strength of the wind pressure and the airflow disturbance. The smoothed wind pressure data and the airflow disturbance data arranged at multiple positions are fused through a spatial interpolation method to generate a high-resolution wind pressure distribution atlas. The spatial interpolation method is specifically a Kriging interpolation method for spatial fusion to generate a high-resolution wind pressure distribution map: the wind pressure and airflow disturbance data of the discrete sampling points are matched in spatial coordinates, and a sample data set containing position information (latitude / longitude / cavity coordinates) and corresponding physical quantities is established; then the spatial correlation of the sample data is analyzed by a variogram function, the distance between different sampling points and the data difference are calculated, and a theoretical variogram function model reflecting the spatial variation law of the data is fitted, such as a spherical model, an exponential model, to determine the spatial autocorrelation range and intensity parameters; then based on the model, the entire powder selection cavity is divided into grids (with a high-resolution grid unit size set), for each grid node, the weight coefficient is calculated and weighted interpolation is performed according to the spatial distance from the surrounding known sampling points and the variogram function parameters, and the spatial characteristics of the smoothed wind pressure data and airflow disturbance data are fused; finally, the interpolation parameters (such as adjusting the search radius and iteratively optimizing the weight matrix) are optimized through cross-validation to reduce edge effects and data bias, and finally a high-resolution wind pressure distribution map that can accurately depict the spatial distribution details of the wind pressure inside the cavity, with a resolution that adapts to actual regulation requirements, is generated, clearly presenting the coordinated variation characteristics of wind pressure and airflow disturbance in different regions.

[0016] The clustering analysis is used to extract the partition characteristics from the high-resolution wind pressure distribution map to determine the spatial mode of the wind pressure distribution, and the deployment position of the sensor network is optimized by the grid division method in combination with the mountain terrain data to obtain an optimized collection system configuration.

[0017] Specifically, in view of the problems of noise and extreme values of wind pressure data generated by complex airflow and terrain disturbance under mountain terrain, and the difficulty of reflecting the global distribution by discrete sampling and the unreasonable deployment of sensors, the Hampel filter is used to smooth the data, the Kriging interpolation is used to generate a high-resolution wind pressure distribution map, the clustering analysis and terrain data are used to optimize the sensor deployment, and finally high-quality data that can accurately present the spatial coordinated variation of wind pressure and airflow disturbance, and an efficient collection system configuration that adapts to the mountain environment are obtained.

[0018] The wind pressure fluctuation pattern recognition module uses a convolutional neural network algorithm to process the airflow disturbance signal according to the initial wind pressure distribution map to determine the wind pressure fluctuation pattern and the particle separation precision influence area.

[0019] Further, the wind pressure fluctuation pattern recognition module comprises: The initial wind pressure distribution map data is obtained, the wind pressure value is standardized to obtain a standardized wind pressure data matrix, a convolutional neural network algorithm is used to extract features from the standardized wind pressure data matrix, and a disturbance signal feature vector is obtained through convolution and pooling layers; Among them, the normalized wind pressure data matrix contains the global wind pressure spatial distribution information of the powder selection cavity, and the convolution neural network algorithm is used for feature extraction: different sizes of convolution kernels are applied in turn through multiple convolution layers to perform sliding window convolution operation on the data matrix, capture the local correlation characteristics of wind pressure in the spatial dimension (such as gradient change, regional disturbance intensity difference, etc.), and enhance the nonlinear feature expression through the activation function; then the convolution result is down-sampled through the pooling layer to retain the key features while reducing the data dimension and reducing redundant information interference; through the alternating processing of multiple rounds of convolution and pooling, the original wind pressure data matrix is gradually converted into a high-dimensional disturbance signal feature vector that can condense the core features of airflow disturbance (such as disturbance range, intensity distribution, spatial correlation), providing accurate feature support for subsequent pressure gradient calculation and wind pressure fluctuation pattern recognition.

[0020] According to the disturbance signal feature vector, the pressure gradient change rate is calculated, and if the pressure gradient change rate of a monitoring point exceeds the preset threshold, it is judged that there is a significant airflow disturbance at the corresponding monitoring point. The time series analysis method is used to analyze the wind pressure value of the significant airflow disturbance area in the time domain, and the time series parameters of the wind pressure fluctuation rule are obtained; Among them, the time series analysis method is used to carry out time domain analysis, which is to calculate the mean, standard deviation and range of wind pressure in different time periods through sliding window, to capture the amplitude characteristics of wind pressure fluctuation; use autocorrelation analysis to identify the repeated fluctuation period in the data (such as the periodic disturbance interval of airflow caused by mountainous terrain); combine trend decomposition (such as STL decomposition) to separate the long-term trend item, periodic item and random noise item in the wind pressure sequence, and clarify the persistence characteristics of the disturbance; finally, the time series parameters including average wind pressure value, fluctuation amplitude range, main cycle length, peak value appearance frequency and continuous disturbance time are extracted, which completely describe the fluctuation rule of the wind pressure in the time domain, and provide time domain feature basis for subsequent frequency domain transformation and particle separation precision correlation analysis.

[0021] The time series parameters are converted into frequency response data by using frequency domain transformation technology, the main fluctuation frequency range is determined according to the peak value distribution of the frequency response data, the target particle size range is obtained by looking up the pre-established particle size-frequency mapping table according to the corresponding relationship between the main fluctuation frequency range and the particle size, and if the target particle size range matches the expected separation precision requirement, the wind pressure fluctuation mode and the particle separation precision influence area are determined.

[0022] Among them, the particle size-frequency mapping table is pre-established, which has been through statistical analysis to determine the one-to-one correspondence between different quartz sand particle size intervals and wind pressure main fluctuation frequencies, covering the full particle size range from coarse powder to fine powder and the corresponding characteristic frequency threshold.

[0023] Specifically, it solves the problems of complex and difficult-to-identify wind pressure fluctuation patterns in mountainous terrain and the difficulty in locating key areas affecting particle separation accuracy. By extracting airflow disturbance features through convolutional neural networks and combining time series analysis and frequency domain transformation to correlate particle size and fluctuation frequency, it can accurately identify wind pressure fluctuation patterns and clarify areas that have a significant impact on separation accuracy, providing a basis for precise control of the powder selection process.

[0024] If the wind pressure fluctuation pattern exceeds the preset threshold, the airflow velocity field optimization module will use the natural elevation difference potential energy to adjust the airflow velocity field deviation and obtain the optimized airflow channel parameters.

[0025] Furthermore, the airflow velocity field optimization module includes: S11. Obtain real-time wind pressure sensor data, calculate the fluctuation range change sequence of wind pressure value through a sliding window, and if the fluctuation range exceeds the preset threshold point, trigger the potential energy difference calculation module to calculate the natural potential energy distribution matrix based on the height difference data of each floor of the building. The process involves first collecting real-time wind pressure sensor data from the cavity and key airflow channels of the powder classifier, and then setting a sliding window size and step size adapted to the dynamic response characteristics of the wind pressure. The continuous time-series wind pressure data is then segmented and extracted piece by piece. The fluctuation intensity is quantified by calculating the difference between the maximum and minimum wind pressure values ​​within each window, thus forming a complete sequence of wind pressure fluctuation amplitude changes. The calculation of the natural potential energy distribution matrix involves retrieving the actual height difference data of each layer of the structure where the powder classifier is located. Based on the correlation conversion logic between gravitational potential energy and airflow potential energy, a natural potential energy distribution matrix that can accurately characterize the differences in natural potential energy distribution in different areas inside the equipment is generated through spatial grid modeling and global numerical extrapolation.

[0026] S12. The potential energy distribution matrix is ​​used to drive the velocity field reconstruction algorithm to correct the deviation distribution of the current airflow velocity field. The flow distribution coefficient and pressure gradient parameters of each airflow channel section are calculated using the corrected velocity field data. Wherein, the natural potential energy distribution matrix is taken as the core driving data, which is input into the preset velocity field reconstruction algorithm. First, the deviation area (such as the area of local flow speed too fast or too slow, or the energy loss area caused by air flow vortex) which does not match the natural potential energy distribution and leads to wind pressure fluctuation is located in the velocity field by combining the geometric structure parameters of the air flow channel of the powder selecting device with the real-time monitoring data of the current air flow velocity field. Then, according to the global potential energy gradient law depicted by the potential energy distribution matrix, the velocity vector of the deviation area is dynamically adjusted through fluid dynamics numerical iterative calculation, and the deviation distribution state of the current air flow velocity field is gradually corrected, so that the velocity field and the natural potential energy distribution form a coordinated adaptation. After the velocity field reconstruction correction is completed, based on the real-time flow rate data of each air flow channel cross section, the cross section geometric size and the fluid viscosity coefficient, the flow distribution coefficient (quantifying the proportion of air flow in different channels) and the pressure gradient parameter (reflecting the pressure change rate along the air flow direction) of each air flow channel cross section are obtained through the continuity equation and Bernoulli equation derivation calculation, which provides accurate fluid mechanics basis for subsequent air flow channel parameter adjustment.

[0027] S13, adjusting the channel diameter size control instruction according to the flow distribution coefficient to obtain the opening adjustment amount value of each channel node, and using parameter group fusion processing to superimpose the opening adjustment amount and the original channel parameters to obtain a new channel geometric configuration. If the optimization degree evaluation value under the new configuration reaches the convergence condition, the final air flow channel parameter combination scheme is output, which provides optimized air flow conditions for the quartz sand powder selecting device.

[0028] Wherein, the parameter group fusion processing includes: determining the corresponding association relationship of the opening adjustment amount parameter group (including the opening angle increment / decrement of each air flow channel node and the adjustment priority) and the original channel parameter group (including the initial pipe diameter, initial opening, cross section geometric size, flow resistance coefficient and other core parameters of each channel); unify the parameter unit and data format and verify the compliance; then based on the air flow adaptation demand of the quartz sand non-powered powder selecting, using the parameter group fusion processing logic, the opening adjustment amount and the corresponding original channel parameters are superimposed node by node, that is, for each air flow channel node, the original channel opening is superimposed with the corresponding opening adjustment amount, and the original pipe diameter, cross section size and other parameters are adjusted in combination with the adaptability of the flow distribution coefficient, so as to ensure that the superimposed parameters meet the channel structure mechanics and fluid dynamics constraints; finally, a new channel geometric configuration containing the final opening of each channel node, the optimized pipe diameter and cross section size is generated, realizing the coordinated adaptation of the adjustment amount and the original parameters.

[0029] Specifically, the airflow velocity field deviation caused by wind pressure fluctuation exceeding the preset threshold in mountainous terrain is solved, and the problem of insufficient utilization of natural elevation potential and poor airflow condition adaptability in the unpowered powder selection scene is solved. By triggering potential difference calculation, driving the velocity field reconstruction with the natural potential distribution matrix, and optimizing the airflow channel parameters, the velocity field deviation is finally corrected, and the adaptive airflow channel parameter combination scheme is output, providing stable and optimized airflow conditions for quartz sand unpowered powder selection and ensuring efficient operation of the powder selection process.

[0030] The particle sedimentation behavior prediction module obtains particle sedimentation behavior prediction data from the optimized airflow channel parameters, and determines whether the separation precision reaches the target level.

[0031] Further, the particle sedimentation behavior prediction module comprises: The optimized airflow channel parameters are obtained, the airflow velocity distribution is obtained by calculating the fluid dynamics model, and the particle sedimentation behavior is obtained by using particle trajectory analysis according to the airflow velocity distribution and the particle size distribution; Wherein, the optimized airflow channel parameters (including the final opening of each channel, the optimized pipe diameter, the cross-sectional size and the flow resistance coefficient, etc. Core parameters) and the airflow medium attribute parameters (such as air density, viscosity coefficient) are input into the preset computational fluid dynamics (CFD) model together, the flow state of the airflow in the powder selection cavity and each channel is simulated through numerical discretization (such as finite volume method) and iterative solution, and three-dimensional airflow velocity distribution data (explicit flow velocity, direction and turbulence intensity at different spatial positions) covering the whole cavity and each airflow section are generated; Then, the actual particle size distribution data of the quartz sand raw material (including the particle proportion, density and other physical properties in each particle size interval) are retrieved, based on Newton's law of motion and fluid drag model, the particle trajectory analysis method is used, the airflow velocity distribution data is input as the flow field environment of particle motion, the force state and motion trajectory of particles of different particle sizes in the flow field are tracked one by one, the motion speed, direction change and residence time of particles in the cavity are recorded synchronously, and finally the particle sedimentation behavior data reflecting the sedimentation position, sedimentation rate and separation trend of quartz sand particles of different particle sizes in the optimized airflow field are summarized.

[0032] The settling rate is extracted from the particle sedimentation behavior, the separation efficiency is calculated, if the separation efficiency is greater than the preset threshold, it is determined that the separation precision reaches the target level, the determination result is output, if the separation efficiency is less than the preset threshold, the channel geometry is adjusted, and the airflow channel parameters are recalculated; The space position coordinates at different time are extracted from the motion trajectory data of each particle size quartz sand particle recorded from the particle settling behavior, the instantaneous settling rate of each particle is obtained by calculating the displacement change per unit time, and then the average settling rate and rate distribution characteristics (such as the average settling rate of coarse powder particles, the suspension-settling critical rate of fine powder particles, etc.) in the particle size interval are statistically calculated; on this basis, taking the preset target separation particle size as the basis, the effective settling area of the corresponding coarse powder and fine powder in the powder selection cavity is defined, such as the bottom coarse powder collection area and the side fine powder separation channel, the number ratio of the particles in the target particle size interval that successfully settle into the corresponding effective area is calculated, and the adaptability of the average settling rate and the equipment operation cycle, that is, whether the settling separation is completed within the set time, is combined, and the separation efficiency reflecting the classification and separation effect of the quartz sand particles according to the target particle size is comprehensively calculated.

[0033] According to the adjusted air flow channel parameters, the fluid dynamics model is re-executed to obtain a new air flow velocity distribution, and through the new air flow velocity distribution and the particle size distribution, the particle trajectory analysis is updated to obtain a new separation precision determination result.

[0034] Specifically, the problems that the particle settling behavior under the optimized air flow field in the mountain area is difficult to predict, and whether the separation precision meets the standard cannot be determined in advance are solved, by inputting the optimized air flow channel parameters into the computational fluid dynamics model to obtain the air flow velocity distribution, combining the particle size distribution to carry out trajectory analysis to obtain the settling behavior data, calculating the separation efficiency and iteratively adjusting the channel parameters when the standard is not met, the particle settling law is finally accurately predicted, the separation precision is ensured to reach the target level, and the powder selection quality is stabilized.

[0035] The particle trajectory classification and regulation module classifies the coarse and fine powder particle trajectories by using a support vector machine algorithm according to the particle settling behavior prediction data to obtain a dynamic regulation instruction sequence.

[0036] Further, the particle trajectory classification and regulation module comprises: S21, acquiring particle settling trajectory data by using a sensor to generate an original data set containing time and space coordinates, extracting particle motion speed and direction features from the original data set by a trajectory feature extraction algorithm to obtain a particle motion mode; S22, if the particle motion mode meets a preset coarse and fine powder particle classification standard, classifying the motion mode by using a support vector machine algorithm to obtain a coarse and fine powder particle classification result, and then analyzing the trajectory dynamic characteristics of the coarse and fine powder particles to generate trajectory dynamic analysis data; S23, extract the settling behavior prediction parameters from the trajectory dynamic analysis data to obtain a settling behavior prediction model, generate a dynamic regulation instruction sequence corresponding to the particle settling trajectory according to the settling behavior prediction model, obtain the regulation instruction sequence, input the regulation instruction sequence into the control system, adjust the particle settling equipment parameters in real time to obtain the optimized settling trajectory data, and ensure efficient operation of the quartz sand powder selection equipment.

[0037] The trajectory dynamic analysis data includes the real-time motion speed of the fine powder particles, the direction deflection angle, the distance deviation from the target settling area, the trajectory stability coefficient, and the like, and the key settling behavior prediction parameters are extracted, including the predicted time of the particles reaching the preset separation area, the change rate of the trajectory deviation, the coordinates of the settling path bifurcation points of particles of different particle sizes, and the like. These parameters are associated with the labeled high-quality trajectory-regulation effect samples in the historical settling data for correlation training to construct a settling behavior prediction model. The settling behavior prediction model establishes a mapping relationship between the prediction parameters and the future settling state through regression analysis, and outputs the trajectory trend of the particles in the future period and the deviation risk value. Based on the real-time prediction result of the current particle settling trajectory based on the model, in combination with the adjustable parameter range of the powder selection equipment, such as the air flow passage valve opening degree, the guide plate angle, and the like, a targeted dynamic regulation instruction sequence is generated, which includes the adjustment time, adjustment amplitude, and duration of each execution component, for example: for the prediction of the fine powder trajectory deviating from the collection area, the instruction of "opening the No. 3 valve by 15° and maintaining for 5 seconds" is output, and finally the regulation instruction sequence that can directly drive the control system is formed to realize precise intervention on the particle settling trajectory.

[0038] Specifically, the problems of difficult accurate classification of coarse and fine powder particle trajectories and easy deviation of the settling trajectory from the target, which affect the powder selection accuracy, are solved. The particle settling trajectory data is obtained by a sensor and the motion characteristics are extracted, the support vector machine algorithm is used to classify the coarse and fine powder trajectories, the dynamic regulation instruction is generated in combination with the settling behavior prediction model, the equipment parameters are adjusted in real time to optimize the settling trajectory, and the accuracy and efficient operation of the quartz sand powder selection are ensured.

[0039] The wind pressure stability and efficiency correction module drives the unpowered regulation valve through the dynamic regulation instruction sequence, obtains the real-time feedback of the wind pressure stability index, and determines the efficiency uneven correction scheme.

[0040] Further, the wind pressure stability and efficiency correction module comprises: The current opening angle of the valve and the real-time value of the wind pressure sensor are obtained, the timestamp and value change sequence of the wind pressure data are recorded by the data acquisition module, the pressure fluctuation amplitude is calculated according to the wind pressure data change sequence, and if the pressure fluctuation amplitude exceeds the preset stability threshold, it is judged that the current valve state needs to be adjusted. The Kalman filtering algorithm is used to filter the noise of the wind pressure data, and the smoothed pressure trend curve and the predicted value are obtained. The pressure trend curve is used to analyze the change rule of the wind pressure, calculate the deviation between the current time and the target pressure value, and determine the valve adjustment direction and adjustment amplitude. Among them, the real-time value of the wind pressure sensor collected during the unpowered adjustment of the valve (including the value change sequence with the corresponding time stamp), considering the random noise interference caused by complex airflow disturbance in mountainous areas and equipment operation vibration, adopts the Kalman filtering algorithm which dynamically tracks the demand by adapting to real-time feedback data, constructs the state equation and observation equation of the wind pressure time sequence change, estimates the prior prediction value of the current wind pressure based on the historical data and system model, combines the real-time collected wind pressure observation value to correct the posterior error, iteratively optimizes the filtering gain to minimize the estimation error, finally accurately removes the high-frequency noise and sudden interference in the data, and outputs the smoothed pressure trend curve which can truly reflect the smooth change trend of the wind pressure. At the same time, based on the data time sequence correlation, the subsequent short-term wind pressure value is predicted, providing high-credibility data support for subsequent analysis of wind pressure change rule, calculation of deviation between current and target pressure value.

[0041] According to the adjustment amplitude, the corresponding instruction sequence parameter is generated, which includes the valve rotation angle increment and the execution time interval. The PID control algorithm is used to process the instruction sequence parameter, and the standardized valve driving signal is output to drive the unpowered valve to adjust the position according to the calculated angle. Among them, when the PID control algorithm is used to process the instruction sequence parameter, the valve rotation angle increment contained in the instruction sequence is taken as the target value, and the current opening of the valve is taken as the feedback value to calculate the deviation (the difference between the target opening and the actual opening). Then, the proportional part (P) outputs the immediate adjustment amount according to the size of the deviation, quickly reducing the current deviation; the integral part (I) performs time accumulation operation on the deviation to eliminate the long-term existing steady-state error and avoid adjustment lag; the derivative part (D) calculates the change rate of the deviation to predict the deviation trend and output the suppression signal in advance to reduce the overshoot; the outputs of the proportional, integral and derivative parts are weighted and superimposed to obtain the total control amount; then the total control amount is converted into a standardized valve driving signal, such as a pulse width modulation signal or a current signal that adapts to the unpowered valve actuator, to ensure that the signal amplitude and frequency meet the valve mechanical action characteristics, drive the valve actuator to rotate accurately according to the calculated angle increment, and at the same time, feedback the adjusted valve opening in real time to form a closed-loop control until the actual opening of the valve is consistent with the target angle, completing the position adjustment.

[0042] The wind pressure feedback value after valve adjustment is obtained, and the efficiency improvement ratio before and after adjustment is calculated. If the efficiency improvement ratio is lower than the preset correction threshold, the adjustment parameters are recalculated and a new correction strategy is generated.

[0043] Among them, Kalman filtering is a dynamic prediction for real-time data, suitable for dynamic tracking of real-time feedback data.

[0044] Specifically, the problems of large wind pressure fluctuation, strong data noise interference, and unstable wind pressure and uneven efficiency caused by inaccurate valve regulation due to complex airflow and equipment vibration in mountainous areas are solved. Through Kalman filtering to eliminate noise, PID control to accurately drive the non-powered valve adjustment, and iterative correction of the strategy according to the efficiency improvement, the wind pressure is finally stabilized, the powder selection efficiency is improved, and the efficient operation of the equipment is ensured.

[0045] The potential utilization path optimization module optimizes the potential utilization path using the gradient descent algorithm if the efficiency uneven correction scheme shows a resource waste risk, and obtains the final powder selection process control sequence.

[0046] Further, the potential utilization path optimization module comprises: Obtain the powder selection system running state data, collect the energy consumption parameters and output ratio of each process node through the efficiency monitoring module, obtain the current system efficiency distribution matrix, if there is a node lower than the preset threshold in the efficiency distribution matrix, trigger the resource configuration abnormality detection mechanism, calculate the resource utilization rate deviation value of each node through the waste identification algorithm; Among them, based on the energy consumption parameters (such as unit time energy consumption, energy conversion loss rate) and output ratio of each process node of the powder selection system, such as target particle size particle separation amount, qualified product output efficiency, the waste identification algorithm first calls the preset benchmark resource utilization rate model, which is constructed based on historical optimal operation data, process design standards and energy efficiency benchmark value under the same working condition, and contains the theoretical optimal resource utilization rate threshold of each node; Then calculate the actual resource utilization rate of each node, which is quantified by the ratio of output ratio and energy consumption parameter, reflecting the actual output benefit of unit resource input; Then the actual resource utilization rate and the corresponding node theoretical threshold in the benchmark model are operated by difference, and the deviation result is standardized according to the node process characteristics, which is used to eliminate the dimensional difference of different node parameters, and finally the resource utilization rate deviation value of each node is obtained, wherein the greater the absolute value of the negative deviation value (actual utilization rate is lower than the theoretical threshold), the higher the resource waste risk of the node, which provides accurate waste node positioning and quantitative basis for the construction of subsequent potential analysis model.

[0047] According to the resource utilization rate deviation value, a potential analysis model is constructed, a gradient descent algorithm is used to derive the potential function, an optimal direction vector of each process parameter is obtained, a path planning strategy is updated through the optimal direction vector, a matching relationship of wind speed, rotating speed and feed amount in the powder selection process is adjusted, and a new parameter adjustment scheme is obtained; The feasibility of the parameter adjustment scheme is verified by iterative calculation. If the loss function value continues to decrease, optimization is continued. If convergence is reached, iteration is stopped and the optimal parameter combination is determined. The control sequence instruction set is generated according to the optimal parameter combination. The instructions are issued to each execution unit through the process control system to automatically regulate and control the powder selection process. The system running data after regulation is obtained, and the optimization effect is monitored through the energy consumption management module. The potential energy utilization efficiency improvement amplitude and resource saving quantitative indicators are recorded to provide data support for energy-saving operation of the quartz sand powder selection equipment.

[0048] Specifically, the resource waste risk revealed by the efficiency uneven correction scheme, and the problems of insufficient natural potential energy utilization and unreasonable process parameter ratio are solved. The resource utilization deviation value is calculated by collecting energy consumption and output data at each process node. The wind speed, rotation speed and feed amount ratio are optimized and iteratively verified based on the potential energy analysis model and gradient descent algorithm. Finally, the potential energy utilization path is optimized to reduce resource waste and improve potential energy utilization efficiency. A precise powder selection process control sequence is generated to ensure efficient and energy-saving operation of the equipment.

[0049] The system adaptability evaluation module extracts the product purity improvement index from the final powder selection process control sequence to determine whether the overall system response meets the requirements of mountain environment adaptability.

[0050] Further, the system adaptability evaluation module comprises: The sensor array is used to collect temperature, pressure and flow parameters in the powder selection control sequence in real time to obtain an environmental data set. The environmental data is time-stamped according to a preset sampling frequency to obtain an environmental parameter sequence with time stamping; The environmental parameter sequence is classified and trained by a support vector machine algorithm to establish a mountain environment condition recognition model. If the current environmental parameters exceed the preset threshold range, the environmental adaptability evaluation program is triggered to obtain the environmental adaptability evaluation result; The purity deviation quantitative data is obtained by comparing the product purity sample value detected by the spectrum analyzer with the product purity benchmark value calculated according to the environmental adaptability evaluation result. Whether the product purity meets the expected standard is determined. If the purity deviation quantitative data shows that the deviation value is too large, the powder selection process parameters are corrected by calling the control parameter optimization program; The random forest algorithm is used to associate and analyze historical control parameters and purity data to determine the optimal parameter combination scheme. The powder selection equipment operating parameters are updated according to the optimal parameter combination scheme, and updated product purity monitoring data is obtained. By continuously monitoring the product purity data trend, the stability of the purity improvement effect is determined. If the stability of the purity improvement effect meets the preset requirements, the current system response time and control accuracy data are recorded, the system response characteristic parameters are calculated by statistical analysis method, and the comprehensive adaptability evaluation index of the system in the mountain environment is obtained.

[0051] Specifically, the problem that the system adaptation after regulation is unknown, and the product purity and stability are difficult to guarantee due to the complex and changeable mountain environment is solved. By collecting environmental parameters to establish a mountain environment recognition model, combining spectral analysis to detect product purity, random forest algorithm to optimize process parameters, monitoring purity improvement stability and calculating comprehensive adaptability index, it is finally determined whether the system meets the adaptation requirements of mountain environment, ensuring that the product purity and stability meet the standards, and ensuring that the system runs adaptively and efficiently in the mountain environment.

[0052] Embodiment 2

[0053] This embodiment provides a self-adaptive air pressure regulation system for quartz sand non-powered powder separation equipment, which is adapted to the high-differential potential powder separation scene of mountain quartz sand mine. The implementation mode of dynamically adjusting the air door opening degree combined with the fuzzy PID adaptive algorithm is significantly different from the PID control of embodiment 1. The core is to adapt to the mountain wind speed fluctuation characteristics in real time through fuzzy logic, and to realize the precise dynamic regulation of the air door opening degree (0-90°): The specific content includes: The wind speed sensor and the particle settling monitoring device deployed near the air door are used to collect the instantaneous wind speed fluctuation value (including turbulence intensity) and the actual settling speed of particles of different particle sizes in real time, which are used as the input of the fuzzy controller; A fuzzy rule base is constructed to adapt to the mountain wind speed characteristics: the wind speed fluctuation amplitude (divided into three levels of micro disturbance, medium disturbance and strong disturbance) and the airflow velocity field uniformity (quantified by standard deviation, ≤0.5 m / s for uniform, 0.5-1.2 m / s for general, ≥1.2 m / s for disorder) are used as input fuzzy variables, the critical settling speed of particles is calculated according to Stokes law: v= (2r²(ρp-ρf)g) / (9μ), where r is the particle radius, ρp is the quartz sand density, ρf is the air density, g is the gravitational acceleration, and μ is the air dynamic viscosity, and the deviation (divided into five levels of large negative deviation, small negative deviation, zero deviation, small positive deviation, and large positive deviation) between the actual settling speed and the critical settling speed is used as the output fuzzy variable. Through 27 fuzzy rules such as "if the wind speed is strongly disturbed and the velocity field is turbulent, and the actual settling speed is more than 15% lower than the critical value, then increase the proportional coefficient Kp to 1.2 times and the differential coefficient Kd to 1.5 times", the Kp, Ki and Kd parameters of the PID controller are adjusted in real time. The matching degree γ is defined as (actual settling velocity mean / critical settling velocity) x (1-velocity field standard deviation / average wind speed). When γ≥0.9, it is determined that the matching is good, and no adjustment is needed. When 0.7≤γ<0.9, a fuzzy PID output damper opening degree fine tuning instruction (±5°) is output. When γ<0.7, a large step adjustment instruction (5-15°) is output, and the upper limit of the opening degree is not more than 90°, and the lower limit is not less than 0°. For example, a sudden gust of wind in the mountain area causes the wind speed to increase by 3 m / s, the velocity field standard deviation increases to 1.8 m / s, and the actual settling velocity decreases by 20% compared with the critical value. At this time, γ=0.63, the fuzzy rule triggers the parameter combination of “Kp=1.3×initial value, Kd=1.6×initial value, Ki=0.8×initial value”, which drives the damper opening degree from the current 30° to 45°, and the velocity field standard deviation decreases to 0.6 m / s within 3 seconds. The actual settling velocity increases to 92% of the critical value, and γ increases to 0.91, completing the rapid compensation of the wind speed fluctuation.

[0054] The whole process realizes online self-tuning of the PID parameters through fuzzy logic, without presetting fixed adjustment thresholds, and is more suitable for the complex characteristics of “sudden change-slow change” alternation of the wind speed in the mountain area. The response speed of the conventional PID adjustment of embodiment 1 is improved by 40%, the overshoot is reduced to less than 5%, the damper opening degree adjustment precision is controlled within ±1°, and the particle separation efficiency is stabilized at more than 92%.

[0055] The above is only a preferred embodiment of the present application, and does not limit the present application in any form. Although the present application has been disclosed as above, it is not intended to limit the present application. Any person skilled in the art can make some changes or modifications to the above disclosed technical content to obtain equivalent embodiments with equivalent changes, without departing from the technical solution of the present application. Any modification, equivalent change and modification of the above embodiments based on the technical essence of the present application are still within the scope of the technical solution of the present application.

Claims

1. An adaptive air pressure regulating system for a non-powered quartz sand powder separation device, characterized in that: The method comprises the following steps: A wind pressure data acquisition and preprocessing module acquires real-time wind pressure fluctuation data and airflow disturbance signals from the mountainous terrain environment through a sensor network deployed at multiple locations in the powder selection cavity, and obtains an initial wind pressure distribution atlas; A wind pressure fluctuation pattern recognition module processes the airflow disturbance signals using a convolutional neural network algorithm based on the initial wind pressure distribution atlas to determine the wind pressure fluctuation pattern and the particle separation precision influence area; An airflow velocity field optimization module adjusts the airflow velocity field deviation by utilizing natural elevation potential if the wind pressure fluctuation pattern exceeds a preset threshold, and obtains optimized airflow channel parameters; A particle settling behavior prediction module obtains particle settling behavior prediction data from the optimized airflow channel parameters to determine whether the separation precision has reached the target level; A particle trajectory classification and control module classifies the coarse and fine powder particle trajectories using a support vector machine algorithm based on the particle settling behavior prediction data to obtain a dynamic control instruction sequence; A wind pressure stabilization and efficiency correction module drives the unpowered regulating valve using the dynamic control instruction sequence to obtain real-time feedback of the wind pressure stabilization index and determine an efficiency uneven correction scheme; A potential utilization path optimization module optimizes the potential utilization path using a gradient descent algorithm if the efficiency uneven correction scheme shows a risk of resource waste, and obtains a final powder selection process control sequence.

2. The self-adaptive air pressure regulating system of the non-powered quartz sand powder separating device according to claim 1, characterized in that: The wind pressure data acquisition and preprocessing module comprises: Periodic variation characteristics are extracted from the collected real-time wind pressure fluctuation data using time series analysis to obtain a wind pressure dynamic pattern, and if there are abnormal values in the wind pressure dynamic pattern, the wind pressure fluctuation data is smoothed by Hampel filtering to obtain smoothed wind pressure data; The correlation strength between wind pressure and airflow disturbance is determined by calculating the Pearson correlation coefficient of the smoothed wind pressure data and the airflow disturbance data, and the smoothed wind pressure data and the airflow disturbance data deployed at multiple locations are fused by a spatial interpolation method to generate a high-resolution wind pressure distribution atlas; Cluster analysis is used to extract partition features from the high-resolution wind pressure distribution atlas to determine the spatial pattern of wind pressure distribution, and the deployment location of the sensor network is optimized by a grid division method in combination with mountainous terrain data to obtain an optimized collection system configuration.

3. The self-adaptive air pressure regulating system of the non-powered quartz sand powder separating device according to claim 1, characterized in that: The wind pressure fluctuation pattern recognition module comprises: The initial wind pressure distribution atlas data is obtained, the wind pressure values are standardized to obtain a standardized wind pressure data matrix, and a convolutional neural network algorithm is used to extract features from the standardized wind pressure data matrix to obtain a disturbance signal feature vector through convolution and pooling layers; The pressure gradient change rate is calculated based on the disturbance signal feature vector, and if the pressure gradient change rate of a certain monitoring point exceeds a preset threshold, it is determined that there is significant airflow disturbance at the corresponding monitoring point, and the time domain analysis of the wind pressure values in the significant airflow disturbance area is performed by a time series analysis method to obtain the time series parameters of the wind pressure fluctuation law; Adopting frequency domain transform technology to convert time series parameters into frequency response data, determining the main fluctuation frequency range according to the peak value distribution of the frequency response data, and obtaining the target particle size range through the corresponding relationship between the main fluctuation frequency range and the particle size and by looking up the pre-established particle size-frequency mapping table, if the target particle size range matches the expected separation precision requirement, the wind pressure fluctuation mode and the particle separation precision influence area are determined.

4. The self-adaptive air pressure regulating system of the non-powered quartz sand powder separating device according to claim 1, characterized in that: The air flow velocity field optimization module comprises: Real-time wind pressure sensor data is acquired, a fluctuation amplitude change sequence of the wind pressure value is calculated through a sliding window, if the fluctuation amplitude exceeds a preset threshold point, a potential energy difference calculation module is triggered, and a natural potential energy distribution matrix is calculated according to the height difference data of each floor of the building; A velocity field reconstruction algorithm is driven by the potential energy distribution matrix to correct the deviation distribution state in the current air flow velocity field, and the flow distribution coefficient and the pressure gradient parameter of each air flow passage cross section are calculated through the corrected velocity field data; The channel diameter size control instruction is adjusted according to the flow distribution coefficient to obtain the opening adjustment amount value of each channel node, and the opening adjustment amount and the original channel parameter are superimposed and operated through parameter group fusion processing to obtain a new channel geometric configuration, if the optimization degree evaluation value under the new configuration reaches the convergence condition, the final air flow channel parameter combination scheme is output.

5. The self-adaptive air pressure regulating system of the non-powered quartz sand powder separating device according to claim 1, characterized in that: The particle settling behavior prediction module comprises: Optimized air flow channel parameters are acquired, air flow velocity distribution is obtained through a computational fluid dynamics model, particle settling behavior is obtained through particle trajectory analysis according to the air flow velocity distribution and the particle size distribution; The settling rate is extracted from the particle settling behavior, the separation efficiency is calculated, if the separation efficiency is greater than a preset threshold value, it is judged that the separation precision reaches the target level, and the determination result is output, if the separation efficiency is less than the preset threshold value, the channel geometric structure is adjusted, and the air flow channel parameters are recalculated; According to the adjusted air flow channel parameters, the fluid dynamics model is executed again to obtain a new air flow velocity distribution, the particle trajectory analysis is updated through the new air flow velocity distribution and the particle size distribution to obtain a new separation precision determination result.

6. The self-adapting air pressure regulating system of the non-powered quartz sand powder separating device according to claim 1, characterized in that: The particle trajectory classification and regulation module comprises: Particle settling trajectory data is acquired through a sensor to generate an original data set containing time and space coordinates, particle motion speed and direction features are extracted from the original data set through a trajectory feature extraction algorithm to obtain a particle motion mode; If the particle motion mode meets the preset coarse and fine powder particle classification standard, the motion mode is classified through a support vector machine algorithm to obtain a coarse and fine powder particle classification result, and the trajectory dynamic features of the coarse and fine powder particles are analyzed to generate trajectory dynamic analysis data; Settling behavior prediction parameters are extracted from the trajectory dynamic analysis data to obtain a settling behavior prediction model, dynamic regulation instruction sequences corresponding to the particle settling trajectories are generated according to the settling behavior prediction model to obtain the regulation instruction sequences, the regulation instruction sequences are input into a control system to adjust the particle settling equipment parameters in real time to obtain optimized settling trajectory data.

7. The self-adapting air pressure regulating system of the non-powered quartz sand powder separating device according to claim 1, characterized in that: The wind pressure stability and efficiency correction module comprises: Acquire the current opening angle of the valve and the real-time value of the air pressure sensor, record the timestamp and value change sequence of the air pressure data through the data acquisition module, calculate the pressure fluctuation amplitude according to the air pressure data change sequence, and if the pressure fluctuation amplitude exceeds the preset stable threshold, determine that the current valve state needs to be adjusted; Adopt Kalman filtering algorithm to filter the noise of the air pressure data, obtain the smoothed pressure trend curve and predicted value, analyze the air pressure change rule through the pressure trend curve, calculate the deviation between the current time and the target pressure value, and determine the valve adjustment direction and adjustment amplitude; Generate corresponding instruction sequence parameters according to the adjustment amplitude, which include valve rotation angle increment and execution time interval, process the instruction sequence parameters by PID control algorithm, output standardized valve driving signal, and drive the non-powered valve to adjust the position according to the calculated angle; Acquire the feedback value of the adjusted air pressure of the valve, calculate the efficiency improvement ratio before and after adjustment, and if the efficiency improvement ratio is lower than the preset correction threshold, recalculate the adjustment parameters and generate a new correction strategy.

8. The self-adapting air pressure regulating system of the non-powered quartz sand powder separating device according to claim 1, characterized in that: The potential energy utilization path optimization module comprises: Acquire the running state data of the powder selection system, collect the energy consumption parameters and output ratio of each process node through the efficiency monitoring module, obtain the current system efficiency distribution matrix, and if there is a node lower than the preset threshold in the efficiency distribution matrix, trigger the resource configuration abnormality detection mechanism, and calculate the resource utilization deviation value of each node through the waste identification algorithm; Build a potential energy analysis model according to the resource utilization deviation value, perform derivative operation on the potential energy function by using gradient descent algorithm, obtain the optimization direction vector of each process parameter, update the path planning strategy through the optimization direction vector, adjust the matching relationship of air speed, rotating speed and feed amount in the powder selection process, and obtain a new parameter adjustment scheme; Verify the feasibility of the parameter adjustment scheme by using iterative calculation method, continue optimization if the loss function value continues to decrease, stop iteration and determine the optimal parameter combination if it converges, generate control sequence instruction set according to the optimal parameter combination, and issue the instructions to each execution unit through the process control system to automatically control the powder selection process; Acquire the system running data after control, monitor the optimization effect through the energy consumption management module, and record the potential energy utilization efficiency improvement amplitude and resource saving quantitative indicators.

9. The self-adapting air pressure regulating system of the non-powered quartz sand powder separating device according to claim 1, characterized in that: Further comprising: The system adaptability evaluation module extracts the product purity improvement index from the final powder selection process control sequence, and judges whether the overall system response meets the mountain environment adaptation requirements.

10. The self-adaptive air pressure regulating system of the non-powered quartz sand powder separating device according to claim 9, characterized in that: The system adaptability evaluation module comprises: Real-time acquisition of temperature, pressure and flow parameters in the powder selection control sequence by using sensor array, obtain environmental data set, perform time sequence labeling processing on the environmental data according to the preset sampling frequency, and obtain environmental parameter sequence with timestamp; Classify and train the environmental parameter sequence by using support vector machine algorithm, establish a mountain environment condition recognition model, and if the current environmental parameters exceed the preset threshold range, trigger the environmental adaptability evaluation program, and obtain the environmental adaptability evaluation result; According to the environmental adaptability evaluation result, a product purity benchmark value is calculated, a spectral analyzer is used to detect a current product sample purity value, comparative analysis is performed to obtain purity deviation quantitative data, whether the product purity meets an expected standard is judged, and if the purity deviation quantitative data shows that the deviation value is too large, a control parameter optimization program is called to correct the powder selection process parameters; A random forest algorithm is used to perform correlation analysis on historical control parameters and purity data, an optimal parameter combination scheme is determined, the powder selection equipment operating parameters are updated according to the optimal parameter combination scheme, and updated product purity monitoring data is obtained; By continuously monitoring the product purity data change trend, the stability of the purity improvement effect is judged, if the stability of the purity improvement effect meets a preset requirement, the current system response time and control precision data are recorded, a statistical analysis method is used to calculate system response characteristic parameters, and a comprehensive adaptability evaluation index of the system in a mountainous environment is obtained.

Images