Self-adaptive control method for adjusting posture of sampler

Abstract

The invention provides a self-adaptive control method for attitude adjustment of a sampler, and relates to the technical field of sampler control, a sensing device is arranged on the sampler, the sensing device comprises a tilt angle sensor, a pressure sensor and a data channel connected with the tilt angle sensor and the pressure sensor, and the tilt angle and the pressure value are obtained in real time; the control module is connected with the trigger processing module and is used for carrying out recognition processing according to the inclination angle and the pressure value to obtain the height and density of the material pile, fitting a self-adaptive control algorithm based on test data of a sampler, and calculating according to the height and density of the material pile through the self-adaptive control algorithm to determine a posture adjustment strategy; and sending the attitude adjustment strategy to a control center for attitude adjustment control of the sampler. The technical problem that the sampling accuracy and efficiency are not high due to the fact that the posture of a sampler in the prior art depends on manual fixed parameters for adjustment is solved. The technical effects that the posture is automatically adjusted according to the actual conditions of different material piles, and the sampling accuracy and the working efficiency are improved are achieved.

Description

Technical Field

[0001] The invention relates to the technical field of sampling machine control, and in particular to an adaptive control method for adjusting the posture of a sampling machine. Background Art

[0002] In the management of material yards in industries such as grain and mining, the performance of the sampling machine is crucial as it is a key device to ensure the efficiency of material quality assessment, inventory management and subsequent processing. The height, density and other characteristics of the material pile vary due to many factors such as storage time, weather conditions, and material type. These dynamic changes require the sampling machine to be able to sense and flexibly adjust its posture in real time to ensure that the sampling position is accurate and the depth is appropriate. However, most traditional methods rely on manual experience or preset fixed parameters for posture adjustment. This method is not only inefficient, but also difficult to accurately capture the real-time status of the material pile, resulting in deviations in the sampling results, which affects the accuracy of the assessment and the efficiency of subsequent processes.

[0003] In the prior art, the posture of the sampling machine depends on manual fixed parameters for adjustment, which leads to technical problems of low sampling accuracy and efficiency. Summary of the invention

[0004] The present application provides an adaptive control method for adjusting the posture of a sampling machine, which is used to solve the technical problem in the prior art that the posture of a sampling machine depends on artificial fixed parameters for adjustment, resulting in low sampling accuracy and efficiency.

[0005] In view of the above problems, the present application provides an adaptive control method for attitude adjustment of a sampling machine, the method comprising: deploying a sensing device on the sampling machine, the sensing device comprising an inclination sensor and a pressure sensor; connecting the data channels of the inclination sensor and the pressure sensor to obtain the inclination angle and the pressure value in real time; connecting a trigger processing module to perform identification processing according to the inclination angle and the pressure value to obtain the height and density of the material pile; fitting an adaptive control algorithm based on the test data of the sampling machine, and determining the attitude adjustment strategy through the operation of the adaptive control algorithm according to the height and density of the material pile; and sending the attitude adjustment strategy to a control center to perform attitude adjustment control of the sampling machine.

[0006] In a possible implementation, the following processing is performed: real-time acquisition of adjustment control monitoring data; performing posture analysis based on the adjustment control monitoring data to determine the adjustment posture through the processing module; evaluating the adjustment posture based on the sampling results, and providing feedback on the evaluation results.

[0007] In a possible implementation, the following processing is performed: based on the evaluation result, determine whether the adjusted posture meets the sampling target; when it does not meet the target, analyze and trace the adjusted posture based on the evaluation result to obtain the posture deviation value; perform compensation analysis on the posture adjustment strategy based on the posture deviation value to determine the compensation control parameters; and send the compensation control parameters to the control center for posture adjustment control.

[0008] In a possible implementation, the following processing is performed: establishing an association mapping between the compensation control parameters and the posture adjustment strategy, and constructing a compensation sample set; performing incremental learning on the adaptive control algorithm according to the compensation sample set, and optimizing the adaptive control algorithm.

[0009] In a possible implementation, the following processing is performed: the monitoring data is adjusted and controlled according to real-time acquisition, and a time series relationship of the monitoring data is established according to the acquisition timestamp; the monitoring data is continuously acquired according to the evaluation result until the evaluation result meets the sampling target; all the monitoring data are integrated based on the time series relationship to construct the compensation sample set.

[0010] In a possible implementation, the following processing is performed: configuring a sampling machine test to cover different material pile heights and density conditions; collecting the inclination angle and pressure value through the inclination sensor and the pressure sensor; establishing a mapping relationship between the inclination angle, pressure value and the material pile height and density conditions, and fitting the recognition processing relationship; according to the recognition processing relationship, identifying and processing the inclination angle and pressure value to obtain the material pile height and density.

[0011] In a possible implementation, the following processing is performed: in a sampling machine test, the working parameters of the sampling machine rotating motor, the sampling trolley moving motor, and the sampling rod lifting motor are obtained; the characteristics of the working parameters are extracted as posture parameter characteristics; the characteristics of the material pile height and density conditions are extracted as environmental parameter characteristics; the sampling results in the test are recorded, and the characteristics of the sampling results are extracted to obtain sampling result characteristics; a mapping relationship among the posture parameter characteristics, environmental parameter characteristics, and sampling result characteristics is established, and the sampling result characteristics are used as screening conditions to select test data that meet the sampling result characteristics, and construct a test sample set, which includes environmental parameter characteristics and posture parameter characteristics; according to the test sample set, the control relationship between the parameters in the environmental parameter characteristics and the posture parameter characteristics is fitted to generate an algorithm model, and according to the output posture parameters of the algorithm model, an adaptive control strategy is set to adjust the posture parameters according to the environmental parameter characteristics, and generate the adaptive control algorithm.

[0012] In a possible implementation, the following processing is performed: obtaining the height of the vehicle floor of the sample loading vehicle; setting limit information and limit sensors according to the height of the vehicle floor; using the limit information as a constraint to constrain the adaptive control algorithm in the posture adjustment strategy operation; and activating the limit sensor for real-time monitoring when executing the posture adjustment strategy.

[0013] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0014] The method provided in the embodiment of the present application is to arrange a sensing device on the sampler, wherein the sensing device includes an inclination sensor and a pressure sensor, connect the data channels of the inclination sensor and the pressure sensor, obtain the inclination angle and the pressure value in real time, connect the trigger processing module, perform identification processing according to the inclination angle and the pressure value, obtain the height and density of the material pile, fit the adaptive control algorithm based on the test data of the sampler, calculate the height and density of the material pile through the adaptive control algorithm, determine the posture adjustment strategy, and send the posture adjustment strategy to the control center to control the posture adjustment of the sampler. The technical effect of automatically adjusting the posture according to the actual situation of different material piles and improving the sampling accuracy and work efficiency is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A schematic flow chart of the adaptive control method for adjusting the posture of a sampling machine provided in this application;

[0017] Figure 2 A schematic diagram of a flow chart for feeding back evaluation results in an adaptive control method for adjusting the posture of a sampling machine provided in the present application. DETAILED DESCRIPTION

[0018] The present application provides an adaptive control method for adjusting the attitude of a sampler, which is used to solve the technical problem that the attitude of a sampler in the prior art depends on artificial fixed parameters for adjustment, resulting in low sampling accuracy and efficiency. The method achieves the technical effect of automatically adjusting the attitude according to the actual conditions of different material piles, improving sampling accuracy and work efficiency.

[0019] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0020] like Figure 1 As shown, the present application provides an adaptive control method for adjusting the posture of a sampling machine, the method comprising:

[0021] The sensing device is arranged on the sampling machine, and the sensing device includes a tilt sensor and a pressure sensor.

[0022] Specifically, a sampler is a device specially used to extract samples from bulk materials, and is used to obtain representative samples from large-scale material piles for quality inspection and analysis. In order to improve the accuracy and efficiency of sampling, sensing devices are arranged on the sampler, and the sensing devices include inclination sensors and pressure sensors. The inclination sensor is used to detect the inclination angle of the sampler relative to the horizontal plane in real time, and the inclination angle data can reflect the slope and angle changes of the material pile. The pressure sensor is used to measure the pressure value of the sampler at different positions, and the pressure data can reveal the density and pressure distribution of the material pile. For example, the inclination sensor is arranged at the top or middle position of the sampling rod or sampling tube to detect the inclination angle of the sampling device when it is inserted into the material pile. The inclination sensor is arranged at the joint of the robotic arm or the part connected to the sampling device to monitor the angle change of the robotic arm during operation and help the control system adjust the posture. By installing the pressure sensor on the outer surface of the sampling rod or sampling tube, especially the part that contacts the material, the pressure of the sampling rod at different depths can be measured in real time. The pressure sensor can be installed at the end of the mechanical arm or near the sampling device to detect the force applied to the sampling device during operation, thereby optimizing the sampling force and depth. By deploying sensing equipment at key locations of the sampling machine, accurate tilt angle and pressure data can be obtained in real time.

[0023] The data channels of the tilt sensor and the pressure sensor are connected to obtain the tilt angle and the pressure value in real time.

[0024] Specifically, the data channel is used to connect and transmit the key data collected by the inclination sensor and the pressure sensor in real time. By connecting the inclination sensor channel, the inclination angle of the sampler relative to the horizontal plane can be continuously monitored and recorded. At the same time, by connecting the pressure sensor data channel, the pressure value can be obtained, which is used to represent the density distribution and internal pressure state of the material accumulation. In order to ensure the accuracy and real-time nature of the data, the data channel adopts a high-speed and stable communication protocol, and integrates a data verification and error correction mechanism, which effectively avoids packet loss and errors during data transmission, realizes the seamless connection and real-time transmission of the inclination sensor and pressure sensor data, and improves data accuracy and reliability.

[0025] A trigger processing module is connected to perform identification processing according to the tilt angle and pressure value to obtain the height and density of the pile.

[0026] Furthermore, identification processing is performed according to the inclination angle and pressure value to obtain the height and density of the pile, including: configuring a sampling machine test to cover different pile height and density conditions; collecting the inclination angle and pressure value through the inclination sensor and the pressure sensor; establishing a mapping relationship between the inclination angle, pressure value and the pile height and density conditions, and fitting the identification processing relationship; according to the identification processing relationship, identifying processing is performed on the inclination angle and pressure value to obtain the pile height and density.

[0027] Specifically, a trigger processing module is connected, and the trigger processing module is used to perform data recognition and processing based on the inclination angle and pressure value obtained in real time to obtain the height and density of the pile. First, the sampling machine tests are carried out. These tests cover different pile height and density conditions to ensure the comprehensiveness and representativeness of the data. In each test, the inclination angle and pressure value of the sampling machine under different pile conditions are collected in real time through the inclination sensor and pressure sensor installed on the sampling machine. The inclination angle change of the sampling device relative to the horizontal plane is collected through the inclination sensor. At the same time, the pressure sensor is used to measure the pressure value of the sampling device at different positions.

[0028] Next, the collected inclination angle and pressure value data are paired with the corresponding stockpile height and density data for analysis. Statistical methods such as regression analysis are used to find the relationship between the inclination angle, pressure value, stockpile height and density, and the inclination angle and pressure value are mapped to the stockpile height and density. The established regression model is trained and verified using test data, and the model parameters are adjusted and optimized so that it can accurately identify and predict the height and density of the stockpile. Finally, according to the recognition and processing relationship established by the processing module, the inclination angle and pressure value are identified and processed to quickly and accurately obtain the current stockpile height and density information. By triggering the processing module, the real-time data from the sensor is intelligently identified and processed according to the previously established recognition and processing relationship, which realizes the rapid analysis of the inclination angle and pressure value, and can also accurately calculate the current stockpile height and density, providing strong data support for subsequent material management and decision-making.

[0029] An adaptive control algorithm is fitted based on the test data of the sampling machine, and the posture adjustment strategy is determined by calculating the adaptive control algorithm according to the height and density of the pile.

[0030] Furthermore, the adaptive control algorithm is fitted based on the sampling machine test data, including: in the sampling machine test, obtaining the working parameters of the sampling machine rotating motor, the sampling trolley moving motor, and the sampling rod lifting motor; extracting the characteristics of the working parameters as posture parameter characteristics; extracting the characteristics of the material pile height and density conditions as environmental parameter characteristics; recording the sampling results in the test, performing feature extraction on the sampling results, and obtaining sampling result characteristics; establishing a mapping relationship among the posture parameter characteristics, environmental parameter characteristics, and sampling result characteristics, using the sampling result characteristics as screening conditions, selecting test data that meets the sampling result characteristics, and constructing a test sample set, wherein the test sample set includes environmental parameter characteristics and posture parameter characteristics; according to the test sample set, fitting the control relationship between the parameters in the environmental parameter characteristics and the posture parameter characteristics, generating an algorithm model, and setting an adaptive control strategy according to the output posture parameters of the algorithm model, which is used to adjust the posture parameters according to the environmental parameter characteristics, and generate the adaptive control algorithm.

[0031] Specifically, in the sampling machine test, sensors and data acquisition devices are used to collect the working parameters of each key motor of the sampling machine in real time. The working parameters of each key motor of the sampling machine include the working data of the sampling machine rotating motor, the sampling trolley moving motor and the sampling rod lifting motor, including but not limited to speed, current, voltage, position (or displacement), acceleration, etc. These parameters directly reflect the working state and performance of the motor. After collecting and acquiring each data, the data is preprocessed, and the preprocessing includes denoising, normalization and outlier detection processing. Then, features are extracted from the preprocessed working parameters, such as calculating the mean, standard deviation, trend change, etc., to form attitude parameter features, which reflect the attitude changes and motion characteristics of the sampling machine in different sampling operations. At the same time, the characteristics of the material pile height and density conditions are extracted as environmental parameter features. The environmental parameter features not only describe the geometric morphology of the material pile, but also reflect the differences in its physical properties, which are crucial for understanding the physical interactions in the sampling process and ensuring the accuracy of sampling. During the test, each sampling result was recorded in detail, and features were extracted from these results to obtain sampling result characteristics, which included sample quality, component distribution, particle size, etc., reflecting the sampling effect and performance of the sampling machine.

[0032] Statistical analysis methods such as regression analysis and correlation analysis are used to analyze the correlation between the posture parameter features, the environmental parameter features and the sampling result features, and a mapping relationship between the posture parameter features, the environmental parameter features and the sampling result features is established according to the correlation relationship. Then, the sampling result features are used as screening conditions, and test data that meet the sampling result features are selected to construct a test sample set, which includes the environmental parameter features and the posture parameter features.

[0033] A model that can capture nonlinear relationships is selected, such as a neural network or a support vector machine. Based on the constructed test sample set, the selected model is trained and fitted. For example, a neural network model is selected, and the environmental parameter characteristics and posture parameter characteristics in the test sample set are used to train the neural network model. Through the training process, the neural network model learns the mapping relationship between the environmental parameter characteristics and the posture parameter characteristics until the model training is completed and the algorithm model is generated. The algorithm model can output corresponding posture parameters according to the input environmental parameter characteristics. According to the output posture parameters of the algorithm model, a clear adaptive control strategy is formulated. The adaptive control strategy defines how to adjust the posture parameters of the sampling machine according to different environmental parameters to ensure the accuracy and efficiency of sampling. For example, if the model output indicates that the inclination angle of the sampling rod needs to be increased at the current stockpile height, the control strategy will include specific operating instructions. The adaptive control algorithm that implements the control strategy includes PID control, fuzzy logic control or machine learning algorithm, and the posture parameters are adjusted according to the environmental parameter characteristics. For example, when using PID control, the algorithm calculates the required control input according to the current posture deviation to minimize the deviation. Using the trained adaptive control algorithm, the optimal posture adjustment strategy is calculated according to the currently detected material pile height and density, including the specific adjustment parameters of the rotating motor, mobile motor and lifting motor. By generating an algorithm model and setting an adaptive control strategy, the posture parameters are dynamically adjusted according to the characteristics of environmental parameters, and the posture of the sampling machine is intelligently controlled to ensure the accuracy and efficiency of the sampling process.

[0034] The posture adjustment strategy is sent to the control center to perform posture adjustment control of the sampling machine.

[0035] Specifically, after determining the posture adjustment strategy, the posture adjustment strategy is transmitted to the control center of the sampler. After receiving the posture adjustment strategy, the control center will parse the control instructions, which include the angle adjustment of the rotating motor, the displacement parameters of the moving motor, and the height setting of the lifting motor. The control center then converts these instructions into actual control signals to drive the corresponding motors and mechanical components to adjust, so as to achieve precise control of the posture of the sampler, ensure that the sampler can make adaptive adjustments according to the real-time material pile height and density, and improve the accuracy and efficiency of sampling.

[0036] Furthermore, the posture adjustment strategy is sent to the control center to perform posture adjustment control of the sampling machine, and then it also includes: real-time collection of adjustment control monitoring data; through the processing module, posture analysis is performed according to the adjustment control monitoring data to determine the adjustment posture; the adjustment posture is evaluated according to the sampling result, and the evaluation result is fed back.

[0037] Specifically, in the process of the sampler executing the posture adjustment strategy, the actual operation data of the sampler is continuously obtained through the deployed sensors. The actual operation data includes the current tilt angle, pressure value, working status of each motor, etc. The processing module analyzes these real-time monitoring data to determine the current posture of the sampler and evaluate whether the expected adjustment effect is achieved. Subsequently, the adjusted posture is evaluated according to the actual sampling results to determine the accuracy and representativeness of the sampling. The evaluation results are fed back to the control center for further optimization and adjustment of the posture control strategy. This process ensures that the sampler can adaptively adjust its posture under different material pile conditions through continuous real-time monitoring and feedback, ensuring the accuracy and reliability of the sampling process.

[0038] In one embodiment, Figure 2 As shown, the adjustment posture is evaluated according to the sampling result, and the evaluation result is fed back, including: judging whether the adjustment posture meets the sampling target according to the evaluation result; when it does not meet the target, analyzing and tracing the adjustment posture based on the evaluation result to obtain the posture deviation value; performing compensation analysis on the posture adjustment strategy according to the posture deviation value to determine the compensation control parameters; and sending the compensation control parameters to the control center for posture adjustment control.

[0039] Specifically, first, the evaluation result of the adjustment posture is evaluated according to the sampling result to determine whether the current posture has reached the expected sampling target. When it is determined that the adjustment posture result has not reached the target, the analysis and tracing mechanism is automatically started to deeply analyze the posture data, accurately calculate the deviation value between the posture and the sampling target, and obtain the posture deviation value.

[0040] Next, the attitude deviation value is preliminarily analyzed to obtain the specific cause of the deviation. Then, according to the cause of the deviation, the existing attitude adjustment strategy is compensated and analyzed to determine new control parameters to correct and optimize the attitude of the sampler. Finally, these compensation control parameters are sent to the control center to implement further attitude adjustment control to ensure that the sampler can adjust its attitude more accurately in subsequent sampling and achieve the sampling target. Through loop feedback and continuous optimization, the accuracy and efficiency of sampling are improved.

[0041] Furthermore, the compensation control parameters are sent to the control center for posture adjustment control, including: establishing an association mapping between the compensation control parameters and the posture adjustment strategy, and constructing a compensation sample set; performing incremental learning on the adaptive control algorithm according to the compensation sample set, and optimizing the adaptive control algorithm.

[0042] Specifically, first, the relationship between the compensation control parameters and the attitude adjustment strategy is established. By analyzing the compensation control parameters obtained after each attitude adjustment, the regular relationship between them and the specific adjustment strategy is found, and an association mapping is established based on the relationship. Then, based on the association mapping, a compensation sample set is constructed, which contains the compensation control parameters and corresponding attitude adjustment strategies in multiple adjustment processes. After the compensation sample set is constructed, the adaptive control algorithm is incrementally learned. Incremental learning is a machine learning method that continuously optimizes the existing model by gradually adding new training data. Incremental learning uses the data in the compensation sample set to adjust and optimize the adaptive control algorithm so that it can better adapt to different material pile heights and density conditions, and improve the accuracy and efficiency of attitude adjustment. Finally, through this cyclic incremental learning and optimization process, the adaptive control algorithm can continuously improve itself, thereby showing higher flexibility and accuracy in practical applications, ensuring that the sampling machine can achieve the best sampling effect under various working conditions, and improving sampling accuracy and efficiency.

[0043] Furthermore, the construction of the compensation sample set includes: adjusting and controlling the monitoring data according to real-time acquisition, and establishing a time series relationship of the monitoring data according to the acquisition timestamp; continuously acquiring monitoring data according to the evaluation results until the evaluation results meet the sampling target, integrating all monitoring data based on the time series relationship, and constructing the compensation sample set.

[0044] Specifically, firstly, monitoring data is collected in real time during the adjustment and control process of the sampler, and the timestamp of each data point is recorded to establish the monitoring data arranged in chronological order to form a time series relationship, wherein the monitoring data includes the tilt angle, the pressure value, the working status of each motor, etc. Then, the monitoring data is continuously collected according to the evaluation of the sampling results. If the current adjustment posture fails to meet the sampling target, the data is continuously collected until the adjusted posture reaches the expected target. In this process, the data of each adjustment and compensation operation will be recorded. Finally, these monitoring data arranged in chronological order are integrated to form a complete compensation sample set, which contains all the monitoring data and their corresponding timestamps and adjustment results. By constructing the compensation sample set, rich and comprehensive training data can be provided for the incremental learning of the adaptive control algorithm. The incremental learning uses these data to continuously optimize and adjust the algorithm parameters, so that it can more accurately predict and adjust the posture, and improve the sampling effect of the sampler under various stockpile conditions.

[0045] Furthermore, the method also includes: obtaining the height of the floor of the sample loading vehicle; setting limit information and limit sensors according to the height of the floor; using the limit information as a constraint condition to constrain the adaptive control algorithm in the posture adjustment strategy operation; and when executing the posture adjustment strategy, activating the limit sensor for real-time monitoring.

[0046] Specifically, in a fully automatic sampling machine, the connection relationship of the vehicle's trunk floor height is also crucial to the sampling process, because the sampling rod needs to be inserted to a certain depth to obtain samples, and this depth needs to be adjusted according to the height of the trunk floor. If the height is not properly adjusted, representative samples may not be obtained, affecting the accuracy of the sampling results. More seriously, the trunk floor may be touched, causing damage to the sampling rod or the floor, affecting the normal operation of the equipment, and may also increase maintenance costs and downtime. Therefore, in order to ensure the accuracy of sampling and avoid equipment damage, first use a height sensor or laser rangefinder to measure the height of the floor of the sample loading vehicle in real time. The height measurement process can be performed automatically when the vehicle enters the sampling position to ensure the real-time and accuracy of the data.

[0047] Then, according to the obtained height of the car floor, the limit information of the sampling rod is calculated and set, and the limit information is used to limit the maximum insertion depth of the sampling rod to prevent it from touching the car floor. After the equipment limit information, a limit sensor is installed in the limit information to detect the insertion depth of the sampling rod. When the sampling rod reaches the preset limit position, the limit sensor will send a signal to notify the control system to stop the insertion operation, ensure that it works within a safe range, and avoid equipment damage caused by excessive insertion.

[0048] The set limit information is input into the adaptive control algorithm as a constraint condition for the posture adjustment strategy operation, so that the adaptive control algorithm considers the height of the car floor and the limit information when calculating the posture adjustment strategy, ensuring that the adjustment strategy meets the safety and sampling requirements. When executing the posture adjustment strategy, the limit sensor is activated for real-time monitoring. The limit sensor continuously monitors the insertion depth of the sampling rod to ensure that the fully automatic sampling machine can accurately and effectively sample under different car height conditions, avoiding inaccurate sampling or equipment damage caused by improper depth.

[0049] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0050] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An adaptive control method for adjusting the posture of a sampler, characterized in that: The method comprises: Arranging sensing equipment on the sampling machine, wherein the sensing equipment includes a tilt sensor and a pressure sensor; Connect the data channels of the tilt sensor and the pressure sensor to obtain the tilt angle and pressure value in real time; Connecting the trigger processing module, performing identification processing according to the tilt angle and the pressure value, and obtaining the height and density of the pile; Fitting an adaptive control algorithm based on the test data of the sampler, and determining a posture adjustment strategy through calculation of the adaptive control algorithm according to the height and density of the pile; The posture adjustment strategy is sent to the control center to perform posture adjustment control of the sampling machine.

2. The adaptive control method for adjusting the posture of a sampling machine according to claim 1, characterized in that: The posture adjustment strategy is sent to the control center to perform posture adjustment control of the sampling machine, and then the following steps are further included: Collect, adjust, control and monitor data in real time; By means of the processing module, posture analysis is performed according to the adjustment control monitoring data to determine the adjustment posture; The adjustment posture is evaluated according to the sampling result, and the evaluation result is fed back.

3. The adaptive control method for adjusting the posture of a sampling machine according to claim 2, characterized in that: The step of evaluating the adjustment posture according to the sampling result and feeding back the evaluation result includes: According to the evaluation result, determining whether the adjusted posture meets the sampling target; When it is not satisfied, analyzing and tracing the adjusted posture based on the evaluation result to obtain a posture deviation value; Perform compensation analysis on the posture adjustment strategy according to the posture deviation value to determine compensation control parameters; The compensation control parameters are sent to the control center for posture adjustment control.

4. The adaptive control method for adjusting the posture of a sampling machine according to claim 3, characterized in that: Sending the compensation control parameters to the control center for posture adjustment control includes: Establishing a correlation mapping between the compensation control parameters and the posture adjustment strategy, and constructing a compensation sample set; Incremental learning is performed on the adaptive control algorithm according to the compensation sample set to optimize the adaptive control algorithm.

5. The adaptive control method for adjusting the posture of a sampling machine according to claim 4, characterized in that: The constructing of the compensation sample set comprises: Adjust and control monitoring data based on real-time acquisition, and establish a time series relationship of monitoring data according to acquisition timestamps; The monitoring data is continuously collected according to the evaluation result until the evaluation result meets the sampling target, and all the monitoring data are integrated based on the time series relationship to construct the compensation sample set.

6. The adaptive control method for adjusting the posture of a sampling machine according to claim 1, characterized in that: According to the tilt angle and the pressure value, identification processing is performed to obtain the height and density of the pile, including: Configure the sampling machine test to cover different stockpile heights and density conditions; The tilt angle and pressure value are collected by the tilt sensor and the pressure sensor; Establishing a mapping relationship between the tilt angle, the pressure value, the material pile height and the density conditions, and fitting the identification processing relationship; According to the identification and processing relationship, the inclination angle and the pressure value are identified and processed to obtain the height and density of the pile.

7. The adaptive control method for adjusting the posture of a sampling machine according to claim 6, characterized in that: The adaptive control algorithm based on the test data of the prototyping machine includes: In the sampling machine test, the working parameters of the sampling machine rotating motor, the sampling trolley moving motor, and the sampling rod lifting motor are obtained; Extracting the features of the working parameters as posture parameter features; Extracting the characteristics of the stockpile height and density conditions as environmental parameter characteristics; Record the sampling results in the test, extract features from the sampling results, and obtain the features of the sampling results; Establishing a mapping relationship among the posture parameter features, the environmental parameter features, and the sampling result features, taking the sampling result features as screening conditions, selecting test data satisfying the sampling result features, and constructing a test sample set, wherein the test sample set includes the environmental parameter features and the posture parameter features; According to the test sample set, the control relationship between the parameters in the environmental parameter characteristics and the posture parameter characteristics is fitted to generate an algorithm model. According to the output posture parameters of the algorithm model, an adaptive control strategy is set to adjust the posture parameters according to the environmental parameter characteristics to generate the adaptive control algorithm.

8. The adaptive control method for adjusting the posture of a sampling machine according to claim 1, characterized in that: The method further comprises: Obtain the height of the bottom plate of the sample loading vehicle; According to the height of the vehicle box bottom plate, limit information is set, and a limit sensor is set; Using the limit information as a constraint condition to constrain the adaptive control algorithm in the posture adjustment strategy operation; When the posture adjustment strategy is executed, the limit sensor is activated for real-time monitoring.

Images