Attitude Control System Based on Single-Rail Inspection Vehicle

Abstract

The present invention discloses an attitude control system based on a single-rail inspection vehicle, which specifically includes: a driving data acquisition module: during the turning process of the inspection vehicle, the inspection driving data of the inspection vehicle is collected through an angle sensor and a speed sensor; an attitude control module: based on the inspection driving data, adjustment data is output through a PID control algorithm to control and regulate the attitude of the inspection vehicle; a control data integration module: based on the driving data and adjustment data of the inspection vehicle, integration is performed to obtain an inspection vehicle control data set. The present invention can more comprehensively evaluate the effect of the attitude control system of the single-rail inspection vehicle, reduce the inaccurate evaluation caused by only focusing on a single factor. By integrating and analyzing the driving data and adjustment data, the attitude deviation of the inspection vehicle during cornering operation can be understood, providing strong support for the optimization and improvement of the attitude control during the cornering operation of the subsequent inspection vehicle, thereby improving the running stability and safety of the inspection vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of single-rail inspection vehicle control, and particularly to an attitude control system based on a single-rail inspection vehicle. Background Art

[0002] With the rapid development of industrial automation and intelligent technologies, the safety inspection work of rail transit is gradually transforming from manual to automated and intelligent. As an efficient inspection device, a single-rail inspection vehicle can autonomously travel on the track and complete the monitoring tasks of the track and its surrounding environment;

[0003] However, during the inspection process of the inspection vehicle, when running along the track, especially when turning, the attitude control of the inspection vehicle is particularly important. The existing attitude control systems of inspection vehicles cannot capture the attitude changes of the inspection vehicle during the turning process in the face of complex and changeable curved track environments, resulting in lag or over-adjustment of attitude, which in turn affects the driving stability and safety of the inspection vehicle. In addition, when evaluating the attitude control effect, the existing systems often focus on a single attitude deviation index, making it difficult to comprehensively and accurately reflect the actual operating state of the inspection vehicle. Summary of the Invention

[0004] The purpose of the present invention is to provide an attitude control system based on a single-rail inspection vehicle to solve at least one of the above-mentioned problems in the prior art.

[0005] The present invention provides an attitude control system based on a single-rail inspection vehicle, specifically including:

[0006] A driving data acquisition module: During the turning process of the inspection vehicle, collect the inspection driving data of the inspection vehicle through an angle sensor and a speed sensor;

[0007] An attitude control module: Based on the inspection driving data, output adjustment data through a PID control algorithm to adjust and control the attitude of the inspection vehicle;

[0008] A control data integration module: Integrate based on the driving data and adjustment data of the inspection vehicle to obtain an inspection vehicle control data set;

[0009] An attitude control effect evaluation module: Evaluate the attitude control effect based on the inspection vehicle control data set and generate an attitude control effect poor signal;

[0010] An optimization control module: Based on the attitude control effect poor signal, perform optimization adjustment through a deviation coefficient combined with a genetic algorithm.

[0011] Advantages of the present invention:

[0012] 1. The present invention improves the stability and safety of the inspection vehicle when turning on a single rail, and also ensures the accuracy of data and the reliability of subsequent analysis through high-frequency data collection and accurate timestamp recording;

[0013] 2. The present invention can more comprehensively evaluate the effect of the attitude control system of the single-rail inspection vehicle, reduce the inaccurate evaluation caused by only focusing on a single factor. By integrating and analyzing the driving data and adjustment data, it is possible to understand the attitude deviation of the inspection vehicle during cornering operation, providing strong support for the optimization and improvement of the attitude control during the cornering operation of the subsequent inspection vehicle, thereby improving the running stability and safety of the inspection vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0015] Figure 1 is a schematic structural diagram of the attitude control system of the single-rail inspection vehicle based on the present invention;

[0016] Figure 2 is a flowchart of the attitude control method of the single-rail inspection vehicle based on the present invention;

[0017] Figure 3 is a schematic structural diagram of the attitude control device of the single-rail inspection vehicle based on the present invention.

[0018] In the figure: 3. Computer device; 301. Processor; 302. Memory; 303. Computer program; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0020] Embodiment 1

[0021] Figure 2The flowchart of the attitude control method for a single-rail inspection vehicle provided by Embodiment 1 of the present invention is applicable to the situation of attitude control adjustment of the inspection vehicle during the operation on a curved track. The attitude control method for the single-rail inspection vehicle can be executed by the attitude control system of the single-rail inspection vehicle. The attitude control system of the single-rail inspection vehicle can be implemented by software and / or hardware and can be configured in the attitude control device of the single-rail inspection vehicle. Optionally, the attitude control device of the single-rail inspection vehicle can be an electronic device, such as a notebook, a desktop computer, and a smart tablet, etc. The embodiments of the present invention do not limit this.

[0022] As Figure 1 shown, the attitude control system of the single-rail inspection vehicle provided by the embodiments of the present invention specifically includes:

[0023] Travel data acquisition module: During the turning process of the inspection vehicle, collect the inspection travel data of the inspection vehicle through an angle sensor and a speed sensor;

[0024] Among them, the angle sensor includes a gyroscope and an inclination sensor; the speed sensor includes a wheel speed sensor;

[0025] In some embodiments, during the operation of the inspection vehicle on the single rail, when the inspection vehicle detects that it is about to enter a turn, send a start acquisition instruction;

[0026] Among them, the ways for the inspection vehicle to detect that it is about to enter a turn include but are not limited to: based on track map information, based on a steering instruction;

[0027] Specifically, the process of detecting based on track map information is: when the vehicle approaches a curve through the vehicle-mounted positioning system (such as GPS combined with a track odometer), immediately send a start acquisition instruction to the travel data acquisition module;

[0028] Among them, it should be noted that the inspection vehicle pre-stores track map data, including but not limited to: the position, curvature, and length of the curve;

[0029] Exemplarily, when the inspection vehicle is 12 meters away from the starting point of the curve, data collection is performed according to the precise coordinate matching of the track map;

[0030] The process of detecting based on a steering instruction is: if the inspection vehicle turns manually by the driver or based on the steering instruction of the automatic driving system, then when the steering wheel angle changes or the automatic driving system issues a steering signal, immediately send a start acquisition instruction to the travel data acquisition module;

[0031] Exemplarily, when the turning angle of the steering wheel exceeds 5 degrees, it is determined that the vehicle starts the turning operation and data collection is performed;

[0032] When the acquisition instruction is initiated, the angle sensor and the speed sensor collect data at a high frequency of 100 times per second to obtain the inspection driving data of the inspection vehicle;

[0033] Among them, the inspection driving data of the inspection vehicle includes angular velocity, body tilt angle, and vehicle speed;

[0034] The process of data acquisition includes: the gyroscope continuously measures the rotational angular velocity of the inspection vehicle in the horizontal direction, and each measurement data is attached with a timestamp, which is accurate to the microsecond level, so as to accurately restore the dynamic changes of the inspection vehicle during the turning process in the future;

[0035] Exemplarily, at a certain microsecond moment, the angular velocity measured by the gyroscope is 0.5 degrees / second, and this angular velocity is recorded together with the corresponding timestamp;

[0036] The tilt sensor works synchronously to measure the tilt angle of the vehicle body relative to the direction of gravity, and also records the timestamp. Since the tilt angle of the vehicle body may change rapidly in a short time, especially when driving on a curve, high-frequency acquisition can capture these subtle changes;

[0037] Exemplarily, at a certain moment, the vehicle body tilts 3 degrees to the left, and this tilt angle is recorded together with the corresponding timestamp;

[0038] The wheel speed sensor closely tracks the rotation of the wheels. Each pulse signal generated by the rotation of the wheels is counted. Combining the known circumference of the wheels (for example, if the wheel diameter is 0.5 meters, the circumference is calculated as 1.57 meters according to the circle circumference formula), the real-time driving speed of the inspection vehicle is calculated through the number of pulses per unit time;

[0039] Exemplarily, within 1 second, the wheel speed sensor receives 100 pulse signals. It is known that each pulse represents the wheel advancing 0.01 meters (1.57 meters ÷ 100). Then the vehicle speed at this time is 1 meter / second, and this speed is recorded together with the corresponding timestamp;

[0040] Organize the collected inspection vehicle driving data according to the data format specification;

[0041] Specifically, for the setting of the data format specification, each data record includes a sensor number, a timestamp, and a specific measured value;

[0042] The sensor number is used to distinguish the data of the gyroscope, the tilt sensor, or the wheel speed sensor;

[0043] The timestamp is used for subsequent data synchronization and analysis;

[0044] Exemplarily, a data record is "GYRO_01, 2024 - 01 - 03T10:00:00.000001, 0.5", indicating that for gyroscope No. 01, at 10:00:00.000001 microseconds on January 3, 2024, the measured angular velocity is 0.5 degrees / second;

[0045] Attitude control module: Based on the inspection driving data, through a control algorithm, it outputs adjustment data to control and adjust the attitude of the inspection vehicle;

[0046] Among them, the control algorithm includes but is not limited to: PID (Proportional-Integral-Derivative) control algorithm and fuzzy algorithm;

[0047] In a specific embodiment, when using the PID (Proportional-Integral-Derivative) control algorithm, the process of outputting adjustment data is as follows:

[0048] Set the target attitude of the inspection vehicle during the turning process on the single rail. Among them, the target attitude includes the target angular velocity, the target body inclination angle, and the target vehicle speed;

[0049] The target attitude is set by those skilled in the art based on the track design requirements, safety operation specifications, and past experience data;

[0050] Obtain the inspection driving angular velocity, body inclination angle, and vehicle speed, and mark them as the actual angular velocity, the actual body inclination angle, and the actual vehicle speed;

[0051] Calculate the deviation value between the actual angle and the target angle, and mark it as the angle deviation value. Among them, the actual angle is obtained by integrating the rotational angular velocity;

[0052] Calculate the deviation value between the actual body inclination angle and the target body inclination angle, and mark it as the body inclination angle deviation value;

[0053] Calculate the deviation value between the actual vehicle speed and the target vehicle speed, and mark it as the vehicle speed deviation value;

[0054] Exemplarily, the target angle is set to 10 degrees, and the current deflection angle obtained by integrating the gyroscope data is 12 degrees. Then the deflection angle deviation is 12 - 10 = 2 degrees. The target body inclination angle is 1 degree, and the actually measured body inclination angle is 3 degrees. At this time, the inclination angle deviation is 3 - 1 = 2 degrees. The target vehicle speed is set to 15 m / s, and the actual vehicle speed is 13 m / s. The speed deviation is 13 - 15 = -2 m / s, indicating that the actual vehicle speed is lower than the target vehicle speed;

[0055] For any one of the data of angular velocity, vehicle body inclination angle, and vehicle speed, set the proportional coefficient (P), integral time constant (TI), and derivative time constant (TD).

[0056] Among them, the proportional coefficient (P), integral time constant (TI), and derivative time constant (TD) are summarized and set by those skilled in the art according to historical experience and industry specifications.

[0057] Based on the calculated angle deviation value, vehicle body inclination angle deviation value, and vehicle speed deviation value, calculate the adjustment amounts of the proportional term, integral term, and derivative term.

[0058] Specifically, for the calculation of the proportional term adjustment amount: calculate the proportional control amount according to the proportional coefficient (P).

[0059] Exemplarily, if the deflection angle deviation is 2 degrees and the proportional coefficient is 0.5, then the proportional control amount for the deflection angle is an adjustment amount of 2×0.5 = 1 degree. Similarly, for a speed deviation of -2 m / s, if the proportional coefficient for speed control is set to 0.3, the proportional control amount for speed is -2×0.3 = -0.6 m / s, indicating the adjustment direction and magnitude of the amount to increase the vehicle speed.

[0060] For the calculation of the integral term adjustment amount: the calculation of the integral term is to accumulate the deviation values over a period of time and then multiply by the integral coefficient (1 / TI).

[0061] Exemplarily, within the past 5 seconds, the inclination angle deviations are 1 degree, 1.2 degrees, 0.8 degrees, 1.1 degrees, and 0.9 degrees in sequence. The sum of these deviation values is 5 degrees. The integral time constant (TI) is 10 seconds, and the integral coefficient is 1 / 10 = 0.1. Then the integral control amount for the inclination angle is an adjustment amount of 5×0.1 = 0.5 degrees, which is used to eliminate possible steady-state errors and make the attitude approach the target attitude more precisely.

[0062] For the calculation of the derivative term adjustment amount: determine the derivative term control amount by calculating the change rate of the deviation value.

[0063] For example, the calculation process of the change rate of the angle deviation value is: the difference between the angle deviation value at the current moment and the angle deviation value at the previous moment is divided by the sampling time interval to obtain the change rate of the angle deviation value.

[0064] Exemplarily, the deflection angle deviation at the previous moment is 1.5 degrees, the deflection angle deviation at the current moment is 2 degrees, and the sampling time interval is 0.01 seconds (since the sensor collects data at a frequency of 100 times per second). Then the deviation change rate is (2 - 1.5) ÷ 0.01 = 50 degrees / second. If the differential time constant (TD) is 2 seconds, the differential coefficient is 2, and the differential control amount of the deflection angle is an adjustment amount of 50×2 = 100 degrees / second. It is mainly used to suppress the excessive oscillation that may occur during the attitude adjustment process and make the adjustment process smoother;

[0065] For any one of the angular velocity, vehicle body inclination angle, and vehicle speed data, calculate the adjustment amounts obtained by calculating the proportional term, integral term, and differential term, and sum them to obtain the adjustment data;

[0066] The technical solution of this embodiment is as follows: The driving data acquisition module high-frequency collects the angular velocity, vehicle body inclination angle, and vehicle speed inspection driving data when the inspection vehicle turns, and uses these data to output adjustment data through the control algorithm (such as the PID algorithm) in the attitude control module to accurately control the attitude of the inspection vehicle;

[0067] Thereby improving the stability and safety of the inspection vehicle when turning on the single rail, and also ensuring the accuracy of the data and the reliability of subsequent analysis through high-frequency data acquisition and accurate timestamp recording.

[0068] Embodiment 2

[0069] Based on the above embodiment, as Figure 1 shown, the attitude control system based on the single-rail inspection vehicle provided by the embodiment of the present invention specifically includes:

[0070] Control data integration module: Based on the driving data and adjustment data of the inspection vehicle, integrate them to obtain the inspection vehicle control data set;

[0071] In some embodiments, when the inspection vehicle is running on a curve, the driving data is collected in real time, and the real-time driving data of the inspection vehicle and the target attitude at the same moment are marked as the same-time array;

[0072] Among them, the real-time driving data includes real-time angular velocity, real-time vehicle body inclination angle, and real-time vehicle speed;

[0073] After the inspection vehicle passes through the single-rail curve, integrate the same-time data at all times to obtain the inspection vehicle control data set;

[0074] Attitude control effect evaluation module: Based on the inspection vehicle control data set, evaluate the attitude control effect, and generate an attitude control effect excellent signal or generate an attitude control effect poor signal;

[0075] In some embodiments, based on the obtained inspection vehicle control data set, the difference between the real-time driving data and the target attitude in the same-time data is calculated to obtain a difference characterization value;

[0076] The calculation process of the difference characterization value is as follows: Calculate the difference between the real-time angular velocity and the target angular velocity, take the absolute value of the difference to obtain the angular velocity difference value, calculate the difference between the real-time vehicle body inclination angle and the target vehicle body inclination angle, take the absolute value of the difference to obtain the inclination angle difference value, calculate the difference between the real-time vehicle speed and the target vehicle speed, and take the absolute value of the difference to obtain the vehicle speed difference value;

[0077] Perform a weighted sum calculation on the angular velocity difference value, the inclination angle difference value, and the vehicle speed difference value to obtain a difference characterization value;

[0078] Set a difference characterization threshold, where the difference characterization threshold is set by those skilled in the art based on historical experimental data from multiple experiments;

[0079] Divide the total time of the process of the inspection vehicle running on a curve into several sub-time points. Take the sub-time points as the abscissa and the corresponding difference characterization values at the sub-time points as the ordinate to draw a difference characterization value change curve;

[0080] Mark the curve between adjacent sub-time points as a difference characterization value change sub-curve, and calculate the slope of each difference characterization value change sub-curve;

[0081] Mark the difference characterization value change sub-curve with a positive slope as an increasing sub-curve, count the number of increasing sub-curves, and calculate the ratio of the number of increasing sub-curves to the total number of difference characterization value change sub-curves to obtain the proportion of the number of increasing sub-curves;

[0082] Integrate consecutive increasing sub-curves and mark them as an increasing sub-curve group. Count the number of each increasing sub-curve group, extract the maximum value of the number of increasing sub-curve groups, and calculate the ratio of the maximum value of the number of increasing sub-curve groups to the number of increasing sub-curves to obtain the proportion of the maximum number of consecutive increasing sub-curves;

[0083] Perform a weighted sum calculation on the proportion of the number of increasing sub-curves and the proportion of the maximum number of consecutive increasing sub-curves to obtain a slope quantity characterization value;

[0084] It should be noted that the proportion of the number of increasing sub-curves reflects the proportion of the sub-time periods during which the attitude deviation of the inspection vehicle increases in the total time period during the entire curve running process. If the proportion of the number of increasing sub-curves is high, it means that during the curve running of the inspection vehicle, the attitude deviation increases in more time periods; the proportion of the maximum number of consecutive increasing sub-curves reflects the severity of the continuous increase in the attitude deviation of the inspection vehicle. If the proportion of the maximum number of consecutive increasing sub-curves is high, it means that there is a situation where the attitude deviation of the inspection vehicle continuously increases during a relatively long continuous time period;

[0085] Compare the difference characterization values corresponding to each sub - time point of the difference characterization value change curve with the difference characterization threshold respectively. If the difference characterization value is greater than the difference characterization threshold, generate a large attitude deviation signal; if the difference characterization value is less than or equal to the difference characterization threshold, generate a small attitude deviation signal.

[0086] Count the number of large attitude deviation signals generated, and calculate the ratio of the number of large attitude deviation signals to the total number of sub - time points to obtain the ratio of the number of large attitude deviations.

[0087] Calculate the difference between the difference characterization values corresponding to the large attitude deviation signals and the difference characterization threshold respectively to obtain the difference characterization deviation value. Sum up and average all the difference characterization deviation values to obtain the average difference characterization deviation. Calculate the ratio of the average difference characterization deviation to the difference characterization threshold to obtain the difference characterization over - limit ratio.

[0088] Perform a weighted sum calculation on the ratio of the number of large attitude deviations and the difference characterization over - limit ratio to obtain the over - limit characterization value of the attitude deviation.

[0089] It should be noted that the ratio of the number of large attitude deviations reflects the frequency of the occurrence of large attitude deviations during the operation of the inspection vehicle on the curve. The difference characterization over - limit ratio reflects the relative size of the average level of the deviation degree of the inspection vehicle when the attitude deviation exceeds the threshold with respect to the threshold. A higher over - limit characterization value of the attitude deviation indicates that the control effect of the attitude control system during the curve operation is poor.

[0090] Multiply the slope quantity characterization value by the over - limit characterization value of the attitude deviation to obtain the attitude effect evaluation value.

[0091] By multiplying the slope quantity characterization value by the over - limit characterization value of the attitude deviation to obtain the attitude effect evaluation value, it is possible to comprehensively consider the change trend of the attitude deviation of the inspection vehicle during curve operation and the situation where the deviation exceeds the threshold. This comprehensive consideration can more comprehensively evaluate the effect of the attitude control system and reduce the inaccuracy of the evaluation caused by only focusing on a single factor.

[0092] Set the attitude effect evaluation threshold, and compare the attitude evaluation value with the attitude effect evaluation threshold. If the attitude evaluation value is greater than the attitude effect evaluation threshold, generate a poor attitude control effect signal; if the attitude evaluation value is less than or equal to the attitude effect evaluation threshold, generate an excellent attitude control effect signal.

[0093] Among them, the attitude effect evaluation threshold is set by those skilled in the art based on historical experimental data from multiple experiments.

[0094] The technical solution of this embodiment is as follows: By integrating the driving data and adjustment data of the inspection vehicle, a control data set is obtained, and then the attitude control effect is evaluated. The evaluation process includes calculating the difference characterization value, plotting the change curve of the difference characterization value, analyzing the growth sub-curve and the large signal of the attitude deviation. Considering comprehensively the change trend of the attitude deviation of the inspection vehicle during cornering and the situation where the deviation exceeds the threshold, a signal indicating excellent or poor attitude control effect is generated;

[0095] Therefore, it is possible to more comprehensively evaluate the effect of the attitude control system of the single-rail inspection vehicle, reduce the inaccurate evaluation caused by only focusing on a single factor. By integrating and analyzing the driving data and adjustment data, the attitude deviation of the inspection vehicle during cornering can be understood, providing strong support for the subsequent optimization and improvement of the attitude control during the cornering operation of the inspection vehicle, thereby improving the running stability and safety of the inspection vehicle.

[0096] Embodiment III

[0097] Based on the above embodiments, as Figure 1 shown, the attitude control system based on the single-rail inspection vehicle provided by the embodiment of the present invention specifically includes:

[0098] Optimization control module: Based on the poor attitude control effect signal, through the deviation coefficient combined with the genetic algorithm, optimize and adjust;

[0099] The deviation ratio between the evaluation effect value and the evaluation effect threshold can intuitively reflect the gap between the current control effect of the attitude control system and the expected effect. If the deviation ratio is large, it means that the control effect is quite different from the desired effect, and it is necessary to adjust the PID parameters (i.e., the proportional coefficient P, the integral time constant TI, and the differential time constant TD) to improve the control effect;

[0100] In some embodiments, the three parameters of PID are encoded, where the parameters include: proportional coefficient, integral coefficient, and differential coefficient;

[0101] The encoding methods include but are not limited to: binary encoding or real number encoding;

[0102] Exemplarily, when using binary encoding, the encoding length is determined according to the required accuracy. Assuming that each parameter is represented by 10-bit binary, then an individual (i.e., a set of PID parameters) is composed of a 30-bit binary string;

[0103] Randomly initialize a population of a certain scale. The population scale is usually preset according to the complexity of the problem, such as set to 50 - 100 individuals. These individuals represent different combinations of PID parameters, and they are randomly generated in the initial stage;

[0104] Calculate the difference between the evaluation effect value and the evaluation effect threshold, and calculate the ratio of the difference to the evaluation effect value to obtain the deviation coefficient R;

[0105] Set the fitness function F, specifically: , the smaller the deviation coefficient R, the larger the fitness function value F;

[0106] Pair the selected parent individuals in pairs and perform crossover operations according to a certain crossover probability. The position of the crossover point is randomly determined;

[0107] Methods for selecting parent individuals include but are not limited to: roulette wheel selection method, tournament selection method;

[0108] If binary coding is used, for example, crossover occurs between the 15th and 16th bits, and the corresponding part of the genes of the two parent individuals is exchanged to generate two new offspring individuals;

[0109] Simulates the gene recombination process in biological inheritance. Through crossover operations, the genes of different excellent individuals can be combined together, and it is possible to generate a PID parameter combination with better performance;

[0110] For each gene in the offspring individuals, perform mutation according to a lower mutation probability;

[0111] If binary coding is used, mutation is to change 0 to 1 or 1 to 0;

[0112] If real number coding is used, mutation can be a random perturbation within a certain range of the gene value, such as adding a small random value that follows a normal distribution;

[0113] Mutation operations can introduce new gene characteristics, prevent the algorithm from prematurely falling into a local optimal solution, make the search space more comprehensive, and it is possible to discover a better PID parameter combination;

[0114] Replace the original population with the offspring individuals after selection, crossover, and mutation to form a new population, and continuously iterate and optimize;

[0115] Set the termination condition. When the change in the optimal fitness value of the population for several consecutive generations is less than the change extreme value, it is considered that the algorithm has converged to a better PID parameter combination at this time, and output the PID parameters corresponding to the optimal individual;

[0116] Among them, the change extreme value is set by those skilled in the art according to experience;

[0117] The technical solution of this embodiment is as follows: when it is detected that the attitude control effect is poor, first encode the PID control parameters (proportional coefficient, integral coefficient, derivative coefficient), then randomly initialize the population, and use the deviation ratio between the evaluation effect value and the evaluation effect threshold as the basis for the fitness function. Continuously iterate and optimize the population through operations such as selection, crossover, and mutation until the termination condition is met, and finally output the optimal PID parameter combination;

[0118] Therefore, when the attitude control effect is not good, the genetic algorithm can be used to optimize the PID parameters. A better PID parameter combination can effectively improve the performance of the attitude control system of the single-rail inspection vehicle, make the inspection vehicle run more stably, and reduce the safety hazards caused by attitude control problems. At the same time, the iterative optimization of the algorithm combined with the clear termination condition not only ensures the optimization effect but also avoids the waste of meaningless computing resources;

[0119] Embodiment Four

[0120] Based on the above embodiments, as Figure 2 shown, the attitude control method based on a single-rail inspection vehicle provided by the embodiments of the present invention specifically includes the following steps:

[0121] Step 1: During the turning process of the inspection vehicle, collect the inspection driving data of the inspection vehicle through an angle sensor and a speed sensor;

[0122] Among them, the angle sensor includes a gyroscope and an inclination sensor; the speed sensor includes a wheel speed sensor;

[0123] Step 2: Based on the inspection driving data, output adjustment data through a control algorithm to adjust and control the attitude of the inspection vehicle;

[0124] Among them, the control algorithm includes but is not limited to: PID (Proportional-Integral-Derivative) control algorithm and fuzzy algorithm;

[0125] Step 3: Integrate the driving data and adjustment data of the inspection vehicle to obtain an inspection vehicle control data set;

[0126] Step 4: Based on the inspection vehicle control data set, evaluate the attitude control effect, and generate an excellent attitude control effect signal or a poor attitude control effect signal;

[0127] Step 5: Based on the poor attitude control effect signal, perform optimization and adjustment through the deviation coefficient combined with the genetic algorithm.

[0128] Embodiment Five

[0129] As Figure 3As shown in the figure, an embodiment of the present invention further provides a computer device 3, including: a memory 302, a processor 301, and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, the attitude control method based on a single-rail inspection vehicle as described in any one of the above methods is implemented.

[0130] The computer device 3 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art can understand that Figure 3 merely examples of the computer device 3, which do not constitute a limitation on the computer device 3, may include more or fewer components than those shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0131] The so-called processor 301 may be a central processing unit (CPU), and the processor 301 may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0132] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In some other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 3. Further, the memory 302 may also include both the internal storage unit and the external storage device of the computer device 3. The memory 302 is used to store an operating system, application programs, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or will be output.

[0133] Embodiment Six

[0134] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it implements the attitude control method based on a single-rail inspection vehicle as described in any one of the above methods.

[0135] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above embodiment methods of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0136] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0137] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0138] In the embodiments disclosed in the present application, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0139] One point is that the couplings or direct couplings or communication connections shown or discussed among each other can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0140] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0141] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulation to get a formula that is closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0142] The above has described a detailed description of an embodiment of the present invention, but the content described is only the preferred embodiment of the present invention and cannot be considered as used to limit the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. The posture control system based on the single rail inspection vehicle is characterized by: Specifically include: Driving data acquisition module: When the inspection vehicle turns, the inspection driving data of the inspection vehicle is collected through the angle sensor and speed sensor; Posture control module: Based on the inspection driving data, the PID control algorithm is used to output adjustment data to adjust and control the posture of the inspection vehicle; Control data integration module: Based on the driving data and adjustment data of the inspection vehicle, the module integrates and obtains the inspection vehicle control data set; Posture control effect evaluation module: Based on the inspection vehicle control data set, it evaluates the posture control effect and generates a posture control effect difference signal; Obtaining a difference characterization value change sub-curve with a positive slope; The difference characterization value change sub-curve with a positive slope is marked as a growth sub-curve, the number of growth sub-curves is counted, and the ratio of the number of growth sub-curves to the total number of difference characterization value change sub-curves is calculated to obtain the ratio of the number of growth sub-curves; Integrate the continuous growth sub-curves and mark them as growth sub-curve groups. Count the number of each growth sub-curve group, extract the maximum number of the growth sub-curve group, calculate the ratio of the maximum number of the growth sub-curve group to the number of growth sub-curves, and obtain the maximum continuous growth sub-curve ratio. The weighted sum of the percentage of the number of growth sub-curves and the percentage of the number of maximum continuous growth sub-curves is calculated to obtain the slope quantity representation value; Obtain the slope quantity representation value and the attitude deviation excess representation value; The slope quantity representation value and the attitude deviation excess representation value are multiplied to obtain the attitude effect evaluation value; Setting a posture effect evaluation threshold, comparing the posture evaluation value with the posture evaluation threshold, and generating a posture control effect difference signal if the posture evaluation value is greater than the posture evaluation threshold; Optimization control module: Based on the attitude control effect difference signal, optimization adjustment is performed through the deviation coefficient combined with genetic algorithm.

2. The posture control system based on the single rail inspection vehicle according to claim 1 is characterized in that: The driving data acquisition module specifically includes: When the inspection vehicle is running on a single rail, it sends a start collection command when it detects that it is about to enter a turn; When the collection instruction is started, the angle sensor and the speed sensor collect data to obtain the inspection driving data of the inspection vehicle; Among them, the inspection driving data of the inspection vehicle includes angular velocity, vehicle body inclination angle, and vehicle speed; The collected inspection vehicle driving data is sorted according to the data format specifications.

3. The posture control system based on the single rail inspection vehicle according to claim 1 is characterized in that: The process of outputting the adjustment data is as follows: Setting the target posture of the inspection vehicle during the turning process on a single rail, wherein the target posture includes the target angular velocity, the target vehicle body inclination angle, and the target vehicle speed; Obtain the inspection driving angular velocity, vehicle body inclination angle, and vehicle speed, and mark them as actual angular velocity, actual vehicle body inclination angle, and actual vehicle speed; Calculate the deviation between the actual angle and the target angle, marked as the angle deviation value, where the actual angle is obtained by integrating the rotation angular velocity; Calculate the deviation between the actual vehicle body inclination angle and the target vehicle body inclination angle, and mark it as the vehicle body inclination angle deviation value; Calculate the deviation between the actual vehicle speed and the target vehicle speed, and mark it as the vehicle speed deviation value; For any one of the data of angular velocity, vehicle body inclination angle and vehicle speed, set the proportional coefficient (P), integral time constant (TI) and differential time constant (TD); Based on the calculated angle deviation value, body tilt deviation value and vehicle speed deviation value, and in combination with the proportional coefficient (P), the integral time constant (TI) and the differential time constant (TD), the adjustment amounts of the proportional term, the integral term and the differential term are calculated; For any one of the angular velocity, vehicle body inclination angle, and vehicle speed, the adjustment amounts calculated by the proportional term, the integral term, and the differential term are summed to obtain the adjustment data.

4. The posture control system based on the single rail inspection vehicle according to claim 1 is characterized in that: The acquisition process of the inspection vehicle control data set is as follows: When the inspection vehicle is running on a curve, real-time driving data is collected, and the real-time driving data of the inspection vehicle and the target posture at the same time are marked as a time array; Among them, the real-time driving data includes real-time angular velocity, real-time vehicle body tilt angle, and real-time vehicle speed; After the inspection vehicle passes through the single-rail curve, the simultaneous data of all moments are integrated to obtain the inspection vehicle control data set.

5. The posture control system based on the single rail inspection vehicle according to claim 1 is characterized in that: The process of obtaining the difference characterization value change sub-curve with a positive slope is as follows: Based on the acquired inspection vehicle control data set, the difference between the real-time driving data and the target posture in the same time data is calculated to obtain the difference representation value; The total time of the inspection vehicle running on the curve is divided into several sub-time points, and the sub-time points are used as the horizontal coordinates, and the difference characterization values ​​corresponding to the sub-time points are used as the vertical coordinates to draw a difference characterization value change curve; The curves between adjacent sub-time points are marked as difference characterization value change sub-curves, and the slope of each difference characterization value change sub-curve is calculated.

6. The posture control system based on the single rail inspection vehicle according to claim 5 is characterized in that: The calculation process of the difference characterization value is: The real-time angular velocity and the target angular velocity are calculated to be different, and the difference is taken as an absolute value to obtain an angular velocity difference value; the real-time vehicle body tilt angle and the target vehicle body tilt angle are calculated to be different, and the difference is taken as an absolute value to obtain a tilt angle difference value; the real-time vehicle speed and the target vehicle speed are calculated to be different, and the difference is taken as an absolute value to obtain a vehicle speed difference value; The angular velocity difference value, the inclination angle difference value and the vehicle speed difference value are weightedly summed to obtain a difference representation value.

7. The posture control system based on the single rail inspection vehicle according to claim 5 is characterized in that: The process of obtaining the attitude deviation over-limit characterization value is as follows: The difference characterization value corresponding to each sub-time point of the difference characterization value change curve is compared with the difference characterization threshold value. If the difference characterization value is greater than the difference characterization threshold value, a large posture deviation signal is generated. If the difference characterization value is less than or equal to the difference characterization threshold value, a small posture deviation signal is generated. The number of large posture deviation signals is generated by counting, and the ratio of the number of large posture deviation signals to the total number of sub-time points is calculated to obtain the proportion of large posture deviation signals; The difference characterization values ​​corresponding to the large signal of the posture deviation are respectively calculated with the difference characterization threshold to obtain the difference characterization deviation value, all the difference characterization deviation values ​​are summed and averaged to obtain the difference characterization deviation mean, and the difference characterization deviation mean is calculated with the difference characterization threshold to obtain the difference characterization overlimit ratio; The weighted sum of the proportion of large posture deviations and the difference representation excess ratio is calculated to obtain the posture deviation excess representation value.

8. The posture control system based on a single rail inspection vehicle according to claim 1 is characterized in that: The specific process of the optimization control module is as follows: Encode the three parameters of PID, where the parameters include: proportional coefficient, integral coefficient, and differential coefficient; Initialize a population of a certain size; Obtain an evaluation effect value, calculate the difference between the evaluation effect value and the evaluation effect threshold, calculate the ratio between the difference and the evaluation effect value, and obtain a deviation coefficient R; Set the fitness function F, specifically: ; The selected parent individuals are paired in pairs, and the crossover operation is performed according to the crossover probability. The position of the crossover point is randomly determined; For each gene in the offspring individuals, mutate according to the lower mutation probability; Replace the original population with offspring individuals that have undergone selection, crossover, and mutation to form a new population, and continuously iterate and optimize; Set the termination conditions and output the PID parameters corresponding to the optimal individual.

Images