An aggregate loading size identification and detection control system based on radar identification

Abstract

The present invention discloses an aggregate loading size recognition and detection control system based on radar recognition, which specifically relates to the field of construction engineering and includes a multi-source perception module, a feature extraction module, an index calculation module, a threshold judgment module, a logic decision module, and a control execution module. The present invention extracts feature parameters such as phase difference and coordinate deviation through multi-modal processing, generates four types of comprehensive indexes such as volume uniformity and overloading risk, realizes risk classification and early warning by adopting a three-level threshold system, generates control instructions by combining a state machine model and a logic gate strategy, the system is configured with an electro-hydraulic proportional valve and a redundant braking mechanism, supports multi-level responses from speed regulation to emergency braking, has the characteristics of multi-dimensional dynamic monitoring, intelligent decision-making and environmental adaptability, effectively improves the safety and automation level of bulk material loading operations, and is applicable to the continuous operation requirements of complex industrial scenarios.

Description

Technical Field

[0001] The present invention relates to the technical field of construction engineering. More specifically, the present invention relates to an aggregate loading size recognition, detection and control system based on radar recognition. Background Art

[0002] Monitoring the aggregate loading process is a core link in the field of construction engineering, which directly affects transportation safety and operation efficiency. Traditional methods mainly rely on manual visual inspection or single sensors, such as weighbridge weighing and two-dimensional vision detection, and it is difficult to meet the real-time monitoring requirements under complex working conditions. With the development of intelligent construction technology, the industry's requirements for automatic and refined control of the loading process are increasing day by day.

[0003] Traditional aggregate loading detection systems usually use a single sensor for data collection, obtain the total mass or planar image information at fixed intervals, and then calculate the loading volume based on a linear weighted algorithm. When the value exceeds the preset threshold, an audible and visual alarm device is triggered, and the static data of key nodes is recorded. The entire process relies on manually set empirical parameters, and the control instructions only include start and stop signals, lacking real-time regulation of dynamic parameters such as loading rate and material distribution.

[0004] Existing solutions are limited to single-modal data collection and linear judgment logic, and it is difficult to accurately identify three-dimensional space features such as mixed aggregate particle sizes and carriage deformation, resulting in frequent overloading misjudgments and missed detections of potential safety hazards. At the same time, the fixed threshold mechanism cannot adapt to the non-linear changing working conditions during the loading process, and it is easy to cause equipment damage due to instantaneous impact during emergency braking. In addition, sensors are easily interfered in complex environments such as dust and temperature changes, and the problem of data drift is prominent, requiring frequent manual calibration and maintenance, which seriously restricts the reliability of the system. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide an aggregate loading size recognition, detection and control system based on radar recognition, through the following solutions to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solution: An aggregate loading size recognition, detection and control system based on radar recognition, comprising:

[0007] A multi-source perception module: realizing dynamic monitoring of the loading process through heterogeneous sensor fusion technology, including millimeter-wave radar, inertial measurement unit, optical vision system and laser ranging device, and transmitting the multi-modal original data stream to the feature extraction module;

[0008] Feature extraction module: It is used to extract features from the multi-modal data stream transmitted by the multi-source perception module, including dynamic three-dimensional volume distribution detection data, aggregate particle size mixing detection data, dynamic overload risk detection data, and carriage deformation detection data, and transmit the extracted feature data to the index calculation module;

[0009] Index calculation module: It combines multi-dimensional feature parameters through a non-linear formula, calculates four core indexes of volume uniformity index, particle size mixing index, dynamic overload coefficient, and structural deformation index in real time, realizes the mapping from physical quantity to risk value by using the experimentally calibrated parameter system, and transmits the calculated indexes to the threshold judgment module;

[0010] Threshold judgment module: It adopts a three-level threshold system to independently evaluate the four core indexes, outputs the real-time safety status of each index through binary coding, and transmits the judgment result to the logic decision module;

[0011] Logic decision module: It adopts a multi-level state machine architecture, combines the threshold states of each detection index through Boolean logic gates, generates hierarchical control instructions, and transmits the control instructions to the control execution module;

[0012] Control execution module: It converts the logic decision into physical control actions and realizes the real-time regulation of the loading process through a multi-level actuator.

[0013] Technical effects and advantages of the present invention:

[0014] 1. Multi-dimensional three-dimensional monitoring and precise recognition: Through the heterogeneous sensor fusion technology, combined with millimeter-wave radar, optical vision and laser ranging devices, multi-dimensional dynamic monitoring of the aggregate loading process is realized, effectively capturing multi-dimensional features such as material distribution, particle size mixing and carriage deformation, overcoming the limitations of traditional single-point detection, and significantly improving the detection accuracy and reliability under complex working conditions;

[0015] 2. Intelligent risk warning and hierarchical control: Based on the non-linear feature fusion and multi-level threshold judgment mechanism, the system can analyze core indexes such as volume uniformity, overload risk and structural deformation in real time, generate hierarchical control instructions through the logic decision module, realize intelligent response from warning prompt to emergency braking, avoid the lag of manual intervention, and ensure the safety of the loading operation;

[0016] 3. Adaptive regulation and high-robustness design: The control execution module adopts an electro-hydraulic proportional valve and a dual-redundancy braking mechanism, combined with dynamic rate regulation and fail-safe mode, to ensure that the system can still operate stably under extreme working conditions or communication interruption. At the same time, through the self-cleaning air curtain and temperature compensation technology, the long-term stability of the sensor in harsh environments such as dust and temperature difference is enhanced, and the maintenance cost is reduced. Description of the drawings

[0017] Figure 1 This is the overall structural schematic diagram of the present invention.

[0018] Figure 2 This is the structural schematic diagram of the control and execution module of the present invention. Specific embodiments

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the 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] Reference Figure 1 Shown is an aggregate loading size recognition and detection control system based on radar recognition, including a multi-source perception module, a feature extraction module, an index calculation module, a threshold judgment module, a logic decision module, and a control execution module.

[0021] Multi-source perception module: Realize dynamic monitoring of the loading process through heterogeneous sensor fusion technology, including millimeter-wave radar, inertial measurement unit, optical vision system, and laser ranging device, and transmit the multi-modal raw data stream to the feature extraction module.

[0022] The millimeter-wave radar is installed on the rotating platform at the top of the loading arm. Through 3 groups of 77GHz radar modules with adjustable pitch angles and 2 groups of 24GHz radar modules, 3D point cloud data within a distance range of 0 - 5m on the surface of the material pile is obtained at a scanning frequency of 30Hz. The inertial measurement unit is installed on the drive motor base, specifically in an XYZ three-axis orthogonal layout, monitoring vibration acceleration signals in the 0 - 2kHz frequency band, especially capturing high-frequency impact components above 500Hz. The optical vision system is installed in a protective cover 1.5m above the feed inlet, using a binocular camera installed at a 45° inclination angle, combined with an 850nm infrared fill light, to capture the movement trajectories of particles with a particle size of 5 - 25mm in a dusty environment. The laser ranging device is installed on equidistant mounting brackets on both sides of the carriage guardrail, with an interval of 1.2m. 8 groups of laser sensors form a deformation monitoring network, and the deformation of the carriage side plate is detected by comparing the reference distance in real time. The initial calibration value is ±1mm.

[0023] All sensors in the multi-modal perception module are installed using quick-release mechanical interfaces. The radar and vision system are equipped with self-cleaning air curtain devices. The accelerometer uses double fixation of magnetic attraction and threads. The laser sensor is provided with a temperature compensation module to ensure measurement stability under working conditions of -20°C to 65°C.

[0024] Feature extraction module: used to extract features from the multi-modal data stream transmitted by the multi-source perception module, including dynamic three-dimensional volume distribution detection data, aggregate particle size mixing detection data, dynamic overloading risk detection data, and carriage deformation detection data, and transmit the extracted feature data to the index calculation module.

[0025] The dynamic three-dimensional volume distribution detection data includes the stacking standard deviation of the X / Y / Z axes, the density of surface curvature mutation points, the reflection intensity gradient entropy, and the dynamic filling rate ratio, which are respectively marked as σ x , σ y , σ z , C avg , E g , and V ratio . The aggregate particle size mixing detection data includes the difference in dual-frequency reflection intensity, the dispersion of attenuation time, the Doppler broadening coefficient, and the polarization scattering entropy, which are respectively marked as ΔR, D τ , B d , and H p . The dynamic overloading risk detection data includes the impact force frequency domain integral, the trajectory deflection acceleration, the mass flow mutation rate, and the spatial momentum vector modulus, which are respectively marked as F int , a θ , ΔM, and |P|. The carriage deformation detection data includes the multi-baseline interference phase difference, the reflection intensity coefficient of variation, the dynamic deformation propagation speed, and the asymmetry index, which are respectively marked as ΔΦ, CV R , V def , and ASI.

[0026] The stacking standard deviation of the X / Y / Z axes is collected by calculating the standard deviation of the three axial coordinates for the point cloud data in each 77GHz millimeter-wave radar scanning cycle. The density of surface curvature mutation points is calculated by constructing a surface mesh through Delaunay triangulation to calculate the Gaussian curvature of each triangular patch, and the proportion of patches with curvature > K_threshold is statistically analyzed, where K_threshold = 0.5. The reflection intensity gradient entropy is collected by dividing the scanning area into 10×10 grids and calculating the Shannon entropy of the reflection intensity values of each grid, reflecting the degree of chaos in the reflection intensity distribution of the loading surface. The larger the value, the more uneven the material or density. The calculation formula is: , p i represents the proportion of the reflection intensity of the i-th grid. The dynamic filling rate ratio is collected by calculating the instantaneous volume change through consecutive frame point clouds, indicating the degree of deviation of the instantaneous volume change rate from the historical average value. The calculation formula is: V r a t i o = V t − V t − Δ t Δ t × V ¯ [ t − 1 0 , t ] , V t represents the volume at the current moment, V t-Δt represents the volume at the previous time sequence, V ¯ [ t − 1 0 , t ] It represents the average volume of the most recent 10 frames, with Δt = 0.05 s.

[0027] The dynamic three-dimensional volume distribution detection data is analyzed through the joint analysis of multi-dimensional spatial features, breaking through the limitation of traditional volume detection that only focuses on the change in total quantity. The stacking standard deviation of the X / Y / Z axes reveals the spatial dispersion characteristics of the material distribution, the density of surface curvature mutation points captures local stacking anomalies, the reflection intensity gradient entropy quantifies the chaos degree of electromagnetic wave scattering on the loading surface, and the dynamic filling rate ratio monitors the time-domain instability of the loading process. For the first time, a three-dimensional dynamic characterization of the loading form is realized, solving the problem that traditional weighbridges and single-point laser detections cannot identify three-dimensional defects such as offloading and cavities.

[0028] The difference in dual-frequency reflection intensity is collected by calculating the difference in echo power between the two frequency bands by synchronously transmitting 24 GHz and 77 GHz chirp waves, and is used for detecting the sensitivity difference and mixing of different particle size aggregates. The calculation formula is: P 77 represents the echo power of the 77 GHz frequency band, and P 24 represents the echo power of the 24 GHz frequency band. The decay time dispersion is collected by calculating the coefficient of variation of the time series obtained by extracting the time when the echo envelope decays to -3 dB, and is used to reflect the fluctuation characteristics of the echo signal decay time. The calculation formula is: τ j represents the -3 dB decay time of the jth measurement, std represents the standard deviation operation, mean represents the mean operation. The Doppler broadening coefficient is collected by performing FFT spectrum analysis on moving particles, representing the velocity distribution range of moving particles. The larger the value, the greater the velocity difference. The calculation formula is: f high represents the -3 dB upper limit frequency of the spectrum, and f low represents the -3 dB lower limit frequency of the spectrum, and f c represents the radar carrier frequency. The polarization scattering entropy is calculated by calculating the eigenvalue entropy through the polarization scattering matrix, and is used to quantify the complexity of the scattering mechanism. A high value indicates the existence of multiple scattering types. The calculation formula is: λ u represents the normalized eigenvalue of the coherence matrix.

[0029] The detection data of aggregate particle size mixing utilizes the different scattering frequency responses of electromagnetic waves by different particle sizes through dual-frequency reflection difference. The decay time dispersion reflects the particle collision damping characteristics, the Doppler broadening coefficient captures the moving particle size distribution, and the polarization scattering entropy reveals the orientation chaos degree of non-spherical particles. A joint feature space of particle size - motion - morphology is established, breaking through the limitation that traditional screening methods can only statically detect samples at specific positions, and realizing the dynamic on-line monitoring of the full-section particle size distribution.

[0030] The impact force frequency domain integral collects the energy in the 50 - 200 Hz frequency band by performing FFT on the vibration signal collected by the accelerometer, which is used to quantify the high - frequency impact energy and reflect the risk of hard object impact. The calculation formula is: , where \(a(t)\) represents the time - domain acceleration signal, FFT represents the fast Fourier transform, \(f\) represents the frequency. The trajectory deflection acceleration is collected by calculating the second - order derivative of the tangential acceleration of the typical particle trajectory, which represents the degree of sudden change in the particle movement direction. The calculation formula is: , where \(\rho\) represents the material density, \(v\) represents the instantaneous velocity of the particle, \(t\) represents time. The mass flow mutation rate is collected by differential processing of the weighbridge data, which is used to reflect the severity of the change in the loading mass. The calculation formula is: , where \(M\) represents the mass measurement value, \(t\) 0 represents the current moment. The spatial momentum vector modulus is collected by fusing vision and radar data, which is used to comprehensively represent the total impact momentum of the moving material. The calculation formula is: , represents the instantaneous mass flow rate, \(v\) terminal represents the particle terminal velocity.

[0031] The dynamic overload risk detection data captures the infrasonic energy caused by structural resonance through the impact force frequency domain integral, quantifies the kinetic energy change rate of the material impact through the trajectory deflection acceleration, monitors the second - order discontinuity of the loading rate through the mass flow mutation rate, and constructs a comprehensive index of energy transfer through the spatial momentum vector modulus. It breaks through the traditional static weighing mode and for the first time establishes a dynamic overload warning system, solving the problem that the existing technology cannot detect dynamic risks such as impact loads and momentum overloads.

[0032] The multi - baseline interference phase difference is collected by calculating the phase standard deviation measured by the three - baseline radar array, which is used to reflect the spatial consistency of the deformation on the carriage surface. The calculation formula is: , represents the phase measurement value of the \(m\) - th antenna, represents the three - channel phase average value. The reflection intensity coefficient of variation is collected by calculating the comparison value by dividing the deformation area and the normal area, which is used to quantify the abnormality degree of the reflection characteristics in the deformation area. The calculation formula is: , where \(\sigma\) represents the standard deviation of the regional reflection intensity, \(\mu\) represents the average value of the regional reflection intensity. The dynamic deformation propagation speed is collected by performing time - domain cross - correlation analysis on the deformation time - series data, which is used to characterize the propagation dynamics of the deformation wave. The calculation formula is: , where \(\Delta x\) represents the monitoring point spacing, \(R\) 12 (\(\tau\)) represents the cross - correlation function of the signals at two monitoring points, \(\tau\) represents the time - delay parameter. The asymmetry index is collected by calculating the standardized difference in the distances of the left and right side plates, which is used to quantify the asymmetry of the left - right deformation of the carriage. The calculation formula is: , \(D\) LDenote the left - hand laser ranging value, D R Denote the right - hand laser ranging value, and 0.01 is a constant to prevent division by zero.

[0033] The deformation detection data of the carriage improves the detection accuracy of micron - level deformation through multi - baseline interference phase difference, the coefficient of variation of reflection intensity identifies the surface roughness changes caused by material yield, the dynamic propagation speed quantifies the mechanical energy transfer efficiency of the deformation wave, and the asymmetry index diagnoses the structural imbalance caused by eccentric load. It breaks through the limitation of single - point measurement of traditional strain gauges, realizes the full - chain analysis of deformation generation - propagation - consequences, and solves the problem that the prior art cannot early - warn plastic deformation.

[0034] Index calculation module: Combine multi - dimensional characteristic parameters through a non - linear formula, calculate four core indexes of volume uniformity index, particle size mixing index, dynamic overload coefficient, and structural deformation index in real - time, realize the mapping from physical quantity to risk value using an experimentally calibrated parameter system, and transmit the calculated indexes to the threshold judgment module.

[0035] The volume uniformity index calculated by the index calculation module from the dynamic three - dimensional volume distribution detection data is specifically expressed as: , where VUI represents the volume uniformity index, α represents the logarithmic scaling coefficient, β represents the anti - zero - division correction amount, γ represents the curvature non - linear gain, δ represents the entropy value suppression coefficient, and η represents the rate - sensitive factor.

[0036] The volume uniformity index adopts a non - linear combination of logarithmic compression and hyperbolic tangent function. The first term reflects the overall uniformity through the axial dispersion ratio, the second term enhances the surface anomaly recognition using the power - law relationship between curvature and reflection entropy, and the last term captures transient mutations through the non - linear mapping of the dynamic rate difference. The formula structure realizes the collaborative amplification of abnormal signals by multiple physical quantities, avoiding the sensitivity loss caused by simple weighted averaging.

[0037] The particle size mixing index calculated by the index calculation module from the aggregate particle size mixing detection data is specifically expressed as: , where PSI represents the particle size mixing index, κ represents the frequency - difference enhancement coefficient, μ represents the broadening normalization factor, ν represents the anti - zero - division correction amount, ξ represents the entropy value amplification coefficient, ρ 1 represents the Sigmoid steepness coefficient, and θ represents the frequency - difference activation threshold.

[0038] The particle size mixing index constructs a two - path fusion architecture. The first term amplifies the electromagnetic characteristics of abnormal particle sizes through the product of frequency - difference and attenuation dispersion, and the second term uses an entropy - driven Sigmoid function to realize the non - linear grading of the mixing degree. The introduction of the exponential term makes the formula have the characteristic self - enhancement property, which can automatically adapt to the detection sensitivity requirements of different material aggregates.

[0039] The index calculation module calculates the dynamic overload coefficient from the dynamic overload risk detection data, which is specifically expressed as: , where DOC represents the dynamic overload coefficient, ω represents the momentum decay coefficient, λ represents the dimension balance factor, ε represents the acceleration non-linear correction, ζ represents the logarithmic scaling coefficient, ξ 1 represents the mutation rate reference value, and ι represents the exponential sensitivity.

[0040] The dynamic overload coefficient adopts a sub-item coupling design. The former item characterizes the steady-state overload risk through the power-law combination of frequency-domain energy and momentum vector, and the latter item uses the logarithmic transformation of acceleration and the exponential amplification of mutation rate to achieve transient impact detection. The denominator balance factor in the formula eliminates the dimension difference, and the exponential parameter setting enables the physical quantities to produce a synergistic amplification effect when exceeding the limit.

[0041] The index calculation module calculates the structure deformation index from the carriage deformation detection data, which is specifically expressed as: , where SDI represents the structure deformation index, τ 1 represents the phase-sensitive coefficient, υ 1 represents the variation suppression factor, ψ represents the denominator balance constant, φ represents the asymmetric amplification index, χ represents the velocity activation steepness, ω 1 represents the propagation speed threshold.

[0042] The structure deformation index adopts a dual-channel fusion architecture. The former item enhances the early deformation recognition through the non-linear combination of phase difference and reflection variation, and the latter item evaluates the deformation expansion risk using the exponential relationship between propagation speed and asymmetric index. The Sigmoid function in the denominator realizes the soft switching of the speed threshold, enabling the formula to maintain high sensitivity during low-speed deformation and trigger a strong alarm during high-speed expansion.

[0043] The determination methods of the constant parameters such as α, β, γ, etc. in the index calculation module include experimental calibration: based on the reference test data under standard working conditions, theoretical derivation: according to the material mechanics characteristics and the physical model of the sensor, equipment parameters: matching the hardware characteristics of the used radar array and inertial unit, engineering experience: referring to the statistical laws of historical loading abnormal cases. This embodiment will not be specifically introduced.

[0044] Threshold judgment module: Adopts a three-level threshold system to independently evaluate the states of the four core indicators, outputs the real-time safety states of each indicator through binary coding, and transmits the judgment results to the logic decision module.

[0045] The three - level threshold system presets three - level thresholds of safety, warning, and alarm for each indicator. The hysteresis comparison method is used in the judgment process to prevent state oscillation: when the indicator value approaches the threshold from below, it is necessary to exceed the limit for 3 consecutive 60 - ms cycles to trigger a state switch. When it falls back from above, it immediately degrades. The state of each indicator is represented by a 2 - bit binary code, where 00 represents safety, 01 represents warning, and 11 represents alarm. A total of 8 - bit status words are generated for the four indicators. The module integrates a sliding standard - deviation verification function, which automatically freezes the status output when the indicator volatility exceeds the set value to avoid misjudgment caused by transient interference.

[0046] The three - level threshold system is expressed as [safety, warning, alarm]. The threshold intervals of VUI are divided into [<1.2, 1.2 - 1.8, ≥1.8], the threshold intervals of PSI are divided into [<0.7, 0.7 - 1.3, ≥1.3], the threshold intervals of DOC are divided into [<15, 15 - 28, ≥28], and the threshold intervals of SDI are divided into [<1.5, 1.5 - 2.8, ≥2.8].

[0047] Logic decision - making module: Adopting a multi - level state - machine architecture, it combines the threshold states of each detection indicator through Boolean logic gates to generate hierarchical control instructions and transmits the control instructions to the control execution module.

[0048] The logic decision - making module receives 4 groups of 2 - bit status encodings from the threshold judgment module and generates hierarchical control instructions through a predefined decision matrix.

[0049] The triggering conditions of the logic decision - making module include: when (VUI≥1.8∧PSI≥1.3)∨SDI≥2.8, the action to be taken is to immediately stop loading and alarm; when DOC≥28∧(VUI≥1.8∨PSI≥1.3), the action to be taken is to pause loading and start manual review; when any two indicators enter the warning interval, the actions to be taken are to reduce the loading rate and give an audible and visual prompt; when a single indicator is in warning, the actions to be taken are data recording and status indicator lighting.

[0050] The status indicator is green when the safety state is safe, yellow when the safety state is warning, and red when the safety state is alarm.

[0051] Control execution module: Transforms logical decisions into physical control actions and realizes real - time regulation of the loading process through a multi - level actuator.

[0052] Reference Figure 2, the execution channels of the control execution module include a flow control channel, an emergency braking channel, and a human-machine interaction channel. The flow control channel receives 0-10V analog signals through an electro-hydraulic proportional valve with a rated pressure of 35MPa to achieve stepless adjustment of the loading rate within the range of 0-100%, with a response time ≤ 20ms. The emergency braking channel uses a dual-redundancy relay to control the electromagnetic brake, with a holding torque ≥ 850N·m, cutting off the power and activating mechanical locking within 10ms after receiving the stop command. The human-machine interaction channel includes a 360° visible 105dB rotating alarm light and a 7-inch industrial touch screen, synchronously displaying the real-time curves of four indicators and the threshold status.

[0053] The control execution module adopts a specially designed dual-mode control mechanism, automatically switching to the safety mode when the communication is interrupted, and gradually reducing the flow rate at a frequency of 5Hz until it stops completely.

[0054] Through the heterogeneous sensor fusion technology, this invention combines millimeter-wave radar, optical vision, and laser ranging devices to achieve multi-dimensional dynamic monitoring of the aggregate loading process, effectively capturing multi-dimensional features such as material distribution, particle size mixing, and carriage deformation, overcoming the limitations of traditional single-point detection, and significantly improving the detection accuracy and reliability under complex working conditions. Based on the non-linear feature fusion and multi-level threshold judgment mechanism, the system can analyze core indicators such as volume uniformity, overloading risk, and structural deformation in real time, generate hierarchical control instructions through the logical decision-making module, and achieve intelligent responses from early warning prompts to emergency braking, avoiding the lag of manual intervention and ensuring the safety of the loading operation. The control execution module adopts an electro-hydraulic proportional valve and a dual-redundancy braking mechanism, combined with dynamic rate adjustment and a fail-safe mode, to ensure the stable operation of the system under extreme working conditions or communication interruption. At the same time, through the self-cleaning air curtain and temperature compensation technology, the long-term stability of the sensor in harsh environments such as dust and temperature difference is enhanced, and the maintenance cost is reduced.

[0055] Secondly: In the attached drawings of the disclosed embodiments of this invention, only the structures related to the disclosed embodiments are involved. For other structures, reference can be made to the usual designs. Without conflict, the same embodiment and different embodiments of this invention can be combined with each other;

[0056] Finally: The above are only the preferred embodiments of this invention and are not used to limit this invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of this invention shall be included in the protection scope of this invention.

Claims

1. A radar-based aggregate loading size recognition detection and control system, characterized in that: include: Multi-source perception module: It realizes dynamic monitoring of the loading process through heterogeneous sensor fusion technology, including millimeter wave radar, inertial measurement unit, optical vision system and laser ranging device, and transmits multi-modal raw data stream to the feature extraction module; Feature extraction module: used to extract features from the multimodal data stream transmitted by the multi-source perception module, including dynamic three-dimensional volume distribution detection data, aggregate particle size mixing detection data, dynamic overload risk detection data and car body deformation detection data, and transmit the extracted feature data to the index calculation module; Index calculation module: It combines multi-dimensional characteristic parameters through nonlinear formulas to calculate four core indicators in real time, namely, volume uniformity index, particle size mixing index, dynamic overload coefficient and structural deformation index. It uses experimentally calibrated parameter system to realize the mapping of physical quantity to risk value, and transmits the calculated indicators to the threshold judgment module. Threshold judgment module: It uses a three-level threshold system to independently evaluate the status of four core indicators, outputs the real-time safety status of each indicator through binary coding, and transmits the judgment results to the logic decision module; Logical decision module: adopts a multi-level state machine architecture, combines the threshold states of various detection indicators through Boolean logic gates, generates hierarchical control instructions, and transmits the control instructions to the control execution module; Control execution module: converts logical decisions into physical control actions and realizes real-time regulation of the loading process through multi-level actuators.

2. According to the radar-based aggregate loading size recognition detection and control system of claim 1, it is characterized by: The millimeter-wave radar is installed on the rotating platform at the top of the loading arm. Through three groups of 77GHz radar modules and two groups of 24GHz radar modules with adjustable pitch angles, the three-dimensional point cloud data within the distance range of 0-5m on the surface of the material pile is obtained at a scanning frequency of 30Hz. The inertial measurement unit is installed on the drive motor base, specifically in an XYZ three-axis orthogonal layout, to monitor the vibration acceleration signal in the 0-2kHz frequency band, especially to capture high-frequency impact components above 500Hz. The optical vision system is installed in a protective cover 1.5m above the feed port, using a binocular camera installed at a 45° inclination angle, in conjunction with an 850nm infrared fill light, to capture the motion trajectory of particles with a particle size of 5-25mm in a dusty environment. The laser ranging device is installed on the equidistant mounting brackets of the guardrails on both sides of the carriage, with an interval of 1.2m. Eight groups of laser sensors constitute a deformation monitoring network, which detects the deformation of the side panels of the carriage by real-time comparison of the reference distance, and the initial calibration value is ±1mm.

3. The aggregate loading size identification detection and control system based on radar identification according to claim 1 is characterized by: The dynamic three-dimensional volume distribution detection data includes X / Y / Z axis stacking standard deviation, surface curvature mutation point density, reflection intensity gradient entropy and dynamic filling rate ratio, which are marked as σ x , σ y , σ z , C avg 、E g and V ratio The aggregate particle size mixed detection data include dual-frequency reflection intensity difference, attenuation time dispersion, Doppler broadening coefficient and polarization scattering entropy, marked as ΔR, D τ , B d and H p The dynamic overload risk detection data include the frequency domain integral of the impact force, the trajectory deflection acceleration, the mass flow mutation rate and the space momentum vector modulus, which are marked as F int 、a θ , ΔM and |P|, the cabin deformation detection data includes multi-baseline interference phase difference, reflection intensity variation coefficient, dynamic deformation propagation speed and asymmetry index, marked as ΔΦ, CV, respectively. R 、V def and ASI.

4. The aggregate loading size identification detection and control system based on radar identification according to claim 1 is characterized by: The index calculation module calculates the volume uniformity index through dynamic three-dimensional volume distribution detection data, which is specifically expressed as: , VUI represents the volume uniformity index, α represents the logarithmic scaling factor, β represents the anti-zero division correction, γ represents the curvature nonlinear gain, δ represents the entropy suppression coefficient, and η represents the rate sensitivity factor.

5. The aggregate loading size identification detection and control system based on radar identification according to claim 1 is characterized by: The index calculation module calculates the particle size mixing index through the aggregate particle size mixing detection data, which is specifically expressed as: , PSI represents the particle size mixing index, κ represents the frequency difference enhancement coefficient, μ represents the broadening normalization factor, ν represents the anti-zero division correction, ξ represents the entropy amplification coefficient, ρ1 represents the Sigmoid steepness coefficient, and θ represents the frequency difference activation threshold.

6. The aggregate loading size identification detection and control system based on radar identification according to claim 1 is characterized by: The indicator calculation module calculates the dynamic overload coefficient through dynamic overload risk detection data, which is specifically expressed as: , DOC represents the dynamic overload coefficient, ω represents the momentum attenuation coefficient, λ represents the dimensional balance factor, ε represents the acceleration nonlinear correction, ζ represents the logarithmic scaling factor, ξ1 represents the mutation rate reference value, and ι represents the exponential sensitivity.

7. The aggregate loading size identification detection and control system based on radar identification according to claim 1 is characterized by: The index calculation module calculates the structural deformation index through the car body deformation detection data, which is specifically expressed as: , SDI represents the structural deformation index, τ1 represents the phase sensitivity coefficient, υ1 represents the variation suppression factor, ψ represents the denominator equilibrium constant, φ represents the asymmetric amplification index, χ represents the velocity activation steepness, and ω1 represents the propagation velocity threshold.

8. The aggregate loading size identification detection and control system based on radar identification according to claim 1 is characterized by: The three-level threshold system presets three-level thresholds of safety, warning and alarm for each indicator. The judgment process adopts the hysteresis comparison method to prevent state oscillation: when the indicator value approaches the threshold from the bottom, it needs to exceed the limit for 3 consecutive 60ms cycles to trigger the state switching. When it falls back from the top, it will be downgraded immediately. Each indicator state is represented by a 2-bit binary code, 00 represents safety, 01 represents warning, and 11 represents alarm. The four indicators generate a total of 8-bit status words. The module integrates a sliding standard deviation check function. When the indicator volatility exceeds the set value, the state output is automatically frozen to avoid misjudgment caused by transient interference; The three-level threshold system is expressed as [safety, warning, alarm], the threshold intervals of VUI are divided into [<1.2, 1.2-1.8, ≥1.8], the threshold intervals of PSI are divided into [<0.7, 0.7-1.3, ≥1.3], the threshold intervals of DOC are divided into [<15, 15-28, ≥28], and the threshold intervals of SDI are divided into [<1.5, 1.5-2.8, ≥2.8].

9. The aggregate loading size identification detection and control system based on radar identification according to claim 1 is characterized by: The triggering conditions of the logic decision module include: when (VUI≥1.8∧PSI≥1.3)∨SDI≥2.8, the execution action is to immediately stop loading and alarm; when DOC≥28∧(VUI≥1.8∨PSI≥1.3), the execution action is to suspend loading and start manual review; when any two indicators enter the warning interval, the execution action is to reduce the loading rate and sound and light prompts; when a single indicator is warned, the execution action is data recording and status indicator light.

10. The aggregate loading size identification detection and control system based on radar identification according to claim 1, characterized in that: The execution channel of the control execution module includes a flow control channel, an emergency braking channel and a human-machine interaction channel. The flow control channel receives a 0-10V analog signal through an electro-hydraulic proportional valve with a rated pressure of 35MPa, realizes stepless adjustment of the loading rate within the range of 0-100%, and the response time is ≤20ms. The emergency braking channel uses dual redundant relays to control the electromagnetic brake, with a holding torque of ≥850N·m. After receiving the stop command, the power is cut off and the mechanical lock is started within 10ms. The human-machine interaction channel includes a 360° visible 105dB rotating alarm light and a 7-inch industrial touch screen, which synchronously displays the real-time curves of four indicators and the threshold status.

Images