Engineering operation vehicle load analysis method

Abstract

The invention provides an engineering operation vehicle load analysis method which comprises the following steps: predicting the change trend of the pressure of a hydraulic cylinder according to the descending speed and the load capacity of a fork, establishing a pressure prediction model through a support vector machine algorithm, and when the predicted pressure exceeds a safety threshold value, controlling the opening degree of a cushion valve in advance to realize predictive control of the pressure; a fuzzy rule base is established by combining the loading capacity of a forklift, the descending speed of a pallet fork and the pressure of a hydraulic cylinder, fuzzy self-adaptive control over the opening degree of a cushion valve is achieved, the opening degree of the cushion valve is automatically adjusted according to different working conditions, and it is ensured that the pressure of a hydraulic system is stabilized within a safety range. Establishing a nonlinear mapping relation among the loading capacity, the descending speed of the pallet fork and the opening degree of the buffer valve, training and optimizing a neural network model, achieving intelligent control over the opening degree of the buffer valve, and automatically adjusting the opening degree of the buffer valve according to the loading capacity and the descending speed of the pallet fork which are collected in real time.

Description

Technical Field

[0001] This invention relates to the field of information technology, and in particular to a method for analyzing the load of engineering vehicles. Background Technology

[0002] When a forklift is fully loaded and the forks are lowered rapidly, the pressure in the hydraulic cylinder rises sharply due to the inertial force of the load, causing significant pressure fluctuations in the system. These pressure pulsations negatively impact the stability and reliability of the hydraulic system and may even lead to safety accidents. To mitigate this problem, a buffer valve is typically installed in the hydraulic circuit. The opening of the throttle valve core is used to regulate the return oil flow, thereby buffering the pressure pulsations. However, the opening area of ​​the buffer valve directly affects the dynamic response characteristics of the system. If the opening area is too small, the buffering effect will be insignificant, and the pressure pulsations will still be severe; if the opening area is too large, the fork descent speed will be too slow, affecting operational efficiency. Optimizing the opening area of ​​the buffer valve according to different load conditions is a technical challenge that urgently needs to be solved. Furthermore, there is a complex nonlinear relationship between load capacity and buffer pressure, influenced by various factors such as hydraulic oil temperature, pipeline resistance, and seal friction. Summary of the Invention

[0003] This invention provides a method for analyzing the load of engineering operation vehicles, mainly including:

[0004] The system obtains the load capacity of the forklift under full load, identifies the descent speed of the forks during rapid descent, calculates the pressure change curve of the hydraulic cylinder under full load conditions using the established hydraulic system mathematical model, and determines whether the pressure exceeds the preset safety threshold. If the pressure exceeds the threshold, the pressure regulation function of the hydraulic buffer valve is triggered.

[0005] A pressure sensor is used to detect the inlet and outlet pressures of the hydraulic buffer valve in real time to obtain pressure pulsation signals. The pressure pulsation signals are analyzed in the time and frequency domain to obtain the pressure pulsation amplitude at different frequencies. It is then determined whether the pressure pulsation exceeds the preset safety threshold. If the threshold is exceeded, the opening of the buffer valve is controlled to reduce the pressure pulsation.

[0006] The opening area of ​​the buffer valve is obtained. For different buffer valve opening areas, the dynamic response characteristics of the hydraulic system are analyzed by simulation. The change curves of system pressure, flow rate and valve opening are obtained, thereby optimizing the buffer valve opening control strategy and determining the target buffer valve opening area to obtain the target system dynamic response performance.

[0007] Under different load conditions, hydraulic cylinder pressure and buffer valve opening data are collected. A polynomial regression model of load and buffer valve pressure is established by fitting with the least squares method to obtain the correlation between load and target buffer pressure. Based on the correlation between load and target buffer pressure, the buffer valve pressure is adaptively adjusted.

[0008] Based on the fork descent speed and load capacity, the trend of hydraulic cylinder pressure change is predicted. A pressure prediction model is established using a support vector machine algorithm. When the predicted pressure exceeds the safety threshold, the opening of the buffer valve is controlled in advance to achieve predictive pressure control.

[0009] By combining the forklift's load capacity, fork descent speed, and hydraulic cylinder pressure, a fuzzy rule base is established to achieve fuzzy adaptive control of the buffer valve opening. The buffer valve opening is automatically adjusted according to different working conditions to ensure that the hydraulic system pressure remains stable within a safe range.

[0010] A nonlinear mapping relationship is established between load capacity, fork descent speed and buffer valve opening. A neural network model is trained and optimized to achieve intelligent control of the buffer valve opening. The buffer valve opening is automatically adjusted based on the real-time collected load capacity and fork descent speed.

[0011] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0012] This invention discloses a method for analyzing the load of engineering vehicles. By acquiring the load of a forklift under full load and the descent speed of the forks during rapid descent, a mathematical model of the hydraulic system is established. The pressure change curve of the hydraulic cylinder under full load is calculated, and it is determined whether the pressure exceeds a preset safety threshold. If the threshold is exceeded, the pressure regulation function of the hydraulic buffer valve is triggered. Simultaneously, this invention uses pressure sensors to detect the inlet and outlet pressures of the hydraulic buffer valve in real time, acquiring pressure pulsation signals. Time-frequency domain analysis is used to determine whether the pressure pulsation exceeds the safety threshold. If the threshold is exceeded, the opening of the buffer valve is controlled to reduce the pressure pulsation. Furthermore, this invention optimizes the buffer valve opening control strategy through simulation analysis and establishes a polynomial regression model of load and buffer valve pressure to achieve adaptive adjustment of the buffer valve pressure. Finally, this invention combines the forklift's load, fork descent speed, and hydraulic cylinder pressure to establish a fuzzy rule base and neural network model, achieving fuzzy adaptive control and intelligent control of the buffer valve opening. This invention effectively solves the problems of pressure shock and pressure pulsation in the forklift hydraulic system under full load, ensuring that the hydraulic system pressure remains stable within a safe range, thus improving the safety and reliability of the forklift. Attached Figure Description

[0013] Figure 1 This is a flowchart of a method for analyzing the load of an engineering work vehicle according to the present invention.

[0014] Figure 2 This is a schematic diagram of a method for analyzing the load of an engineering work vehicle according to the present invention.

[0015] Figure 3 This is another schematic diagram of the method for analyzing the load of an engineering operation vehicle according to the present invention. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0017] like Figure 1-3 The method for analyzing the load of an engineering work vehicle in this embodiment may specifically include:

[0018] S101. Obtain the load capacity of the forklift under full load, identify the descent speed of the forks when they descend rapidly, calculate the pressure change curve of the hydraulic cylinder under full load condition through the established hydraulic system mathematical model, and determine whether the pressure exceeds the preset safety threshold. If it exceeds the threshold, trigger the pressure regulation function of the hydraulic buffer valve.

[0019] Acquire measurement data from the gravity sensor and the lifting angle sensor. Based on the measurement data and the fork arm length, calculate the fork load torque value using the formula M = F × L × cosθ, where F is the gravity acting on the fork, L is the fork arm length, and θ is the fork lifting angle. Use a Kalman filter to filter out noise based on the fork load torque value. Collect fork position change data using a displacement sensor at fixed sampling time intervals. Calculate the hydraulic oil flow rate using the formula Q = v × A, where v is the fork descent speed and A is the piston area. Calculate the pipeline pressure loss value based on the hydraulic oil flow rate using Bernoulli's equation ΔP = ρv² / 2. In this context, ρ represents the hydraulic oil density. Hydraulic oil pressure data is collected via an oil pump pressure sensor, and the hydraulic cylinder pressure value is obtained using the pressure calculation formula P = F / A + ΔP. Cubic spline interpolation is used to perform curve fitting on the hydraulic cylinder pressure value to obtain a hydraulic cylinder pressure change curve. It is then determined whether the hydraulic cylinder pressure value exceeds a preset pressure threshold. If the hydraulic cylinder pressure value exceeds the preset pressure threshold, the hydraulic buffer valve is triggered. A proportional-integral controller outputs a control signal according to the control formula u = Kp × e + Ki × ∫edt, where e is the deviation between the actual pressure and the threshold, Kp is the proportional coefficient, and Ki is the integral coefficient. The opening of the buffer valve is adjusted according to the control signal.

[0020] Specifically, load data and lifting angle data of the forks are obtained through gravity sensors and lifting height sensors. The load torque M = F × L × cosθ is calculated, where F is the gravity on the forks, L is the fork arm length, and θ is the fork lifting angle. A Kalman filter is used to filter out noise from the sensor data to obtain the corrected load torque value. Displacement sensors collect fork position change data at fixed 10ms sampling intervals to calculate the fork descent speed v. The hydraulic oil flow rate Q = v × A is calculated based on the piston area A. The pipeline pressure loss is calculated according to Bernoulli's equation ΔP = ρv² / 2, where ρ is the hydraulic oil density. Hydraulic oil pressure data is collected from the oil pump pressure sensor. The hydraulic cylinder pressure is calculated according to P = F / A + ΔP, where P is the hydraulic cylinder pressure, F is the load force, A is the piston area, and ΔP is the pipeline pressure loss. Interpolation points are selected at 50ms intervals, and cubic spline interpolation is used to calculate the hydraulic cylinder pressure change curve. If the hydraulic cylinder pressure exceeds the preset pressure threshold, the hydraulic buffer valve is triggered. A proportional-integral controller outputs u = Kp × e + Ki × ∫edt to control the buffer valve opening, where e is the deviation between the actual pressure and the threshold, Kp is the proportional coefficient, and Ki is the integral coefficient. The buffer chamber pressure is obtained from the feedback data of the hydraulic buffer valve, and the buffer valve opening is dynamically adjusted based on the pressure difference between the buffer pressure and the main pressure. A forklift load sensor with strain gauges installed at the fork root collects strain signals, and an angle sensor collects the forklift lifting angle signal. The fork length is fixed at 1200mm. The fork is calibrated to zero position under no-load conditions. With a load of 1000kg, the strain signal is 2000με, and the lifting angle is within the range of 0-60 degrees. The Kalman filter is set with a process noise covariance of 0.01 and a measurement noise covariance of 0.1. The steady-state load torque value is obtained through iterative calculation. The displacement sensor acquires fork position data within a 10ms sampling period. The fork descent speed is in the range of 0-300mm / s, the piston diameter is 80mm, and the piston area is 5026mm². 2 The calculated hydraulic oil flow rate is 0-90 L / min, and the hydraulic oil density is 0.9 g / cm³. 3 The pipeline pressure loss was obtained using Bernoulli's equation. The oil pump pressure sensor has a range of 0-35MPa and a sampling frequency of 100Hz. When the forks are fully loaded with 1000kg, the corresponding hydraulic cylinder pressure is 16MPa. Considering the pipeline pressure drop, the actual working pressure is 18MPa. Pressure data points are selected at 50ms intervals, and cubic spline interpolation is used to fit the pressure curve. The hydraulic buffer valve has a preset pressure threshold of 20MPa. The proportional coefficient Kp of the proportional-integral controller is set to 0.8, and the integral coefficient Ki is set to 0.05. The buffer valve opening range is 0-100%. When the pressure difference between the buffer chamber pressure and the main line pressure is 2MPa, the buffer valve opening is adjusted to 50% to achieve dynamic pressure balance.

[0021] S102. A pressure sensor is used to detect the inlet and outlet pressures of the hydraulic buffer valve in real time, obtain the pressure pulsation signal, perform time-frequency domain analysis on the pressure pulsation signal to obtain the pressure pulsation amplitude at different frequencies, and determine whether the pressure pulsation exceeds the preset safety threshold. If it exceeds the threshold, the opening of the buffer valve is controlled to reduce the pressure pulsation.

[0022] Pressure sensors are used to collect pressure signals at the inlet and outlet of the hydraulic buffer valve. These pressure signals are then sampled and quantized using a data acquisition card to obtain a pressure pulsation sampling data sequence. Based on this sequence, a bandpass filter is used to remove power frequency interference and high-frequency noise, and wavelet decomposition is applied to obtain a filtered pressure signal. A fast Fourier transform is performed on the filtered pressure signal to obtain the pressure pulsation amplitude spectrum within a specific frequency range. Frequency components with amplitudes greater than twice the mean are extracted from this spectrum as the dominant frequency component. A linear mapping relationship for the valve opening adjustment is calculated based on this dominant frequency component. If the amplitude of the dominant frequency component exceeds a preset safety threshold, the optimal opening value is calculated using a recursive least squares method, and the valve opening is adjusted accordingly to compensate for the adjustment rate.

[0023] Specifically, pressure signals at the inlet and outlet of the hydraulic buffer valve are acquired using a pressure sensor with a range of 0-40 MPa and an accuracy of 0.1%. A 16-bit high-precision data acquisition card is used to sample and quantize the pressure pulsation signal, with a sampling frequency set to 1000 Hz and a minimum resolution of 0.6 kPa, to obtain a pressure pulsation sampling data sequence. A Butterworth bandpass filter with a passband of 10-200 Hz and a stopband attenuation of 40 dB is used to remove power frequency interference and high-frequency noise from the acquired pressure pulsation data sequence, obtaining the filtered pressure signal. A 4-level decomposition of the signal is performed using a db4 wavelet, and the root mean square value and peak-to-peak value of the pressure pulsation signal are calculated to assess the signal processing quality. A 2048-point Fast Fourier Transform is performed on the filtered pressure pulsation signal to obtain the pressure pulsation amplitude spectrum at different frequencies within the 0-500 Hz range. Frequency components with amplitudes greater than twice the mean are extracted from the amplitude spectrum as the dominant frequency components, and the linear mapping relationship between the amplitude corresponding to the dominant frequency component and the opening adjustment amount is calculated. If the amplitude of the main frequency component exceeds the preset safety threshold, the optimal opening value is calculated using the recursive least squares method with a forgetting factor of 0.95. The pressure change before and after the opening adjustment is obtained from the feedback data. The opening of the buffer valve is proportionally compensated according to the opening adjustment rate limit of 10% / s, and the compensation coefficient is proportional to the pressure amplitude. The pressure sensor collects hydraulic signals at the inlet and outlet of the buffer valve. When the steady-state inlet pressure is 20MPa, the outlet pressure is 18MPa, the peak-to-peak pressure pulsation is 2MPa, the data acquisition card has a sampling resolution of 0.6kPa, and 5000 data points are obtained by continuously collecting data for 5 seconds at a sampling frequency of 1000Hz. The original signal is filtered by a Butterworth bandpass filter with a passband of 10-200Hz. After filtering, the peak-to-peak value of the signal is reduced to 1.5MPa, and the signal-to-noise ratio is improved to 40dB. The filtered signal is decomposed into four levels using a db4 wavelet. The correlation coefficient between the reconstructed signal and the original signal is 0.95, the root mean square value is 0.4MPa, and the peak-to-peak value is 1.2MPa. A Fast Fourier Transform (FFT) was performed on 2048 data points to obtain the amplitude spectrum within the 0-500Hz frequency range. The main pulsation frequencies appeared at 80Hz, 160Hz, and 240Hz, with corresponding amplitudes of 0.3MPa, 0.2MPa, and 0.1MPa, respectively, and a mean of 0.12MPa. Frequency components with amplitudes greater than 0.24MPa were extracted as the dominant frequency components. When the amplitude of the 80Hz frequency component (0.3MPa) exceeded the preset threshold of 0.25MPa, the recursive least squares method was used to iterate five times to obtain an opening compensation value of 15%, with a pressure change of 0.1MPa / 1% opening. Under the condition that the opening adjustment rate was limited to 10% / s, the buffer valve opening was gradually adjusted from 35% to 50%, and the pressure pulsation amplitude decreased to 0.2MPa.

[0024] S103. Obtain the opening area of ​​the buffer valve. For different buffer valve opening areas, analyze the dynamic response characteristics of the hydraulic system through simulation to obtain the change curves of system pressure, flow rate and valve opening. In this way, optimize the buffer valve opening control strategy, determine the target buffer valve opening area, and obtain the target system dynamic response performance.

[0025] A displacement sensor with a range of [range value] is used to collect the valve core displacement signal. Based on the displacement signal, the valve port contour line is identified using the Canny edge detection algorithm to obtain the valve port opening area value. For the valve port opening area value, under the conditions of the pressure inlet boundary and the pressure outlet boundary, the flow channel between the hydraulic cylinder and the buffer valve is calculated using a mesh generation method to obtain pressure distribution field and flow field data. Based on the pressure distribution field and the flow field data, the response characteristics are calculated using a finite-difference time-domain algorithm to obtain the pressure rise time, flow response delay, pressure overshoot, and flow fluctuation value. For the pressure rise time, the flow response delay, the pressure overshoot, and the flow fluctuation value, a cubic polynomial least squares fitting algorithm is used to obtain the correlation curve between the opening degree and dynamic characteristics. If the correlation curve between the opening degree and dynamic characteristics meets the requirements of pressure response time weight, overshoot weight, and flow delay weight, a genetic algorithm is used to optimize the opening response curve to obtain the optimal opening area value.

[0026] Specifically, displacement signals of the buffer valve core are acquired using a displacement sensor with a range of 0-10 mm and an accuracy of 0.01 mm. The valve port contour is identified using a Canny edge detection algorithm with a detection threshold of 50. Based on the correspondence between opening degree and area in the valve core structure, the valve port opening area within the 0%-100% opening range is calculated and discretized using a 0.1 mm grid size. Under pressure conditions of 20 MPa at the inlet boundary and 18 MPa at the outlet boundary, the flow channel between the hydraulic cylinder and the buffer valve is divided into 20,000 grid cells, with the first layer of grid height on the wall set to 0.02 mm. A Reynolds stress turbulence analyzer is used to calculate the pressure distribution field and flow field data within the 0%-100% opening range, obtaining pressure-flow characteristic curves for each opening degree. Using a 0.1 ms time step within a 100 ms sampling time, a finite-difference time-domain algorithm is employed to calculate the response characteristics of the pressure distribution field and flow field data, obtaining the pressure rise time, flow response delay, pressure overshoot, and flow fluctuation values. A cubic polynomial least squares fitting method is used to obtain the correlation curve between the opening degree and dynamic characteristics. A genetic algorithm with a population size of 50, 100 iterations, a crossover probability of 0.8, and a mutation probability of 0.1 was used. Pressure response time (weighted by 0.4), overshoot (weighted by 0.3), and flow delay (weighted by 0.3) were used as optimization objectives. The opening response curve was optimized within the 0-100% opening range to obtain the optimal opening area value that satisfies the requirements of pressure rise time less than 50ms, overshoot less than 5%, and flow response delay less than 30ms. A displacement sensor collects valve core displacement data in real time at the buffer valve installation location. When the valve core displacement increases from 0mm to 5mm, the Canny edge detection algorithm detects that the valve port contour length increases from 150 pixels to 300 pixels. With an edge detection threshold of 50, the detection accuracy reaches 0.02mm, and the valve port opening area increases from 0mm... 2 Increased to 80mm 2After discretization with a 0.1 mm grid size, 800 grid cells were obtained. Under the conditions of an inlet pressure of 20 MPa and an outlet pressure of 18 MPa, the calculated flow rates were 0 L / min at 0% opening, 40 L / min at 25% opening, 85 L / min at 50% opening, 120 L / min at 75% opening, and 150 L / min at 100% opening. Data was continuously collected for 100 ms within a 0.1 ms sampling interval. At 25% opening, the pressure rise time was 80 ms with an overshoot of 8% and a flow response delay of 45 ms; at 50% opening, the pressure rise time was 65 ms with an overshoot of 6% and a flow response delay of 38 ms; and at 75% opening, the pressure rise time was 45 ms with an overshoot of 4% and a flow response delay of 25 ms. After 30 generations of optimization using a genetic algorithm, the optimal opening degree was found to be 72%. At this point, the pressure rise time was 48ms, the overshoot was 4.8%, and the flow response delay was 28ms, which met the dynamic response index requirements.

[0027] S104. Under different load conditions, collect hydraulic cylinder pressure and buffer valve opening data, and establish a polynomial regression model of load and buffer valve pressure by least squares fitting to obtain the correlation between load and target buffer pressure. Based on the correlation between load and target buffer pressure, realize adaptive adjustment of buffer valve pressure.

[0028] The load signal of the hydraulic forklift is acquired by a load sensor. The load signal is quantized and sampled by a data acquisition card to obtain load data. The load data is processed using a median filter. Based on the load data, the pressure of the hydraulic cylinder circuit and the inlet and outlet pressure of the buffer valve are acquired by a pressure sensor. The pressure sensor obtains the corresponding data set of the buffer valve opening value and the pressure data value. For the corresponding data set, a third-order polynomial least squares method is used for curve fitting, and the curve fitting obtains polynomial coefficients. Based on the polynomial coefficients, the curve is smoothed by Lagrange interpolation, and the Lagrange interpolation method obtains a smooth curve with a pressure smoothness error less than a preset threshold. For the smooth curve, a mean filter is used to calculate the target buffer pressure value. The target buffer pressure value is adjusted by a proportional-integral controller with closed-loop control of the opening. The proportional-integral controller adaptively controls the opening of the buffer valve.

[0029] Specifically, load data of the hydraulic forklift under different load capacities is collected using a load sensor with a range of 0-3000 kg and an accuracy of 0.1%. A high-precision data acquisition card is used to perform 16-bit sampling quantization of the load signal, with the sampling frequency set to 100 Hz. Data sets corresponding to load capacities and hydraulic cylinder pressures within the range of 0-2000 kg are obtained. The sampled data is processed using a median filter with a window length of 10. A pressure sensor is used to collect real-time data on the hydraulic cylinder circuit pressure and the inlet and outlet pressures of the buffer valve within a 5-second time window. Pressure data is collected every 10 ms. Steady-state data with pressure fluctuations of less than 1% are selected and recorded as buffer valve opening values ​​and pressure data values ​​within the range of 0-100% opening, thus obtaining corresponding data sets of load capacities and pressures. Interpolation points were selected at 100kg intervals for the collected data sets. A regression curve was fitted using a third-order polynomial least squares method with coefficients a0, a1, a2, and a3, with a fitting accuracy of 0.98. The fitting coefficients were updated every 500 milliseconds. Lagrange interpolation with a pressure smoothness error of less than 0.5% was used to smooth the curve. Based on the fitted polynomial coefficients, a mean filter with a sliding window length of 10 was used to calculate the real-time target buffer pressure value. A proportional-integral controller with a proportional coefficient of 0.8 and an integral time of 0.5s was used to perform closed-loop adjustment of the buffer valve opening within a 20ms control cycle to achieve adaptive pressure control. The load sensor output a 4mA signal when the forklift load is 0kg and a 20mA signal when the load is 3000kg. A 16-bit sampling accuracy data acquisition card was used to collect the load signal, with a minimum resolution of 0.05kg. The measurement accuracy reached 0.1% with a median filtering window length of 10 data points. The pressure sensor collects data within a 5-second time window. At a load of 500 kg, the hydraulic cylinder pressure is 8 MPa, and the buffer pressure is 6 MPa at 25% opening. At a load of 1000 kg, the hydraulic cylinder pressure is 12 MPa, and the buffer pressure is 9 MPa at 50% opening. At a load of 1500 kg, the hydraulic cylinder pressure is 16 MPa, and the buffer pressure is 12 MPa at 75% opening. At a load of 2000 kg, the hydraulic cylinder pressure is 20 MPa, and the buffer pressure is 15 MPa at 100% opening. Twenty interpolation points are selected at 100 kg load intervals. A third-order polynomial fitting is used to obtain coefficients a0 = 5.2, a1 = 0.008, a2 = -2.1 × 10⁻⁶, and a3 = 4.5 × 10⁻¹⁰. The correlation coefficient between the fitted curve and the measured data is 0.992. Under the action of the proportional-integral controller, when the load increases from 1000kg to 1500kg, the opening of the buffer valve is adjusted from 50% to 75% within 0.5 seconds, the buffer pressure rises from 9MPa to 12MPa, the pressure overshoot is 0.3MPa, and the adjustment time is 0.8 seconds.

[0030] S105. Based on the fork descent speed and load capacity, predict the trend of hydraulic cylinder pressure change, establish a pressure prediction model using support vector machine algorithm, and control the opening of the buffer valve in advance when the predicted pressure exceeds the safety threshold to achieve predictive pressure control.

[0031] Hydraulic cylinder pressure signals are acquired using pressure sensors, and fork displacement signals are acquired using displacement sensors. The pressure and displacement signals are quantized to obtain a quantized data sequence. Pressure change process samples are selected from the quantized data sequence, and the minimum-maximum method is used to normalize these samples to obtain a normalized dataset. This normalized dataset includes load capacity parameters, descent speed parameters, and pressure change parameters. A support vector machine (SVM) prediction model is trained based on the normalized dataset. The SVM prediction model uses a radial basis function kernel function, and cross-validation is used to obtain the support vector parameters. The SVM prediction model is used to predict the pressure change trend, and the prediction results are smoothed using a moving average filter to obtain a smoothed predicted pressure value. If the smoothed predicted pressure value exceeds a safety threshold, a fuzzy controller is used for opening compensation. The opening compensation value is calculated using the centroid method to defuzzify the pressure deviation and deviation change rate, and the opening of the buffer valve is adjusted accordingly.

[0032] Specifically, hydraulic cylinder pressure signals are acquired using a pressure sensor with a range of 0-40 MPa and an accuracy of 0.1%, and fork displacement signals are acquired using a displacement sensor with a range of 0-2 m and an accuracy of 0.1 mm. A high-precision data acquisition card is used to perform 16-bit quantization on the pressure and displacement signals. Data is acquired every 10 ms, recording the relationship between pressure changes and descent speed within a pressure fluctuation range of less than 2% and a constant descent speed. 1000 complete pressure change processes, including load capacity, descent speed, and pressure change, are selected from the pressure data sequences acquired by the pressure sensors. The raw data is normalized using the minimax method. The data is divided into training and validation sets in an 8:2 ratio, and 5-fold cross-validation is performed on the training data, with a validation error of less than 3%. A support vector machine (SVM) algorithm is used to establish a pressure prediction model, employing a radial basis function kernel, a penalty factor of 100, and a relaxation variable of 0.01. 200 support vectors are obtained through training, achieving a cross-validation accuracy of 95%. The prediction time lead is set to 500 ms, and the prediction results are smoothed using a moving average filter. Based on the pressure change trend predicted by the support vector machine, if the predicted pressure value exceeds the safety threshold of 20 MPa, a fuzzy controller based on 7 fuzzy subsets is used for opening compensation. Pressure deviation and deviation change rate are used as inputs, and the opening compensation value is obtained through centroid defuzzification calculation, adjusting the buffer valve opening. When the fork descent speed is 300 mm / s under no-load conditions, the displacement sensor sampling signal changes from 0 mm to 1800 mm, and the hydraulic cylinder pressure remains at 5 MPa; when the load is 500 kg, the descent speed is 250 mm / s, and the hydraulic cylinder pressure is 8 MPa; when the load is 1000 kg, the descent speed is 200 mm / s, and the hydraulic cylinder pressure is 12 MPa; when the load is 1500 kg, the descent speed is 150 mm / s, and the hydraulic cylinder pressure is 16 MPa; when the load is 2000 kg, the descent speed is 100 mm / s, and the hydraulic cylinder pressure is 20 MPa. After normalization using the maximum-minimum method, the normalized values ​​for load capacity improved from 0.25 to 1, descent speed improved from 0.33 to 1, and pressure improved from 0.25 to 1. Support vector machines were trained on 800 datasets and validated on 200 datasets. The average error of the 5-fold cross-validation was 2.8%. The system predicted pressure changes 500ms in advance. When the load suddenly increased from 1000kg to 1500kg, the predicted pressure rose from 12MPa to 15.8MPa within 300ms, while the actual pressure reached 16MPa after 500ms, with a prediction error of 1.2%. The fuzzy controller input was divided into 7 fuzzy subsets, with pressure deviations ranging from -3MPa to +3MPa and a deviation change rate from -0.1MPa / ms to +0.1MPa / ms. The output opening compensation value ranged from -20% to +20%. Using the centroid method to defuzzify, an opening compensation value of 15% was obtained, reducing the actual pressure to 14.5MPa.

[0033] S106. By combining the forklift's load capacity, fork descent speed, and hydraulic cylinder pressure, a fuzzy rule base is established to achieve fuzzy adaptive control of the buffer valve opening. The buffer valve opening is automatically adjusted according to different working conditions to ensure that the hydraulic system pressure remains stable within a safe range.

[0034] The system acquires forklift load, fork descent speed, and hydraulic cylinder pressure signals from sensors. The sampling frequency of the sensors is a preset frequency value. The forklift load, fork descent speed, and hydraulic cylinder pressure signals are quantized to form the first input data. Based on the first input data, a pre-established Gaussian membership function is used to perform fuzzy quantization processing on the load, descent speed, and hydraulic cylinder pressure to obtain the membership values ​​of the load, descent speed, and hydraulic cylinder pressure. For the membership values ​​of the load, descent speed, and hydraulic cylinder pressure, a fuzzy rule base is constructed using preset weight coefficients. The activation intensity of the rules is calculated using the minimum operator to obtain the activation degree of the fuzzy rule base. Based on the activation degree of the fuzzy rule base, the maximum operator is used to perform rule synthesis operations to obtain the fuzzy control quantity of the buffer valve opening. The buffer valve opening is divided into a preset number of fuzzy subsets. For the fuzzy control quantity of the buffer valve opening, the centroid method is used for defuzzification calculation. The opening output value is smoothed using a moving average filter to obtain the precise control quantity of the buffer valve opening.

[0035] Specifically, three input variables—forklift load, fork descent speed, and hydraulic cylinder pressure—are collected using sensors with a sampling frequency of 100Hz and an accuracy of 0.1%. The variable ranges are 0-2500kg, 0-400mm / s, and 0-25MPa, respectively. The load is divided into four fuzzy subsets: zero load, light load, medium load, and heavy load; the descent speed is divided into three fuzzy subsets: slow, medium, and fast; and the hydraulic cylinder pressure is divided into three fuzzy subsets: low pressure, medium pressure, and high pressure. A Gaussian membership function with a standard deviation of 20% of the center value is used to quantify the fuzzy variables. The overlap between adjacent membership functions is set to 25%. The center values ​​for load membership are set to 0kg, 500kg, 1000kg, and 2000kg; the center values ​​for descent speed membership are set to 100mm / s, 200mm / s, and 300mm / s; and the center values ​​for pressure membership are set to 5MPa, 10MPa, and 20MPa. A fuzzy rule base containing 36 rules is constructed based on input variable weights of 0.5, 0.3, and 0.2. The antecedent of each rule is a combination of load, descent speed, and hydraulic cylinder pressure. The minimum operator is used to calculate the rule activation intensity, and the maximum operator is used for rule synthesis. The consequent of each rule is the buffer valve opening value, which is divided into three fuzzy subsets: small opening, medium opening, and large opening, with center values ​​of 25%, 50%, and 75%, respectively. The centroid method is used to defuzzify the rule inference results. The values ​​of the three input variables under the current operating condition are collected in real time within a 20ms control cycle. The opening output is smoothed by a moving average filter with a window length of 5, limiting the opening change rate to within 10% / s, thus obtaining the precise control value of the buffer valve opening. Sensor data collected during forklift lifting under no-load conditions showed the following: load capacity 0 kg, descent speed 300 mm / s, pressure 5 MPa, corresponding to a zero-load subset membership degree of 0.95, a fast subset membership degree of 0.85, a low-pressure subset membership degree of 0.9, a regular activation intensity of 0.85, and an output opening degree of 25%. When the forklift load reached 500 kg, the descent speed decreased to 250 mm / s, and the pressure increased to 8 MPa, corresponding to a light-load subset membership degree of 0.8, a medium-speed subset membership degree of 0.75, a low-pressure subset membership degree of 0.6, a regular activation intensity of 0.6, and an output opening degree of 35%. When the load increased to 1000 kg, the descent speed decreased to 200 mm / s, and the pressure increased to 12 MPa, corresponding to a medium-load subset membership degree of 0.85, a medium-speed subset membership degree of 0.9, a medium-pressure subset membership degree of 0.8, a regular activation intensity of 0.8, and an output opening degree of 55%. When the load reaches 2000kg, the descent speed drops to 100mm / s, the pressure rises to 20MPa, corresponding to a heavy load subset membership degree of 0.9, a slow speed subset membership degree of 0.85, a high pressure subset membership degree of 0.9, a regular activation intensity of 0.85, and an output opening of 75%.After the moving average filter, the opening output curve is smooth. As the load increases from 1000kg to 2000kg, the opening gradually increases from 55% to 75%, with the rate of change remaining at 8% / s. The pressure rises steadily to 20MPa, meeting the safety control requirements.

[0036] S107. Establish a nonlinear mapping relationship between load capacity, fork descent speed and buffer valve opening, train and optimize the neural network model to realize intelligent control of buffer valve opening, and automatically adjust the buffer valve opening according to the real-time collected load capacity and fork descent speed.

[0037] The system acquires load and descent speed signals from sensors. These signals are then quantized to 16 bits using a data acquisition card. A median filter is used to filter the quantized signals to obtain training sample data. Based on this training sample data, the load, descent speed, and buffer valve opening value are normalized to obtain normalized data. The z-score method is then used to standardize the normalized data to obtain standardized training data. A dual-hidden-layer neural network is trained using this standardized training data. The weights are initialized using the Xavier method. If the training error is less than a preset threshold and the test set accuracy exceeds a specified threshold, a trained neural network model is obtained. The system processes the real-time acquired load and descent speed signals using the trained neural network model, outputting the buffer valve opening value. A moving average filter is used to smooth the buffer valve opening value. If the smoothed opening value exceeds the standard deviation threshold, outlier removal is performed. Finally, an opening limiter is used to limit the opening value to obtain the final output opening value.

[0038] Specifically, data was collected using sensors under operating conditions of 0-2000kg load intervals of 200kg and descent speed intervals of 0-300mm / s of 30mm / s. A high-precision data acquisition card was used to perform 16-bit quantization of the signals, and the sampling frequency was set to 100Hz. A median filter was used to remove noise from the sampled data, resulting in 1000 complete training sample data sets. Outliers exceeding three times the standard deviation were removed. The collected training sample data were normalized: load, descent speed, and buffer valve opening were all normalized to the 0-1 range. The dataset was randomly shuffled three times and then divided into training and test sets in an 8:2 ratio. The mean and standard deviation of the training set were used to perform z-score standardization on the data. A feedforward neural network with two hidden layers was constructed. The weights were initialized using the Xavier method, with 8 nodes in the first hidden layer and 4 nodes in the second. The hyperbolic tangent function was used as the activation function, and the learning rate was set to 0.01. Iteration was stopped when the training error was less than 0.001 within 1000 iterations. The network was validated on a test set after every 100 training iterations, achieving an accuracy of over 95%. The trained neural network was used to process real-time collected load and descent speed data. A moving average filter with a window length of 10 was used to smooth the output results. Outliers exceeding three standard deviations were removed, and the opening output was limited to the range of 0-100%, with the opening change rate controlled within 10% / s. During forklift data collection, the descent speed was 300 mm / s and the opening degree was 25% when the load was 0 kg; 270 mm / s and 35% when the load was 400 kg; 240 mm / s and 45% when the load was 800 kg; 210 mm / s and 55% when the load was 1200 kg; 180 mm / s and 65% when the load was 1600 kg; and 150 mm / s and 75% when the load was 2000 kg. After data normalization, the mean and standard deviation of the load data were 0.5, the mean and standard deviation of the descent speed data were 0.6 and 0.15, and the mean and standard deviation of the opening degree data were 0.4 and 0.18. After 200 training iterations, the training error decreased to 0.0009, and the test set validation accuracy reached 96.5%. The weights of the 8 nodes in the first hidden layer ranged from -0.8 to 0.8, and the weights of the 4 nodes in the second hidden layer ranged from -0.5 to 0.5. During real-time control, when the load increased from 800kg to 1200kg, the collected descent speed decreased from 240mm / s to 210mm / s. After calculation by the neural network, the opening value increased from 45% to 55%. After moving average filtering, the opening change rate remained at 8% / s, and the pressure transitioned smoothly.

[0039] The above are only some preferred embodiments of the present invention, but the present invention is not limited thereto, and many improvements and modifications can be made. Any improvements and modifications made based on the basic principles of the present invention should be considered to fall within the protection scope of the present invention.

Claims

1. A method for analyzing the load of an engineering vehicle, characterized in that: The method comprises: Obtain the load weight of the forklift under full load, identify the descending speed of the fork when it descends quickly, calculate the pressure change curve of the hydraulic cylinder under full load condition of the forklift through the established hydraulic system mathematical model, and judge whether the pressure exceeds the preset safety threshold. If it exceeds the threshold, the pressure regulation function of the hydraulic buffer valve is triggered; A pressure sensor is used to detect the inlet and outlet pressures of the hydraulic buffer valve in real time to obtain the pressure pulsation signal. The pressure pulsation signal is analyzed in the time-frequency domain to obtain the pressure pulsation amplitude at different frequencies, and it is judged whether the pressure pulsation exceeds the preset safety threshold. If it exceeds the threshold, the opening of the buffer valve is controlled to reduce the pressure pulsation. Obtain the opening area of ​​the buffer valve. For different buffer valve opening areas, analyze the dynamic response characteristics of the hydraulic system through simulation, obtain the change curves of system pressure, flow, and valve opening, thereby optimizing the buffer valve opening control strategy and determining the target buffer valve opening area to obtain the target system dynamic response performance; Under different load conditions, the hydraulic cylinder pressure and buffer valve opening data are collected, and a polynomial regression model of load and buffer valve pressure is established through least squares fitting to obtain the correlation between load and target buffer pressure. According to the correlation between load and target buffer pressure, adaptive adjustment of buffer valve pressure is achieved. According to the fork lowering speed and load, the change trend of the hydraulic cylinder pressure is predicted, and the pressure prediction model is established through the support vector machine algorithm. When the predicted pressure exceeds the safety threshold, the buffer valve opening is controlled in advance to achieve predictive control of the pressure; Combined with the forklift's load, fork lowering speed, and hydraulic cylinder pressure, a fuzzy rule base is established to achieve fuzzy adaptive control of the buffer valve opening. The buffer valve opening is automatically adjusted according to different working conditions to ensure that the hydraulic system pressure is stable within a safe range. A nonlinear mapping relationship between load weight, fork descent speed and buffer valve opening is established, and the neural network model is trained and optimized to realize intelligent control of buffer valve opening. The buffer valve opening is automatically adjusted according to the load weight and fork descent speed collected in real time.

2. The method according to claim 1, characterized in that The method of obtaining the load of the forklift under the fully loaded state, identifying the descending speed of the fork when the fork is rapidly descended, calculating the pressure change curve of the hydraulic cylinder under the fully loaded working condition of the forklift through the established hydraulic system mathematical model, and judging whether the pressure exceeds the preset safety threshold, and triggering the pressure adjustment function of the hydraulic buffer valve if the pressure exceeds the threshold, includes: Obtain measurement data of the gravity sensor and the lifting angle sensor, and obtain the fork load moment value according to the measurement data and the fork arm length according to the load moment calculation formula M=F×L×cosθ, where F is the gravity value of the fork, L is the fork arm length, and θ is the fork lifting angle; According to the fork load moment value, a Kalman filter is used to perform noise filtering processing, and the fork position change data is collected by a displacement sensor within a fixed sampling time interval, and the hydraulic oil flow value is obtained according to the flow calculation formula Q=v×A, where v is the fork descending speed and A is the piston area; According to the hydraulic oil flow value, the pipeline pressure loss value is calculated according to the Bernoulli equation ΔP=ρv2 / 2, where ρ is the hydraulic oil density, the hydraulic oil pressure data is collected through the oil pump pressure sensor, and the hydraulic cylinder pressure value is obtained according to the pressure calculation formula P=F / A+ΔP; Using cubic spline interpolation to perform curve fitting processing on the hydraulic cylinder pressure value to obtain a hydraulic cylinder pressure change curve, and determine whether the hydraulic cylinder pressure value exceeds a preset pressure threshold; If the hydraulic cylinder pressure value exceeds the preset pressure threshold, the hydraulic buffer valve is triggered, and a proportional-integral controller is used to output a control signal according to the control formula u=Kp×e+Ki×∫edt, where e is the deviation between the actual pressure and the threshold, Kp is the proportional coefficient, and Ki is the integral coefficient. The buffer valve opening is adjusted according to the control signal.

3. The method according to claim 1, characterized in that The method uses a pressure sensor to detect the inlet and outlet pressures of the hydraulic buffer valve in real time, obtains a pressure pulsation signal, performs time-frequency domain analysis on the pressure pulsation signal, obtains pressure pulsation amplitudes at different frequencies, and determines whether the pressure pulsation exceeds a preset safety threshold. If the pressure pulsation exceeds the threshold, the opening of the buffer valve is controlled to reduce the pressure pulsation, including: A pressure sensor is used to collect the inlet and outlet pressure signals of the hydraulic buffer valve, and the pressure signal is sampled and quantified by a data acquisition card to obtain a pressure pulsation sampling data sequence; According to the pressure pulsation sampling data sequence, a bandpass filter is used to remove power frequency interference and high-frequency noise, and a filtered pressure signal is obtained through wavelet decomposition processing; Performing a fast Fourier transform on the filtered pressure signal to obtain a pressure pulsation amplitude spectrum within a frequency range; Extracting frequency components with amplitudes greater than twice the mean value from the pressure pulsation amplitude spectrum as main frequency components, and calculating a linear mapping relationship of the opening adjustment amount according to the main frequency components; If the amplitude of the main frequency component exceeds the preset safety threshold, the optimal opening value is calculated using the recursive least squares method, and the buffer valve opening is compensated and adjusted according to the opening adjustment rate.

4. The method according to claim 1, characterized in that: The method of obtaining the buffer valve opening area, analyzing the dynamic response characteristics of the hydraulic system through simulation for different buffer valve opening areas, obtaining the change curves of system pressure, flow, and valve opening, thereby optimizing the buffer valve opening control strategy, determining the target buffer valve opening area, and obtaining the target system dynamic response performance, includes: A displacement sensor with a measuring range is used to collect a valve core displacement signal, and a Canny edge detection algorithm is used to identify the valve port contour line according to the displacement signal to obtain a valve port opening area value; According to the valve opening area value, under the pressure inlet boundary and pressure outlet boundary conditions, the flow channel between the hydraulic cylinder and the buffer valve is calculated by a grid division method to obtain the pressure distribution field and flow field data; According to the pressure distribution field and the flow field data, a time-domain finite difference algorithm is used to calculate the response characteristics to obtain the pressure rise time, flow response delay, pressure overshoot and flow fluctuation value; The pressure rise time, the flow response delay, the pressure overshoot and the flow fluctuation value are calculated by using a cubic polynomial least squares fitting algorithm to obtain a correlation curve between the opening and the dynamic characteristics; If the opening degree and dynamic characteristic correlation curve meets the pressure response time weight, overshoot weight and flow delay weight requirements, a genetic algorithm is used to optimize the opening degree response curve to obtain the optimal opening area value.

5. The method according to claim 1, characterized in that Under different load conditions, the hydraulic cylinder pressure and buffer valve opening data are collected, and a polynomial regression model of the load and buffer valve pressure is established by least squares fitting to obtain the correlation between the load and the target buffer pressure. According to the correlation between the load and the target buffer pressure, adaptive adjustment of the buffer valve pressure is achieved, including: The load signal of the hydraulic forklift is collected by the load sensor, the load signal is sampled by a data acquisition card for 16-bit quantization to obtain load data, and the load data is processed by a median filter; According to the load data, a pressure sensor is used to collect the hydraulic cylinder circuit pressure and the buffer valve inlet and outlet pressures, and the pressure sensor obtains a corresponding data set of the buffer valve opening value and the pressure data value; For the corresponding data group, a third-order polynomial least square method is used to perform curve fitting, and the curve fitting obtains polynomial coefficients; According to the polynomial coefficients, the curve is smoothed by using a Lagrange interpolation method, wherein the Lagrange interpolation method obtains a smooth curve whose pressure smoothness error is less than a preset threshold value; For the smooth curve, a mean filter is used to calculate a target buffer pressure value, and the target buffer pressure value is adjusted by a proportional-integral controller for closed-loop opening, and the proportional-integral controller performs adaptive control on the buffer valve opening.

6. The method according to claim 1, characterized in that The method predicts the change trend of the hydraulic cylinder pressure according to the fork lowering speed and the load, establishes a pressure prediction model through a support vector machine algorithm, and controls the opening of the buffer valve in advance when the predicted pressure exceeds the safety threshold to achieve predictive control of the pressure, including: Collecting a hydraulic cylinder pressure signal through a pressure sensor and a fork displacement signal through a displacement sensor, and performing data quantization according to the pressure signal and the displacement signal to obtain a quantized data sequence; A pressure change process sample is selected for the quantitative data sequence, and a maximum and minimum value method is used to normalize the pressure change process sample to obtain a normalized data set, wherein the normalized data set includes a load parameter, a descent speed parameter, and a pressure change parameter; Training a support vector machine prediction model according to the normalized data set, wherein the support vector machine prediction model adopts a radial basis kernel function and obtains support vector parameters through cross validation; The support vector machine prediction model is used to predict the pressure change trend, and the prediction result is smoothed by a sliding average filter to obtain a smoothed predicted pressure value; If the smoothed predicted pressure value exceeds the safety threshold, a fuzzy controller is used to perform opening compensation, and the opening compensation value is obtained by defuzzification calculation using the center of gravity method according to the pressure deviation and the deviation change rate, and the buffer valve opening is adjusted.

7. The method according to claim 1, characterized in that The method combines the load capacity of the forklift, the fork lowering speed, and the hydraulic cylinder pressure to establish a fuzzy rule base, realize the fuzzy adaptive control of the buffer valve opening, automatically adjust the buffer valve opening according to different working conditions, and ensure that the hydraulic system pressure is stable within a safe range, including: Acquire the forklift load, fork lowering speed and hydraulic cylinder pressure signals collected by the sensor, wherein the sampling frequency of the sensor is a preset frequency value, and the forklift load, fork lowering speed and hydraulic cylinder pressure signals are quantized to form first input data; According to the first input data, a pre-established Gaussian membership function is used to perform fuzzy quantization processing on the load, the descent speed and the hydraulic cylinder pressure to obtain membership values ​​of the load, the descent speed and the hydraulic cylinder pressure; According to the membership values ​​of the load, the lowering speed and the hydraulic cylinder pressure, a fuzzy rule base is constructed by using preset weight coefficients, and the activation strength of the rule is calculated by a minimum operator to obtain the activation degree of the fuzzy rule base; According to the activation degree of the fuzzy rule base, a maximum operator is used to perform rule synthesis operation to obtain a fuzzy control amount of the buffer valve opening, and the buffer valve opening is divided into a preset number of fuzzy subsets; For the fuzzy control value of the buffer valve opening, the centroid method is used to perform defuzzification calculation, and the opening output value is smoothed by a sliding average filter to obtain the accurate control value of the buffer valve opening.

8. The method according to claim 1, characterized in that The nonlinear mapping relationship between the load weight, the fork lowering speed and the buffer valve opening is established, and the neural network model is trained and optimized to realize the intelligent control of the buffer valve opening, and the buffer valve opening is automatically adjusted according to the load weight and the fork lowering speed collected in real time, including: Obtain the load signal and the descent speed signal collected by the sensor, perform 16-bit quantization processing on the load signal and the descent speed signal through the data acquisition card, and use the median filter to filter the quantized signal to obtain training sample data; According to the training sample data, the load weight, the descent speed and the buffer valve opening value are normalized to obtain normalized data, and the normalized data are normalized by using a z-score method to obtain standardized training data; The double hidden layer neural network is trained using the standardized training data, and the weights of the neural network are initialized using the Xavier method. If the training error is less than a preset threshold and the accuracy of the test set exceeds a specified threshold, a trained neural network model is obtained; Processing the real-time collected load signal and descent speed signal according to the trained neural network model, and outputting the buffer valve opening value through the neural network model; The buffer valve opening value is smoothed by a sliding average filter. If the smoothed opening value exceeds the standard deviation threshold, abnormal values ​​are eliminated, and the opening value is limited by an opening limiter to obtain a final opening output value.

Images