CN115140685A - Forklift data driving stability control method - Google Patents
Forklift data driving stability control method Download PDFInfo
- Publication number
- CN115140685A CN115140685A CN202210528993.4A CN202210528993A CN115140685A CN 115140685 A CN115140685 A CN 115140685A CN 202210528993 A CN202210528993 A CN 202210528993A CN 115140685 A CN115140685 A CN 115140685A
- Authority
- CN
- China
- Prior art keywords
- forklift
- state
- data
- neural network
- rbf neural
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000013528 artificial neural network Methods 0.000 claims abstract description 59
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 14
- 230000001133 acceleration Effects 0.000 claims description 12
- 230000000368 destabilizing effect Effects 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 239000003921 oil Substances 0.000 claims description 7
- 230000001687 destabilization Effects 0.000 claims description 6
- 239000010720 hydraulic oil Substances 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 4
- 230000002542 deteriorative effect Effects 0.000 claims description 3
- 239000012535 impurity Substances 0.000 claims description 3
- 230000003313 weakening effect Effects 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims 1
- 238000010200 validation analysis Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 10
- 238000005457 optimization Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 210000002569 neuron Anatomy 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000000354 decomposition reaction Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000005316 response function Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000000356 contaminant Substances 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005312 nonlinear dynamic Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000002087 whitening effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66F—HOISTING, LIFTING, HAULING OR PUSHING, NOT OTHERWISE PROVIDED FOR, e.g. DEVICES WHICH APPLY A LIFTING OR PUSHING FORCE DIRECTLY TO THE SURFACE OF A LOAD
- B66F9/00—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes
- B66F9/06—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes movable, with their loads, on wheels or the like, e.g. fork-lift trucks
- B66F9/075—Constructional features or details
- B66F9/20—Means for actuating or controlling masts, platforms, or forks
- B66F9/22—Hydraulic devices or systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66F—HOISTING, LIFTING, HAULING OR PUSHING, NOT OTHERWISE PROVIDED FOR, e.g. DEVICES WHICH APPLY A LIFTING OR PUSHING FORCE DIRECTLY TO THE SURFACE OF A LOAD
- B66F17/00—Safety devices, e.g. for limiting or indicating lifting force
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66F—HOISTING, LIFTING, HAULING OR PUSHING, NOT OTHERWISE PROVIDED FOR, e.g. DEVICES WHICH APPLY A LIFTING OR PUSHING FORCE DIRECTLY TO THE SURFACE OF A LOAD
- B66F9/00—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes
- B66F9/06—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes movable, with their loads, on wheels or the like, e.g. fork-lift trucks
- B66F9/075—Constructional features or details
- B66F9/07504—Accessories, e.g. for towing, charging, locking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66F—HOISTING, LIFTING, HAULING OR PUSHING, NOT OTHERWISE PROVIDED FOR, e.g. DEVICES WHICH APPLY A LIFTING OR PUSHING FORCE DIRECTLY TO THE SURFACE OF A LOAD
- B66F9/00—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes
- B66F9/06—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes movable, with their loads, on wheels or the like, e.g. fork-lift trucks
- B66F9/075—Constructional features or details
- B66F9/0755—Position control; Position detectors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
Landscapes
- Engineering & Computer Science (AREA)
- Structural Engineering (AREA)
- Transportation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Mechanical Engineering (AREA)
- Civil Engineering (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Chemical & Material Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Combustion & Propulsion (AREA)
- Forklifts And Lifting Vehicles (AREA)
Abstract
The invention discloses a forklift data driving stability control method, which comprises the following steps: step 1, acquiring forklift running state parameters, and establishing a forklift state prediction model, wherein the forklift state prediction model is a gray radial basis GM-RBF neural network prediction model; step 2, training the prediction model until the grey radial basis GM-RBF neural network prediction model can accurately predict the running state of the forklift; step 3, acquiring and processing real-time driving parameters of the forklift, inputting the processed real-time driving parameters of the forklift into the trained gray radial basis GM-RBF neural network prediction model in the step 2, and then outputting forklift state signals after model processing; and 4, carrying out state control on the forklift according to the forklift state signal output in the step 3, dividing the motion state of the counter-weight forklift, rapidly and accurately determining the motion state of the forklift, and rapidly adjusting the forklift when the forklift is not in a safe state to ensure the stable posture of the forklift.
Description
Technical Field
The invention relates to the field of stability control of forklifts, in particular to a data drive stability control method of a forklift.
Background
The method improves the industrial production efficiency and quality, and has great significance for guaranteeing the national basic material transportation demand and improving the material living standard. The counter-weight forklift is one of core equipment for industrial transportation, plays an irreplaceable role in the fields of ports, buildings, engineering construction and the like, and effectively improves the efficiency and quality of industrial operation, thereby improving the industrial productivity. The counter-balanced forklift is used as a carrying machine, the operation environment is relatively complex, the forklift body and the front axle are fixedly connected and are convenient to carry and carry, the rear axle and the forklift body are connected in a hinged mode, the forklift body can swing up and down around a hinged point, the copying function of tires is met, however, when the forklift turns to at a high speed, due to the fact that the forklift is large in mass, small in wheel distance and high in gravity center, rollover accidents of the forklift are frequent, life safety of drivers is endangered, property loss is caused, industrial transportation progress is influenced, and therefore practical significance is achieved for research and engineering application for preventing the forklift from rollover.
The dynamic system of the whole forklift is a responsible nonlinear system, so that the accurate judgment of the stability state of the forklift is difficult to realize, the judgment of the stability state of the forklift at present mainly is calibrated through expert experience and real-vehicle test, a practical method and a stability control method for accurately judging the stability are lacked, and the stability judgment and control method of the counter-weight forklift need to be deeply researched to improve the stability of the counter-weight forklift.
Disclosure of Invention
The invention aims to provide a data driving stability control method for a counterweight type forklift, which aims to solve the problems in the background technology, so that the rollover prevention control of the counterweight type forklift can be optimized according to the motion state of the forklift, the best posture of the forklift is kept, and the working efficiency and stability of the counterweight type forklift are improved.
In order to achieve the purpose, the invention provides the following technical scheme:
a forklift data drive stability control method comprises the following steps:
step 1, acquiring forklift driving state parameters, and establishing a forklift state prediction model according to the acquired parameter data, wherein the forklift state prediction model is a gray radial basis GM-RBF neural network prediction model;
step 2, training a grey radial basis GM-RBF neural network prediction model until the grey radial basis GM-RBF neural network prediction model can accurately predict the running state of the forklift;
step 3, acquiring and processing the real-time driving parameters of the forklift, inputting the processed real-time driving parameters of the forklift into the trained gray radial basis GM-RBF neural network prediction model in the step 2, and then outputting forklift state signals after model processing;
and 4, carrying out state control on the forklift according to the forklift state signal output in the step 3.
As a further scheme of the invention: and in the step 1, the running state parameters of the forklift comprise the lateral acceleration, the load and the roll angle of the forklift.
As a further scheme of the invention: the establishment of the grey radial basis GM-RBF neural network prediction model in the step 1 comprises the following steps:
step 1.1, acquiring lateral acceleration, load and roll angle data through a sensor arranged on a forklift;
step 1.2, processing the data by using a GM (1, 3) gray model, weakening the random factors of the data, and finding out the dynamic relation of the internal time among the data;
step 1.3, processing the data by using an RBF neural network;
step 1.4, a series-connection type grey neural network model is adopted, different data are taken from the same sequence to obtain different prediction results, then RBF neural networks are used for combining a plurality of grey prediction results, a series of prediction values are obtained after a plurality of sequences of forklift motion are predicted by using grey GM (1, 3) models, the prediction values are used as combined model input samples, actual values are used as output samples, a difference value combination method is adopted, the RBF neural network model is used for combining the prediction values and the actual values, and the RBF neural network is trained to simulate the deviation relation between the prediction values and the actual values and the mutual relation between the sequences.
As a further scheme of the invention: the training process of the grey radial basis GM-RBF neural network prediction model in the step 2 comprises the following steps:
2.1, performing three-order discrete wavelet transform on the lateral acceleration, load and roll angle data of the forklift acquired by the sensor by adopting a Mallet algorithm, and repeatedly decomposing for three times to finally obtain useful characteristics of impurity signals removed;
step 2.2, carrying out data normalization, and replacing the original data by dividing the difference between the original data and the mean value thereof by the standard deviation;
and 2.3, randomly dividing the processed data into two types, wherein 80% of the total amount of one type is used for training a GM-RBF model to evaluate the rollover risk of the forklift, and 20% of the total amount of the other type is used for verifying the accuracy.
As a further scheme of the invention: and when the accuracy of the training set and the verification set of the grey radial basis GM-RBF neural network prediction model is not less than 80%, judging that the grey radial basis GM-RBF neural network prediction model can accurately predict the running state of the forklift.
As a further scheme of the invention: the forklift state is divided into a safe state, a dangerous state and a destabilizing state, and the forklift state division comprises the following steps:
step 3.1, acquiring real-time data of lateral acceleration, load and roll angle of the forklift and inputting the data into the established GM-RBF neural network combined prediction model;
step 3.2, the output of the combined prediction model through the GM-RBF neural network belongs to the element of Y [0,1];
and 3.3, dividing the state of the forklift according to the output value of the model, defining the state as a safe state when the output value is 0, defining the state as a dangerous state when the output value is 0-1, and defining the state as a destabilization state when the output value is 1.
As a further scheme of the invention: the step 4 of controlling the state of the forklift comprises the following steps:
step 4.1, acquiring the state of the forklift, and executing step 4.2 if the forklift is in a safe state; if the forklift is in a dangerous state, executing the step 4.3, and if the forklift is in a destabilizing state, executing the step 4.4;
4.2, when the forklift is in a safe state, the electromagnetic valve is fully opened, the oil cylinder can move freely, and the forklift body and the rear axle can rotate freely;
4.3, when the forklift is in a dangerous state, adjusting the lateral force of the hydraulic oil cylinder based on self-optimizing fuzzy control at the moment, and avoiding the forklift from deteriorating to a destabilizing state as much as possible;
and 4.4, when the forklift is in a destabilizing state, fully closing the electromagnetic valve, directly locking the oil cylinder, fixedly connecting the forklift body and the rear axle, expanding the stable area of the forklift, increasing the anti-rollover moment of the forklift, and improving the stability of the forklift.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention divides the motion state of the counter-weight forklift, can rapidly and accurately determine the motion state of the forklift, can rapidly be adjusted when the forklift is not in a safe state, and ensures the stable posture of the forklift.
2. The method applies the gray system radial basis function neural network combination model, adopts the gray system to weaken the random factors of data, adopts the nearest neighbor cluster learning algorithm as the radial basis function, can track and detect the change of the motion state of the forklift in real time, does not need to establish an accurate forklift nonlinear dynamics model, and is suitable for judging the stability of the forklift with different parameters.
3. According to the invention, the anti-rollover supporting force is adjusted by changing the hydraulic oil cylinder valve of the counterweight type forklift, the operation is convenient and easy to realize, the structure of the counterweight type forklift does not need to be changed on a large scale, the improvement difficulty is low, the improvement cost is low, and the working efficiency of the counterweight type forklift can be obviously improved after the improvement is completed.
Drawings
FIG. 1 is a diagram of the topology of the RBF neural network of the present invention;
FIG. 2 is a diagram of a GM-RBF neural network of the present invention;
FIG. 3 is a schematic diagram of the signal decomposition process of the present invention;
FIG. 4 is a diagram illustrating the results of model training according to the present invention;
FIG. 5 is a diagram illustrating the error of the GM-RBF neural network recognition training of the present invention;
FIG. 6 is a schematic diagram of a lateral stability control strategy for a fork lift truck according to the present invention;
FIG. 7 is a diagram illustrating the application of the GM-RBF neural network prediction model system structure of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-7, in an embodiment of the present invention, a method for controlling stability of data driving of a forklift includes the following steps:
step 1, acquiring forklift running state parameters, and establishing a forklift state prediction model according to acquired parameter data, wherein the forklift state prediction model is a gray radial basis GM-RBF neural network prediction model;
the method specifically comprises the following steps:
step 1, establishing a grey radial basis GM-RBF neural network prediction model;
the method for establishing the grey radial basis GM-RBF neural network prediction model comprises the following steps:
step 1.1, acquiring lateral acceleration, load and roll angle data through a sensor arranged on a balance weight type forklift;
step 1.2, processing the data by using a GM (1, 3) gray model, weakening the random factors of the data, and finding out the dynamic relation of the internal time among the data;
the steps of establishing a grey GM (1, 3) model prediction model are as follows:
accumulating the original forklift data once to generate a corresponding sequence: let x be (0) As the original sequence
x (0) =[x (0) (1),x (0) (2),x (0) (3)] (1)
Remembering the number of generations to
x (1) =[x (1) (1),x (1) (2),x (1) (3)] (2)
Note x (1) And x (0) Satisfies the following relation:
then is x (0) Is generated. So the r-th accumulation is generated as
Establishing a gray differential equation, and generating an adjacent mean sequence:
Wherein a is the coefficient of development, b 2 、b 3 In order to be a driving coefficient of the motor,are the drive terms.
Establishing a whitening differential equation:
and (3) solving an approximate time response function: parameter columnIs satisfied by least squares estimation
Wherein
When x is i When the variation amplitude of (A) is small, the approximate time response function is
And (3) carrying out accumulation reduction to restore the original number sequence, and solving to obtain a restored value:
and checking the precision of the final result. The final model fitting accuracy results are as follows, the development coefficient a =1.364, and the driving coefficient b i The mean fitting variance E (x) and the mean fitting relative variance Er (x) were small, indicating that the model accuracy was good, = 0.141. The GM (1, 3) prediction model requires less sample information, but if the sample data has large oscillation, the model prediction effect is not very good. Therefore, an RBF neural network having a strong fitting property to data is considered as a combined model.
Step 1.3, processing the data by using an RBF neural network, and having higher learning efficiency and stronger fitting capability;
the RBF neural network comprises the following components: the input layer is composed of signal source nodes and plays a role in transmitting data information; the hidden layer is a Gaussian kernel function, and the neural network is more accurate by adjusting the parameters of the Gaussian kernel function; the output layer carries out linear weighting on the information output by the neuron in the hidden layer and then outputs the information, and a linear optimization strategy is adopted. The topology is shown in fig. 1.
Wherein, X = (X) 1 ,X 2 ,X 3 ) 3-dimensional input layer for RBF,. Phi i =R i And (X) is a p-dimensional hidden layer, Y is a 1-dimensional output layer and has a structure of 3-p-1.w is the output weight.
The RBF structure can be represented as:
wherein the Gaussian basis function of RBF is
In the formula, C i A center vector representing the ith perceptual variable; sigma i Represents the ith hidden layer width; p represents the number of hidden layer neurons; i X-C i | | denotes the vector (X-C) i ) Norm of (d).
RBF neural network determines center C thereof through self-organizing learning i And the positions of the neurons in the hidden layer are positioned in the important areas, so that the information contained in the data can be better expressed. Learning for an RBF neural network requires the determination of three parameters: center vector C i Width σ i And the weight value w i 。
Wherein, min (x) k ) Is the minimum value of the kth feature data, max (x) k ) Is the maximum value of the kth feature data.
Width vector sigma i The smaller the response of the neuron center is; sigma i The larger the influence range of the neurons is, the more accurate the expression of the neural network is, and the smoothness among the neurons is better. Width sigma i The initial calculation formula of (2) is as follows:
wherein delta f <1 is a width adjustment coefficient that can improve the local response capability. Weight w i Generally, a gradient descent method is used, and the formula is as follows:
wherein W i (t) is the proportionality coefficient between neurons. Eta is a learning factor and E is an evaluation function.
Wherein, O l Is a desired output value; y is l The value is output for the network. The equation for calculating the root mean square error RMS of the output is as follows:
and if the RMS is less than or equal to epsilon, the model accuracy is considered to be satisfied, and the training is finished.
Step 1.4, a series-connection type grey neural network model is adopted, different data are obtained from the same sequence to obtain different prediction results, then RBF neural networks are used for combining a plurality of grey prediction results, and the structure diagram of the GM-RBF neural network is shown in figure 2. A series of predicted values were obtained after predicting multiple sequences of forklift motion using a gray GM (1, 3) model. The predicted values are used as input samples of a combined model, the actual values are used as output samples, the RBF neural network model is used for combining the predicted values and the actual values by adopting a difference value combination method, and the RBF neural network is trained to simulate the deviation relation between the predicted values and the actual values and the mutual relation between sequences.
Step 2, training a grey radial basis GM-RBF neural network prediction model until the grey radial basis GM-RBF neural network prediction model can accurately predict the running state of the forklift;
the learning training of the GM-RBF neural network prediction model comprises the following steps:
2.1, performing three-order discrete wavelet transform on the lateral acceleration, load and roll angle data of the forklift acquired by the sensor by adopting a Mallet algorithm, and repeatedly decomposing for three times to finally obtain useful characteristics of impurity signals removed;
the formula of the Mallet algorithm is as follows:
whereinFor the input signal, j is the decomposition scale, h k And g k Are the coefficients of the low-pass and high-pass filters,is j th The low-frequency smooth component at the scale,is j th High frequency detail components on a scale. The original signalThe low frequency smooth component and the high frequency detailed component are decomposed, and then the low frequency smooth component here is taken as a signal of the next decomposition. Repeatedly decomposing for three times to obtainThe signal decomposition process is shown in fig. 3 using a model characterized by the removal of the contaminant signal. After wavelet transformation, clutter interference signals are removed, and compared with original signals, the clutter interference signals are smoother and higher in accuracy.
And 2.2, performing data normalization, and replacing the original data by dividing the difference between the original data and the mean value of the original data by the standard deviation.
Z-score is a common normalization method, which reflects the relative standard distance between data and a mean value, eliminates the influence of different dimensions, and ensures comparability between data. The calculation formula is as follows:
wherein x is original data;σ is the standard deviation of the raw data, which is the mean of the raw data.
And 2.3, randomly dividing the processed data into two types, wherein one type accounts for 80% of the total number and is used for training a GM-RBF model to evaluate the rollover risk of the forklift, and the other type accounts for 20% of the total number and is used for verifying the accuracy. The accuracy of both the model training set and the verification set exceeds 80%, which shows that the model has better prediction effect, and the model training result is shown in fig. 4
Step 3, acquiring and processing real-time driving parameters of the forklift, inputting the processed real-time driving parameters of the forklift into the trained gray radial basis GM-RBF neural network prediction model in the step 2, and outputting forklift state signals after model processing, wherein the forklift state is divided into a safe state, a dangerous state and a destabilization state, and the forklift state division comprises the following steps:
step 3.1, acquiring real-time data of lateral acceleration, load and roll angle of the forklift and inputting the data into the established GM-RBF neural network combined prediction model;
step 3.2, the output of the combined prediction model through the GM-RBF neural network belongs to the element of Y [0,1];
3.3, dividing the state of the forklift according to the output value of the model, defining the state as a safe state when the output value is 0, defining the state as a dangerous state when the output value is 0-1, and defining the state as a destabilization state when the output value is 1; a schematic diagram of the error of the GM-RBF neural network recognition training is shown in FIG. 5.
And 4, carrying out state control on the forklift according to the forklift state signal output in the step 3.
The step 4 of controlling the state of the forklift comprises the following steps:
step 4.1, acquiring the state of the forklift, and executing step 4.2 if the forklift is in a safe state; if the forklift is in a dangerous state, executing the step 4.3, and if the forklift is in a destabilizing state, executing the step 4.4;
4.2, when the forklift is in a safe state, the electromagnetic valve is fully opened, and the oil cylinder can move freely, so that the forklift can freely rotate with the rear axle, and the forklift does not have strong bumping feeling when encountering an uneven road surface;
4.3, when the forklift is in a dangerous state, adjusting the supporting force of the hydraulic oil cylinder based on self-optimizing fuzzy control at the moment, and avoiding the forklift from deteriorating to a destabilizing state as much as possible, specifically performing the following processes:
in order to control the solenoid valve to regulate the efficient operation of the lateral force of the cylinder, the solenoid valve must operate at an optimal point throughout the process. However, since the optimal point changes with the change of the operating condition and the mathematical model of the operation of the solenoid valve cannot be accurately established, the solenoid valve opening degree set value f s It is difficult to determine in a timely manner. In order to enable the electromagnetic valve to be always in the optimal state, a self-optimization algorithm for adjusting the lateral force of the oil cylinder by the electromagnetic valve is provided.
The self-optimization algorithm increases f at the beginning of each self-optimization cycle s And the fuzzy logic controller controls the electromagnetic valve to stably work at a set value. When the system is stable, the algorithm judges whether the current set value is the optimal point according to the change of v. If not, f s Will increase (or decrease) in the next self-optimization cycle. Finally, an optimum point can be found. For example, let the set value be f in the last self-optimization cycle s 1 . At the beginning of the next cycle, f s 1 +Δf s =f s 2 。f s 2 Is a set value of the current period, Δ f s Is a fixed self-optimization step. When the control device is stable, if v increases from the previous period, f s 2 Will increase by Δ f s In the next self-optimization cycle. If v decreases in the next self-optimization cycle, then f s 2 The optimal point is; otherwise, the set value is increased again by Δ f s . However, considering the stability and large delay of the system, the self-optimization period must be set longer;
and 4.4, when the forklift is in a destabilizing state, fully closing the electromagnetic valve, and directly locking the oil cylinder, so that the forklift body is fixedly connected with the rear axle, the stable area of the forklift is enlarged, the rollover-preventing torque of the forklift is greatly increased, and the stability of the forklift is improved.
In conclusion, the invention provides a method for controlling rollover prevention of a balance weight type forklift based on a GM-RBF neural network, which can divide the motion state of the forklift according to the GM-RBF neural network, adjust the valves of hydraulic oil cylinders in different motion states, optimize the rollover prevention control of the balance weight type forklift, do not greatly change the structure of the balance weight type forklift, are simple and convenient, do not influence the normal operation of the balance weight type forklift, and can effectively improve the working efficiency of the balance weight type forklift, and the structural application schematic diagram of a GM-RBF neural network prediction model system is shown in FIG. 7.
According to the method, a gray radial basis GM-RBF neural network prediction model is established, lateral acceleration, load and roll angle of forklift motion data are obtained through a sensor, a GM-RBF neural network combination model is input for training, the model can accurately predict the running state of the forklift, the forklift state is divided into a safety state, a dangerous state and a destabilization state, the hydraulic oil cylinder is controlled in a grading manner according to different forklift stability states, and the stability of the forklift is improved. The invention can accurately judge the stability state of the forklift, improve the running posture of the forklift and improve the stability of the forklift.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (7)
1. A forklift data drive stability control method is characterized by comprising the following steps:
step 1, acquiring forklift running state parameters, and establishing a forklift state prediction model according to acquired parameter data, wherein the forklift state prediction model is a gray radial basis GM-RBF neural network prediction model;
step 2, training a grey radial basis GM-RBF neural network prediction model until the grey radial basis GM-RBF neural network prediction model can accurately predict the running state of the forklift;
step 3, acquiring and processing real-time driving parameters of the forklift, inputting the processed real-time driving parameters of the forklift into the trained gray radial basis GM-RBF neural network prediction model in the step 2, and then outputting forklift state signals after model processing;
and 4, carrying out state control on the forklift according to the forklift state signal output in the step 3.
2. The method for controlling the stability of the data drive of the forklift according to claim 1, wherein the driving state parameters of the forklift in the step 1 comprise the lateral acceleration, the load and the roll angle of the forklift.
3. The data driving stability control method for forklift according to claim 1, it is characterized in that the preparation method is characterized in that, the establishment of the grey radial basis GM-RBF neural network prediction model in the step 1 comprises the following steps:
step 1.1, acquiring lateral acceleration, load and roll angle data through a sensor arranged on a forklift;
step 1.2, processing the data by using a GM (1, 3) gray model, weakening the random factors of the data, and finding out the dynamic relation of the internal time among the data;
step 1.3, processing the data by using an RBF neural network;
step 1.4, a series-connection type gray neural network model is adopted, different data are taken from the same sequence to obtain different prediction results, then, RBF neural networks are used for combining a plurality of gray prediction results, a series of prediction values are obtained after a plurality of sequences of forklift motion are predicted by using a gray GM (1, 3) model, the prediction values are used as combination model input samples, actual values are used as output samples, a difference value combination method is adopted, the RBF neural network model is used for combining the prediction values and the actual values, and the RBF neural network is trained to simulate the deviation relation between the prediction values and the actual values and the mutual relation between the sequences.
4. The method for controlling the stability of the data driving of the forklift as recited in claim 1, wherein the training process of the gray radial basis GM-RBF neural network prediction model in the step 2 comprises the following steps:
2.1, performing three-order discrete wavelet transform on the lateral acceleration, load and roll angle data of the forklift acquired by the sensor by adopting a Mallet algorithm, and repeatedly decomposing for three times to finally obtain useful characteristics of impurity signals removed;
step 2.2, carrying out data normalization, and replacing the original data by dividing the difference between the original data and the mean value thereof by the standard deviation;
and 2.3, randomly dividing the processed data into two types, wherein 80% of the total amount of one type is used for training a GM-RBF model to evaluate the rollover risk of the forklift, and 20% of the total amount of the other type is used for verifying the accuracy.
5. The method for controlling the data driving stability of the forklift according to claim 4, wherein when the accuracy of the training set and the validation set of the gray radial basis GM-RBF neural network prediction model is not less than 80%, it is determined that the gray radial basis GM-RBF neural network prediction model can accurately predict the driving state of the forklift.
6. The data drive stability control method for the forklift as claimed in claim 1, wherein the forklift state is divided into a safe state, a dangerous state and a destabilizing state, and the forklift state division comprises the following steps:
step 3.1, acquiring real-time data of lateral acceleration, load and roll angle of the forklift and inputting the data into the established GM-RBF neural network combined prediction model;
step 3.2, the output of the combined prediction model through the GM-RBF neural network is Y ∈ [0,1];
and 3.3, dividing the state of the forklift according to the output value of the model, defining the state as a safe state when the output value is 0, defining the state as a dangerous state when the output value is 0-1, and defining the state as a destabilization state when the output value is 1.
7. The method for controlling the stability of the data driving of the forklift according to claim 6, wherein the step 4 of controlling the state of the forklift comprises the following steps:
step 4.1, acquiring the state of the forklift, and executing step 4.2 if the forklift is in a safe state; if the forklift is in a dangerous state, executing the step 4.3, and if the forklift is in a destabilizing state, executing the step 4.4;
4.2, when the forklift is in a safe state, fully opening the electromagnetic valve, enabling the oil cylinder to move freely, and enabling the forklift body and the rear axle to rotate freely;
4.3, when the forklift is in a dangerous state, adjusting the lateral force of the hydraulic oil cylinder based on self-optimizing fuzzy control at the moment, and avoiding the forklift from deteriorating to a destabilization state as much as possible;
and 4.4, when the forklift is in a destabilizing state, fully closing the electromagnetic valve, directly locking the oil cylinder, fixedly connecting the forklift body and the rear axle, expanding the stable area of the forklift, increasing the rollover-preventing torque of the forklift and improving the stability of the forklift.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210528993.4A CN115140685B (en) | 2022-05-16 | 2022-05-16 | Forklift data driving stability control method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210528993.4A CN115140685B (en) | 2022-05-16 | 2022-05-16 | Forklift data driving stability control method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115140685A true CN115140685A (en) | 2022-10-04 |
CN115140685B CN115140685B (en) | 2024-02-13 |
Family
ID=83406726
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210528993.4A Active CN115140685B (en) | 2022-05-16 | 2022-05-16 | Forklift data driving stability control method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115140685B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117842909A (en) * | 2024-03-08 | 2024-04-09 | 美通重工有限公司 | Automatic leveling method and system for high-altitude vehicle platform |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104270281A (en) * | 2014-09-03 | 2015-01-07 | 河海大学 | Web Service QoS (Quality of Service) combined forecasting method |
CN104573170A (en) * | 2014-10-13 | 2015-04-29 | 芜湖扬宇机电技术开发有限公司 | Method for determining initial pressure of optimal operation of steam turbine |
CN107368928A (en) * | 2017-08-03 | 2017-11-21 | 西安科技大学 | A kind of combination forecasting method and system of ancient building sedimentation |
CN111143989A (en) * | 2019-12-25 | 2020-05-12 | 北京无线电计量测试研究所 | Frequency adjustment amount calculation method, module, system, storage medium, and device |
DE102019113765A1 (en) * | 2019-05-23 | 2020-11-26 | Jungheinrich Ag | Method for controlling a hydraulic system of a mobile work machine and mobile work machine |
-
2022
- 2022-05-16 CN CN202210528993.4A patent/CN115140685B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104270281A (en) * | 2014-09-03 | 2015-01-07 | 河海大学 | Web Service QoS (Quality of Service) combined forecasting method |
CN104573170A (en) * | 2014-10-13 | 2015-04-29 | 芜湖扬宇机电技术开发有限公司 | Method for determining initial pressure of optimal operation of steam turbine |
CN107368928A (en) * | 2017-08-03 | 2017-11-21 | 西安科技大学 | A kind of combination forecasting method and system of ancient building sedimentation |
DE102019113765A1 (en) * | 2019-05-23 | 2020-11-26 | Jungheinrich Ag | Method for controlling a hydraulic system of a mobile work machine and mobile work machine |
CN111143989A (en) * | 2019-12-25 | 2020-05-12 | 北京无线电计量测试研究所 | Frequency adjustment amount calculation method, module, system, storage medium, and device |
Non-Patent Citations (1)
Title |
---|
夏光 等: ""平衡重式叉车防侧翻分层控制研究"", 中国机械工, vol. 30, no. 17, pages 2066 - 2075 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117842909A (en) * | 2024-03-08 | 2024-04-09 | 美通重工有限公司 | Automatic leveling method and system for high-altitude vehicle platform |
Also Published As
Publication number | Publication date |
---|---|
CN115140685B (en) | 2024-02-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Lin et al. | Enhanced fuzzy sliding mode controller for active suspension systems | |
Guvenc et al. | Robust two degree-of-freedom vehicle steering controller design | |
CN105159094B (en) | The design method of vehicle active suspension LQG controller Optimal Control Forces | |
Soleymani et al. | Adaptive fuzzy controller for vehicle active suspension system based on traffic conditions | |
Gobbi et al. | Optimising a car chassis | |
CN110386191B (en) | Electro-hydraulic intelligent steering system performance monitor and performance optimization method | |
CN110497916B (en) | Automobile driving state estimation method based on BP neural network | |
CN109002599B (en) | Automobile ride comfort optimization analysis method based on Taguchi experiment | |
CN115140685A (en) | Forklift data driving stability control method | |
Robert et al. | Fuzzy control of active suspension system based on quarter car model | |
CN109398020B (en) | Nonlinear model-based prediction control method for vehicle hydro-electric coupling type ISD suspension | |
CN109910863A (en) | A kind of control method based on plug-in hybrid car dedicated transmission | |
Shi et al. | Double-layer dynamic decoupling control system for the yaw stability of four wheel steering vehicle | |
CN112776551A (en) | Motion diagram based semi-active control method and system for magneto-rheological suspension | |
Liu et al. | Vehicle state estimation based on unscented Kalman filtering and a genetic-particle swarm algorithm | |
Niasar et al. | Yaw moment control via emotional adaptive neuro-fuzzy controller for independent rear wheel drives of an electric vehicle | |
CN114590090A (en) | Direct-drive semi-active suspension control system construction method based on self-adaptive LQR (Low-speed response) wheel hub | |
Senthil et al. | Optimal preview control of a two-dof vehicle model using stochastic optimal control theory | |
Lin et al. | DSP-based self-organising fuzzy controller for active suspension systems | |
Arslan et al. | Quarter Car Active Suspension System Control Using Fuzzy Controller | |
CN113705865B (en) | Automobile stability factor prediction method based on deep neural network | |
CN116373846A (en) | Back wheel steering vehicle stability control method based on BP neural network optimization | |
Feng et al. | Bandwidth-limited active suspension controller for an off-road vehicle based on co-simulation technology | |
CN110329028B (en) | Hybrid electromagnetic suspension mode switching system and method based on highway grade recognition | |
Vu et al. | Optimal selection of weighting functions by genetic algorithms to design H∞ anti-roll bar controllers for heavy vehicles |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |