Adaptive cooperative control strategy based on variable speed reaching law and neural network

Abstract

The invention discloses a self-adaptive cooperative control strategy based on a variable speed reaching law and a neural network, belongs to the field of intelligent control, and mainly aims at estimating and compensating uncertainty, external disturbance and actuator saturation existing in a queue in queue control and improving the stability, robustness and control performance of the whole queue. The method comprises the following steps: establishing a queue system model with uncertainty, external disturbance and actuator saturation; establishing a Gaussian error function approximation strategy; establishing a tracking error; establishing a variable speed reaching law; establishing a queue integral sliding mode error; establishing a queue coupling sliding mode error; establishing an adaptive parameter estimation mechanism for external disturbance and Gaussian function approximation errors in the queue; establishing a neural network estimation mechanism for uncertainty in the queue; and establishing a queue integral sliding mode control strategy based on a variable speed reaching law, a Gaussian error function approximation strategy, an adaptive parameter estimation mechanism and a neural network estimation mechanism. The method is used for queue cooperative intelligent control.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent control, and mainly relates to an adaptive collaborative control strategy based on a variable speed reaching law and a neural network. Background Art

[0002] In today's transportation system, traffic congestion, energy consumption, and environmental pollution are becoming increasingly serious, posing a significant challenge to the efficiency and sustainability of transportation systems. Platoon cooperative control technology, as a key component of intelligent transportation systems, aims to improve traffic flow, enhance traffic safety, and reduce energy consumption by coordinating vehicle driving states. This technology plays a significant role in alleviating traffic pressure and improving the environment. However, existing platoon cooperative control methods still have limitations in practical applications. First, platoon systems contain a large amount of uncertainty and external disturbances, such as changes in vehicle dynamics, fluctuations in road conditions, and the randomness of traffic flow. These factors can severely impact platoon stability and control performance. Second, actuator saturation is also common in practical systems, limiting the range of control inputs and further increasing the complexity of platoon control. Furthermore, existing platoon disturbance observation techniques often require prior knowledge of the disturbance boundary or a precise system model, which is often difficult to achieve in practical applications, limiting their applicability and effectiveness. In summary, to meet the higher standards and requirements for platoon cooperative control in intelligent systems, existing platoon cooperative control methods need further improvement and refinement. Summary of the Invention

[0003] The purpose of this invention is to address the problem in platoon cooperative control that uncertainty, external disturbances, and actuator saturation can lead to actual system performance degradation and even system instability. This invention provides an adaptive cooperative control strategy based on a variable speed reaching law and a neural network.

[0004] An adaptive cooperative control strategy based on a variable speed reaching law and a neural network is characterized by being able to estimate and compensate for uncertainties, external disturbances, and actuator saturation in the queue, thereby improving the stability, robustness, and control performance of the entire queue. The control strategy includes the following steps:

[0005] Step 1: Establish a queue system model with uncertainty, external disturbances, and actuator saturation:

[0006] Queue system model

[0007] (1)

[0008] in, is the serial number, and Representing the The position and velocity of each agent, Indicates time, represents the saturation function, represents a column vector containing position, velocity and time, is the uncertainty and external disturbance to the system, is the control input.

[0009] Step 2: Establish a Gaussian error function approximation strategy:

[0010] Gaussian error function approximation strategy

[0011] (2)

[0012] in, , represents the Gaussian error function approximation error.

[0013] Step 3: Establish tracking error:

[0014] Tracking Error

[0015] (3)

[0016] in, represents the tracking error of the position, and is an intermediate variable, is the adjacent spacing of agents, is the safe distance when stationary, represents a natural constant, Indicates the headway time, Indicates the speed of the navigator, represents the velocity tracking error, , , express The limit value approaches 0, .

[0017] Step 4: Establish the speed reaching law:

[0018] Speed reaching law

[0019] (4)

[0020] in, is the sliding mode error, and are all normal numbers, is the absolute value, is the hyperbolic tangent function.

[0021] Step 5: Establish queue integral sliding mode error:

[0022] Sliding mode error

[0023] (5)

[0024] in, is the sliding mode error, Represents time from 0 to time The points, is the integration variable, , , .

[0025] Step 6: Establish queue coupling sliding mode error:

[0026] Coupled sliding mode error

[0027] (6)

[0028] in, is the coupled sliding mode error, , is the number of agents.

[0029] Step 7: Establish an adaptive parameter estimation mechanism for external disturbances in the queue and Gaussian function approximation errors:

[0030] Adaptive parameter estimation mechanism

[0031] (7)

[0032] in, , , and is a constant greater than zero, and They are and estimated value.

[0033] Step 8: Establish a neural network estimation mechanism for uncertainty in the queue:

[0034] Neural network estimation mechanism

[0035] (8)

[0036] in, activation function, is the ideal weight, is the approximation error of the neural network, and is a constant greater than zero, yes estimated value.

[0037] Step 9: Establish a queue integral sliding mode control strategy based on the variable speed reaching law, Gaussian error function approximation strategy, adaptive parameter estimation mechanism and neural network estimation mechanism:

[0038] Queue Control Law

[0039] (9)

[0040] in, .

[0041] The beneficial effect of this invention is that it effectively solves the problem of actual system performance degradation and even system instability caused by uncertainty, external disturbances, and actuator saturation in platoon cooperative control. Utilizing this invention, the internal stability and queue stability of the entire platoon can be ensured, improving system robustness and control performance, increasing traffic flow, enhancing platoon safety, and reducing energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 Schematic diagram of the control method described in the first embodiment DETAILED DESCRIPTION

[0043] Specific implementation method 1: Combination Figure 1 This embodiment describes an adaptive collaborative control strategy based on a speed reaching law and a neural network. The control strategy includes the following steps:

[0044] Step 1: Establish a queue system model with uncertainty, external disturbances, and actuator saturation:

[0045] Queue system model

[0046] (1)

[0047] in, is the serial number, and Representing the The position and velocity of each agent, Indicates time, represents the saturation function, represents a column vector containing position, velocity and time, is the uncertainty and external disturbance to the system, is the control input.

[0048] Step 2: Establish a Gaussian error function approximation strategy:

[0049] Gaussian error function approximation strategy

[0050] (2)

[0051] in, , represents the Gaussian error function approximation error.

[0052] Step 3: Establish tracking error:

[0053] Tracking Error

[0054] (3)

[0055] in, represents the tracking error of the position, and is an intermediate variable, is the adjacent distance between agents, is the safe distance when stationary, represents a natural constant, Indicates the headway time, Indicates the speed of the navigator, represents the velocity tracking error, , , express The limit value tends to 0, .

[0056] Step 4: Establish the speed reaching law:

[0057] Speed reaching law

[0058] (4)

[0059] in, is the sliding mode error, and are all normal numbers, is the absolute value, is the hyperbolic tangent function.

[0060] Step 5: Establish queue integral sliding mode error:

[0061] Sliding mode error

[0062] (5)

[0063] in, is the sliding mode error, Represents time from 0 to time The points, is the integration variable, , , .

[0064] Step 6: Establish queue coupling sliding mode error:

[0065] Coupled sliding mode error

[0066] (6)

[0067] in, is the coupled sliding mode error, , is the number of agents.

[0068] Step 7: Establish an adaptive parameter estimation mechanism for external disturbances in the queue and Gaussian function approximation errors:

[0069] Adaptive parameter estimation mechanism

[0070] (7)

[0071] in, , , and is a constant greater than zero, and They are and estimated value.

[0072] Step 8: Establish a neural network estimation mechanism for uncertainty in the queue:

[0073] Neural network estimation mechanism

[0074] (8)

[0075] in, activation function, is the ideal weight, is the approximation error of the neural network, and is a constant greater than zero, yes estimated value.

[0076] Step 9: Establish a queue integral sliding mode control strategy based on the variable speed reaching law, Gaussian error function approximation strategy, adaptive parameter estimation mechanism and neural network estimation mechanism:

[0077] Queue Control Law

[0078] (9)

[0079] in, .

[0080] Effects of this implementation:

[0081] The proposed strategy effectively addresses the issues of performance degradation and even system instability caused by uncertainty, external disturbances, and actuator saturation in platoon cooperative control. This approach ensures both internal and platoon stability, improves system robustness and control performance, increases traffic flow, enhances platoon safety, and reduces energy consumption.

Claims

1. An adaptive cooperative control strategy based on variable speed reaching law and neural network, characterized by The control strategy can estimate and compensate for the uncertainty, external disturbance and actuator saturation in the queue control, thereby improving the stability, robustness and control performance of the entire queue. The control strategy includes the following steps: Step 1: Establish a queue system model with uncertainty, external disturbances and actuator saturation; Step 2: Establish a Gaussian error function approximation strategy; Step 3: Establish tracking error; Step 4: Establish the speed reaching law; Step 5: Establish queue integral sliding mode error; Step 6: Establish queue coupling sliding mode error; Step 7: Establish an adaptive parameter estimation mechanism for external disturbances in the queue and Gaussian function approximation errors; Step 8: Establish a neural network estimation mechanism for uncertainty in the queue; Step 9: Establish a queue integral sliding mode control strategy based on the variable speed reaching law, Gaussian error function approximation strategy, adaptive parameter estimation mechanism and neural network estimation mechanism.

2. An adaptive cooperative control strategy based on speed reaching law and neural network according to claim 1, characterized in that: In the step 1, Queue system model (1) in, is the serial number, and Representing the The position and velocity of each agent, Indicates time, represents the saturation function, represents a column vector containing position, velocity and time, is the uncertainty and external disturbance to the system, is the control input.

3. An adaptive cooperative control strategy based on speed reaching law and neural network according to claim 1, characterized in that: In the step 2, Gaussian error function approximation strategy (2) in, , represents the Gaussian error function approximation error.

4. An adaptive cooperative control strategy based on speed reaching law and neural network according to claim 1, characterized in that: In the step three, Tracking Error (3) in, represents the tracking error of the position, and is an intermediate variable, is the adjacent distance between agents, is the safe distance when stationary, represents a natural constant, Indicates the headway time, Indicates the speed of the navigator, represents the velocity tracking error, , , express The limit value tends to 0, .

5. An adaptive cooperative control strategy based on speed reaching law and neural network according to claim 1, characterized in that: In the step 4, Speed reaching law (4) in, is the sliding mode error, and are all normal numbers, is the absolute value, is the hyperbolic tangent function.

6. An adaptive cooperative control strategy based on speed reaching law and neural network according to claim 1, characterized in that: In the step five, Sliding mode error (5) in, is the sliding mode error, Represents the time from time 0 to time The points, is the integration variable, , , .

7. An adaptive cooperative control strategy based on speed reaching law and neural network according to claim 1, characterized in that: In the step six, Coupled sliding mode error (6) in, is the coupled sliding mode error, , is the number of agents.

8. An adaptive cooperative control strategy based on speed reaching law and neural network according to claim 1, characterized in that: In the step seven, Adaptive parameter estimation mechanism (7) in, , , and is a constant greater than zero, and They are and estimated value.

9. An adaptive cooperative control strategy based on speed reaching law and neural network according to claim 1, characterized in that: In the step eight, Neural network estimation mechanism (8) in, activation function, is the ideal weight, is the approximation error of the neural network, and is a constant greater than zero, yes estimated value.

10. An adaptive cooperative control strategy based on speed reaching law and neural network according to claim 1, characterized in that: In the step nine, Queue Control Law (9) in, .

Images