CN115649240B - Online real-time optimization multi-train cooperative cruise control method and system - Google Patents
Online real-time optimization multi-train cooperative cruise control method and system Download PDFInfo
- Publication number
- CN115649240B CN115649240B CN202211702024.2A CN202211702024A CN115649240B CN 115649240 B CN115649240 B CN 115649240B CN 202211702024 A CN202211702024 A CN 202211702024A CN 115649240 B CN115649240 B CN 115649240B
- Authority
- CN
- China
- Prior art keywords
- train
- time
- varying
- gain
- cooperative control
- 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.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention discloses an online real-time optimization multi-train cooperative cruise control method and system, wherein the method comprises the following steps: calculating the distance deviation and the speed deviation between each train and the adjacent train; introducing time-varying cooperative control gain to construct an optimal cooperative control law; calculating the optimal cooperative control gain of the current state by a cuckoo search algorithm by taking the minimum distance and the speed deviation as targets; and then, a sample data set corresponding to the distance and speed deviation state and the optimal control gain is constructed through multiple sampling calculations and used for training a neural network, and the optimal cooperative control gain is obtained on line in real time through the neural network during actual running of multiple trains. According to the method, the time-varying cooperative control gain is designed, the multi-train cooperative control law is optimized on line in real time according to the state change, the train is enabled to be stabilized to a consistent state at the highest speed, the convergence speed of multi-train cooperative cruise is improved, the instantaneous overshoot is reduced, and the requirement of safe and efficient operation of the train is met.
Description
Technical Field
The invention belongs to the technical field of intelligent operation control of rail transit trains, and particularly relates to a control method and a system for optimizing multi-train cooperative cruise control in real time on line.
Background
Under the support of the railway construction development policy, the tasks of passenger transportation and cargo transportation borne by railways are increasingly heavy, and the carrying capacity faces more and more serious examination. In recent years, railway transportation pressure is relieved to a certain extent by means of railway building, station crossing building, line rewiring and the like. However, the problem of operational energy shortage still exists.
The multi-train cooperative cruise control strategy is an effective method for solving the increasingly heavy railway transportation pressure. The research on the multi-train cooperative cruise control is abundant at home and abroad. However, since the multi-train cooperative operation process is in dynamic adjustment, the control performance requirements of each stage are different, most cooperative cruise control methods adopt fixed cooperative control gain, are not adaptive, are difficult to achieve optimal control effect, cause large overshoot and fluctuation adjustment, and have slow convergence speed. Therefore, the gain coefficient development real-time optimization aiming at the cooperative control strategy plays an important role in improving the overall control performance of the multi-train cruise system. However, most of the existing optimization solving methods are low in convergence speed and time-consuming, and are difficult to operate on line in a multi-train cruise-coordinated real-time control system.
Disclosure of Invention
The invention aims to solve the technical problems of fixed cooperative control gain and low optimal value solving efficiency in the conventional multi-train cooperative optimal control method, and further provides a multi-train cooperative cruise control method and system for online real-time optimization. The existing multi-train cooperative control strategy has the technical defects that the control gain is not optimal and is fixed, or the existing multi-train cooperative control strategy solves a fixed optimal value by using an off-line optimization algorithm, so that the convergence speed is low, the instantaneous overshoot in the convergence process is large, and the safety range is easily exceeded. The control method provided by the technical scheme of the invention truly realizes the multi-train cooperative cruise online optimization control technology running on a real-time train running control system, wherein the time-varying cooperative control gain is adjusted in real time along with the state change, so that train workshops are enabled to be stabilized to a consistent running state at the highest speed, the convergence speed of multi-train cooperative cruise is increased, the instantaneous overshoot is reduced, and the requirement of safe and efficient running of trains is met.
On one hand, the invention provides an online real-time optimization multi-train cooperative cruise control method, which comprises the following steps:
step 1: acquiring real-time running information and position information of a train;
and 2, step: introducing time-varying cooperative control gain, and constructing a time-varying cooperative control law based on distance deviation and speed deviation; the time-varying cooperative control gain comprises a distance deviation gain and a speed deviation gain, and values of the distance deviation gain and the speed deviation gain are dynamically changed; the distance deviation represents the deviation between the actual distance between the two communication trains and the expected safe distance, and the speed deviation represents the real-time speed deviation between the two communication trains;
and 3, step 3: inputting the real-time distance deviation and speed deviation of the train into a trained neural network to obtain real-time globally optimal time-varying cooperative control gain;
the input of the neural network is the distance deviation and the speed deviation of the train, and the output is the globally optimal time-varying cooperative control gain;
and 4, step 4: obtaining the time-varying cooperative control law based on the globally optimal time-varying cooperative control gain, and generating traction or braking force by using a traction braking system of the train based on the time-varying cooperative control law so as to control the acceleration change of each train; wherein the time-varying cooperative control law is specifically represented as traction or braking force applied to the train.
The invention carries out further research aiming at the problem of multi-train collaborative optimal control, optimizes collaborative control gain on line according to state change, improves timeliness, improves the convergence speed of multi-train collaborative cruise on the premise of ensuring safe operation of trains, and reduces instantaneous overshoot so as to improve the overall operation efficiency of railways.
Specifically, according to the technical scheme of the multi-train cooperative cruise control method provided by the invention, the time-varying cooperative control law based on the distance deviation and the speed deviation is constructed by introducing the time-varying cooperative control gain, so that the dynamically-changing time-varying cooperative control gain is introduced into the control system of the train, the optimal time-varying cooperative control law changing along with the state can be obtained, the distance and the speed deviation are reduced at the highest speed, the overshoot is reduced at the same time, and the coordinated and consistent adjustment time of the multi-train is shortened on the premise of ensuring the running safety of the train. In addition, the technical scheme of the invention introduces the neural network, and the trained neural network can be used for solving the globally optimal time-varying cooperative control gain under different states at different moments, so that the defects of low convergence speed and difficulty in online real-time operation of the conventional multi-train cooperative cruise control optimization method (intelligent heuristic algorithms such as cuckoo algorithm, genetic algorithm, gene evolution algorithm and the like) are solved. In conclusion, the technical scheme provided by the invention can solve the optimal cooperative control gain on line in real time, shorten the cooperative convergence process, reduce the overshoot range and improve the overall operation efficiency of the railway. It should be understood that, in the embodiment of the present invention, a BP neural network is used, and in other possible embodiments, other types of neural networks with a prediction function may be selected, which is not specifically limited by the present invention.
Further optionally, the time-varying cooperative control law constructed in step 2 is expressed as:
wherein, the first and the second end of the pipe are connected with each other,u i (t) Representing trainsiThe traction or braking force experienced;k 1 (t)、k 2 (t) Time-varying cooperative control gains to be determined respectively correspond to the distance deviation gain and the speed deviation gain;a ij for trainsiWith trainsjThe communication relation coefficient of (a), if there is a communication,a ij is 1, otherwisea ij Is 0, and
，v i (t)、v j (t) Respectively representing trainsi、Train with wheelsjReal-time speed of (d);x i (t)、x j (t) Respectively representing trainsi、Train with movable trackjThe real-time location of the mobile station,nfor the total number of trains in the multi-train cooperation system,dfor a given desired safety distance between the two cars,trepresenting time.
Further optionally, the neural network in step 3 is trained based on a training set, where the training set is formed by distance deviation and speed deviation obtained through multiple state sampling and corresponding globally optimal time-varying cooperative control gain;
after the distance deviation and the speed deviation obtained through state sampling each time, calculating by using a cuckoo search algorithm to obtain a globally optimal time-varying cooperative control gain, specifically as follows:
step 3.1: initiation ofAnd (3) chemically setting relevant parameters of the cuckoo search algorithm: total number of bird nestsMFinding probability P ∈ [0,1 ]]Maximum number of iterationsNAnd correspond ton 1 Initial population of cuckoo
，
，X 1 ,X 2 ,
Respectively represent the 1 st, the 2 nd and the 2 ndn 1 The position of a bird nest found by each cuckoo,
、
respectively representn 1 Distance deviation gain and speed deviation gain corresponding to the position of the bird nest found by each cuckoo,n 1 the number of cuckoo;
step 3.2: updating the position of each bird nest in the population according to the following rules;
calculating an objective function value after the new bird nest position is reached through the Laevir flight, comparing the objective function value with an objective function value of a previous generation bird nest position, replacing and updating the bird nest position if the objective function value is reduced, and keeping the original bird nest position unchanged if the objective function value is not reduced; the formula of the lewy flight is as follows:
in the formula (I), the compound is shown in the specification,αin order to be the step size,levy(β) In order to be a lavi random path,Tin response to the number of iterations,X i (T)、X i (T-1) representing the nest positions found by the ith cuckoo in the Tth iteration and the T-1 st iteration respectively;
step 3.3: after obtaining the nest position of a new population, randomly generating a numerical value R which is uniformly distributed according to 0 to 1, comparing the numerical value R with a discovery probability P, if R is greater than P, randomly updating the nest position once, then calculating an updated objective function value of the nest position, if the objective function value is smaller, replacing and updating the original nest position, otherwise, keeping the original nest position; if R is less than or equal to P, keeping the current bird nest position;
step 3.4: finding out the optimal positions of all current bird nests, wherein the bird nest position corresponding to the minimum objective function value is the optimal position;
step 3.5: judging whether the maximum iteration times are reached, if so, outputting an optimal position to obtain a distance deviation gain and a speed deviation gain in the globally optimal time-varying cooperative control gain corresponding to the substituted current state sample; if the maximum iteration times are not reached, the step 3.2-3.5 is circulated until the maximum iteration times are reached;
and (3) circularly and repeatedly carrying out the steps 3.1-3.5, and substituting all the state samples to obtain the global optimal cooperative gain corresponding to different state samples so as to construct the training set.
According to the technical scheme, the cuckoo search algorithm is used for constructing the training set, and the time-varying cooperative control gain corresponding to each training sample in the training set is further ensured to be the globally optimal time-varying cooperative control gain, so that the precision of a neural network is higher, the control effect of a multi-train system control system is better, and the control efficiency is better.
Further optionally, the formula of the objective function is:
in the formula (I), the compound is shown in the specification,Jin order to be said objective function, the method comprises the steps of,u i (t) Representing the traction or braking force borne by the train i, and correspondingly constructing a time-varying cooperative control law;a ij for trainsiAnd the trainjThe communication relationship coefficient of (c), if there is a communication,a ij is 1, otherwisea ij Is 0, and
；v i (t)、v j (t) Traffic display traini、Train with movable trackjReal-time speed of (d);x i (t)、x j (t) Respectively representing trainsi、Train with wheelsjThe real-time location of the mobile station,nfor the total number of trains in the multi-train cooperation system,dfor a given desired safety distance between the two cars,trepresenting time.
Further optionally, the neural network in the step 3 is a BP neural network, and the training step of the BP neural network is as follows:
s-1: initializing BP neural network parameters: the number of neurons in an input layer is 2, one input corresponds to a distance deviation, and the other input corresponds to a speed deviation; a hidden layer, wherein the number of the neurons of the hidden layer is an arbitrary value; the number of neurons in an output layer is 2, and the distance deviation gain and the speed deviation gain are corresponded; initializing a link weight to be any value between (0, 1);
s-2: taking a certain training sample from a training set and inputting the training sample into the BP neural network;
s-3: calculating the output of each layer of nodes in the forward direction by the BP neural network;
s-4: calculating the error of the actual output and the expected output of the BP neural network;
s-5: reversely calculating from the output layer to the first hidden layer, and adjusting each connection weight of the whole BP neural network in a direction of reducing errors by adopting a gradient descent method;
s-6: and repeating the steps S-2 to S-5 for each training sample in the training set until the error of the whole BP neural network reaches the preset requirement.
Further optionally, step 1 is that each train acquires real-time operation information and position information of itself and the communication train.
In a second aspect, the invention provides an online real-time optimization multi-train cooperative cruise control method, which is applied to a single train of a multi-train cooperative control system, and the multi-train cooperative cruise control method includes the following steps:
s1: the current train acquires real-time running information and position information of the current train and the communication train;
s2: introducing time-varying cooperative control gain, and constructing a time-varying cooperative control law based on distance deviation and speed deviation; the time-varying cooperative control gain comprises a distance deviation gain and a speed deviation gain, and numerical values dynamically change; the distance deviation represents the deviation between the actual distance between the two communication trains and the expected safe distance, and the speed deviation represents the real-time speed deviation between the two communication trains;
s3: inputting the real-time distance deviation and speed deviation of the current train into a trained neural network to obtain real-time globally optimal time-varying cooperative control gain;
s4: and obtaining the time-varying cooperative control law based on the globally optimal time-varying cooperative control gain, and controlling the acceleration change of the current train by utilizing a traction braking system of the current train based on the time-varying cooperative control law to generate traction force or braking force, wherein the time-varying cooperative control law is specifically represented as the traction force or the braking force applied to the train.
In a third aspect, the invention provides a system based on the multi-train vehicle collaborative cruise control method, which includes: the system comprises a multi-train system, an operation information acquisition subsystem, a train communication subsystem and a control subsystem;
the multi-train system consists of a plurality of trains;
the running information acquisition subsystem consists of vehicle-mounted equipment and/or trackside equipment of each train and is used for acquiring real-time running information of each train;
the train communication subsystem is composed of communication modules and/or wireless block centers of all trains and is used for constructing communication connection among the trains and realizing information transmission among the communication trains;
and the control subsystem is composed of controllers of all trains, and is used for obtaining or acquiring a time-varying cooperative control law of all trains according to the steps 2-4 or the steps S2-S4, and acting on a traction braking system of the trains to generate traction or braking force so as to control the acceleration variation of the trains.
In a fourth aspect, the present invention provides an electronic terminal, which includes:
one or more processors;
a memory storing one or more computer programs;
the processor invokes the computer program to implement:
disclosed is a method for optimizing multi-row vehicle collaborative cruise control in real time on line.
In a fifth aspect, the present invention provides a readable storage medium storing a computer program, the computer program being invoked by a processor to implement:
disclosed is a method for optimizing a multi-train cooperative cruise control method in real time on line.
Advantageous effects
According to the method for online real-time optimization of multi-train cooperative cruise control, provided by the invention, on one hand, by introducing time-varying cooperative control gain, global optimal time-varying cooperative control gain under different states at different moments can be solved by utilizing a neural network, an optimal time-varying cooperative control law changing along with the states can be obtained, the distance and the speed deviation are reduced at the highest speed, the overshoot is reduced at the same time, the adjustment time for the multi-train cooperative and consistent is reduced on the premise of ensuring the running safety of a train, and the overall operation efficiency of a railway is improved.
Secondly, in the preferred scheme of the invention, aiming at the training set of the neural network, the technical scheme of the invention is to utilize a plurality of times of sampling to construct a data set to train the neural network according to the corresponding relation of distance deviation, speed deviation and optimal cooperative control gain solved by the cuckoo algorithm, thereby further ensuring the accuracy of the globally optimal time-varying cooperative control gain.
It should be understood that the control system based on the multi-train cooperative cruise control method has good control performance, and further ensures the safety and stability of train operation. In conclusion, the strategy provided by the technical scheme of the invention can acquire the optimal value of the time-varying cooperative control gain on line in real time according to the state change, the optimal control gain is larger when the deviation of the speed and the distance is larger, the tracking convergence speed is accelerated, the optimal control gain is smaller when the deviation of the speed and the distance is smaller, the overshoot is reduced, the calculated amount is small, and the method is a control method which can really run in a real-time train running control system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a preferred embodiment of a method for optimizing multi-train cooperative cruise control on-line in real time according to the present invention;
FIG. 2 is a block diagram of a cooperative controller based on online real-time optimization according to the present invention;
fig. 3 is a flow chart of a cuckoo search algorithm provided by 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 obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Example 1:
the method aims to solve the technical problems that the cooperative control gain is fixed and unchanged and the optimal value solving efficiency is low in the conventional multi-train cooperative optimal control method, namely the technical defects that the control gain is not optimal and is fixed and unchanged in the conventional multi-train cooperative control strategy, or the conventional multi-train cooperative control strategy is to solve a fixed optimal value by using an off-line optimization algorithm, so that the convergence speed is low, the instantaneous overshoot in the convergence process is large, and the safety range is easily exceeded are overcome. The embodiment of the invention provides an online real-time optimization multi-train collaborative cruise control method, which comprises the following steps:
step 1: acquiring real-time running information and position information of a train; each train acquires real-time running position information and position information of the train and communication adjacent trains.
In this embodiment, the train acquires real-time running information of the train from the on-board device and the trackside device through the on-board communication module, communicates with the radio block center through the communication module to transmit the real-time running information and the position information of the train to the communication train in real time, and acquires the real-time running information and the position information of the communication train.
In this embodiment, only the adjacent trains are considered to be able to communicate with each other, and in other possible embodiments, the existence of communication between non-adjacent trains can also be considered.
Step 2: introducing time-varying cooperative control gain, and constructing a time-varying cooperative control law based on distance deviation and speed deviation; wherein the distance deviation represents a deviation between an actual distance between the two communicating trains and an expected safe distance, and the speed deviation represents a real-time speed deviation between the two communicating trains.
The constructed time-varying cooperative control law is expressed as:
wherein, the first and the second end of the pipe are connected with each other,u i (t) Representing trainsiThe traction or braking force experienced;k 1 (t)、k 2 (t) The time-varying cooperative control gains are to-be-determined time-varying cooperative control gains which respectively correspond to the distance deviation gain and the speed deviation gain, and the numerical values are dynamically changed, namely dynamically changed along with the change of the time state;a ij for trainsiAnd the trainjThe communication relationship coefficient of (c), if there is a communication,a ij is 1, otherwisea ij Is 0, and
；v i (t)、v j (t) Respectively representing trainsi、Train with movable trackjReal-time speed of (d);x i (t)、x j (t) Respectively representing trainsi、Train with wheelsjThe real-time location of the mobile station,nfor the total number of trains in the multi-train cooperation system,dfor a given desired safety distance between the two cars,trepresenting time.
And step 3: and inputting the real-time distance deviation and speed deviation of the train into the trained neural network to obtain the real-time globally optimal time-varying cooperative control gain.
In this embodiment, the selected neural network is a BP neural network, and the training step of the BP neural network is as follows:
s-1: initializing BP neural network parameters: the number of neurons in an input layer is 2, one input corresponds to a distance deviation, and the other input corresponds to a speed deviation; a hidden layer, wherein the number of the neurons of the hidden layer takes an arbitrary value; the number of neurons in the output layer is 2, and the corresponding distance deviation gain and the corresponding speed deviation gain are obtained; the link weight is initialized to an arbitrary value between (0, 1).
S-2: and taking a certain training sample from the training set and inputting the training sample into the BP neural network.
S-3: and calculating the output of each layer of nodes in the forward direction by the BP neural network.
S-4: and calculating the error of the actual output and the expected output of the BP neural network.
S-5: and reversely calculating from the output layer to the first hidden layer, and adjusting each connection weight of the whole BP neural network in a direction of reducing the error by adopting a gradient descent method.
S-6: and repeating the steps S-2 to S-5 for each training sample in the training set until the error of the whole BP neural network meets the preset requirement.
It should be noted that, the error formula and the gradient descent method selected in the training process of the BP neural network can refer to the prior art, and therefore, no specific constraint is imposed on them. The training set which is preferably used for training in the embodiment is composed of distance deviation and speed deviation obtained through multiple state sampling and corresponding globally optimal time-varying cooperative control gain;
after the distance deviation and the speed deviation obtained through state sampling each time, calculating by using a cuckoo search algorithm to obtain a globally optimal time-varying cooperative control gain, specifically as follows:
step 3.1: initializing and setting relevant parameters of a cuckoo search algorithm: total number of bird's nestMFinding the probability P ∈ [0,1 ]]Maximum number of iterationsNAnd correspond ton 1 Initial population of cuckoo
，
，X 1 ,X 2 ,
Respectively represent the 1 st, the 2 nd and the 2 ndn 1 The position of a bird nest found by each cuckoo,
、
respectively representn 1 Distance deviation gain and speed deviation gain corresponding to the position of the bird nest found by each cuckoo,n 1 the number of cuckoo.
Wherein, the set objective function is:
in the formula of the objective function, the first two terms are the minimum indexes of the error of the multi-row vehicle cooperative state, and the last term is the energy consumption index.
Step 3.2: updating the position of each bird nest in the population according to the following rulesX i （T）。
Wherein, the objective function value is calculated after reaching a new bird nest position through the Laevir flight, and then the objective function value is compared with the previous generation bird nest positionX i Comparing the objective function values of (T-1), if the objective function values become smaller, replacing and updating the position of the bird nest, otherwise, keeping the position of the original bird nest unchanged; the formula of the levy flight is as follows:
where α is the step size, levy (β) is the Levy random path,tcorresponding to the number of iterations.
Step 3.3: obtaining the nest position of a new populationX i (T) Thereafter, values R obeying a uniform distribution of 0 to 1 are randomly generated and compared with the probability of finding P, if R>P, then randomly updating the position of the bird nest onceX i (T) Calculating an objective function value after the bird nest position is updated, if the objective function value is smaller, replacing and updating the original bird nest position, otherwise, keeping the original bird nest position; if R is<Or = P, then the current nest position is maintained.
Step 3.4: and (5) arranging to find out the optimal position in all bird nests.
Step 3.5: judging whether the maximum iteration times is reached, if so, outputting an optimal position, and obtaining a distance deviation gain and a speed deviation gain in the globally optimal time-varying cooperative control gain corresponding to the substituted current state sampling; if the maximum number of iterations is not reached, steps 3.2-3.5 are looped until the maximum number of iterations is reached.
And (3) circularly and repeatedly carrying out the steps 3.1-3.5, and substituting all the state samples to obtain the global optimal cooperative gain corresponding to different state samples so as to construct the training set.
And 4, step 4: obtaining the time-varying cooperative control law based on the globally optimal time-varying cooperative control gain, and generating traction or braking force by using a traction braking system of the train based on the time-varying cooperative control law so as to control the acceleration change of each train; wherein, the time-varying cooperative control law is specifically represented as traction force or braking force applied to the train.
It should be noted that, in this embodiment, it is preferable that each train acquires real-time operation information and position information of itself and a communication train, so that after a globally optimal time-varying cooperative control gain is obtained, a time-varying cooperative control law is calculated, and based on the time-varying cooperative control law, a traction braking system of the train is used to generate traction force or braking force, so as to control an acceleration change of each train. In other feasible embodiments, the processing center on each train may upload the real-time operation information and the location information in a unified manner, and then the controller of each train calculates the time-varying cooperative control law, or the processing center calculates the time-varying cooperative control law. The method does not restrict how the signals of each train are transmitted, for example, the real-time running information/position information of each train can be directly fed back to other trains or fed back to the control center, and each train can directly generate a control variable of the train according to the technical idea of the invention, or the control center generates the control quantity of each train and feeds back the control quantity to each train.
Example 2:
the implementation process of embodiment 1 can be understood as an overall cooperative control method of a multi-train cooperative control system, and according to the technical idea of the present invention, the technical idea of the present invention can also be implemented at the angle of each train, that is, each train acquires its own real-time operation information and the real-time operation information and location information of the communicating train. Namely, the multi-train cooperative cruise control method comprises the following steps:
s1: the current train acquires real-time running information and position information of the current train and the communication train.
S2: introducing time-varying cooperative control gain, and constructing a time-varying cooperative control law based on distance deviation and speed deviation; the time-varying cooperative control gain comprises a distance deviation gain and a speed deviation gain, and numerical values dynamically change; the distance deviation represents a deviation between an actual distance between the two communicating trains and an expected safe distance, and the speed deviation represents a real-time speed deviation between the two communicating trains.
S3: and inputting the real-time distance deviation and speed deviation of the current train into the trained neural network to obtain the real-time globally optimal time-varying cooperative control gain.
S4: and obtaining the time-varying cooperative control law based on the globally optimal time-varying cooperative control gain, and based on the time-varying cooperative control law, generating traction or braking force by using a traction braking system of the current train to further control the acceleration change of the current train, wherein the time-varying cooperative control law is specifically represented as the traction or braking force applied to the train.
It should be understood that the specific implementation process and the optimization means can refer to the specific contents of embodiment 1, and are not described herein again.
Example 3:
the system based on the multi-row vehicle collaborative cruise control method provided by the embodiment comprises the following steps: the system comprises a multi-train system, an operation information acquisition subsystem, a train communication subsystem and a control subsystem;
the multi-train system consists of a plurality of trains; the operation information acquisition subsystem consists of vehicle-mounted equipment and/or trackside equipment of each train and is used for acquiring real-time operation information of each train; the train communication subsystem is composed of communication modules and/or wireless block centers of all trains and is used for constructing communication connection among the trains and realizing information transmission among the communication trains; the control subsystem is composed of controllers of all trains, and is used for obtaining or acquiring a time-varying cooperative control law of all trains according to the steps 2-4 or the steps S2-S4, and acting on a traction braking system of the trains to generate traction or braking force so as to control the acceleration variation of the trains.
It should be noted that, in some implementation processes, the controller of each train obtains the control variable of each train according to step 2 to step 4 or according to step S2 to step S4, and then generates the corresponding traction or braking force; in other implementation processes, the control center obtains the control variable of each train according to the steps 2 to 4 or the steps S2 to S4, and then feeds the control variable back to the controller of each train, and the control variable acts on the traction braking system of the train to generate traction or braking force.
Example 4:
the embodiment provides an electronic terminal, which includes: one or more processors; and a memory storing one or more computer programs; wherein the processor invokes the computer program to: disclosed is a method for optimizing multi-row vehicle collaborative cruise control in real time on line. The method is realized specifically as follows:
step 1: acquiring real-time running information and position information of a train;
each train acquires real-time running position information and position information of the train and communication adjacent trains;
step 2: introducing time-varying cooperative control gain, and constructing a time-varying cooperative control law based on distance deviation and speed deviation; the time-varying cooperative control gain comprises a distance deviation gain and a speed deviation gain, and numerical values dynamically change; the distance deviation represents the deviation between the actual distance between the two communication trains and the expected safe distance, and the speed deviation represents the real-time speed deviation between the two communication trains;
and step 3: inputting the real-time distance deviation and speed deviation of the train into a trained neural network to obtain real-time globally optimal time-varying cooperative control gain;
the input of the neural network is the distance deviation and the speed deviation of the train, and the output is the globally optimal time-varying cooperative control gain;
and 4, step 4: obtaining the time-varying cooperative control law based on the globally optimal time-varying cooperative control gain, and generating traction or braking force by using a traction braking system of the train based on the time-varying cooperative control law so as to control the acceleration change of each train; wherein the time-varying cooperative control law is specifically represented as traction or braking force applied to the train.
Or the specific implementation is as follows:
s1: the current train acquires real-time running information and position information of the current train and the communication train;
s2: introducing time-varying cooperative control gain, and constructing a time-varying cooperative control law based on distance deviation and speed deviation; the time-varying cooperative control gain comprises a distance deviation gain and a speed deviation gain, and values of the distance deviation gain and the speed deviation gain are dynamically changed; the distance deviation represents the deviation between the actual distance between the two communication trains and the expected safe distance, and the speed deviation represents the real-time speed deviation between the two communication trains;
s3: inputting the real-time distance deviation and speed deviation of the current train into a trained neural network to obtain real-time globally optimal time-varying cooperative control gain;
s4: and obtaining the time-varying cooperative control law based on the globally optimal time-varying cooperative control gain, and controlling the acceleration change of the current train by utilizing a traction braking system of the current train based on the time-varying cooperative control law to generate traction force or braking force, wherein the time-varying cooperative control law is specifically represented as the traction force or the braking force applied to the train.
It should be understood that the specific implementation process refers to the relevant contents of the embodiments 1-2. The electronic terminal of the embodiment may be a device installed on a train, and is used for generating a control variable of the train; or may be an external device in communication with the train for generating control variables for each train.
The terminal further includes: and the communication interface is used for communicating with external equipment and carrying out data interactive transmission. For example, the system communicates with the acquisition equipment of the operation information acquisition subsystem and communication modules of other trains to acquire real-time operation information of the train and adjacent trains.
The memory may include high speed RAM memory, and may also include a non-volatile defibrillator, such as at least one disk memory.
If the memory, the processor and the communication interface are implemented independently, the memory, the processor and the communication interface may be connected to each other through a bus and perform communication with each other. The bus may be an industry standard architecture bus, a peripheral device interconnect bus, an extended industry standard architecture bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc.
Optionally, in a specific implementation, if the memory, the processor, and the communication interface are integrated on a chip, the memory, the processor, that is, the communication interface may complete communication with each other through an internal interface.
The specific implementation process of each step refers to the explanation of the foregoing method.
It should be understood that in the embodiments of the present invention, the Processor may be a Central Processing Unit (CPU), and the Processor may also be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The memory may include both read-only memory and random access memory and provides instructions and data to the processor. The portion of memory may also include non-volatile random access memory. For example, the memory may also store device type information.
Example 5:
the present embodiments provide a readable storage medium storing a computer program for invocation by a processor to implement: disclosed is a method for optimizing multi-row vehicle collaborative cruise control in real time on line.
Wherein, specifically realize:
step 1: acquiring real-time running information and position information of a train;
each train acquires real-time running position information and position information of the train and a communication adjacent train;
step 2: introducing time-varying cooperative control gain, and constructing a time-varying cooperative control law based on distance deviation and speed deviation; the time-varying cooperative control gain comprises a distance deviation gain and a speed deviation gain, and values of the distance deviation gain and the speed deviation gain are dynamically changed; the distance deviation represents the deviation between the actual distance between the two communication trains and the expected safe distance, and the speed deviation represents the real-time speed deviation between the two communication trains;
and step 3: inputting the real-time distance deviation and speed deviation of the train into a trained neural network to obtain real-time globally optimal time-varying cooperative control gain;
the input of the neural network is the distance deviation and the speed deviation of the train, and the output is the globally optimal time-varying cooperative control gain;
and 4, step 4: obtaining the time-varying cooperative control law based on the globally optimal time-varying cooperative control gain, and generating traction force or braking force by using a traction braking system of the train based on the time-varying cooperative control law so as to control the acceleration variation of each train; wherein, the time-varying cooperative control law is specifically represented as traction force or braking force applied to the train.
Or specifically realizing:
s1: the current train acquires real-time running information and position information of the current train and the communication train;
s2: introducing time-varying cooperative control gain, and constructing a time-varying cooperative control law based on distance deviation and speed deviation; the time-varying cooperative control gain comprises a distance deviation gain and a speed deviation gain, and numerical values dynamically change; the distance deviation represents the deviation between the actual distance between the two communication trains and the expected safe distance, and the speed deviation represents the real-time speed deviation between the two communication trains;
s3: inputting the real-time distance deviation and speed deviation of the current train into a trained neural network to obtain real-time globally optimal time-varying cooperative control gain;
s4: and obtaining the time-varying cooperative control law based on the globally optimal time-varying cooperative control gain, and based on the time-varying cooperative control law, generating traction or braking force by using a traction braking system of the current train to further control the acceleration change of the current train, wherein the time-varying cooperative control law is specifically represented as the traction or braking force applied to the train.
It should be understood that the specific implementation process refers to the relevant contents of the embodiments 1-2.
The readable storage medium is a computer readable storage medium, which may be an internal storage unit of the controller according to any of the foregoing embodiments, for example, a hard disk or a memory of the controller. The readable storage medium may also be an external storage device of the controller, such as a plug-in hard disk provided on the controller, a Smart Memory Card (SMC), a Secure Digital (SD) Card, a flash Card (FlashCard), and the like. Further, the readable storage medium may also include both an internal storage unit of the controller and an external storage device. The readable storage medium is used for storing the computer program and other programs and data required by the controller. The readable storage medium may also be used to temporarily store data that has been output or is to be output.
Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned readable storage medium comprises: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Claims (9)
1. The method for online real-time optimization of multi-train collaborative cruise control is characterized by comprising the following steps of:
step 1: acquiring real-time running information and position information of a train;
each train acquires real-time running information and position information of the train and a communication train thereof; or acquiring real-time running information and position information of each train and communication relations among the trains;
step 2: introducing time-varying cooperative control gain, and constructing a time-varying cooperative control law based on distance deviation and speed deviation; the time-varying cooperative control gain comprises a distance deviation gain and a speed deviation gain, and values of the distance deviation gain and the speed deviation gain are dynamically changed; the distance deviation represents the deviation between the actual distance between the two communication trains and the expected safe distance, and the speed deviation represents the real-time speed deviation between the two communication trains;
and step 3: inputting the real-time distance deviation and speed deviation of the train into a trained neural network to obtain real-time globally optimal time-varying cooperative control gain;
the input of the neural network is the distance deviation and the speed deviation of the train, and the output is the globally optimal time-varying cooperative control gain;
and 4, step 4: obtaining the time-varying cooperative control law based on the globally optimal time-varying cooperative control gain, and generating traction or braking force by using a traction braking system of the train based on the time-varying cooperative control law so as to control the acceleration change of each train; wherein, the time-varying cooperative control law is specifically represented as traction force or braking force applied to the train.
2. The multi-train cooperative cruise control method according to claim 1, wherein the time-varying cooperative control law constructed in step 2 is expressed as:
wherein the content of the first and second substances,u i (t) Representing trainsiThe traction or braking force experienced;k 1 (t)、k 2 (t) Time-varying cooperative control gains to be determined respectively correspond to the distance deviation gain and the speed deviation gain;a ij for trainsiWith trainsjThe communication relation coefficient of (a), if there is a communication,a ij is 1, otherwisea ij Is 0, and
，v i (t)、v j (t) Respectively representing trainsi、Train with movable trackjReal-time speed of (d);x i (t)、x j (t) Respectively representing trainsi、Train with movable trackjThe real-time location of the mobile station,nfor the total number of trains in the multi-train cooperation system,dfor a given desired safety distance between the two cars,trepresenting time.
3. The multi-train cooperative cruise control method according to claim 1, wherein the neural network in step 3 is trained based on a training set, and the training set is composed of distance deviation and speed deviation obtained through multiple state sampling and corresponding globally optimal time-varying cooperative control gain;
after the distance deviation and the speed deviation obtained through state sampling each time, calculating by using a cuckoo search algorithm to obtain a globally optimal time-varying cooperative control gain, specifically as follows:
step 3.1: initializing and setting relevant parameters of cuckoo search algorithm: total number of bird's nestMFinding the probability P ∈ [0,1 ]]Maximum number of iterationsNAnd correspond ton 1 Initial population of individual cuckoos
，
，X 1 ,X 2 ,
Respectively represent the 1 st, the 2 nd and the 2 ndn 1 The position of a bird nest found by each cuckoo,
、
respectively representn 1 Distance deviation gain and speed deviation gain corresponding to the nest position of each cuckoo,n 1 the number of cuckoo;
step 3.2: updating the position of each bird nest in the population according to the following rules;
calculating an objective function value after the new bird nest position is reached through the Laevir flight, comparing the objective function value with an objective function value of a previous generation bird nest position, replacing and updating the bird nest position if the objective function value is reduced, and keeping the original bird nest position unchanged if the objective function value is not reduced; the formula of the levy flight is as follows:
in the formula (I), the compound is shown in the specification,αin order to be the step size,levy(β) In order to be a lavi random path,Tin response to the number of iterations,X i (T)、X i (T-1) representing the positions of the nests found by the ith cuckoo in the Tth iteration and the T-1 st iteration respectively;
step 3.3: after obtaining the nest position of a new population, randomly generating a numerical value R which is uniformly distributed according to 0 to 1, comparing the numerical value R with a discovery probability P, if R is greater than P, randomly updating the nest position once, then calculating an updated objective function value of the nest position, if the objective function value is smaller, replacing and updating the original nest position, otherwise, keeping the original nest position; if R is less than or equal to P, keeping the current bird nest position;
step 3.4: finding out the optimal positions of all current bird nests, wherein the bird nest position corresponding to the minimum objective function value is the optimal position;
step 3.5: judging whether the maximum iteration times is reached, if so, outputting an optimal position, and obtaining a distance deviation gain and a speed deviation gain in the globally optimal time-varying cooperative control gain corresponding to the substituted current state sampling; if the maximum iteration number is not reached, the step 3.2-3.5 is circulated until the maximum iteration number is reached;
and (3) circularly and repeatedly carrying out steps 3.1-3.5, and substituting all state samples to obtain the global optimal cooperative gain corresponding to different state samples so as to construct the training set.
4. The multi-train cooperative cruise control method according to claim 3, wherein the formula of the objective function is:
in the formula (I), the compound is shown in the specification,Jin order to be said objective function, the method comprises the steps of,u i (t) Representing the traction or braking force received by the train i, and correspondingly constructing a time-varying cooperative control law;a ij for trainsiAnd the trainjThe communication relation coefficient of (a), if there is a communication,a ij is 1, otherwisea ij Is 0, and
；v i (t)、v j (t) Traffic display traini、Train with wheelsjReal-time speed of (d);x i (t)、x j (t) Respectively representing trainsi、Train with movable trackjThe real-time location of the mobile station,nfor the total number of trains in the multi-train cooperation system,dfor a given desired safety distance between the two cars,trepresenting time.
5. The multi-train cooperative cruise control method according to claim 1, characterized in that: the neural network in the step 3 is a BP neural network, and the training step of the BP neural network is as follows:
s-1: initializing BP neural network parameters: the number of neurons in the input layer is 2, one input corresponds to a distance deviation, and the other input corresponds to a speed deviation; a hidden layer, wherein the number of the neurons of the hidden layer takes an arbitrary value; the number of neurons in the output layer is 2, and the corresponding distance deviation gain and the corresponding speed deviation gain are obtained; initializing the link weight value to be any value between (0 and 1);
s-2: taking a certain training sample from a training set and inputting the training sample into the BP neural network;
s-3: calculating the output of each layer of nodes in the forward direction by the BP neural network;
s-4: calculating the error between the actual output and the expected output of the BP neural network;
s-5: reversely calculating from the output layer to the first hidden layer, and adjusting each connection weight of the whole BP neural network in a direction of reducing errors by adopting a gradient descent method;
s-6: and repeating the steps S-2 to S-5 for each training sample in the training set until the error of the whole BP neural network reaches the preset requirement.
6. The method for optimizing the multi-train collaborative cruise control in real time on line is characterized by being applied to a single train of a multi-train collaborative control system, and comprising the following steps:
s1: the current train acquires real-time running information and position information of the current train and the communication train;
s2: introducing time-varying cooperative control gain, and constructing a time-varying cooperative control law based on distance deviation and speed deviation; the time-varying cooperative control gain comprises a distance deviation gain and a speed deviation gain, and values of the distance deviation gain and the speed deviation gain are dynamically changed; the distance deviation represents the deviation between the actual distance between the two communication trains and the expected safe distance, and the speed deviation represents the real-time speed deviation between the two communication trains;
s3: inputting the real-time distance deviation and speed deviation of the current train into a trained neural network to obtain real-time globally optimal time-varying cooperative control gain;
s4: and obtaining the time-varying cooperative control law based on the globally optimal time-varying cooperative control gain, and based on the time-varying cooperative control law, generating traction or braking force by using a traction braking system of the current train to further control the acceleration change of the current train, wherein the time-varying cooperative control law is specifically represented as the traction or braking force applied to the train.
7. A system for controlling multiple trains in cooperation with cruise according to any one of claims 1 to 6, comprising: the system comprises a multi-train system, an operation information acquisition subsystem, a train communication subsystem and a control subsystem;
the multi-train system consists of a plurality of trains;
the operation information acquisition subsystem consists of vehicle-mounted equipment and/or trackside equipment of each train and is used for acquiring real-time operation information of each train;
the train communication subsystem is composed of communication modules and/or wireless block centers of all trains and is used for constructing communication connection among the trains and realizing information transmission among the communication trains;
and the control subsystem is composed of controllers of all trains, and is used for obtaining or acquiring a time-varying cooperative control law of all trains according to the steps 2-4 or the steps S2-S4, and acting on a traction braking system of the trains to generate traction force or braking force so as to control the acceleration variation of the trains.
8. An electronic terminal, characterized by: the method comprises the following steps:
one or more processors;
a memory storing one or more computer programs;
the processor invokes the computer program to implement:
the steps of the multi-train cooperative cruise control method according to any of claims 1-6.
9. A readable storage medium, characterized by: a computer program is stored, which computer program is invoked by a processor to implement:
the steps of the multi-train cooperative cruise control method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211702024.2A CN115649240B (en) | 2022-12-29 | 2022-12-29 | Online real-time optimization multi-train cooperative cruise control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211702024.2A CN115649240B (en) | 2022-12-29 | 2022-12-29 | Online real-time optimization multi-train cooperative cruise control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115649240A CN115649240A (en) | 2023-01-31 |
| CN115649240B true CN115649240B (en) | 2023-03-17 |
Family
ID=85022861
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211702024.2A Active CN115649240B (en) | 2022-12-29 | 2022-12-29 | Online real-time optimization multi-train cooperative cruise control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115649240B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115016264A (en) * | 2022-05-26 | 2022-09-06 | 同济大学 | Master-slave cooperative control method and device for dynamic following vehicle distance adjustment and storage medium |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109656255A (en) * | 2019-01-28 | 2019-04-19 | 湖南大学 | Consider the vehicle platoon under communication topology time-varying with stability control method of speeding |
| CN110428093A (en) * | 2019-07-19 | 2019-11-08 | 北京工商大学 | City railway train running optimizatin method based on improved cuckoo algorithm |
| CN112298281B (en) * | 2020-10-23 | 2022-02-11 | 北京交通大学 | Train operation control method in time-lag communication network environment |
| CN112193280B (en) * | 2020-12-04 | 2021-03-16 | 华东交通大学 | Heavy-load train reinforcement learning control method and system |
| CN112637805B (en) * | 2020-12-11 | 2022-02-11 | 浙江大学 | Plug-and-play distributed estimation method for running state of high-speed train |
| CN113589690B (en) * | 2021-07-13 | 2023-07-21 | 清华大学 | Robust fault-tolerant method and device for cooperative self-adaptive cruise control |
| CN114407895B (en) * | 2022-02-25 | 2023-08-29 | 清华大学 | Vehicle predictive cruise control method, device, electronic equipment and storage medium |
| CN114580290A (en) * | 2022-03-10 | 2022-06-03 | 中南大学 | High-speed train set cooperative control method and system based on joint optimization of energy consumption and comfort level |
| CN114670901B (en) * | 2022-04-22 | 2022-12-13 | 长沙瑞纬电气有限公司 | Multi-train cooperative cruise control method and system based on potential function |
| CN114995129A (en) * | 2022-05-17 | 2022-09-02 | 南京航空航天大学 | Distributed optimal event trigger cooperative guidance method |
| CN115071784B (en) * | 2022-06-22 | 2023-12-01 | 长沙理工大学 | Multi-train distributed cooperative cruise control method and system |
-
2022
- 2022-12-29 CN CN202211702024.2A patent/CN115649240B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115016264A (en) * | 2022-05-26 | 2022-09-06 | 同济大学 | Master-slave cooperative control method and device for dynamic following vehicle distance adjustment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115649240A (en) | 2023-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20140005877A1 (en) | Method for Determining Run-Curves for Vehicles in Real-Time Subject to Dynamic Travel Time and Speed Limit Constraint | |
| CN112445229A (en) | Single-lane multi-queue hierarchical control method for piloting motorcade cooperation | |
| CN107272405B (en) | Vehicle distributed controller gain solving method and device for homogeneous vehicle queue | |
| CN115034390B (en) | Deep learning model reasoning acceleration method based on cloud edge-side cooperation | |
| CN113219962A (en) | Control method and system for hybrid queue following safety and storage medium | |
| CN115071784B (en) | Multi-train distributed cooperative cruise control method and system | |
| CN113344255A (en) | Vehicle-mounted network application data transmission and charging optimization method based on mobile edge calculation and block chain | |
| CN113401077A (en) | Intelligent vehicle dynamic reconfigurable network system and network scheduling method | |
| CN115649240B (en) | Online real-time optimization multi-train cooperative cruise control method and system | |
| Mynuddin et al. | Distributed predictive cruise control based on reinforcement learning and validation on microscopic traffic simulation | |
| CN114834467A (en) | Control operation method and device for automatic driving vehicle and unmanned vehicle | |
| CN113078974B (en) | Method for neural network sparse channel generation and inference | |
| Li et al. | An improved sliding mode control (SMC) approach for enhancement of communication delay in vehicle platoon system | |
| CN113905354A (en) | Vehicle-mounted network content delivery method and system based on regional content popularity | |
| CN114670901B (en) | Multi-train cooperative cruise control method and system based on potential function | |
| CN117042003A (en) | Energy efficiency optimization method for hybrid RIS-assisted UAV mobile edge computing system | |
| US20190299989A1 (en) | Prime mover power shaping controls responsive to surrounding vehicle characteristic | |
| Chen et al. | Communication-Efficient Decentralized Multi-Agent Reinforcement Learning for Cooperative Adaptive Cruise Control | |
| CN111047853A (en) | Vehicle formation control method and system for guaranteeing traffic flow stability | |
| US20220188621A1 (en) | Generative domain adaptation in a neural network | |
| CN114138466A (en) | Task cooperative processing method and device for intelligent highway and storage medium | |
| CN114475663B (en) | Automatic driving transverse control processing method | |
| Johansson et al. | On quantization and communication topologies in multi-vehicle rendezvous | |
| CN109910869A (en) | A kind of hybrid power passenger car control method and device | |
| Begizhonov et al. | Increasing the Accuracy of the Electronic Control Units’ Adjustment in Modern Vehicles Parts to Ensure Their Reliability and Safety |
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 |