Train track driving control method and device

Abstract

The present application discloses a train track driving control method and device. The method includes: segmenting the driving route of the train to obtain position points corresponding to different segments; determining the first motion relationship, the second motion relationship and the speed range of the driving speed of different position points in each segment; using the first motion relationship, the second motion relationship and the speed range as constraint conditions to solve the first curve of the speed corresponding to different position points that satisfy the constraint conditions; when triggering train speed control, determining the tracking speed according to the first curve, and determining the target control amount corresponding to reaching the tracking speed based on the current driving speed, the output control amount and the tracking speed; adjusting the currently output control amount according to the target control amount to control the driving speed of the train. This solves the problem of the emergency stop of the train caused by the sudden change of the ATP speed limit during the normal control of the automatic train operation ATO.

Description

Background Art

[0002] In automated train driving systems, automated tracking (ATO) relies on automated tracking (ATP) for safety protection. Currently designed train track control algorithms generally do not directly consider the ATP speed limit. Instead, they use algorithms, such as the PID algorithm, to control the train's actual speed so that it minimizes contact with the ATP's control curve. The PID algorithm uses proportional, integral, and differential control based on the deviation between the target tracking curve and the actual output value. The disadvantage of this method is the high number of switching cycles, which is not conducive to smooth operation and has low comfort. Furthermore, because the PID controller does not consider the impact of the ATP speed limit, the actual operating speed may exceed the ATP speed limit at the speed drop point, resulting in an emergency stop. Summary of the Invention

[0003] The purpose of this application is to provide a train track travel control method and device to solve the problem of train emergency stop caused by sudden change of ATP speed limit during normal train control by existing automatic train control (ATO).

[0004] In a first aspect, an embodiment of the present application provides a train track travel control method, the method comprising:

[0005] Divide the train's route into sections to obtain location points corresponding to different sections;

[0006] When each segment is set to use the same acceleration, determine the first motion relationship between the driving speed and the acceleration and the segment distance at different positions of each segment, the second motion relationship between the driving speed and the driving time and the segment distance at different positions of each segment, and the speed range of the driving speed at different positions of each segment;

[0007] Using the first motion relationship, the second motion relationship, and the speed range as constraints, solving a first curve of speeds corresponding to different position points that satisfy the constraints;

[0008] When the train speed control is triggered, the tracking speed is determined according to the first curve, and the target control amount corresponding to the tracking speed is determined based on the current running speed, the output control amount and the tracking speed;

[0009] The currently output control amount is adjusted according to the target control amount to control the running speed of the train.

[0010] In some possible embodiments, using the first motion relationship, the second motion relationship, and the speed range as constraints, solving a first curve of speeds corresponding to different position points that satisfy the constraints includes:

[0011] Taking the first motion relationship, the second motion relationship, the speed range, and the acceleration not exceeding the maximum acceleration as constraint conditions, and taking the minimum traction energy consumption as the objective function, a speed prediction model is established;

[0012] Using the speed prediction model to solve for the first curve of the speeds corresponding to different position points that satisfy the constraint conditions.

[0013] In some possible embodiments, the target travel time is the maximum travel time, and establishing the speed prediction model includes:

[0014] Taking the relationship defined by the following formula as a constraint condition, and taking the minimum traction energy consumption as the objective function, a non-linear speed prediction model is established:

[0015]

[0016]

[0017] 0 ≤ v n ≤ min(v n-1,max , v n,max )

[0018] a min ≤ a n ≤ a max

[0019] where the segment [s n-1 , s n includes the (n - 1)th position point s n-1 and the nth position point s n , v n is the speed of the nth position point, v n-1 is the speed of the (n - 1)th position point, a n is the acceleration of the segment [s n-1 , s n , r n is the basic resistance of the segment [s n-1 , s n , g n is the grade resistance of the segment [s n-1 , s n , c n is the curve resistance of the segment [s n-1 , s n , t n is the time when the train travels to the position point s n , t n-1 is the time when the train travels to the position point s n-1 , v n-1,max is the maximum speed of the (n - 1)th position point determined according to the speed range, v n,maxThe maximum speed of the nth position point determined according to the speed range, v turn The speed at the intermediate position determined according to the speed range, β 11 , β 12 , β 21 , β 22 Are set different coefficients.

[0020] In some possible embodiments, taking the first motion relationship, the second motion relationship, the speed range, and the acceleration not exceeding the maximum acceleration as constraint conditions, and taking the minimum traction energy consumption as the objective function, a speed prediction model is established, including:

[0021] Taking the following motion relationship as a constraint condition:

[0022] 2(a n -r n -g n -c n )(s n -s n-1 ) = v n 2 -v n-1 2 ,

[0023]

[0024] 0 ≤ v n 2 ≤ min(v n-1,max 2 , v n,max 2 )

[0025] a min ≤ a n ≤ a max ;

[0026] Taking the following minimum traction energy consumption as the objective function, a speed prediction model is established;

[0027]

[0028] Among them, the segmentation [s n-1 , s n includes the (n - 1)th position point s n-1 and the nth position point s n , v n is the speed of the nth position point, v n-1 is the speed of the (n - 1)th position point, a n is the acceleration of the segmentation [s n-1 , s n , r n is the segmentation [sn-1 , s n The basic resistance of [], g n is the segmented [s n-1 , s n ramp resistance, c n is the segmented [s n-1 , s n curve resistance, t n is the time when the train travels to position point s n , t n-1 is the time when the train travels to position point s n-1 , and is the coefficient corresponding to the conversion to a linear expression, v n-1,max is the maximum speed of the (n - 1)th position point determined according to the speed range, v n,max is the maximum speed of the nth position point determined according to the speed range, α1, α2 are set coefficients, v turn is the speed at the intermediate position determined according to the speed range, β′ 11 , β′ 12 , β′ 21 , β′ 22 are different set coefficients.

[0029] In some possible embodiments, the method further includes:

[0030] Fitting candidate curves of the speeds corresponding to different position points in each segment according to the speed limit condition, and determining the travel times corresponding to the train traveling to different positions at the speeds on the candidate curves;

[0031] Determining, when the train travels according to the candidate curve, the difference between the expected total travel duration and the travel durations of the train traveling to different position points, and the ratio of the distance from the current position point to the end point to the distance of the travel route, to obtain a mapping remaining duration curve corresponding to the start to the end of the travel;

[0032] When it is determined that the relationship between the mapping remaining duration curve and the actual remaining duration curve does not satisfy that the fitting degree gradually increases with the increase of the travel duration, adjusting the candidate curve until it satisfies the relationship, and when it satisfies the relationship, using the candidate curve as the second curve;

[0033] Determining the tracking speed according to the first curve, including:

[0034] Determining a first tracking speed according to the first curve, determining a second tracking speed according to the second curve, and determining the smaller value of the first tracking speed and the second tracking speed as the tracking speed.

[0035] In some possible embodiments, the following formula is used to determine the mapping remaining duration curve corresponding to the start to the end of the travel:

[0036]

[0037] t1 is the remaining mapping duration corresponding to running to the position point, t a is the total expected driving duration, t u is the driving duration when the train runs to different position points when the train runs according to the to-be-selected curve, A and B are set coefficients, s l is the distance from the current position point to the end point, s t is the driving route distance.

[0038] In some possible embodiments, based on the current driving speed, the output control amount, and the tracking speed, determining the target control amount corresponding to reaching the tracking speed includes:

[0039] Determining the expected output acceleration corresponding to at least one future control period according to the tracking speed;

[0040] Inputting the current state and the expected output acceleration of each control period into an acceleration prediction model, and the acceleration prediction model predicts the control amount according to the current state and the expected output acceleration, obtaining a loss function value according to the difference between the predicted acceleration output value corresponding to the predicted control amount and the expected output acceleration, and outputting the target control amount of this control period when the output loss function value meets the requirements;

[0041] The current state includes the current driving speed, the output control amount, the tracking speed, and the current acceleration.

[0042] In some possible embodiments, the target control amount of this control period corresponding to when the output loss function value meets the requirements includes:

[0043] Calculating the following objective function value:

[0044]

[0045] is the tracking speed corresponding to the future control period, is the predicted speed determined according to the predicted acceleration output value corresponding to the predicted control amount, λ is a weighting coefficient, is the change value of the predicted acceleration output value corresponding to the predicted control amount and the current acceleration in the future control period;

[0046] Determining that the control amount corresponding to the minimum loss function value under the condition that the difference between the objective function and the state reference value is less than the set value is the target control amount and outputting it, and the state reference value is the objective function value corresponding to the speed change and acceleration change according to the train's smooth driving state.

[0047] In some possible embodiments, the target control quantity of the control cycle corresponding to when the output loss function value meets the requirements includes:

[0048] Determine the control quantity corresponding to the minimum loss function value that satisfies at least one of the following constraints as the target control quantity and output it according to the predicted control quantity and / or the acceleration value corresponding to the predicted control quantity:

[0049] The control quantity does not exceed the maximum output of the traction motor;

[0050] The impact rate determined according to the acceleration ≤ 0.75 m / s 3 ;

[0051] When controlling the train, the unbalanced centrifugal acceleration ≤ 0.4 m / s 2 ;

[0052] The traveling speed is greater than or equal to zero.

[0053] In a second aspect, an embodiment of the present application provides a train track driving control device, including at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the train track driving control method provided in the first aspect above.

[0054] In the embodiments of the present application, in order to solve the problem that the train fails to respond in time during train control and causes emergency stops due to frequent reduction and increase of the line speed limit. The present application proposes a train track driving control method and device, which can use constraint conditions to fit a corresponding curve for the traveling speed during the entire driving stage in advance, and control the train driving according to the fitted curve to ensure smooth operation during the entire process of train track driving, and improve the operation efficiency and passenger experience. Description of the Drawings

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required to be used in the embodiments of the present application. Obviously, the following introduced drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0056] Figure 1 It is a schematic flowchart of a train track driving control method according to an embodiment of the present application;

[0057] Figure 2 It is a relationship diagram between the maximum traction force and the running speed of a train according to an embodiment of the present application;

[0058] Figure 3 Schematic diagram of mapping remaining time in a train track driving control method according to an embodiment of the present application;

[0059] Figure 4 Schematic structural diagram of a train track driving control device according to an embodiment of the present application;

[0060] Figure 5 Schematic structural diagram of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0061] The technical solutions in the embodiments of the present application will be clearly and elaborately described below with reference to the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " means "or". For example, A / B may mean A or B. The "and / or" in the text is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B may mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present application, "a plurality of" means two or more than two.

[0062] In the description of the embodiments of the present application, unless otherwise specified, the term "a plurality of" means two or more than two, and other quantifiers should be understood similarly. The preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. And without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0063] To further illustrate the technical solutions provided by the embodiments of the present application, the following will be described in detail with reference to the accompanying drawings and specific implementation manners. Although the embodiments of the present application provide method operation steps as shown in the following embodiments or drawings, more or fewer operation steps may be included in the method based on routine or non-creative labor. In steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided by the embodiments of the present application. When the method is actually processed or executed by the control device, it can be executed in the order shown in the embodiments or drawings or executed in parallel.

[0064] In view of the problem that in the related art, the train fails to respond in time during train control due to the frequent reduction and increase of the line speed limit, resulting in emergency stops. The present application proposes a train track driving control method, device, and electronic device, which can improve the operation efficiency and passenger experience.

[0065] In view of this, the inventive concept of the present application is as follows: When designing the train control algorithm, the speed limit of ATP is considered, and through the method of model prediction, it is solved that in the normal train control of the general train track driving control method, due to the frequent decrease and increase of the line speed limit, the train fails to respond in time during train control, resulting in emergency stops, and the operation efficiency and passenger experience are improved.

[0066] Other features and advantages of the present application will be described in the following specification, and, in part, will become apparent from the specification, or will be understood by implementing the present application. The objectives and other advantages of the present application can be achieved and obtained through the structures specifically pointed out in the written specification, claims, and drawings.

[0067] The following will describe in detail the train track driving control method in the embodiments of the present application with reference to the accompanying drawings.

[0068] Figure 1 The flow diagram of the train track driving control method provided by an embodiment of the present application is shown, including:

[0069] Step 101: Segment the train's driving route to obtain position points corresponding to different segments.

[0070] The train's driving route is discretized into N different segments, and the position points are represented as s0, s1, …, s N , where s0 is the current position of the train, and s N is the end point of the train's travel on the driving route. The speeds and times corresponding to the position points are v0, v1,..., v N and t0, t1,..., t N .

[0071] Step 102: When it is determined that the same acceleration is used for each segment, determine the first motion relationship between the driving speeds, accelerations, and segment distances of different position points in each segment, the second motion relationship between the driving speeds, travel times, and segment distances of different position points in each segment, and the speed range of the driving speeds of different position points in each segment.

[0072] The speed range is determined according to at least one speed limit condition. The at least one speed limit condition includes the ATP speed limit, and also includes the vehicle speed limit and the obstacle speed limit. After comprehensively considering all speed limit conditions, a speed limit range that does not exceed the maximum speed corresponding to the above speed limit conditions is determined.

[0073] Specifically, the accelerations corresponding to each driving route segment are a1, a2, …, a N , and it is assumed that the acceleration is a constant value in each segment, that is, the train has an acceleration of a constant value in a segment [s n-1 , s n] is uniform motion, uniformly accelerated motion or uniformly decelerated motion.

[0074] Currently designed train track control methods generally do not directly consider the ATP speed limit constraint. Instead, algorithms are used to control the train's actual speed so that it does not touch the ATP control curve as much as possible. For example, PID algorithms, because the PID controller does not consider the impact of the ATP speed limit, the actual operating speed may exceed the ATP speed limit at the speed limit drop point, causing an emergency stop. Therefore, this application considers the ATP speed limit in the context of train track control, ensuring that the speed range does not exceed the speed range corresponding to the ATP speed limit.

[0075] The specific effects of the first motion relationship, the second motion relationship, and the speed range are shown in step 103 below.

[0076] Step 103: Using the first motion relationship, the second motion relationship and the speed range as constraints, a first curve of speeds corresponding to different position points that meets the constraints is solved.

[0077] Specifically, under the three constraints of the first motion relationship, the second motion relationship, and the speed range, a first curve can be obtained. The first curve is obtained by comprehensively considering factors such as driving speed, acceleration, segment distance, and driving time.

[0078] Step 104: When the train speed control is triggered, the tracking speed is determined according to the first curve, and the target control amount corresponding to the tracking speed is determined based on the current travel speed, the output control amount and the tracking speed.

[0079] Tracking speed is the speed corresponding to each position point obtained after comprehensive consideration of multiple factors. It is different from the actual speed of the train. Ultimately, the control of the train needs to achieve the target control amount corresponding to the tracking speed.

[0080] Step 105: Adjust the currently output control variable according to the target control variable to control the running speed of the train.

[0081] The currently output control quantity is the actual control quantity output to the train in real time. This application achieves the ultimate control of the train speed by continuously matching the currently output control quantity with the target control quantity, so that the train can travel safely without exceeding the ATP speed limit.

[0082] This application mainly provides a new train track travel control method. When the train is in the control algorithm, the ATP speed limit is taken into consideration. Through the speed prediction model prediction method, the problem of the general train control method being unable to respond in time during normal control due to the frequent reduction or increase of the train speed limit on the line, resulting in an emergency stop, is solved, thereby improving operation efficiency and passenger experience.

[0083] As an alternative implementation, using the first motion relationship, the second motion relationship, and the speed range as constraint conditions, solving for the first curve of the speeds corresponding to different position points that satisfy the constraint conditions includes:

[0084] Taking the first motion relationship, the second motion relationship, the speed range, and the acceleration not exceeding the maximum acceleration as constraint conditions, and taking the minimum traction energy consumption as the objective function, to establish a speed prediction model;

[0085] Using the speed prediction model to solve for the first curve of the speeds corresponding to different position points that satisfy the constraint conditions.

[0086] The maximum acceleration refers to the maximum acceleration value that the train cannot exceed in the section of [[s n-1 , s n .

[0087] The target travel time is preset. The travel time is related to the train's traction energy consumption, and the corresponding target travel time can be set according to the energy consumption requirements. For example, when the energy consumption is the smallest, the target travel time is determined to be the largest.

[0088] Specifically, the constraint conditions of the speed prediction model, in addition to the three constraint conditions in step 103 above, also include the constraint conditions regarding acceleration.

[0089] The speeds corresponding to different position points refer to the speeds corresponding to different position points that satisfy the constraint conditions obtained through the first curve described in step 103. Here, the constraint conditions include the first motion relationship, the second motion relationship, the speed range, and the constraint conditions of acceleration.

[0090] Because the longer the target travel time, the smaller the corresponding traction energy consumption, so when the target travel time is the maximum travel time, the corresponding traction energy consumption is the smallest.

[0091] Based on the train operation process in the embodiments of the present application, the motion relationship conforms to the following principle to propose a speed prediction model using the above constraint conditions.

[0092] If the braking distance allowed for the train at the current moment is known, according to Newton's second law, the maximum operating speed of the train is:

[0093]

[0094] In the formula: V t is the current speed of the train; V0 is the speed of the train when it reaches the target point, a is the braking acceleration of the train, and s is the braking distance of the train.

[0095] If considering the reaction time of the VOBC system and the braking system on this basis, the following relationship is satisfied:

[0096]

[0097]

[0098] In the formula: S b is the braking distance of the train; v is the current speed of the train; V b is the speed of the train when it reaches the target point, and a r is the braking acceleration of the train. The reaction time t R includes the reaction time t r of the ATO system, the delay time t s from issuing the braking command to the start of the braking system implementation, and the delay time t b from the start of braking by the braking system to the achievement of full braking by the braking system.

[0099] Based on the above principle, on the basis of segmenting the train's driving route, the embodiment of the present application can perform non - linear modeling or linear modeling based on the above - mentioned constraint conditions to obtain a speed prediction model. The following gives a specific implementation method.

[0100] 1) Non - linear modeling method

[0101] The embodiment of the present application takes the relationship defined by the following formula as a constraint condition, and takes the minimum traction energy consumption as the objective function to establish a non - linear speed prediction model:

[0102]

[0103]

[0104] 0 ≤ v n ≤ min(v n-1,max , v n,max )

[0105] a min ≤ a n ≤ a max

[0106] Among them, the segment [s n-1 , s n includes the (n - 1)th position point s n-1 and the nth position point s n , v n is the speed at the nth position point, v n-1 is the speed at the (n - 1)th position point, a n is the acceleration of the segment [s n-1 , s n , r n is the resistance of the segment [s n-1 , s nThe basic resistance, g n is the ramp resistance for the segment [s n-1 , s n , c n is the curve resistance for the segment [s n-1 , s n , t n is the time when the train travels to the position point s n , t n-1 is the time when the train travels to the position point s n-1 , v n-1,max is the maximum speed of the (n - 1)th position point determined according to the speed range, v n,max is the maximum speed of the nth position point determined according to the speed range, v turn is the speed at the intermediate position determined according to the speed range, β 11 , β 12 , β 21 , β 22 are different set coefficients.

[0107] Specifically, the ramp resistance and curve resistance of the train in each segment of the driving route can be expressed as g1, g2, …, g N and c1, c2, …, c N . The basic resistance during the train operation is also approximately a constant value within a segment of the driving route. The specific calculation is as follows:

[0108]

[0109] Among them, is the average speed of the train running in the segment [s n-1 , s n , r a , r b , r c is the coefficient of the basic resistance, r a , r b , r c can be obtained according to the dynamic characteristics of the train.

[0110] According to the above Second Newton's Law, taking the first motion relationship as a constraint condition, the train needs to satisfy n-1 , s n during the operation in the segment [s this constraint condition.

[0111] Taking the second motion relationship as a constraint condition, the train needs to satisfy n-1 , s n during the operation in the segment [s this constraint condition.

[0112] Taking the speed range as a constraint condition, the maximum running speed of the train at different position points during the running process is expressed as v 0,max , v 1,max , …, v N,max . The maximum running speed of each position point can be determined according to speed limit conditions such as vehicle speed limit and obstacle speed limit, and ATP speed limit. Then, if the train speed at position point s n satisfies 0 ≤ v n ≤ min(v n-1,max , v n,max ), the train speed at any position point will not exceed the ATP limit speed.

[0113] In the embodiment of the present application, for the above constraint condition a min ≤ a n ≤ a max , the minimum acceleration can be set, and the maximum acceleration can be determined by the following formula. Refer to the relationship diagram between the maximum traction force and running speed of the train shown in Figure 2 . It can be seen from the figure that there is a non-linear relationship between the maximum traction force of the train and the running speed. For the sake of simplification, in the present application, this non-linear function is approximated as a piecewise linear function, that is, the relationship between the piecewise acceleration and speed:

[0114]

[0115] The maximum traction force and braking force of the train are not constant values, but decrease with the increase of the running speed. The above piecewise linear function only contains two sub-functions. If more accuracy is required, more sub-functions can be introduced to reduce the approximation error. Similarly, if there is also such a non-linear relationship between the maximum braking force of the train and the running speed, similar treatment is carried out. It should be noted that the relationship described in the above formula is the relationship between the maximum acceleration of the train and the speed. Therefore, the acceleration of the train in the section [s n-1 , s n needs to satisfy the following constraint conditions:

[0116] a min ≤ a n ≤ a max .

[0117] The embodiment of the present application takes the minimum traction energy consumption as the objective function:

[0118] where J represents the traction energy consumption. The objective function contains the acceleration max function, and finally a minimum value of the traction energy consumption is obtained.

[0119] Based on the determination of the above objective function and constraints, non-linear modeling is carried out. The objective function is solved under the condition of meeting the above constraints to obtain the fitted first curve. The specific solution process can adopt the existing sequential quadratic programming to solve the non-linear modeling method for this problem, and the specific process will not be elaborated here.

[0120] 2) Linear modeling method

[0121] In the embodiment of the present application, the first motion relationship, the second motion relationship and the speed range are used as constraints to establish a speed prediction model, including:

[0122] Taking the following motion relationship as a constraint and the minimum traction energy consumption as the objective function, a linear speed prediction model is established:

[0123] 2(a n -r n -g n -c n )(s n -s n-1 ) = v n 2 -v n-1 2 ,

[0124]

[0125] 0 ≤ v n 2 ≤ min(v n-1,max 2 , v n,max 2 )

[0126]

[0127] Among them, the segment [s n-1 , s n includes the (n - 1)-th position point s n-1 and the n-th position point s n , v n is the speed of the n-th position point, v n-1 is the speed of the (n - 1)-th position point, a n is the acceleration of the segment [s n-1 , s n , r n is the basic resistance of the segment [s n-1 , s n , g n is the ramp resistance of the segment [s n-1 , s n , c n is the curve resistance of the segment [s n-1 , sn Curve resistance of ], t n Is the time when the train travels to position point s n Time, t n-1 Is the time when the train travels to position point s n-1 Time, is the coefficient corresponding to the conversion to a linear expression, v n-1,max Is the maximum speed of the (n - 1)th position point determined according to the speed range, v n,max Is the maximum speed of the nth position point determined according to the speed range, α1, α2 are set coefficients, v turn Is the speed at the middle position determined according to the speed range, β′ 11 , β′ 12 , β′ 21 , β′ 22 Are different set coefficients.

[0128] Specifically, in the quadratic programming problem, the square of the train speed is selected, i.e., v1 2 , v2 2 , …, v N 2 Is the independent variable of the problem, then the constraints on the traveling speeds of different position points in each segment can be transformed into 0 ≤ v n 2 ≤ min(v n-1,max 2 , v n,max 2 ).

[0129] v n Speed range, the speed range is determined according to at least one speed limit condition. At least one speed limit condition includes ATP speed limit, and also includes vehicle speed limit and obstacle speed limit. After comprehensively considering all speed limit conditions, the speed limit range not exceeding the maximum speed corresponding to the above speed limit conditions is determined.

[0130] The basic resistance calculation during the train operation is approximately r n = r a '+ r c 'v n 2 Or r n = r a '+ r c 'v n-1 2 .

[0131] Here, in the segment [s n-1 , s n , the average speed is no longer used for the basic resistance calculation, but the endpoint speeds are used for approximate calculation. In addition, the first-order term in the basic running resistance is no longer considered. Here, the new basic resistance parameter r can be obtained by the least squares method.a ' and r c '. The relational expressions between different segments of train operation and the speeds at the endpoints are as follows:

[0132] 2(a n -r n -g n -c n )(s n -s n-1 ) = v n 2 -v n-1 2 , as a constraint condition, the calculation formula of the running time contains nonlinear terms and needs to be approximated. The approximation process using the Trapezoidal Rule is as follows:

[0133]

[0134] where is still a nonlinear term and can be approximated as a linear function, that is

[0135] Then the calculation of the travel time can be transformed into the following linear form:

[0136]

[0137] where, in the calculation of the travel time t n , two approximations are introduced. The error of the first approximation increases with the increase of the difference between v n and v n-1 . The magnitude of the error of the second approximation is related to the range of the considered speed interval and the selected linear function.

[0138] The relationship between the maximum traction force of the train and the speeds at various position points during train operation is also transformed into a relationship with the square of the speed and approximated by a piecewise function. The expression of the maximum acceleration of the train can be written as:

[0139]

[0140] After such transformation, the objective function is linear and the constraint conditions are also linear. This problem is transformed into a linear programming problem, which speeds up the solution.

[0141] Based on the above step 103, taking the first motion relationship, the second motion relationship and the speed range as constraint conditions, establishing a speed prediction model, and using the speed prediction model to solve the first curve of the speeds corresponding to different position points that satisfy the constraint conditions, the present application further optimizes the train track driving control method.

[0142] Based on the determination of the above objective function and constraints, linear modeling is carried out, and the objective function is solved under the condition of satisfying the above constraints to obtain the fitted first curve. The specific solution process can adopt existing linear modeling methods, with faster solution speed, and the specific process will not be elaborated here.

[0143] As an alternative implementation, the method further includes:

[0144] Step 201: Fit candidate curves corresponding to the speeds of different position points in each segment according to the speed limit conditions, and determine the travel times corresponding to the train traveling to different positions at the speeds on the candidate curves.

[0145] Step 202: Determine, when the train travels according to the candidate curve, the difference between the expected total travel time and the travel times of the train traveling to different position points, and the ratio of the distance from the current position point to the end point to the distance of the travel route, to obtain the mapped remaining travel time curve corresponding to the start to the end of the travel.

[0146] As an alternative implementation, the following formula is used to determine the mapped remaining travel time curve corresponding to the start to the end of the travel:

[0147]

[0148] t1 is the mapped remaining travel time corresponding to running to the position point, t a is the expected total travel time, t u is the travel time of the train traveling to different position points when the train travels according to the candidate curve, A and B are set coefficients, s l is the distance from the current position point to the end point, s t is the distance of the travel route.

[0149] Step 203: When it is determined that the relationship between the mapped remaining travel time curve and the actual remaining travel time curve does not satisfy the condition that the fitting degree gradually increases with the increase of the travel time, adjust the candidate curve until the relationship is satisfied. When the relationship is satisfied, use the candidate curve as the second curve.

[0150] As an alternative implementation, determining the tracking speed according to the first curve includes:

[0151] Determine the first tracking speed according to the first curve, determine the second tracking speed according to the second curve, and determine the smaller value of the first tracking speed and the second tracking speed as the tracking speed.

[0152] The speed limit conditions include simultaneously considering ATP speed limit, section speed limit, vehicle speed limit, obstacle speed limit, etc.

[0153] Among them, through experiments, the value of A is obtained as 20, and the value range of B is (-10, 10). Specifically, for the mapped remaining duration curve, the remaining time t that can be mapped a is the total running duration t u The current running time changes continuously during the train operation. Refer to Figure 3 , at the start of the train operation, the first curve is fitted according to the speed limit conditions. At this time, t a -t u is the largest value. Because the running time is short and the speed is high at the beginning, the calculated remaining time is smaller than the actual remaining time, and the fitting degree between the two lines is relatively small. The mapped remaining time at the starting point is T - A - B. According to the formula:

[0154]

[0155] At the very beginning starting point, s t is the same as the value of s l , so the initial value is 1. Regarding the value of t a -t u as T, the remaining duration obtained according to the mapped remaining duration curve is T - A - B.

[0156] The bisection method is used to calculate the appropriate tracking speed to meet the requirements during train control and operation. When fitting the curve, the bisection method is used for fitting. The fitting speed in the early stage of the speed limit condition should be as large as possible as long as it does not exceed the speed limit and meets each speed limit condition. The fitting speed in the later stage should be as small as possible to ensure that the fitted curve has an increasing fitting degree between the two curves as the driving time increases.

[0157] When calculating according to the curve of the fitted driving, it is calculated that:

[0158] The fitting degree refers to the difference between the remaining time from large to small corresponding to the same driving time. For the same driving time, the difference gradually decreases until it coincides at a certain point. The relationship between the second curve and the actual first curve is that the fitting degree gradually increases from small to large to achieve precise train control.

[0159] The train motion system is a complex non - linear system. To facilitate train control, an acceleration prediction model is established. According to the current measurement state and future control quantity of the train, the control quantity output for a certain future section is predicted, and then compared with the expected acceleration output to obtain a loss function.

[0160] If optimization is not considered, the output value is the minimum of the objective function value, and the difference between the expected acceleration output and the actual acceleration output is the smallest, which is the optimal output.

[0161] As an alternative implementation, determining a target control quantity corresponding to the tracking speed based on the current driving speed, the output control quantity, and the tracking speed includes:

[0162] Determining the expected output acceleration corresponding to at least one future control period according to the tracking speed;

[0163] Inputting the current state and the expected output acceleration of each control period into an acceleration prediction model. The acceleration prediction model predicts the control quantity according to the current state and the expected output acceleration, and obtains a loss function value based on the difference between the acceleration output value corresponding to the predicted control quantity and the expected output acceleration, and outputs the target control quantity of the control period when the output loss function value meets the requirements;

[0164] The current state includes the current driving speed, the output control quantity, the tracking speed, and the current acceleration.

[0165] Among them, at least one future control period is preferably 30 future control periods.

[0166] In the embodiment of the present application, the acceleration prediction model can be trained in advance, using the current state and the expected output acceleration in the training samples as inputs, so that the acceleration prediction model predicts the control quantity according to the control quantity in the training samples. During the vehicle control process, the current state and the expected output acceleration of each control period collected in real time are input into the acceleration prediction model. The acceleration prediction model predicts the control quantity according to the current state and the expected output acceleration, and calculates the loss function according to the following loss function, and outputs the target control quantity corresponding to the minimum loss function value:

[0167] Loss function = (future output acceleration (model, future control quantity, current state) - expected output acceleration).

[0168] The above future output acceleration is determined by the above acceleration prediction model according to the current state and the predicted future control quantity. Since the model, the current state, and the expected output acceleration in the above formula are all known, there is only one independent variable, the future control quantity. Solving for a future control quantity that minimizes the loss function is the control quantity of the current control period.

[0169] When each control period is reached in this embodiment, the ATO control is performed using the above method proposed in the embodiment of the present application. When performing the train track driving control, the control quantity of multiple future control periods can be predicted in the current control period. Assume that the predicted system states within the next n control periods are:

[0170] X k =[x(k + 1|k) T x(k + 2|k) T...x(k+n|k) T T

[0171] where n is called the prediction horizon, and k+1|k in the parentheses represents the predicted system state at the (k+1)-th moment at the current k-th moment, and so on. In addition, when predicting the future state of the dynamic system, the control quantity U within the prediction horizon is also required to be known k :

[0172] U k =[u(k|k) T u(k+1|k) T ...u(k+n-1|κ) T T

[0173] Since the above acceleration prediction model has a prediction function and a series of reference values are required before prediction, when performing control at the k-th moment, the reference values from the k-th moment to the (k+n)-th moment must have been obtained. In the present invention, it corresponds to all ATP speed limits and other speed limit information at the current moment and the next n moments. According to these speed limit information and other constraint conditions, the optimal control quantity is selected by substituting them into the control model

[0174] To ensure the smooth operation, comfortable energy conservation, and precise parking of train track driving control, the embodiments of the present application can predict the control quantity by using the above acceleration prediction model, further add the objective function of smooth train control, and use this objective function to find the best control quantity, so that the state vector within the time domain is closer to the state reference value. This is an open-loop optimal control problem

[0175] As an optional implementation manner, the target control quantity corresponding to the control cycle when the output loss function value meets the requirements includes:

[0176] Calculate the following objective function value:

[0177]

[0178] is the tracking speed corresponding to the future control cycle, is the predicted speed determined according to the acceleration output value corresponding to the predicted control quantity, λ is the weighting coefficient, is the change value between the acceleration output value corresponding to the predicted control quantity in the future control cycle and the current acceleration;

[0179] Determine that when the difference between the objective function and the state reference value meets the condition of being less than the set value, the control quantity corresponding to the minimum loss function value is used as the target control quantity and output. The state reference value is the objective function value corresponding to the speed change and acceleration change corresponding to the smooth driving state of the train​​

[0180] Since the embodiments of the present application perform prediction of the control quantity for at least one future control period, the in the above formula is the tracking speed corresponding to the future n control periods, is the predicted speed determined according to the acceleration output value corresponding to the predicted control quantity at the future n moments, λ is the weighting coefficient, is the change value of the acceleration corresponding to the predicted control quantity and the current acceleration in the future n control periods. Therefore, the above expression is the summation of the corresponding vectors, and the obtained vector is compared with the state reference value. The above state reference value is a vector obtained according to the speed change and acceleration change at multiple moments corresponding to the stable running state of the train and the corresponding objective function value.

[0181] The output loss function value meeting the requirements means that under the condition that the difference between the objective function and the state reference value is less than the set value, the above loss function is the smallest. If this condition is not considered, the loss function value will not be adopted even if it is the smallest. For example, many loss function values are calculated. The smallest loss function value needs to be further judged whether it meets the condition that the difference between the objective function and the state reference value is less than the set value. If not, this smallest loss function value is filtered out, and the smallest loss function value is continuously searched from the remaining loss function values that meet the stable running state of the train, considering both aspects.

[0182] The state reference value refers to the objective function value corresponding to the speed change and acceleration change when the train is in a stable running state. To meet the objective function, when approaching the state reference value, the loss function value is the smallest and then output for train control.

[0183] When determining the closeness of the above two vectors, specifically, the cosine distance between the two vectors can be calculated. The smaller the cosine distance, the closer they are.

[0184] As an optional implementation manner, the target control quantity of the control period corresponding to the output loss function value meeting the requirements includes:

[0185] According to the predicted control quantity and / or the acceleration value corresponding to the predicted control quantity, determine the control quantity corresponding to the minimum loss function value that satisfies at least one of the following constraints as the target control quantity and output:

[0186] The control quantity does not exceed the maximum output of the traction motor;

[0187] The impact rate determined according to the acceleration ≤ 0.75m / s 3 ;

[0188] When controlling the train, the unbalanced centrifugal acceleration ≤ 0.4m / s 2 ;

[0189] The driving speed is greater than or equal to zero.

[0190] Specifically, when the output loss function is minimized, it is necessary to satisfy the above constraint conditions, and the loss function value needs to be minimized before output can be achieved. Each constraint condition can be determined based on the acceleration and the predicted speed. The acceleration and the predicted speed determine the control quantity. If the current control quantity causes the acceleration and speed not to meet the above conditions, the current control quantity will not be output even if the loss function value is minimized.

[0191] As an alternative implementation, controlling the driving speed of the train includes:

[0192] Obtain the acceleration obtained by the ATO through model predictive control according to the speed prediction model, and determine whether to output traction, braking, or coasting based on the magnitude and sign of the acceleration;

[0193] When in traction, based on the obtained acceleration, referring to Table 1, the vehicle traction performance curve table, and the acceleration comparison table, through interpolation, using the difference between the maximum output value and the minimum output value of the current loop as the range, calculate the output current loop value of the ATO system;

[0194] When in braking, based on the obtained acceleration, referring to Table 2, the vehicle braking performance curve table, and the deceleration comparison table, through interpolation, using the difference between the maximum output value and the minimum output value of the current loop as the range, calculate the output current loop value of the ATO system; it should be noted that if the obtained deceleration is greater than the maximum deceleration, output the current value corresponding to the maximum deceleration;

[0195] To ensure comfort and smooth operation of the train, limit the acceleration current and deceleration current output per cycle, and the change does not exceed a certain threshold.

[0196]

[0197] Table 1

[0198]

[0199] Table 2

[0200] Embodiment 2

[0201] Based on the same inventive concept, the present application also provides a train track driving control device 400, as Figure 4 shown, the device includes:

[0202] A segmentation module 401 for segmenting the driving route of the train to obtain position points corresponding to different segments;

[0203] Determination module 402, configured to determine, when each segment travels at the same acceleration, a first motion relationship among the traveling speeds, accelerations, and segment distances of different position points in each segment, a second motion relationship among the traveling speeds, traveling times, and segment distances of different position points in each segment, and a speed range of the traveling speeds of different position points in each segment;

[0204] First curve solving module 403, configured to use the first motion relationship, the second motion relationship, and the speed range as constraint conditions to solve a first curve of the speeds corresponding to different position points that satisfy the constraint conditions;

[0205] Target control quantity determination module 404, configured to, when triggering train speed control, determine a tracking speed according to the first curve, and determine a target control quantity corresponding to reaching the tracking speed based on the current traveling speed, the output control quantity, and the tracking speed;

[0206] Adjustment module 405, configured to adjust the currently output control quantity according to the target control quantity to control the traveling speed of the train.

[0207] Optionally, the first curve solving module 403 is specifically configured to:

[0208] Take the first motion relationship, the second motion relationship, the speed range, and the acceleration not exceeding the maximum acceleration as constraint conditions, and establish a speed prediction model with the minimum traction energy consumption as the objective function;

[0209] Use the speed prediction model to solve a first curve of the speeds corresponding to different position points that satisfy the constraint conditions.

[0210] Optionally, the target traveling time is the maximum traveling time, and the first curve solving module 403 is specifically configured to:

[0211] Take the relationship defined by the following formula as a constraint condition, and establish a non-linear speed prediction model with the minimum traction energy consumption as the objective function:

[0212]

[0213]

[0214] 0 ≤ v n ≤ min(v n-1,max , v n,max )

[0215] a min ≤ a n ≤ a max

[0216] wherein, for segment [s n-1 , s nincluding the (n - 1)-th position point s n-1 and the n-th position point s n , v n is the speed of the n-th position point, v n-1 is the speed of the (n - 1)-th position point, a n is the acceleration of the segment [s n-1 , s n , r n is the basic resistance of the segment [s n-1 , s n , g n is the ramp resistance of the segment [s n-1 , s n , c n is the curve resistance of the segment [s n-1 , s n , t n is the time when the train travels to the position point s n , t n-1 is the time when the train travels to the position point s n-1 , v n-1,max is the maximum speed of the (n - 1)-th position point determined according to the speed range, v n,max is the maximum speed of the n-th position point determined according to the speed range, v turn is the speed at the intermediate position determined according to the speed range, β 11 , β 12 , β 21 , β 22 are different set coefficients.

[0217] Optionally, solve the first curve module 403, specifically for:

[0218] Take the following motion relationship as a constraint condition:

[0219] 2(a n - r n - g n - c n )(s n - s n-1 ) = v n 2 - v n-1 2 ,

[0220]

[0221] 0 ≤ v n 2 ≤ min(v n-1,max 2 , v n,max 2 )

[0222] a min ≤a n ≤a max ;

[0223] Taking the minimum traction energy consumption as the objective function, a speed prediction model is established;

[0224]

[0225] Among them, the segmentation [s n-1 , s n includes the (n - 1)-th position point s n-1 and the n-th position point s n , v n is the speed at the n-th position point, v n-1 is the speed at the (n - ¹)-th position point, a n is the acceleration of the segmentation [s n-1 , s n , r n is the basic resistance of the segmentation [s n-1 , s n , g n is the ramp resistance of the segmentation [s n-1 , s n , c n is the curve resistance of the segmentation [s n-1 , s n , t n is the time when the train travels to the position point s n , t n-1 is the time when the train travels to the position point s n-1 is the coefficient corresponding to the conversion to linear expression, v n-1,max is the maximum speed of the (n - 1)-th position point determined according to the speed range, v n,max is the maximum speed of the n-th position point determined according to the speed range, α1 and α2 are set coefficients, v turn is the speed at the intermediate position determined according to the speed range, β′ 11 , β′ 12 , β′ 21 , β′ 22 are different set coefficients.

[0226] Optionally, the device further includes a fitting candidate curve module 406 for:

[0227] Fitting candidate curves corresponding to the speeds of different position points in each segmentation according to the speed limit condition, and determining the travel times corresponding to the train traveling to different positions at the speeds on the candidate curves;

[0228] When it is determined that the train travels along the to-be-selected curve, the difference between the expected total travel duration and the travel durations of the train at different position points, and the ratio of the distance from the current position point to the end point to the travel route distance are obtained to obtain the corresponding mapped remaining duration curve from the start of travel to the end of travel;

[0229] When it is determined that the relationship between the mapped remaining duration curve and the actual remaining duration curve does not satisfy the condition that the fitting degree gradually increases with the increase of the travel duration, the to-be-selected curve is adjusted until the relationship is satisfied. When the relationship is satisfied, the to-be-selected curve is used as the second curve.

[0230] Optionally, the target control quantity determination module 404 is specifically configured to determine a first tracking speed according to the first curve, determine a second tracking speed according to the second curve, and determine the smaller value of the first tracking speed and the second tracking speed as the tracking speed.

[0231] Optionally, the to-be-selected curve fitting module 406 is specifically configured to:

[0232] The following formula is used to determine the corresponding mapped remaining duration curve from the start of travel to the end of travel:

[0233]

[0234] t1 is the mapped remaining duration corresponding to running to the position point, t a is the expected total travel duration, t u is the travel duration of the train at different position points when the train travels along the to-be-selected curve, A and B are set coefficients, s l is the distance from the current position point to the end point, s t is the travel route distance.

[0235] Optionally, the target control quantity determination module 404 is specifically configured to,

[0236] Determine the expected output acceleration corresponding to at least one future control period according to the tracking speed;

[0237] Input the current state and the expected output accelerations of each control period into the acceleration prediction model. The acceleration prediction model performs control quantity prediction according to the current state and the expected output accelerations, and obtains a loss function value according to the difference between the acceleration output value corresponding to the predicted control quantity and the expected output acceleration. When the output loss function value meets the requirements, the target control quantity of this control period is output;

[0238] The current state includes the current travel speed, the output control quantity, the tracking speed, and the current acceleration.

[0239] Optionally, the target control quantity determination module 404 is specifically configured to,

[0240] Calculate the following objective function values:

[0241]

[0242] is the tracking speed corresponding to the future control period, is to determine the predicted speed according to the acceleration output value corresponding to the predicted control amount, and λ is the weighting coefficient, is the change value of the acceleration output value corresponding to the predicted control amount according to the future control period and the current acceleration;

[0243] Determine that under the condition that the difference between the objective function and the state reference value is less than the set value, the control amount corresponding to the minimum loss function value is the target control amount and output it. The state reference value is the objective function value corresponding to the speed change and acceleration change according to the smooth running state of the train.

[0244] Optionally, the target control amount determination module 404 is specifically used for,

[0245] According to the predicted control amount and / or the acceleration value corresponding to the predicted control amount, determine that the control amount corresponding to the minimum loss function value under at least one of the following constraints is the target control amount and output it:

[0246] The control amount does not exceed the maximum output of the traction motor;

[0247] The impact rate determined according to the acceleration ≤ 0.75m / s 3 ;

[0248] When controlling the train, the unbalanced centrifugal acceleration ≤ 0.4m / s 2 ;

[0249] The running speed is greater than or equal to zero.

[0250] After introducing the train track driving control method and device of the exemplary embodiment of the present application, next, an electronic device according to another exemplary embodiment of the present application is introduced.

[0251] Those skilled in the art can understand that various aspects of the present application can be implemented as a system, method or program product. Therefore, various aspects of the present application can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to as "circuit", "module" or "system" here.

[0252] In some possible embodiments, an electronic device according to the present application may at least include at least one processor and at least one memory. Among them, the memory stores program code, and when the program code is executed by the processor, the processor executes the steps in the train track driving control method according to various exemplary embodiments of the present application described above in this specification.

[0253] Reference is made below Figure 5 to describe the electronic device 130 according to this embodiment of the present application, that is, the train track driving control device. Figure 5 The electronic device 130 shown is only an example and should not impose any restrictions on the functions and usage scope of the embodiments of the present application.

[0254] As Figure 5 shown, the electronic device 130 is presented in the form of a general-purpose electronic device. The components of the electronic device 130 may include, but are not limited to: the above-mentioned at least one processor 131, the above-mentioned at least one memory 132, and a bus 133 connecting different system components (including the memory 132 and the processor 131).

[0255] The bus 133 represents one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a processor, or a local bus using any bus structure in a variety of bus structures.

[0256] The memory 132 may include a readable medium in the form of volatile memory, such as a random access memory (RAM) 1321 and / or a cache memory 1322, and may further include a read-only memory (ROM) 1323.

[0257] The memory 132 may further include a program / utilities 1325 having a set (at least one) of program modules 1324. Such program modules 1324 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. The implementation of a network environment may be included in each or some combination of these examples.

[0258] The electronic device 130 may also communicate with one or more external devices 134 (such as a keyboard, a pointing device, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 130, and / or communicate with any device (such as a router, a modem, etc.) that enables the electronic device 130 to communicate with one or more other electronic devices. Such communication may be carried out through the input / output (I / O) interface 135. Moreover, the electronic device 130 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 136. As shown in the figure, the network adapter 136 communicates with other modules for the electronic device 130 through the bus 133. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 130, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0259] In some possible implementation manners, each aspect of a train track driving control method provided in this application may also be implemented in the form of a program product, which includes program code. When the program product runs on a computer device, the program code is used to cause the computer device to execute the steps of a train track driving control method according to various exemplary implementation manners of this application described above in this specification.

[0260] The program product may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0261] The program product for monitoring in the implementation manner of this application may adopt a portable compact disc read-only memory (CD-ROM) and include program code, and may run on an electronic device. However, the program product of this application is not limited thereto. In this document, the readable storage medium may be any tangible medium that contains or stores a program, and this program may be used by or in combination with an instruction execution system, apparatus, or device.

[0262] A readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium can also be any readable medium other than a readable storage medium that can send, propagate, or transmit a program for use in or in conjunction with an instruction execution system, apparatus, or device.

[0263] The program code contained on the readable medium can be transmitted by any appropriate medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination of the above.

[0264] The program code for performing the operations of the present application can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's electronic device, partially on the user's device, executed as a stand-alone software package, partially on the user's electronic device and partially on a remote electronic device, or entirely on the remote electronic device or server. In the case of a remote electronic device, the remote electronic device can be connected to the user's electronic device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external electronic device (for example, by using an Internet service provider to connect through the Internet).

[0265] It should be noted that although several units or subunits of the apparatus are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more of the above-mentioned units can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0266] In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be decomposed into multiple steps for execution.

[0267] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0268] The present application is described with reference to the flowcharts and block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and block diagram can be implemented by computer program instructions, and the combination of the flows and blocks in the flowchart and block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one flow or multiple flows and blocks Figure 1 one block or multiple blocks.

[0269] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the specified functions in Figure 1 one flow or multiple flows and blocks Figure 1 one block or multiple blocks.

[0270] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0271] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. A train track driving control method, characterized in that, The method includes: Segmenting the driving route of the train to obtain position points corresponding to different segments; When it is set that each segment travels with the same acceleration, determining the first motion relationship between the driving speeds, accelerations, and segment distances of different position points in each segment, the second motion relationship between the driving speeds, driving times, and segment distances of different position points in each segment, and the speed range of the driving speeds of different position points in each segment; Taking the first motion relationship, the second motion relationship, the speed range, and the acceleration not exceeding the maximum acceleration as constraint conditions, and taking the minimum traction energy consumption as the objective function, to establish a speed prediction model; Using the speed prediction model to solve the first curve of the speeds corresponding to different position points that satisfy the constraint conditions; When triggering the train speed control, determining the tracking speed according to the first curve, and based on the current driving speed, the output control quantity, and the tracking speed, determining the target control quantity corresponding to reaching the tracking speed; Adjusting the currently output control quantity according to the target control quantity to control the driving speed of the train.

2. The method according to claim 1, characterized in that, The establishing of the speed prediction model includes: Taking the relationship defined by the following formula as a constraint condition, taking the minimum traction energy consumption as the objective function, setting the corresponding target driving time as the maximum driving time, and establishing a non-linear speed prediction model: 0≤v n ≤min(v n-1,max ,v n,max ) a min ≤ a n ≤ a max Among them, the segment [s n-1 , s n includes the (n - 1)-th position point s n-1 and the n-th position point s n , where v n is the speed of the n-th position point, v n-1 is the speed of the (n - 1)-th position point, a n is the acceleration of the segment [s n-1 , s n , r n is the basic resistance of the segment [s n-1 , s n , g n is the ramp resistance of the segment [s n-1 , s n , c n is the curve resistance of the segment [s n-1 , s n , t n is the time when the train travels to the position point s n , t n-1 is the time when the train travels to the position point s n-1 , v n-1,max is the maximum speed of the (n - 1)-th position point determined according to the speed range, v n,max is the maximum speed of the n-th position point determined according to the speed range, a min is the set minimum acceleration, a max is the maximum acceleration determined by the formula, v turn is the speed at the intermediate position determined according to the speed range, β 11 , β 12 , β 21 , β 22 are different set coefficients.

3. The method according to claim 1, wherein Taking the first motion relationship, the second motion relationship, the speed range, and the acceleration not exceeding the maximum acceleration as constraint conditions, and taking the minimum traction energy consumption as the objective function, the establishing of the speed prediction model includes: Taking the following motion relationship as a constraint condition: 2(a n -r n -g n -c n )(s n -s n-1 ) = v n 2 -v n-1 2 , 0≤v n 2 ≤min(v n-1,max 2 ,v n,max 2 ) a min ≤ a n ≤ a max ; Taking the following minimum traction energy consumption as the objective function, and establishing a speed prediction model: Among them, the segment [s n-1 , s n includes the (n - 1)-th position point s n-1 and the n-th position point s n , where v n is the speed of the n-th position point, v n-1 is the speed of the (n - 1)-th position point, a n is the acceleration of the segment [s n-1 , s n , r n is the basic resistance of the segment [s n-1 , s n , g n is the ramp resistance of the segment [s n-1 , s n , c n is the curve resistance of the segment [s n-1 , s n , t n is the time when the train travels to the position point s n , t n-1 is the time when the train travels to the position point s n-1 . is the coefficient corresponding to the conversion to a linear expression, v n-1,max is the maximum speed of the (n - 1)-th position point determined according to the speed range, v n,max is the maximum speed of the n-th position point determined according to the speed range, α1, α2 are set coefficients, a min is the set minimum acceleration, a max is the maximum acceleration determined by the formula, v turn is the speed at the intermediate position determined according to the speed range, β′ 11 , β′ 12 , β′ 21 , β′ 22 are different set coefficients.

4. The method according to claim 1, wherein It also includes: Fitting candidate curves of the speeds corresponding to different position points in each segment according to the speed limit conditions, and determining the driving times corresponding to the train traveling to different positions at the speeds on the candidate curves; Determining, when the train travels according to the candidate curve, the difference between the expected total driving duration and the driving durations of the train traveling to different position points, and the ratio of the distance from the current position point to the end point to the distance of the driving route, to obtain a mapping remaining duration curve corresponding to the start to the end of the driving; When it is determined that the relationship that the fitting degree between the mapping remaining duration curve and the actual remaining duration curve does not increase gradually with the increase of the driving duration is not satisfied, adjusting the candidate curve until the relationship is satisfied, and when the relationship is satisfied, taking the candidate curve as the second curve; Determining the tracking speed according to the first curve includes: Determining a first tracking speed according to the first curve, determining a second tracking speed according to the second curve, and determining the smaller value of the first tracking speed and the second tracking speed as the tracking speed.

5. The method according to claim 4, wherein Using the following formula to determine the mapping remaining duration curve corresponding to the start to the end of the driving: t1 is the remaining mapping duration corresponding to running to the position point, t a is the total expected driving duration, t u is the driving duration of the train when running to different position points according to the to-be-selected curve, A and B are set coefficients, s l is the distance from the current position point to the end point, s t is the driving route distance.

6. The method according to claim 1, wherein Based on the current driving speed, the output control quantity, and the tracking speed, determining the target control quantity corresponding to reaching the tracking speed includes: Determining the expected output acceleration corresponding to at least one future control period according to the tracking speed; Input the current state and the expected acceleration to be output in each control period into the acceleration prediction model. The acceleration prediction model predicts the control quantity based on the current state and the expected acceleration to be output. Obtain the loss function value according to the difference between the acceleration output value corresponding to the predicted control quantity and the expected acceleration to be output. Output the target control quantity of the control period corresponding to when the output loss function value meets the requirements. The current state includes the current driving speed, the output control quantity, the tracking speed, and the current acceleration.

7. The method according to claim 6, characterized in that The target control quantity of the control period corresponding to when the output loss function value meets the requirements includes: Calculate the following objective function value: is the tracking speed corresponding to the future control period, is to determine the predicted speed according to the acceleration output value corresponding to the predicted control amount, and λ is the weighting coefficient, is the change value of the acceleration output value corresponding to the predicted control amount according to the future control period and the current acceleration; Determine that the control quantity corresponding to the minimum loss function value is the target control quantity and output it under the condition that the difference between the objective function and the state reference value is less than the set value. The state reference value is the objective function value corresponding to the speed change and acceleration change according to the stable driving state of the train.

8. The method according to claim 6, characterized in that, The target control quantity of the control period corresponding to when the output loss function value meets the requirements includes: Determine that the control quantity corresponding to the minimum loss function value that meets at least one of the following constraints according to the predicted control quantity and / or the acceleration value corresponding to the predicted control quantity is the target control quantity and output it: The control quantity does not exceed the maximum output of the traction motor; The shock rate determined according to the acceleration ≤ 0.75 m / s 3 ; When controlling the train, the unbalanced centrifugal acceleration ≤ 0.4 m / s 2 ; The driving speed is greater than or equal to zero.

9. A train track driving control device, characterized in that, Includes at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-8.

Images