Train auxiliary driving method, system, equipment, medium and program

Abstract

The invention relates to a train auxiliary driving method, system and device, a storage medium and a computer program, and the method comprises the steps: obtaining the state data of a target train during operation, and calculating the index data according to the state data; generating a multi-target dynamic constraint function according to the index data; performing multi-target dynamic optimization according to the multi-target dynamic constraint function to obtain a train speed curve and a recommended working condition; and performing driving assistance on the target train according to the train speed curve and the recommended working condition. The method effectively assists the driver in driving, and improves the running safety and running efficiency of the train.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence assisted driving, and in particular to a train assisted driving method, system, device, medium and program. Background Art

[0002] As one of the main modes of land transportation, railway transportation has been expanding in scale since its birth in the last century. By the end of 2015, more than 130 regions and countries in the world have railways, of which my country's total operating mileage has reached 121,000 kilometers. With the rapid increase in the number of trains, train accidents caused by train failures and human errors are increasing. For drivers, drivers not only need to visually observe the line conditions ahead, but also need to make comprehensive judgments based on information such as train signals, line conditions and dispatching orders, which reduces the safety and efficiency of train operation.

[0003] In the existing technology, train drivers mainly control trains based on static control prompt cards generated by offline information and combined with driving experience. When the line conditions change and become complex, the driver's work becomes more difficult, which can easily lead to improper control and safety hazards, making it difficult for the driver to drive and the train running efficiency is low. Therefore, how to effectively assist the driver in driving and improve the train running efficiency has become an urgent problem to be solved. Summary of the invention

[0004] The present invention provides a train assisted driving method, system, device, medium and program to solve the problem of assisted driver driving and low train operation efficiency.

[0005] In a first aspect, the present disclosure provides a train assisted driving method, comprising:

[0006] Acquire the state data of the target train during operation, and calculate the index data according to the state data;

[0007] Generate a multi-objective dynamic constraint function according to the indicator data;

[0008] Perform multi-objective dynamic optimization according to the multi-objective dynamic constraint function to obtain a train speed curve and a recommended operating condition;

[0009] Driving assistance is provided to the target train according to the train speed curve and the recommended operating condition.

[0010] In some embodiments, calculating indicator data according to the status data includes:

[0011] Obtaining a processing formula corresponding to the status data;

[0012] The corresponding status data is subjected to index calculation according to the processing formula to obtain index data.

[0013] In some embodiments, generating a multi-objective dynamic constraint function according to the indicator data includes:

[0014] Generate multiple objective functions according to the indicator data;

[0015] A multi-objective dynamic constraint function is constructed according to the predefined constraint conditions and the objective function.

[0016] In some embodiments, constructing a multi-objective dynamic constraint function according to the predefined constraint conditions and the objective function includes:

[0017] Generating a weighted speed difference function according to the speed difference function and a preset weighting function;

[0018] A first target dynamic constraint function is generated according to a preset speed difference threshold condition and the weighted speed difference function.

[0019] In some embodiments, constructing a multi-objective dynamic constraint function according to the predefined constraint conditions and the objective function includes:

[0020] Generating a weighted time difference function according to the time difference function and a preset weighting function;

[0021] A second target dynamic constraint function is generated according to a preset time difference threshold condition and the weighted time difference function.

[0022] In some embodiments, constructing a multi-objective dynamic constraint function according to the predefined constraint conditions and the objective function includes:

[0023] Generating a weighted signal change function according to the signal change function and a preset weighting function;

[0024] A first target dynamic constraint function is generated according to a preset signal change threshold condition and the weighted signal change function.

[0025] In some embodiments, constructing a multi-objective dynamic constraint function according to the predefined constraint conditions and the objective function includes:

[0026] generating a weighted power loss function according to the power loss function and a preset weighting function;

[0027] A first target dynamic constraint function is generated according to a preset power threshold condition and the weighted power loss function.

[0028] In some embodiments, performing multi-objective dynamic optimization according to the multi-objective dynamic constraint function to obtain a train speed curve and a recommended operating condition includes:

[0029] Constructing a multi-objective model according to the multi-objective dynamic constraint function;

[0030] Performing model discretization and linear approximation on the multi-objective model to obtain a multi-objective optimization model;

[0031] Using an optimization algorithm to generate a curve according to the target optimization model to obtain a train speed curve;

[0032] The target data corresponding to the train speed curve and the preset optimization constraint conditions are calculated to obtain the recommended operating conditions corresponding to the train speed curve.

[0033] In some embodiments, the step of generating a curve according to the target optimization model using an optimization algorithm to obtain a train speed curve includes:

[0034] Obtaining initial train speed curve;

[0035] In the target optimization model, calculation is performed according to the initial train speed curve and the preset curve weight to obtain an optimization target function;

[0036] The initial train speed curve is updated according to the optimization objective function and preset optimization constraints to obtain a train speed curve.

[0037] In some embodiments, the calculation is performed according to the target data corresponding to the train speed curve and the preset optimization constraint conditions to obtain the recommended operating condition corresponding to the train speed curve, including:

[0038] Generating a safety evaluation index function according to target data corresponding to the train speed curve and a preset curve weight;

[0039] A first optimization objective function is generated according to a preset safety threshold condition and the safety evaluation index function.

[0040] The optimization data corresponding to the first optimization objective function is used as the corresponding recommended operating condition.

[0041] In some implementation columns, the calculation is performed according to the target data corresponding to the train speed curve and the preset optimization constraint conditions to obtain the recommended operating condition corresponding to the train speed curve, including:

[0042] generating an error tolerance function according to target data corresponding to the train speed curve and a preset curve weight;

[0043] A third optimization objective function is generated according to a preset time error threshold condition and the error allowable function.

[0044] The optimization data corresponding to the third optimization objective function is used as the corresponding recommended operating condition.

[0045] In some embodiments, the performing driving assistance on the target train according to the train speed curve and the recommended operating condition includes:

[0046] Monitoring the target train to obtain monitoring data;

[0047] Comparing the monitoring data with the train speed curve and data corresponding to the recommended operating condition to obtain difference data;

[0048] An early warning notification is issued to the target train corresponding to the difference data.

[0049] In a second aspect, the present disclosure provides a train assisted driving method device, comprising:

[0050] A data calculation module, used to obtain the state data of the target train during operation, and calculate the index data according to the state data;

[0051] A function generation module, used to generate a multi-objective dynamic constraint function according to the indicator data;

[0052] A dynamic optimization module, used for performing multi-objective dynamic optimization according to the multi-objective dynamic constraint function to obtain a train speed curve and a recommended operating condition;

[0053] A driving assistance module is used to provide driving assistance to the target train according to the train speed curve and the recommended operating condition.

[0054] In a third aspect, the present disclosure provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the above aspects.

[0055] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described in the above aspects when executed by a processor.

[0056] In a fifth aspect, the present disclosure provides a computer program product, including a computer program, which implements the steps of the method described in the above aspects when executed by a processor.

[0057] The present application discloses a train assisted driving method, system, device, medium and program, which removes abnormal data such as noise data from status data to ensure the accuracy and reliability of the obtained status data, and converts the status data into quantifiable index data, so as to facilitate the subsequent construction of a multi-objective dynamic constraint function. According to the multi-objective dynamic constraint function, the constraint conditions can be dynamically adjusted to ensure that the train achieves a better operating state in multiple dimensions and reduces energy consumption and operating time; multi-objective dynamic optimization is performed according to the multi-objective dynamic constraint function to obtain a train speed curve and recommended operating conditions, thereby providing driving assistance for the target train, achieving precise control and early warning of the target train, providing precise driving guidance for the train driver, and effectively improving the safety and stability of train operation, and improving the train operation efficiency and the driver's driving efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The present disclosure will be described in more detail below based on embodiments and with reference to the accompanying drawings:

[0059] Figure 1 A flow chart of a train assisted driving method provided by an embodiment of the present disclosure;

[0060] Figure 2 A schematic diagram of functional modules of a train auxiliary driving device provided in an embodiment of the present disclosure;

[0061] Figure 3 A schematic diagram of the structure of an electronic device of a train assisted driving method provided in an embodiment of the present disclosure.

[0062] In the drawings, the same reference numerals are used for the same components, and the drawings are not drawn to scale. DETAILED DESCRIPTION

[0063] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, and to fully understand and implement how the present disclosure applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. The embodiments of the present disclosure and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0064] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0065] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0066] The embodiment of the present disclosure provides a train assisted driving method. The execution subject of the train assisted driving method includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the system provided by the embodiment of the present disclosure. In other words, the train assisted driving method can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0067] Embodiment 1

[0068] Figure 1 A flow chart of a train assisted driving method provided by an embodiment of the present disclosure is shown as follows: Figure 1 As shown, the train assisted driving method includes:

[0069] S1. Obtain the status data of the target train during operation, and calculate the index data according to the status data.

[0070] In the embodiment of the present invention, the state data refers to the state information of the train during operation, including train system time, train number, train operating condition, train speed, train running direction, train pipe pressure, train tail pressure, train position, train signal, line speed limit, train traction and other train state information;

[0071] The index data refers to the required parameters calculated with the goals of safety, stability, punctuality and energy saving, including safety indicators, stability indicators, punctuality indicators, energy saving indicators, such as weighted speed difference, actual train power, signal light color and other required parameters.

[0072] In an embodiment of the present invention, the state data of the target train during operation can be obtained through an on-board sensor, such as a speed sensor, which is based on the photoelectric effect and detects the train wheel speed by inducing magnetic fields, electromagnetic waves or light signals to obtain state data such as train speed; such as a pressure sensor, which is based on capacitance changes, etc., and obtains train pipe pressure, train air pressure and other state data by monitoring pressure changes. The on-board sensor converts the real-time measured state data into electrical signals or digital signals, and transmits them to the preset train system by wireless means, thereby facilitating the calculation of subsequent indicator data.

[0073] In the embodiment of the present invention, the step of calculating the indicator data according to the status data includes:

[0074] Obtaining a processing formula corresponding to the status data;

[0075] The corresponding status data is subjected to index calculation according to the processing formula to obtain index data.

[0076] In detail, the processing formulas include acceleration calculation formula, traction force calculation formula, train displacement calculation formula, power calculation formula, etc.

[0077] In detail, the present invention can obtain the distribution characteristics and change laws of the status data based on the statistical characteristics of the status data, such as setting abnormal thresholds for the mean and standard deviation, and treating the status data exceeding the abnormal threshold as abnormal data and eliminating them, and then selecting a suitable calculation formula, i.e., a processing formula, to perform index calculation based on its distribution characteristics and change laws, thereby obtaining index data. The processing formula can be a formula based on physical principles, mathematical models or empirical definitions; for example, if the status data is the initial speed and the final speed of the train, and the index data is the acceleration of the train, the definition formula of acceleration (acceleration = (final speed - initial speed) / time) is used to calculate the index data.

[0078] Specifically, the processed state data is calculated by a formula to obtain the index data. If the weighted speed is calculated, if V i is the velocity at the i-th moment, ti is the duration of the i-th moment, T total is the sum of all time periods, that is, the total time, then the weighted speed is

[0079] If the basic resistance of the train is calculated, if V i is the speed in the i-th time period, a, b, c are resistance parameters, which are determined by the train model and structure, then the basic resistance of the train is For example, if V i is the speed in the i-th time period, P is the train power, then the train traction force is F = P / V i Similarly, all the indicator data can be calculated by corresponding calculation formulas to obtain the indicator data.

[0080] Furthermore, in the present invention, if it is known that the average speed of the target train is 100 km / h and the power of the target train is 10000 kW, the traction force of the target train is calculated to be 100 N through the calculation formula.

[0081] In the embodiment of the present invention, the accuracy and reliability of the obtained state data are ensured by removing abnormal data such as noise data from the state data, and then the calculation formula corresponding to the state data is obtained, thereby facilitating the subsequent calculation of indicator data.

[0082] S2. Generate a multi-objective dynamic constraint function according to the indicator data.

[0083] In an embodiment of the present invention, the multi-objective dynamic constraint function refers to a function that simultaneously optimizes multiple objective functions during the optimization process, and the objective functions and constraints change over time; the multi-objective dynamic constraint function includes multi-objective dynamic constraint functions such as speed deviation, time deviation, signal change, and power loss.

[0084] In the embodiment of the present invention, the step of generating a multi-objective dynamic constraint function according to the indicator data includes:

[0085] Generate multiple objective functions according to the indicator data;

[0086] A multi-objective dynamic constraint function is constructed according to the predefined constraint conditions and the objective function.

[0087] In detail, the objective function includes speed difference function, time difference function, signal change function, power loss function and other objective functions; the constraint conditions include speed difference threshold condition, time difference threshold condition, signal change threshold condition, power threshold condition.

[0088] In an embodiment of the present invention, different objective functions (speed difference function, time difference function, signal change function, power loss function, etc.) and corresponding constraints can generate different target dynamic constraint functions (first target dynamic constraint function, second target dynamic constraint function, third target dynamic constraint function, etc.).

[0089] Specifically, if the objective function is a speed difference function, the multi-objective dynamic constraint function is constructed according to the predefined constraint conditions and the objective function, including:

[0090] Generating a weighted speed difference function according to the speed difference function and a preset weighting function;

[0091] A first target dynamic constraint function is generated according to a preset speed difference threshold condition and the weighted speed difference function.

[0092] Specifically, if the index data is the train displacement x, the actual train speed V actual (x), optimized target speed V target (x), then the speed difference function can be generated as ΔV(x) = |V actual (x)-V target (x)|, according to the preset weighted function of train running time t and train displacement x as w(x,t), the weighted speed difference function ΔV can be generated weighted (x) = w(x, t) * ΔV(x), the preset speed difference threshold is ∈>0, then the multi-objective dynamic constraint function, i.e., the speed deviation, can be set to ΔV weighted (x)>ε*(1+m*e -nf(x) ), where m and n are parameters for adjusting the speed difference threshold, and f(x) is the function relationship between the train running time t and the train displacement x.

[0093] Furthermore, if the objective function is a time difference function, constructing a multi-objective dynamic constraint function according to the predefined constraint conditions and the objective function includes:

[0094] Generating a weighted time difference function according to the time difference function and a preset weighting function;

[0095] A second target dynamic constraint function is generated according to a preset time difference threshold condition and the weighted time difference function.

[0096] In detail, if the train schedule is set to specify the actual arrival time as t schedule , the running time corresponding to the optimized target speed is t optical , then the time difference function can be generated as Δt=|t schedule -t optical ∣, according to the preset train displacement Where L is the calculation step of displacement, p and q are the parameters for adjusting weights, and f(x) is the function relationship between train running time t and train displacement x. Then the weighted time difference function Δt can be generated. weighted (x) = w(x)*Δt, the preset time difference threshold is ε t >0, then the multi-objective dynamic constraint function, i.e., the time deviation, can be set to Δt weighted (x)>ε t .

[0097] Furthermore, if the objective function is a signal change function, constructing a multi-objective dynamic constraint function according to the predefined constraint conditions and the objective function includes:

[0098] Generating a weighted signal change function according to the signal change function and a preset weighting function;

[0099] A first target dynamic constraint function is generated according to a preset signal change threshold condition and the weighted signal change function.

[0100] In detail, it is known that there are 7 states of train signals, namely green light, yellow light, yellow double light, red and yellow light, double yellow light, red light, and white light. Suppose the state of the train signal at the previous moment is S prev , the current train signal status is S curr , then the signal change function can be generated as Δs = |S curr -S prev ∣, according to the preset index I to represent the impact of the traffic light state change, the weighted signal change function can be generated as Where v represents the speed of the train, d represents the distance between the train and the traffic light ahead, k represents the train load, and c(green) represents the weight factor corresponding to when the traffic light is green.

[0101] The present invention can set the weight factor to change the indicator impact when the traffic light changes. Similarly, other traffic lights can be set to different weight factors when they change state, such as I yellow ,I yellow 2.I redyellow ,I doubleyellow ,I red ,I white , the preset signal change threshold is ε I , when the train signal changes, that is, S prev ≠S curr When the corresponding index I is calculated, the multi-objective dynamic constraint function, i.e., the signal change, can be set to I>ε I .

[0102] Furthermore, if the objective function is a power loss function, constructing a multi-objective dynamic constraint function according to the predefined constraint conditions and the objective function includes:

[0103] generating a weighted power loss function according to the power loss function and a preset weighting function;

[0104] A first target dynamic constraint function is generated according to a preset power threshold condition and the weighted power loss function.

[0105] In detail, the rated power of the train is set to P rated The maximum power that the train can exert while running is set as P max , then the power difference ratio is Then the power loss function can be generated as Where v represents the train speed, d represents the distance to the front signal light, k represents the train load, and c(S) represents the weight factor corresponding to the signal light color. When the maximum power of the train is less than the rated power due to a locomotive equipment failure, a weighted power loss function can be generated as: The preset power threshold is ε p , then the multi-objective dynamic constraint function, i.e., power loss, can be set to P<ε p .

[0106] In an embodiment of the present invention, the state data is converted into quantifiable indicator data, so that a multi-objective dynamic constraint function is constructed to simultaneously consider multiple optimization objectives, ensure that the train achieves a better operating state in multiple dimensions, reduce unnecessary acceleration and deceleration processes, reduce energy consumption and operating time, and improve train operation efficiency.

[0107] S3. Perform multi-objective dynamic optimization according to the multi-objective dynamic constraint function to obtain a train speed curve and a recommended operating condition.

[0108] In an embodiment of the present invention, the multi-objective dynamic optimization refers to real-time, comprehensive optimization of the train with safety, stability, punctuality and energy saving as the goals. The multi-objective dynamic optimization not only considers various dynamic factors during the operation of the train, but also adjusts the speed curve and recommended operating conditions of the train to ensure that the train achieves the optimization of overall performance while meeting the above goals.

[0109] Furthermore, the train speed curve refers to the speed curve drawn during the operation of the train according to the specific conditions of the train operation (such as line conditions, vehicle performance, traffic rules, etc.) to ensure the safety and efficiency of the train; the recommended operating condition refers to the assisted driving of the train through the operating conditions of safety, stability, punctuality, energy saving, etc. through target data such as acceleration, constant speed, deceleration, and braking.

[0110] In the embodiment of the present invention, the multi-objective dynamic optimization is performed according to the multi-objective dynamic constraint function to obtain the train speed curve and the recommended operating condition, including:

[0111] Constructing a multi-objective model according to the multi-objective dynamic constraint function;

[0112] Performing model discretization and linear approximation on the multi-objective model to obtain a multi-objective optimization model;

[0113] Using an optimization algorithm to generate a curve according to the target optimization model to obtain a train speed curve;

[0114] The target data corresponding to the train speed curve and the preset optimization constraint conditions are calculated to obtain the recommended operating conditions corresponding to the train speed curve.

[0115] In detail, according to the multi-objective dynamic constraint function, the weighted coefficient method is used to integrate multiple objective functions and constraints into the multi-objective model. The weighted coefficient method refers to assigning a preset weight to each of the safety, stability, punctuality, and energy saving objectives, and calculating the weighted sum as a single objective function.

[0116] In the present invention, since the state data of the train during operation (such as speed, position, etc.) usually changes continuously, and the curve iteration algorithm based on quadratic programming is often better at dealing with discretization and linearization problems, it is necessary to discretize and linearize the multi-objective model.

[0117] The discretization refers to dividing the continuous time or space into several discrete intervals so as to solve the multi-objective model in each interval; the linear approximation refers to simplifying the nonlinear relationship in the multi-objective model into a linear relationship so as to reduce the complexity of the solution and improve the efficiency of the solution.

[0118] In detail, the present invention can clearly and intuitively represent the target data of the target train according to the generated train speed curve, generate recommended operating conditions according to the target data, and the train makes a reference for train driving according to the recommended operating conditions. The recommended operating conditions include train states such as acceleration and deceleration, traction, and braking, and assist in driving the train in terms of safety, stability, punctuality, energy saving, etc. For example, when the train is in a stable operating condition, it quickly accelerates to the driving speed during the train start-up phase, and in the process keeps the train speed stable to reduce energy consumption. According to the road speed limit or parking requirements, the stable operating condition is adopted in advance to ensure that the train decelerates or stops safely and smoothly.

[0119] In the embodiment of the present invention, the original multi-objective model can be transformed into a multi-objective optimization model that is easier to handle through discretization and linear approximation.

[0120] In the embodiment of the present invention, the step of generating a curve according to the target optimization model using an optimization algorithm to obtain a train speed curve includes:

[0121] Obtaining an initial train speed curve;

[0122] In the target optimization model, calculation is performed according to the initial train speed curve and the preset curve weight to obtain an optimization target function;

[0123] The initial train speed curve is updated according to the optimization objective function and preset optimization constraints to obtain a train speed curve.

[0124] In detail, the train operation history data and line data can be represented in the form of a time-speed relationship diagram, and then the initial objective function value is optimized and calculated according to the preset curve weight. The initial function value is iteratively calculated according to an optimization algorithm such as a genetic algorithm, a gradient descent method, etc., so as to obtain the optimized objective function. Finally, the initial train speed curve is updated according to the optimized objective function to finally obtain the train speed curve.

[0125] In an embodiment of the present invention, different target data (actual train speed, train traction force change rate, train running time, train traction force, etc.) and corresponding optimization constraints can generate different optimization objective functions (first optimization objective function, second optimization objective function, third optimization objective function, etc.).

[0126] In the embodiment of the present invention, multi-objective dynamic optimization such as safety, stability, punctuality, energy saving, etc. is performed according to the multi-objective dynamic constraint function.

[0127] Specifically, if the target data corresponding to the train speed curve is the actual train speed and the train running time, the recommended operating condition is a safety operating condition, and the optimization constraint condition is a safety threshold condition, the target data corresponding to the train speed curve and the preset optimization constraint condition are calculated to obtain the recommended operating condition corresponding to the train speed curve, including:

[0128] Generating a safety evaluation index function according to target data corresponding to the train speed curve and a preset curve weight;

[0129] A first optimization objective function is generated according to a preset safety threshold condition and the safety evaluation index function.

[0130] The optimization data corresponding to the first optimization objective function is used as the corresponding recommended operating condition.

[0131] Specifically, if the recommended operating condition is a safe operating condition, a safety evaluation index S is constructed. safety , the target data is the actual train speed V actual, line speed limit V lim , then the ratio of the actual train speed to the line speed limit is Consider the impact of train advance or delay and add time deviation normalization t represents the train running time. Considering the influence of locomotive signal change, the curve weight corresponding to the train speed curve, that is, the weight factor corresponding to the signal light is c(S), and the signal change normalization is designed. Where ΔS is the locomotive signal change, defined as the difference between the current signal state and the previous signal state, S max is the maximum change value of the signal state. If the power is lost during operation, the design indicator The influence of power loss on the safety evaluation index can be expressed as Among them, α, β, γ, and δ represent the weights of each part in the safety evaluation index. The preset optimization constraint condition is the safety threshold condition εs>0, which ensures that the actual safety evaluation index is less than the safety threshold condition, that is, the first optimization objective function corresponding to the safety condition is S safety <εs.

[0132] Furthermore, if the target data corresponding to the train speed curve is the train traction force change rate Δf(x), the recommended working condition is the stable working condition, and the optimization constraint condition is the stable threshold condition, that is, the upper limit of the traction force change rate Δf lim (x), the rate of change of the train traction and braking force during the whole operation is Δf(x)<Δf lim (x), that is, the second optimization objective function corresponding to the stable working condition is Δf(x)<Δf lim (x).

[0133] Further, if the target data corresponding to the train speed curve is the train running time, the recommended operating condition is the punctuality operating condition, and the optimization constraint condition is the time error threshold condition, the calculation is performed according to the target data corresponding to the train speed curve and the preset optimization constraint condition to obtain the recommended operating condition corresponding to the train speed curve, including:

[0134] generating an error tolerance function according to target data corresponding to the train speed curve and a preset curve weight;

[0135] A third optimization objective function is generated according to a preset time error threshold condition and the error allowable function.

[0136] The optimization data corresponding to the third optimization objective function is used as the corresponding recommended operating condition.

[0137] Specifically, if the recommended operating condition is a punctual operating condition, the present invention is set on a straight track, and if the target data is the train running time t, the running time required by the timetable tp , then the actual error of train running time is Δt=|tt p |, according to the route curvature k and slope θ, the curve weight is the corresponding curvature slope adjustment factor f(k,θ), the curvature slope adjustment factor reflects the influence of curvature and slope on the error allowable value, according to the traction force F traction and train speed v, the curve weight is the corresponding traction speed adjustment factor g(F traction ,v), the traction force speed adjustment factor reflects the influence of traction force and speed on the error tolerance value; considering the two adjustment factors comprehensively, the error tolerance function can be generated as where ε base represents the allowable value of the basic error, and the preset optimization constraint is the time error threshold condition ε dynamic , ensuring that the actual error is less than the error threshold ε dynamic , that is, the third optimization objective function corresponding to the punctuality condition is

[0138] Furthermore, if the target data corresponding to the train speed curve is the train traction force, the recommended operating condition is the energy-saving operating condition, and the target data is the displacement x of the train at the i-th moment i , the train traction force F corresponding to the train displacement at the i-th moment t (x i ), the train braking force F corresponding to the train displacement at the i-th moment d (x i ), then the fourth optimization objective function corresponding to the energy-saving condition can be generated Wherein, Z represents the utilization rate of regenerative energy, and the entire line is divided into N sections with Δx as the step length of the line.

[0139] In the embodiment of the present invention, when the recommended operating condition is a safety operating condition, the present invention ensures that no safety accidents will occur during the operation of the train, including avoiding collisions with other trains or obstacles, ensuring stable operation of the train in bad weather or emergency situations, etc.; when the recommended operating condition is a stability operating condition, the present invention can improve the stability of the train operation and reduce the bumps and discomfort felt by passengers during the journey; when the recommended operating condition is a punctuality operating condition, the present invention can ensure that the train can arrive at each station on time according to the predetermined schedule; when the recommended operating condition is an energy-saving operating condition, the present invention can reduce the energy consumption during the operation of the train and reduce the impact on the environment.

[0140] In an embodiment of the present invention, multi-objective dynamic optimization is performed based on the multi-objective dynamic constraint function to obtain a train speed curve and recommended operating conditions, thereby reducing the bumps and discomfort felt by passengers during train travel, improving the passenger riding experience, and providing accurate driving guidance for train drivers or automatic driving systems to ensure that the train runs according to the optimized speed curve and recommended operating conditions.

[0141] S4. Perform driving assistance on the target train according to the train speed curve and the recommended operating condition.

[0142] In the embodiment of the present invention, the train speed curve and the recommended operating conditions and other information are displayed in real time through a preset human-computer interaction interface so that the driver can clearly understand the current operating status of the train and perform manual intervention as needed.

[0143] In an embodiment of the present invention, the step of providing driving assistance to the target train according to the train speed curve and the recommended operating condition includes:

[0144] Monitoring the target train to obtain monitoring data;

[0145] Comparing the monitoring data with the train speed curve and data corresponding to the recommended operating condition to obtain difference data;

[0146] An early warning notification is issued to the target train corresponding to the difference data.

[0147] In detail, the monitoring data is obtained through on-board sensors, such as a speed sensor, which is based on the photoelectric effect and detects the rotation speed of the train wheels by inducing magnetic fields, electromagnetic waves or light signals, thereby obtaining monitoring data such as the train speed. The monitoring data is compared with the data corresponding to the train speed curve and the recommended operating conditions according to a data comparison algorithm to obtain difference data. If a target train does not run according to the train speed curve and the recommended operating condition data, such as if the speed is too fast, too slow, or fails to perform operations such as reversing or braking at a designated position, an early warning will be immediately issued. The early warning notification may be presented to the train driver in the form of sound, light signals or text information on a display screen to remind him to pay attention and take corresponding corrective measures.

[0148] In the embodiment of the present invention, driving assistance is performed on the target train according to the train speed curve and the recommended operating conditions, thereby achieving precise control and early warning of the target train, ensuring that the train runs in a safe and stable state, reducing the risk of accidents, effectively improving the safety and stability of train operation, and improving driving efficiency and passenger comfort.

[0149] In an embodiment of the present invention, by removing abnormal data such as noise data from state data to ensure the accuracy and reliability of the obtained state data, the state data is converted into quantifiable index data, which is convenient for the subsequent construction of a multi-objective dynamic constraint function. According to the multi-objective dynamic constraint function, the constraint conditions can be dynamically adjusted to ensure that the train achieves a better operating state in multiple dimensions and reduces energy consumption and operating time; multi-objective dynamic optimization is performed according to the multi-objective dynamic constraint function to obtain a train speed curve and recommended operating conditions, thereby providing driving assistance for the target train, achieving precise control and early warning of the target train, providing accurate driving guidance for the train driver, and effectively improving the safety and stability of the train operation, and improving the train operation efficiency and the driver's driving efficiency.

[0150] Embodiment 2

[0151] like Figure 2 , which is a functional module diagram of a train auxiliary driving device 100 provided for this embodiment.

[0152] The train auxiliary driving device 100 of the present invention can be installed in an electronic device. According to the functions to be implemented, the train auxiliary driving device 100 can include a data calculation module 101, a function generation module 102, a dynamic optimization module 103, and a driving assistance module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0153] In this embodiment, the functions of each module / unit are as follows:

[0154] A data calculation module 101 is used to obtain the state data of the target train during operation and calculate the index data according to the state data;

[0155] A function generation module 102, used to generate a multi-objective dynamic constraint function according to the indicator data;

[0156] A dynamic optimization module 103, configured to perform multi-objective dynamic optimization according to the multi-objective dynamic constraint function to obtain a train speed curve and a recommended operating condition;

[0157] The driving assistance module 104 is used to provide driving assistance to the target train according to the train speed curve and the recommended operating condition.

[0158] Embodiment 3

[0159] Figure 3 A schematic diagram of the structure of an electronic device of a train assisted driving method provided in an embodiment of the present disclosure.

[0160] On the basis of the above embodiments, this embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the above embodiments.

[0161] In some implementations of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0162] In some implementations of this embodiment, a computer program product is provided, including a computer program, characterized in that when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0163] The processor may include, but is not limited to, one or more processors or microprocessors, etc. Each processor may be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components to execute the methods in the above embodiments.

[0164] The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, and the computer-readable storage medium may include but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CD ROM, DVD ROM, Blu-ray disc, etc.).

[0165] The computer-readable storage medium may also store at least one computer executable program, such as a computer-readable instruction. The computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The computer-readable storage medium may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0166] In addition, the computer device may also include (but not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (eg, keyboard, mouse, speaker, etc.), etc.

[0167] The processor may communicate with a communication interface of an external device via an I / O bus via a wired or wireless network.

[0168] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product / computer program product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0169] In the embodiments provided in the present disclosure, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to the multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the above-mentioned module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0170] It should be noted that in the present disclosure, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element limited by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0171] Although the embodiments disclosed in the present disclosure are as above, the above contents are only embodiments adopted for facilitating the understanding of the present disclosure and are not intended to limit the present disclosure. Any technician in the technical field to which the present disclosure belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present disclosure, but the scope of patent protection of the present disclosure shall still be subject to the scope defined in the attached claims.

Claims

1. A train assisted driving method, characterized in that: include: Acquire the state data of the target train during operation, and calculate the index data according to the state data; Generate a multi-objective dynamic constraint function according to the indicator data; Perform multi-objective dynamic optimization according to the multi-objective dynamic constraint function to obtain a train speed curve and a recommended operating condition; Driving assistance is provided to the target train according to the train speed curve and the recommended operating condition.

2. The method according to claim 1, characterized in that The calculating the indicator data according to the status data comprises: Obtaining a processing formula corresponding to the status data; The corresponding status data is subjected to index calculation according to the processing formula to obtain index data.

3. The method according to claim 1, characterized in that The generating of a multi-objective dynamic constraint function according to the indicator data comprises: Generate multiple objective functions according to the indicator data; A multi-objective dynamic constraint function is constructed according to the predefined constraint conditions and the objective function.

4. The method according to claim 1, characterized in that: The multi-objective dynamic optimization is performed according to the multi-objective dynamic constraint function to obtain a train speed curve and a recommended operating condition, including: Constructing a multi-objective model according to the multi-objective dynamic constraint function; Performing model discretization and linear approximation on the multi-objective model to obtain a multi-objective optimization model; Using an optimization algorithm to generate a curve according to the target optimization model to obtain a train speed curve; The target data corresponding to the train speed curve and the preset optimization constraint conditions are calculated to obtain the recommended operating conditions corresponding to the train speed curve.

5. The method according to claim 4, characterized in that The step of generating a curve using an optimization algorithm according to the target optimization model to obtain a train speed curve includes: Obtaining an initial train speed curve; In the target optimization model, calculation is performed according to the initial train speed curve and the preset curve weight to obtain an optimization target function; The initial train speed curve is updated according to the optimization objective function and preset optimization constraints to obtain a train speed curve.

6. The method according to claim 1, characterized in that The performing driving assistance on the target train according to the train speed curve and the recommended operating condition includes: Monitoring the target train to obtain monitoring data; Comparing the monitoring data with the train speed curve and data corresponding to the recommended operating condition to obtain difference data; An early warning notification is issued to the target train corresponding to the difference data.

7. A train auxiliary driving device, characterized in that: include: A data calculation module, used to obtain the state data of the target train during operation, and calculate the index data according to the state data; A function generation module, used to generate a multi-objective dynamic constraint function according to the indicator data; A dynamic optimization module, used for performing multi-objective dynamic optimization according to the multi-objective dynamic constraint function to obtain a train speed curve and a recommended operating condition; A driving assistance module is used to provide driving assistance to the target train according to the train speed curve and the recommended operating condition.

8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images