Train Jumping Alignment Method, Device, Electronic Device and Storage Medium

Abstract

The present invention provides a train jump alignment method, device, electronic device and storage medium. The train jump alignment method is applied to the ATO of the train, and the method includes: determining a distance deviation value between the current stop position and the target stop position of the train; inputting the distance deviation value into a fuzzy controller to obtain a traction duration output by the fuzzy controller; based on the traction duration and the direction from the current stop position to the target stop position, outputting a traction command to the train, and after the duration of the train traveling based on the traction command reaches the traction duration, outputting a coasting and / or braking command to the train, so that the train stops in alignment after jumping; which can improve the jump accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of train intelligent control, and particularly to a train jump alignment method, device, electronic device and storage medium. Background Art

[0002] With the development of the fully automatic operation system, the accuracy requirements for fully automatic operation are getting higher and higher. When the train is in the fully automatic train operating mode (FAM) and creep automatic mode (CAM), when the train stops short of or overshoots the target position within a certain range during approach, the on-board controller controls the train to move forward or backward to realign and stop again, which is called "jump alignment". During the jump alignment process, it is necessary to continuously obtain the train position and the distance between the train and the stop point, and control the train to jump forward or backward according to the distance between the train and the stop point.

[0003] In the related art, after the jump distance of the train jump alignment reaches the preset distance, when the traction command is invalid and the traction level returns to zero, the train is controlled to decelerate and stop stably by outputting braking after a certain delay. This jump method makes the jump distance inflexible and can only jump a fixed distance. If the shortfall or overshoot distance is long, it is very likely that multiple jumps are required, and there is a possibility that the jump distance exceeds the expectation, that is, the low accuracy of jump alignment leads to low efficiency and poor practicability. In another related art, the train obtains the current position information through a transponder to determine the jump direction of the train, but there are errors and delays, so there are errors in calculating the jump distance. In actual jump tests, it often exceeds the preset distance, the jump accuracy is low, and during the jump process, traction is applied to control the vehicle to jump forward a certain distance and then braking is directly output, resulting in a poor riding experience.

[0004] Therefore, how to provide a train jump alignment method with improved jump alignment accuracy has become an urgent problem to be solved. Summary of the Invention

[0005] The present invention provides a train jump alignment method, device, electronic device and storage medium to solve the defect of low jump alignment accuracy in the prior art and achieve improved jump alignment accuracy.

[0006] The present invention provides a train jump alignment method applied to the ATO of a train. The method includes:

[0007] Determine the distance deviation value between the current stop position and the target stop position of the train;

[0008] Input the distance deviation value into a fuzzy controller to obtain the traction duration output by the fuzzy controller;

[0009] Output a traction command to the train based on the traction duration and the direction from the current parking position to the target parking position, and output a coasting and / or braking command to the train after the duration of the train traveling based on the traction command reaches the traction duration, so that the train stops in alignment after the jump.

[0010] According to a train jump alignment method provided by the present invention, the fuzzy controller includes a fuzzification interface, a knowledge base, an inference engine, and a defuzzification interface. The knowledge base includes a database and a rule base;

[0011] The fuzzification interface is used to perform fuzzification processing on the distance deviation value to obtain the membership degree of the distance deviation value;

[0012] The database is used to store the membership degree set, and the membership degree set includes the membership degree of the distance deviation value;

[0013] The inference engine is used to determine a fuzzy control quantity based on the membership degree corresponding to the distance deviation value, the fuzzy relationship corresponding to the rule base, and the traction duration adjustment coefficient. The traction duration adjustment coefficient is adjusted and determined based on the historical jump alignment results of the train;

[0014] The defuzzification interface is used to perform defuzzification processing on the fuzzy control quantity to obtain the traction duration.

[0015] According to a train jump alignment method provided by the present invention, the fuzzy relationship is expressed as:

[0016] R = (Oe × Ou) ∪ (Te × Tu) ∪ (Se × Su) ∪ (Be × BSu) ∪ (He × Hu);

[0017] Among them, the fuzzy sets corresponding to the distance deviation values are respectively expressed as: O, T, S, B, H; e represents the distance deviation value, and u represents the traction duration.

[0018] According to a train jump alignment method provided by the present invention, the inference engine is specifically used for:

[0019] Determine an initial fuzzy control quantity based on a first expression; the first expression is:

[0020] Obtain the fuzzy control quantity based on the initial fuzzy control quantity and the traction duration adjustment coefficient.

[0021] According to a train jump alignment method provided by the present invention, the defuzzification interface is specifically used to perform defuzzification processing on the fuzzy control quantity based on the principle of the maximum membership degree to obtain the traction duration.

[0022] A train jump alignment method provided by the present invention, the traction duration adjustment coefficient is adjusted and determined based on the following method:

[0023] Based on the traction duration and the direction from the current stop position to the target stop position, a traction command is output to the train, and after the duration of the train traveling based on the traction command reaches the traction duration, a coasting and / or braking command is output to the train, so that after the train jumps and aligns to stop, based on the direction of the train traveling based on the traction command, and the overshoot distance or undershoot distance of the train after jumping and aligning to stop, update the membership vector value change table of the traction duration adjustment coefficient;

[0024] Based on the membership vector value change table of the traction duration adjustment coefficient, update the traction duration adjustment coefficient.

[0025] The present invention also provides a train jump alignment device, which is applied to the ATO of the train. The device includes:

[0026] A first determination module, configured to determine the distance deviation value between the current stop position and the target stop position of the train;

[0027] A traction duration determination module, configured to input the distance deviation value into a fuzzy controller to obtain the traction duration output by the fuzzy controller;

[0028] An alignment stop module, configured to output a traction command to the train based on the traction duration and the direction from the current stop position to the target stop position, and after the duration of the train traveling based on the traction command reaches the traction duration, output a coasting and / or braking command to the train, so that the train jumps and aligns to stop.

[0029] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the train jump alignment method as described in any one of the above.

[0030] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the train jump alignment method as described in any one of the above.

[0031] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the train jump alignment method as described in any one of the above.

[0032] The train jump alignment method, device, electronic device and storage medium provided by the present invention can improve the jump accuracy by building a fuzzy controller in the ATO system and using the distance deviation value between the current stop position and the target stop position after the train stops stably as the input. After the fuzzy processing, reasoning and defuzzification processing of the fuzzy controller, the control quantity output by the fuzzy controller is obtained, and this control quantity is used as the traction duration to output the corresponding traction command for the train forward or backward. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0034] Figure 1 is a flowchart of the train jump alignment method provided by the present invention;

[0035] Figure 2 is a schematic diagram of the train under - alignment provided by the present invention;

[0036] Figure 3 is a flowchart of the train jump alignment provided by the present invention;

[0037] Figure 4 is a schematic structural diagram of the train jump alignment device provided by the present invention;

[0038] Figure 5 illustrates a schematic physical structure diagram of an electronic device. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] To make the objectives, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0040] First, the following content will be introduced:

[0041] In the related art, the Automatic Train Protection (ATP) system sends a jump command to the Automatic Train Operation (ATO) system. After a preset first time period elapses, it sends a direction command to both the train and the ATO simultaneously. After receiving the direction command, the train completes the jump preparation and sends a valid feedback of the direction command to the ATO. After receiving the direction command and the valid feedback, the ATO delays for a preset second time period and then sends a traction command to the train's traction system. After sending the traction command to the train's traction system, the ATO delays for a preset third time period and then sends a command with a preset traction level to the train's traction system, so that the traction system outputs traction force according to the traction command and the preset traction level to control the train to jump in the jump direction. After the jump distance reaches the preset distance, the traction command received by the traction system becomes invalid and the traction level returns to zero. After a preset fourth time period elapses, the ATO sends a braking command with a preset braking level to the train's braking system, so that the braking system outputs braking force according to the braking command to control the train to decelerate until it stops stably. After the train stops stably, after a preset fifth time period elapses, the ATO sends a jump completion message to the ATP, so that the ATP determines that the current jump is completed after receiving the jump completion message.

[0042] However, after the jump distance reaches the preset distance, the traction command becomes invalid and the traction level returns to zero, and then the train is controlled to decelerate and stop stably by outputting braking after a certain delay. This jump method makes the jump distance inflexible and can only jump a fixed distance. If the under-standard or over-standard distance is long, it is very likely that multiple jumps are required, and there is also a possibility that the jump distance exceeds the expectation, resulting in low efficiency and poor practicability.

[0043] In the related art, the jump direction of the train can also be determined based on the target stop position and the current stop position of the train, and the train's traction system is controlled to traction the train in the jump direction with a preset first traction torque. During the process from the start of traction to the maximum jump control time, the current position of the train is periodically obtained. If it is determined that the distance between the current position obtained in this cycle and the target stop position is less than or equal to the preset stop distance threshold, the train's braking system is controlled to brake the train with a preset braking torque, so that the train decelerates until it stops stably.

[0044] However, the ultimate goal of jump alignment is to solve the problem of accurate alignment and parking. In the second prior art solution, there are errors and delays in the train obtaining the current position information through the transponder. Therefore, there are errors in calculating the jump distance, and it often exceeds the preset distance in actual jump tests, resulting in low jump accuracy. Moreover, during the jump process, after applying traction to control the vehicle to jump forward a certain distance, braking is directly output, resulting in a poor riding experience.

[0045] Therefore, the present invention provides a train jump alignment method, device, electronic device and storage medium, which can improve the accuracy of jump alignment.

[0046] The train jump alignment method, device, electronic device and storage medium of the present invention will be described below with reference to the accompanying drawings.

[0047] Figure 1 It is a flowchart of the train jump alignment method provided by the present invention. As Figure 1 shown, this method is applied to the ATO of the train, that is, the execution subject of this train jump alignment method is the ATO of the train. This train jump alignment method includes:

[0048] Step 100, determining the distance deviation value between the current stop position and the target stop position of the train;

[0049] Step 110, inputting the distance deviation value into a fuzzy controller to obtain the traction duration output by the fuzzy controller;

[0050] Step 120, based on the traction duration and the direction from the current stop position to the target stop position, outputting a traction command to the train, and after the duration of the train traveling based on the traction command reaches the traction duration, outputting a coasting and / or braking command to the train, so that the train stops in alignment after jumping.

[0051] Specifically, the present invention takes the distance deviation value between the current stop position and the target stop position after the train stops stably as the input. After the fuzzy processing, reasoning and defuzzification processing of the fuzzy controller, the control quantity of the fuzzy controller, that is, the traction duration, is output. The ATO can output a traction command with a corresponding duration forward or backward to the train according to the traction duration output by the fuzzy controller, which can solve the defects of low efficiency and low jump accuracy caused by outputting a fixed-time traction command to the train in the related art, and can also solve the defect of low jump accuracy caused by outputting a train control command according to whether a preset distance is reached in the related art.

[0052] Among them, the ATO outputs a coasting and / or braking command to the train so that the train stops in alignment after jumping. Specifically, it can be: the ATO outputs a forward or backward traction command with a corresponding duration and a fixed traction level to the train according to the traction duration output by the fuzzy controller, and after reaching the traction duration, outputs a coasting command to the vehicle. After a preset time, outputs a service braking command to the vehicle to control the train to decelerate until it stops stably.

[0053] Alternatively, the ATO outputs a coasting and / or braking instruction to the train to make the train stop accurately after jumping. Specifically, it can be that the ATO outputs a forward or backward traction instruction and a fixed traction level for a corresponding duration to the train according to the traction duration output by the fuzzy controller, and after reaching the traction duration, outputs a braking instruction to the vehicle to control the train to decelerate until it stops stably.

[0054] In one embodiment, after the train stops stably at the station in the FAM or CAM mode and is under or over the target position by a certain range, for example, within the range of 0.5 meters to 5 meters, the Automatic Train Operation (ATO) system of the train sends a forward or backward jump application to the Automatic Train Protection (ATP) system. After the ATP determines that the jump condition is met, it sends an instruction allowing the jump to the ATO. The ATO has a built-in fuzzy controller. The ATO inputs the distance deviation value between the current stopping position and the target stopping position of the train into the fuzzy controller. After the fuzzy controller performs fuzzyfication processing, inference, and defuzzification processing, it obtains the control quantity output by the fuzzy controller, that is, the traction duration. The ATO outputs a forward or backward traction instruction and a fixed traction level for a corresponding duration to the train according to the traction duration output by the fuzzy controller, and after reaching the traction duration, outputs a coasting instruction to the vehicle. After a preset time, it outputs a service braking instruction to the vehicle to control the train to decelerate until it stops stably.

[0055] For example, after the train stops stably at the station in the FAM or CAM mode and is 4.5 meters under the target position, the Automatic Train Operation (ATO) system of the train sends a forward jump application to the Automatic Train Protection (ATP) system. After the ATP determines that the jump condition is met, it sends an instruction allowing the jump to the ATO. The ATO has a built-in fuzzy controller. The ATO inputs the distance deviation value (-4.5 meters) between the current stopping position and the target stopping position of the train into the fuzzy controller. After the fuzzy controller performs fuzzyfication processing, inference, and defuzzification processing, it obtains the control quantity output by the fuzzy controller, that is, the traction duration t1. The ATO outputs a forward traction instruction and a preset fixed traction level A for a corresponding duration to the train according to the traction duration t1 output by the fuzzy controller, and after reaching the traction duration t1, outputs a coasting instruction to the vehicle. After a preset time (a fixed value t), it outputs a service braking instruction to the vehicle to control the train to decelerate until it stops stably.

[0056] For example, after the train stops stably at a station in the FAM or CAM mode and exceeds the mark by 1.5 meters, the Automatic Train Operation (ATO) system of the train sends a backward jump application to the Automatic Train Protection (ATP) system. After the ATP determines that the jump condition is met, it sends an instruction allowing the jump to the ATO. The ATO has a built-in fuzzy controller. The ATO inputs the distance deviation value (+1.5 meters) between the current stopping position and the target stopping position of the train into the fuzzy controller. After the fuzzy controller undergoes fuzzification processing, inference, and defuzzification processing, it outputs the control quantity of the fuzzy controller, that is, the traction duration t2. The ATO outputs a backward traction instruction of the corresponding duration and a preset fixed traction level B to the train according to the traction duration t2 output by the fuzzy controller, and after reaching the traction duration t2, it outputs a coasting instruction to the vehicle. After a preset time (fixed value t), it outputs a service braking instruction to the vehicle to control the train to decelerate until it stops stably.

[0057] In the present invention, by building a fuzzy controller in the ATO system and using the distance deviation value between the current stopping position and the target stopping position after the train stops stably as the input, after the fuzzification processing, inference, and defuzzification processing of the fuzzy controller, the control quantity output by the fuzzy controller is obtained. Using this control quantity as the traction duration to output a traction instruction of the corresponding duration for the train to move forward or backward can improve the jump accuracy.

[0058] In some embodiments, the fuzzy controller includes a fuzzification interface, a knowledge base, an inference engine, and a defuzzification interface. The knowledge base includes a database and a rule base;

[0059] The fuzzification interface is used to perform fuzzification processing on the distance deviation value to obtain the membership degree of the distance deviation value;

[0060] The database is used to store the membership degree set, and the membership degree set includes the membership degree of the distance deviation value;

[0061] The inference engine is used to determine the fuzzy control quantity based on the membership degree corresponding to the distance deviation value, the fuzzy relationship corresponding to the rule base, and the traction duration adjustment coefficient, and the traction duration adjustment coefficient is adjusted and determined based on the historical jump alignment result of the train;

[0062] The defuzzification interface is used to perform defuzzification processing on the fuzzy control quantity to obtain the traction duration.

[0063] Specifically, the structure of building a fuzzy controller in the ATO system of the present invention includes: a fuzzification interface, a knowledge base, an inference engine, and a defuzzification interface.

[0064] Among them, the fuzzification interface can perform fuzzification processing on the input quantity of the fuzzy controller. For example, it performs fuzzification processing on the distance deviation value to obtain the membership degree of the distance deviation value;

[0065] The knowledge base includes a database and a rule base. The database stores the membership degree vector value change tables (i.e., membership degree sets) of all fuzzy sets of all input and output variables. Among them, the rule base includes fuzzy relations and traction duration adjustment coefficients. The fuzzy relations are determined based on expert knowledge or long-term accumulated experience from jump tests, and are a form of representation according to human intuitive reasoning. The fuzzy rules for determining fuzzy relations include if-then, else, also, end, or, etc. The database and the rule base provide data to the inference engine, such as fuzzy relations and traction duration adjustment coefficients;

[0066] The inference engine completes fuzzy inference based on the distance deviation value after fuzzy processing and the data in the knowledge base, and obtains a fuzzy control quantity, realizing the determination of the fuzzy control quantity based on the membership degree corresponding to the distance deviation value, the fuzzy relation corresponding to the rule base, and the traction duration adjustment coefficient.

[0067] It should be noted that the initial membership degree vector value change table in each embodiment of the present application can be determined by expert experience, and the membership degree vector value change table will be updated in combination with the data samples of the previous or multiple previous times each time a jump occurs. The membership degree vector value change table is used to determine the membership degree of the distance deviation value.

[0068] The fuzzy control quantity is converted through a defuzzification interface to obtain a clear control quantity output, and the traction duration is obtained.

[0069] In one embodiment, the design and application method of the built-in fuzzy controller in the ATO system includes:

[0070] (1) According to the operation experience of jump alignment, obtain the basic control rule: "If the distance deviation value between the current stop position and the target stop position is greater than 0.5m and less than 5m, then apply traction to the train. The greater the deviation, the longer the traction time."

[0071] (2) According to the above rules, determine the observed quantity (distance deviation value) and the control quantity (traction duration). Figure 2 This is a schematic diagram of the train being under the target of the present invention. As Figure 2 shown, define the position point of the ideal stop point O (target stop position) as LO, the current stop position as L, and the distance deviation value: |e| = □L = LO - L. Take the distance deviation value between the current stop position and point O as the observed quantity.

[0072] (3) Fuzzification of the input quantity and output quantity. Divide the distance deviation value e into five fuzzy sets: zero (O), tiny (T), small (S), large (B), huge (H). Divide it into seven change levels according to the change range of the distance deviation value: 0, 1, 2, 3, 4, 5, 6. Obtain the membership degree vector value change table of the distance deviation value, as shown in Table 1:

[0073] Table 1

[0074]

[0075] The control variable u is the time for outputting a traction command to the train. It is divided into five fuzzy sets: zero (O), tiny (T), small (S), large (B), and huge (H). The change range of u is divided into 9 levels: 0, 1, 2, 3, 4, 5, 6, 7, 8. The change table of the membership vector value of the control variable is obtained, as shown in Table 2:

[0076] Table 2

[0077]

[0078] (4) Description of fuzzy rules. According to operation experience, the following fuzzy rules are designed:

[0079] If e is O, then u is O;

[0080] If e is tiny, then u is tiny;

[0081] If e is small, then u is small;

[0082] If e is large, then u is large;

[0083] If e is huge, then u is huge.

[0084] The above fuzzy rules are described in the if-then form:

[0085] (1) if e = O then u = O;

[0086] (2) if e = T then u = T;

[0087] (3) if e = S then u = S;

[0088] (4) if e = B then u = B;

[0089] (5) if e = H then u = H

[0090] According to the above experience, the fuzzy control rule table is obtained, as shown in Table 3:

[0091] Table 3

[0092]

[0093] (5) Obtain the fuzzy relationship;

[0094] In some embodiments, the fuzzy relationship is expressed as:

[0095] R = (Oe × Ou) ∪ (Te × Tu) ∪ (Se × Su) ∪ (Be × BSu) ∪ (He × Hu);

[0096] Among them, the fuzzy sets corresponding to the distance deviation values are respectively represented as: O, T, S, B, H; e represents the distance deviation value, and u represents the traction duration.

[0097] Among them, the intersection is taken for the fuzzy set operations within the rules, and the union is taken for the fuzzy set operations between the rules, which is expressed as follows:

[0098]

[0099]

[0100]

[0101]

[0102]

[0103] Taking the union of the above five fuzzy matrices, we get:

[0104]

[0105] (6) Fuzzy decision-making: The control quantity is the composition of the distance deviation value and the fuzzy relationship;

[0106] Specifically, the control quantity can be expressed as:

[0107] For example, when the distance deviation value e is B, the control quantity of e is:

[0108]

[0109] = [0 0 0 0 0.5 0.5 1 0.5 0.5].

[0110] In some embodiments, the inference engine is specifically used for:

[0111] Based on the first expression, determine the initial fuzzy control quantity; the first expression is:

[0112] Based on the initial fuzzy control quantity and the traction duration adjustment coefficient, obtain the fuzzy control quantity.

[0113] Specifically, when the inference engine performs fuzzy decision-making, first based on Determine the initial fuzzy control quantity, and based on the initial fuzzy control quantity and the current latest traction duration adjustment coefficient, obtain the fuzzy control quantity, which can be similar to the calculation method of the initial fuzzy control quantity. The set of traction duration adjustment coefficients a obtained after the jump is combined with that before the jump The calculation results are combined again to calculate a new fuzzy control quantity

[0114] (7) Defuzzification of the control quantity.

[0115] Optionally, the defuzzification interface is specifically used to defuzzify the fuzzy control quantity based on the principle of maximum membership degree to obtain the traction duration. Specifically, it can be known from the fuzzy control rules that when the distance deviation value between the current parking position and the target parking position is large, the longer the traction time is output to the list. The control quantity output by the controller can be expressed as:

[0116]

[0117] If defuzzification is performed according to the "principle of maximum membership degree", and the fuzzy output with the maximum membership degree is selected as the result of defuzzification processing, then the control quantity u = 6 is selected, that is, the ATO outputs a longer traction time to the vehicle.

[0118] Among them, the "principle of maximum membership degree" (maximum membership principle) is the basic principle of fuzzy mathematics; in the specific calculation process, the fuzzy output with the maximum membership degree can be selected as the result of defuzzification processing to more accurately control the train jump.

[0119] In the present invention, by designing a fuzzy controller and using the distance deviation value between the current parking position and the target parking position after the train stops stably as the input of the fuzzy controller, the fuzzy controller performs fuzzy processing on the input quantity through the fuzzy interface to obtain the membership degree set of the input quantity and saves it in the database of the knowledge base. The inference engine calculates and synthesizes the fuzzy control quantity according to the membership degree set in the database and the traction duration adjustment coefficient in the rule base, and obtains the control quantity of the traction duration through defuzzification processing and outputs it to the ATO. The ATO outputs a traction command with a corresponding duration to the train according to the traction duration output by the fuzzy controller. Therefore, the train jump can be controlled more accurately, and the accuracy and efficiency of the train jump alignment can be greatly improved.

[0120] In some embodiments, the traction duration adjustment coefficient is adjusted and determined based on the following method:

[0121] Output a traction command to the train based on the traction duration and the direction from the current parking position to the target parking position. After the duration of the train's travel based on the traction command reaches the traction duration, output a coasting and / or braking command to the train so that after the train stops accurately after jumping, update the membership vector value table of the traction duration adjustment coefficient based on the direction of the train's travel based on the traction command and the overshoot distance or undershoot distance after the train stops accurately after jumping.

[0122] Update the traction duration adjustment coefficient based on the membership vector value table of the traction duration adjustment coefficient.

[0123] Specifically, ATO can control the train to apply traction forward or backward for the corresponding duration according to the traction duration output by the fuzzy controller. After that, ATO outputs a coasting command to the vehicle. After a preset time, ATO outputs a service braking command to the vehicle to control the train to decelerate until it stops stably. After stopping, ATO collects whether the train stops accurately after jumping. If it does not stop accurately, input the jumping result into the fuzzy controller, and the fuzzy controller updates the traction duration adjustment coefficient according to the jumping result.

[0124] Specifically, the fuzzy set of the traction duration adjustment coefficient a can be defined as five fuzzy sets: Negative Big (NB), Negative Small (NS), Zero (O), Positive Small (PS), Positive Big (PB). The relationship between the jumping result and a is as follows:

[0125] (1) If the undershoot distance is large after the train jumps forward, then a is Positive Big.

[0126] (2) If the undershoot distance is small after the train jumps forward, then a is Positive Small.

[0127] (3) If the train stops accurately after jumping forward or backward, then a is Zero.

[0128] (4) If the overshoot distance is small after the train jumps forward, then a is Negative Small.

[0129] (5) If the overshoot distance is large after the train jumps forward, then a is Negative Big.

[0130] (6) If the overshoot distance is large after the train jumps backward, then a is Positive Big.

[0131] (7) If the overshoot distance is small after the train jumps backward, then a is Positive Small.

[0132] (8) If the undershoot distance is small after the train jumps backward, then a is Negative Small.

[0133] (9) If the undershoot distance is large after the train jumps backward, then a is Negative Big.

[0134] It is divided into seven levels according to the change range of a: -3, -2, -1, 0, +1, +2, +3. The membership degree vector value change table of the traction duration adjustment coefficient a is obtained as shown in Table 4 below:

[0135] Table 4

[0136]

[0137] The membership degree vector value change table of the obtained traction duration adjustment coefficient a is synthesized with the traction duration adjustment coefficient currently stored in the rule base and saved as the latest traction duration adjustment coefficient. When jumping again, the initial fuzzy control quantity output is synthesized with the latest traction duration adjustment coefficient to obtain the final fuzzy control quantity.

[0138] As the number of jumps increases, more and more rules can be accumulated in the rule base, making the output control quantity more and more accurate, and ultimately making the train jump more and more accurately.

[0139] The present invention introduces the fuzzy control theory in the process of jumping and aligning to stop. By designing a fuzzy controller, the distance deviation between the current position of the train after stopping and the stop point is used as the input of the fuzzy controller. The fuzzy controller performs fuzzy processing on the input quantity through a fuzzification interface to obtain the membership degree set of the input quantity and saves it in the database of the knowledge base. The inference engine calculates and synthesizes to obtain the fuzzy control quantity according to the membership degree set in the database and the traction duration adjustment coefficient in the rule base, and obtains the control quantity of the traction time through defuzzification processing and outputs it to the ATO. According to the traction time control quantity output by the fuzzy controller, the ATO outputs a traction command for a corresponding time to the train. After the traction time ends, the ATO outputs a coasting command to the train. After a preset time, the ATO outputs a service braking command to the train to control the train to decelerate until it stops stably. After the train stops stably, the ATO inputs the jump result into the fuzzy controller, and the fuzzy controller obtains the latest traction duration adjustment coefficient through fuzzy processing and saves it in the rule base of the knowledge base as the basis for the next fuzzy control quantity inference.

[0140] In one embodiment, Figure 3 is the flow schematic diagram of the train jump alignment provided by the present invention, as Figure 3 shown, including the following steps:

[0141] Step 300, after the train stops stably, first the ATO determines whether the train is under the mark or over the mark by a certain range. If so, it jumps to step 310; if not, it jumps to step 380;

[0142] Step 310, the ATO can input the distance deviation value between the current stop position and the target stop position of the train into the fuzzy controller;

[0143] In step 320, after the fuzzy controller undergoes fuzzification processing, inference, and defuzzification processing, the control quantity output by the fuzzy controller, that is, the traction duration, is obtained.

[0144] In step 330, based on the traction duration output by the fuzzy controller, the ATO outputs a forward or backward traction command and a fixed traction level of the corresponding duration to the train.

[0145] In step 340, after the traction duration is reached, a coasting command is output to the vehicle.

[0146] In step 350, after a preset time, a service brake command is output to the vehicle to control the train to decelerate until it stops stably.

[0147] In step 360, after the train stops, the ATO collects whether the train is accurately stopped after jumping. If it is not accurately stopped, it jumps to step 370. If it is accurately stopped, it jumps to step 380.

[0148] In step 370, the jumping result is input into the fuzzy controller. The fuzzy controller updates the traction duration adjustment coefficient according to the jumping result, and then jumps to step 300.

[0149] In step 380, the jumping and alignment are completed.

[0150] Next, the train jumping and alignment device provided by the present invention will be described. The train jumping and alignment device described below can be mutually corresponding and referenced to the train jumping and alignment method described above.

[0151] Figure 4 is a schematic structural diagram of the train jumping and alignment device provided by the present invention. As Figure 4 shown, the train jumping and alignment device 400 is applied to the ATO of the train. The train jumping and alignment device 400 includes:

[0152] A first determination module 410, configured to determine the distance deviation value between the current stop position and the target stop position of the train.

[0153] A traction duration determination module 420, configured to input the distance deviation value into the fuzzy controller to obtain the traction duration output by the fuzzy controller.

[0154] An alignment and stop module 430, configured to output a traction command to the train based on the traction duration and the direction from the current stop position to the target stop position, and output a coasting and / or braking command to the train after the duration of the train traveling based on the traction command reaches the traction duration, so that the train stops in alignment after jumping.

[0155] It should be noted that the train jump alignment device of the present invention can implement the steps of the above-mentioned train jump alignment method and achieve the same technical effects, so it will not be elaborated here again.

[0156] Figure 5 An example of a schematic physical structure diagram of an electronic device is shown as Figure 5 shown. The electronic device may include: a processor 510, a communications interface 520, a memory 530, and a communication bus 540. Among them, the processor 510, the communications interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call the logical instructions in the memory 530 to execute the train jump alignment method, and the method includes:

[0157] Determine the distance deviation value between the current stop position and the target stop position of the train;

[0158] Input the distance deviation value into a fuzzy controller to obtain the traction duration output by the fuzzy controller;

[0159] Based on the traction duration and the direction from the current stop position to the target stop position, output a traction instruction to the train, and after the duration of the train traveling based on the traction instruction reaches the traction duration, output a coasting and / or braking instruction to the train, so that the train aligns and stops after jumping.

[0160] In addition, when the logical instructions in the above-mentioned memory 530 can be implemented in the form of software function units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. And the aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, etc., which can store program codes.

[0161] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the train jump alignment method provided by the above-mentioned various methods. The method includes:

[0162] Determine the distance deviation value between the current stop position and the target stop position of the train;

[0163] Input the distance deviation value into a fuzzy controller to obtain the traction duration output by the fuzzy controller;

[0164] Based on the traction duration and the direction from the current stop position to the target stop position, output a traction command to the train, and after the duration of the train traveling based on the traction command reaches the traction duration, output a coasting and / or braking command to the train, so that the train stops in alignment after the jump.

[0165] In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the train jump alignment method provided by the above-mentioned various methods. The method includes:

[0166] Determine the distance deviation value between the current stop position and the target stop position of the train;

[0167] Input the distance deviation value into a fuzzy controller to obtain the traction duration output by the fuzzy controller;

[0168] Based on the traction duration and the direction from the current stop position to the target stop position, output a traction command to the train, and after the duration of the train traveling based on the traction command reaches the traction duration, output a coasting and / or braking command to the train, so that the train stops in alignment after the jump.

[0169] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0170] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0171] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A train jump benchmarking method, characterized in that: The ATO applied to a train comprises: Determining a distance deviation value between a current parking position of the train and a target parking position; The distance deviation value is input into the fuzzy controller, and after the fuzzification processing, reasoning and defuzzification processing of the fuzzy controller, the traction time output by the fuzzy controller is obtained; the fuzzy controller uses the distance deviation value as the observation quantity and the traction time as the control quantity; wherein the defuzzification processing includes: performing defuzzification according to the maximum membership principle, and selecting the fuzzy output with the maximum membership as the result of the defuzzification processing; Based on the traction duration, and the direction from the current parking position to the target parking position, a forward or backward traction instruction of a corresponding duration and a preset fixed traction level are output to the train, and after the duration of the train's travel based on the traction instruction reaches the traction duration, an idling and / or braking instruction is output to the train so that the train stops at the mark after jumping.

2. The train jump benchmarking method according to claim 1, characterized in that: The fuzzy controller includes a fuzzification interface, a knowledge base, an inference engine and a defuzzification interface, and the knowledge base includes a database and a rule base; The fuzzification interface is used to perform fuzzification processing on the distance deviation value to obtain the degree of membership of the distance deviation value; The database is used to store a membership set, wherein the membership set includes the membership of the distance deviation value; The inference engine is used to determine the fuzzy control amount based on the membership degree corresponding to the distance deviation value, the fuzzy relationship corresponding to the rule base and the traction time adjustment coefficient, and the traction time adjustment coefficient is adjusted and determined based on the historical jump benchmarking result of the train; The defuzzification interface is used to perform defuzzification processing on the fuzzy control quantity to obtain the traction duration.

3. The train jump benchmarking method according to claim 2, characterized in that: The fuzzy relationship is expressed as: R=(Oe×Ou)∪(Te×Tu)∪(Se×Su)∪(Be×BSu)∪(He×Hu); Among them, the fuzzy sets corresponding to the distance deviation values ​​are represented as: O, T, S, B, H; e represents the distance deviation value, and u represents the traction time.

4. The train jump benchmarking method according to claim 3, characterized in that: The inference engine is specifically used for: Based on the first expression, the initial fuzzy control amount is determined; the first expression is: The fuzzy control amount is obtained based on the initial fuzzy control amount and the traction duration adjustment coefficient.

5. The train jump benchmarking method according to any one of claims 2 to 4, characterized in that: The defuzzification interface is specifically used to perform defuzzification processing on the fuzzy control quantity based on the maximum membership principle to obtain the traction duration.

6. The train jump benchmarking method according to claim 2, characterized in that: The traction duration adjustment coefficient is determined based on the following adjustment method: Based on the traction duration and the direction from the current parking position to the target parking position, a traction instruction is output to the train, and after the duration of the train's travel based on the traction instruction reaches the traction duration, an idling and / or braking instruction is output to the train, so that after the train stops at the mark after jumping, the membership vector value change table of the traction duration adjustment coefficient is updated based on the direction of the train's travel based on the traction instruction and the over-mark distance or under-mark distance of the train after the train stops at the mark after jumping; Based on the membership vector value change table of the traction duration adjustment coefficient, the traction duration adjustment coefficient is updated.

7. A train jump benchmarking device, characterized in that: The ATO applied to a train comprises: A first determination module is used to determine a distance deviation value between a current parking position of the train and a target parking position; A traction duration determination module is used to input the distance deviation value into a fuzzy controller, and obtain the traction duration output by the fuzzy controller after fuzzification processing, reasoning and defuzzification processing by the fuzzy controller; the fuzzy controller uses the distance deviation value as an observation quantity and the traction duration as a control quantity; wherein the defuzzification processing includes: performing defuzzification according to the maximum membership principle, and selecting the fuzzy output with the maximum membership as the result of the defuzzification processing; The target parking module is used to output a forward or backward traction instruction of a corresponding duration and a preset fixed traction level to the train based on the traction duration and the direction from the current parking position to the target parking position, and output an idling and / or braking instruction to the train after the duration of the train's travel based on the traction instruction reaches the traction duration, so that the train stops at the target after jumping.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the train jump benchmarking method as described in any one of claims 1 to 6 is implemented.

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

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

Images