COMPUTER IMPLEMENTED METHOD AND CONTROL DEVICE FOR DETERMINING REAL-TIME STEERING ANGLE - Patent application

Abstract

The present disclosure relates to a computer-implemented method for determining a real-time steering angle (58) of a railway bogie (1), and a control device (40) configured to perform the method, the method including determining, by a sensor assembly, at least one lateral real-time sensor signal (38) indicative of a lateral position characteristic of at least one wheel tread of the railway bogie (1) relative to the railway track, determining, by a positioning algorithm (47), a real-time position and / or orientation of the railway bogie (1) relative to the railway track (31) using the received at least one lateral real-time sensor signal (38), and determining a real-time steering angle (58) for steering the railway bogie (1) using the determined real-time position and / or orientation of the railway bogie (1).

Description

[Technical field]

[0001] The present disclosure relates to a computer-implemented method and control device for determining a real-time steering angle of a railway bogie. In particular, the present disclosure relates to a computer-implemented method for determining a real-time steering angle of a railway bogie, the method comprising a number of steps. Furthermore, the present disclosure relates to a control device for determining a real-time steering angle of a railway bogie, the control device comprising a processor configured to perform the number of steps for determining the real-time steering angle. [Background technology]

[0002] Rail vehicles coupled to rail tracks, such as trains, trams (streetcars, streetcars), or other vehicles, often exhibit less than optimal alignment of the wheels with respect to the track, which leads to higher friction between the rail track and the wheel treads. This contact, especially in curves with small radii, results in increased wear of both the wheel and rail profiles, known as Rail Contact Fatigue (RCF), and noise pollution. In the case of low-floor vehicles, this effect is even more pronounced. Low-floor vehicles feature smaller and fewer wheels per car to increase passenger comfort and interior space of the vehicle by having a continuous low-floor structure. However, this also results in increased loads per wheel and more pronounced fatigue of the material of the wheels, causing small cracks or even larger material failures.

[0003] Several attempts to reduce track and wheel wear are known. In the 1990s, systems were developed that allowed the wheels to be steered on curves. However, these solutions often turned out to suffer from undesirable side effects in straight track sections, such as the wheels sticking to the track on one side of the tread, leading to increased wear and noise in straight track sections. Therefore, after a few years, most of these concepts were abandoned and traditional concepts combined with wheel noise absorbers and advanced industrial lubricants were promoted again. In particular, a challenge was and still is to accurately and reliably determine the position and orientation of the bogie relative to the railway track while it is in motion.

[0004] One example of a rail bogie that successfully addresses these disadvantages is US Pat. No. 5,399,233, published in 2018 in the name of the same applicant. The vehicle disclosed comprises a wheel assembly interconnected to a chassis, as well as a method for steering said vehicle. The wheel assembly comprises a cross member having a first end, to which a first hub is interconnected by a first steering joint, and a second end, to which a second hub is interconnected by a second steering joint. A first wheel is mounted to the first hub rotatably about a first axis of rotation, and a second wheel is mounted to the second hub rotatably about a second axis of rotation.

[0005] Tram or streetcar running on narrow curved railroad tracks at relatively low speeds generates a lot of noise when the wheel flanges hit the railroad tracks while running, especially on curves. Even steered tram or streetcar does not have precise and fast steering to avoid the noise-causing contact of the wheel flanges on the railroad tracks. Noise is also generated when there is a stick-slip phenomenon between the wheels, which are generally connected by an axle, causing the wheels to rotate at different speeds as the vehicle travels around the curved track section. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] International Publication No. 2018015290 Summary of the Invention [Problem to be solved by the invention]

[0007] It is an object of the present disclosure to provide a computer-implemented method and control device for determining a real-time steering angle for a railway bogie. In particular, it is an object of the present disclosure to provide a computer-implemented method for determining a real-time steering angle for use by a railway bogie, and a control device for a railway bogie for determining a real-time steering angle for the railway bogie.

[0008] According to the present disclosure, these objects are addressed by the features of the independent claims. Further advantageous embodiments follow from the dependent claims and the description.

[0009] The present disclosure provides a computer-implemented method for determining real-time steering angles for a railway bogie. The method may include: determining, by the sensor assembly, at least one lateral real-time sensor signal characteristic of a lateral position of at least one wheel tread of the rail bogie relative to the rail track, the lateral position of the wheel tread determining the lateral distance of the tread, and thus the current real-time lateral distance of the wheel flange relative to the rail of the rail track, in particular during operation of the rail bogie on the rail track; - determining by a positioning algorithm a real-time position and / or orientation of the rail bogie relative to the rail track using the at least one received lateral real-time sensor signal. The positioning algorithm uses the at least one received lateral real-time sensor signal to determine the position and / or orientation of the rail bogie on the rail track. The position is for example a lateral displacement of the wheel flanges relative to a target or set lateral displacement value. In a variant, the real-time position may be a lateral displacement of the geometric center of the rail bogie relative to a current center of the rail track. The current center of the rail track is for example half the distance between the two rails of the rail track of the section of the rail track on which the rail bogie is currently running. The orientation of the rail bogie is for example determined by the angle between the axis of rotation of the wheel(s) and the main extension direction of the respective rail of the rail track. A target or set position is for example when the geometric center of the rail bogie is over the current center of the rail track and a target or set orientation is for example when the angle between the axis of rotation of the wheels and the respective rail is 90°. In other words, the axis of rotation extends perpendicular to the main direction of extension of the respective rail, or the rolling direction of the respective wheels is arranged tangentially to the respective rail (tangential angle of attack). - determining a real-time steering angle for steering the rail bogie using the determined real-time position and / or orientation of the rail bogie. Based on the current real-time position and / or orientation of the rail bogie during operation, the real-time steering angle is determined to steer the rail bogie towards or maintain the desired position / orientation relative to the rail track. If the set position and / or orientation match the determined position and / or orientation, no change in the current steering angle is required. If the set position and / or orientation do not match the determined position and / or orientation, a change in the real-time steering angle is required to guide the rail bogie back to the desired position. The real-time steering angle is, for example, an angle value or another value characteristic of the real-time steering angle.

[0010] For example, the lateral real-time sensor signals measured by at least one sensor of the sensor assembly determine, for example, the distance of the wheel flange to the track. In curves, this distance may change, which can be read or seen in the respective lateral real-time sensor signals. For example, the rail bogies should be individually steered to maintain the lateral distance within a certain range to avoid contact. With the determined real-time steering angle, it is possible to steer the rail bogie back to a desired position or to keep the rail bogie in a desired position during operation. Thus, undesired contact of the wheel flange with the rail can be avoided. This advantageously reduces wheel wear and avoids noise pollution during operation.

[0011] For advantageous determination of the position and / or orientation, the positioning algorithm may use a geometric algorithm that uses a specific geometric extension of the rail bogie. The geometric method may interpolate at least one received real-time sensor signal prior to or during determination of the position and / or orientation of the rail bogie.

[0012] In a variation of the disclosure, the computer-implemented method further comprises determining, by the sensor assembly, at least one vertical real-time sensor signal specific to a vertical position of at least a part of the sensor assembly relative to the railroad track, and additionally using the received vertical real-time sensor signal to determine a real-time position and / or orientation of the railroad bogie relative to the railroad track. The sensor assembly may comprise a dedicated sensor configured to measure the vertical real-time sensor signal. This sensor and the sensor for the lateral real-time sensor signal may be assembled as a sensor unit forming part of the sensor assembly. The vertical real-time sensor signal measures, for example, a vertical distance between the sensor itself and the rail. The real-time vertical distance is transmitted as the vertical real-time sensor signal and is used to determine the position and / or orientation of the railroad bogie on the railroad track by a positioning algorithm. The vertical distance may be used to determine on which type of track the railroad bogie is currently located. This information may affect the determination of the position and / or orientation of the railroad bogie. Different sections of the railroad track, such as junctions, switches or crossings, are distinguishable, for example, by the vertical position of the sensor relative to the rail. Some sections of railroad track lift the railroad bogie upwards, which is evident by the vertical real-time sensor signal. Further accuracy can be achieved by further using the vertical real-time sensor signal for determining the position and / or orientation of the railroad bogie. The vertical distance can further assist in determining any wear or tear condition of the railroad track profile.

[0013] In a variation of the present disclosure, the computer-implemented method further includes determining, by the sensor assembly, a first lateral real-time sensor signal characteristic of a lateral position of a tread of a first wheel of the rail car relative to the rail track, and a second lateral real-time sensor signal characteristic of a lateral position of a tread of a second wheel of the rail car relative to the rail track, and determining a real-time position and / or orientation of the rail car relative to the rail track using the received first and second lateral real-time sensor signals. In a variation, the first wheel and the second wheel are arranged parallel to each other. For example, the first wheel is configured to contact a first rail of the rail track, and the second wheel is configured to contact a second rail of the rail track. The first lateral real-time sensor signal, for example, characteristic of a first lateral distance between a flange of the first wheel and the first rail, and the second lateral real-time sensor signal characteristic of a second lateral distance between a flange of the second wheel and the second rail. The distance between the first rail and the second rail is not constant along the railway track. For example, at curves, at branching points or misalignment sections, the distance between the first rail and the second rail changes at least slightly. By taking into account the first and second lateral real-time sensor signals, the geometric center of the railway track is constantly updated, for example, based on the lateral real-time sensor signals, which increases the accuracy of the determination of the position and / or orientation of the railway bogie.

[0014] Preferably, the computer-implemented method further comprises determining, by the sensor assembly, a first vertical real-time sensor signal characteristic of a vertical position of the first vertical sensor relative to the railway track and a second vertical real-time sensor signal characteristic of a vertical position of the second vertical sensor relative to the railway track. Each wheel may be provided with a sensor unit having a first sensor for lateral measurement and a second sensor for vertical measurement.

[0015] Increased accuracy can be achieved if the computer-implemented method further includes determining, by the sensor assembly, a forward lateral real-time sensor signal characteristic of a forward lateral position of the tread of a wheel of the rail bogie relative to the rail track and a rearward lateral real-time sensor signal characteristic of a rearward lateral position of the tread of a second wheel of the rail bogie relative to the rail track. The sensor assembly may comprise a first lateral sensor located in front of the respective wheel and a second sensor located behind the respective wheel in terms of the direction of travel of the rail bogie. In a further variation, each of the wheels of the rail bogie comprises a forward lateral sensor and a rearward lateral sensor. For example, a tram bogie having two wheels may comprise four lateral sensors. The four real-time sensor signals are used to determine the position and / or orientation of the rail bogie. This advantageously increases the accuracy of the output signal.

[0016] In a further variation of the present disclosure, the computer-implemented method further includes determining, by the sensor assembly, a forward real-time vertical sensor signal characteristic of a forward vertical position of the sensor relative to the railroad track and a rearward real-time vertical sensor signal characteristic of a rearward vertical position of the rearward sensor relative to the railroad track. For example, each wheel of the railroad bogie may include a forward sensor in front of the respective wheel for measuring the real-time vertical sensor signal and a rearward sensor aft of the respective wheel for measuring the real-time vertical sensor signal.

[0017] The received rear real-time sensor signals (lateral and vertical) may be used, among other things, by the positioning algorithm for validation purposes of the forward real-time sensor signals.

[0018] In particular, the sensor assembly may comprise a front sensor unit and a rear sensor unit for each wheel. Each sensor unit comprises a first sensor for lateral measurement and a second sensor for vertical measurement, arranged adjacent to each other. A tram bogie with two wheels may comprise, for example, four sensor units, each providing a lateral real-time sensor signal and a vertical real-time sensor signal. A high number of sensor signals advantageously increases the accuracy of the determination of the real-time position and / or orientation of the rail bogie on the rail track during its operation.

[0019] In a variant, the rail bogie may comprise four wheels, e.g. two wheels on two axles, or four wheels with independent suspension within the rail bogie. The sensor assembly may be configured to determine real-time sensor signals (lateral and / or vertical, forward and / or rearward) of one wheel, two wheels, three wheels, and / or four wheels of such a rail bogie with four wheels. For example, steering of a train bogie, e.g. a train freight car or locomotive, a rail bogie with four wheels, non-driven or driven, may be difficult, especially since steering of one of the four wheels will probably also affect all of the wheels of the rail bogie. It may therefore be particularly important to monitor and control all lateral distances of all four wheels to the respective rails.

[0020] In a variant of the disclosure, the computer-implemented method further comprises adapting the at least one received real-time sensor signal using predetermined sensor calibration data. The sensor calibration data is, for example, rail bogie-specific or even track-specific data, collected, for example, during a test run along the planned operating route of the respective rail bogie. This sensor calibration data may be used continuously to adapt the received real-time sensor signal. The sensor calibration data may be used to identify and classify disturbances in the received sensor signal. In a further variant, adapting the at least one received real-time sensor signal is aided by at least a trained neural network. The input data of the neural network are raw sensor data and the output data are calibrated sensor data. The neural network is, for example, constantly updated based on the received sensor data and the resulting position and / or orientation of the rail bogie on the rail track.

[0021] In a variant of the disclosure, during the step of determining the real-time position and / or orientation of the rail bogie, the positioning algorithm filters at least one received real-time sensor signal, preferably a calibrated sensor signal, using at least one predefined filter parameter and determines, based on the result of the filtering, suitable real-time sensor signal data to be used for determining the real-time position and / or orientation of the rail bogie relative to the rail track. For example, very large signal deviations may result from signal disturbances or erroneous measurements. These signal deviations should be filtered out, which is performed by the positioning algorithm using the predefined filter parameters. The filter parameters may be replaced or changed during the operation of the rail bogie. For example, the filter parameters are different in straight sections of the rail track compared to curved sections of the rail track. The filtering allows to at least temporarily screen out non-suitable sensor signals. For example, at intersections or junctions, some sensor signals should not be used for determining the real-time position and / or orientation of the rail bogie.

[0022] The at least one predefined filter parameter is preferably dependent on at least one of: rail bogie type, rail car type, rail bogie load, rail bogie speed, and wheel size. The filter parameters may include fixed parameters and / or variable parameters that change over time.

[0023] Preferably, the step of determining the real-time steering angle further uses at least one predefined steering parameter, which may depend on the particular rail bogie, the current speed or load of the rail bogie, and / or further parameters of the rail bogie, or parameters of the rail track, such as the current rail track inclination angle, radius of curvature and / or the particular section. These steering parameters may be input data for the determination of the real-time steering angle.

[0024] Preferably, determining the real-time steering angle may further include using a feedforward control system. Particularly preferably, the predetermined steering parameters and / or other parameters may be used in such a feedforward control system, in particular a predictive control system (predictive feedforward control system). In other words, the predetermined steering parameters and / or other parameters may be used to determine a feedforward control signal as part of the real-time steering angle during the operation of the railway bogie. The feedforward control system improves the response speed of the system.

[0025] In a variation of the disclosure, the computer-implemented method further comprises the steps of transmitting the determined real-time steering angle to a steering actuator controller and / or controlling the steering actuator using the steering actuator controller to steer the railway bogie about the vertical steering axis using the real-time steering angle. The determined real-time steering angle or a corresponding value or signal is transmitted to the steering actuator controller configured to control the steering actuator according to the received real-time steering angle. In a variation, the steering actuator controller uses actuator controller parameters to adjust the control command to the steering actuator. The servo drive parameters may, for example, depend on characteristics of the steering actuator used in the railway bogie.

[0026] In a further variation of the present disclosure, in the step of determining the real-time position and / or orientation of the rail bogie, the positioning algorithm uses a neural network to determine the real-time position and / or orientation of the rail bogie relative to the rail track. At least one real-time sensor signal is input data of the neural network. The real-time position and / or orientation of the rail bogie relative to the rail track is output data of the neural network. The neural network is preferably a trained feed-forward neural network that provides a desired accuracy in the real-time determination of the position and / or orientation of the rail bogie. The input training data of the neural network are, for example, real-time sensor signal data in the lateral and vertical directions. The output training data for building (training) the neural network are the corresponding position and / or orientation of the rail bogie relative to the rail track. The neural network is, for example, a feed-forward neural network.

[0027] The neural network is preferably trained by using the neural network to determine a real-time position and / or orientation of the rail bogie relative to the rail track, controlling steering of the rail bogie based on the determined real-time position and / or orientation of the rail bogie, and receiving a feedback reward for steering of the rail bogie based on the actual position and / or orientation of the rail bogie relative to the rail track. Reinforcement learning of this neural network is performed constantly during operation of the rail bogie, for example, to constantly improve the accuracy of determining the position and / or orientation of the rail bogie relative to the rail track. The feedback reward is, for example, the deviation of the actual position of the rail bogie from a target (set) position and / or target (set) orientation of the rail bogie. The goal is to minimize this deviation over time.

[0028] An improvement in performance can be realised by the neural network being trained or additionally trained with training data obtained by operating the particular rail bogie on the section of the rail track where it is intended to be used. For example, training data is collected during test runs on the particular section of the rail track. This training data is used to train the neural network. Furthermore, the rail bogie collecting the training data does not have to be the rail bogie operating on the rail track, for example the collected training data is transmitted to each rail bogie. Furthermore, the training data used is selected, for example, based on the planned path of the rail bogie. This makes it possible to adjust the positioning algorithm, in particular the neural network, based on the planned path of the rail bogie. Furthermore, the parameters of the neural network may be selected based on the planned path of the rail bogie.

[0029] The sensor providing the sensor signal may be, for example, an ultrasonic / ultrasonic sensor, an inductive sensor, a laser sensor, a capacitive sensor, an optical sensor, a radar sensor, or a combination thereof.

[0030] In a variant, the computer-implemented method may further comprise determining rolling contact fatigue parameters of the railroad tracks using at least one of the real-time sensor signals of the sensor assemblies. The sensor signals may comprise information on fatigue or wear of the respective railroad tracks, for example read from the respective sensor signals. The sensor signals of ultrasonic sensors may comprise such information. In a further variant, the respective fatigue or wear information is collected, stored over time and used to predict the progression of fatigue or wear of the respective railroad tracks. It is thus possible to use the sensor signals to make predictions on the progression of fatigue or wear of the respective railroad tracks, preferably input to a neural network. Thus, all railroad tracks on which the respective railroad bogies operate can be advantageously monitored over time, so that possible railroad track cracks or failures are advantageously detected early.

[0031] According to another aspect of the present disclosure, a controller for determining a real-time steering angle of a railway bogie is provided, the controller comprising a processor configured to perform the following steps: receiving, by a processor, at least one lateral real-time sensor signal from a sensor assembly indicative of a lateral position characteristic of at least one wheel tread of a rail car relative to a rail track; - determining, by a processor, a real-time position and / or orientation of the rail bogie relative to the rail track using the received at least one lateral real-time sensor signal by a positioning algorithm; - determining, by the processor, a real-time steering angle for steering the rail bogie using the determined real-time position and / or orientation of the rail bogie.

[0032] In a variation of the present disclosure, the processor of the control device is further configured to receive from the sensor assembly at least one vertical real-time sensor signal characteristic of a vertical position of the sensor assembly relative to the railway track, and additionally use the received vertical real-time sensor signal to determine a real-time position and / or orientation of the railway bogie relative to the railway track.

[0033] Further, the processor of the control device may be configured to receive from the sensor assembly a first lateral real-time sensor signal indicative of a lateral position characteristic of a first wheel tread of the rail bogie relative to the rail track and a second lateral real-time sensor signal indicative of a lateral position characteristic of a second wheel tread of the rail bogie relative to the rail track, and to determine a real-time position and / or orientation of the rail bogie relative to the rail track using the received first and second lateral real-time sensor signals.

[0034] In a further variation of the present disclosure, the processor of the control device is further configured to receive from the sensor assembly a first vertical real-time sensor signal characteristic of a vertical position of the first vertical sensor relative to the railroad track and a second vertical real-time sensor signal characteristic of a vertical position of the second vertical sensor relative to the railroad track. Each wheel may be equipped with a sensor unit having a first sensor for lateral measurement and a second sensor for vertical measurement.

[0035] In a further variation of the disclosure, the processor of the control device is further configured to receive from the sensor assembly a forward lateral real-time sensor signal characteristic of a forward lateral position of the tread of a wheel of the rail bogie relative to the rail track and a rearward lateral real-time sensor signal characteristic of a rearward lateral position of the tread of a second wheel of the rail bogie relative to the rail track. The sensor assembly may comprise a first lateral sensor arranged in front of the respective wheel and a second sensor arranged behind the respective wheel in terms of the direction of travel of the rail bogie. In a further variation, each of the wheels of the rail bogie comprises a forward lateral sensor and a rearward lateral sensor. For example, a tram bogie having two wheels may comprise four lateral sensors. The four real-time sensor signals are used to determine the position and / or orientation of the rail bogie. This advantageously increases the accuracy of the output signal.

[0036] The processor of the controller may be further configured to receive from the sensor assembly a forward real-time vertical sensor signal characteristic of a forward vertical position of the sensor relative to the railroad track and a rearward real-time vertical sensor signal characteristic of a rearward vertical position of the rearward sensor relative to the railroad track. For example, each wheel of the rail bogie may include a forward sensor for measuring the forward real-time vertical sensor signal and a rearward sensor for measuring the rearward real-time vertical sensor signal.

[0037] In particular, the sensor assembly may comprise a front sensor unit and a rear sensor unit for each wheel, each sensor unit comprising a first sensor for lateral measurement and a second sensor for vertical measurement. A tram bogie having two wheels may comprise, for example, four sensor units, each providing a lateral real-time sensor signal and a vertical real-time sensor signal. A high number of sensor signals advantageously increases the accuracy of the determination of the real-time position and / or orientation of the rail bogie on the rail track during its operation.

[0038] Preferably, the processor of the controller is further configured to adapt the received at least one real-time sensor signal using the predetermined sensor calibration data.

[0039] Advantageous results are achievable if the positioning algorithm is configured to filter at least one received real-time sensor signal using at least one predefined filter parameter and, based on a result of the filtering, determine appropriate real-time sensor signal data to be used for determining a real-time position and / or orientation of the rail bogie relative to the rail track.

[0040] The at least one predefined filter parameter is preferably dependent on at least one of: rail bogie type, rail car type, rail bogie load, rail bogie speed, and wheel size.

[0041] Advantageously, the controller processor is arranged to use the predetermined steering parameters for determining the real-time steering angle.

[0042] In a variation of the present disclosure, the controller processor is further configured to transmit the determined real-time steering angle to a steering actuator controller, the steering actuator controller configured to use the received real-time steering angle to control the steering actuator to steer the rail bogie about the vertical steering axis.

[0043] In a further variation of the present disclosure, the processor of the control device is further configured to receive global positioning data of the rail bogie, which is used to determine a real-time position and orientation of the rail bogie relative to the rail track, for example received from a GPS module disposed on the rail bogie, for example used to determine a position of the rail bogie relative to a global reference frame.

[0044] In a further variation of the present disclosure, the processor of the control device is further configured to receive lidar or radar data of the rail bogie, which is used to determine a real-time position and orientation of the rail bogie relative to the rail track. The lidar or radar data is, for example, received from a lidar and / or radar module arranged in front of the rail bogie, preferably facing the rail track. The lidar or radar data is, for example, used to determine the position and / or orientation of the rail bogie relative to a local reference system or a local reference point.

[0045] In a variant of the disclosure, the processor of the control device is configured to classify and identify a section of the railroad track using the received at least one real-time sensor signal. For example, the real-time sensor signal may enable identifying on which type of railroad track the railroad bogie is currently traveling. It would be possible to identify whether the railroad bogie is currently on a straight railroad track section, on a curved railroad track section, on an intersection, or on a junction section. Furthermore, the processor of the control device may be configured to determine a real-time steering angle using the identified railroad track section. In a variant, the filter parameters are selected depending on the identified railroad track section.

[0046] Advantageous real-time utilization is achievable when the controller has a processing speed of 50 ms or less, preferably 25 ms or less, and even more preferably 20 ms or less, which allows for the desired accurate and rapid determination of the real-time steering angle, and the desired rapid and responsive steering of the rail bogie.

[0047] In a further variation of the present disclosure, the control device is configured to transmit a heartbeat signal to a train controller management system, the heartbeat system being configured to transmit the steering gear status information. The train controller management system has a processing speed of, for example, 100 ms or faster. In a variation, the heartbeat signal is transmitted, for example, every 100 ms.

[0048] According to a further aspect of the present disclosure, the processor of the controller is configured to execute the computer-implemented methods for determining real-time steering angle described above and below.

[0049] A further aspect of the present disclosure provides a computer program product including a non-transitory computer readable medium having stored thereon computer program code configured to instruct a processor of a control device to perform the methods for determining real-time steering angle described above and below.

[0050] According to a further aspect of the present disclosure there is provided a railway bogie comprising a control device as described above or below. [Brief description of the drawings]

[0051] The disclosure set forth herein will become more fully understood from the following detailed description and the accompanying drawings, which should not be construed as limiting the disclosure set forth in the appended claims.

[0052] [Figure 1] FIG. 1 is a perspective view of a first modified example of a dolly according to the present disclosure. [Diagram 2]FIG. 13 is a first perspective view of a second variant of the dolly according to the present disclosure. [Diagram 3] FIG. 3 is a second perspective view of the second modified example of FIG. 2; [Figure 4] FIG. 4 is a detailed view of FIG. [Diagram 5] FIG. 3 is a cross-sectional view of a second modified example of FIG. 2. [Figure 6] FIG. 6 is a detailed view of FIG. 5. [Figure 7] FIG. 13 is a detailed view of a further modified example of the sensor device. [Figure 8] FIG. 2 is a schematic block diagram of a control configuration of the railway bogie. [Figure 9] 1 is a first schematic control loop for a rail bogie. [Figure 10] 2 is a second schematic control loop for a rail bogie. [Figure 11] FIG. 1 is a schematic block diagram of a neural network. [Figure 12] 4 is a flow chart outlining steps executed by a processor to determine real-time steering angles of a rail bogie; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0053] Reference will now be made in detail to certain embodiments, examples of which are illustrated in the accompanying drawings, in which some, but not all, features are shown. Indeed, the embodiments disclosed herein may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are presented so that this disclosure will satisfy applicable legal requirements. Wherever possible, the same reference numbers will be used to refer to the same components or parts.

[0054] FIG. 1 shows a perspective view of a first variant of a railway bogie according to the present disclosure. FIG. 2 shows a first perspective view of a second variant of a railway bogie according to the present disclosure. FIG. 3 shows a second perspective view of the second variant of FIG. 2. FIG. 4 shows a detail view of FIG. 3. FIG. 5 shows a cross-sectional view of the second variant of FIG. 2. FIG. 6 shows a detail view of FIG. 5. FIG. 7 shows a detailed view of a further variant of the sensor arrangement. FIG. 8 shows a schematic block diagram of a control arrangement of the railway bogie. FIG. 9 shows a first schematic control loop of the railway bogie. FIG. 10 shows a second schematic control loop of the railway bogie. FIG. 11 shows a schematic block diagram of a neural network. FIG. 12 shows a flow chart that generally illustrates steps performed by a processor to determine a real-time steering angle of the railway bogie.

[0055] For example, as shown in Figures 1, 2 and 3, the railway bogie 1 comprises a base 2 configured to be mounted on a chassis of a railway vehicle. The base 2 may be connected to a coupling 9 configured to be connected to the chassis of the railway vehicle during operation of the railway bogie 1. The railway bogie 1 further comprises a frame 3 rotatably arranged relative to the base 2 about a vertical steering axis 4. The railway bogie 1 further comprises two wheels 5 each having a tread 6. The tread 6 or tread profile is a radially outer portion of the wheels 5. The tread 6 comprises a contact surface or rolling surface that contacts a rail 32 of a railway track 31 during operation. The wheels 5 further comprise wheel flanges conventionally configured to guide the respective wheels 5 on the rail. The wheels 5 are rotatably arranged relative to the frame 3 about respective wheel rotation axes 7. The wheel rotation axes 7 of the two wheels 5 are arranged substantially coaxially relative to each other, and the steering axis 4 is arranged in the lateral direction Y between the two wheels 5. In another variant, the wheel rotation axis 7 may be arranged at a certain angle to the lateral direction Y. In this case, the wheel rotation axis 7 is inclined to the lateral direction Y. Figure 1 further shows a cover 30 arranged on the frame 3 to protect the bogie 1 during operation. The railway bogie 1 shown in figure 2 in particular does not comprise a coupling 9.

[0056] The figure further shows that the frame 3 comprises a base frame 23 and a wheel frame 24. The base frame 23 is disposed generally above the wheel frame 24. The base frame 23 is interconnected to the wheel frame 24 and vice versa via the spring-damping arrangement 12. The spring-damping arrangement 12 comprises a damper 25 and a spring assembly 26 having a first spring 27 and a second spring 28. A strut 29 is disposed between the base frame 23 and the wheel frame 24.

[0057] Figure 1 further shows a steering actuator 16 coupled to the frame 3 and to the linkage 9. Movement of the steering actuator 16 rotates the frame 3 about the steering axis 4 by a steering angle relative to the base 2 and relative to the linkage 9 and also relative to the chassis of the rail vehicle. Figure 1 further shows a fluid engine configured to drive the steering actuator 16. The fluid engine is, for example, an electric engine driving a hydraulic pump for controlling the steering actuator 16.

[0058] The railway bogie 1 further comprises a sensor assembly 11, best shown in Figures 3 and 4. The sensor assembly 11 comprises a front sensor unit 13 arranged in front of the respective treads 6 of the wheels 5 with respect to the running direction X of the bogie 1. The sensor assembly 11 further comprises a rear sensor unit 14 arranged behind the respective treads 6 of the wheels 5 with respect to the running direction X of the bogie 1. As best shown in Figure 3, both wheels 5 of the railway bogie 1 are equipped with a front sensor unit 13 and a rear sensor unit 14. The front sensor unit 13 and the rear sensor unit 14 are arranged on a sensor bracket 15 that is pivotally mounted with respect to the wheels 5. The sensor bracket 15 extends along the wheels 5 and holds each sensor unit 13, 14 in a predetermined position during the operation of the railway bogie 1. The sensor bracket 15 is arranged to be pivotable with respect to the wheels about a leveling axis 10, best shown in Figure 4. The leveling axis 10 is arranged parallel to the respective wheel rotation axis 4 and in the same vertical imaginary plane as the wheel rotation axis 4.

[0059] The carriage 1 further includes a leveling actuator 8 connected to the frame 3 and respective sensor brackets 15. The linear motion of the leveling actuator 8 adjusts the vertical position of the front sensor unit 13 and / or the rear sensor unit 14 with respect to the rail during the operation of the carriage 1. Movements of the frame 3 that may affect the vertical position of at least one of the sensor units 13, 14, in particular the movement of the swing arm 20 of the frame 3, can be compensated for by the movement of the leveling actuator 8. In the exemplary embodiment of the present disclosure shown in the figures, the linear motion of the leveling actuator 8 causes the connected sensor bracket 15 to rotate about the leveling axis 10. The rotation about the leveling axis 10 compensates for the deflection that the swing arm 20 may undergo with respect to the swing arm spring 22 around the pivot axis 21 during the operation of the railway carriage 1, and can keep the vertical positions of the respective sensor units 13, 14 as stationary as possible during the operation of the railway carriage 1.

[0060] FIG. 1 further shows that each wheel 5 further includes an electric engine 18 and a brake 19. The electric engine 18 is configured to drive / accelerate the respective wheel 5 during operation, if necessary, and the brake 19 is configured to decelerate the respective wheel 5 during the operation of the railway carriage 1, if necessary. The brake 19 is a disc brake, and the disc of the disc brake is arranged on the same shaft as the respective wheel 5 and the respective electric engine 18. The wheel 5, the electric engine 18, and the disc are partially surrounded and held by the swing arm 20, and are best shown in FIG. 3. The brake caliper of the brake 19 is arranged on the swing arm 20.

[0061] These figures further schematically show a control device 40. The control device 40 including a processor 17 is arranged, for example, inside the railway carriage 1 or at another position within the railway vehicle.

[0062] 1 and 2 further show four struts 29 connecting the base frame 23 with the wheel frame 24. The longitudinal axes of the struts 29 are arranged parallel to each other and further to the running direction X in the rest state of the bogie 1. The struts 29 are connected to the base frame 23 and the wheel frame 24 in such a way that a vertical movement of the base frame 23 and the wheel frame 24 between these two parts is possible within a certain range (damped by the spring-damping assembly 12) and a movement in the running direction X is prevented.

[0063] The figure further shows stops 31, best seen in Figure 2, located on the base frame 23, some of which limit the movement of the base frame 23 relative to the wheel frame 24. Other stops 31 limit the maximum rotation of the frame 3 about the vertical steering axis 4.

[0064] As best shown in Figures 5 and 6, the sensor assembly 11 of this embodiment comprises a number of sensor units 35. A front sensor unit 35 is disposed in front of each wheel 5, and a rear sensor unit 35 is disposed behind each wheel. As best shown in Figure 5, both wheels 5 are provided with two sensor units 35. Figures 6 and 7 further show that advantageously, each sensor unit 35 comprises a first sensor 36 and a second sensor 37. The first sensor 36 is configured to provide a lateral real-time sensor signal 38, and the second sensor 37 is configured to provide a vertical real-time sensor signal 39. Thus, the entire sensor assembly 11 shown in the figures is configured to provide four lateral real-time sensor signals 38 and four vertical real-time sensor signals 39.

[0065] As best shown in Figures 5, 6 and 7, the railway track 31 comprises two rails 32 with at least one substantially vertical flange 33 and at least one substantially horizontal surface 34. Substantially vertical means that one extension direction of this flange extends along the vertical direction Z. Substantially horizontal means that one extension direction of this surface extends along the transverse direction Y. The rails 32 of the railway track 31 are not flat but correspond to the shape of the treads 6 of the respective wheels 5 and vice versa. In other words, the vertical flanges 33 extend in the vertical direction Z and are used, for example, as guide surfaces for the flanges of the treads 6 of the wheels 5. The horizontal surfaces 34 extend in the transverse direction Y and are used, for example, as running surfaces for the treads 6 of the wheels 5.

[0066] 7 further shows a variant of the sensor unit 35 comprising a first sensor 36 and a second sensor 37 with a housing. The housing comprises a protective layer arranged under the sensors 36, 38 to protect the sensors 36, 37. The housing with the protective layer is according to this embodiment molded around the sensors 36, 37. The material of the housing is a non-conductive material, for example an epoxy-based resin, so that it is at least partially transparent for the measurement of the sensors.

[0067] Fig. 8 shows a schematic block diagram of a real-time control arrangement of the railway bogie 1. The control arrangement comprises the railway bogie 1, a control device 40 with its processor 17 and a steering actuator controller 41. These three parts are shown by respective blocks. The railway bogie 1, in particular the sensor assembly 11, is configured to provide real-time sensor signals 38, 39. The control device 40 is configured to receive the real-time sensor signals 38, 39 and to determine a real-time steering angle 58. The control device 40 is further configured to transmit the real-time steering angle 58, or a respective signal, to the steering actuator controller 41, which is configured to convert the real-time steering angle 58 into a corresponding steering actuator command 59 that is transmitted to the steering actuator 16 for steering the railway bogie 1. The control device 40 comprises an operating system 42 configured to operate the control device 40, in particular by using at least one controller device parameter 51. The steering actuator control 41 also comprises an operating system 43 configured to operate the steering actuator control 41, in particular additionally by using at least one steering control parameter 56. The parameters 51, 54 may be stored in the respective control device 40, 41.

[0068] The operation system 42 of the control device 40 comprises a main logic 44 configured to determine a real-time steering angle 58. The main logic 44 is illustrated diagrammatically by a sensor data block 46, a positioning algorithm block 47 and a steering control block 49. The sensor data block 46 is configured to receive real-time sensor data 38, 39 from the sensor assembly 11. The sensor data 38, 39 may be adapted or processed using sensor calibration parameters 53, for example stored in the control device 40 and accessed by the processor 17. The positioning algorithm block 47 is configured to use the received real-time sensor data 38, 39 to determine a position and / or an orientation of the rail bogie 1 relative to the rail track 31. The positioning algorithm 47 may use filtering to process the received sensor data 38, 39. The filtering is illustrated diagrammatically by a filtering block 48. The filtering may be performed using filter parameters 54, for example stored in the control device 40 and accessed by the processor 17. The main logic 44 further comprises a steering control block 49. The steering control block 49 is configured to determine a real-time steering angle 58 or a respective value / signal using the measured position and / or orientation of the rail bogie 1 relative to the rail track 31. The steering control block 49 may constantly determine the real-time steering angle 58 during operation using a PID controller 50. Furthermore, the steering control block 49 may use steering parameters 55, which are for example stored in the control device 40 and accessed by the processor 17. FIG. 8 further illustrates a safety application block 45 using safety parameters. The safety application block 45 diagrammatically illustrates that different safety measures of the rail bogie 1 are taken to suppress different types of failures. The safety application 45 may use different safety parameters 52, which are for example stored in the control device 40 and accessed by the processor 17, to control the rail bogie 1. FIG. 8 further illustrates a GPS module 70 and a Radar / Lidar module 71.The GPS module 70 is configured to collect GPS data during the movement of the rail bogie 1. The radar / lidar module 71 is configured to collect radar and / or lidar data during the movement of the rail bogie 1. This data is also, in a variant, transmitted to the controller 40 for determining by the positioning algorithm 47 a real-time position and / or real-time orientation of the rail bogie 1 relative to the rail track. The GPS module 70 and / or the radar / lidar module 71 may be located in a rail vehicle comprising the rail bogie 1.

[0069] Fig. 9 shows a schematic representation of a first variant of a control loop. The control loop is configured to constantly determine a real-time steering angle 58 during the movement of the rail bogie 1. The setpoint 57 of this control loop is that the mechanical centre of the rail bogie 1 is directly over the centre of the rail track 31, the deviation should be zero. The mechanical centre of the rail bogie 1 is, for example, a point at half the distance between the two wheels 5 of the rail bogie 1. The centre of the rail track 31 is, for example, a point at half the distance between the two rails of the rail track 31. The setpoint is that the lateral distance between the mechanical centre of the rail bogie 1 and the centre of the rail track 31 is zero. The feedback or recirculation values ​​are the real-time sensor signals 38, 39. The control error 66 of the control loop is the difference between the setpoint 57 and the actual real-time position and / or orientation of the rail bogie 1 relative to the rail track 31, determined using the sensor signals 38, 39. A correction input 67 is determined, for example by the processor 17 of the control device 40, using the control error 66. The correction input 67 is determined, for example, using a PID controller. The correction input 67 is, for example, the real-time steering angle 58. The real-time steering angle 58 is used for each steering of the railway bogie 1. In the absence of disturbances 68, the railway bogie 1 can be steered such that the set position corresponds to the actual position. Disturbances 68, which may result from changes in the railway track 31, in the steering actuator 16 or in its steering actuator controller 41, result in a deviation of the actual position with respect to the set position. This deviation 69 is determined and fed back using the sensor signals 38, 39.

[0070] FIG. 10 shows a schematic representation of a second variant of the control loop. The control loop is configured to constantly determine a real-time steering angle 58 during the operation of the railway bogie 1. The control loop of the second variant differs from the control loop of the first variant in that it further comprises a feedforward controller 72, which can increase the control speed of the control loop. The feedforward controller 72 can receive steering parameter data 55 and set values. The feedforward controller 72 can determine control inputs to the steering actuator controller 41 for directly controlling the actuator controller 41. The feedforward controller 72 increases the control speed and can be used instead of or in addition to the control loop of the first variant. The feedforward controller 72 may use a neural network to determine the output data. The feedforward controller 72 is implemented, for example, in the control device 40 and / or in the processor 17.

[0071] Fig. 11 shows diagrammatically a block diagram of a neural network 60 that may be used by the positioning algorithm 47 to determine the real-time position and / or orientation of the rail bogie 1 with respect to the rail track 31. The neural network 60 comprises an input layer 63, a hidden layer 64 and an output layer 65. Input data 61, in particular at least one lateral real-time sensor signal 38 and at least one vertical real-time sensor signal 39, are input to the neural network 60. The hidden layer 64 processes the received data and the neural network 60 produces as output data 62 the real-time position and / or orientation of the rail bogie 1 with respect to the rail track 31.

[0072] Figure 12 shows a flow diagram illustrating generally the sequence of steps performed by the processor 17 of the control device 40 for determining a real-time steering angle 58 of the railway bogie 1 on a current section of railway track. The sequence of steps, implemented for example as a computer implemented method, is performed by the control device 40 as shown in for example Figure 8.

[0073] In step S1, the processor 17 of the controller 40 receives from the sensor assembly 11 at least one lateral real-time sensor signal 38 characteristic of a lateral position of a tread 6 of at least one wheel 5 of the railway bogie 1 relative to the railway track 31. The sensor assembly 11, which comprises a plurality of sensor units 35 having a first sensor 36 and a second sensor 37, transmits or transmits the real-time sensor signal to the controller 40.

[0074] In optional step S4, the processor 17 of the control device 40 adapts the received at least one real-time sensor signal using predetermined sensor calibration data 53. In this step, which can also be performed by the sensor assembly 11 itself, the sensor signals 38, 39 are, for example, smoothed or averaged by using the predetermined sensor calibration data 53.

[0075] In step S2, the processor 17 of the control device 40 uses the received at least one lateral real-time sensor signal to determine a real-time position and / or orientation of the railway bogie 1 relative to the railway track 31 by a positioning algorithm 47. The current or actual (real-time) position and / or orientation of the railway bogie 1 is determined based on the received real-time sensor signals, and the positioning algorithm 47 may use geometric algorithms, interpolation algorithms, neuronal networks and / or combinations thereof.

[0076] In step S3, the processor 17 of the control device 40 uses the determined real-time position and / or orientation of the rail bogie 1 relative to the rail track 31 to determine a real-time steering angle 58 for steering the rail bogie 1. The real-time steering angle 58 is determined additionally using steering parameters 55, such as, for example, speed, additional track information, etc. The steering angle 58 is, for example, an angle value or a signal corresponding to an angle value. The real-time steering angle 58 is, for example, the angle between the current (tangential) main extension direction of the rail 32 and the running direction of the respective wheels 5. The real-time steering angle 58 may also be the angle between the running direction of the rail bogie 1 or wheels 5 and the chassis or coupling 9 of the rail vehicle. In both variants, a change in the real-time steering angle 58 results in a lateral displacement of the rail bogie 1 relative to the rail track during operation. The target value of the real-time steering angle 58 is, for example, the curvature angle of the rail track 31.

[0077] In step S5, the processor of the control device 40 transmits the determined real-time steering angle 58 to the steering actuator controller 41. The steering actuator controller 41 is configured to convert the received real-time steering angle 58 into desired control commands for the steering actuator 16 configured to pivot or rotate the railway bogie 1 about the vertical steering axis 4.

[0078] In step S6, the steering actuator 16 is controlled by the steering actuator controller 41 to steer the railway bogie 1 about the vertical steering axis 4 using the real-time steering angle 58. The steering actuator 16 is constantly operating to pivot / rotate the railway bogie 1 about the vertical steering axis 4 such that the actual position and / or orientation of the railway bogie 1 is aligned as closely as possible with a target (set) position and / or orientation while the railway bogie 1 is in operation.

[0079] At least some steps are preferably performed constantly in order to keep the rail bogie 1 perfectly aligned on the rail track 31. Disturbances 68 that may affect the control loop are taken into account so that a smooth running of the rail bogie 1 on the rail track 31 is achieved.

[0080] Rather, the words used herein are words of description rather than of limitation, and it is understood that various changes can be made without departing from the spirit and scope of the disclosure. [Explanation of symbols]

[0081] 1 Railway bogie 2. Bass 3 Frame 4 Steering shaft 5 wheels 6 Tread 7 Wheel rotation axis 8 Leveling Actuator 9 Connecting part 10 Leveling Axis 11 Sensor Assembly 12 Spring damping device 13 Front Sensor 14 Rear Sensor 15 Sensor bracket 16 Steering actuator 17 Processors 18 Electric Engine 19 Brakes 20 Swingarm 21 Swivel Axis 22 Swing arm spring 23 Base Frame 24 Wheel Frame 25 Damper 26 Spring Assembly 27 First Spring 28 Second Spring 29 Strut 30 Cover 31 Railway Tracks 32 Rail 33 Vertical flange 34 Horizontal flange 35 Sensor unit 36 First Sensor 37 Second Sensor 38 Lateral real-time sensor signals 39 Vertical real-time sensor signals 40 Control device 41 Steering actuator controller 42 Control device operation system 43 Steering actuator controller operation system 44 Main Logic 45 Safety Application Block 46 Sensor Data Block 47 Position Algorithm Block 48 Filtering Blocks 49 Steering control block 50 PID Controller 51 Control device parameters 52 Safety parameters 53 Sensor Calibration Data 54 Filter parameters 55 Steering parameters 56 Steering actuator controller parameters 57 Setting value (machine center) 58 Real-time steering angle 59 Steering actuator control command 60 Neural Networks 61 Input Data 62 Output Data 63 Input Layer 64 Hidden Layers 65 Output layer 66 Control Error 67 Correction Input 68 Disturbance 69 deviation 70 GPS Module 71 Radar / Lidar Module 72 Feedforward Controller X Traveling direction Y Horizontal Z vertical direction S1 Reception S2 Position determination S3 Steering angle determination S4 Adaptation of received real-time sensor signals S5 Steering angle transmission S6 Steering actuator control

Claims

1. A computer execution method for determining the real-time steering angle (58) of a railway bogie (1), wherein the method is: a. Step (S1) of determining, by the sensor assembly (11), at least one lateral real-time sensor signal (38) that indicates the characteristics of the lateral position of the tread (6) of at least one wheel (5) of the railway bogie (1) relative to the railway track (31), b. A step (S2) in which the real-time position and / or orientation of the railway bogie (1) relative to the railway track (31) is determined using the at least one lateral real-time sensor signal (38) determined by the positioning algorithm (47), c. A computer execution method comprising the step (S3) of determining the real-time steering angle (58) for steering the railway bogie (1) using the determined real-time position and / or orientation of the railway bogie (1).

2. a. Step (S1) of determining at least one vertical real-time sensor signal (39) that indicates the vertical position characteristics of the sensor assembly (11) with respect to the railway track (31) using the sensor assembly (11), b. A step (S2) of further using the received vertical real-time sensor signal (39) to determine the real-time position and / or orientation of the railway bogie (1) with respect to the railway track (31), The computer execution method according to claim 1, further comprising:

3. a. Step (S1) of determining a first lateral real-time sensor signal (38) that indicates the characteristics of the lateral position of the tread (6) of the first wheel (5) of the railway bogie (1) relative to the railway track (31) using the sensor assembly (11), and a second lateral real-time sensor signal (38) that indicates the characteristics of the lateral position of the tread (6) of the second wheel (5) of the railway bogie (1) relative to the railway track (31), b. Using the received first and second lateral real-time sensor signals (38), the step (S2) of determining the real-time position and / or orientation of the railway bogie (1) relative to the railway track (31), The computer execution method according to claim 1, further comprising:

4. a. Step (S1) of determining, using the sensor assembly (11) of at least one wheel (5) of the railway bogie (1), a forward lateral real-time sensor signal (38) indicating the lateral position characteristics of the tread (6) of the wheel (5), and a forward vertical real-time sensor signal (39) indicating the vertical position characteristics of the sensor assembly (11), using the forward sensor unit of the sensor assembly (11) of the wheel (5), and / or, using the sensor assembly (11) of at least one wheel (5) of the railway bogie (1), a rear lateral real-time sensor signal (38) indicating the lateral position characteristics of the tread (6) of the wheel (5), and a rear vertical real-time sensor signal (39) indicating the vertical position characteristics of the sensor assembly (11), using the rear sensor unit of the sensor assembly (11) of the wheel (5), b. A step (S2) in which the real-time position and / or orientation of the railway bogie (1) relative to the railway track (31) is determined using the received forward and rear real-time sensor signals (38, 39), The computer execution method according to claim 1, further comprising:

5. a. Step (S4) of adapting at least one received real-time sensor signal (38, 39) using predetermined sensor calibration data (53), The computer execution method according to claim 1, further comprising:

6. The computer execution method according to claim 1, wherein in step (S2) of determining the real-time position and / or orientation of the railway bogie (1), the positioning algorithm (47) filters at least one received real-time sensor signal (38, 39) using at least one predetermined filter parameter (54), and determines appropriate real-time sensor signal data to be used to determine the real-time position and / or orientation of the railway bogie (1) with respect to the railway track (31) based on the result of the filtering.

7. The computer execution method according to claim 6, wherein the at least one predetermined filter parameter (54) depends on at least one of the following: type of railway bogie, type of railway vehicle, railway bogie load, railway bogie speed, and wheel size.

8. The computer execution method according to claim 1, wherein the step (S3) of determining the real-time steering angle (58) further uses predetermined steering parameters (55).

9. a. Step (S5) of transmitting the determined real-time steering angle (58) to the steering actuator controller (41), b. A step (S6) in which the steering actuator (16) is controlled by the steering actuator controller (41) in order to steer the railway bogie (1) around the vertical steering axis (4) using the real-time steering angle (58), The computer execution method according to claim 1, further comprising:

10. The computer execution method according to claim 1, wherein in the step (S2) of determining the real-time position and / or orientation of the railway bogie (1), the positioning algorithm (47) uses a neural network (60) to determine (S2) the real-time position and / or orientation of the railway bogie (1) with respect to the railway track (31), and at least one real-time sensor signal (38, 39) is input data (61) to the neural network (60), and the real-time position and / or orientation of the railway bogie (1) with respect to the railway track (31) is output data (62) to the neural network (60).

11. The aforementioned neural network (60) a. Using the neural network (60) to determine the real-time position and / or orientation of the railway bogie (1) relative to the railway track (31), controlling the steering of the railway bogie (1) based on the determined real-time position and / or orientation of the railway bogie (1), and receiving feedback rewards for steering the railway bogie (1) based on the actual position and / or orientation of the railway bogie (1) relative to the railway track (31) for training the neural network (60). A computer execution method according to claim 10, which is trained by the means described above.

12. The computer execution method according to claim 10, wherein the neural network (60) is trained using training data obtained by operating the railway bogie (1) in a section of the railway track (31) where a particular railway bogie (1) is intended to be used.

13. A computer execution method according to any one of claims 1 to 12, further comprising determining a rolling contact fatigue parameter of the railway track (31) using at least one of the real-time sensor signals (38, 39) of the sensor assembly (11).

14. A control device (40) for determining the real-time steering angle (58) of a railway bogie (1), wherein the control device (40) comprises a processor (17), and the processor is a. Step (S1) of the processor (17) receiving from the sensor assembly (11) at least one lateral real-time sensor signal (38) indicating the characteristics of the lateral position of the tread (6) of at least one wheel (5) of the railway bogie (1) relative to the railway track (31), b. The processor (17) uses the received lateral real-time sensor signal (38) to determine the real-time position and / or orientation of the railway bogie (1) relative to the railway track (31) using a positioning algorithm (47) (S2), c. The processor (17) determines the real-time steering angle (58) for steering the railway bogie (1) using the determined real-time position and / or orientation of the railway bogie (1) (S3), A control device (40) configured to perform the following.

15. The aforementioned processor (17) a. The processor (17) receives from the sensor assembly (11) at least one vertical real-time sensor signal (39) that indicates the vertical position characteristics of the sensor assembly (11) with respect to the railway track (31) (S1), b. The processor (17) additionally uses the received vertical real-time sensor signal (39) to determine the real-time position and / or orientation of the railway bogie (1) with respect to the railway track (31) (S2). The control device (40) according to claim 14, further configured as follows.

16. The aforementioned processor (17) a. The processor (17) receives from the sensor assembly (11) a first lateral real-time sensor signal (38) indicating the characteristics of the lateral position of the tread (6) of the first wheel (5) of the railway bogie (1) relative to the railway track (31), and a second lateral real-time sensor signal (38) indicating the characteristics of the lateral position of the tread (6) of the second wheel (5) of the railway bogie (1) relative to the railway track (31) (S1). b. The processor (17) uses the received first and second lateral real-time sensor signals (38) to determine the real-time position and / or orientation of the railway bogie (1) with respect to the railway track (31) (S2). The control device (40) according to claim 14, further configured as follows.

17. The control device (40) according to claim 14, wherein the processor (17) is further configured to adapt at least one received real-time sensor signal (38, 39) using predetermined sensor calibration data.

18. The control device (40) according to claim 14, wherein the processor (17) is further configured to filter at least one received real-time sensor signal (38, 39) using at least one predetermined filter parameter (54) by the positioning algorithm (47), and to determine appropriate real-time sensor signal data used to determine the real-time position and / or orientation of the railway bogie (1) with respect to the railway track (31) based on the result of the filtering.

19. The control device (40) according to claim 18, wherein the at least one predetermined filter parameter (54) depends on at least one of the following: type of railway bogie, type of railway vehicle, railway bogie load, railway bogie speed, and wheel size.

20. The control device (40) according to claim 14, wherein the processor (17) is configured to further use predetermined steering parameters (55) for the determination (S3) of the real-time steering angle (58).

21. The control device (40) according to claim 14, wherein the processor (17) is further configured to transmit the determined real-time steering angle (58) to a steering actuator controller (41) (S5), and the steering actuator controller (41) is configured to control a steering actuator (16) to steer the railway bogie (1) about a vertical steering axis (4) using the received real-time steering angle (58).

22. The control device (40) according to claim 14, wherein the processor (17) is configured to receive (S1) and process at least one real-time sensor signal (38, 39) from the ultrasonic / ultrasonic sensor, induction sensor, laser sensor, capacitive sensor, optical sensor, and / or radar sensor of the sensor assembly (11).

23. The controller (40) according to any one of claims 14 to 22, wherein the processor (17) is further configured to determine the rolling contact fatigue parameter of the railway track (31) using at least one of the real-time sensor signals (38, 39) received from the sensor assembly (11).

Images