Turnout state monitoring and fault prediction method and system based on multi-source curve

Abstract

The present application relates to the field of railway equipment monitoring technology, in particular to a turnout state monitoring and fault prediction method and system based on multiple source curves, current data during turnout operation is collected to generate an action current curve, and the time domain characteristics of several operation subintervals of the turnout are calibrated therefrom; the electrical state of the turnout is monitored, the operation start node of the turnout is determined, and the action image set of the turnout itself and the motor output detection data set of the turnout are collected in combination with the time domain characteristics; the action parameter curve and the output action parameter curve are generated according to the action image set and the motor output detection data set, the action switching abnormal event of the turnout is determined, the fault state of the turnout is predicted, and a warning notice is generated. All operation subintervals of the turnout are demarcated by constructing the action current curve, the action parameter curve of the turnout and the output action parameter curve of the motor thereof are constructed, the hardware abnormalities of the turnout are represented by multiple curves, potential faults are accurately predicted, and the safety of the turnout is improved.

Description

Technical Field

[0001] This invention relates to the field of railway equipment monitoring technology, and in particular to a method and system for turnout status monitoring and fault prediction based on multi-source curves. Background Technology

[0002] Turnouts are crucial railway signaling devices, primarily composed of switches (including point rails), connecting rails, frogs, and guard rails. The point rails guide train wheels to turn by swinging left and right. The efficient and accurate operation of turnouts directly impacts train operating efficiency and safety. Existing technology uses operating current curves to characterize the change in operating current during the entire operation of the turnout. However, considering that this operating current corresponds to the operating current of the motor driving the turnout, these operating current curves only reflect the motor's own response and drive output states, such as whether there is a response delay and the magnitude of the motor's drive output torque. They cannot truly reflect the mechanical hardware condition of the turnout itself. Hardware components within the turnout, especially the point rails, experience wear and tear during prolonged and repeated operation. Operating current curves alone cannot accurately identify hardware faults in the turnout, reducing the reliability and accuracy of turnout monitoring. Therefore, how to dynamically monitor and predict turnout faults at the hardware level is of great significance for improving the electrical and mechanical safety of turnouts. Summary of the Invention

[0003] Given that existing technologies, relying on a single operating current curve, can only monitor the electrical performance of turnouts, they cannot promptly and accurately detect hardware faults formed during long-term, repeated switching of turnout components, thus reducing the reliability and accuracy of turnout monitoring. In view of the above problems, this invention is proposed to provide a turnout condition monitoring and fault prediction method based on multi-source curves that overcomes or at least partially solves the above problems, including:

[0004] Step S1: Collect current data during turnout operation to generate operating current curve; calibrate the time-domain characteristics of several operating sub-intervals of the turnout from the operating current curve.

[0005] Step S2: Monitor the electrical status of the turnout and determine the working start node of the turnout; based on the working start node and the time domain characteristics, collect the motion image set of the turnout itself and the motor output detection dataset of the turnout;

[0006] Step S3: Based on the motion image set and the motor output detection dataset, generate motion parameter curves and output action parameter curves; compare the motion parameter curves and output action parameter curves of the turnout during several working periods to determine the abnormal motion switching events of the turnout;

[0007] Step S4: Based on the abnormal event of the action switching, predict the fault status of the turnout, and generate an early warning notification accordingly.

[0008] Optionally, in step S1, current data during turnout operation is collected to generate an operating current curve; the time-domain characteristics of several operating sub-intervals of the turnout are calibrated from the operating current curve, including:

[0009] Monitor the operating status of the starting electrical equipment of the turnout to determine whether the turnout has entered the working cycle;

[0010] Collect the full-process current data of the turnout during several working cycles, identify the time-domain distribution of interference intensity of the full-process current data of each working cycle, and determine the reliability of the full-process current data of each working cycle.

[0011] By comparing the reliability of all current data throughout the entire process, the effective operating current curve of the turnout is generated.

[0012] The effective operating current curve is subjected to time-domain change identification to determine all turning points of the effective operating current curve; based on all turning points, the time range characteristics covered by several working sub-intervals of the turnout are marked; wherein the several working sub-intervals correspond one-to-one with several hardware operation stages of the turnout.

[0013] Optionally, in step S2, the electrical state of the turnout is monitored to determine the turnout's operating start point; based on the operating start point and the time-domain characteristics, a set of motion images of the turnout itself and a set of motor output detection data of the turnout are collected, including:

[0014] The starting electrical equipment of the turnout is monitored to receive the trigger command, and the time point when the trigger command is successfully executed is taken as the working start node of the turnout;

[0015] Taking the work start node as the starting time point, and based on the time range of the one-to-one correspondence of the several working sub-intervals contained in the time domain features, adjust the time domain change strategy for the shooting parameters of the actual scene where the turnout is located and the time domain change strategy for the detection of the motor output of the turnout.

[0016] Based on the time-domain variation strategy of the shooting parameters and the time-domain variation strategy of the motor output detection, the action image set of the turnout itself and the motor output detection dataset of the turnout are collected; wherein the action image set includes a subset of several turnout entity action images corresponding one-to-one with the several working sub-sections, and the motor output detection dataset includes a subset of several motor output torque data corresponding one-to-one with the several working sub-sections.

[0017] Optionally, in step S3, based on the motion image set and the motor output detection dataset, motion parameter curves and output action parameter curves are generated; by comparing the motion parameter curves and output action parameter curves of the turnout during several working periods, abnormal motion switching events of the turnout are determined, including:

[0018] The action image subsets of all turnout entities under the action image set are identified to obtain several action trajectories of the turnout entities corresponding to the several working sub-intervals, and then integrated to generate action parameter curves.

[0019] The motor output torque data subset under the motor output detection dataset is integrated according to time sequence to generate an output action parameter curve;

[0020] By comparing the action parameter curves and output action parameter curves of the turnout during the same working period, the trajectory deviation between the expected turnout action trajectory generated by the motor output torque during the same working period and the actual turnout action trajectory is obtained.

[0021] By comparing the trajectory deviation of the turnout over a certain period of time, the cumulative trajectory offset of the turnout during a certain hardware operation phase is determined, thereby identifying the abnormal event of the turnout's operation switching.

[0022] Optionally, in step S4, based on the abnormal event of the action switch, the fault state of the turnout is predicted, thereby generating an early warning notification, including:

[0023] Based on the hardware action stage of the turnout corresponding to the abnormal action switching event, identify the potential wear components of the turnout.

[0024] Based on the deviation trend of the movement trajectory of the potentially worn components during the aforementioned operating periods, the timing information of the turnout failure is predicted, thereby generating an early warning notification.

[0025] As one aspect of the present invention, embodiments of the present invention also provide a turnout condition monitoring and fault prediction system based on multi-source curves, including:

[0026] The first curve generation module is used to collect current data during turnout operation and generate operating current curves accordingly.

[0027] The working interval calibration module is used to calibrate the time-domain characteristics of several working sub-intervals of the turnout from the operating current curve.

[0028] The turnout start determination module is used to monitor the electrical status of the turnout and determine the start node of the turnout.

[0029] The acquisition module is used to acquire the action image set of the turnout itself and the motor output detection dataset of the turnout based on the working start node and the time domain characteristics.

[0030] The second curve generation module is used to generate motion parameter curves and output action parameter curves based on the motion image set and the motor output detection dataset.

[0031] An abnormal event determination module is used to compare the action parameter curves and output action parameter curves of the turnout during several working periods to determine the abnormal event of the turnout's action switching.

[0032] The fault prediction and early warning module is used to predict the fault status of the turnout based on the abnormal event of the action switching, and thereby generate an early warning notification.

[0033] Optionally, the first curve generation module is used to collect current data during turnout operation to generate an operating current curve, including:

[0034] Monitor the operating status of the starting electrical equipment of the turnout to determine whether the turnout has entered the working cycle;

[0035] Collect the full-process current data of the turnout during several working cycles, identify the time-domain distribution of interference intensity of the full-process current data of each working cycle, and determine the reliability of the full-process current data of each working cycle.

[0036] By comparing the reliability of all current data throughout the entire process, the effective operating current curve of the turnout is generated.

[0037] The working interval calibration module is used to calibrate the time-domain characteristics of several working sub-intervals of the turnout from the operating current curve, including:

[0038] The effective operating current curve is subjected to time-domain change identification to determine all turning points of the effective operating current curve; based on all turning points, the time range characteristics covered by several working sub-intervals of the turnout are marked; wherein the several working sub-intervals correspond one-to-one with several hardware operation stages of the turnout.

[0039] Optionally, the turnout start-up determination module is used to monitor the electrical status of the turnout and determine the start-up node of the turnout, including:

[0040] The starting electrical equipment of the turnout is monitored to receive the trigger command, and the time point when the trigger command is successfully executed is taken as the working start node of the turnout;

[0041] The acquisition module is used to acquire a set of motion images of the turnout itself and a set of motor output detection data of the turnout based on the working start node and the time-domain features, including:

[0042] Taking the work start node as the starting time point, and based on the time range of the one-to-one correspondence of the several working sub-intervals contained in the time domain features, adjust the time domain change strategy for the shooting parameters of the actual scene where the turnout is located and the time domain change strategy for the detection of the motor output of the turnout.

[0043] Based on the time-domain variation strategy of the shooting parameters and the time-domain variation strategy of the motor output detection, the action image set of the turnout itself and the motor output detection dataset of the turnout are collected; wherein the action image set includes a subset of several turnout entity action images corresponding one-to-one with the several working sub-sections, and the motor output detection dataset includes a subset of several motor output torque data corresponding one-to-one with the several working sub-sections.

[0044] Optionally, the second curve generation module is used to generate motion parameter curves and output action parameter curves based on the motion image set and the motor output detection dataset, including:

[0045] The action image subsets of all turnout entities under the action image set are identified to obtain several action trajectories of the turnout entities corresponding to the several working sub-intervals, and then integrated to generate action parameter curves.

[0046] The motor output torque data subset under the motor output detection dataset is integrated according to time sequence to generate an output action parameter curve;

[0047] The abnormal event determination module is used to compare the action parameter curves and output action parameter curves of the turnout during several working periods to determine the abnormal event of the turnout's action switching, including:

[0048] By comparing the action parameter curves and output action parameter curves of the turnout during the same working period, the trajectory deviation between the expected turnout action trajectory generated by the motor output torque during the same working period and the actual turnout action trajectory is obtained.

[0049] By comparing the trajectory deviation of the turnout over a certain period of time, the cumulative trajectory offset of the turnout during a certain hardware operation phase is determined, thereby identifying the abnormal event of the turnout's operation switching.

[0050] Optionally, the fault prediction and early warning module is used to predict the fault state of the turnout based on the abnormal event of the action switching, and thereby generate an early warning notification, including:

[0051] Based on the hardware action stage of the turnout corresponding to the abnormal action switching event, identify the potential wear components of the turnout.

[0052] Based on the deviation trend of the movement trajectory of the potentially worn components during the aforementioned operating periods, the timing information of the turnout failure is predicted, thereby generating an early warning notification.

[0053] The beneficial effects of the above-mentioned technical solutions provided in the embodiments of the present invention include at least the following:

[0054] This invention provides a method and system for turnout status monitoring and fault prediction based on multi-source curves. The system collects current data during turnout operation to generate an operating current curve, thereby identifying the time-domain characteristics of several operating sub-intervals of the turnout. It monitors the electrical state of the turnout, determines the turnout's operating start node, and, combined with the time-domain characteristics, collects a set of the turnout's own operating images and a set of motor output detection data. Based on the operating image set and the motor output detection data, it generates operating parameter curves and output action parameter curves to determine abnormal turnout operation switching events, predict turnout fault states, and generate early warning notifications. By constructing operating current curves to delineate all operating sub-intervals of the turnout, it constructs the turnout's operating parameter curves and its motor's output action parameter curves. Utilizing multiple curves to characterize turnout hardware anomalies, it accurately predicts potential faults and improves the electrical and mechanical safety of the turnout.

[0055] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0056] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0057] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0058] Figure 1 This is a flowchart illustrating the turnout condition monitoring and fault prediction method based on multi-source curves provided in this embodiment of the invention.

[0059] Figure 2 This is a schematic diagram of the structure of the turnout condition monitoring and fault prediction system based on multi-source curves provided in an embodiment of the present invention. Detailed Implementation

[0060] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0061] In the description of this invention, it should be noted that the terms "upper," "lower," "left," "right," and "rear," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0062] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the term "connection" should be interpreted broadly. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0063] Please see Figure 1 As shown, an embodiment of this application provides a turnout condition monitoring and fault prediction method based on multi-source curves. This turnout condition monitoring and fault prediction method based on multi-source curves includes:

[0064] Step S1: Collect current data during turnout operation to generate operating current curve; calibrate the time-domain characteristics of several operating sub-intervals of the turnout from the operating current curve.

[0065] Step S2: Monitor the electrical status of the turnout and determine the turnout's working start point; based on the working start point and time domain characteristics, collect the turnout's own motion image set and the turnout's motor output detection dataset;

[0066] Step S3: Based on the motion image set and the motor output detection dataset, generate motion parameter curves and output action parameter curves; compare the motion parameter curves and output action parameter curves of the turnout during several working periods to determine the abnormal motion switching events of the turnout.

[0067] Step S4: Based on the abnormal event of action switching, predict the fault status of the turnout and generate an early warning notification accordingly.

[0068] This multi-source curve-based turnout condition monitoring and fault prediction method delineates all working sub-intervals of the turnout by constructing an operating current curve, thereby constructing the turnout's operating parameter curve and the motor's output operating parameter curve. By using multiple curves to characterize hardware anomalies of the turnout, it accurately predicts potential faults and improves the electrical and mechanical safety of the turnout.

[0069] In another embodiment, in step S1, current data during turnout operation is collected to generate an operating current curve; the time-domain characteristics of several operating sub-intervals of the turnout are calibrated from the operating current curve, including:

[0070] Monitor the operating status of the starting electrical equipment of the turnout to determine whether the turnout has entered the working cycle;

[0071] Collect the full-process current data of the turnout during several working cycles, identify the time-domain distribution of interference intensity of the full-process current data of each working cycle, and determine the reliability of the full-process current data of each working cycle.

[0072] By comparing the reliability of all current data throughout the entire process, the effective operating current curve of the turnout is generated.

[0073] The effective operating current curve is subjected to time-domain variation identification to determine all inflection points of the effective operating current curve; based on all inflection points, the time range characteristics covered by several working sub-sections of the turnout are calibrated; and the several working sub-sections correspond one-to-one with several hardware operation stages of the turnout.

[0074] In the above technical solution, the main components of the turnout include the switch (including the switch rail), connecting rail, frog, and guard rail. In actual operation, a three-phase AC motor or other electric motor can be used to drive the turnout, especially the switch rail. The electric motor provides a matching driving force to the switch according to the required wheel steering size and direction, and the driving force depends on the size of the electric motor. Furthermore, the turnout is triggered when wheel steering is required; at other times, the turnout is in a non-operating state. That is, the electric motor is only supplied with the corresponding driving current when the turnout is triggered, and the magnitude of the driving current directly reflects the actual operating state of the turnout. Specifically, when the driving current is within a certain range, the turnout is in the corresponding hardware operation stage (i.e., the switch rail operation stage).

[0075] To determine the time range corresponding to all hardware operation stages of the turnout within its entire working cycle, full-process current data of the turnout is first collected during several working cycles (i.e., the working cycle corresponding to each time the turnout is triggered and enters the working state). The full-process current data corresponding to each working cycle reflects the magnitude of the current applied to the turnout by the motor. During the operation of the turnout driven by the motor, internal and external factors affect the collected full-process current data, resulting in noise interference that obscures the magnitude changes in the current due to driving requirements. To accurately divide all working sub-intervals of the turnout within a complete working cycle, the time-domain distribution of interference intensity is identified for the full-process current data of each working cycle, i.e., the average interference noise intensity of the full-process current data over the entire time range is determined. This determines the reliability of the full-process current data; it can be understood that the lower the average interference noise intensity, the higher the reliability. By comparing the reliability of all full-process current data, the full-process current data with the lowest reliability is used as the original data to generate the effective operating current curve of the turnout. That is, the effective operating current curve reflects the change of current magnitude over time in the full-process current data with the lowest reliability.

[0076] The operation of a turnout (especially a switch rail) driven by an electric motor is a dynamic process. The movement of the switch rail from its initial position to its target position includes multiple action stages, such as unlocking, switching, locking, and release. In each of these stages, the driving current applied by the motor differs. By identifying the time-domain changes in the effective operating current curve, all inflection points of the effective operating current curve are determined. These inflection points can be, but are not limited to, the curve's inflection points. Then, based on all these inflection points, the time axis of the effective operating current curve is divided into several working sub-intervals of the turnout, each covering a specific time range. It can be understood that each working sub-interval corresponds to one hardware action stage; that is, all working sub-intervals correspond one-to-one with the unlocking, switching, locking, and release stages. By defining the time range characteristics covered by each working sub-interval, a time reference is provided for subsequent time-domain change analysis and comparison of the action parameter curves and output action parameter curves.

[0077] In another embodiment, in step S2, the electrical state of the turnout is monitored to determine the turnout's operating start point; based on the operating start point and time-domain characteristics, a set of motion images of the turnout itself and a set of motor output detection data of the turnout are collected, including:

[0078] The electrical equipment for monitoring the start of the turnout receives the trigger command and takes the time when the trigger command is successfully executed as the start node of the turnout.

[0079] Starting from the work start node, and based on the time range of several working sub-intervals contained in the time domain characteristics, adjust the time domain change strategy for the shooting parameters of the actual scene where the turnout is located and the time domain change strategy for the detection of the motor output of the turnout.

[0080] Based on the time-domain variation strategy of shooting parameters and the time-domain variation strategy of motor output detection, a set of motion images of the turnout itself and a set of motor output detection data of the turnout are collected; the motion image set includes a subset of motion images of several turnout entities corresponding one-to-one with several working sub-sections, and the motor output detection data set includes a subset of motor output torque data corresponding one-to-one with several working sub-sections.

[0081] In the above technical solution, the operating current curve only reflects the electrical performance of the turnout and the motor. However, as a hardware device, the turnout inevitably experiences wear during repeated operation over a long period, leading to response delays and failure to move to the target position under the same motor drive, thus reducing the turnout's reliability and accuracy. To identify turnout anomalies at the mechanical hardware level, during actual turnout operation, the trigger commands (such as electrical pulse commands received by the relay device) received by the turnout's starting electrical equipment (such as relay devices) are monitored. The time point at which the starting electrical equipment successfully executes the corresponding engagement action after responding to the trigger command is taken as the turnout's working start (time) node.

[0082] After the turnout successfully operates, using the aforementioned work start (time) node as the starting time point, and combining the various time ranges covered by the aforementioned sub-intervals, the time-domain variation strategy for the shooting parameters of the actual scene where the turnout is located and the time-domain variation strategy for the turnout's motor output detection are adjusted. It can be understood that the aforementioned time-domain variation strategy for shooting parameters refers to the strategy for changing the actual shooting parameters (such as shooting focal length and / or shooting field of view) of the turnout operation within the aforementioned time range, starting from the aforementioned starting time point; the aforementioned time-domain variation strategy for motor output detection refers to the strategy for changing the detection parameters (such as detection sensitivity and / or detection sampling frequency) of the motor output (torque) within the aforementioned time range, starting from the aforementioned starting time point. Then, based on the aforementioned time-domain variation strategies for shooting parameters and motor output detection, the turnout's own action image set and the turnout's motor output detection dataset are collected respectively, thereby obtaining several subsets of turnout entity action images and several subsets of motor output torque data corresponding to several sub-intervals, providing sufficient data for subsequent identification of the turnout's hardware wear status.

[0083] In another embodiment, in step S3, motion parameter curves and output action parameter curves are generated based on the motion image set and the motor output detection dataset; by comparing the motion parameter curves and output action parameter curves of the turnout during several working periods, abnormal motion switching events of the turnout are determined, including:

[0084] The action image subsets of all turnout entities under the action image set are identified to obtain several action trajectories of several working sub-intervals corresponding to the turnout entities, and these are integrated to generate action parameter curves.

[0085] The output torque data subsets of the motor output detection dataset are integrated according to time sequence to generate output action parameter curves.

[0086] By comparing the action parameter curves and output action parameter curves of the turnout during the same working period, the trajectory deviation between the expected turnout action trajectory generated by the motor output torque during the same working period and the actual turnout action trajectory is obtained.

[0087] By comparing the trajectory deviation of the turnout over a certain period of time, the cumulative trajectory offset of the turnout during a certain hardware operation stage is determined, thereby identifying abnormal events in the turnout's operation switching.

[0088] In the above technical solution, the motion image set and the motor output detection dataset correspond to the motion state of the turnout's hardware components (especially the switch rail) and the torque state output by the motor to the aforementioned hardware components, respectively, during actual operation. To this end, the motion image subsets of all turnout entities under the motion image set are identified to obtain several motion trajectories for several working sub-intervals corresponding to the turnout entities. All motion trajectories are integrated to generate motion parameter curves (i.e., continuous curves showing the change of motion trajectory position over time). Similarly, the motor output torque data subsets under the motor output detection dataset are integrated according to time sequence to generate output action parameter curves (i.e., continuous curves showing the change of output torque magnitude over time). Understandably, considering that the hardware wear of a turnout is a relatively long process, curve analysis is needed over multiple operating periods of the turnout (i.e., during which the turnout performs multiple wheel steering tasks over time). Specifically, by comparing the motion parameter curve and output action parameter curve of the turnout during the same operating period, the trajectory deviation between the expected turnout motion trajectory generated by the motor output torque and the actual turnout motion trajectory during the same operating period is obtained. The expected turnout motion trajectory generated by the motor output torque can be determined based on the output action parameter curve; the actual turnout motion trajectory can be determined based on the motion parameter curve. Then, by comparing the trajectory deviation of the turnout over several operating periods over time, the cumulative trajectory offset of the turnout during several hardware operation stages is determined. If the cumulative trajectory offset exceeds a preset offset threshold, it is determined that there is an abnormal action switching event in the turnout; otherwise, it is determined that there is no abnormal action switching event in the turnout. This method allows for accurate determination of the fault state at the hardware level.

[0089] In another embodiment, in step S4, based on the abnormal action switching event, the fault state of the turnout is predicted, thereby generating an early warning notification, including:

[0090] Based on the hardware action stage of the turnout corresponding to the abnormal action switching event, identify the potential wear parts of the turnout.

[0091] Based on the deviation trend of the movement trajectory of potentially worn parts during several working periods, the timing information of turnout failure is predicted, and early warning notifications are generated accordingly.

[0092] In the above technical solution, it is understood that the hardware action stages of the turnout, such as the unlocking stage, switching stage, locking stage, and release stage, require the cooperation of different hardware components inside the turnout. Based on the hardware action stage of the turnout corresponding to the abnormal action switching event, potential wear components of the turnout are identified, thereby accurately determining the mechanical wear condition of the internal hardware components. Furthermore, based on the deviation trend of the movement trajectory of potential wear components during several working periods, the time when the deviation reaches the acceptable deviation limit is estimated, and this time is used as the time information of turnout failure, thereby generating an early warning notification and sending it to the platform to achieve safe monitoring of the turnout.

[0093] Please see Figure 2 As shown, an embodiment of this application provides a turnout condition monitoring and fault prediction system based on multi-source curves. This turnout condition monitoring and fault prediction system based on multi-source curves includes:

[0094] The first curve generation module is used to collect current data during turnout operation and generate operating current curves accordingly.

[0095] The working interval calibration module is used to calibrate the time-domain characteristics of several working sub-intervals of the turnout from the operating current curve.

[0096] The turnout start determination module is used to monitor the electrical status of the turnout and determine the start point of the turnout's operation.

[0097] The acquisition module is used to acquire the turnout's own motion image set and the turnout's motor output detection dataset based on the work start node and time domain characteristics.

[0098] The second curve generation module is used to generate motion parameter curves and output action parameter curves based on the motion image set and the motor output detection dataset.

[0099] The abnormal event determination module is used to compare the action parameter curves and output action parameter curves of the turnout during several working periods to determine abnormal events in the turnout's action switching.

[0100] The fault prediction and early warning module is used to predict the fault status of the turnout based on abnormal events during action switching, and thereby generate early warning notifications.

[0101] This turnout condition monitoring and fault prediction system based on multi-source curves delineates all working sub-intervals of the turnout by constructing operating current curves, thereby constructing the turnout's operating parameter curves and the output operating parameter curves of its motor. By using multiple curves to characterize hardware anomalies of the turnout, it accurately predicts potential faults and improves the electrical and mechanical safety of the turnout.

[0102] In another embodiment, the first curve generation module is used to collect current data during turnout operation to generate an operating current curve, including:

[0103] Monitor the operating status of the starting electrical equipment of the turnout to determine whether the turnout has entered the working cycle;

[0104] Collect the full-process current data of the turnout during several working cycles, identify the time-domain distribution of interference intensity of the full-process current data of each working cycle, and determine the reliability of the full-process current data of each working cycle.

[0105] By comparing the reliability of all current data throughout the entire process, the effective operating current curve of the turnout is generated.

[0106] The working interval calibration module is used to calibrate the time-domain characteristics of several working sub-intervals of the turnout from the operating current curve, including:

[0107] The effective operating current curve is subjected to time-domain variation identification to determine all inflection points of the effective operating current curve; based on all inflection points, the time range characteristics covered by several working sub-sections of the turnout are calibrated; and the several working sub-sections correspond one-to-one with several hardware operation stages of the turnout.

[0108] In another embodiment, the turnout start-up determination module is used to monitor the electrical status of the turnout and determine the turnout's start-up node, including:

[0109] The electrical equipment for monitoring the start of the turnout receives the trigger command and takes the time when the trigger command is successfully executed as the start node of the turnout.

[0110] The acquisition module is used to acquire a set of motion images of the turnout itself and a set of motor output detection datasets of the turnout, based on the working start node and time-domain characteristics, including:

[0111] Starting from the work start node, and based on the time range of several working sub-intervals contained in the time domain characteristics, adjust the time domain change strategy for the shooting parameters of the actual scene where the turnout is located and the time domain change strategy for the detection of the motor output of the turnout.

[0112] Based on the time-domain variation strategy of shooting parameters and the time-domain variation strategy of motor output detection, a set of motion images of the turnout itself and a set of motor output detection data of the turnout are collected; the motion image set includes a subset of motion images of several turnout entities corresponding one-to-one with several working sub-sections, and the motor output detection data set includes a subset of motor output torque data corresponding one-to-one with several working sub-sections.

[0113] In another embodiment, the second curve generation module is used to generate motion parameter curves and output action parameter curves based on the motion image set and the motor output detection dataset, including:

[0114] The action image subsets of all turnout entities under the action image set are identified to obtain several action trajectories of several working sub-intervals corresponding to the turnout entities, and these are integrated to generate action parameter curves.

[0115] The output torque data subsets of the motor output detection dataset are integrated according to time sequence to generate output action parameter curves.

[0116] The abnormal event determination module is used to compare the action parameter curves and output action parameter curves of the turnout during several working periods to determine abnormal events in the turnout's action switching, including:

[0117] By comparing the action parameter curves and output action parameter curves of the turnout during the same working period, the trajectory deviation between the expected turnout action trajectory generated by the motor output torque during the same working period and the actual turnout action trajectory is obtained.

[0118] By comparing the trajectory deviation of the turnout over a certain period of time, the cumulative trajectory offset of the turnout during a certain hardware operation stage is determined, thereby identifying abnormal events in the turnout's operation switching.

[0119] In another embodiment, the fault prediction and early warning module is used to predict the fault state of the turnout based on the abnormal event of the action switching, and thereby generate an early warning notification, including:

[0120] Based on the hardware action stage of the turnout corresponding to the abnormal action switching event, identify the potential wear parts of the turnout.

[0121] Based on the deviation trend of the movement trajectory of potentially worn parts during several working periods, the timing information of turnout failure is predicted, and early warning notifications are generated accordingly.

[0122] The turnout condition monitoring and fault prediction system based on multi-source curves of the present invention has the same operation and effect as the turnout condition monitoring and fault prediction method based on multi-source curves described above, and will not be described again here.

[0123] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. This disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims. Thus, if these modifications and variations of the invention fall within the scope of the claims of the invention and their equivalents, the invention is also intended to include these modifications and variations.

Claims

1. A method for monitoring and failure prediction of turnout state based on multi-source curve, characterized in that, Comprise: Step S1: Collecting current data during the operation of the turnout to generate an action current curve; and calibrating time domain features of a plurality of operation subintervals of the turnout from the action current curve; Step S2: Monitoring the electrical state of the turnout to determine the operation start node of the turnout; and collecting the action image set of the turnout itself and the motor output detection data set of the turnout according to the operation start node and the time domain features; Step S3: Generating an action parameter curve and an output action parameter curve according to the action image set and the motor output detection data set; and determining an action switching abnormal event of the turnout by comparing the action parameter curve and the output action parameter curve of the turnout during a plurality of operation periods; Step S4: Predicting the fault state of the turnout according to the action switching abnormal event to generate a warning notification; In step S3, the action parameter curve and the output action parameter curve are generated according to the action image set and the motor output detection data set; The action switching abnormal event of the turnout is determined by comparing the action parameter curve and the output action parameter curve of the turnout during a plurality of operation periods, comprising: All turnout entity action image subsets under the action image set are identified to obtain a plurality of action trajectories of the turnout entity corresponding to the plurality of operation subintervals, thereby generating an action parameter curve; The motor output torque data subset under the motor output detection data set is integrated according to time sequence to generate an output action parameter curve; The trajectory deviation between the expected turnout action trajectory and the actual turnout action trajectory of the motor output torque of the turnout during the same operation period is obtained by comparing the action parameter curve and the output action parameter curve of the turnout during the same operation period; The trajectory deviation of the turnout during a plurality of operation periods is compared according to time lapse to determine the trajectory deviation accumulation of the turnout during a plurality of hardware action stages, thereby determining the action switching abnormal event of the turnout.

2. The turnout state monitoring and fault prediction method based on multiple source curves according to claim 1, wherein: In step S1, the current data during the operation of the turnout is collected to generate an action current curve; and the time domain features of a plurality of operation subintervals of the turnout are calibrated from the action current curve, comprising: The action state of the starting electrical equipment of the turnout is monitored to determine whether the turnout enters an operation period; The full-process current data of the turnout during a plurality of operation periods is collected, the interference intensity time domain distribution of the full-process current data of each operation period is identified, and the credibility of the full-process current data of each operation period is determined; The credibility of all full-process current data is compared to generate an effective action current curve of the turnout; The time domain change of the effective action current curve is identified to determine all turning points of the effective action current curve; and the time range features covered by a plurality of operation subintervals are calibrated according to all turning points; wherein the plurality of operation subintervals one-to-one correspond to a plurality of hardware action stages of the turnout. 3.The method of claim 1, wherein: in step S2, an electrical state of the turnout is monitored to determine a work start node of the turnout; and in step S3, based on the work start node and the time domain feature, a set of action images of the turnout itself and a set of motor output detection data of the turnout are collected, including: monitoring a trigger instruction received by a starting electrical device of the turnout, and taking a time point at which the trigger instruction is successfully executed as the work start node of the turnout; taking the work start node as a starting time point, and adjusting a shooting parameter time domain variation strategy for the actual scene in which the turnout is located and a motor output detection time domain variation strategy for the turnout according to a plurality of time ranges corresponding to the plurality of work subintervals included in the time domain feature; and collecting the set of action images of the turnout itself and the set of motor output detection data of the turnout according to the shooting parameter time domain variation strategy and the motor output detection time domain variation strategy; wherein the set of action images includes a plurality of turnout entity action image subsets corresponding to the plurality of work subintervals, and the set of motor output detection data includes a plurality of motor output torque data subsets corresponding to the plurality of work subintervals. 4.The method of claim 1, wherein: in step S4, based on the action switching abnormal event, a fault state of the turnout is predicted to generate an early warning notification, including: according to a hardware action phase of the turnout corresponding to the action switching abnormal event, a potential wear component of the turnout is marked; and according to a trend of action trajectory deviation of the potential wear component during the plurality of work periods, time information of failure of the turnout is predicted to generate the early warning notification. including: a first curve generation module configured to collect current data during a work period of the turnout to generate an action current curve; a work interval marking module configured to mark time domain features of a plurality of work subintervals of the turnout from the action current curve; a turnout start determination module configured to monitor an electrical state of the turnout to determine a work start node of the turnout; a collection module configured to collect a set of action images of the turnout itself and a set of motor output detection data of the turnout based on the work start node and the time domain feature; a second curve generation module configured to generate an action parameter curve and an output action parameter curve based on the set of action images and the set of motor output detection data; an abnormal event determination module configured to compare the action parameter curve and the output action parameter curve of the turnout during a plurality of work periods to determine an action switching abnormal event of the turnout; and a fault prediction and early warning module configured to predict a fault state of the turnout based on the action switching abnormal event to generate an early warning notification. the second curve generation module is configured to generate an action parameter curve and an output action parameter curve based on the set of action images and the set of motor output detection data, including: ​ ​ ​ ​ ​ ​ 5. A system for monitoring and predicting failure of a turnout based on multi-source curves, characterized in that, ​ ​ ​ ​ ​ ​ ​ ​ ​ identify all switch entity action image subsets under the action image set to obtain a plurality of action trajectories of the switch entity corresponding to the plurality of work subintervals, and integrate to generate an action parameter curve; integrate the motor output torque data subset under the motor output detection data set according to time sequence to generate an output action parameter curve; The abnormal event determination module is configured to compare the action parameter curve and the output action parameter curve of the switch during a plurality of work periods to determine an action switching abnormal event of the switch, including: comparing the action parameter curve and the output action parameter curve of the switch during the same work period to obtain a trajectory deviation between a switch action trajectory expected to be generated by the motor output torque of the switch during the same work period and an actual switch action trajectory of the switch; comparing the trajectory deviations of the switch during a plurality of work periods according to time lapse to determine a trajectory deviation accumulation of the switch during a plurality of hardware action stages, thereby determining the action switching abnormal event of the switch.

6. The switch state monitoring and fault prediction system based on multiple source curves according to claim 5, wherein: The first curve generation module is configured to collect current data of the switch during work to generate an action current curve, including: monitoring an action state of a starting electrical device of the switch to determine whether the switch enters a work cycle; collecting whole-process current data of the switch during a plurality of work cycles, identifying an interference intensity time domain distribution of the whole-process current data of each work cycle, and determining a credibility of the whole-process current data of each work cycle; comparing the credibilities of all whole-process current data to generate an effective action current curve of the switch; The work interval calibration module is configured to calibrate time domain features of a plurality of work subintervals of the switch from the action current curve, including: identifying time domain changes of the effective action current curve to determine all turning points of the effective action current curve, and calibrating time range features covered by the plurality of work subintervals according to the all turning points; wherein the plurality of work subintervals one-to-one correspond to a plurality of hardware action stages of the switch.

7. The switch state monitoring and fault prediction system based on multiple source curves according to claim 5, wherein: The switch starting determination module is configured to monitor an electrical state of the switch to determine a work starting node of the switch, including: monitoring a trigger instruction received by a starting electrical device of the switch, and taking a time point at which the trigger instruction is successfully executed as the work starting node of the switch; The collection module is configured to collect an action image set of the switch and a motor output detection data set of the switch according to the work starting node and the time domain features, including: adjusting a shooting parameter time domain change strategy of an actual scene in which the switch is located and a motor output detection time domain change strategy of the switch according to a plurality of time ranges corresponding to the plurality of work subintervals included in the time domain features, with the work starting node as a starting time point. According to the shooting parameter time domain change strategy and the motor output detection time domain change strategy, a motion image set of the turnout itself and a motor output detection data set of the turnout are collected; wherein the motion image set includes a plurality of turnout entity motion image subsets corresponding to the plurality of working subintervals, and the motor output detection data set includes a plurality of motor output torque data subsets corresponding to the plurality of working subintervals.

8. The turnout state monitoring and fault prediction system based on multi-source curves according to claim 5, wherein: The fault prediction and early warning module is configured to predict a fault state of the turnout according to the motion switching abnormal event, and generate an early warning notification, including: According to the hardware motion stage of the turnout corresponding to the motion switching abnormal event, the potential wear component of the turnout is calibrated; According to the motion trajectory deviation trend of the potential wear component during the plurality of working periods, the time information of the failure of the turnout is predicted, and an early warning notification is generated.

Images