A platform door anomaly diagnosis method and device, a terminal device, and a storage medium

Abstract

Embodiments of the present application disclose a platform door abnormality diagnosis method and device, a terminal device and a storage medium. The method comprises: acquiring current data of a motor, speed data of a door body movement and displacement data of the door body when the platform door performs an opening action multiple times; performing discrete processing on the displacement data to obtain multiple displacement intervals; constructing a current envelope line and a speed envelope line according to the current data, the speed data and the displacement intervals; and determining whether the platform door is abnormal according to the speed data, the current data, the current envelope line and the speed envelope line. Embodiments of the present application can accurately detect whether the platform door is abnormal according to the action data when the platform door performs an opening action, thereby solving the technical problem that the prior art cannot accurately determine whether the platform door is abnormal.

Description

Technical Field

[0001] This application relates to the field of rail transit, and in particular to a method, device, terminal equipment, and storage medium for diagnosing platform screen door anomalies. Background Technology

[0002] With continuous economic development, rail transit construction is booming in major cities. Currently, to separate passengers from the tracks, platform screen doors are generally installed on both sides of the platform at rail transit stations to ensure train operation safety. Therefore, regular maintenance of platform screen doors is particularly important. Most current maintenance solutions for platform screen doors fall under the category of periodic maintenance; however, this approach is prone to "over-maintenance" or "under-maintenance." Furthermore, other intelligent maintenance solutions used in the operation and maintenance process are mostly based on feature engineering and machine learning; however, intelligent maintenance solutions involve a large workload and are difficult to apply in the platform screen door scenario.

[0003] In conclusion, accurately detecting whether there are any abnormalities in platform screen doors has become a pressing technical problem that needs to be solved. Summary of the Invention

[0004] This invention provides a method, device, terminal equipment, and storage medium for diagnosing platform screen door anomalies, which solves the technical problem that existing technologies cannot accurately detect whether platform screen doors have anomalies.

[0005] In a first aspect, embodiments of the present invention provide a method for diagnosing platform screen door anomalies, including:

[0006] Acquire the motor current data, door movement speed data, and door displacement data when the platform door performs multiple opening actions;

[0007] The displacement data is discretized to obtain multiple displacement intervals;

[0008] Based on the current data, the velocity data, and the displacement range, construct the current envelope and the velocity envelope;

[0009] Based on the speed data, the current data, the current envelope, and the speed envelope, determine whether the platform door is abnormal.

[0010] Preferably, the step of discretizing the displacement data to obtain multiple displacement intervals includes:

[0011] Based on the displacement data and preset filtering conditions, the target displacement data is obtained;

[0012] The target displacement data is divided into multiple displacement intervals by dividing the interval length corresponding to the target displacement data.

[0013] The displacement data is assigned to the corresponding displacement intervals, and the value of the displacement data in each displacement interval is updated to the right boundary of the displacement interval.

[0014] Preferably, obtaining the target displacement data based on the displacement data and preset filtering conditions includes:

[0015] The first displacement data with the largest value is determined from the displacement data;

[0016] Determine the sub-interval length of each displacement interval, and calculate the minimum value that is greater than or equal to the first displacement data and is divisible by the sub-interval length;

[0017] The minimum value is used as the target displacement data.

[0018] Preferably, constructing the current envelope and velocity envelope based on the current data, the velocity data, and the displacement interval includes:

[0019] Obtain first current data corresponding to each displacement interval from the current data, and construct a current array corresponding to each displacement interval based on the first current data;

[0020] Obtain first velocity data corresponding to each displacement interval from the velocity data, and construct a velocity array corresponding to each displacement interval based on the first velocity data;

[0021] A current envelope is constructed based on each of the current arrays, and a velocity envelope is constructed based on each of the velocity arrays.

[0022] Preferred options also include:

[0023] The first current data in each of the current arrays and the first velocity data in each of the velocity arrays are filtered.

[0024] Preferably, the step of constructing a current envelope based on each of the current arrays and constructing a velocity envelope based on each of the velocity arrays includes:

[0025] Obtain the maximum current data and minimum current data from each of the current arrays; construct the upper current envelope based on each of the maximum current data and construct the lower current envelope based on each of the minimum current data.

[0026] Obtain the maximum speed data and minimum speed data from each of the speed arrays. Construct an upper speed envelope based on each maximum speed data and a lower speed envelope based on each minimum speed data.

[0027] Preferably, determining whether the platform screen door is abnormal based on the speed data, the current data, the current envelope, and the speed envelope includes:

[0028] Based on the speed data and current data of each door opening action, construct the current curve and speed curve corresponding to each door opening action;

[0029] Calculate the first area between the velocity curve and the velocity envelope, and calculate the second area between the current curve and the current envelope;

[0030] Based on the first area and the second area corresponding to each door opening action, it is determined whether there is an abnormal door opening action.

[0031] Preferably, calculating the first area between the velocity curve and the velocity envelope includes:

[0032] Calculate the sub-area between each point on the velocity curve and the velocity envelope;

[0033] Within each displacement interval, the sub-area with the largest value is determined, and the sub-area with the largest value is taken as the target sub-area corresponding to the displacement interval.

[0034] The target sub-areas corresponding to each displacement interval are added together to obtain the first area between the velocity curve and the velocity envelope.

[0035] Preferably, calculating the sub-area between each point on the velocity curve and the velocity envelope includes:

[0036] Determine the target displacement interval corresponding to each velocity data on the velocity curve, and determine the target maximum velocity data and target minimum velocity data corresponding to the target displacement interval;

[0037] Based on the target maximum speed data and the target minimum speed data corresponding to each speed data, calculate the area corresponding to each speed data.

[0038] Preferably, determining whether an abnormal door opening action exists based on the first area and the second area corresponding to each door opening action includes:

[0039] Based on the distribution of the first area and the distribution of the second area corresponding to each door opening action, it is determined whether there is any abnormality in the platform door.

[0040] Secondly, embodiments of the present invention provide a platform door anomaly diagnosis device, comprising:

[0041] The data acquisition module is used to acquire the motor current data, door movement speed data, and door displacement data when the platform door performs multiple opening actions;

[0042] The discrete processing module is used to perform discrete processing on the displacement data to obtain multiple displacement intervals;

[0043] An envelope construction module is used to construct a current envelope and a velocity envelope based on the current data, the velocity data, and the displacement range.

[0044] The abnormal action determination module is used to determine whether there is an abnormal door opening action in the door opening action based on the speed data, the current data, the current envelope, and the speed envelope.

[0045] Thirdly, embodiments of the present invention provide a terminal device, the terminal device including a processor and a memory;

[0046] The memory is used to store computer programs and to transfer the computer programs to the processor;

[0047] The processor is configured to execute a platform door anomaly diagnosis method as described in the first aspect, according to instructions in the computer program.

[0048] Fourthly, embodiments of the present invention provide a storage medium for storing computer-executable instructions, which, when executed by a computer processor, are used to perform a platform door anomaly diagnosis method as described in the first aspect.

[0049] The present invention provides a method, device, terminal equipment, and storage medium for diagnosing platform screen door anomalies. The method includes: acquiring current data of the motor, speed data of the door body, and displacement data of the door body when the platform screen door performs multiple opening actions; discretizing the displacement data to obtain multiple displacement intervals; constructing a current envelope and a speed envelope based on the current data, speed data, and displacement intervals; and determining whether there is an anomaly in the platform screen door based on the speed data, current data, current envelope, and speed envelope.

[0050] This invention, through its embodiments, can accurately detect whether a platform screen door is malfunctioning simply by analyzing the action data during its opening action. This solves the technical problem in existing technologies where accurate detection of platform screen door malfunctions is impossible. Furthermore, the platform screen door malfunction detection method provided in this embodiment does not require periodic maintenance of the platform screen door, reducing the likelihood of "over-maintenance" or "under-maintenance." Additionally, this invention does not rely on feature engineering or machine learning, has fewer limitations, and is applicable to most platform screen door scenarios, avoiding situations where it is difficult to apply in platform screen door applications. Attached Figure Description

[0051] Figure 1 This is a flowchart illustrating a platform door anomaly diagnosis method provided in an embodiment of the present invention.

[0052] Figure 2 This is a schematic diagram illustrating the discrete processing of displacement data provided in an embodiment of the present invention.

[0053] Figure 3 This is a schematic diagram of an envelope provided in an embodiment of the present invention.

[0054] Figure 4 This is a flowchart illustrating another platform door anomaly diagnosis method provided in an embodiment of the present invention.

[0055] Figure 5 This is a schematic diagram of a current envelope provided in an embodiment of the present invention.

[0056] Figure 6 This is a schematic diagram of a velocity envelope provided in an embodiment of the present invention.

[0057] Figure 7 This is a schematic diagram of the first interval distribution of the first area provided in an embodiment of the present invention.

[0058] Figure 8 This is a schematic diagram illustrating the setting of a first abnormal threshold according to an embodiment of the present invention.

[0059] Figure 9 This is a schematic diagram of the second interval distribution of the second area provided in an embodiment of the present invention.

[0060] Figure 10 This is a schematic diagram illustrating the setting of a second abnormal threshold according to an embodiment of the present invention.

[0061] Figure 11 The results of anomaly identification of the velocity curve provided in the embodiments of the present invention.

[0062] Figure 12 The results of anomaly identification of the current curve provided in the embodiments of the present invention.

[0063] Figure 13 This is a schematic diagram of the structure of a platform door abnormality diagnosis device provided in an embodiment of the present invention.

[0064] Figure 14 This is a schematic diagram of the structure of a terminal device provided in an embodiment of the present invention. Detailed Implementation

[0065] The following description and accompanying drawings fully illustrate specific embodiments of this application to enable those skilled in the art to practice them. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of embodiments of this application includes the entire scope of the claims and all available equivalents of the claims. In this document, each embodiment may be referred to individually or collectively by the term "invention," which is merely for convenience and is not intended to automatically limit the scope of the application to any single invention or inventive concept if more than one invention is disclosed. Relational terms such as "first" and "second" are used herein only to distinguish one entity or operation from another, without requiring or implying any actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed. The various embodiments in this document are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the structures, products, etc., disclosed in the embodiments, since they correspond to the disclosed parts, the descriptions are relatively simple; relevant details can be found in the method section.

[0066] Currently, most maintenance solutions for platform screen doors are periodic, meaning they are inspected and maintained only periodically. However, periodic maintenance is prone to either over-maintenance or under-maintenance. Furthermore, most other intelligent maintenance solutions used in the operation and maintenance process are based on feature engineering and machine learning, which have the following main problems:

[0067] (1) Feature engineering requires extensive mechanistic knowledge and a large amount of work to achieve good application results.

[0068] (2) Machine learning and deep learning models lack interpretability and are difficult to implement in security-critical platform door scenarios.

[0069] (3) Most intelligent operation and maintenance solutions currently use supervised machine learning models. However, supervised machine learning models require a large amount of labeled data, which is difficult to meet in reality.

[0070] Based on this, embodiments of the present invention provide a method for diagnosing platform screen door anomalies, such as... Figure 1 As shown, Figure 1This is a flowchart illustrating a platform screen door anomaly diagnosis method provided in an embodiment of the present invention. The platform screen door anomaly diagnosis method provided in this embodiment can be executed by a platform screen door anomaly diagnosis device. This device can be implemented through software and / or hardware, and can consist of two or more physical entities, or a single physical entity. For example, the platform screen door anomaly diagnosis device can be a computer, a host computer, a tablet, or other terminal device. The method includes the following steps:

[0071] Step 101: Obtain the motor current data, door movement speed data, and door displacement data when the platform door performs the opening action multiple times.

[0072] In this embodiment, motion data of the platform screen door during multiple historical opening actions is first acquired. This motion data includes motor current data, door movement speed data, and door displacement data. Specifically, the motor current data refers to the current of the motor driving the platform screen door during the opening process; the door movement speed data refers to the speed at which the door moves during the opening process; and the door displacement data refers to the distance the door moves during the opening process. For example, in one embodiment, motion data of the platform screen door during a total of 410,719 opening actions are acquired. For each opening action, motor current data, door movement speed data, and door displacement data are collected. Each data point is sampled at 110 points with a sampling interval of 0.045 seconds; that is, 110 data points of current, speed, and displacement data are collected for each opening action.

[0073] Step 102: Discretize the displacement data to obtain multiple displacement intervals.

[0074] Since displacement data is a continuous variable, in order to reduce data storage and subsequent computation, this embodiment further discretizes the displacement data to obtain multiple displacement intervals. For example, the displacement data can be divided into multiple displacement intervals, and the displacement data within each interval can be updated to the same value, thus completing the discretization of the displacement data.

[0075] In one embodiment, the displacement data is discretized to obtain multiple displacement intervals, including:

[0076] Step 1021: Obtain the target displacement data based on the displacement data and the preset filtering conditions.

[0077] First, based on the displacement data and preset filtering conditions, the target displacement data needs to be determined and used as the largest boundary value in the displacement data. This allows for the determination of interval lengths during subsequent discretization of the displacement data, and the division of these intervals into multiple displacement intervals. The preset filtering conditions refer to pre-defined selection criteria. For example, the filtering conditions could be to use values ​​greater than or equal to the largest displacement data that are divisible by the sub-interval length as the target displacement data.

[0078] In one embodiment, the target displacement data is obtained based on displacement data and preset filtering conditions, including:

[0079] Step 10211: Determine the first displacement data with the largest value from the displacement data.

[0080] First, identify the largest displacement data from the displacement data. For example, let m be the total number of door opening actions, and n be the number of sampling points for the current and velocity data of each door opening action. Then the displacement data is d. ij Let represent the j-th displacement value in the i-th door opening action (i∈{1,2,…,m}, j∈{1,2,…,n}). Similarly, let the current data be denoted as c. ij And the speed data is s ij The first displacement data d with the largest value is determined from the displacement data. max for:

[0081] d max =max{d ij (i=1,2,…,m)(j=1,2,…,n)}.

[0082] Step 10212: Determine the sub-interval length of each displacement interval, and calculate the minimum value that is greater than or equal to the first displacement data and is divisible by the sub-interval length.

[0083] Next, the length of the sub-interval for each displacement interval is determined. It is understood that the sub-interval length can be set according to actual needs in this embodiment, and the specific value of the sub-interval length is not limited in this embodiment. After determining the sub-interval length for each displacement interval, the minimum value that is greater than or equal to the first displacement data and divisible by the sub-interval length is further calculated. For example, taking the sub-interval length as 'a', the minimum value is calculated using the following filtering conditions:

[0084] Filtering condition (1)d u >=d max .

[0085] Filtering condition (2) a|d u .

[0086] Among all integers that satisfy filtering conditions (1) and filtering conditions (2), determine the minimum value with the smallest value.

[0087] Step 10213: Use the minimum value as the target displacement data.

[0088] Then, the minimum value is taken as the target displacement data, and the target displacement data is denoted as d. umin .

[0089] Step 1022: Divide the interval length corresponding to the target displacement data to obtain multiple displacement intervals.

[0090] After obtaining the target displacement data, the length of the interval corresponding to the target displacement data can be determined, i.e., [0, d]. umin Then, based on the sub-interval length a, the interval length [0, d] is... umin Divided into Multiple displacement intervals are obtained from a small interval.

[0091] Step 1023: Assign the displacement data to the corresponding displacement intervals, and update the value of the displacement data in each displacement interval to the right boundary of the displacement interval.

[0092] Next, the displacement data are assigned to the corresponding displacement intervals, as follows:

[0093]

[0094] For each displacement interval, update the value of each displacement data point to the right boundary of the displacement interval, i.e., d. ij = a(k+1), thus obtaining the updated displacement data.

[0095] For example, the total number of door opening actions is m = 410719, the number of sampling points for each action is n = 110, and the first displacement data is d. max =968.4, subinterval length a=5. Based on the selection criteria, d is calculated. umin =970, and obtain 194 displacement intervals with a length of 5: {[0,5],(5,10],(10,15],…,(965,970]}.

[0096] Then, all displacement data d ij Assign the data to the corresponding displacement interval and let the displacement data d ij The value is updated to the right boundary value of the displacement interval, thus completing the discretization of the displacement data. Figure 2 As shown.

[0097] Step 103: Construct the current envelope and velocity envelope based on the current data, velocity data, and displacement range.

[0098] After obtaining the displacement range, current envelopes and velocity envelopes are further constructed based on current data, velocity data, and the displacement range. An envelope is a curve that is tangent to at least one point in every curve of the curve family; that is, at at least one point on the envelope, the envelope and a curve in the curve family passing through that point share a common tangent. In this embodiment, the envelope includes an upper boundary and a lower boundary enveloping the curve family, such as... Figure 3 As shown. In one embodiment, a current array and a velocity array corresponding to each displacement interval can be constructed based on the current data and velocity data, and a current envelope can be constructed based on the current array and a velocity envelope can be constructed based on the velocity array.

[0099] Step 104: Based on the speed data, current data, current envelope, and speed envelope, determine whether there is any abnormality in the platform screen door.

[0100] Finally, based on the speed data, current data, current envelope, and speed envelope, it can be determined whether the platform screen door is abnormal. For example, based on the speed and current data corresponding to each door opening action, a current curve and a speed curve corresponding to each door opening action can be constructed. Then, the first area between the speed curve and the speed envelope is calculated, and the second area between the current curve and the current envelope is calculated. Finally, based on the distribution of the first and second areas corresponding to each door opening action, it can be determined whether there is an abnormal door opening action. For example, if there is a clear boundary between the interval distribution of the first area or the interval distribution of the second area, the center point of the boundary is used as the abnormality threshold. Door opening actions corresponding to speed curves with a first area greater than the abnormality threshold are determined to be abnormal door opening actions, or door opening actions corresponding to current curves with a second area greater than the abnormality threshold are determined to be abnormal door opening actions. If an abnormal door opening action is found, the platform screen door is confirmed to be abnormal.

[0101] As described above, this embodiment of the invention discretizes the displacement data of the platform screen door during its opening action to obtain multiple displacement intervals. Then, based on current data, velocity data, and the displacement intervals, current envelopes and velocity envelopes are constructed. Finally, based on the velocity data, current data, current envelopes, and velocity envelopes, it is determined whether the platform screen door exhibits any abnormalities. This embodiment of the invention only requires the action data of the platform screen door during its opening action to accurately detect whether there are any abnormalities, solving the technical problem in the prior art that it is impossible to accurately determine whether there are any abnormalities in the platform screen door. Furthermore, the platform screen door anomaly detection method provided in this embodiment does not require periodic maintenance of the platform screen door, reducing the likelihood of "over-maintenance" or "under-maintenance." In addition, this embodiment of the invention does not rely on feature engineering and machine learning, has fewer limitations, and is applicable to most platform screen door scenarios, avoiding situations where it is difficult to apply in platform screen door scenarios.

[0102] like Figure 4 As shown, Figure 4 This is a flowchart of another platform door anomaly diagnosis method provided by an embodiment of the present invention. Figure 4 The platform screen door anomaly diagnosis method shown is a concretization of the above-mentioned platform screen door anomaly diagnosis method, including:

[0103] Step 201: Obtain the motor current data, door movement speed data, and door displacement data when the platform door performs the opening action multiple times.

[0104] Step 202: Discretize the displacement data to obtain multiple displacement intervals.

[0105] Step 203: Construct the current envelope and velocity envelope based on the current data, velocity data, and displacement range.

[0106] Based on the above embodiments, current envelopes and velocity envelopes are constructed according to current data, velocity data, and displacement range, including:

[0107] Step 2031: Obtain the first current data corresponding to each displacement interval from the current data, and construct the current array corresponding to each displacement interval based on the first current data.

[0108] In this embodiment, the first step is to construct current data. Specifically, first current data corresponding to each displacement interval is obtained from the current data, and a current array corresponding to each displacement interval is constructed based on the first current data. For example, after discretizing the displacement data, for displacement data d... ij Only Total The displacement takes various values. For ease of description, let the displacement data be denoted as... Traverse d k And for each d k Maintain the current array C separately k The current array C k It stores displacement data d k At least one corresponding first current data was obtained, and a total of Current array

[0109] Step 2032: Obtain the first velocity data corresponding to each displacement interval from the velocity data, and construct a velocity array corresponding to each displacement interval based on the first velocity data.

[0110] Similarly, for velocity data, a velocity array S corresponding to each displacement interval is constructed. k The velocity array stores the displacement data d for each displacement. k At least one corresponding first velocity data was obtained, and a total of velocity array

[0111] In one embodiment, it also includes:

[0112] Filter the first current data in each current array and the first velocity data in each velocity array.

[0113] In one embodiment, after obtaining the current array and speed array, the current array and speed array are further filtered. In this embodiment, the purpose of filtering the current array and speed array is that, since the present invention aims to retain the motion data of the platform screen door under normal conditions, during the motion data acquisition process, some abnormal motion data may be generated due to sensor defects or human influence. Abnormal motion data differs from normal motion data; therefore, to ensure the accuracy of subsequent anomaly detection of the platform screen door, it is necessary to filter the abnormal motion data.

[0114] In one embodiment, the specific process for filtering speed data and current data is as follows:

[0115] For each displacement data d k The corresponding current array C k and velocity array S k Calculate the current array C respectively k mean μ Ck and velocity array S k mean μ Sk and the current array C for calculation k Standard deviation σ Ck and velocity array S k Standard deviation σSk Then, for the current array C k Only retain current data that meets the following conditions.

[0116] u Ck -3σ Ck <c k Ck +3σ Ck

[0117] Among them, c k For the current array C k The first current data in the data.

[0118] For the velocity array, only retain velocity data that meets the following conditions.

[0119] u Sk -3σ Sk k Sk +3σ Sk

[0120] Among them, s k For the velocity array S k The first velocity data in the data.

[0121] Step 2033: Construct a current envelope for each current array and a velocity envelope for each velocity array.

[0122] Then, a current envelope can be constructed based on each current array, and a velocity envelope can be constructed based on each velocity array. Specifically, when constructing the current envelope, the maximum and minimum current data are obtained from each current array. Based on each maximum current data, an upper current envelope is constructed, and based on each minimum current data, a lower current envelope is constructed. For example, for each discrete displacement data d... k The corresponding current array C k Obtain each current array C separately. k Maximum current data and minimum current data

[0123]

[0124]

[0125] Then, the maximum current data of all current arrays will be processed. By connecting them sequentially, the upper envelope of the current can be obtained. Minimum current number of all current arrays By connecting them sequentially, the current envelope can be obtained. Current envelope such as​​​Figure 5 As shown.

[0126] When constructing the velocity envelope, the maximum and minimum velocity data are obtained from each velocity array. Based on each maximum velocity data, the upper velocity envelope is constructed, and based on each minimum velocity data, the lower velocity envelope is constructed.

[0127] Similarly, when constructing the velocity envelope, for each displacement data d k Corresponding velocity array S k Get each S separately k Maximum speed data and minimum speed data

[0128]

[0129]

[0130] Next, the maximum speed data of all speed arrays. By connecting them sequentially, the upper envelope of velocity can be obtained. Minimum speed data for all speed arrays By connecting them sequentially, the lower envelope of velocity can be obtained. like Figure 6 As shown.

[0131] Step 204: Based on the speed data and current data of each door opening action, construct the corresponding current curve and speed curve for each door opening action.

[0132] After obtaining the velocity and current envelopes, anomaly detection for the platform screen doors can be performed. First, based on the velocity and current data corresponding to each door opening action, construct the current and velocity curves corresponding to each opening action. This is done by connecting the velocity data corresponding to each door opening action to obtain the velocity curve {s}. j ,j=1,2,…,n}. Similarly, by connecting the current data corresponding to each door opening action, the current curve {c j ,j=1,2,…,n}.

[0133] Step 205: Calculate the first area between the velocity curve and the velocity envelope, and calculate the second area between the current curve and the current envelope.

[0134] Then, the first area between each velocity curve and the velocity envelope is calculated, and the second area between each current curve and the current envelope is calculated. For example, the first area between the velocity curve and the velocity envelope can be calculated based on each velocity data point in the velocity curve and the corresponding boundary points in the upper and lower velocity envelopes. Specifically, in one embodiment, calculating the first area between the velocity curve and the velocity envelope includes:

[0135] Step 2051: Calculate the sub-area between each point on the velocity curve and the velocity envelope.

[0136] When calculating the first area, we first calculate the sub-area between each point on the velocity curve and the velocity envelope, that is, we calculate the area between each velocity data and the upper and lower velocity envelopes.

[0137] Specifically, the sub-area between each point on the velocity curve and the velocity envelope is calculated, including:

[0138] Step 20511: Determine the target displacement interval corresponding to each velocity data on the velocity curve, and determine the target maximum velocity data and target minimum velocity data corresponding to the target displacement interval.

[0139] First, determine the target displacement interval corresponding to each velocity data point on the velocity curve. Then, determine the target maximum velocity data and target minimum velocity data corresponding to each target displacement interval. That is, iterate through the velocity values ​​{s}. j Given the group {j = 1, 2, ..., n}, determine the relationship between s and j. j Corresponding displacement data d ij Determine the displacement data d ij The corresponding displacement data d after the update ij ′(d ij ′∈{d k}), determine the relationship with d ij Corresponding target maximum speed data and with d ij Corresponding target minimum speed data and This refers to the target's maximum speed data and target's minimum speed data, which correspond to the speed data.

[0140] Step 20512: Calculate the sub-area corresponding to each speed data based on the target maximum speed data and the target minimum speed data corresponding to each speed data.

[0141] Next, based on the target's maximum and minimum speed data corresponding to each speed data point, the area corresponding to each speed data point is calculated. Specifically, the area (AREA) corresponding to each speed data point can be calculated using the following formula. j :

[0142]

[0143] Step 2052: Determine the sub-area with the largest value in each displacement interval, and take the sub-area with the largest value as the target sub-area corresponding to the displacement interval.

[0144] Next, within each displacement interval, the sub-area with the largest value is determined, and this sub-area is used as the target sub-area corresponding to the displacement interval. The reason for using the sub-area with the largest value as the target sub-area corresponding to the displacement interval is that, since each displacement interval corresponds to multiple velocity data points, i.e., each displacement interval corresponds to multiple areas. Therefore, to avoid recalculating the sub-area within each displacement interval, if different displacement data d... ij The corresponding displacement data d after the update ij ′(d ij ′∈{d k}) are the same d ij ′, then the corresponding AREA j Only the one with the largest area is retained, and the others are the same. ij The corresponding AREA j It is set to 0, as shown in Table 1.

[0145]

[0146]

[0147] Table 1

[0148] Step 2053: Add up the target sub-areas corresponding to each displacement interval to obtain the first area between the velocity curve and the velocity envelope.

[0149] Then, the target sub-areas corresponding to each displacement interval are added together to obtain the first area between the velocity curve and the velocity envelope, which is the first area corresponding to one door opening action. Specifically:

[0150]

[0151] Where AREA is the first area, AREA k For each displacement interval d ij The corresponding target sub-area.

[0152] Similarly, the same method can be used to calculate the second area between the current curve and the current envelope, thereby obtaining the second area corresponding to each door opening action. The specific process can be referred to the above-described process of calculating the first area between the speed curve and the speed envelope, and will not be repeated in this embodiment.

[0153] Step 206: Determine whether there is any abnormality in the platform door based on the first area and the second area corresponding to each door opening action.

[0154] Based on the above embodiments, determining whether there is an abnormality in the platform door according to the first area and the second area corresponding to each door opening action includes:

[0155] Based on the distribution of the first area and the distribution of the second area corresponding to each door opening action, determine whether there is any abnormality in the platform door.

[0156] In one embodiment, the presence of an anomaly in the platform screen door can be determined based on the distribution of a first area and a second area corresponding to each door opening action. Specifically, in one embodiment, the first area and the second area can be used as the first and second anomaly values ​​of the platform screen door, respectively. A first interval distribution of the first anomaly value and a second interval distribution of the second anomaly value are determined. If there is a clear boundary between the first interval distribution of the first anomaly value and the second interval distribution of the second anomaly value, the median value of the boundary in the first interval distribution is used as the first anomaly threshold, and the median value of the boundary in the second interval distribution is used as the second anomaly threshold. Door opening actions corresponding to a first anomaly value greater than the first anomaly threshold or a second anomaly value greater than the second threshold are determined as abnormal door opening actions. For example, as shown... Figure 7 As shown, Figure 7 A schematic diagram showing the distribution of the first interval of the first area corresponding to all door opening actions, from Figure 7 As can be seen, when the outlier value is around 7000, there is a clear boundary in the first area, which divides the first area into two categories. Therefore, the first outlier threshold corresponding to the velocity curve is set to 7000, as follows: Figure 8 As shown. The speed curve with an area greater than 7000 is identified as an abnormal speed curve, and the door opening action corresponding to this speed curve is identified as an abnormal door opening action.

[0157] In another embodiment, when there is no clear boundary between the intervals of the first or second outlier, an outlier threshold is set where the proportion of abnormal door-opening actions to all door-opening actions is in the range of 0.2%-0.5%. For example,... Figure 9 As shown, Figure 9 This is a schematic diagram showing the distribution of the second interval of the second area corresponding to the door-opening action. Figure 9In the second area distribution, there is no clear boundary line, so the second abnormal threshold corresponding to the specified current curve is 8000. Figure 10 As shown, a current curve with an area exceeding 8000 is identified as an abnormal current curve, and the door opening action corresponding to this abnormal current curve is identified as an abnormal door opening action. It can be understood that in this embodiment, in a single door opening action, if either the current curve is an abnormal current curve or the speed curve is an abnormal speed curve, the door opening action is determined to be an abnormal door opening action, indicating an anomaly in the platform door. In one embodiment, 2344 abnormal speed curves and 1286 abnormal current curves are selected from the speed curves and current curves, respectively. Figure 11 and Figure 12 As shown.

[0158] like Figure 13 As shown, Figure 13 A schematic diagram of a platform door anomaly diagnosis device provided in an embodiment of the present invention includes:

[0159] The data acquisition module 301 is used to acquire the motor current data, the door movement speed data, and the door displacement data when the platform door performs multiple opening actions.

[0160] Discrete processing module 302 is used to discretize displacement data to obtain multiple displacement intervals;

[0161] Envelope construction module 303 is used to construct current envelope and velocity envelope based on current data, velocity data and displacement range;

[0162] The abnormal action determination module 304 is used to determine whether there is an abnormal door opening action based on speed data, current data, current envelope, and speed envelope.

[0163] Based on the above embodiments, the discrete processing module 302 includes:

[0164] The data determination unit is used to obtain target displacement data based on displacement data and preset filtering conditions;

[0165] Interval division unit is used to divide the target displacement data into intervals of the specified length, resulting in multiple displacement intervals;

[0166] The data update unit is used to allocate displacement data to the corresponding displacement intervals and update the value of the displacement data in each displacement interval to the right boundary of the displacement interval.

[0167] Based on the above embodiments, the data determination unit is specifically used to determine the first displacement data with the largest value in the displacement data; determine the sub-interval length of each displacement interval; calculate the minimum value that is greater than or equal to the first displacement data and can be divided evenly by the sub-interval length; and use the minimum value as the target displacement data.

[0168] Based on the above embodiments, the envelope construction module 303 includes:

[0169] The current array construction unit is used to obtain the first current data corresponding to each displacement interval from the current data, and construct the current array corresponding to each displacement interval based on the first current data;

[0170] The velocity array construction unit is used to obtain the first velocity data corresponding to each displacement interval from the velocity data, and construct the velocity array corresponding to each displacement interval based on the first velocity data;

[0171] Envelope construction unit, used to construct current envelopes for each current array and velocity envelopes for each velocity array.

[0172] Based on the above embodiments, a filtering unit is also included, which is used to filter the first current data in each current array and the first speed data in each speed array.

[0173] Based on the above embodiments, the envelope construction unit is specifically used to obtain the maximum current data and minimum current data from each current array, construct the upper current envelope based on each maximum current data, and construct the lower current envelope based on each minimum current data; and to obtain the maximum speed data and minimum speed data from each speed array, construct the upper speed envelope based on each maximum speed data, and construct the lower speed envelope based on each minimum speed data.

[0174] Based on the above embodiments, the abnormal action determination module 304 includes:

[0175] The curve construction unit is used to construct the current curve and speed curve corresponding to each door opening action based on the speed data and current data of each door opening action;

[0176] The area calculation unit is used to calculate the first area between the velocity curve and the velocity envelope, and to calculate the second area between the current curve and the current envelope.

[0177] The anomaly detection unit is used to determine whether there is an abnormal door opening action based on the first area and the second area corresponding to each door opening action.

[0178] Based on the above embodiments, the area calculation unit is specifically used to calculate the sub-area between each point on the velocity curve and the velocity envelope; determine the sub-area with the largest value in each displacement interval, and take the sub-area with the largest value as the target sub-area corresponding to the displacement interval; add the target sub-areas corresponding to each displacement interval to obtain the first area between the velocity curve and the velocity envelope.

[0179] Based on the above embodiments, the area calculation unit is specifically used to determine the target displacement interval corresponding to each velocity data on the velocity curve, determine the target maximum velocity data and target minimum velocity data corresponding to the target displacement interval, and calculate the area corresponding to each velocity data according to the target maximum velocity data and the corresponding target minimum velocity data.

[0180] Based on the above embodiments, the anomaly determination unit is specifically used to determine whether there is an anomaly in the platform door according to the distribution of the first area and the distribution of the second area corresponding to each door opening action.

[0181] This embodiment also provides a terminal device, such as Figure 14 As shown, the terminal device 40 includes a processor 400 and a memory 401;

[0182] The memory 401 is used to store the computer program 402 and to transmit the computer program 402 to the processor;

[0183] The processor 400 is used to execute the steps in the above-described embodiment of a platform door anomaly diagnosis method according to the instructions in the computer program 402.

[0184] For example, the computer program 402 may be divided into one or more modules / units, which are stored in the memory 401 and executed by the processor 400 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 402 in the terminal device 40.

[0185] The terminal device 40 may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device 40 may include, but is not limited to, a processor 400 and a memory 401. Those skilled in the art will understand that... Figure 14 This is merely an example of terminal device 40 and does not constitute a limitation on terminal device 40. It may include more or fewer components than shown, or combine certain components, or different components. For example, terminal device 40 may also include input / output devices, network access devices, buses, etc.

[0186] The processor 400 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0187] The memory 401 can be an internal storage unit of the terminal device 40, such as a hard disk or RAM of the terminal device 40. The memory 401 can also be an external storage device of the terminal device 40, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the terminal device 40. Furthermore, the memory 401 can include both internal and external storage units of the terminal device 40. The memory 401 is used to store the computer program and other programs and data required by the terminal device 40. The memory 401 can also be used to temporarily store data that has been output or will be output.

[0188] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0189] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0190] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0191] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0192] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing computer programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0193] This invention also provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform a platform door anomaly diagnosis method, the method comprising the following steps:

[0194] Acquire the motor current data, door movement speed data, and door displacement data when the platform door performs multiple opening actions;

[0195] The displacement data is discretized to obtain multiple displacement intervals;

[0196] Based on the current data, the velocity data, and the displacement range, construct the current envelope and the velocity envelope;

[0197] Based on the speed data, the current data, the current envelope, and the speed envelope, determine whether the platform door is abnormal.

[0198] Note that the above are merely preferred embodiments and the technical principles applied in this invention. Those skilled in the art will understand that the embodiments of this invention are not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the protection scope of this invention. Therefore, although the embodiments of this invention have been described in detail above, the embodiments of this invention are not limited to the above embodiments. More other equivalent embodiments may be included without departing from the concept of the embodiments of this invention, and the scope of the embodiments of this invention is determined by the scope of the appended claims.

Claims

1. A method for diagnosing platform screen door anomalies, characterized in that, include: Acquire the motor current data, door movement speed data, and door displacement data when the platform door performs multiple opening actions; The displacement data is discretized to obtain multiple displacement intervals; Based on the current data, the velocity data, and the displacement range, construct the current envelope and the velocity envelope; Based on the speed data, current data, current envelope, and speed envelope, determine whether the platform door is abnormal, including: constructing a current curve and a speed curve corresponding to each door opening action based on the speed data and current data for each door opening action; calculating a first area between the speed curve and the speed envelope, and calculating a second area between the current curve and the current envelope; and determining whether there is an abnormal door opening action based on the first area and the second area corresponding to each door opening action.

2. The platform door anomaly diagnosis method according to claim 1, characterized in that, The displacement data is discretized to obtain multiple displacement intervals, including: Based on the displacement data and preset filtering conditions, the target displacement data is obtained; The target displacement data is divided into multiple displacement intervals by dividing the interval length corresponding to the target displacement data. The displacement data is assigned to the corresponding displacement intervals, and the value of the displacement data in each displacement interval is updated to the right boundary of the displacement interval.

3. The platform door anomaly diagnosis method according to claim 2, characterized in that, The step of obtaining target displacement data based on the displacement data and preset filtering conditions includes: The first displacement data with the largest value is determined from the displacement data; Determine the sub-interval length of each displacement interval, and calculate the minimum value that is greater than or equal to the first displacement data and is divisible by the sub-interval length; The minimum value is used as the target displacement data.

4. The platform door anomaly diagnosis method according to claim 1, characterized in that, The step of constructing the current envelope and velocity envelope based on the current data, the velocity data, and the displacement interval includes: Obtain first current data corresponding to each displacement interval from the current data, and construct a current array corresponding to each displacement interval based on the first current data; Obtain first velocity data corresponding to each displacement interval from the velocity data, and construct a velocity array corresponding to each displacement interval based on the first velocity data; A current envelope is constructed based on each of the current arrays, and a velocity envelope is constructed based on each of the velocity arrays.

5. The platform door anomaly diagnosis method according to claim 4, characterized in that, Also includes: The first current data in each of the current arrays and the first velocity data in each of the velocity arrays are filtered.

6. The platform door anomaly diagnosis method according to claim 4, characterized in that, The step of constructing a current envelope based on each of the current arrays and constructing a velocity envelope based on each of the velocity arrays includes: Obtain the maximum current data and minimum current data from each of the current arrays; construct the upper current envelope based on each of the maximum current data and construct the lower current envelope based on each of the minimum current data. Obtain the maximum speed data and minimum speed data from each of the speed arrays. Construct an upper speed envelope based on each maximum speed data and a lower speed envelope based on each minimum speed data.

7. The platform door anomaly diagnosis method according to claim 1, characterized in that, The calculation of the first area between the velocity curve and the velocity envelope includes: Calculate the sub-area between each point on the velocity curve and the velocity envelope; Within each displacement interval, the sub-area with the largest value is determined, and the sub-area with the largest value is taken as the target sub-area corresponding to the displacement interval. The target sub-areas corresponding to each displacement interval are added together to obtain the first area between the velocity curve and the velocity envelope.

8. The platform door anomaly diagnosis method according to claim 7, characterized in that, The calculation of the sub-area between each point on the velocity curve and the velocity envelope includes: Determine the target displacement interval corresponding to each velocity data on the velocity curve, and determine the target maximum velocity data and target minimum velocity data corresponding to the target displacement interval; Based on the target maximum speed data and the target minimum speed data corresponding to each speed data, calculate the area corresponding to each speed data.

9. The platform door anomaly diagnosis method according to claim 1, characterized in that, Based on the first area and the second area corresponding to each door opening action, determine whether there is an abnormal door opening action, including: Based on the distribution of the first area and the distribution of the second area corresponding to each door opening action, it is determined whether there is any abnormality in the platform door.

10. A platform door anomaly diagnosis device, characterized in that, include: The data acquisition module is used to acquire the motor current data, door movement speed data, and door displacement data when the platform door performs multiple opening actions; The discrete processing module is used to perform discrete processing on the displacement data to obtain multiple displacement intervals; An envelope construction module is used to construct a current envelope and a velocity envelope based on the current data, the velocity data, and the displacement range. An abnormal action determination module is used to determine whether there is an abnormal door opening action in the door opening action based on the speed data, the current data, the current envelope, and the speed envelope. This includes: constructing a current curve and a speed curve corresponding to each door opening action based on the speed data and current data for each door opening action; calculating a first area between the speed curve and the speed envelope, and calculating a second area between the current curve and the current envelope; and determining whether there is an abnormal door opening action based on the first area and the second area corresponding to each door opening action.

11. A terminal device, characterized in that, The terminal device includes a processor and a memory; The memory is used to store computer programs and to transfer the computer programs to the processor; The processor is configured to execute, according to instructions in the computer program, a platform door anomaly diagnosis method as described in any one of claims 1-9.

12. A storage medium for storing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform a platform door anomaly diagnosis method as described in any one of claims 1-9.

Images