Inspection control method and system for intelligent rail robot

Abstract

The present application discloses an inspection control method and system for an intelligent rail robot, and relates to the technical field of robots moving along guide rails. The inspection control method for an intelligent rail robot comprises: obtaining the inspection data of the rail robot; based on the inspection data, obtaining the time series temperature data of the first cable; based on the time series temperature data, obtaining the temperature abnormality change data of the first cable; the temperature abnormality change data is at least used to characterize the possibility of abnormal temperature change of the first cable; based on the temperature abnormality change data, adjusting the inspection speed of the rail robot. The present application determines the degree of abnormal temperature change of the cable by analyzing the inspection data collected by the rail robot, which is used for subsequent speed control of the rail robot. It is possible to accurately monitor whether the cable has actually undergone an abnormality while being able to timely monitor the abnormality of the cable.

Description

Technical Field

[0001] The present application relates to the technical field of robots moving along guide rails, and specifically to an inspection control method and system for intelligent rail robots. Background Art

[0002] At present, intelligent track robots are widely used in water conservancy projects. For example, intelligent track robots are deployed in cable tunnels or underground pipe galleries of hydropower stations to conduct regular or real-time inspections of transmission cables. Among them, the track robot monitors whether there are abnormalities in the cable (for example, abnormal heating, etc.) through various sensors. If there is abnormal heating, the track robot will issue an alarm to prompt the staff to deal with the abnormal area. In the prior art, the inspection speed of general track robots is fixed. It is easy to understand that during the inspection process, if the speed of the track robot is slower, although the various monitoring data are more accurate, the inspection cycle is longer, and if there is an abnormality in the cable, it cannot be discovered in time; if the speed of the track robot is faster, although the inspection cycle is shorter, it is impossible to obtain accurate monitoring data, that is, it is impossible to accurately determine whether the cable is really abnormal. Summary of the invention

[0003] The purpose of this application is to provide a patrol control method and system for an intelligent rail robot to solve the technical problem that the prior art cannot simultaneously and timely and accurately monitor cable anomalies by patrolling at a fixed speed.

[0004] To achieve the above objectives, this application provides the following technical solutions:

[0005] In the first aspect, the present application proposes a patrol control method for an intelligent rail robot, wherein the rail robot comprises: a thermal imager, a temperature sensor, a vibration sensor and a locator; the rail robot is used to patrol each cable in a cable tunnel; the patrol control method for the intelligent rail robot comprises:

[0006] Obtaining inspection data of the rail robot; the inspection data includes: time-series thermal imaging images taken by the thermal imager, time-series ambient temperature values ​​obtained by the temperature sensor, time-series vibration data obtained by the vibration sensor, time-series positions obtained by the positioner, and time-series current values ​​of each cable;

[0007] Based on the inspection data, obtaining time-series temperature data of a first cable; the first cable is any one of the cables;

[0008] Based on the time-series temperature data, acquiring abnormal temperature change data of the first cable; the abnormal temperature change data is at least used to characterize the possibility of abnormal temperature change of the first cable;

[0009] Based on the abnormal temperature change data, the inspection speed of the rail robot is adjusted.

[0010] As a specific solution in the technical solution of the present application, the obtaining of the time series temperature data of the first cable based on the inspection data includes:

[0011] Inputting the time-series thermal imaging images into an image segmentation model to obtain time-series images of each cable;

[0012] Acquire a time-series image of the first cable from the time-series images of the cables based on a target tracking algorithm;

[0013] Based on the time-series images of the first cable, obtaining a pixel average value of each image;

[0014] Based on the pixel average values ​​of the images, the time-series temperature data of the first cable is acquired; the time-series temperature data includes the time-series temperature sequence of the first cable.

[0015] As a specific solution in the technical solution of the present application, the step of obtaining abnormal temperature change data of the first cable based on the time series temperature data includes:

[0016] Based on the inspection data, obtaining a time series ambient temperature value;

[0017] Based on the time-series ambient temperature values, a time-series ambient temperature sequence of the first cable is obtained; the data in the time-series ambient temperature sequence corresponds one-to-one with the data in the time-series temperature sequence, and the time sequence of the corresponding data is the same;

[0018] Based on the time-series ambient temperature sequence and the time-series temperature sequence, abnormal temperature change data of the first cable is acquired.

[0019] As a specific solution in the technical solution of the present application, the obtaining of abnormal temperature change data of the first cable based on the time-series ambient temperature sequence and the time-series temperature sequence includes:

[0020] Based on the inspection data, obtaining the time-series current value of each cable;

[0021] Based on the time-series current value, a time-series current sequence of the first cable is obtained; the data in the time-series current sequence corresponds one-to-one with the data in the time-series temperature sequence, and the time sequence of the corresponding data is the same;

[0022] Based on the time-series current sequence and the time-series ambient temperature sequence, temperature influence factor data is acquired; the temperature influence factor data is at least used to characterize the temperature change trend of the first cable in adjacent time sequences;

[0023] Based on the temperature influencing factor data, abnormal temperature change data of the first cable is acquired.

[0024] As a specific solution in the technical solution of the present application, the calculation formula for obtaining the temperature influence factor data based on the timing current sequence and the timing ambient temperature sequence is as follows:

[0025]

[0026] in, represents the temperature influence factor of the i-th time series; is the ambient temperature value of the i-th time series, i is greater than or equal to 2; is the ambient temperature value of the i-1th time series; is the current value of the first cable in the i-th time sequence; is the current value of the first cable in the i-1th time sequence; R represents the resistance of the first cable; Indicates the time length between adjacent time series; represents the total mass of the first cable; represents the specific heat capacity of the first cable; A represents the cross-sectional area of ​​the first cable.

[0027] As a specific solution in the technical solution of the present application, based on the temperature influence factor data, a calculation formula for obtaining the abnormal temperature change data of the first cable is as follows:

[0028]

[0029] in, represents the abnormal temperature change data of the i-th time series; represents the temperature value of the first cable at the i-th time sequence; represents the temperature value of the first cable at the i-1th time sequence; Represents the temperature impact factor of the i-th time series.

[0030] As a specific solution in the technical solution of the present application, after obtaining the time-series temperature data of the first cable based on the pixel average value of each image, the method further includes:

[0031] Based on the inspection data, acquiring time-series vibration data;

[0032] Based on the time-series vibration data, a time-series vibration data sequence of the track robot is obtained; the data in the time-series vibration data sequence corresponds one-to-one with the data in the time-series temperature sequence, and the time sequence of the corresponding data is the same;

[0033] Based on the time series vibration data sequence, temperature correction factor data is obtained; the temperature correction factor data is at least used to characterize the degree of influence of the time series vibration data on the time series temperature; the temperature correction factor data includes the Pearson correlation coefficient of the time series vibration data sequence and the time series temperature sequence;

[0034] Based on the temperature correction factor data, the time series temperature data of the first cable is corrected.

[0035] As a specific solution in the technical solution of the present application, after obtaining the abnormal temperature change data of the first cable based on the time series temperature data, the method further includes:

[0036] If the abnormal temperature change data is greater than a first preset value, an abnormal image is acquired based on the inspection data; the abnormal image is a time sequence image including the first cable in each time sequence image and corresponding to the time sequence of the abnormal temperature change data;

[0037] Based on the abnormal image, a plurality of high temperature areas are acquired; the high temperature areas are areas in the abnormal image where the temperature value is higher than the first cable temperature;

[0038] Based on the multiple high temperature areas, obtaining multiple first temperature values;

[0039] Based on the first cable, obtaining a second temperature value;

[0040] Based on the second temperature value and the plurality of first temperature values, a fault probability is obtained; the fault probability is used to characterize at least the possibility of the first cable failing;

[0041] If the failure probability is greater than a second preset value, the inspection speed of the track robot is adjusted based on the abnormal temperature change data.

[0042] As a specific solution in the technical solution of the present application, based on the second temperature value and multiple first temperature values, the calculation formula for obtaining the failure probability is as follows:

[0043]

[0044]

[0045] Wherein, U represents the probability of failure of the first cable; K represents the average value of the abnormal temperature change data of the first cable corresponding to n time series; y represents the number of time series images; Indicates the maximum number of high temperature areas in n time series images; Indicates the degree of influence of the mth high temperature area on the temperature of the first cable in the nth timing diagram; represents the temperature of the first cable in the nth time series image; Indicates the temperature value of the mth high temperature area in the nth time series image; represents the distance between the mth high temperature area and the first cable in the nth time series image; Represents a linear normalization function, which is used to normalize data to the interval (0, 1).

[0046] In the second aspect, the present application proposes a patrol control system for an intelligent rail robot, wherein the rail robot comprises: a thermal imager, a temperature sensor, a vibration sensor and a locator; the rail robot is used to patrol each cable in a cable tunnel; the patrol control system for the intelligent rail robot comprises:

[0047] A reader, used to obtain inspection data of the rail robot; the inspection data includes: time-series thermal imaging images taken by the thermal imager, time-series ambient temperature values ​​obtained by the temperature sensor, time-series vibration data obtained by the vibration sensor, time-series positions obtained by the positioner, and time-series current values ​​of each cable;

[0048] The server is configured to obtain time-series temperature data of a first cable based on the inspection data; the first cable is any one of the cables;

[0049] And, based on the time series temperature data, acquiring abnormal temperature change data of the first cable; the abnormal temperature change data is at least used to characterize the possibility of abnormal temperature change of the first cable;

[0050] The controller is used to adjust the inspection speed of the track robot based on the abnormal temperature change data.

[0051] As a specific solution in the technical solution of the present application, the server is also used to input the time-series thermal imaging images into an image segmentation model to obtain time-series images of each cable;

[0052] and, acquiring a time-series image of the first cable from the time-series images of the cables based on a target tracking algorithm;

[0053] and, based on the time-series images of the first cable, obtaining a pixel average value of each image;

[0054] And, based on the pixel average values ​​of the respective images, the time-series temperature data of the first cable is acquired; the time-series temperature data includes the time-series temperature sequence of the first cable.

[0055] As a specific solution in the technical solution of the present application, the server is also used to obtain a time series ambient temperature value based on the inspection data;

[0056] And, based on the time-series ambient temperature values, a time-series ambient temperature sequence of the first cable is obtained; the data in the time-series ambient temperature sequence corresponds one-to-one with the data in the time-series temperature sequence, and the time sequence of the corresponding data is the same;

[0057] And, based on the time-series ambient temperature sequence and the time-series temperature sequence, abnormal temperature change data of the first cable is acquired.

[0058] As a specific solution in the technical solution of the present application, the server is also used to obtain the time sequence current value of each cable based on the inspection data;

[0059] And, based on the time-series current value, a time-series current sequence of the first cable is obtained; the data in the time-series current sequence corresponds one-to-one with the data in the time-series temperature sequence, and the time sequence of the corresponding data is the same;

[0060] And, based on the time-series current sequence and the time-series ambient temperature sequence, acquiring temperature influence factor data; the temperature influence factor data is at least used to characterize the temperature change trend of the first cable in adjacent time sequences;

[0061] And, based on the temperature influencing factor data, abnormal temperature change data of the first cable is obtained.

[0062] As a specific solution in the technical solution of the present application, the server obtains the temperature influence factor data based on the time series current sequence and the time series ambient temperature sequence using the following calculation formula:

[0063]

[0064] in, represents the temperature influence factor of the i-th time series; is the ambient temperature value of the i-th time series, i is greater than or equal to 2; is the ambient temperature value of the i-1th time series; is the current value of the first cable in the i-th time sequence; is the current value of the first cable in the i-1th time sequence; R represents the resistance of the first cable; Indicates the time length between adjacent time series; represents the total mass of the first cable; represents the specific heat capacity of the first cable; A represents the cross-sectional area of ​​the first cable.

[0065] As a specific solution in the technical solution of the present application, the server obtains the calculation formula of the abnormal temperature change data of the first cable based on the temperature influence factor data as follows:

[0066]

[0067] in, represents the abnormal temperature change data of the i-th time series; represents the temperature value of the first cable at the i-th time sequence; represents the temperature value of the first cable at the i-1th time sequence; Represents the temperature impact factor of the i-th time series.

[0068] As a specific solution in the technical solution of the present application, the server is also used to obtain time series vibration data based on the inspection data;

[0069] And, based on the time-series vibration data, a time-series vibration data sequence of the rail robot is obtained; the data in the time-series vibration data sequence corresponds one-to-one with the data in the time-series temperature sequence, and the time sequence of the corresponding data is the same;

[0070] And, based on the time series vibration data sequence, obtaining temperature correction factor data; the temperature correction factor data is at least used to characterize the degree of influence of the time series vibration data on the time series temperature; the temperature correction factor data includes the Pearson correlation coefficient of the time series vibration data sequence and the time series temperature sequence;

[0071] And, based on the temperature correction factor data, correcting the time series temperature data of the first cable.

[0072] As a specific solution in the technical solution of the present application, the server is further used to, if the temperature abnormal change data is greater than a first preset value, obtain an abnormal image based on the inspection data; the abnormal image is a time sequence image including the first cable in each time sequence image and corresponding to the time sequence of the temperature abnormal change data;

[0073] And, based on the abnormal image, a plurality of high temperature areas are obtained; the high temperature areas are areas in the abnormal image whose temperature values ​​are higher than the first cable temperature;

[0074] and, based on the plurality of high temperature regions, obtaining a plurality of first temperature values;

[0075] and, based on the first cable, obtaining a second temperature value;

[0076] And, based on the second temperature value and the plurality of first temperature values, a fault probability is obtained; the fault probability is at least used to characterize the possibility of the first cable failing;

[0077] And, if the failure probability is greater than a second preset value, the inspection speed of the rail robot is adjusted based on the abnormal temperature change data.

[0078] As a specific solution in the technical solution of the present application, the server obtains the calculation formula of the failure probability based on the second temperature value and multiple first temperature values ​​as follows:

[0079]

[0080]

[0081] Wherein, U represents the probability of failure of the first cable; K represents the average value of the abnormal temperature change data of the first cable corresponding to n time series; y represents the number of time series images; Indicates the maximum number of high temperature areas in n time series images; Indicates the degree of influence of the mth high temperature area on the temperature of the first cable in the nth timing diagram; represents the temperature of the first cable in the nth time series image; Indicates the temperature value of the mth high temperature area in the nth time series image; represents the distance between the mth high temperature area and the first cable in the nth time series image; Represents a linear normalization function, which is used to normalize data to the interval (0, 1).

[0082] Compared with the prior art, the beneficial effects of this application are:

[0083] This application determines the abnormal degree of temperature change of the cable by analyzing the inspection data collected by the track robot, which is used for subsequent speed control of the track robot. On the premise of being able to timely monitor the abnormality of the cable, it is also possible to accurately monitor whether the cable has actually been abnormal. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Figure 1 A schematic diagram of a flow chart of an inspection control method for an intelligent rail robot proposed in an embodiment of the present application;

[0085] Figure 2 A schematic diagram of the structure of an inspection control system for an intelligent rail robot proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0086] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0087] The terms "first", "second", etc. in the specification of the embodiment of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence, such as the first temperature value and the second temperature value proposed below, which belong to different temperature values. It should be understood that the temperature values ​​used in this way can be interchanged in appropriate circumstances, so that the embodiments described here can be implemented in an order other than the content illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device including a series of steps or modules need not be limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The division of the modules that appear in the embodiment of the present application is only a logical division. There may be other division methods when implemented in practical applications, such as multiple modules can be combined into or integrated in another system, or some features can be ignored, or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, and the indirect coupling or communication connection between modules can be electrical or other similar forms, which are not limited in the embodiment of the present application. Furthermore, the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in multiple circuit modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiment of the present application.

[0088] In order to solve the technical problem that the prior art proposed by the background technology cannot simultaneously realize timely and accurate monitoring of cable anomalies by patrolling at a fixed speed, this application proposes an embodiment of a patrol control method for an intelligent rail robot, wherein the rail robot includes a thermal imager, a temperature sensor, a vibration sensor and a locator, and the rail robot is used to patrol each cable in a cable tunnel. It should be clear that the rail robot, thermal imager, temperature sensor, vibration sensor and locator are all mature technologies and will not be described in detail here.

[0089] like Figure 1 As shown, in an embodiment of the present application, the inspection control method for the intelligent rail robot includes steps S100 to S400.

[0090] Step S100: Acquire the inspection data of the rail robot.

[0091] It should be clear that in an embodiment of the present application, the inspection data includes the time-series thermal imaging images taken by the thermal imager, the time-series ambient temperature values ​​obtained by the temperature sensor, the time-series vibration data obtained by the vibration sensor, the time-series position obtained by the locator, and the time-series current values ​​of each cable.

[0092] It should be noted that, in this embodiment, a current transformer can be installed on each cable in the cable tunnel to collect current data in real time. Since the current transformer is a mature technology, it will not be described in detail here.

[0093] In an embodiment of the present application, the time-series thermal imaging image can be a time-series image captured from a thermal imaging video, or a time-series image taken by a thermal imager. In order to clearly obtain the temperature of each cable based on the time-series image, in an embodiment of the present application, the track robot can use a thermal imager to shoot each cable from above to ensure that there is no overlap between the cables in the video, and one round trip in the cable tunnel along a fixed track route is considered a patrol process. When the patrol process detects that the temperature of a cable exceeds the set temperature upper limit, an alarm maintenance is performed.

[0094] Step S200: Based on the inspection data, obtaining time-series temperature data of the first cable.

[0095] It should be clear that in each inspection process, the temperature of each cable needs to be determined to determine whether the temperature of the cable is abnormal. That is, in this embodiment, the first cable is any one of the cables.

[0096] It should be clear that in the embodiments of the present application, any suitable method can be used to obtain the time-series temperature data of the first cable based on the inspection data. For example, in one embodiment of the present application, step S200: obtaining the time-series temperature data of the first cable based on the inspection data includes steps S210 to S240.

[0097] Step S210: input the time-series thermal imaging images into an image segmentation model to obtain time-series images of each cable.

[0098] It should be clear that the time-series thermal imaging image includes a cable area and a background area. In an embodiment of the present application, the cable area is segmented out by an image segmentation model, and then the time-series images of each cable are obtained. In this embodiment, the image segmentation model can be any model in the prior art that can segment an image. For example, the image segmentation model can be a MaskR-CNN neural network model. Before using the MaskR-CNN neural network model to segment the time-series thermal imaging image, the time-series MaskR-CNN neural network model needs to be trained. Since the pixels that need to be segmented in the time-series thermal imaging image are divided into 2 categories (i.e., the cable area and the background area), the label annotation process corresponding to the training set can be a single-channel semantic label, and the corresponding position pixel point belonging to the background area is labeled as 0, and the label belonging to the cable area is 1. The task of the MaskR-CNN neural network model is classification, so the loss function can be used as a cross-entropy loss function. Since this training process is a mature technology, it will not be described in detail here.

[0099] Step S220: acquiring a time-series image of the first cable from the time-series images of the cables based on a target tracking algorithm.

[0100] It should be clear that since each time-series thermal imaging image only contains a portion of a certain cable (for example, the first cable), in order to obtain the temperature value of each location of the entire cable, in this embodiment, a target tracking algorithm can be used to obtain the cable connectivity domain of the first cable in each frame of the time-series image, and then obtain the pixel value of each location of the entire first cable, and then obtain the temperature value of each location of the first cable based on the pixel value of each location. Since the target tracking algorithm is a mature technology, it will not be described in detail here.

[0101] Step S230: Based on the time-series images of the first cable, obtain the pixel average value of each image.

[0102] In the embodiment of the present application, the temperature value of the corresponding position can be obtained by using the pixel value of each pixel point on the time-series image of the first cable. It is easy to understand that if the temperature of a certain position point of the first cable is higher, the color of the corresponding position in the time-series image is lighter, that is, the gray value of the position in the time-series image is lower; if the temperature of a certain position point of the first cable is lower, the gray value of the corresponding position in the time-series image is higher.

[0103] In an embodiment of the present application, in order to accurately obtain the temperature of a certain area of ​​the first cable, the pixels in the area may be averaged. For example, in this embodiment, an 11×11 sliding window may be set in the time-series image of the first cable, and the average grayscale value of all pixels in the sliding window centered at the i-th pixel is calculated as the pixel value of the i-th pixel.

[0104] Step S240: based on the pixel average values ​​of the images, obtaining the time-series temperature data of the first cable, wherein the time-series temperature data includes the time-series temperature sequence of the first cable.

[0105] It should be understood that, in the embodiment of the present application, the time series temperature data of the first cable may be the temperature data of different positions on the first cable within the same inspection cycle, or may be the temperature data obtained at the same position on the first cable in different inspection cycles.

[0106] As can be seen from the foregoing, obtaining the corresponding temperature value based on the pixel average value is a mature technology and will not be elaborated here.

[0107] In an embodiment of the present application, a corresponding alarm can be issued based on whether the temperature at each position on the first cable is abnormal. However, it should be clear that during the inspection of the track robot, the track robot will vibrate. The vibration will affect the stability of the thermal imager and the quality of the acquired image. In other words, the greater the vibration, the worse the imaging quality of the thermal imager, that is, the less reliable the image information. In an embodiment of the present application, the acquired time series temperature sequence of the first cable can be corrected based on the vibration data of the track robot to make the time series temperature sequence of the first cable more accurate.

[0108] In one embodiment of the present application, after step S240, based on the pixel average value of each image, acquiring the time series temperature data of the first cable, the method further includes steps S250 to S280.

[0109] Step S250: Based on the inspection data, obtaining time series vibration data.

[0110] It should be clear that obtaining some data from a certain data is a mature technology and will not be elaborated here.

[0111] Step S260: Based on the time-series vibration data, obtain the time-series vibration data sequence of the track robot.

[0112] In this embodiment, the data in the time series vibration data sequence corresponds to the data in the time series temperature sequence, and the time series of the corresponding data is the same. In this embodiment, the vibration data can be the vibration amplitude, or the vibration frequency, or both the vibration amplitude and the vibration frequency.

[0113] Step S270: Based on the time series vibration data sequence, obtain temperature correction factor data.

[0114] In an embodiment of the present application, the temperature correction factor data is at least used to characterize the degree of influence of the time series vibration data on the time series temperature. The temperature correction factor data includes the Pearson correlation coefficient of the time series vibration data sequence and the time series temperature sequence. The Pearson correlation coefficient is a mature technology, which is a statistic used to measure the degree of linear correlation between two variables X (that is, the time series vibration data sequence in the present application) and Y (that is, the time series temperature sequence in the present application). The closer its value is to 1, the two variables are positively correlated; the closer it is to -1, the two variables are negatively correlated; the closer it is to 0, the two variables are unrelated. When the vibration change value at a certain moment is smaller, it means that the imaging quality of the thermal imager is better, the image information is more reliable, that is, the cable temperature value is more reliable, so the temperature correction factor data can be obtained based on the time series vibration data sequence with the help of the Pearson correlation coefficient.

[0115] Step S280: Correcting the time series temperature data of the first cable based on the temperature correction factor data.

[0116] It should be clear that in the embodiments of the present application, the time series temperature data of the first cable can be corrected based on the temperature correction factor data in any suitable manner. For example, in one embodiment of the present application, step S280: based on the temperature correction factor data, the calculation formula for correcting the time series temperature data of the first cable is as follows:

[0117]

[0118] in, represents the corrected temperature value of the first cable at the i-th time sequence; represents the temperature value of the first cable before correction at the i-th time sequence; A Pearson correlation coefficient representing a time series vibration data sequence and the time series temperature sequence; Represents the data value of the vibration data at the i-th time series; Represents the average value of each data value in the time series vibration data sequence.

[0119] Step S300: Based on the time-series temperature data, obtain abnormal temperature change data of the first cable.

[0120] It should be clear that in the embodiment of the present application, the abnormal temperature change data is at least used to characterize the possibility of abnormal temperature change of the first cable. It should be noted that in this embodiment, abnormal change means that the temperature change of the first cable generally does not exceed the temperature threshold. For example, if the temperature of the first cable generally does not suddenly rise by 20°C during normal use, the temperature threshold can be set to 20°C. If the track robot monitors that the temperature of a certain area of ​​the first cable rises by more than 20°C between adjacent time sequences, it can be considered that the area of ​​the first cable is likely to have undergone abnormal changes, that is, the greater the possibility of abnormal changes.

[0121] In an embodiment of the present application, the temperature abnormal change data of the first cable can be obtained based on the time series temperature data in any suitable manner. For example, in an embodiment of the present application, step S300, based on the time series temperature data, obtains the temperature abnormal change data of the first cable, including steps S310 to S330.

[0122] It should be noted that the temperature of the first cable is closely related to the ambient temperature. If the ambient temperature is higher, the temperature of the first cable may also be higher. For example, in the hot summer, due to the high ambient temperature, even if the temperature of the first cable exceeds 40°C, it does not mean that the temperature of the first cable has changed abnormally; in the cold winter, due to the low ambient temperature, if the temperature of the first cable exceeds 40°C, it indicates that the temperature of the first cable is likely to have changed abnormally. That is to say, in the embodiment of the present application, the temperature abnormal change data of the first cable can be obtained based on the ambient temperature of the first cable and the temperature of the first cable itself.

[0123] Step S310: Based on the inspection data, obtain the time series ambient temperature value.

[0124] It should be clear that obtaining some data from a certain data is a mature technology and will not be elaborated here.

[0125] Step S320: Based on the time-series ambient temperature values, obtain the time-series ambient temperature sequence of the first cable.

[0126] The data in the time-series ambient temperature sequence corresponds one-to-one to the data in the time-series temperature sequence, and the time sequence of the corresponding data is the same. It should be clear that in the same inspection cycle, the ambient temperature at various locations on the first cable is basically the same. In other words, the temperature at various locations on the first cable is also basically the same. If the temperature in a certain area on the first cable is greatly abnormal, it means that the temperature in this area of ​​the first cable may have changed abnormally. In different inspection cycles, the ambient temperature at the same position on the first cable may be different, but the temperature change amplitude at the same position on the first cable is basically the same, that is, if the ambient temperature is low, the temperature of the first cable should also be low; if the ambient temperature is high, the temperature of the first cable should also be high. If the ambient temperature is low, but the corresponding temperature of the first cable is high, then the temperature of the first cable is likely to have changed abnormally.

[0127] Step S330: Based on the time-series ambient temperature sequence and the time-series temperature sequence, acquiring abnormal temperature change data of the first cable.

[0128] It should be understood that, in the embodiment of the present application, the abnormal temperature change data of the first cable may be determined based on the difference in ambient temperature between adjacent time series and the temperature difference of the first cable.

[0129] It should be noted that the temperature of the first cable itself is positively correlated with the ambient temperature and the current in the first cable. That is to say, if the current in the first cable is larger, the corresponding temperature of the first cable is relatively higher; if the current in the first cable is smaller, the corresponding temperature of the first cable is relatively lower.

[0130] Step S330, based on the time-series ambient temperature sequence and the time-series temperature sequence, obtaining abnormal temperature change data of the first cable, including steps S331 to S334.

[0131] Step S331: Based on the inspection data, the time-series current value of each cable is obtained.

[0132] It should be clear that obtaining some data from a certain data is a mature technology and will not be elaborated here.

[0133] Step S332: Based on the time-series current value, obtain the time-series current sequence of the first cable.

[0134] It should be clear that the data in the timing current sequence corresponds one-to-one with the data in the timing temperature sequence, and the timing of the corresponding data is the same.

[0135] Step S333: acquiring temperature influence factor data based on the time-series current sequence and the time-series ambient temperature sequence.

[0136] It is easy to understand that in the embodiment of the present application, the temperature influence factor data is at least used to characterize the temperature change trend of the first cable in the adjacent time sequence. It is easy to understand that if the temperature change of the first cable exceeds the temperature threshold, and the temperature change trend of the first cable in the adjacent time sequence is small (for example, the change trend is negative, that is, the temperature of the current time sequence of the first cable should be lower than the temperature of the previous time sequence), but the actual temperature of the current time sequence of the first cable is higher than the temperature of the previous time sequence, it is likely that the current temperature of the first cable is abnormal.

[0137] In an embodiment of the present application, the temperature impact factor data is obtained based on the timing current sequence and the timing ambient temperature sequence in any suitable manner. For example, in one embodiment of the present application, in step S333, the calculation formula for obtaining the temperature impact factor data based on the timing current sequence and the timing ambient temperature sequence is as follows:

[0138]

[0139] in, represents the temperature influence factor of the i-th time series; is the ambient temperature value of the i-th time series, i is greater than or equal to 2; is the ambient temperature value of the i-1th time series; is the current value of the first cable in the i-th time sequence; is the current value of the first cable in the i-1th time sequence; R represents the resistance of the first cable; Indicates the time length between adjacent time series; represents the total mass of the first cable; represents the specific heat capacity of the first cable; A represents the cross-sectional area of ​​the first cable.

[0140] It is easy to understand that in the embodiment of the present application, if the temperature influence factor is positive, the temperature of the first cable will increase with a high probability in the next sequence, and The larger the value of , the greater the temperature rise of the first cable in the next sequence; if the temperature influence factor is negative, the temperature of the first cable in the next sequence is likely to drop, and The larger the absolute value of , the greater the temperature drop of the first cable in the next sequence.

[0141] Step S334: Based on the temperature influencing factor data, obtaining abnormal temperature change data of the first cable.

[0142] As can be seen from the foregoing, it is possible to determine whether the temperature of the first cable has undergone an abnormal change based on the temperature influence factor data and the actual temperature change of the first cable. In one embodiment of the present application, step S334, based on the temperature influence factor data, obtains the calculation formula for the abnormal temperature change data of the first cable as follows:

[0143]

[0144] in, represents the abnormal temperature change data of the i-th time series; represents the temperature value of the first cable at the i-th time sequence; represents the temperature value of the first cable at the i-1th time sequence; Represents the temperature impact factor of the i-th time series.

[0145] It should be clear that if The closer it is to 1, the more normal the temperature change of the first cable is; otherwise, the more abnormal the temperature change of the first cable is.

[0146] It should be noted that in an embodiment of the present application, if there are other heat sources near the first cable (for example, lighting inside the inspection tunnel, or other cables with heating failures next to the first cable, etc.), the system may also mistakenly believe that the first cable has also failed. In order to further determine whether the temperature of the first cable has changed abnormally, that is, to determine whether the first cable has failed. In one embodiment of the present application, step S300, after obtaining the temperature abnormal change data of the first cable based on the time series temperature data, the method also includes steps S340 to S390.

[0147] Step S340: If the abnormal temperature change data is greater than a first preset value, an abnormal image is acquired based on the inspection data.

[0148] In this embodiment, the abnormal image is a time sequence image including the first cable in each time sequence image and corresponding to the time sequence of the abnormal degree change data. In an embodiment of the present application, the first preset value can be set according to experience and demand, for example, the first preset value is set to 2 or 3.

[0149] Step S350: Based on the abnormal image, a plurality of high temperature areas are acquired.

[0150] In this embodiment, the high temperature area is an area in the abnormal image whose temperature value is higher than the temperature of the first cable. It is easy to understand that there may be multiple heat sources around the first cable, that is, each heat source corresponds to a high temperature area. If there is no high temperature area with a temperature higher than the first cable in the abnormal image, the number of high temperature areas is 0.

[0151] Step S360: Based on the multiple high temperature areas, obtain multiple first temperature values.

[0152] It should be clear that in the embodiment of the present application, the first temperature value corresponds to the high temperature region one by one. The first temperature value can be the highest value of the temperature of each point in the corresponding high temperature region, or can be the average value of the temperature of each point in the corresponding high temperature region.

[0153] Step S370: Based on the first cable, obtain a second temperature value.

[0154] It should be clear that in the embodiment of the present application, the second temperature value may be the temperature value of the first cable before correction as described above. Of course, in order to calculate the accuracy of the result, in the embodiment of the present application, the second temperature value may also be the temperature value of the first cable after correction as described above.

[0155] Step S380: Obtaining a failure probability based on the second temperature value and a plurality of first temperature values.

[0156] In this embodiment, the failure probability is at least used to characterize the possibility of the first cable failing. It is easy to understand that if the difference between the first temperature value and the second temperature value is larger and the distance between the high temperature area and the first cable is smaller, the possibility of the first cable failing is smaller; otherwise, the possibility of the first cable failing is greater.

[0157] In an embodiment of the present application, in step S380, based on the second temperature value and the plurality of first temperature values, a calculation formula for obtaining the failure probability is as follows:

[0158]

[0159]

[0160] Wherein, U represents the probability of failure of the first cable; K represents the average value of the abnormal temperature change data of the first cable corresponding to n time series; y represents the number of time series images; Indicates the maximum number of high temperature areas in n time series images; Indicates the degree of influence of the mth high temperature area on the temperature of the first cable in the nth timing diagram; represents the temperature of the first cable in the nth time series image; Indicates the temperature value of the mth high temperature area in the nth time series image; represents the distance between the mth high temperature area and the first cable in the nth time series image; Represents a linear normalization function, which is used to normalize data to the interval (0, 1).

[0161] It should be understood that in the embodiments of the present application, if the temperature of the high temperature area is The temperature of the first cable The greater the difference, the greater the degree of influence of the high temperature area on the temperature of the first cable. The smaller the temperature, the greater the impact of the high temperature area on the first cable temperature. The larger the distance between the high temperature area and the first cable The larger the value, the greater the impact of the high temperature area on the temperature of the first cable. The smaller the temperature, the greater the impact of the high temperature area on the first cable temperature. If the high temperature area affects the temperature of the first cable The smaller U is, the smaller U is. It is easy to understand that if U is smaller, the probability of the first cable failing is smaller; if U is larger, the probability of the first cable failing is greater.

[0162] Step S390: If the failure probability is greater than a second preset value, the inspection speed of the rail robot is adjusted based on the abnormal temperature change data.

[0163] In the embodiment of the present application, the second preset value can be set based on demand, without any restriction. For example, the second preset value can be 0.7 or 0.8, etc. It is easy to understand that if the probability of failure is greater than the second preset value, it indicates that the temperature of the first cable has a high probability of abnormal change, that is, the first cable has a fault, so when approaching the first cable or the fault point of the first cable, the inspection speed of the track robot can be reduced to accurately determine whether the temperature is abnormal there.

[0164] Step S400: adjusting the inspection speed of the track robot based on the abnormal temperature change data.

[0165] In an embodiment of the present application, the inspection speed of the track robot can be adjusted based on the abnormal temperature change data in any suitable manner. For example, in an application scenario where the cable tunnel is long or the inspection speed is slow (that is, the inspection cycle of the track robot is long, and there is enough time to adjust the inspection speed of the track robot in real time), the time-series temperature data of the first cable can be the temperature values ​​of different positions of the first cable during the same inspection process. That is to say, during the same inspection process, the temperature value of the position photographed first in the first cable is in the first sequence, and the temperature value of the position photographed later in the first cable is in the latter sequence. That is to say, in this embodiment, the inspection speed of the track robot can be directly adjusted based on the abnormal temperature change data corresponding to the i-th sequence. In an application scenario where the cable tunnel is short or the inspection speed is fast (that is, the inspection cycle of the track robot is short, and there is not enough time to adjust the inspection speed of the track robot in real time), the time-series temperature data of the first cable can be the temperature value of the same position of the first cable during different inspections. In this embodiment, the abnormal temperature change data of the first cable in the i-th sequence is used to calculate the temperature of the first cable at the same position of the first cable. , as the speed adjustment coefficient of the track robot in the i+1th time sequence.

[0166] In this embodiment, according to the speed adjustment coefficients at all times during the i-th inspection (i.e., the i-th time sequence), the APCP segmentation algorithm (adaptive segmentation constant approximation, which is a mature technology and will not be described in detail) is used to obtain several update time periods and the approximate value of the speed adjustment coefficient for each update time period. The approximate value of the speed adjustment coefficient is normalized to between -1 and 1 using a normalization function. The position coordinates of the track robot at each moment in each update time period are used to form the movement trajectory of the track robot corresponding to each update time period.

[0167] In a specific embodiment, the initial speed is set to 0.5 m / s, and the speed is adjusted to Then during the i+1th inspection (i.e. the i+1th time sequence), the moving speed of the track robot on the bth moving track is The calculation formula is:

[0168]

[0169] in, It is the normalized value of the approximate value of the speed adjustment coefficient of the update time period corresponding to the b-th moving track of the rail robot. The larger the value, the greater the possibility that the cable within the moving track is faulty, and the more careful inspection is needed, that is, the speed needs to be slowed down and more data needs to be collected. Similarly, the moving speed of the rail robot on each moving track during the i+1th inspection is obtained. The data collected during each inspection process is used to determine the moving speed of the rail robot during the next inspection process, and the inspection speed control of the intelligent rail robot is completed.

[0170] It should be clear that the inspection control method embodiment for intelligent rail robots proposed in this application determines the abnormal degree of temperature change of the cable by analyzing the inspection data collected by the rail robot, which is used for subsequent speed control of the rail robot. Under the premise of being able to monitor cable abnormalities in a timely manner, cable abnormalities can also be accurately monitored.

[0171] After introducing the embodiment of the inspection control method for the intelligent rail robot proposed in the present application, the inspection control system for the intelligent rail robot proposed in the present application is introduced below. The rail robot includes: a thermal imager, a temperature sensor, a vibration sensor and a positioner; the rail robot is used to inspect each cable in the cable tunnel; Figure 2 As shown, the inspection control system for the intelligent rail robot includes:

[0172] The reader 11 is used to obtain the inspection data of the rail robot; the inspection data includes: the time-series thermal imaging images taken by the thermal imager, the time-series ambient temperature values ​​obtained by the temperature sensor, the time-series vibration data obtained by the vibration sensor, the time-series position obtained by the locator, and the time-series current values ​​of each cable;

[0173] The server 12 is used to obtain time-series temperature data of a first cable based on the inspection data; the first cable is any one of the cables;

[0174] And, based on the time series temperature data, acquiring abnormal temperature change data of the first cable; the abnormal temperature change data is at least used to characterize the possibility of abnormal temperature change of the first cable;

[0175] The controller 13 is used to adjust the inspection speed of the rail robot based on the abnormal temperature change data.

[0176] As a specific embodiment of the present application, the server 12 is further used to input the time-series thermal imaging images into an image segmentation model to obtain time-series images of each cable;

[0177] and, acquiring a time-series image of the first cable from the time-series images of the cables based on a target tracking algorithm;

[0178] and, based on the time-series images of the first cable, obtaining a pixel average value of each image;

[0179] And, based on the pixel average values ​​of the respective images, the time-series temperature data of the first cable is acquired; the time-series temperature data includes the time-series temperature sequence of the first cable.

[0180] As a specific embodiment of the present application, the server 12 is further used to obtain a time series ambient temperature value based on the inspection data;

[0181] And, based on the time-series ambient temperature values, a time-series ambient temperature sequence of the first cable is obtained; the data in the time-series ambient temperature sequence corresponds one-to-one with the data in the time-series temperature sequence, and the time sequence of the corresponding data is the same;

[0182] And, based on the time-series ambient temperature sequence and the time-series temperature sequence, abnormal temperature change data of the first cable is acquired.

[0183] As a specific embodiment of the present application, the server 12 is further used to obtain the time sequence current value of each cable based on the inspection data;

[0184] And, based on the time-series current value, a time-series current sequence of the first cable is obtained; the data in the time-series current sequence corresponds one-to-one with the data in the time-series temperature sequence, and the time sequence of the corresponding data is the same;

[0185] And, based on the time-series current sequence and the time-series ambient temperature sequence, acquiring temperature influence factor data; the temperature influence factor data is at least used to characterize the temperature change trend of the first cable in adjacent time sequences;

[0186] And, based on the temperature influencing factor data, abnormal temperature change data of the first cable is obtained.

[0187] As a specific embodiment of the present application, the server 12 obtains the temperature influence factor data based on the time series current sequence and the time series ambient temperature sequence using the following calculation formula:

[0188]

[0189] in, represents the temperature influence factor of the i-th time series; is the ambient temperature value of the i-th time series, i is greater than or equal to 2; is the ambient temperature value of the i-1th time series; is the current value of the first cable in the i-th time sequence; is the current value of the first cable in the i-1th time sequence; R represents the resistance of the first cable; Indicates the time length between adjacent time series; represents the total mass of the first cable; represents the specific heat capacity of the first cable; A represents the cross-sectional area of ​​the first cable.

[0190] As a specific embodiment of the present application, the server 12 obtains the temperature abnormal change data of the first cable based on the temperature influence factor data by the following calculation formula:

[0191]

[0192] in, represents the abnormal temperature change data of the i-th time series; represents the temperature value of the first cable at the i-th time sequence; represents the temperature value of the first cable at the i-1th time sequence; Represents the temperature impact factor of the i-th time series.

[0193] As a specific embodiment of the present application, the server 12 is further used to obtain time series vibration data based on the inspection data;

[0194] And, based on the time-series vibration data, a time-series vibration data sequence of the rail robot is obtained; the data in the time-series vibration data sequence corresponds one-to-one with the data in the time-series temperature sequence, and the time sequence of the corresponding data is the same;

[0195] And, based on the time series vibration data sequence, obtaining temperature correction factor data; the temperature correction factor data is at least used to characterize the degree of influence of the time series vibration data on the time series temperature; the temperature correction factor data includes the Pearson correlation coefficient of the time series vibration data sequence and the time series temperature sequence;

[0196] And, based on the temperature correction factor data, correcting the time series temperature data of the first cable.

[0197] As a specific embodiment of the present application, the server 12 is further used to obtain an abnormal image based on the inspection data if the abnormal temperature change data is greater than a first preset value; the abnormal image is a time sequence image including the first cable in each time sequence image and corresponding to the time sequence of the abnormal temperature change data;

[0198] And, based on the abnormal image, a plurality of high temperature areas are obtained; the high temperature areas are areas in the abnormal image whose temperature values ​​are higher than the first cable temperature;

[0199] and, based on the plurality of high temperature regions, obtaining a plurality of first temperature values;

[0200] and, based on the first cable, obtaining a second temperature value;

[0201] And, based on the second temperature value and the plurality of first temperature values, a fault probability is obtained; the fault probability is at least used to characterize the possibility of the first cable failing;

[0202] And, if the failure probability is greater than a second preset value, the inspection speed of the rail robot is adjusted based on the abnormal temperature change data.

[0203] As a specific embodiment of the present application, the server 12 obtains the following calculation formula for the failure probability based on the second temperature value and multiple first temperature values:

[0204]

[0205]

[0206] Wherein, U represents the probability of failure of the first cable; K represents the average value of the abnormal temperature change data of the first cable corresponding to n time series; y represents the number of time series images; Indicates the maximum number of high temperature areas in n time series images; Indicates the degree of influence of the mth high temperature area on the temperature of the first cable in the nth timing diagram; represents the temperature of the first cable in the nth time series image; Indicates the temperature value of the mth high temperature area in the nth time series image; represents the distance between the mth high temperature area and the first cable in the nth time series image; Represents a linear normalization function, which is used to normalize data to the interval (0, 1).

[0207] It should be clear that the inspection control system embodiment for intelligent rail robots proposed in this application determines the abnormal degree of temperature change of the cable by analyzing the inspection data collected by the rail robot, which is used for subsequent speed control of the rail robot. Under the premise of being able to monitor cable abnormalities in a timely manner, cable abnormalities can also be accurately monitored.

[0208] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0209] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the methods, devices and equipment described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0210] In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0211] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0212] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0213] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0214] The computer program product includes one or more computer instructions. When the computer program is loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disk), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0215] Although the embodiments of the present application have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles of the present application.

Claims

1. An inspection control method for an intelligent rail robot, the rail robot comprising: Thermal imagers, temperature sensors, vibration sensors and locators; The track robot is used to inspect each cable in the cable tunnel; it is characterized in that the inspection control method for the intelligent track robot includes: Obtaining inspection data of the rail robot; the inspection data includes: time-series thermal imaging images taken by the thermal imager, time-series ambient temperature values ​​obtained by the temperature sensor, time-series vibration data obtained by the vibration sensor, time-series positions obtained by the positioner, and time-series current values ​​of each cable; Based on the inspection data, obtaining time-series temperature data of a first cable; the first cable is any one of the cables; Based on the time-series temperature data, acquiring abnormal temperature change data of the first cable; the abnormal temperature change data is at least used to characterize the possibility of abnormal temperature change of the first cable; Adjusting the inspection speed of the track robot based on the abnormal temperature change data; The step of acquiring the time-series temperature data of the first cable based on the inspection data includes: Inputting the time-series thermal imaging images into an image segmentation model to obtain time-series images of each cable; Acquire a time-series image of the first cable from the time-series images of the cables based on a target tracking algorithm; Based on the time-series images of the first cable, obtaining a pixel average value of each image; Based on the pixel average values ​​of the respective images, acquiring time-series temperature data of the first cable; the time-series temperature data comprises a time-series temperature sequence of the first cable; The step of acquiring abnormal temperature change data of the first cable based on the time series temperature data includes: Based on the inspection data, obtaining a time series ambient temperature value; Based on the time-series ambient temperature values, a time-series ambient temperature sequence of the first cable is obtained; the data in the time-series ambient temperature sequence corresponds one-to-one with the data in the time-series temperature sequence, and the time sequence of the corresponding data is the same; Based on the time-series ambient temperature sequence and the time-series temperature sequence, acquiring abnormal temperature change data of the first cable; The acquiring the abnormal temperature change data of the first cable based on the time-series ambient temperature sequence and the time-series temperature sequence includes: Based on the inspection data, obtaining the time-series current value of each cable; Based on the time-series current value, a time-series current sequence of the first cable is obtained; the data in the time-series current sequence corresponds one-to-one with the data in the time-series temperature sequence, and the time sequence of the corresponding data is the same; Based on the time-series current sequence and the time-series ambient temperature sequence, temperature influence factor data is acquired; the temperature influence factor data is at least used to characterize the temperature change trend of the first cable in adjacent time sequences; Based on the temperature influencing factor data, acquiring abnormal temperature change data of the first cable; The calculation formula for obtaining the temperature influence factor data based on the timing current sequence and the timing ambient temperature sequence is as follows: in, represents the temperature influence factor of the i-th time series; is the ambient temperature value of the i-th time series, i is greater than or equal to 2; is the ambient temperature value of the i-1th time series; is the current value of the first cable in the i-th time sequence; is the current value of the first cable in the i-1th time sequence; R represents the resistance of the first cable; Indicates the time length between adjacent time series; represents the total mass of the first cable; represents the specific heat capacity of the first cable; A represents the cross-sectional area of ​​the first cable; Based on the temperature influence factor data, the calculation formula for obtaining the abnormal temperature change data of the first cable is as follows: in, represents the abnormal temperature change data of the i-th time series; represents the temperature value of the first cable at the i-th time sequence; represents the temperature value of the first cable at the i-1th time sequence; Represents the temperature impact factor of the i-th time series.

2. The inspection control method for an intelligent rail robot according to claim 1, characterized in that: After acquiring the time-series temperature data of the first cable based on the pixel average values ​​of the respective images, the method further includes: Based on the inspection data, acquiring time-series vibration data; Based on the time-series vibration data, a time-series vibration data sequence of the track robot is obtained; the data in the time-series vibration data sequence corresponds one-to-one with the data in the time-series temperature sequence, and the time sequence of the corresponding data is the same; Based on the time series vibration data sequence, temperature correction factor data is obtained; the temperature correction factor data is at least used to characterize the degree of influence of the time series vibration data on the time series temperature; the temperature correction factor data includes the Pearson correlation coefficient of the time series vibration data sequence and the time series temperature sequence; Based on the temperature correction factor data, the time series temperature data of the first cable is corrected.

3. The inspection control method for an intelligent rail robot according to claim 1, characterized in that: After obtaining the abnormal temperature change data of the first cable based on the time series temperature data, the method further includes: If the abnormal temperature change data is greater than a first preset value, an abnormal image is acquired based on the inspection data; the abnormal image is a time sequence image including the first cable in each time sequence image and corresponding to the time sequence of the abnormal temperature change data; Based on the abnormal image, a plurality of high temperature areas are acquired; the high temperature areas are areas in the abnormal image where the temperature value is higher than the first cable temperature; Based on the multiple high temperature areas, obtaining multiple first temperature values; Based on the first cable, obtaining a second temperature value; Based on the second temperature value and the plurality of first temperature values, a fault probability is obtained; the fault probability is used to characterize at least the possibility of the first cable failing; If the failure probability is greater than a second preset value, the inspection speed of the track robot is adjusted based on the abnormal temperature change data.

4. The inspection control method for an intelligent rail robot according to claim 3, characterized in that: Based on the second temperature value and the plurality of first temperature values, a calculation formula for obtaining the failure probability is as follows: Wherein, U represents the probability of failure of the first cable; K represents the average value of the abnormal temperature change data of the first cable corresponding to n time series; y represents the number of time series images; Indicates the maximum number of high temperature areas in n time series images; Indicates the degree of influence of the mth high temperature area on the temperature of the first cable in the nth timing diagram; represents the temperature of the first cable in the nth time series image; Indicates the temperature value of the mth high temperature area in the nth time series image; represents the distance between the mth high temperature area and the first cable in the nth time series image; Represents a linear normalization function, which is used to normalize data to the interval (0, 1).

5. Inspection control system for an intelligent rail robot, the rail robot comprising: Thermal imager, temperature sensor, vibration sensor and locator; the rail robot is used to inspect each cable in the cable tunnel; it is characterized in that the inspection control system for the intelligent rail robot is used to implement the inspection control method for the intelligent rail robot according to any one of claims 1 to 4, and the inspection control system for the intelligent rail robot includes: A reader, used to obtain inspection data of the rail robot; the inspection data includes: time-series thermal imaging images taken by the thermal imager, time-series ambient temperature values ​​obtained by the temperature sensor, time-series vibration data obtained by the vibration sensor, time-series positions obtained by the positioner, and time-series current values ​​of each cable; The server is configured to obtain time-series temperature data of a first cable based on the inspection data; the first cable is any one of the cables; And, based on the time series temperature data, acquiring abnormal temperature change data of the first cable; the abnormal temperature change data is at least used to characterize the possibility of abnormal temperature change of the first cable; The controller is used to adjust the inspection speed of the track robot based on the abnormal temperature change data.

Images