A method for detecting opening and closing of a train body inspection cover

Abstract

The invention relates to a method for detecting the opening and closing of a cover plate of a train body, and specifically to the field of vehicle management. A sound sensor is used to monitor sound data generated by the opening and closing of a cover plate, an infrared sensor is used to monitor the infrared radiation change information of a body surface caused by the opening and closing of the cover plate, and a data transfer system is established. The sound data and the infrared radiation change information are converted into corresponding electrical signals through a system data acquisition point, and the two electrical signals are filtered and conditioned by a median filter. Spectral analysis and time domain analysis are performed on the sound data and the infrared radiation electrical signal, the extracted features are marked, and the selection of the cover plate opening and closing state is judged through a random forest model, indicating that the train body cover plate is not completely closed and there is an opening and closing abnormality when the train body cover plate makes a sound when opening and closing and when the opening and closing temperature of the train body cover plate changes, and a graphical interface is displayed through a train control console for visualization of the real-time cover plate opening and closing state.

Description

Technical Field

[0001] The present invention relates to the field of vehicle management, and more specifically, to a method for detecting the opening and closing of a train body inspection cover. Background Art

[0002] The train body cover refers to the cover covering the train body. During the operation of the train, it is subject to the influence of multiple factors such as wind pressure, vibration, and temperature changes. The opening and closing status of the cover needs to be inspected and maintained regularly to ensure its safety and reliability.

[0003] At present, the opening and closing of the train body inspection cover is monitored manually, which is subjective and prone to missed detection and false detection, affecting the accuracy of the detection results. In addition, the manual inspection method cannot record and analyze data in real time, making it difficult to conduct data statistics and analysis, and unable to conduct effective data management and traceability. It is affected by the technical level and experience of personnel, and there are certain stability and reliability issues. Summary of the invention

[0004] The present invention aims at the technical problems existing in the prior art and provides a method for detecting the opening and closing of a train body inspection cover plate to solve the problems raised in the above-mentioned background technology.

[0005] The technical solution of the present invention to solve the above technical problem is as follows: A method for detecting the opening and closing of a train body inspection cover comprises the following steps:

[0006] S101: using a sound sensor to monitor the sound data generated by the opening and closing of the cover, using an infrared sensor to monitor the infrared radiation change information of the vehicle body surface due to the opening and closing of the cover, and establishing a data transfer system for transmitting the vehicle body cover opening and closing sound data and infrared radiation change information to the system data collection point;

[0007] S102: converting the sound data and infrared radiation change information into corresponding electrical signals through the system data collection point, filtering and conditioning the two electrical signals using median filtering, converting the electrical signals into digital signals using an analog-to-digital converter, and transmitting them to the data transfer system through wireless communication for temporary storage;

[0008] S103: performing spectrum analysis and time domain analysis on the sound data and the electrical signal of infrared radiation, extracting features for describing the process of the cover opening and closing state, annotating the extracted features and judging the selection of the cover opening and closing state through a random forest model;

[0009] S104: judging the cover state according to the feature extraction and random forest detection results, and indicating that the train body cover makes a sound when opening and closing, and that the train body cover is not completely closed and has an opening and closing abnormality when the opening and closing temperature changes;

[0010] S105: Displaying a graphical interface for real-time visualization of the cover opening and closing status through the train console, connecting to the train console database through a physical interface, and generating statistical icons and time trend lines to store the cover opening and closing status at different time points;

[0011] In S102, the system data acquisition point receives the opening and closing sound data and converts it into mechanical vibration using the vibrating diaphragm, and converts the mechanical vibration into an electrical signal corresponding to the sound data through the vibration sensor of the internal components of the sensor. The system data acquisition point receives the infrared radiation change information in combination with the infrared photodiode. When the infrared radiation is reflected on the infrared photodiode, it is converted into electron energy through the photoelectric effect, and the PN junction inside the infrared photodiode is used to generate an electrical signal according to the electron energy, and reflects the intensity of the infrared radiation, and the two electrical signals are filtered and conditioned using the median filter;

[0012] The median filter determines the filter window size as 2k+1, and applies the electrical signal parameters, determines the window range as [ik,i+k] for the ith electrical signal data point, sorts and obtains an ordered data series, selects the middle value of the ordered series as the median value of the ith electrical signal data point and assigns it to the ith electrical signal data point, and repeats the operation to perform median filtering on all electrical signal data points;

[0013] In the S103, by performing spectrum analysis on the electric signal corresponding to the sound data, the sound data is converted to the frequency domain and the frequency domain features are extracted, the bandwidth of the spectrum is obtained to describe the frequency distribution of the sound signal, and the frequency component is obtained to describe the uniformity of energy distribution. By performing continuous wavelet transform on the electric signal reflecting the intensity of infrared radiation, the electric signal is continuously transformed using different scale and translation parameters to generate a continuous scale image, providing transformation information of the electric signal at different frequencies and times, analyzing the waveform, amplitude and frequency characteristics of the electric signal in the time domain, extracting the time domain parameters of the electric signal, observing the periodicity and trend of the electric signal for time analysis and description of the electric signal, extracting features related to the opening and closing state of the cover, annotating the extracted features, determining the state of the cover corresponding to the electric signal, and inputting them into the random forest model as training data for training;

[0014] The specific steps of training the random forest model are: by constructing a tree structure, using internal nodes to represent features and leaf nodes to represent decision results to construct a decision tree, by randomly selecting features and samples to construct multiple decision trees and intersecting the results, judging the choice of the cover opening and closing state, and using the trained model to detect the opening and closing state of the train body cover.

[0015] In a preferred embodiment, in S101, a sound sensor is installed inside the train body cover to monitor the sound data generated by the opening and closing of the cover, and an infrared sensor is installed on the train body bogie to monitor the infrared radiation change information on the body surface due to the opening and closing of the cover. The wireless sensor network is integrated through wireless transmission using sound sensors and infrared sensor nodes, and the continuous collection time interval is preset to 30 minutes. A data transfer system is established to transmit the body cover opening and closing sound data and infrared radiation change information to the system data collection point.

[0016] Furthermore, the data transfer system selects a transfer node location that is close to the middle point between the sensor and the data collection point and meets the signal coverage and transmission stability requirements. The LoRaWAN wireless communication protocol is used to configure the transfer node to connect with the sensor. The transfer node is wirelessly connected to the sound sensor and the infrared sensor through a physical interface. The transfer node serves as an intermediate link in data transmission, forwarding the data received by the sound sensor and the infrared sensor in real time and sending it to the system data collection point.

[0017] In a preferred embodiment, in S104, the state of the cover is judged according to the feature extraction and random forest detection results. When the frequency domain of the sound data changes drastically and the random forest judges the state of the cover according to the sound generated by the opening and closing of the cover, it is used to indicate that the train body cover is not completely closed or there is an opening and closing abnormality when the opening and closing sound is made. The state of the cover is judged according to the feature extraction and random forest detection results. When the cover is opened, the temperature of the surface of the vehicle body changes. When the continuous scale image generated by the electrical signal reflecting the intensity of the infrared radiation changes drastically and the random forest judges the state of the cover according to the infrared radiation change information, it is used to indicate that the train body cover is not completely closed or there is an opening and closing abnormality when the opening and closing temperature changes.

[0018] In a preferred embodiment, in S105, a graphical interface is displayed on the train control console for visualization of the real-time cover opening and closing status, and a horn-shaped indicator light is used to indicate sound-related cover opening and closing, wherein the horn-shaped indicator light shows green to indicate that the cover is closed, shows red to indicate that the cover is open, and shows yellow to indicate that the cover is moving; a handle-shaped indicator light is used to indicate infrared radiation-related cover opening and closing, wherein the handle-shaped indicator light shows green to indicate that the cover is closed, shows red to indicate that the cover is open, and shows yellow to indicate that the cover is moving; a physical interface is used to connect to the train control console database, and statistical icons and time trend lines are generated to store the cover opening and closing status at different time points.

[0019] The beneficial effects of the present invention are: using sound sensors and infrared sensors to monitor the opening and closing status of train body covers, helping railway departments to better manage and maintain trains, avoiding safety problems caused by opening body covers, and improving the reliability and safety of train operation; effectively removing noise interference through median filtering processing, and realizing rapid transmission and storage of data, providing reliable data support for the monitoring and management of the opening and closing status of train covers; extracting the characteristics of sound data and infrared radiation through spectrum analysis and time domain analysis, more accurately describing the opening and closing status of the cover, helping to improve the safety and reliability of train operation, and using a visual interface to achieve long-term tracking and analysis of the cover status. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0021] 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 those skilled in the art without creative work are within the scope of protection of this application.

[0022] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0023] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0024] This embodiment provides Figure 1 A train body inspection cover opening and closing detection method is shown, which specifically includes the following steps:

[0025] S101: using a sound sensor to monitor the sound data generated by the opening and closing of the cover, using an infrared sensor to monitor the infrared radiation change information of the vehicle body surface due to the opening and closing of the cover, and establishing a data transfer system for transmitting the vehicle body cover opening and closing sound data and infrared radiation change information to the system data collection point;

[0026] Furthermore, a sound sensor is installed inside the train body cover to monitor the sound data generated by the opening and closing of the cover, and an infrared sensor is installed on the train body bogie to monitor the infrared radiation change information on the body surface due to the opening and closing of the cover. The wireless sensor network is integrated through wireless transmission using sound sensors and infrared sensor nodes, and the continuous collection time interval is preset to 30 minutes. A data transfer system is established to transmit the body cover opening and closing sound data and infrared radiation change information to the system data collection point.

[0027] Furthermore, the data transfer system selects a transfer node location that is close to the middle point between the sensor and the data collection point and meets the signal coverage and transmission stability requirements. The LoRaWAN wireless communication protocol is used to configure the transfer node to connect with the sensor. The transfer node is wirelessly connected to the sound sensor and the infrared sensor through a physical interface. The transfer node serves as an intermediate link in data transmission, forwarding the data received by the sound sensor and the infrared sensor in real time and sending it to the system data collection point.

[0028] S102: converting the sound data and infrared radiation change information into corresponding electrical signals through the system data collection point, filtering and conditioning the two electrical signals using median filtering, converting the electrical signals into digital signals using an analog-to-digital converter, and transmitting them to the data transfer system through wireless communication for temporary storage;

[0029] Furthermore, the system data collection point receives the opening and closing sound data and converts it into mechanical vibration using a vibrating diaphragm, and converts the mechanical vibration into an electrical signal corresponding to the sound data through the vibration sensor of the internal components of the sensor. The system data collection point combines with the infrared photodiode to receive infrared radiation change information. When the infrared radiation is reflected on the infrared photodiode, it is converted into electron energy through the photoelectric effect, and the PN junction inside the infrared photodiode is used to generate an electrical signal based on the electron energy, and reflect the intensity of the infrared radiation.

[0030] Furthermore, the two electrical signals are filtered and conditioned by using a median filter, wherein the median filter determines a filter window size of 2k+1, and applies electrical signal parameters, determines a window range of [ik,i+k] for the ith electrical signal data point, and sorts the window to obtain an ordered data series, selects the middle value of the ordered series as the median of the ith electrical signal data point and assigns it to the ith electrical signal data point, repeats the operation to perform a median filter on all electrical signal data points, and uses an analog-to-digital converter to convert the electrical signal into a digital signal, which is then transmitted to a data transfer system for temporary storage via wireless communication.

[0031] S103: performing spectrum analysis and time domain analysis on the sound data and the electrical signal of infrared radiation, extracting features for describing the process of the cover opening and closing state, annotating the extracted features and judging the selection of the cover opening and closing state through a random forest model;

[0032] Furthermore, by performing spectral analysis on the electrical signal corresponding to the sound data, the sound data is converted to the frequency domain and the frequency domain features are extracted, the bandwidth of the spectrum is obtained to describe the frequency distribution of the sound signal, and the frequency component is obtained to describe the uniformity of the energy distribution. By performing continuous wavelet transform on the electrical signal reflecting the intensity of infrared radiation, the signal of the electrical signal is continuously transformed using different scale and translation parameters to generate a continuous scale image, providing transformation information of the electrical signal at different frequencies and times, analyzing the waveform, amplitude and frequency characteristics of the electrical signal in the time domain, extracting the time domain parameters of the electrical signal, observing the periodicity and trend of the electrical signal, and performing temporal analysis and description of the electrical signal, and extracting features related to the opening and closing state of the cover.

[0033] Furthermore, the extracted features are labeled to determine the cover state corresponding to the electrical signal, and are input as training data into the random forest model for training. The specific steps are as follows: a decision tree is constructed by building a tree structure, using internal nodes to represent features and leaf nodes to represent decision results, and multiple decision trees are constructed by randomly selecting features and samples and intersecting the results to determine the choice of the cover opening and closing state, and the trained model is used to detect the opening and closing state of the train body cover.

[0034] S104: judging the cover state according to the feature extraction and random forest detection results, and indicating that the train body cover makes a sound when opening and closing, and that the train body cover is not completely closed and has an opening and closing abnormality when the opening and closing temperature changes;

[0035] Furthermore, the state of the cover is judged according to the feature extraction and random forest detection results. When the frequency domain of the sound data changes drastically and the random forest judges the state of the cover according to the sound generated by the opening and closing of the cover, it is used to indicate that the train body cover is not completely closed or there is an opening and closing abnormality when the opening and closing sound is made. The state of the cover is judged according to the feature extraction and random forest detection results. When the cover is opened, the temperature of the surface of the body changes. When the continuous-scale image generated by the electrical signal reflecting the intensity of the infrared radiation changes drastically and the random forest judges the state of the cover according to the infrared radiation change information, it is used to indicate that the train body cover is not completely closed or there is an opening and closing abnormality when the opening and closing temperature changes.

[0036] S105: Displaying a graphical interface for real-time visualization of the cover opening and closing status through the train console, connecting to the train console database through a physical interface, and generating statistical icons and time trend lines to store the cover opening and closing status at different time points;

[0037] Furthermore, a graphical interface is displayed on the train control console for visualization of the real-time cover opening and closing status, and a horn-shaped indicator light is used to indicate sound-related cover opening and closing, wherein the horn-shaped indicator light shows green to indicate that the cover is closed, red to indicate that the cover is open, and yellow to indicate that the cover is moving; a handle-shaped indicator light is used to indicate infrared radiation-related cover opening and closing, wherein the handle-shaped indicator light shows green to indicate that the cover is closed, red to indicate that the cover is open, and yellow to indicate that the cover is moving; a physical interface is used to connect to the train control console database, and statistical icons and time trend lines are generated to store the cover opening and closing status at different time points.

[0038] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0039] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0040] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0041] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0042] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0043] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0044] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A train body inspection cover opening and closing detection method, characterized in that: The specific steps include: S101: using a sound sensor to monitor the sound data generated by the opening and closing of the cover, using an infrared sensor to monitor the infrared radiation change information of the vehicle body surface due to the opening and closing of the cover, and establishing a data transfer system for transmitting the vehicle body cover opening and closing sound data and infrared radiation change information to the system data collection point; S102: converting the sound data and infrared radiation change information into corresponding electrical signals through the system data collection point, filtering and conditioning the two electrical signals using median filtering, converting the electrical signals into digital signals using an analog-to-digital converter, and transmitting them to the data transfer system through wireless communication for temporary storage; S103: performing spectrum analysis and time domain analysis on the sound data and the electrical signal of infrared radiation, extracting features for describing the process of the cover opening and closing state, annotating the extracted features and judging the selection of the cover opening and closing state through a random forest model; S104: judging the cover state according to the feature extraction and random forest detection results, and indicating that the train body cover makes a sound when opening and closing, and that the train body cover is not completely closed and has an opening and closing abnormality when the opening and closing temperature changes; S105: displaying a graphical interface for real-time visualization of the cover opening and closing status through the train console, connecting to the train console database through a physical interface, and generating statistical icons and time trend lines to store the cover opening and closing status at different time points; In S102, the system data acquisition point receives the opening and closing sound data and converts it into mechanical vibration using the vibrating diaphragm, and converts the mechanical vibration into an electrical signal corresponding to the sound data through the vibration sensor of the internal components of the sensor. The system data acquisition point receives the infrared radiation change information in combination with the infrared photodiode. When the infrared radiation is reflected on the infrared photodiode, it is converted into electron energy through the photoelectric effect, and the PN junction inside the infrared photodiode is used to generate an electrical signal according to the electron energy, and reflects the intensity of the infrared radiation, and the two electrical signals are filtered and conditioned using the median filter; The median filter determines the filter window size as 2k+1, and applies the electrical signal parameters, determines the window range as [ik,i+k] for the ith electrical signal data point, sorts and obtains an ordered data series, selects the middle value of the ordered series as the median value of the ith electrical signal data point and assigns it to the ith electrical signal data point, and repeats the operation to perform median filtering on all electrical signal data points; In the S103, by performing spectrum analysis on the electric signal corresponding to the sound data, the sound data is converted to the frequency domain and the frequency domain features are extracted, the bandwidth of the spectrum is obtained to describe the frequency distribution of the sound signal, and the frequency component is obtained to describe the uniformity of energy distribution. By performing continuous wavelet transform on the electric signal reflecting the intensity of infrared radiation, the electric signal is continuously transformed using different scale and translation parameters to generate a continuous scale image, providing transformation information of the electric signal at different frequencies and times, analyzing the waveform, amplitude and frequency characteristics of the electric signal in the time domain, extracting the time domain parameters of the electric signal, observing the periodicity and trend of the electric signal for time analysis and description of the electric signal, extracting features related to the opening and closing state of the cover, annotating the extracted features, determining the state of the cover corresponding to the electric signal, and inputting them into the random forest model as training data for training; The specific steps of training the random forest model are: by constructing a tree structure, using internal nodes to represent features and leaf nodes to represent decision results to construct a decision tree, by randomly selecting features and samples to construct multiple decision trees and intersecting the results, judging the choice of the cover opening and closing state, and using the trained model to detect the opening and closing state of the train body cover.

2. A train body inspection cover opening and closing detection method according to claim 1, characterized in that: In the S101, a sound sensor is installed inside the train body cover to monitor the sound data generated by the opening and closing of the cover, and an infrared sensor is installed on the train body bogie to monitor the infrared radiation change information on the body surface due to the opening and closing of the cover. The wireless sensor network is integrated through wireless transmission using the sound sensor and the infrared sensor node, and the continuous collection time interval is preset to 30 minutes. A data transfer system is established to transmit the body cover opening and closing sound data and infrared radiation change information to the system data collection point.

3. A train body inspection cover opening and closing detection method according to claim 2, characterized in that: The data transfer system selects a transfer node location that is close to the middle point between the sensor and the data collection point and meets the signal coverage and transmission stability requirements. The LoRaWAN wireless communication protocol is used to configure the transfer node to connect with the sensor. The transfer node is wirelessly connected to the sound sensor and the infrared sensor through a physical interface. The transfer node serves as an intermediate link in data transmission, forwarding the data received by the sound sensor and the infrared sensor in real time and sending it to the system data collection point.

4. A train body inspection cover opening and closing detection method according to claim 1, characterized in that: In S104, the state of the cover is determined based on the feature extraction and random forest detection results. When the cover is opened, the vehicle body sound data is generated and the temperature of the vehicle body surface changes.

5. A train body inspection cover opening and closing detection method according to claim 4, characterized in that: When the frequency domain of the sound data changes significantly and the random forest judges the cover status based on the sound produced by the opening and closing of the cover, it indicates that the train body cover was not completely closed or there was an opening and closing abnormality when the opening and closing sound was made. When the continuous scale image generated by the electrical signal reflecting the intensity of infrared radiation changes significantly and the random forest judges the cover status based on the infrared radiation change information, it indicates that the train body cover was not completely closed or there was an opening and closing abnormality when the opening and closing temperature changed.

6. A train body inspection cover opening and closing detection method according to claim 1, characterized in that: In the S105, a graphical interface is displayed on the train control console for visualization of the real-time cover opening and closing status, and a horn-shaped indicator light is used to indicate sound-related cover opening and closing, wherein the horn-shaped indicator light shows green to indicate that the cover is closed, shows red to indicate that the cover is open, and shows yellow to indicate that the cover is moving. A handle-shaped indicator light is used to indicate infrared radiation-related cover opening and closing, wherein the handle-shaped indicator light shows green to indicate that the cover is closed, shows red to indicate that the cover is open, and shows yellow to indicate that the cover is moving. A physical interface is used to connect to the train control console database, and statistical icons and time trend lines are generated to store the cover opening and closing status at different time points.

Images