A method for monitoring and early warning of tire pressure in trackless rubber-tired vehicles in underground mines

Abstract

This invention relates to the field of trackless rubber-tired vehicle technology, and particularly to a method for monitoring and warning tire pressure of an underground trackless rubber-tired vehicle. The method includes simultaneously acquiring real-time road condition images of the roadway floor in front of and / or below the vehicle, real-time tire pressure timing signals and vibration signals of the target tire, and real-time load and speed of the trackless rubber-tired vehicle; based on the real-time road condition images, quantitatively extracting the unevenness characteristic parameters of the current road surface; inputting the unevenness characteristic parameters, real-time load, and speed into a preset tire pressure response prediction model to obtain the expected tire pressure fluctuation characteristics corresponding to the current driving conditions; extracting the measured tire pressure fluctuation characteristics from the real-time tire pressure timing signals and calculating the deviation between these characteristics and the expected tire pressure fluctuation characteristics; based on the deviation and combined with the vibration signals, determining the tire pressure status, and generating a warning signal when an abnormality is detected.

Description

Technical Field

[0001] This invention relates to the technical field of trackless rubber-tired vehicles, and more particularly to a method for monitoring and early warning of tire pressure in underground trackless rubber-tired vehicles. Background Technology

[0002] In underground mining operations, trackless rubber-tired vehicles are critical transportation equipment, requiring real-time and accurate tire pressure monitoring to prevent safety accidents such as tire blowouts and abnormal wear. Existing tire pressure monitoring and early warning methods mainly rely on installing pressure sensors on the tires. By monitoring the absolute value or rate of change of tire pressure and comparing it with preset fixed thresholds, they determine whether air leaks or abnormal pressure have occurred. Existing alarm methods based on fixed thresholds work well in relatively flat and stable environments.

[0003] However, the underground tunnel floor conditions are complex, often featuring uneven surfaces such as undulations, potholes, and exposed rocks. When vehicles travel on such surfaces, the tires experience severe and irregular impact loads, causing instantaneous and dramatic deformation of the tire body, which in turn leads to inherent, high-frequency fluctuations in tire pressure. If the aforementioned monitoring method based on fixed thresholds is still used, these normal pressure fluctuations caused by road conditions are easily misinterpreted as tire abnormalities, resulting in numerous false alarms. Frequent false alarms not only interfere with the judgment of drivers and dispatchers but also reduce their trust in the alarm signals, potentially masking genuine tire malfunctions and creating safety hazards.

[0004] Therefore, there is an urgent need for a tire pressure monitoring and early warning method for trackless rubber-tired vehicles in underground mines that can effectively distinguish between normal tire pressure fluctuations caused by uneven roadway floor and abnormal pressure changes caused by tire malfunctions, thereby reducing the false alarm rate. Summary of the Invention

[0005] This invention provides a method for monitoring and early warning of tire pressure in trackless rubber-tired vehicles used in underground mines, which can effectively solve the problems in the background art.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0007] A method for monitoring and early warning of tire pressure in underground trackless rubber-tired vehicles includes:

[0008] Simultaneously acquire real-time road condition images of the roadbed in front of and / or below the vehicle, real-time tire pressure timing signals and vibration signals of the target tires, as well as the real-time load and speed of the trackless rubber-tired vehicle.

[0009] Based on the real-time road condition images, the unevenness feature parameters of the current driving road surface are quantitatively extracted.

[0010] The roughness characteristic parameters, the real-time load, and the vehicle speed are input together into a preset tire pressure response prediction model to obtain the expected tire pressure fluctuation characteristics corresponding to the current driving conditions.

[0011] The measured tire pressure fluctuation characteristics are extracted from the real-time tire pressure time-series signal, and the deviation between the measured tire pressure fluctuation characteristics and the expected tire pressure fluctuation characteristics is calculated.

[0012] Based on the deviation and the vibration signal, the tire pressure status is determined, and an early warning signal is generated when an abnormality is detected.

[0013] Furthermore, the simultaneous acquisition of real-time road condition images of the roadbed in front of and / or below the vehicle includes installing an industrial camera with wide-angle shooting function at the front of the trackless rubber-tired vehicle and an adjustable-angle camera at the bottom of the vehicle; the simultaneous acquisition of real-time tire pressure timing signals and vibration signals of the target tire includes installing a pressure sensor inside the target tire and a vibration sensor on the tire rim; the simultaneous acquisition of real-time load and speed of the trackless rubber-tired vehicle includes installing a strain gauge load sensor on the frame of the trackless rubber-tired vehicle and a Hall sensor or photoelectric encoder on the drive axle or wheels of the vehicle.

[0014] Furthermore, during the data acquisition and processing process, a unified time reference is set for each sensor, and a timestamp is added to the stored data samples.

[0015] Furthermore, the roughness characteristic parameters include at least one of the following: road surface elevation standard deviation, pothole surface density, average pothole depth estimate, and surface roughness index calculated based on image edge features.

[0016] Furthermore, based on the real-time traffic image, the unevenness feature parameters of the current road surface are quantified and extracted, wherein the preprocessing method for the real-time traffic image includes:

[0017] The current frame image is selected from the real-time traffic images as the processing object; the image is first converted to grayscale, and then the grayscale image is filtered using a median filtering algorithm while preserving the edge information of the image.

[0018] Use edge detection algorithms to detect edge information in images;

[0019] After detecting the edge, the location and extent of the road surface area are determined.

[0020] Furthermore, the method for generating the tire pressure response prediction model includes:

[0021] During the stage when the tires are confirmed to be in good condition, multiple sets of historical data pairs are collected. Each set of historical data pairs includes historical roughness characteristic parameters, historical load and vehicle speed, and the corresponding historical tire pressure fluctuation characteristics.

[0022] Using the historical roughness characteristic parameters, historical load and vehicle speed as inputs, and the historical tire pressure fluctuation characteristics as the output target, the machine learning model is trained to obtain the tire pressure response prediction model.

[0023] Furthermore, both the expected tire pressure fluctuation characteristics and the measured tire pressure fluctuation characteristics include the amplitude statistics of the tire pressure fluctuation signal.

[0024] Furthermore, the deviation is the degree of deviation of the amplitude statistics of the tire pressure fluctuation signal in the measured tire pressure fluctuation characteristics relative to the amplitude statistics of the tire pressure fluctuation signal in the expected tire pressure fluctuation characteristics.

[0025] Furthermore, the determination of tire pressure includes:

[0026] If the deviation indicates that the amplitude statistics of the tire pressure fluctuation signal in the measured tire pressure fluctuation characteristics are consistently lower than the amplitude statistics of the tire pressure fluctuation signal in the expected tire pressure fluctuation characteristics within a preset time period, then it is diagnosed as a tire pressure deficiency fault.

[0027] If the deviation indicates that the amplitude statistics of the measured tire pressure fluctuation signal in the actual tire pressure fluctuation characteristics are continuously higher than the amplitude statistics of the expected tire pressure fluctuation signal in the expected tire pressure fluctuation characteristics within a preset time period, and the energy of the vibration signal in the structural damage sensitive frequency band exceeds a preset threshold, then it is diagnosed as a tire body structural damage type fault.

[0028] Furthermore, the generation of warning signals when an abnormality is determined includes issuing a warning signal through an audible and visual alarm device when a fault such as insufficient tire pressure or damage to the tire structure is diagnosed, and simultaneously transmitting the warning information to the vehicle monitoring system to record the time, location, and type of the fault.

[0029] The technical solution of this invention achieves the following technical effects: By fusing multi-source data, accurately quantifying road conditions, and dynamically predicting tire pressure, combined with deviation calculation and vibration signal comprehensive judgment, it can effectively distinguish between normal fluctuations and abnormal changes, reduce false alarms caused by road conditions, improve the reliability of alarm signals, and increase the trust of drivers and dispatchers in alarm signals; while reducing the false alarm rate, this method can accurately identify abnormal pressure changes caused by tire malfunctions and generate early warning signals in a timely manner; it helps to detect real tire malfunctions in a timely manner and avoid safety accidents caused by undetected malfunctions; the conditions of underground roadway floors are complex and diverse, and this method, through real-time collection and dynamic analysis of various data, can adapt to different uneven road surfaces such as undulations, potholes, and exposed rocks, as well as different load and speed conditions; regardless of the complex environment in which the vehicle is driving, it can accurately judge the tire condition and has wide applicability; by accurately judging different types of tire malfunctions, it can provide a scientific basis for equipment maintenance; maintenance personnel can formulate targeted maintenance strategies according to different malfunction types and severity, rationally arrange maintenance time and resources, improve equipment maintenance efficiency, and reduce maintenance costs.

[0030] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1 This is a flowchart illustrating the tire pressure monitoring and early warning method for trackless rubber-tired vehicles in underground mines according to the present invention. Detailed Implementation

[0033] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0035] like Figure 1 As shown, the present invention provides a method for monitoring and warning the tire pressure of a trackless rubber-tired vehicle in an underground mine, which specifically includes the following steps:

[0036] S1. Simultaneously acquire real-time road condition images of the roadbed in front of and / or below the vehicle, real-time tire pressure timing signals and vibration signals of the target tires, as well as the real-time load and speed of the trackless rubber-tired vehicle.

[0037] S2. Based on the real-time road condition image, quantitatively extract the unevenness feature parameters of the current driving road surface;

[0038] S3. Input the roughness characteristic parameters, the real-time load and the vehicle speed into the preset tire pressure response prediction model to obtain the expected tire pressure fluctuation characteristics corresponding to the current driving conditions.

[0039] S4. Extract the measured tire pressure fluctuation characteristics from the real-time tire pressure time-series signal, and calculate the deviation between the measured tire pressure fluctuation characteristics and the expected tire pressure fluctuation characteristics;

[0040] S5. Based on the deviation and the vibration signal, determine the tire pressure status and generate a warning signal when an abnormality is detected.

[0041] In this embodiment, by fusing multi-source data, accurately quantifying road conditions, and dynamically predicting tire pressure, combined with deviation calculation and vibration signal analysis, this method can effectively distinguish between normal fluctuations and abnormal changes, reducing false alarms caused by road conditions, improving the reliability of alarm signals, and increasing the trust of drivers and dispatchers in alarm signals. While reducing the false alarm rate, this method can accurately identify abnormal pressure changes caused by tire malfunctions and generate early warning signals in a timely manner. This helps to detect real tire malfunctions promptly and avoid safety accidents caused by undetected malfunctions. Given the complex and diverse conditions of underground roadway floors, this method, through real-time collection and dynamic analysis of various data, can adapt to uneven road surfaces with different undulations, potholes, exposed rocks, and various load and speed conditions. Regardless of the complex environment in which the vehicle is driving, it can accurately determine the tire condition, demonstrating broad applicability. Accurately identifying different types of tire malfunctions provides a scientific basis for equipment maintenance. Maintenance personnel can develop targeted maintenance strategies based on different malfunction types and severity, rationally allocate maintenance time and resources, improve equipment maintenance efficiency, and reduce maintenance costs.

[0042] In some embodiments of the present invention, for step S1, real-time road condition images of the roadbed in front of and / or below the vehicle, real-time tire pressure timing signals and vibration signals of the target tires, and real-time load and speed of the trackless rubber-wheeled vehicle are collected simultaneously.

[0043] A high-definition industrial camera is installed at the front of the trackless rubber-tired vehicle. The camera has a wide-angle shooting function and can cover a certain range of the tunnel floor area in front of the vehicle. If it is necessary to collect images of the road conditions under the vehicle, a rotatable or adjustable camera is installed at a suitable position under the vehicle. The camera angle is adjusted by motor drive to obtain images of the tunnel floor under the vehicle from different perspectives.

[0044] The camera is connected to the vehicle's power system and powered by the vehicle's power supply. It is also equipped with an independent image acquisition card, which is connected to the camera via a high-speed data cable. The image acquisition card converts the analog image signals captured by the camera into digital image signals and stores them in the image acquisition card's cache.

[0045] To ensure real-time image acquisition, the operating frequency of the image acquisition card is set to match the vehicle's speed and the camera's frame rate. Based on the vehicle's average speed and the camera's field of view, the number of images that need to be acquired for each certain distance traveled is calculated, thereby determining the operating frequency of the image acquisition card.

[0046] A high-precision pressure sensor is installed inside the target tire. The pressure sensor can detect changes in the internal pressure of the tire in real time and convert the pressure signal into an electrical signal. The pressure sensor transmits the electrical signal to the data receiving device on the vehicle through a wireless transmission module. The wireless transmission module adopts a wireless communication protocol with strong anti-interference capabilities to ensure the stability of signal transmission in the complex electromagnetic environment underground.

[0047] A vibration sensor is installed on the tire rim. The vibration sensor can detect the vibration and impact that the tire is subjected to during driving and convert the vibration signal into an electrical signal. The vibration sensor and the pressure sensor share the same wireless transmission module to synchronously send the vibration electrical signal to the data receiving device.

[0048] The data receiving device uses a high-performance microprocessor with multi-channel data receiving and processing capabilities. The microprocessor performs analog-to-digital conversion on the received pressure and vibration electrical signals, converts them into digital signals, and stores them according to the time sequence to form real-time tire pressure timing signals and vibration signal data.

[0049] A load sensor is installed on the frame of the trackless rubber-tired vehicle. The load sensor is a high-precision strain gauge sensor that can accurately measure the load borne by the vehicle. The load sensor is connected to the vehicle's data acquisition system, converting the load signal into an electrical signal and transmitting it to the data acquisition system.

[0050] Vehicle speed sensors are installed on the drive shaft or wheels of the vehicle. The vehicle speed sensors can be Hall sensors or photoelectric encoders. Hall sensors calculate vehicle speed by detecting changes in the magnetic signal on the drive shaft or wheels. Photoelectric encoders determine vehicle speed by detecting the pulse signal of the grating when the wheel rotates. The vehicle speed sensor converts the vehicle speed signal into an electrical signal and transmits it to the data acquisition system.

[0051] To ensure that the collected road condition images, tire pressure timing signals, vibration signals, real-time load and vehicle speed data are synchronized in time, a unified time reference is set in each sensor and data acquisition module;

[0052] When storing data, add a timestamp to each data sample.

[0053] In this embodiment, by simultaneously acquiring road condition images in front of and below the vehicle, real-time tire pressure of the target tires, vibration signals, load, and vehicle speed data, the operating status of the trackless rubber-wheeled vehicle can be comprehensively and in real-time monitored, ensuring the timeliness of all critical information. High-definition industrial cameras installed at the front and bottom of the vehicle can acquire clear road condition images and provide real-time feedback on the vehicle's driving environment, helping to promptly identify potential obstacles, road problems, or safety hazards. An adjustable-angle camera installed under the vehicle, with its shooting angle adjusted by a motor, can flexibly acquire road condition images from different perspectives, providing more monitoring dimensions and ensuring comprehensive safety monitoring of the vehicle. High-precision pressure sensors and vibration sensors are also installed. Sensors can detect tire pressure changes and vibration impacts in real time, providing accurate data for potential anomalies during vehicle operation and enabling timely fault warnings. The use of a highly interference-resistant wireless transmission module ensures stable data transmission even in complex underground electromagnetic environments, guaranteeing lossless real-time data transmission. The data receiving device is equipped with a high-performance microprocessor, possessing multi-channel data reception and processing capabilities, and can perform real-time analog-to-digital conversion of signals, ensuring the accuracy of data from various sensors. A unified time base and timestamp mechanism ensures synchronization of all data over time, avoiding analytical errors caused by data deviations and improving the reliability of data analysis.

[0054] In a specific implementation, as one example, for step S2, based on the real-time road condition image, the unevenness feature parameters of the current driving road surface are quantitatively extracted.

[0055] The roughness feature parameters are used to quantify the degree of deviation of the roadway floor surface from an ideal plane, especially a series of parameters that can cause local or global geometric defects that generate additional dynamic loads on the tires. The larger the value of the roughness feature parameters, the worse the road surface condition and the stronger the impact excitation on the tires. The roughness feature parameters include at least one of the following: road surface elevation standard deviation, pothole density, average pothole depth estimate, and surface roughness index calculated based on image edge features.

[0056] The current frame image is selected from the synchronously acquired real-time road condition images as the processing object. Considering the dim lighting and possible interference factors such as dust in the underground environment, the image is first converted to grayscale to reduce the amount of data in subsequent processing. The weighted average method is used for grayscale conversion. In order to eliminate noise interference in the image, the median filtering algorithm is used to filter the grayscale image to remove impulse noise such as salt and pepper noise in the image, while preserving the edge information of the image.

[0057] Since the acquired images may contain vehicle structures or other unrelated objects, it is necessary to accurately extract the road surface area. A method combining edge detection and region growing is adopted. First, the Canny edge detection algorithm is used to detect edge information in the image. The Canny algorithm can accurately detect edges in the image by calculating the gradient magnitude and direction of the image, and then performing non-maximum suppression and double threshold detection.

[0058] After detecting the edge, the approximate location and extent of the road surface area are determined based on prior knowledge. Starting from near the bottom of the image, a seed point is selected, and region growing is performed from this seed point. The rule of region growing is to merge pixels adjacent to the seed point and whose gray values ​​are within a certain threshold range into the same region. This process is repeated until there are no new pixels that can be merged. Through region growing, the approximate outline containing the road surface area can be obtained.

[0059] To further refine the extraction of the road surface area, morphological processing was performed on the results obtained from the region growing; opening operations were used to remove small holes and burrs inside the region, making the boundaries of the road surface area smoother.

[0060] Assuming each pixel in the image corresponds to a tiny area on the actual road surface, the grayscale value of the image is approximated as the height information of the road surface in that tiny area. To unify the dimensions, the grayscale value is first normalized to map the grayscale value range to a reasonable range of the actual road surface height.

[0061] Calculate the standard deviation of the normalized gray values ​​of all pixels in the road area. The standard deviation of road elevation reflects the degree of dispersion of road height relative to the mean. The larger the value, the greater the variation of road surface undulation and the higher the unevenness.

[0062] A local threshold segmentation method is used to detect potholes in the road surface area. The road surface area is divided into several small windows. Within each small window, the mean and standard deviation of the gray values ​​of the pixels within the window are calculated, and a local threshold is determined based on the mean and standard deviation. If the gray value of a pixel within the window is lower than the local threshold, the pixel is considered to belong to the pothole area.

[0063] For each detected pothole area, find the pixel with the lowest gray value in that area, and use its normalized gray value as the depth estimate of the pothole. Calculate the average depth estimate of all pothole areas to obtain the average pothole depth estimate. The average pothole depth estimate reflects the average depth of the road surface potholes. The larger the value, the deeper the potholes and the higher the unevenness of the road surface.

[0064] The Sobel operator is used to perform edge detection on the preprocessed road surface area image to obtain the edge image. The Sobel operator is a commonly used edge detection operator that detects edges by calculating the gradient of the image in the horizontal and vertical directions. The surface roughness index reflects the roughness of the road surface. The larger the value, the rougher the road surface and the higher the unevenness.

[0065] In this embodiment, image processing methods can efficiently and accurately extract road surface areas and their unevenness features. By quantifying road unevenness using indicators such as standard deviation, pothole density, pothole depth, and roughness, the road surface condition can be comprehensively reflected, effectively revealing local or global geometric defects that impact tires. In underground environments, image quality may be limited due to low light and potential dust. However, by employing techniques such as image grayscale conversion, noise removal, and edge detection, road surface information can be accurately obtained, adapting to the special conditions of underground environments. The extracted road unevenness feature parameters can quantify and evaluate the degree of deviation of the road surface from an ideal plane; larger parameter values ​​indicate worse road conditions and a stronger impact on tires, thus helping to make appropriate adjustments during design and operation to mitigate the damage caused by road unevenness to tires. In summary, this step, through efficient image processing technology, accurately extracts road unevenness features, providing reliable data support for dynamic load prediction, vehicle performance optimization, and safety improvement.

[0066] In some embodiments of the present invention, for step S3, the roughness characteristic parameters, the real-time load and the vehicle speed are jointly input into a preset tire pressure response prediction model to obtain the expected tire pressure fluctuation characteristics corresponding to the current driving conditions.

[0067] The method for generating the tire pressure response prediction model includes:

[0068] During the stage when the tires are confirmed to be in good condition, multiple sets of historical data pairs are collected. Each set of historical data pairs includes historical roughness characteristic parameters, historical load and vehicle speed, and the corresponding historical tire pressure fluctuation characteristics.

[0069] Using the historical roughness characteristic parameters, historical load and vehicle speed as inputs, and the historical tire pressure fluctuation characteristics as the output target, the machine learning model is trained to obtain the tire pressure response prediction model.

[0070] After the model training and validation are successful, the real-time collected roughness feature parameters, real-time load and vehicle speed data are preprocessed in the same way as the training data and then input into the trained tire pressure response prediction model.

[0071] The model calculates the expected tire pressure fluctuation characteristics corresponding to the current driving conditions based on the input multi-parameter information.

[0072] In this embodiment, by collecting multiple parameters in real time, the model can quickly predict tire pressure fluctuations, helping the vehicle maintain optimal tire pressure under different operating conditions and improving driving safety. By collecting historical data under healthy tire conditions, the model can learn from actual driving data, ensuring that the prediction results are more consistent with actual usage and reducing errors. It can predict and identify tire pressure fluctuations in advance, helping drivers adjust tire pressure in a timely manner, optimizing fuel efficiency and vehicle handling, and improving the overall driving experience. Through the training and application of machine learning models, the entire process is highly automated, reducing human intervention and improving the vehicle's intelligence level. By accurately predicting tire pressure fluctuations, potential tire pressure anomalies can be identified in advance, thereby taking measures in advance to reduce the risk of traffic accidents caused by tire blowouts or low tire pressure.

[0073] In some embodiments of the present invention, for step S4, the measured tire pressure fluctuation characteristics are extracted from the real-time tire pressure time-series signal, and the deviation between the measured tire pressure fluctuation characteristics and the expected tire pressure fluctuation characteristics is calculated.

[0074] Both the expected tire pressure fluctuation characteristics and the measured tire pressure fluctuation characteristics include the amplitude statistics of the tire pressure fluctuation signal;

[0075] The deviation is the degree of deviation of the amplitude statistics of the tire pressure fluctuation signal in the measured tire pressure fluctuation characteristics relative to the amplitude statistics of the tire pressure fluctuation signal in the expected tire pressure fluctuation characteristics.

[0076] The collected real-time tire pressure timing signal is filtered to eliminate noise interference; the filtered signal is then normalized, which eliminates the influence of different dimensions and facilitates subsequent feature extraction and deviation calculation.

[0077] Amplitude statistics are extracted from the normalized real-time tire pressure time-series signal as one of the characteristics of measured tire pressure fluctuations. The mean and standard deviation of the signal are calculated. The mean reflects the average level of tire pressure fluctuations, and the standard deviation reflects the dispersion of tire pressure fluctuations. Together, they constitute the amplitude statistics, which can comprehensively describe the characteristics of tire pressure fluctuations.

[0078] A peak detection algorithm is used to extract peak values ​​from the real-time tire pressure time-series signal. A suitable threshold is set, and when the signal value exceeds the threshold, it is determined to be a peak value. The threshold can be dynamically determined based on the mean and standard deviation of the signal. The size and occurrence time of the peak value are recorded. The size of the peak value reflects the maximum amplitude of tire pressure fluctuation, and the occurrence time can help analyze the relationship between tire pressure fluctuation and factors such as road conditions.

[0079] The expected tire pressure fluctuation characteristics corresponding to the current driving conditions are obtained from the output of the tire pressure response prediction model. Similarly, the amplitude statistics and peak characteristics of the expected tire pressure fluctuation signal are extracted. The extraction method is the same as the extraction method of the measured tire pressure fluctuation characteristics.

[0080] Calculate the deviation between the mean of the measured tire pressure fluctuation signal and the mean of the expected tire pressure fluctuation signal, as well as the deviation between the standard deviation of the measured tire pressure fluctuation signal and the standard deviation of the expected tire pressure fluctuation signal.

[0081] If both the measured signal and the expected signal detect a peak value, calculate the deviation between the measured peak value and the expected peak value. If neither the measured signal nor the expected signal detects a peak value, special handling can be performed according to the actual situation. For example, when the measured signal does not detect a peak value but the expected signal does, it can be considered that the measured tire pressure fluctuation is abnormal, and the deviation value can be set to a large value.

[0082] In this embodiment, by extracting amplitude statistics, mean, and standard deviation from the real-time tire pressure time-series signal and combining them with a peak detection algorithm, the characteristics of tire pressure fluctuations can be comprehensively described, accurately reflecting the amplitude, average level, and dispersion of tire pressure fluctuations. By filtering the signal to eliminate noise interference and normalizing the filtered signal, the influence of different dimensions can be eliminated, improving the accuracy of subsequent feature extraction and deviation calculation. By dynamically determining the threshold and performing peak detection, reasonable detection standards can be set based on the mean and standard deviation of the real-time signal, improving the accuracy of peak detection and allowing adjustment of detection sensitivity according to different situations, thereby improving the flexibility of the detection system. The measured tire pressure fluctuation characteristics and the expected tire pressure fluctuation characteristics are calculated. The deviation between measured and expected signals can promptly detect abnormal tire pressure fluctuations and identify potential tire pressure problems. Setting a larger deviation can highlight abnormal tire pressure, enhancing fault diagnosis capabilities. By comparing the actual tire pressure fluctuations with the expected characteristics output by the tire pressure response prediction model, it is possible to effectively verify whether the actual tire pressure fluctuations meet expectations, thereby determining whether the vehicle's tire pressure status is normal. This provides a dual guarantee of prediction and detection for the tire pressure monitoring system. Calculating the deviation between measured and expected signals enables more intelligent anomaly detection. This step, through comprehensive analysis, filtering, normalization, and deviation calculation of real-time tire pressure time-series signals, achieves accurate monitoring and anomaly detection of tire pressure fluctuations, improving the reliability of the tire pressure monitoring system.

[0083] In some embodiments of the present invention, for step S5, the tire pressure status is determined based on the deviation and the vibration signal, and an early warning signal is generated when an abnormality is determined.

[0084] The deviation value contains information about the relationship between the measured fluctuation amplitude and the expected range. If the deviation value indicates that the measured fluctuation amplitude is consistently lower than the expected range within a preset time period, it indicates that the tire may have insufficient tire pressure. If the deviation value indicates that the measured fluctuation amplitude is consistently higher than the expected range within a preset time period, the tire may have abnormally high pressure or other potential faults. The preset time period is determined based on the actual operation of the trackless rubber-tired vehicle in the well and experimental data to ensure that the continuous state of abnormal tire pressure can be accurately captured.

[0085] The collected vibration signals were preprocessed, and a bandpass filter was used to remove noise interference while retaining signal components related to the frequency band sensitive to tire structure damage. Through preliminary experiments and analysis, the range of the frequency band sensitive to tire structure damage was determined, and the passband of the bandpass filter was set to this frequency band.

[0086] Calculate the energy of the filtered vibration signal in the structural damage-sensitive frequency band; use short-time Fourier transform to convert the vibration signal from the time domain to the frequency domain to obtain the signal's spectral distribution; then integrate the spectral amplitude within the structural damage-sensitive frequency band to obtain the energy value of that frequency band;

[0087] When the measured fluctuation amplitude of the deviation indicator is consistently lower than the expected range within a preset time period, it is directly diagnosed as a tire pressure deficiency fault. At this time, the tire pressure is lower than the normal level, which may affect the vehicle's driving performance and safety.

[0088] When the measured fluctuation amplitude of the deviation indicator is continuously higher than the expected range within a preset time period, the energy of the vibration signal in the structural damage sensitive frequency band is further checked; if the energy exceeds the preset threshold, it is diagnosed as a tire body structure damage type fault; the preset threshold is determined by collecting vibration signals and calculating the energy of the structural damage sensitive frequency band when the tire is in good condition, combined with experimental data and statistical analysis; because when the tire body structure is damaged, the tire will generate abnormal vibration during driving, which leads to an increase in the energy of the structural damage sensitive frequency band;

[0089] When a fault is diagnosed as insufficient tire pressure or damage to the tire structure, a corresponding warning signal is generated. The warning signal can be issued through an audible and visual alarm device, such as emitting a specific frequency alarm sound and flashing warning lights, to remind the driver and dispatcher to take timely measures. At the same time, the warning information is transmitted to the vehicle monitoring system to record information such as the time, location and type of the fault, which will facilitate subsequent analysis and processing.

[0090] The determination of tire pressure status includes: if the measured fluctuation amplitude of the deviation indicator is continuously lower than the expected range within a preset time period, it is diagnosed as a tire pressure deficiency fault; if the measured fluctuation amplitude of the deviation indicator is continuously higher than the expected range within a preset time period, and the energy of the vibration signal in the structural damage sensitive frequency band exceeds a preset threshold, it is diagnosed as a tire body structural damage fault.

[0091] In this embodiment, by analyzing the deviation, it is possible to accurately determine whether the tire pressure is insufficient or abnormally high. When the measured fluctuation amplitude is consistently below the expected range, insufficient tire pressure can be identified in a timely manner, avoiding safety hazards caused by low tire pressure. If the fluctuation amplitude is consistently above the expected range, potential high pressure or other fault risks can be detected early. A bandpass filter is used to remove noise from the vibration signal, retaining the signal components related to tire structural damage. By converting the signal from the time domain to the frequency domain using a short-time Fourier transform, details related to tire damage can be accurately captured, enhancing the early warning capability of structural damage. Combining the deviation of tire pressure fluctuation and the energy analysis of the vibration signal, a comprehensive fault diagnosis of the tire can be performed. When the system detects insufficient tire pressure or tire structural damage, it can automatically generate a warning signal and trigger an audible and visual alarm. The device alerts the driver or dispatcher; the instant warning function improves emergency response speed and reduces the threat of potential faults to vehicle safety; by collecting vibration signals under tire health conditions and setting preset thresholds in combination with experimental data, it ensures a high degree of accuracy in judging structural damage; timely detection of abnormal tire pressure or tire structural damage can effectively prevent accidents or faults caused by tire problems, thereby improving the overall safety of the vehicle; through precise fault diagnosis and early warning, the system helps the driver take appropriate measures before the problem develops into a serious accident, ensuring the safety of the driver and passengers; in summary, this step, through precise analysis of tire pressure fluctuations and vibration signals, combined with intelligent algorithms to achieve early fault diagnosis and early warning, provides strong technical support for vehicle safety management, reduces potential risks, and improves driving safety and vehicle maintenance efficiency.

[0092] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of the application as defined herein, and are to be considered as covering any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Thus, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method for monitoring and early warning of tire pressure in underground trackless rubber-tired vehicles, characterized in that, include: Simultaneously acquire real-time road condition images of the roadbed in front of and / or below the vehicle, real-time tire pressure timing signals and vibration signals of the target tires, as well as the real-time load and speed of the trackless rubber-tired vehicle. Based on the real-time road condition images, the unevenness feature parameters of the current driving road surface are quantitatively extracted. The roughness characteristic parameters, the real-time load, and the vehicle speed are input together into a preset tire pressure response prediction model to obtain the expected tire pressure fluctuation characteristics corresponding to the current driving conditions. The measured tire pressure fluctuation characteristics are extracted from the real-time tire pressure time-series signal, and the deviation between them and the expected tire pressure fluctuation characteristics is calculated. Both the expected tire pressure fluctuation characteristics and the measured tire pressure fluctuation characteristics include the amplitude statistics of the tire pressure fluctuation signal. The deviation is the degree of deviation of the amplitude statistics of the tire pressure fluctuation signal in the measured tire pressure fluctuation characteristics relative to the amplitude statistics of the tire pressure fluctuation signal in the expected tire pressure fluctuation characteristics. Based on the deviation and the vibration signal, the tire pressure status is determined, and an early warning signal is generated when an abnormality is detected. This includes: using a bandpass filter to preprocess the vibration signal to remove noise interference and retain signal components related to the frequency bands sensitive to tire structural damage. The preprocessed vibration signal is converted from the time domain to the frequency domain using a short-time Fourier transform to obtain the spectral distribution of the vibration signal. The spectral amplitude is then integrated within the structural damage-sensitive frequency band to obtain the energy value of that frequency band. The structural damage-sensitive frequency band is determined through preliminary experiments and analysis, and the passband of the bandpass filter matches the range of this frequency band. If the deviation indicates that the amplitude statistics of the tire pressure fluctuation signal in the measured tire pressure fluctuation characteristics are consistently lower than the amplitude statistics of the tire pressure fluctuation signal in the expected tire pressure fluctuation characteristics within a preset time period, then it is diagnosed as a tire pressure deficiency fault. If the deviation indicates that the amplitude statistics of the measured tire pressure fluctuation signal in the actual tire pressure fluctuation characteristics are continuously higher than the amplitude statistics of the expected tire pressure fluctuation signals within a preset time period; and the energy value of the vibration signal in the structural damage sensitive frequency band exceeds a preset threshold, then it is diagnosed as a tire body structural damage type fault; the preset threshold is determined based on the energy statistics of the vibration signal collected under the tire health condition in the structural damage sensitive frequency band.

2. The method for monitoring and early warning of tire pressure in underground trackless rubber-tired vehicles according to claim 1, characterized in that, The simultaneous acquisition of real-time road condition images of the roadbed in front of and / or below the vehicle includes installing an industrial camera with wide-angle shooting function at the front of the trackless rubber-tired vehicle and an adjustable-angle camera at the bottom of the vehicle; the simultaneous acquisition of real-time tire pressure timing signals and vibration signals of the target tire includes installing a pressure sensor inside the target tire and a vibration sensor on the tire hub; the simultaneous acquisition of real-time load and speed of the trackless rubber-tired vehicle includes installing a strain gauge load sensor on the frame of the trackless rubber-tired vehicle and a Hall sensor or photoelectric encoder on the drive axle or wheels of the vehicle.

3. The method for monitoring and early warning of tire pressure in underground trackless rubber-tired vehicles according to claim 2, characterized in that, Set a unified time base for each sensor and add timestamps to the stored data samples.

4. The method for monitoring and early warning of tire pressure in underground trackless rubber-tired vehicles according to claim 1, characterized in that, The roughness characteristic parameters include at least one of the following: standard deviation of road elevation, pothole density, estimated average pothole depth, and surface roughness index calculated based on image edge features.

5. The method for monitoring and early warning of tire pressure in underground trackless rubber-tired vehicles according to claim 1, characterized in that, Based on the real-time traffic image, the unevenness feature parameters of the current road surface are extracted by quantification, wherein the preprocessing method for the real-time traffic image includes: The current frame image is selected from the real-time traffic images as the processing object; the image is first converted to grayscale, and then the grayscale image is filtered using a median filtering algorithm while preserving the edge information of the image. Use edge detection algorithms to detect edge information in images; After detecting the edge, the location and extent of the road surface area are determined.

6. The method for monitoring and early warning of tire pressure in underground trackless rubber-tired vehicles according to claim 1, characterized in that, The method for generating the tire pressure response prediction model includes: During the stage when the tires are confirmed to be in good condition, multiple sets of historical data pairs are collected. Each set of historical data pairs includes historical roughness characteristic parameters, historical load and vehicle speed, and the corresponding historical tire pressure fluctuation characteristics. Using the historical roughness characteristic parameters, historical load and vehicle speed as inputs, and the historical tire pressure fluctuation characteristics as the output target, the machine learning model is trained to obtain the tire pressure response prediction model.

7. The method for monitoring and early warning of tire pressure in underground trackless rubber-tired vehicles according to claim 1, characterized in that, The generation of warning signals when an abnormality is detected includes issuing a warning signal through an audible and visual alarm device when a fault is diagnosed as insufficient tire pressure or damage to the tire structure, and simultaneously transmitting the warning information to the vehicle monitoring system to record the time, location, and type of the fault.

Images