Accurate parking control method and system based on Internet of Things and storage medium

Abstract

The invention relates to the technical field of the Internet of Things, and discloses an accurate parking control method and system based on the Internet of Things and a storage medium. The method comprises the steps that first image data and a mark position are obtained, a first target graph is recognized through a preset first algorithm, and if the first target graph is recognized, the target position of the first target graph is determined; and meanwhile, first target height data is acquired to adjust a mark position height parameter. Calculating a distance value between the target and the marked position, and calculating and outputting a difference value and a direction when the distance value is greater than or equal to a reference value; and if less than the reference value, driving the second target, using a preset second algorithm to identify a second target graph, calculating a moving distance value, if greater than the moving reference value, calculating contour coincidence data, and judging whether parking succeeds or not according to the data, wherein the moving reference value is inversely correlated with the height parameter. According to the method, the parking precision can be effectively improved, manual operation errors are reduced, and the parking efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of the Internet of Things, and in particular to a precise parking control method, system and storage medium based on the Internet of Things. Background Art

[0002] Slag powder, whose full name is granulated blast furnace slag powder, referred to as ore powder or slag powder, is a fine powder made by drying and grinding the waste slag produced when smelting pig iron in steel plants.

[0003] Slag powder manufacturers use tank trucks and road transport to transport slag powder. The process is to load the slag powder into the tank truck by pneumatic conveying, and use the tank truck's own air compressor to unload the powder to the designated location. Tank truck transportation has the advantages of high flexibility, convenient loading and unloading, and can be delivered directly to the construction site. It is suitable for short-distance transportation and situations with flexible requirements for transportation time and location, such as construction sites within cities.

[0004] The existing slag micro powder loading process is that the driver drives the vehicle into the micro powder storage bin, stops in the pre-marked area, and then climbs onto the roof to open the vehicle tank mouth. The delivery operator then controls the position of the delivery head so that the delivery head can fall exactly into the vehicle tank mouth. Since the delivery operator can only watch the delivery head aligning with the vehicle tank mouth from a fixed direction, there are many blind spots in the viewing angle. To ensure that the delivery head falls into the vehicle tank mouth correctly, the operator needs to stand up and confirm again. If it falls abnormally and needs to be fine-tuned, the operator needs to remotely intercom the driver to manually adjust the delivery head. The existing manual operation process of aligning the delivery head with the vehicle tank mouth is time-consuming and inefficient. Summary of the invention

[0005] In order to improve the working efficiency of aligning the slag powder delivery head with the vehicle tank mouth, the present application provides a precise parking control method, system and storage medium based on the Internet of Things.

[0006] In the first aspect, the present application provides a precise parking control method based on the Internet of Things, which adopts the following technical solutions: A precise parking control method based on the Internet of Things comprises the following steps: Acquire first image data and mark position; Identifying a first target graphic corresponding to a first target from the first image data based on a preset first algorithm; If the first target graphic is identified, the graphic position of the first target graphic is calculated as the target position; Acquire height data of the first target, and adjust the height parameter of the marking position in a positive correlation according to the height data; Calculating a position distance value between the target position and the marked position; If the position distance value is greater than or equal to the distance reference value, then calculating the distance difference between the position distance value and the distance reference value, calculating the position direction between the target position and the mark position, and outputting the distance difference and the position direction; If the position distance value is less than a preset distance reference value, an instruction to drive a second target is issued; a second target pattern is identified from the first image data based on a preset second algorithm; If the second target graphic is identified, a moving distance value of the second target graphic is calculated, and if the moving distance value is greater than a preset moving reference value, contour coincidence data of the second target graphic and the first target graphic is calculated; If the contour overlap data is within a preset contour overlap range, it indicates that the parking is successful; otherwise, it indicates that the parking is unsuccessful, wherein the movement reference value is inversely correlated with the height parameter.

[0007] By adopting the above technical solution, the tank mouth is identified from the on-site image data through the preset first algorithm, and its position and height are calculated, which provides an accurate basis for the subsequent precise adjustment of the position of the feeding tube, improves the accuracy of positioning, and reduces the error of manual judgment. According to the positive correlation of the tank mouth height data, the height parameter of the preset feeding position is adjusted, so that the feeding tube can better adapt to the tank mouth of vehicles with different heights, enhances the versatility and adaptability of the system, avoids the difficulty of alignment caused by the height difference of the tank mouth, and further improves the alignment efficiency. The distance difference and direction between the tank mouth position and the preset feeding position are calculated and output, which can provide clear guidance for the system to adjust the position of the feeding tube in real time, so that the feeding tube can move quickly and accurately to the tank mouth, effectively shorten the alignment time and improve work efficiency. After issuing the instruction to drive the feeding tube, the feeding tube graphics are identified based on the second algorithm, and its moving distance value and the data of coincidence with the contour of the tank mouth are calculated to ensure that the feeding tube is accurately aligned with the tank mouth. At the same time, the moving reference value is inversely correlated with the tank mouth height parameter, which realizes the precision control of the dynamic adjustment of the feeding tube movement according to the tank mouth height, and further guarantees the accuracy and efficiency of alignment. The system determines whether parking is successful based on the contour overlap data and gives corresponding prompts, which facilitates the operator to understand the alignment status in a timely manner. If parking fails, it can be adjusted in time, avoiding invalid operations and time waste, which helps to continuously optimize the alignment process and improve overall work efficiency.

[0008] Optionally, the method for acquiring the first image data comprises the following steps: Based on a camera device inclined toward the first target, collecting a first image at a frequency of N images per unit time; Calculate the coefficient of dispersion of the height data within a set time period; If the discrete coefficient is greater than a set threshold, the size of N is adjusted according to the discrete coefficient. The larger the discrete coefficient is, the larger N is; the smaller the discrete coefficient is, the smaller N is.

[0009] By adopting the above technical solution, the camera and the distance sensor are located on the industrial equipment and there is jitter. Data optimization is performed for jitter. The camera collects N images - the number of images collected per unit time, and then average filtering is performed; the value of N is adjusted by the data jitter of the distance sensor. The camera device is tilted to the first target (tank mouth) and collects images at a frequency of N frames per unit time. With the average filtering process, more stable image data can be obtained when the equipment is jittering. Collecting multiple images per unit time for average filtering can reduce problems such as image blur and deformation caused by jitter, improve image quality, provide a more reliable image basis for accurate identification of the tank mouth, help improve the positioning accuracy of the tank mouth based on image recognition, and ensure the accuracy of precise parking control. Using a laser ranging device tilted to the second target (discharging pipe), the height data is calculated based on the TOF algorithm by the time difference between the emission and reception of laser pulses. This method can obtain the height information of the tank mouth more accurately. In the jitter environment of industrial equipment, this method is relatively less affected by jitter, and provides accurate data support for the subsequent adjustment of the discharging pipe position according to the height of the tank mouth, which enhances the accuracy of height adjustment in precise parking control. Calculate the discrete coefficient of height data within the set time period, and adjust the image acquisition frequency N according to the discrete coefficient. When the discrete coefficient is greater than the set threshold, that is, the height data jitter is large, increase the N value and increase the number of images collected per unit time. In this way, more images can be collected for average filtering, further reducing the impact of jitter on the image, obtaining clearer and more accurate tank mouth images, and improving the accuracy of tank mouth recognition and positioning; on the contrary, when the discrete coefficient is small, reduce the N value, while ensuring image quality, avoid excessive image acquisition and waste of resources, and improve system operation efficiency. The image acquisition frequency N of the camera is adjusted by the data jitter of the distance sensor, realizing the coordinated optimization of image acquisition and distance measurement. In the complex environment of industrial equipment jitter, the system can adaptively adjust the working parameters to ensure the accuracy of image data and height data, improve the stability and reliability of the entire precision parking control system, which is conducive to ensuring that the feed pipe can be more efficiently and accurately aligned with the vehicle tank mouth, and improve the work efficiency of the slag micro powder delivery head.

[0010] Optionally, after acquiring the first image data, the method further comprises the following steps: Based on a preset dust and fog recognition algorithm, identifying target features from the first image; If the target feature is identified, an early warning prompt is issued and an emergency stop command is triggered, and the positioning information of the target feature is sent to the background terminal.

[0011] By adopting the above technical solution, unexpected situations such as dust emission may occur during the delivery process. The panoramic camera collects images of the entire delivery site for identification, and immediately stops the process when dust emission is detected without manual intervention. This can not only prevent the dust emission phenomenon from further deteriorating and avoid the expansion of dust pollution, but also effectively reduce the risk of equipment failure caused by accidents and protect the health of operators.

[0012] Optionally, based on a plurality of distance sensors horizontally facing the first target side wall, the method further comprises the following steps: If the first target pattern is identified, a set of lateral distance parameters measured by a plurality of distance sensors is obtained; A lateral fluctuation curve is fitted according to a set of lateral distance parameters, the lateral fluctuation curve is matched with a preset lateral distance curve for fluctuation amplitude, and the lateral curve matching degree is calculated; If the lateral curve matching degree is lower than a preset threshold, the target position is corrected according to a set of lateral distance parameters.

[0013] By adopting the above technical scheme, during the slag micro powder delivery process, the position of the vehicle tank mouth (first target) may be deviated or irregular. This technical scheme greatly improves the accuracy of the tank mouth position judgment and the stability of the delivery operation with the help of multiple distance sensors facing the side wall of the first target horizontally. After the first target figure is identified, a set of lateral distance parameters measured by multiple distance sensors are obtained, and these parameters can accurately reflect the lateral distance information of different positions of the tank mouth. Based on the fitted lateral fluctuation curve, the fluctuation amplitude is matched with the preset lateral distance curve and the lateral curve matching degree is calculated, which provides a quantitative basis for judging whether the actual position of the tank mouth meets the standard. If the lateral curve matching degree is lower than the preset threshold, it indicates that there is an abnormal deviation in the tank mouth position. At this time, the target position is corrected according to a set of lateral distance parameters, which can effectively correct the misjudgment caused by image blur; reduce the alignment errors caused by incorrect positioning, reduce the risk of material leakage, ensure the smooth progress of the delivery operation, avoid the waste of time and material loss caused by inaccurate judgment of the tank mouth position, and effectively improve the accuracy and reliability of the entire slag micro powder delivery process, ensuring the efficient and stable development of the delivery operation.

[0014] Optionally, the method for obtaining the height data of the first target comprises the following steps: Based on a plurality of distance sensors located on top of the first target and vertically downward; If the first target figure is identified, a set of vertical distance parameters measured by multiple distance sensors is obtained; Calculating the height data of the first target according to a set of vertical distance parameters; A vertical fluctuation curve is fitted according to a set of vertical distance parameters, and the vertical fluctuation curve is matched with a preset vertical distance curve in terms of fluctuation amplitude, and the vertical curve matching degree is calculated; If the vertical curve matching degree is lower than a preset threshold, the target position is corrected according to a set of vertical distance parameters.

[0015] By adopting the above technical solution, with the help of multiple distance sensors located at the top of the first target and vertically downward, the effect of improving the height measurement accuracy and ensuring the stability of the operation is remarkable. After the first target figure is identified, multiple distance sensors can quickly obtain a set of vertical distance parameters, which comprehensively and accurately reflect the vertical distance information from different positions on the top of the tank mouth to the ground. By calculating this set of parameters, the height data can be obtained to ensure the accuracy of the height measurement. At the same time, the vertical distance parameters are fitted into a vertical fluctuation curve, and the fluctuation amplitude is matched with the preset vertical distance curve to calculate the vertical curve matching degree, which provides a quantitative basis for judging the consistency and standardization of the tank mouth height. If the vertical curve matching degree is lower than the preset threshold, it means that the tank mouth may have abnormal conditions such as tilt or deformation. At this time, the target position is corrected according to the vertical distance parameter, which can effectively correct the positioning deviation of the delivery head caused by the abnormal tank mouth. This not only reduces the risk of material leakage during the delivery process, ensures the safety and cleanliness of the working environment, but also reduces the time waste caused by repeated adjustment of the delivery head position, greatly improves the loading efficiency, and ensures that the slag micro powder loading operation is carried out efficiently, accurately and stably.

[0016] Optionally, based on two pairs of laser distance measuring devices symmetrically arranged on both sides of the second target in different directions and tilted toward the first target, each pair of laser distance measuring devices includes two groups of mutually symmetrical laser distance measuring devices, and the method includes the following steps: Obtaining the time difference between the emission and reception of each laser pulse in each group of laser ranging devices, and calculating the height data of each laser ranging device from the first target based on the time difference and a preset algorithm, so as to obtain two groups of height data for each pair; The matching degree of the two sets of height data in each pair of laser ranging devices is calculated. If the matching degree is greater than a preset reference value, an instruction to drive the second target is issued.

[0017] By adopting the above technical solution, two sets of laser distance measuring devices symmetrically arranged on both sides of the delivery head and tilted toward the tank mouth provide a reliable guarantee for achieving this goal. By obtaining the time difference between the emission and reception of each laser pulse in each set of laser distance measuring devices, the height data of each device and the tank mouth can be accurately calculated according to the preset algorithm, and then two sets of height data can be obtained. This method of measuring multiple sets of data effectively avoids the measurement error that may be generated by a single device and greatly improves the accuracy of the height data. Then the matching degree of the two sets of height data is calculated. When the matching degree is greater than the preset reference value, it means that the measurement data on both sides are highly consistent, reflecting the accuracy and stability of the height position of the tank mouth. At this time, an instruction to drive the delivery head is issued. This process ensures that the height position of the tank mouth has been accurately obtained and meets the operating requirements before the delivery head moves, effectively reducing the risk of alignment errors caused by blind movement of the delivery head. It not only ensures the smoothness of material transmission during delivery and reduces the pollution of the working environment caused by material leakage, but also avoids the waste of time caused by repeated adjustment of the delivery head position, greatly improving the overall efficiency of slag micro powder loading operations.

[0018] Optionally, the method further comprises the following steps: Acquiring noise parameters, and performing frequency analysis on the noise parameters; If a characteristic frequency is extracted from the noise parameter, an energy value of the characteristic frequency is calculated; The size of N is adjusted according to the positive correlation of the energy value. The larger the energy value, the larger the N, and the smaller the energy value, the smaller the N; And the cleaning time is adjusted in positive correlation with the energy value. The larger the energy value is, the longer the cleaning time is, and the smaller the energy value is, the shorter the cleaning time is.

[0019] By adopting the above technical solution, the system adjusts N (image acquisition frequency) according to the positive correlation of energy value. When the vehicle brakes frequently, that is, the energy value is large, the N value is increased to increase the number of image acquisitions per unit time. The advantage of this is that when the frequent movement of the vehicle causes the image to be easily blurred, jittered and other interferences, more image acquisitions and processing methods such as average filtering can effectively remove the image interference caused by the movement of the vehicle, significantly improve the clarity and stability of the image, and provide a more reliable and accurate image data basis for the subsequent accurate identification of the position of the tank mouth (first target) of the vehicle, effectively guarantee the accuracy of the alignment between the shipping head (second target) and the tank mouth, avoid alignment errors caused by poor image quality, and improve the accuracy of loading operations. At the same time, the system adjusts the cleaning time according to the positive correlation of the energy value. Frequent braking of the vehicle may raise more dust, resulting in an increase in pollutants in the working environment. When the energy value is larger, that is, the braking is more frequent, the cleaning time is extended. This can timely and effectively clean dust and other pollutants attached to the surface of laser distance measuring devices, camera devices and other equipment and optical components, prevent pollutants from having adverse effects on equipment performance, ensure that the laser distance measuring device can accurately measure the tank mouth height data, and the camera device can clearly collect image data, maintain the accuracy of the height data measurement of the entire system and image acquisition and recognition, and ensure that the equipment is always in good operating condition. Through the clever use of the characteristic frequency of vehicle braking sound and its energy value, dynamic and intelligent adjustment of image acquisition frequency and equipment cleaning time is achieved, so that the entire slag micro powder loading system can better adapt to complex and changeable operating scenarios, effectively improve the stability, accuracy and efficiency of loading operations, reduce the risk of operational errors caused by difficult vehicle position adjustment and environmental interference, and comprehensively optimize the loading operation process.

[0020] In the second aspect, the present application provides a precise parking control system based on the Internet of Things, which adopts the following technical solutions: A precise parking control system based on the Internet of Things comprises a processor, wherein the processor executes the steps of any one of the precise parking control methods based on the Internet of Things described above.

[0021] In a third aspect, the present application provides a storage medium, which adopts the following technical solution: A storage medium stores a program, wherein the program, when executed by a processor, implements the steps of any one of the above-mentioned methods for precise parking control based on the Internet of Things.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: Precisely locate the tank mouth: The preset first algorithm is used to identify the tank mouth from the on-site image data and calculate its position and height, providing an accurate basis for the subsequent precise adjustment of the feed pipe position, improving the positioning accuracy and reducing the error of manual judgment.

[0023] Adaptive height adjustment: The height parameters of the preset unloading position are adjusted in a positive correlation according to the tank mouth height data, so that the unloading pipe can better adapt to the tank mouths of vehicles with different heights, enhancing the versatility and adaptability of the system, avoiding the difficulty of alignment caused by the difference in tank mouth height, and further improving the alignment efficiency.

[0024] Real-time guidance for alignment: The distance difference and direction between the tank opening and the preset unloading position are calculated and output, which can provide clear guidance for the system to adjust the unloading pipe position in real time, so that the unloading pipe can move to the tank opening quickly and accurately, effectively shortening the alignment time and improving work efficiency.

[0025] Precisely control the movement of the feeding tube: After issuing the instruction to drive the feeding tube, the feeding tube pattern is identified based on the second algorithm, and its moving distance value and the data of coincidence with the contour of the tank mouth are calculated to ensure that the feeding tube is accurately aligned with the tank mouth. At the same time, the moving reference value is inversely related to the tank mouth height parameter, realizing the precision control of the feeding tube movement dynamically adjusted according to the tank mouth height, further ensuring the accuracy and efficiency of the alignment.

[0026] Timely feedback of parking results: The system determines whether parking is successful based on the contour overlap data and gives corresponding prompts, so that operators can understand the alignment status in time. If parking fails, adjustments can be made in time to avoid invalid operations and time waste, which helps to continuously optimize the alignment process and improve overall work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a step diagram of a precise parking control method based on the Internet of Things.

[0028] Figure 2 It is a schematic diagram of the positional relationship between a plurality of distance sensors horizontally facing the first target side wall and the side of the vehicle.

[0029] Figure 3 It is a schematic diagram of the relationship between the positions of multiple distance sensors located on the top of the first target and pointing vertically downward and the roof.

[0030] Figure 4 The figure is a schematic diagram of the position relationship between two pairs of laser distance measuring devices symmetrically arranged on both sides of the second target in different directions and tilted toward the first target and the roof.

[0031] Figure 5 The diagram is a schematic diagram of the positional relationship between two pairs of laser distance measuring devices symmetrically arranged at both sides of a second target in different directions and tilted toward a first target and the side of a vehicle. DETAILED DESCRIPTION

[0032] Embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings.

[0033] In the description of this specification, the description with reference to the terms "certain embodiments", "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples" or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0034] The present application embodiment discloses a precise parking control method based on the Internet of Things, referring to Figure 1 , including the following steps: The first image data and the marked position are obtained in real time. The first image data here refers to the on-site image captured by the camera. For example, at the slag powder loading site, the image will present information such as the vehicle and the surrounding environment; and the marked position is the pre-set unloading position.

[0035] The first image data is processed based on the first algorithm to identify the first target graphic. In the actual scenario, the first target graphic is the tank opening on the top of the vehicle for unloading slag. When the tank opening is successfully identified, its graphic position is calculated and determined as the target position.

[0036] The height data of the first target (tank opening) is obtained through the distance sensor. For example, the tank opening heights of different models of vehicles may be different, and the distance sensor can accurately measure the specific heights. Then, based on this height data, the height parameters of the marked position are adjusted in a positive correlation. For example, if the tank opening height is higher, the height of the marked position is increased accordingly.

[0037] Calculate the position distance value between the target position (tank mouth position) and the marked position (unloading position). This distance value is the actual distance between the tank mouth position and the unloading position. If the position distance value is greater than or equal to the distance reference value, then further calculate the distance difference between the position distance value and the distance reference value, and calculate the position direction between the target position and the marked position, and output the distance difference and position direction. In this way, the system can clearly determine the distance and direction that the unloading pipe needs to be adjusted.

[0038] If the position distance value is less than the preset distance reference value, an instruction to drive the second target (feeding tube) is issued. Then, based on the preset second algorithm, the second target figure, that is, the figure of the feeding tube, is identified from the first image data. When the feeding tube figure is identified, its moving distance value is calculated. If the moving distance value is greater than the preset moving reference value, the contour coincidence data of the second target figure and the first target figure is calculated.

[0039] The parking success is judged based on the contour overlap data. If the contour overlap data is within the preset contour overlap range, it indicates that the parking is successful; otherwise, it indicates that the parking is unsuccessful. It should be noted that the moving reference value is inversely correlated with the height parameter.

[0040] The preset first algorithm identifies the tank mouth from the on-site image data, and calculates its position and height, providing an accurate basis for the subsequent precise adjustment of the position of the feeding tube, greatly improving the accuracy of positioning and reducing the errors that may be caused by manual judgment. The height parameters of the preset feeding position are adjusted according to the positive correlation of the tank mouth height data, so that the feeding tube can better adapt to the tank mouths of vehicles with different heights, enhancing the versatility and adaptability of the system, avoiding the difficulty of alignment caused by the height difference of the tank mouth, and further improving the alignment efficiency. The distance difference and direction between the tank mouth position and the preset feeding position are calculated and output, which can provide clear guidance for the system to adjust the position of the feeding tube in real time, so that the feeding tube can move quickly and accurately toward the tank mouth, effectively shortening the alignment time and improving work efficiency. After issuing the instruction to drive the feeding tube, the feeding tube graphics are identified based on the second algorithm, and its moving distance value and the data of coincidence with the contour of the tank mouth are calculated to ensure that the feeding tube can be accurately aligned with the tank mouth. At the same time, the moving reference value is inversely correlated with the tank mouth height parameter, which realizes the precision control of the feed tube movement according to the tank mouth height, further ensuring the accuracy and efficiency of the alignment. The parking success is judged based on the contour overlap data and corresponding prompts are given, which facilitates the operator to understand the alignment situation in time. If the parking fails, it can be adjusted in time, avoiding invalid operations and time waste, which helps to continuously optimize the alignment process and comprehensively improve the overall work efficiency.

[0041] Considering that the industrial equipment on which the camera and the distance sensor rely often has a jitter phenomenon, the method for obtaining the first image data includes the following steps: The image acquisition operation is carried out based on a camera device tilted toward the first target (tank mouth). The camera device acquires the first image at a frequency of N images per unit time. In the actual slag powder loading site, the jitter of the equipment is complex and changeable. For example, the engine operation of the transport vehicle will produce continuous low-frequency vibration, and the mechanical collision during loading and unloading of materials will cause instantaneous high-frequency jitter. Faced with such a complex jitter environment, the camera collects N images per unit time and then performs average filtering. The core principle is that among the multiple images collected per unit time, the degree and direction of jitter influence on each image are different. For example, a certain image may be blurred and displaced on the left edge of the tank mouth due to the instantaneous jitter of the equipment to the left; while another image may be taken when the equipment is jittering to the right, and similar problems may occur on the right edge of the tank mouth. Through average filtering, the pixel information of these images is comprehensively averaged, which can offset the adverse effects of image blurring, deformation, etc. caused by jitter. After such processing, the final generated image can restore the true shape of the tank mouth to the greatest extent, greatly improving the image quality. High-quality images provide a solid and reliable foundation for the subsequent accurate identification of the tank mouth, which helps to significantly improve the accuracy of tank mouth positioning based on image recognition, thereby effectively ensuring the accuracy of precise parking control.

[0042] In terms of height data acquisition, a laser ranging device tilted to the second target (feeding pipe) is used, and the height data is calculated by accurately measuring the time difference between the emission and reception of laser pulses with the help of TOF algorithm (Time of Flight). In the harsh environment of industrial equipment jitter, this measurement method shows excellent anti-interference performance. Unlike some traditional measurement methods that rely on physical contact or are greatly affected by ambient light and air flow, the TOF algorithm uses the characteristics that the propagation speed of laser pulses in a vacuum is constant and is almost unaffected by general environmental factors. Even if the industrial equipment shakes violently during operation, the laser pulses emitted by the laser ranging device can still reach the tank mouth at a stable speed and accurately reflect back to the receiving end. Through the high-precision measurement of the time difference, the tank mouth height information can be obtained more accurately. Taking the loading of slag micro powder as an example, no matter how the equipment shakes, the laser pulse can stably complete the round trip, ensuring that the measured height data is relatively less affected by the jitter. This provides key data support for the subsequent precise adjustment of the feeding pipe position according to the height of the tank mouth, and significantly enhances the accuracy of height adjustment in precise parking control.

[0043] In addition, in order to further optimize the image acquisition process, the system also introduces the calculation link of the discrete coefficient of height data within the set time period. As an important indicator to measure the degree of data discreteness, the discrete coefficient plays an indispensable role in this system. When the calculated discrete coefficient is greater than the set threshold, it clearly shows that the jitter degree of height data within the set time period is relatively severe. At this time, in order to obtain a more stable and clear tank mouth image in a complex jittering environment, the system will dynamically adjust the N value according to the discrete coefficient, which is specifically manifested as the larger the discrete coefficient, the larger the N value. For example, if the discrete coefficient far exceeds the set threshold, it means that the device jitters extremely violently, which has a great impact on the image acquisition quality. In this case, the N value is greatly increased, so that the number of images collected per unit time is significantly increased. More images participate in the subsequent average filtering process, just like selecting the information that best reflects the true shape of the tank mouth from more samples. Through multiple averaging and screening, the impact of jitter on the image can be further reduced, so as to obtain a clearer and more accurate tank mouth image, which effectively improves the accuracy of tank mouth recognition and positioning. On the contrary, when the discrete coefficient is small, it means that the height data is relatively stable and the impact of equipment jitter on image acquisition is within an acceptable range. In this case, the N value should be reduced. This can not only ensure that the image quality meets the basic requirements of can mouth recognition, but also avoid a series of problems caused by excessive image acquisition, such as large occupation of storage resources, tight data transmission bandwidth, and slow data processing speed, thereby effectively improving the overall operating efficiency of the system.

[0044] The image acquisition frequency N of the camera is dynamically adjusted through the data jitter of the distance sensor, realizing the deep collaborative optimization of the two key links of image acquisition and distance measurement. In the complex environment of industrial equipment jitter, the system can perceive the jitter changes of the distance sensor data in real time, respond quickly, and adaptively adjust the image acquisition frequency of the camera. When the equipment jitters violently, the system detects that the discrete coefficient of the distance sensor data increases, and then automatically increases the N value, increases the image acquisition frequency, and obtains more images to counteract the impact of jitter on image quality; when the equipment jitters less, the discrete coefficient decreases, and the system correspondingly reduces the N value and reduces the image acquisition frequency. This adaptive adjustment mechanism enables the system to always ensure the accuracy of image data and height data under different jitter conditions. Through this collaborative optimization, the stability and reliability of the entire precision parking control system are greatly improved, laying a solid foundation for ensuring that the feeding pipe can be more efficiently and accurately aligned with the vehicle tank mouth, and ultimately achieving the goal of improving the working efficiency of the slag micro powder delivery head, helping industrial production operations to run more efficiently and stably.

[0045] During the delivery of slag powder, the on-site environment is complex and changeable, and various unexpected situations occur from time to time. After successfully acquiring the first image data, the system will further conduct an in-depth and detailed analysis of the first image based on the preset dust and fog recognition algorithm, aiming to accurately identify specific target features from it.

[0046] The dust and fog recognition algorithm has been designed and trained with a large amount of data, and has powerful image analysis capabilities. It can keenly capture the subtle features related to abnormal phenomena such as dust emission in the image, such as the shape of dust diffusion, grayscale differences caused by concentration changes, and specific texture structures. Through accurate analysis and comparison of these features, the algorithm can quickly determine whether there are target features corresponding to unexpected situations such as dust emission in the image.

[0047] Once the algorithm successfully identifies the target features, the system will immediately initiate a series of efficient and automated response measures. First, a sharp and eye-catching early warning prompt is issued, and through various means such as sound and light alarms, it ensures that the workers at the operation site can detect abnormal conditions at the first time. At the same time, the emergency stop command is quickly triggered to immediately stop the ongoing delivery operation process. This emergency stop command will be transmitted to the control system of the relevant equipment at a speed of milliseconds, so that the running parts of the equipment will be quickly braked to prevent the dust emission phenomenon from further deteriorating due to the continuous operation of the equipment, effectively curbing the expansion of dust pollution.

[0048] The system will also accurately send the positioning information of the target features to the back-end terminal. This positioning information is accurate to the specific coordinates of the dust emission phenomenon in the image of the delivery site. The back-end staff can intuitively see the exact location where the dust emission occurs through special monitoring software. With this precise positioning, the staff can quickly determine the source of the dust emission and promptly organize professional maintenance personnel to rush to the site for investigation and treatment, greatly shortening the troubleshooting time and improving the efficiency of problem solving.

[0049] During the delivery process, the occurrence of unexpected situations such as dust emission will not only cause serious pollution to the working environment, but may also trigger a series of chain reactions. A large amount of diffused dust can easily enter the precision parts of the equipment, accelerate equipment wear, and increase the risk of equipment failure. The panoramic camera collects all-round images of the entire delivery site, and uses the dust and fog recognition algorithm for intelligent recognition. Once the dust emission phenomenon is detected, it will automatically stop immediately without manual intervention. This automated mechanism is like a guard who is always vigilant and can respond quickly at the moment of an accident. It can not only prevent the dust emission phenomenon from further deteriorating in time, avoid the spread of dust pollution in the working area, and create a cleaner and safer working environment, but also effectively reduce the risk of equipment failure caused by accidents, extend the service life of the equipment, and reduce the cost of equipment maintenance. More importantly, it greatly protects the health of the operators, reduces the risk of respiratory diseases, pneumoconiosis and other occupational diseases caused by excessive dust inhalation, fully reflects the care and attention to the life and health of the workers, and provides a solid and powerful guarantee for the safe, stable and efficient operation of slag micro powder delivery operations.

[0050] Reference Figure 2 In the actual operation scenario of slag powder delivery, the position of the vehicle tank mouth (i.e., the first target) is often complex and changeable. Due to factors such as angle deviation and uneven ground when the vehicle is parked, the tank mouth position may deviate. This application is based on multiple distance sensors facing the side wall of the first target horizontally, and the method also includes the following steps: Once the system recognizes the first target pattern, that is, the pattern of the tank mouth of the vehicle, it will obtain a set of lateral distance parameters measured by multiple distance sensors. These distance sensors are evenly distributed around the tank mouth, facing horizontally towards the side wall of the tank mouth, and can accurately measure the lateral distance between themselves and different positions of the tank mouth. For example, in a large slag micro powder shipping yard, a transport vehicle is equipped with 3×9 matrix-distributed distance sensors around the tank mouth, and each sensor can provide real-time feedback on the lateral distance data of its corresponding position with the tank mouth.

[0051] According to this set of lateral distance parameters, a lateral fluctuation curve is fitted, which can reflect the curve of the lateral distance change trend of the can mouth. This curve intuitively shows the shape characteristics and position changes of the can mouth in the lateral direction. The fluctuation amplitude of this lateral fluctuation curve is matched with the preset lateral distance curve, and the lateral curve matching degree is calculated. The preset lateral distance curve is an ideal curve pre-set according to the standard can mouth shape and position, which represents the standard state that the can mouth should present. By comparing the fluctuation amplitudes of the two, a specific value can be obtained, namely the lateral curve matching degree, which can determine whether the actual position of the can mouth is consistent with the position in image recognition.

[0052] If the calculated lateral curve matching degree is lower than the preset threshold, it indicates that there is an abnormal deviation in the position of the tank mouth. This indicates that the result of image recognition deviates from the data of the distance sensor, which may be caused by problems such as image jitter when the vehicle is parked. At this time, the system will correct the target position based on this set of lateral distance parameters. For example, if the lateral distance parameters show that the tank mouth is offset to the right by a certain distance in the horizontal direction, the system will move the target position determined by image recognition to the right by the same distance in the horizontal direction to match it with the actual position of the tank mouth. The data measured by the distance sensor is generally faster than the result of image recognition. Compared with the time delay of image processing, the results of the sensor are also more accurate and timely. Therefore, the combination of the data of the two is more conducive to improving the accuracy of the data.

[0053] The system will correct the target position based on this set of lateral distance parameters. The specific steps are as follows: Preprocess the lateral distance parameters measured by multiple distance sensors. Since the sensor may be affected by environmental interference and other factors and produce certain measurement errors, it is necessary to filter the data, such as using mean filtering, median filtering and other methods to remove abnormal data points to make the distance parameters more accurate and reliable. At the same time, according to the installation position and distribution law of the sensor, the measurement data of each sensor is converted into coordinates and unified into a standard coordinate system for subsequent analysis.

[0054] Compare the pre-processed lateral distance parameters with the preset standard distance parameters (corresponding to the preset lateral distance curve). For each distance sensor's measured value, calculate the difference between it and the standard value to obtain the deviation value of each position point. These deviation values ​​reflect the difference between the actual position of the tank mouth and the standard position at different points. Through the comprehensive analysis of all deviation values, the overall position deviation direction and approximate amplitude of the tank mouth can be determined.

[0055] Based on the calculated deviation value, the system determines the correction direction and amplitude of the target position. If most of the deviation values ​​show that the tank mouth is offset to the left in the horizontal direction, then the correction direction is to the right; the average size of the deviation value determines the size of the correction amplitude. In order to determine the correction amplitude more accurately, the system may use a weighted average method to assign different weights to the deviation values ​​at different positions, because the deviation at different positions of the tank mouth may have different effects on the overall position.

[0056] After determining the correction direction and amplitude, the system performs correction operations on the target position. This may involve adjusting the target position coordinates in the image recognition system, or modifying the control parameters related to the target position. For example, in a system that automatically controls the alignment of the slag powder conveying pipeline with the tank mouth, the horizontal and vertical position parameters of the conveying pipeline are adjusted according to the corrected target position information so that it can accurately align with the tank mouth.

[0057] After correcting the target position, the system will monitor the measurement data of the distance sensor in real time and recalculate the lateral curve matching degree. If the matching degree is still lower than the preset threshold, it means that the correction effect is not ideal. The system will recalculate the deviation and make corrections based on the new measurement data until the lateral curve matching degree reaches the preset requirements. In this process, the system will continuously provide feedback and make adjustments to ensure the accuracy of the target position.

[0058] The system will record the relevant information of each correction, including the target position before correction, the lateral distance parameters based on which the correction is made, the direction and magnitude of the correction, and the final target position after correction, etc. This information can be used for subsequent data analysis and system optimization to continuously improve the accuracy and efficiency of target position correction.

[0059] This application is based on multiple distance sensors facing horizontally toward the first target side wall, which improves the accuracy of judging the position of the can mouth and the stability of the delivery operation. When the system recognizes the first target graphic, a set of lateral distance parameters obtained can accurately reflect the lateral distance information of different positions of the can mouth, providing a solid data foundation for subsequent accurate judgment and correction. The lateral fluctuation curve fitted based on these parameters and the lateral curve matching degree obtained by matching and calculating the preset curve make it possible to accurately judge whether the can mouth position is accurately identified in a quantitative manner. In this way, the alignment operation can be completed quickly and accurately, improving the work efficiency. In addition, reducing material losses means reducing production costs and improving the economic benefits of the enterprise.

[0060] Reference Figure 3 In the slag powder loading operation scenario, accurately obtaining the height data of the vehicle tank mouth (the first target) is crucial to achieve accurate docking between the shipping head and the tank mouth and to ensure the smooth progress of the operation. The solution uses multiple distance sensors located at the top of the first target and pointing vertically downward to complete the acquisition and related processing of height data; the method for obtaining the height data of the first target includes the following steps: In the actual operation site, such as a large slag powder loading workshop, multiple distance sensors will be installed on the top of the tank mouth of each vehicle to be loaded, and these sensors are regularly distributed. Assuming a common tank truck, 5 distance sensors are evenly installed on the top of the tank mouth, located at the front, rear, left, right and center of the top of the tank mouth. When the system recognizes the first target figure, that is, the figure of the tank mouth of the vehicle, these 5 distance sensors will start working quickly. They use their own measurement principles, such as laser ranging or ultrasonic ranging technology, to transmit signals downward and measure the time from the transmission to the reception of the signal, and then quickly obtain a set of vertical distance parameters. For example, the front sensor measured 3.5 meters from the ground, 3.48 meters at the rear, 3.51 meters on the left, 3.52 meters on the right, and 4.5 meters at the center. The large height indicates that the irradiation enters the inside of the tank mouth. This set of vertical distance parameters comprehensively and accurately reflects the vertical distance information from different positions on the top of the tank mouth to the ground.

[0061] This set of vertical distance parameters is calculated. The calculation method can be a simple average calculation method. The data is first screened, and the distance values ​​measured by the four sensors are added and divided by 4, that is, (3.5+3.48+3.51+3.52)÷4=3.502 meters. This result is the height data of the first target obtained by calculation, ensuring the accuracy of the height measurement.

[0062] In actual calculation, the number of distance sensors is not simply 5, but a larger number, mainly concentrated near the feeding pipe, and the data irradiated into the inside of the tank mouth does not participate in the calculation of the tank mouth height data. In this embodiment, 5 are used as an example only for the convenience of example calculation.

[0063] At the same time, the system will fit this set of vertical distance parameters into a vertical fluctuation curve, which can intuitively show the height changes at different positions on the top of the tank mouth. After that, the vertical fluctuation curve is matched with the preset vertical distance curve in terms of fluctuation amplitude. The preset vertical distance curve is set in advance based on the height characteristics of the standard tank mouth, and it represents the ideal state that the tank mouth height should present. By comparing the fluctuation amplitudes of the two curves, the system uses a specific mathematical formula to calculate the vertical curve matching degree. For example, after calculation, the vertical curve matching degree is 98%.

[0064] If the vertical curve matching degree is lower than the preset threshold, for example, the preset threshold is 96%, and the actual calculated matching degree is only 85%, this means that the image recognition of the tank mouth may deviate from the actual sensor measurement. In this case, the system will correct the target position based on the vertical distance parameter.

[0065] The above solution effectively reduces the risk of material leakage during the delivery process. In the past, due to the abnormality of the can mouth, the delivery head was not positioned accurately, and the material leaked into the working environment, which not only caused material waste, but also polluted the working site. After adopting this solution, the material leakage was greatly reduced, ensuring the safety and cleanliness of the working environment. At the same time, it reduces the time wasted due to repeated adjustment of the delivery head position.

[0066] Reference Figure 4 and Figure 5 In the slag powder loading operation, ensuring that the delivery head (second target) can accurately align with the height position of the vehicle tank mouth (first target) is crucial for efficient and safe material loading. Based on this, this solution uses two pairs of laser distance measuring devices that are symmetrically set on both sides of the delivery head in different directions and tilted toward the tank mouth. Each group has multiple laser distance measuring devices, which are concentrated near the feeding pipe, to build a highly accurate position measurement and operation control system. The specific steps are as follows: The time difference between emission and reception of each laser pulse in each group of laser ranging devices is obtained, and the height data of each laser ranging device from the first target is calculated based on the time difference based on a preset algorithm, so that each pair of laser ranging devices obtains two sets of height data.

[0067] The matching degree of the two sets of height data in each pair of laser ranging devices is calculated. If the matching degree is greater than the preset reference value, it means that the two sets of data in each pair of data are symmetrical, which means that the data in different directions symmetrical to the direction of the tank mouth are consistent. It can be concluded that the position of the tank mouth is directly below the discharge pipe, and an instruction to drive the second target is issued to drive the discharge pipe downward.

[0068] In the complex operation scenario of loading slag powder, environmental factors have a significant impact on the accuracy and stability of the operation process. In order to effectively cope with these challenges, this system introduces a set of intelligent adjustment mechanisms based on noise parameter analysis. The specific steps and functions are as follows: Real-time acquisition of noise parameters at the work site. At the slag powder loading site, various mechanical equipment are running, vehicles are shuttling back and forth, and the noise sources are complex. The system uses professional noise collection equipment, such as a high-sensitivity microphone array, to collect these noise signals in all directions and convert them into electrical signal parameters for analysis.

[0069] Conduct in-depth frequency analysis on the acquired noise parameters. Use advanced Fourier transform and other algorithms to convert the noise signal in the time domain to the frequency domain, clearly presenting the distribution of noise at different frequencies. In this process, carefully identify the noise spectrum and try to capture characteristic frequencies with special significance. For example, the characteristic frequency is the braking sound when the vehicle stops. Since the brakes of the freight truck are driven by air pressure, gas will be sprayed when the truck stops, which will cause the flow of gas in the space, thus increasing the disturbance frequency of dust particles.

[0070] Once the characteristic frequency is successfully extracted from the noise parameters, the system will immediately calculate the energy value of the characteristic frequency. In actual scenarios, for example, the braking sound generated when the vehicle repeatedly adjusts its position will show specific frequency characteristics in the noise spectrum. When braking, the brake pads and brake discs rub violently, and the sound generated has a relatively concentrated frequency range. The signal corresponding to this frequency range will show a higher energy value in the frequency domain. The system calculates the energy value of this characteristic frequency through precise mathematical operations. The size of this energy value directly reflects the frequency of braking behavior.

[0071] Based on the calculated energy value, the system makes positive correlation adjustments to two key parameters. One is N, which is the image acquisition frequency. When the vehicle brakes frequently, it means that the energy value is large. For example, in a busy loading area, the vehicle frequently brakes and adjusts its position in order to accurately park under the shipping head. At this time, the energy value of the characteristic frequency of the brake sound in the noise increases significantly. In this case, the system automatically increases the N value and increases the number of images collected per unit time. Assuming that 10 images were originally collected per unit time, when the energy value increases to a certain extent, the N value can be increased to 20. The advantage of this is that when the frequent movement of the vehicle causes the image to be easily blurred, jittered, and other interferences, by collecting more images and combining image processing methods such as average filtering, the redundant information between images can be fully utilized. The images collected at different times have different directions and degrees of blur and jitter. After averaging these images, the interference can be effectively offset, significantly improving the clarity and stability of the image. The high-quality images provide a more reliable and accurate image data basis for the subsequent precise identification of the position of the vehicle tank mouth (the first target), effectively ensuring the accuracy of the alignment between the shipping head (the second target) and the tank mouth, effectively avoiding alignment errors caused by poor image quality, and greatly improving the accuracy of loading operations.

[0072] The system adjusts the cleaning time according to the positive correlation of the energy value. Frequent braking of the vehicle will raise a lot of dust, which will cause a sharp increase in pollutants in the working environment. When the energy value is larger, that is, the braking is more frequent, the dust concentration at the work site will increase significantly. At this time, the system automatically extends the cleaning time. For example, under normal circumstances, the laser rangefinder, camera device and other equipment are cleaned once every hour. When the energy value of the characteristic frequency of the brake sound continues to be high, the cleaning time interval may be shortened to 30 minutes. This measure can timely and effectively clean dust and other pollutants attached to the surface of the equipment and optical components. If dust and other pollutants are attached to key parts such as the transmitting and receiving windows of the laser rangefinder and the lens of the camera device for a long time, it will seriously affect the performance of the equipment. For the laser rangefinder, dust may cause the laser signal to scatter and attenuate, which greatly reduces the accuracy of the tank mouth height measurement data; for the camera device, dust will reduce the lens transmittance, causing the image to be blurred and the contrast to decrease. By extending the cleaning time, it is ensured that the laser ranging device can accurately measure the tank mouth height data, and the camera device can clearly collect image data, thereby maintaining the accuracy of the height data measurement, image acquisition and recognition of the entire system, ensuring that the equipment is always in good operating condition.

[0073] By cleverly utilizing the characteristic frequency and energy value of vehicle braking sound, the system realizes dynamic and intelligent adjustment of image acquisition frequency and equipment cleaning time. This intelligent adjustment mechanism enables the entire slag micro-powder loading system to better adapt to complex and changeable operating scenarios, effectively improves the stability, accuracy and efficiency of loading operations, reduces the risk of operational errors caused by difficulties in adjusting vehicle positions and environmental interference, comprehensively optimizes the loading operation process, and provides a strong guarantee for the efficient and accurate loading of slag micro-powder.

[0074] The embodiment of the present application further discloses a precise parking control system based on the Internet of Things, including a processor, wherein the processor executes the steps of any one of the precise parking control methods based on the Internet of Things described above.

[0075] The embodiment of the present application further discloses a storage medium, in which a program is stored. When the program is executed by a processor, the steps of any one of the above-mentioned precise parking control methods based on the Internet of Things are implemented.

[0076] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A precise parking control method based on the Internet of Things, characterized in that: The steps include: Acquire first image data and mark position; Identifying a first target graphic corresponding to a first target from the first image data based on a preset first algorithm; If the first target graphic is identified, the graphic position of the first target graphic is calculated as the target position; Acquire height data of the first target, and adjust the height parameter of the marking position in a positive correlation according to the height data; Calculating a position distance value between the target position and the marked position; If the position distance value is greater than or equal to the distance reference value, then calculating the distance difference between the position distance value and the distance reference value, calculating the position direction between the target position and the mark position, and outputting the distance difference and the position direction; If the position distance value is less than a preset distance reference value, issuing an instruction to drive the second target; Identifying a second target graphic from the first image data based on a preset second algorithm; If the second target graphic is identified, a moving distance value of the second target graphic is calculated, and if the moving distance value is greater than a preset moving reference value, contour coincidence data of the second target graphic and the first target graphic is calculated; If the contour overlap data is within a preset contour overlap range, it indicates that the parking is successful; otherwise, it indicates that the parking is unsuccessful, wherein the movement reference value is inversely correlated with the height parameter.

2. The precise parking control method based on the Internet of Things according to claim 1 is characterized in that: The method for acquiring first image data comprises the following steps: Based on a camera device inclined toward the first target, collecting a first image at a frequency of N images per unit time; Calculate the coefficient of dispersion of the height data within a set time period; If the discrete coefficient is greater than the set threshold, the size of N is adjusted according to the discrete coefficient, and the larger the discrete coefficient, the larger the N; The smaller the dispersion coefficient is, the smaller N is.

3. The precise parking control method based on the Internet of Things according to claim 2 is characterized in that: After acquiring the first image data, the method further comprises the following steps: Based on a preset dust and fog recognition algorithm, identifying target features from the first image; If the target feature is identified, an early warning prompt is issued and an emergency stop command is triggered, and the positioning information of the target feature is sent to the background terminal.

4. The precise parking control method based on the Internet of Things according to claim 2 is characterized in that: Based on a plurality of distance sensors horizontally facing the first target side wall, the method further comprises the following steps: If the first target pattern is identified, a set of lateral distance parameters measured by a plurality of distance sensors is obtained; A lateral fluctuation curve is fitted according to a set of lateral distance parameters, the lateral fluctuation curve is matched with a preset lateral distance curve for fluctuation amplitude, and the lateral curve matching degree is calculated; If the lateral curve matching degree is lower than a preset threshold, the target position is corrected according to a set of lateral distance parameters.

5. The precise parking control method based on the Internet of Things according to claim 2 is characterized in that: The method for obtaining the height data of the first target comprises the following steps: Based on a plurality of distance sensors located on top of the first target and vertically downward; If the first target figure is identified, a set of vertical distance parameters measured by multiple distance sensors is obtained; Calculating the height data of the first target according to a set of vertical distance parameters; A vertical fluctuation curve is fitted according to a set of vertical distance parameters, and the vertical fluctuation curve is matched with a preset vertical distance curve in terms of fluctuation amplitude, and the vertical curve matching degree is calculated; If the vertical curve matching degree is lower than a preset threshold, the target position is corrected according to a set of vertical distance parameters.

6. The precise parking control method based on the Internet of Things according to claim 2 is characterized in that: Based on two pairs of laser distance measuring devices symmetrically arranged on both sides of the second target in different directions and tilted toward the first target, each pair of laser distance measuring devices includes two sets of mutually symmetrical laser distance measuring devices, and the method includes the following steps: Obtaining the time difference between the emission and reception of each laser pulse in each group of laser ranging devices, and calculating the height data of each laser ranging device from the first target based on the time difference and a preset algorithm, so as to obtain two groups of height data for each pair; The matching degree of the two sets of height data in each pair of laser ranging devices is calculated. If the matching degree is greater than a preset reference value, an instruction to drive the second target is issued.

7. The precise parking control method based on the Internet of Things according to claim 2 is characterized in that: The method further comprises the steps of: Acquiring noise parameters, and performing frequency analysis on the noise parameters; If a characteristic frequency is extracted from the noise parameter, an energy value of the characteristic frequency is calculated; The size of N is adjusted according to the positive correlation of the energy value. The larger the energy value, the larger the N, and the smaller the energy value, the smaller the N; And the cleaning time is adjusted in positive correlation with the energy value. The larger the energy value is, the longer the cleaning time is, and the smaller the energy value is, the shorter the cleaning time is.

8. A precise parking control system based on the Internet of Things, characterized in that: The method comprises a processor, wherein the processor executes the steps of the precise parking control method based on the Internet of Things as described in any one of claims 1 to 7.

9. A storage medium, characterized in that: The medium stores a program, and when the program is executed by the processor, the steps of the precise parking control method based on the Internet of Things described in any one of claims 1 to 7 are implemented.

Images