Remote monitoring method and system for weighing sensor based on Internet of Things

Abstract

The present application relates to the field of weighing sensor monitoring, and in particular to a remote monitoring method and system for weighing sensors based on the Internet of Things. The method includes the following steps: constructing a weight sequence according to the weighing data of a vehicle during driving in a weighing detection area; inputting the side image of the vehicle at each moment into a preset tire recognition model to obtain a wheel recognition area; taking the mean of the horizontal coordinates of the pixel points in the wheel recognition area as the horizontal coordinate of the center point, the mean of the vertical coordinates as the vertical coordinate of the center point, taking any edge of the vehicle body as a reference edge, and calculating the vertical distance from the center point to the reference edge; calculating the vehicle bump value; deleting the moments when the vehicle bump value is greater than a preset threshold in the weight sequence to obtain an optimal sequence, and taking the central tendency measurement of the weight data in the optimal sequence as the weighing monitoring result. The present application has the effect of improving the accuracy of weighing data.

Description

Technical Field

[0001] The present application relates to the field of weighing sensor monitoring, and in particular to a remote monitoring method and system for weighing sensors based on the Internet of Things. Background Art

[0002] The technology of weighing a vehicle while it is moving is called dynamic weighing. Dynamic weighing can measure the weight of a vehicle while it is in normal driving state, which is particularly important for monitoring and managing vehicle loads on the road. The vehicle can be weighed without stopping. The weighing detection area is equipped with a weighing sensor, which is used to measure the weight of the vehicle and cargo.

[0003] For example, the patent application document with publication number CN107421617A discloses an electronic floor scale, which includes a main body (weighing detection area) and a slope (side slope) connected to both ends of the main body. A weighing sensor is arranged inside the main body. The vehicle drives onto the main body from one slope, drives out through another slope, and is weighed on the main body. The function of the slope is to guide the vehicle into and out of the weighing detection area.

[0004] Existing non-stop weighing detection systems are usually unmanned, monitoring the vehicle weighing process through surveillance cameras, and wirelessly transmitting the weighing data and surveillance video to a remote monitoring platform to detect abnormal situations in a timely manner.

[0005] However, when the vehicle enters the weighing and detection area, when the front wheels are already on the weighing and detection area and the rear wheels drive onto the weighing and detection area from the slope, the vehicle body will produce continuous vibrations due to the height difference and speed changes. The continuous vibrations will affect the weighing of the vehicle in the weighing and detection area, resulting in inaccurate weighing data. Summary of the invention

[0006] In order to solve the problem of inaccurate weighing data caused by vehicle body vibration, the present application provides a remote monitoring method and system for a weighing sensor based on the Internet of Things.

[0007] In the first aspect, the present application provides a remote monitoring method for a weighing sensor based on the Internet of Things, which adopts the following technical solutions:

[0008] A remote monitoring method for a weighing sensor based on the Internet of Things includes the following steps: constructing a weight sequence according to weighing data of a vehicle during driving in a weighing detection area; inputting a side image of the vehicle at each moment into a preset tire recognition model to obtain a wheel recognition area; taking the mean of the horizontal coordinates of the pixel points in the wheel recognition area as the horizontal coordinate of the center point, the mean of the vertical coordinates as the vertical coordinate of the center point, taking any edge of the vehicle body as a reference edge, and calculating the vertical distance from the center point to the reference edge; and calculating the vehicle bump value, the calculation formula is: ,in, for The vehicle bump value at the moment, for The vertical distance at the moment, for The vertical distance at the moment, for The vertical distance at the moment, represents the maximum value function; the optimal sequence is obtained by deleting the moments when the vehicle bump value is greater than the preset threshold in the weight sequence, and the central tendency measure of the weight data in the optimal sequence is used as the weighing monitoring result.

[0009] The beneficial effects are as follows: the values ​​with larger bumps in the weight sequence are deleted to reduce the influence of mutation data in the weighing data on the calculation results. The calculation of the vehicle bump value can find the mutation data with the largest continuous change amplitude, that is, the vehicle bump value reflects the degree of change at a certain moment relative to the adjacent moments. The trend measurement of the weight data after deleting the mutation data is used as the weighing monitoring result, which reduces the problem of inaccurate weighing data caused by vehicle body vibration, ensures the accuracy and reliability of weighing, and facilitates the discovery and handling of abnormal situations.

[0010] Optionally, the side image of the vehicle at each moment is input into a preset tire recognition model to obtain the wheel recognition area, including the steps of: obtaining the side image of the vehicle during the historical weighing process, and setting a circumscribed rectangular mark on the wheel area in the side image; inputting the side image with the circumscribed rectangular mark into a preset neural network model for training to obtain a tire recognition model; obtaining the side image of the vehicle that is currently passing through the weighing detection area and inputting it into the tire recognition model to obtain the wheel recognition area.

[0011] The beneficial effect is that the tire recognition model obtained through historical data training has a faster recognition speed and a higher recognition accuracy rate for the weighing detection area in actual application.

[0012] Optionally, the side image of the vehicle at each moment is input into a preset tire recognition model to obtain a wheel recognition area, including the steps of: retrieving a data set corresponding to the car tire in a preset Python database; inputting the data set into a yolov5 model and performing model training to obtain a tire recognition model; obtaining a side image of the vehicle that is currently passing through the weighing detection area and inputting it into the tire recognition model to obtain a wheel recognition area.

[0013] The beneficial effect is that using the existing Python database, there is no need to collect and process data to build a data set, which reduces the amount of data processing and workload.

[0014] Optionally, a weight sequence is constructed based on the weighing data of the vehicle during driving in the weighing detection area, including the steps of: constructing an initial weight sequence based on the non-zero weighing results of the vehicle at each moment when the vehicle passes through the weighing detection area and the slope; calculating the screening coefficient, the calculation formula is: ,in, represents the screening coefficient, express The sequence of weighing data before time. express The reverse sequence of Represents the Pearson correlation coefficient; the weighing data contained in the sequence whose screening coefficient is greater than the preset coefficient threshold is deleted, and the other weighing data are sorted in the order of time to obtain the weight sequence.

[0015] The beneficial effect is that when the vehicle is in the process of entering and exiting the weighing detection area, when the front wheels are already on the weighing detection area and the rear wheels are still on the slope, or when the front wheels of the vehicle are still on the slope and the rear wheels are still on the weighing detection area, the weight of the vehicle is not fully applied to the load-bearing table. At this time, the weighing sensor located inside the main body may not receive a complete weight signal, resulting in inaccurate weighing data display. The purpose of deleting the weighing data contained in the sequence with a screening coefficient greater than a preset coefficient threshold is to delete the data in the above process to improve the accuracy of weighing data monitoring.

[0016] Optionally, a weight sequence is constructed based on weighing data of a vehicle during driving in a weighing detection area, including the steps of setting a fixed threshold range, and sorting the weighing data within the fixed threshold range in chronological order to obtain a weight sequence.

[0017] The beneficial effect is that the fixed threshold can directly filter the weighing data and select the weighing data of the vehicle when it moves on the weighing detection area. This method does not require a lot of calculations and can obtain measurement results relatively quickly.

[0018] Optionally, the method for setting the fixed threshold range is: taking the ratio of the length of the slope to the vehicle speed as the initial time period, the moment corresponding to the initial time period as the starting point of the fixed threshold range, and taking the ratio of the length of the weighing detection area to the vehicle speed as the interval length of the fixed threshold range.

[0019] Optionally, the measure of central tendency is the mean or the mode.

[0020] In the second aspect, the present application provides a remote monitoring system for a weighing sensor based on the Internet of Things, which adopts the following technical solutions:

[0021] The remote monitoring system for a weighing sensor based on the Internet of Things includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the remote monitoring method for a weighing sensor based on the Internet of Things is implemented.

[0022] The beneficial effect is: the above-mentioned weighing sensor based on the Internet of Things uses a remote monitoring method to generate a computer program, and stores it in a memory so that it can be loaded and executed by a processor, thereby making a system based on the memory and the processor for easy use.

[0023] In summary, this application has the following technical effects:

[0024] 1. The vehicle bump value reflects the degree of change at a certain moment relative to the adjacent moment. The trend measurement of the weight data after deleting the mutation data is used as the weighing monitoring result, which can effectively eliminate the data error of vehicle driving and improve the accuracy of obtaining vehicle weight.

[0025] 2. Delete the weighing data when the vehicle passes the slope and the intersection of the weighing detection area to make the weighing data more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-restrictive manner, and the same or corresponding numbers represent the same or corresponding parts.

[0027] Figure 1 This is a method flow chart of a remote monitoring method for a weighing sensor based on the Internet of Things in an embodiment of the present application.

[0028] Figure 2 This is a method flow chart of step S1 in a remote monitoring method for a weighing sensor based on the Internet of Things in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0030] It should be understood that when the terms "first", "second", etc. are used in the claims, specification and drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0031] The present application embodiment discloses a remote monitoring method for a weighing sensor based on the Internet of Things, referring to Figure 1 , including steps S1 to S5, which are specifically as follows:

[0032] S1: Construct a weight sequence based on the weighing data of the vehicle during its driving in the weighing detection area.

[0033] The scale used in the present application includes a weighing detection area and a slope connected to both ends of the weighing detection area, and a weighing sensor is arranged inside the weighing detection area. The vehicle drives from one slope to the weighing detection area, drives out through another slope, and is weighed on the weighing detection area.

[0034] Reference Figure 2 , step S1 includes steps S10 to S12, which are specifically as follows:

[0035] S10: When the vehicle passes through the weighing detection area and the slope, an initial weight sequence is constructed according to the non-zero weighing results of the vehicle at each moment.

[0036] The weight data of the vehicle passing by is captured by the weighing sensor. This data includes the weight readings at each moment when the vehicle enters the weighing detection area, drives on the weighing detection area, and leaves the weighing detection area.

[0037] The weight readings at each moment are screened for non-zero weighing results. The purpose is that the vehicle may have a short zero reading during driving because the vehicle is not in the weighing area. Therefore, it is necessary to screen out non-zero weighing results. This step ensures that only valid weight data is included in the sequence.

[0038] S11: Calculate the screening coefficient.

[0039] The calculation formula is: ,in, represents the screening coefficient, express The sequence of weighing data before time. express The reverse sequence of .

[0040] Represents the Pearson correlation coefficient, used to calculate and The value of Pearson correlation coefficient is between -1 and 1, where 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no correlation.

[0041] S12: Deleting the weighing data included in the sequence whose screening coefficient is greater than the preset coefficient threshold, and sorting the other weighing data in chronological order to obtain a weight sequence.

[0042] When the vehicle is entering and exiting the weighing detection area, when the front wheels are already on the weighing detection area and the rear wheels are still on the slope, or when the front wheels of the vehicle are on the slope and the rear wheels are on the weighing detection area, the weight of the vehicle is not fully applied to the load-bearing table. At this time, the weighing sensor located inside the weighing detection area may not receive the complete weight signal, resulting in inaccurate weighing data display. Therefore, the purpose of deleting the weighing data contained in the sequence whose screening coefficient is greater than the preset coefficient threshold is to delete the data in the above process.

[0043] In one embodiment, a fixed threshold range can also be set, and the weighing data within the fixed threshold range are sorted in order of time to obtain a weight sequence, and the weighing data outside the fixed threshold range is deleted. The purpose of the fixed threshold range is to divide the vehicle into stages in the slope and weighing detection area.

[0044] For example, the time when the vehicle enters the weighing detection area is set as time 0, the ratio between the length of the slope and the vehicle speed is used as the initial period, the time corresponding to the initial period is used as the starting point of the fixed threshold range, and the ratio between the length of the weighing detection area and the vehicle speed is used as the interval length of the fixed threshold range. According to the interval starting point and interval length, the interval end point of the fixed threshold range can be determined. For example, if the initial period is 1 second, and the ratio between the length of the weighing detection area and the vehicle speed is 2 seconds, then the fixed threshold interval is , then delete the data from time 0 to time 1 (excluding time 1) and after time 3 (excluding time 3).

[0045] Exemplarily, the fixed threshold range may also be set by the staff according to the actual application scenario, which will not be elaborated here.

[0046] S2: Input the vehicle side image at each moment into a preset tire recognition model to obtain a wheel recognition area.

[0047] A camera is arranged on one side of the vehicle and fixed on the ground or the weighing detection area. The camera is used to capture the video of the vehicle passing through the weighing detection area. The side image of the vehicle during the historical weighing process can be obtained by extracting frames from the historical video.

[0048] The construction method of the tire recognition model is:

[0049] In one embodiment, a side image of the vehicle during the historical weighing process is obtained, and a circumscribed rectangular mark is set for the wheel area in the side image; the side image with the circumscribed rectangular mark is put into a preset neural network model for training to obtain a tire recognition model. The neural network model can use, for example, an FCN (Fully Convolutional Networks) model or a U-Net network model. Model training is a prior art and will not be described in detail here.

[0050] In one embodiment, a data set corresponding to a car tire is retrieved from a preset Python database; the data set is input into a yolov5 model and model training is performed to obtain a tire recognition model. The Python database is an existing database containing wheels, and no image collection is required. Model training is an existing technology and will not be described in detail here.

[0051] The video of the vehicle that is currently passing through the weighing detection area is obtained, and the video is framed at a frame rate of one frame per second to obtain a side image of each frame. The side image is input into the tire recognition model to obtain the wheel recognition area.

[0052] S3: Taking the mean of the horizontal coordinates of the pixels in the wheel recognition area as the horizontal coordinate of the center point, taking the mean of the vertical coordinates as the vertical coordinate of the center point, taking any edge of the vehicle body as the reference edge, and calculating the vertical distance from the center point to the reference edge.

[0053] In one embodiment, any edge of the vehicle body may be a roof edge, a bottom edge, a front edge or a rear edge of the vehicle side.

[0054] S4: Calculate the vehicle bump value.

[0055] The calculation formula of vehicle bump value is: ,in, for The vehicle bump value at the moment, for The vertical distance at the moment, for The vertical distance at the moment, for The vertical distance at the moment, represents the maximum value function, that is, choose as well as The maximum value among them is taken as the vehicle bump value.

[0056] S5: Deleting the moments when the vehicle bump value is greater than a preset threshold value from the weight sequence to obtain an optimal sequence, and taking the central tendency measurement of the weight data in the optimal sequence as the weighing monitoring result.

[0057] After deleting the weight data with large fluctuations in the weight sequence, the other weight data form an optimal sequence. The overall weight data in the optimal sequence is more stable and can better reflect the actual weight of the vehicle.

[0058] Specifically, the mean or mode of the weighing data in the optimal sequence is used as the weighing test result. The mean is the arithmetic average of all weighing data, which can reflect the average level of the data, while the mode is the data value with the highest frequency in the weighing data. The mode or mean is used as the vehicle weighing result to make the weighing result more accurate, which is conducive to the staff to promptly discover the abnormality of vehicle weighing.

[0059] An embodiment of the present application also discloses a remote monitoring system for a weighing sensor based on the Internet of Things, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, a remote monitoring method for a weighing sensor based on the Internet of Things according to the present application is implemented.

[0060] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0061] In the present application, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high bandwidth memory HBM (High Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0062] Although this specification has shown and described a plurality of embodiments of the present application, it is obvious to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, modifications and alternatives without departing from the thought and spirit of the present application. It should be understood that in the process of practicing the present application, various alternatives to the embodiments of the present application described herein may be adopted.

[0063] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A remote monitoring method for a weighing sensor based on the Internet of Things, characterized in that: Includes steps: Construct a weight sequence based on the weighing data of the vehicle during its driving in the weighing detection area; Input the vehicle side image at each moment into the preset tire recognition model to obtain the wheel recognition area; The mean of the horizontal coordinates of the pixels in the wheel recognition area is used as the horizontal coordinate of the center point, the mean of the vertical coordinates is used as the vertical coordinate of the center point, any edge of the vehicle body is used as the reference edge, and the vertical distance from the center point to the reference edge is calculated; Calculate the vehicle bump value, the calculation formula is: ,in, for The vehicle bump value at the moment, for The vertical distance at the moment, for The vertical distance at the moment, for The vertical distance at the moment, represents the maximum value function; The optimal sequence is obtained by deleting the moments when the vehicle bump value is greater than the preset threshold in the weight sequence, and the central tendency measurement of the weight data in the optimal sequence is used as the weighing monitoring result.

2. The remote monitoring method for a weighing sensor based on the Internet of Things according to claim 1 is characterized in that: Inputting the vehicle side image at each moment into a preset tire recognition model to obtain a wheel recognition area includes the following steps: Obtain the side image of the vehicle during the historical weighing process, and set a circumscribed rectangular mark on the wheel area in the side image; The side image with the circumscribed rectangle mark is put into the preset neural network model for training to obtain the tire recognition model; The side image of the vehicle that currently passes through the weighing detection area is obtained and input into the tire recognition model to obtain the wheel recognition area.

3. The remote monitoring method for a weighing sensor based on the Internet of Things according to claim 1 is characterized in that: Inputting the vehicle side image at each moment into a preset tire recognition model to obtain a wheel recognition area includes the following steps: Retrieve the corresponding car tire data set from the preset Python database; Input the data set into the yolov5 model and perform model training to obtain the tire recognition model; The side image of the vehicle that currently passes through the weighing detection area is obtained and input into the tire recognition model to obtain the wheel recognition area.

4. The remote monitoring method for a weighing sensor based on the Internet of Things according to claim 2 or 3, characterized in that: The weight sequence is constructed according to the weighing data of the vehicle during driving in the weighing detection area, including the following steps: When the vehicle passes through the weighing detection area and the slope, the initial weight sequence is constructed according to the non-zero weighing results of the vehicle at each moment; Calculate the screening coefficient using the formula: ,in, represents the screening coefficient, express The sequence of weighing data before time. express The reverse sequence of Represents the Pearson correlation coefficient, used to calculate and The correlation between The weighing data contained in the sequence whose screening coefficient is greater than the preset coefficient threshold is deleted, and the other weighing data are sorted in the order of time to obtain the weight sequence.

5. The remote monitoring method for a weighing sensor based on the Internet of Things according to claim 2 or 3, characterized in that: A weight sequence is constructed according to weighing data of a vehicle during driving in a weighing detection area, including the steps of setting a fixed threshold range, and sorting the weighing data within the fixed threshold range in chronological order to obtain a weight sequence.

6. The remote monitoring method for a weighing sensor based on the Internet of Things according to claim 5 is characterized in that: The method for setting the fixed threshold range is: taking the ratio between the length of the slope and the vehicle speed as the initial period, the moment corresponding to the initial period as the interval starting point of the fixed threshold range, and taking the ratio between the length of the weighing detection area and the vehicle speed as the interval length of the fixed threshold range.

7. The remote monitoring method for a weighing sensor based on the Internet of Things according to claim 1, characterized in that: The measure of central tendency is the mean or the mode.

8. A remote monitoring system for a weighing sensor based on the Internet of Things, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a remote monitoring method for a weighing sensor based on the Internet of Things is implemented according to any one of claims 1 to 7.

Images