Dynamic measurement method and system

Abstract

The invention relates to the technical field of data processing, in particular to a dynamic measurement method and system. The method is used for measuring the weight of a vehicle passing through a monitoring area, the ground of the monitoring area is provided with a multi-line-number quartz piezoelectric sensor, and the method comprises the steps: obtaining pressure information through the multi-line-number quartz piezoelectric sensor under the condition that a to-be-weighed vehicle passes through the monitoring area, acquiring speed information and driving direction information when the vehicle passes through the monitoring area; and inputting the pressure information, the speed information and the driving direction information at different moments when the vehicle passes through the monitoring area into a pre-trained weight prediction model to obtain a weight prediction value of the vehicle output by the weight prediction model, and taking the weight prediction value as a weight measurement result of the vehicle. According to the technical scheme, dynamic measurement of the weight of the vehicle passing through the monitoring area can be well realized.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a dynamic measurement method and system based on a multi-line quartz sensor. Background Art

[0002] Dynamic measurement is a non-invasive vehicle measurement technology. When dynamically measuring the weight of a vehicle, it can measure the weight of the vehicle while the vehicle is driving normally; compared with weighing the vehicle when it is parked, dynamically measuring the weight of the vehicle can shorten the time required for weighing and reduce the number of vehicle stops.

[0003] To achieve the dynamic measurement of the weight of a vehicle, in the Chinese patent application document with the publication number CN114936343A, a dynamic calculation method for the mass of an electric vehicle is provided, including: obtaining the state data during the acceleration driving period of the vehicle to be measured, where the state data includes time, speed, height, gravitational acceleration, effective driving power, and resistance power; calculating the total output work, total resistance work, total change in potential energy, and change in kinetic energy of the vehicle to be measured during the acceleration driving period according to the state data information; calculating the mass of the vehicle to be measured based on the law of conservation of energy, that is, the total output work of the vehicle driving motor is equal to the sum of the total resistance work, the change in potential energy of the vehicle in height, and the change in kinetic energy of the vehicle.

[0004] The related technology mainly determines the weight of a vehicle through operating parameters such as the driving power and total output work of the vehicle. However, as a supervisor for dynamically measuring the weight of passing vehicles, it is difficult to obtain operating parameters such as the driving power and total output work of the vehicle. Therefore, it is difficult to effectively achieve the dynamic measurement of the weight of passing vehicles. Summary of the Invention

[0005] To overcome the problem in the related technology that it is difficult to effectively achieve the dynamic measurement of the weight of passing vehicles, this application provides a dynamic measurement method and system based on a multi-line quartz sensor.

[0006] According to the first aspect of the embodiments of the present application, a dynamic measurement method is provided for measuring the weight of a vehicle passing through a monitoring area. A multi-line quartz piezoelectric sensor is arranged on the ground of the monitoring area, including: when a vehicle to be weighed passes through the monitoring area, obtaining pressure information through the quartz piezoelectric sensor, and obtaining the speed information and driving direction information of the vehicle when passing through the monitoring area; inputting the pressure information, speed information, and driving direction information at different times when the vehicle passes through the monitoring area into a pre-trained weight prediction model to obtain a weight prediction value output by the weight prediction model, and using the weight prediction value as the measurement result of the vehicle's weight; wherein, the weight prediction model is obtained by training a pre-constructed network model with a plurality of training samples under the supervision of an objective function; the training samples include the actual weight information of the test vehicle, as well as the speed information, driving direction information, and pressure information obtained by the quartz piezoelectric sensor at different times when passing through the monitoring area; the objective function is used to minimize the difference between the actual weight information and the predicted weight information determined according to the training samples during the training process, and is used to maximize the credibility of the training samples.

[0007] In this way, when a vehicle to be weighed passes through the monitoring area, pressure information is obtained through the multi-line quartz piezoelectric sensor, and the speed information and driving direction information of the vehicle when passing through the monitoring area are obtained; by inputting the pressure information, speed information, and driving direction information into a pre-trained weight prediction model, a weight prediction value of the vehicle can be obtained, avoiding the parking-type weighing measurement of the vehicle.

[0008] Optionally, the credibility of the training samples is obtained through the following method: G i is the credibility of the i-th training sample, Q i is the number of sampling moments in the i-th training sample, norm is a normalization processing function, A i,j is the first evaluation value of the i-th training sample at the j-th sampling moment, and the first evaluation value is used to characterize the degree of difference in parameter values from other sampling moments; H i,j is the second evaluation value of the j-th sampling moment in the i-th training sample, and the second evaluation value is used to characterize the degree of difference in parameter values from adjacent sampling moments; D i,l is the DTW distance between the i-th training sample and the a-th training sample at multiple sampling moments, N is the number of training samples, and the parameter values include the speed information, driving direction information of the test vehicle at the sampling moment, and the pressure information obtained by the quartz piezoelectric sensor.

[0009] In this way, by comparing the training sample with other training samples and comparing the values of the parameter values in the training sample at different times, the obtained credibility can better characterize the reliability of the training sample.

[0010] Optionally, the first evaluation value is obtained by the following method: A i,j is the first evaluation value of the i-th training sample at the j-th sampling time, norm is the normalization function, W is the number of types of parameter values, and s i,j,k is the value of the k-th parameter value of the i-th training sample at the j-th sampling time, and Q i is the number of sampling times in the i-th training sample.

[0011] In this way, by comparing the parameter values of the training sample at different times, the obtained first evaluation value can better characterize the degree of difference in parameter values from other sampling times.

[0012] Optionally, the second evaluation value is obtained by the following method: where H i,j is the second evaluation value of the i-th training sample at the j-th sampling time, norm is the normalization function, W is the number of types of parameter values, and s i,j,k is the value of the k-th parameter value of the i-th training sample at the j-th sampling time, and s i,j+f,k is the value of the k-th parameter value of the i-th training sample at the j + f-th sampling time.

[0013] In this way, by determining the difference in the parameter values of the training sample at a certain time from the adjacent times, the second evaluation value can characterize the probability that the parameter value at a certain time in the training sample is abnormal, so as to obtain a more accurate quality measurement result for the vehicle.

[0014] Optionally, the method further includes: taking the weight prediction value of the vehicle output by the weight prediction model as the first weight; taking the weight determined according to the pressure information obtained by the multi-line quartz piezoelectric sensor at different times as the second weight of the vehicle to be weighed; determining the difference information between the first weight and the second weight, and outputting a first prompt message when the difference information is greater than a preset difference threshold, where the first prompt message is used to prompt the vehicle to be weighed to pass through the monitoring area again for weighing.

[0015] In this way, when the difference information is greater than the preset difference threshold, outputting the first prompt message can prompt the vehicle to be weighed to pass through the monitoring area again for weighing, so as to obtain a more accurate weighing result for the vehicle.

[0016] Optionally, the method further includes: when the vehicle to be weighed passes through the monitoring area again for weighing, using the weight prediction value output again by the weight prediction model after the vehicle passes through the monitoring area as the third weight; when the third weight is greater than a preset weight threshold, outputting a second prompt message for prompting that the weight of the vehicle is greater than the preset weight threshold.

[0017] Optionally, the weight prediction model is obtained by training in the following manner: using the speed information, driving direction information at different moments when the test vehicle in the training sample passes through the monitoring area, and the pressure information obtained by the quartz piezoelectric sensor as the input of a pre-constructed network model, using the actual weight information of the test vehicle in the training sample as the output of the network model, and using the objective function to supervise the training process of the network model; when the training process meets the preset conditions, using the trained network model as the weight prediction model.

[0018] In this way, by training the pre-constructed network model and using the objective function to supervise the training process to obtain the quality prediction model, the trained quality prediction model can be deployed in advance to the electronic device, so as to use the electronic device to realize the dynamic measurement of the quality of the vehicle passing through the monitoring area.

[0019] Optionally, the speed information when the vehicle passes through the monitoring area is obtained in the following manner: using an image acquisition device arranged above the monitoring area to obtain multiple frames of images of the vehicle passing through the monitoring area from a top-down perspective; according to the position of the vehicle in the multiple frames of images and a preset corresponding relationship, determining the speed information of the vehicle at different moments when passing through the monitoring area, and the preset corresponding relationship is used to represent the relationship between the distance in the image coordinate system and the distance in the space coordinate system.

[0020] Optionally, the objective function G i is the credibility of the i-th training sample, y i is the actual weight information of the vehicle in the i-th training sample, is the predicted weight information determined according to the i-th training sample during the training process, and N is the number of training samples.

[0021] According to the second aspect of the embodiments of the present application, a dynamic measurement system is provided, including: a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the steps of the dynamic measurement method provided in the first aspect of the present application are implemented.

[0022] The technical solution provided by the embodiments of the present application may include the following beneficial effects: A multi-line quartz piezoelectric sensor is provided on the ground of the monitoring area. When a vehicle to be weighed passes through the monitoring area, pressure information is obtained through the multi-line quartz piezoelectric sensor, and speed information and driving direction information of the vehicle when passing through the monitoring area are also obtained. The pressure information, speed information, and driving direction information are input into a pre-trained weight prediction model, and a weight prediction value of the vehicle can be obtained. Thus, the weight prediction value is used as the weight measurement result of the vehicle. Since the supervisor for dynamically measuring the weight of the passing vehicle can effectively obtain information such as the pressure information of the multi-line quartz piezoelectric sensor, the speed information of the vehicle, and the driving direction information, it avoids the dependence of the dynamic measurement process of the vehicle's weight on operating parameters such as the driving power and total output work of the vehicle, enabling the effective dynamic measurement of the weight of the passing vehicle.

[0023] It should be understood that the above general description and subsequent detailed description are only exemplary and explanatory, and cannot limit the present application. Brief Description of the Drawings

[0024] Figure 1 is a flowchart of a dynamic measurement method shown according to an exemplary embodiment;

[0025] Figure 2 is a schematic structural diagram of a dynamic measurement system shown according to an exemplary embodiment;

[0026] Figure 3 is a schematic structural diagram of a multi-line quartz piezoelectric sensor shown according to an exemplary embodiment. Detailed Embodiments

[0027] First, a brief introduction to the application scenario of the embodiments of the present application is given. In the application scenario of the present application, in order to measure the weight of a vehicle during normal driving, in the related art, the weight of the vehicle in the driving state can be determined through information such as the speed, height, gravitational acceleration, effective driving power, resistance power, total output work, total resistance work, total change in potential energy, and change in kinetic energy of the vehicle during driving.

[0028] However, as the supervisor for measuring the weight of the vehicle, it is impossible to directly obtain information such as the resistance power, total output work, total resistance work, total change in potential energy, and change in kinetic energy of the vehicle, making it difficult to achieve the dynamic measurement of the weight of the vehicle passing through the monitoring area.

[0029] To address the above technical problems, the embodiments of the present application provide a multi-line quartz piezoelectric sensor, a dynamic measurement method, and a system. Figure 1 is a flowchart of a dynamic measurement method shown according to an exemplary embodiment, asFigure 1 As shown in the figure, the method includes the following steps.

[0030] In step S101, when the vehicle to be weighed passes through the monitoring area, pressure information is obtained through a multi-line quartz piezoelectric sensor, and speed information and driving direction information of the vehicle when passing through the monitoring area are obtained.

[0031] The ground of the monitoring area can be provided with multi-line quartz piezoelectric sensors. The number of multi-line quartz piezoelectric sensors provided on the ground of the monitoring area can be one or more. The embodiments of the present application do not limit the number and position distribution of the multi-line quartz piezoelectric sensors provided on the ground of the monitoring area.

[0032] Through the multi-line quartz piezoelectric sensor, the pressure signal of the vehicle on the ground when passing through the monitoring area can be converted into an electrical signal, realizing the monitoring of the pressure from the vehicle in the monitoring area.

[0033] Whether the vehicle to be weighed passes through the monitoring area can be determined according to sensors such as distance sensors and image sensors. For example, the distance along a specified direction can be measured by a distance sensor. When the vehicle to be weighed passes through the monitoring area, the distance measured by the distance sensor will change accordingly; or, image data can be collected by an image sensor. When the vehicle to be weighed passes through the monitoring area, the picture in the image data collected by the image sensor will change accordingly.

[0034] Whether the vehicle to be weighed leaves the monitoring area after passing through the monitoring area can also be determined according to sensors such as distance sensors and image sensors, which will not be elaborated here.

[0035] The speed information and driving direction information of the vehicle when passing through the monitoring area can be determined through the monitoring data obtained by a lidar or an image sensor. For example, a lidar is set in the traveling direction of the vehicle to collect point cloud data. According to the collected point cloud data, the speed information and driving direction of different driving points in the driving path of the vehicle when passing through the monitoring area can be determined.

[0036] Point cloud data is a data set composed of points in space. The point cloud data at least includes the position information of multiple position points in the space coordinate system. Through the position information of these position points in the space coordinate system, the shape information of the object in the space coordinate system can be described. Through the shape information of the object at different times, the movement speed and movement direction of the object in the space coordinate system can be determined.

[0037] In one embodiment, the speed information of the vehicle when passing through the monitoring area is obtained in the following manner: through an image acquisition device arranged above the monitoring area, multiple frames of images of the vehicle when passing through the monitoring area are obtained from a top-down perspective; according to the positions of the vehicle in the multiple frames of images and a preset corresponding relationship, the speed information of the vehicle at different moments when passing through the monitoring area is determined, and the preset corresponding relationship is used to represent the relationship between the distance in the image coordinate system and the distance in the spatial coordinate system.

[0038] For example, an image acquisition device can be arranged above the monitoring area to monitor the movement of the vehicle in the monitoring area from a top-down perspective. Since the driving of the vehicle in the monitoring area can be more intuitively viewed from a top-down perspective, the speed of the vehicle between adjacent moments can be determined through the positions of the vehicle in adjacent frames of images, and there is a certain corresponding relationship between the distance between two position points in the image and the actual distance between the two position points in the spatial coordinate system. Therefore, according to the positions of the vehicle in the multiple frames of images and the preset corresponding relationship, the speed information of the vehicle at different moments when passing through the monitoring area can be determined.

[0039] Among them, the preset corresponding relationship is used to represent the relationship between the distance in the image coordinate system and the distance in the spatial coordinate system, and the preset corresponding relationship can be obtained by pre-calibrating the relationship between the distance in the image coordinate system and the distance in the spatial coordinate system.

[0040] In this way, the speed information of the vehicle driving in the monitoring area can be more conveniently determined, so as to determine the weight information of the vehicle based on the speed information of the vehicle.

[0041] In step S102, the pressure information, speed information, and driving direction information of the vehicle at different moments when passing through the monitoring area are input into a pre-trained weight prediction model, and the weight prediction value of the vehicle output by the weight prediction model is obtained, so as to use the weight prediction value as the measurement result of the weight of the vehicle.

[0042] Compared with weighing the vehicle when it is parked, when a moving vehicle enters the monitoring area, it will exert a greater pressure on the quartz piezoelectric sensor arranged on the ground of the monitoring area than the weight of the vehicle, so that the pressure obtained by the quartz piezoelectric sensor cannot be directly used as the pressure corresponding to the weight of the vehicle.

[0043] When the vehicle passes through the monitoring area at different driving speeds, the pressure other than the gravity exerted by the vehicle on the quartz piezoelectric sensor is different, so that the pressure obtained by the quartz piezoelectric sensor is different when vehicles of the same weight pass through the monitoring area at different driving speeds. Therefore, the driving speed of the vehicle affects the measurement of the vehicle weight.

[0044] Since there is usually a certain angle between the monitoring area and the horizontal plane, the vehicle is subject to the supporting force from the quartz piezoelectric sensor, the frictional force between the vehicle's tires and the quartz piezoelectric sensor, and the gravity of the vehicle. When the vehicle travels in the monitoring area at different driving angles, the angular relationships among the supporting force, the frictional force, and the gravity are different.

[0045] When vehicles of the same weight travel in the monitoring area at different driving speeds, or when vehicles of the same weight travel at different driving speeds at different times in the monitoring area, the angular relationships among the supporting force, the frictional force, and the gravity are different, resulting in different pressures received by the quartz piezoelectric sensors installed on the ground of the monitoring area. Therefore, the driving direction of the vehicle in the monitoring area affects the measurement of the vehicle weight.

[0046] By inputting the pressure information, speed information, and driving direction information into a pre-trained weight prediction model, various factors that affect the measurement of the vehicle weight can be fully considered to obtain a more accurate measurement result of the vehicle weight.

[0047] The weight prediction model is obtained by training a pre-constructed network model with multiple training samples under the supervision of an objective function; the training samples include the actual weight information of the test vehicle, as well as the speed information, driving direction information, and pressure information obtained by the quartz piezoelectric sensor at different times when passing through the monitoring area.

[0048] The objective function is used to minimize the difference between the actual weight information and the predicted weight information determined according to the training samples during the training process, and is used to maximize the credibility of the training samples.

[0049] For example, the test vehicle can be weighed when it is parked to obtain the actual weight information of the test vehicle, and the test vehicle can be controlled to pass through the monitoring area at different driving speeds respectively, or test vehicles of different weights can be controlled to pass through the monitoring area, where the self-weights or load weights of the test vehicles of different weights are different; or the test vehicle can be controlled to enter the monitoring area in different driving directions respectively; or the test vehicle can be controlled to drive in different driving directions at different times when traveling in the monitoring area.

[0050] The number of test vehicles can be one or more, and the test vehicle can be a vehicle of the same or different model as the vehicle passing through the monitoring area.

[0051] Since the weight prediction model is obtained by training a pre-constructed network model with multiple training samples under the supervision of an objective function, the training samples include the actual weight information of the test vehicle, as well as the speed information, driving direction information, and pressure information obtained by the multi-line quartz piezoelectric sensor at different times when passing through the monitoring area.

[0052] Therefore, the weight prediction model can fully learn the actual weight information of the vehicle, the speed information at different times when the vehicle passes through the monitoring area, the driving direction information, and the pressure information obtained by the quartz piezoelectric sensor, so as to construct the relationship between the speed information at different times when the vehicle passes through the monitoring area, the driving direction information, and the pressure information obtained by the multi-line quartz piezoelectric sensor, and the actual weight information of the vehicle, so as to determine the weight information of the vehicle according to the pressure information, speed information, and driving direction information.

[0053] Objective function of the weight prediction model G i is the credibility of the i-th training sample, y i is the actual weight information of the vehicle in the i-th training sample, is the predicted weight information determined according to the i-th training sample during the training process, and N is the number of training samples.

[0054] The credibility of the training sample can characterize the reliability or accuracy of the training sample. Here, since the purpose of the loss function is to reduce the degree of difference between the actual output and the expected output of the network model, the corresponding part of the training sample with lower credibility has a larger value in the objective function, which can reduce the reference value of the training sample with lower credibility to the training process, and can avoid the waste of training samples and realize the full utilization of training samples.

[0055] Alternatively, the training sample with higher credibility has a smaller value in the corresponding part of the objective function, so as to improve the reference value of the training sample with higher credibility to the training process, which can help to obtain a more accurate quality prediction model, so as to output a more accurate quality prediction value through the quality prediction model.

[0056] In one embodiment, the weight prediction model is obtained by training in the following manner: the speed information at different times when the test vehicle passes through the monitoring area, the driving direction information, and the pressure information obtained by the quartz piezoelectric sensor in the training sample are used as the input of a pre-constructed network model, the actual weight information of the test vehicle in the training sample is used as the output of the network model, and the training process of the network model is supervised by using the objective function; when the training process meets the preset conditions, the trained network model is used as the weight prediction model.

[0057] Random forest is a tree-based ensemble learning algorithm. Due to the use of the ensemble method, the network model can reduce the risk of overfitting during prediction, so as to obtain more accurate prediction results.

[0058] The training process meets the preset conditions. For example, it can be that the value of the objective function is less than or equal to the preset threshold, or the number of iterations of the training process is greater than or equal to the preset number of times.

[0059] In this way, through the training of the pre-constructed network model and the use of the objective function to supervise the training process to obtain the trained quality prediction model, the trained quality prediction model can be deployed in advance to the electronic device, so as to use the electronic device to realize the dynamic measurement of the quality of the vehicles passing through the monitored area.

[0060] In one embodiment, the credibility of the training samples can be obtained in the following way: G i is the credibility of the i-th training sample, Q i is the number of sampling moments in the i-th training sample, norm is the normalization function, A i,j is the first evaluation value of the i-th training sample at the j-th sampling moment, and the first evaluation value is used to characterize the degree of difference in parameter values from other sampling moments; H i,j is the second evaluation value of the j-th sampling moment in the i-th training sample, and the second evaluation value is used to characterize the degree of difference in parameter values from the adjacent sampling moment; D i,l is the DTW distance between the i-th training sample and the a-th training sample at multiple sampling moments, N is the number of training samples, and the parameter values include the speed information, driving direction information of the test vehicle at the sampling moment, and the pressure information obtained by the quartz piezoelectric sensor.

[0061] ∏ is the symbol of product. In order to give full play to the role of each parameter participating in the product, a value relatively small compared to the DTW distance can be added based on the DTW distance between two training samples at multiple sampling moments.

[0062] For example, if the value range of the DTW distance after normalization by the norm normalization function is between 0 and 1, the sum of the DTW distance between two training samples and the preset value can be used as the DTW distance between the two training samples again. The preset value can be relatively small values compared to the normalized DTW distance, such as 0.01, 0.015, and 0.02, etc.

[0063] Or, when the DTW distance between two training samples is 0, the preset value can be used as the DTW distance between the two training samples to give full play to the role of each parameter participating in the product.

[0064] The DTW (Dynamic Time Warping) distance can reflect the similarity between two time series. Among them, the smaller the DTW distance between two time series, the greater the similarity between the two time series; on the contrary, the greater the DTW distance between two time series, the smaller the similarity between the two time series.

[0065] At different sampling times in the same training sample, they respectively correspond to different times when the vehicle passes through the monitoring area. The same training sample includes pressure information, speed information, driving direction information, etc. of the test vehicle at different times when passing through the monitoring area. The DTW distance between two training samples can be determined according to the differences between the two training samples in terms of pressure information, speed information, and driving direction information.

[0066] For example, the DTW distance between two training samples can be determined according to multiple sub-DTW distances between the two training samples, and the multiple sub-DTW distances respectively correspond to the differences between the two training samples in terms of pressure information, speed information, and driving direction information.

[0067] The greater the differences between a training sample and other training samples in terms of pressure information, speed information, and driving direction information, the lower the probabilities of the information, speed information, and driving information included in the training sample occurring. The training sample has a higher probability of being obtained when the test vehicle is driving abnormally, and this part of the training sample has a lower reference value for the subsequent vehicle quality measurement process. Therefore, a lower credibility can be assigned to this part of the training sample.

[0068] Regarding the speed information and driving direction information of the test vehicle at different times in the same training sample, the greater the differences in the speed information and driving direction at different times when the test vehicle passes through the monitoring area, the more likely the test vehicle is in an abnormal driving state. For example, the test vehicle has behaviors such as sudden acceleration or sudden deceleration.

[0069] The training sample obtained when the test vehicle is in an abnormal driving state has a lower reference value for the subsequent quality measurement process. And the first evaluation value is used to characterize the degree of difference in parameter values from other sampling times, and the second evaluation value is used to characterize the degree of difference in parameter values from adjacent sampling times. Therefore, a lower credibility can be assigned to the training sample with lower first and second evaluation values at multiple times, so that the quality prediction model obtained under the supervision of the objective function can output more accurate quality measurement results.

[0070] In this way, the training samples can be compared with other training samples, and the parameter values of the training samples at different times can be compared, so that the obtained credibility can better characterize the reliability of the training samples, and thus a more accurate quality measurement result can be obtained.

[0071] In one embodiment, the first evaluation value of the training sample can be obtained in the following manner: A i,j is the first evaluation value of the i-th training sample at the j-th sampling time, norm is the normalization processing function, W is the number of types of parameter values, s i,j,k is the value of the k-th parameter of the i-th training sample at the j-th sampling time, Q i is the number of sampling times in the i-th training sample.

[0072] For example, in the case where a test vehicle passes through a monitoring area, the fluctuation of the pressure information obtained by a quartz piezoelectric sensor set on the ground of the monitoring area at different times can be determined, or the fluctuation of the speed information at different times when the test vehicle passes through the monitoring area can be determined, or the fluctuation of the driving direction information at different times when the test vehicle passes through the monitoring area can be determined.

[0073] In this way, by comparing the parameter values of the training sample at different times, the obtained first evaluation value can better characterize the degree of difference in parameter values from other sampling times.

[0074] In one embodiment, the second evaluation value of the training sample can be obtained in the following manner: where, H i,j is the second evaluation value of the i-th training sample at the j-th sampling time, norm is the normalization processing function, W is the number of types of parameter values, s i,j,k is the value of the k-th parameter of the i-th training sample at the j-th sampling time, s i,j+f,k is the value of the k-th parameter of the i-th training sample at the j + f-th sampling time.

[0075] In addition to comparing the parameter value of a certain sampling time in the training sample with the parameter values of all other sampling times, the difference in the parameter values of the training sample at a certain time from the adjacent times can also better characterize the possible abnormality of the parameter value of the training sample at a certain time.

[0076] For example, for a training sample with a corresponding duration of 60 seconds, the driving speed of the test vehicle at the 10th second when passing through the monitoring area can be compared with the driving speeds of the test vehicle at the 9th second and the 11th second when passing through the monitoring area respectively to determine whether there is a large fluctuation in the driving speed of the test vehicle.

[0077] If the difference between the speed of the test vehicle at a certain moment and the adjacent moment when passing through the monitoring area is large, it indicates that the test vehicle is likely to be in an abnormal driving situation. For example, the vehicle has sudden acceleration or deceleration. The reference value of the training sample corresponding to the test vehicle in an abnormal driving situation is lower.

[0078] In this way, by determining the difference in the parameter values of the training sample at a certain moment and the adjacent moment, the second evaluation value can better characterize the probability that the parameter value at a certain moment in the training sample is abnormal, so as to obtain a more accurate quality measurement result of the vehicle.

[0079] In one embodiment, the weight prediction value of the vehicle output by the weight prediction model can also be used as the first weight; the weight determined according to the pressure information obtained by the quartz piezoelectric sensor at different times is used as the second weight of the vehicle to be weighed; the difference information between the first weight and the second weight is determined, and a first prompt message is output when the difference information is greater than a preset difference threshold. The first prompt message is used to prompt the vehicle to be weighed to pass through the monitoring area again for weighing.

[0080] When the vehicle passes over the quartz piezoelectric sensor set on the ground in the monitoring area, since the vehicle is in a driving state, there is a certain difference between the pressure directly obtained by the multi-line quartz piezoelectric sensor and the weight of the vehicle. However, since the pressure information obtained by the multi-line quartz piezoelectric sensor when the vehicle passes through the monitoring area in a driving state is related to the weight of the vehicle, there is a certain correlation between the weight prediction value of the vehicle output by the weight prediction model and the weight determined directly according to the pressure information obtained by the multi-line quartz piezoelectric sensor at different times. Therefore, the difference between the weight prediction value of the vehicle output by the weight prediction model and the weight determined directly according to the pressure information obtained by the multi-line quartz piezoelectric sensor at different times will be within a certain range.

[0081] If the difference between the weight prediction value of the vehicle output by the weight prediction model and the weight determined directly according to the pressure information obtained by the multi-line quartz piezoelectric sensor at different times is too large, it indicates that the measurement result may be inaccurate due to abnormal driving behavior when the vehicle passes through the monitoring area. The vehicle can be prompted to pass through the monitoring area again, so as to dynamically measure the weight of the vehicle again.

[0082] The difference information can be, for example, the ratio of the difference between the first weight and the second weight. The preset difference threshold can be adaptively determined according to the first weight or the second weight. For example, it can be between 20% and 30% of the first weight.

[0083] In this way, when the difference information is greater than a preset difference threshold, a first prompt message is output, which can prompt the vehicle to be weighed to pass through the monitoring area again for weighing, so as to obtain a more accurate weighing result of the vehicle.

[0084] In one embodiment, when the vehicle to be weighed passes through the monitoring area again for weighing, the weight prediction value output again by the weight prediction model after the vehicle passes through the monitoring area again is used as the third weight; when the third weight is greater than a preset weight threshold, a second prompt message is output, and the second prompt message is used to prompt that the weight of the vehicle is greater than the preset weight threshold.

[0085] For example, when the vehicle to be weighed passes through the monitoring area again for weighing, the speed information, driving direction information when the vehicle to be weighed passes through the monitoring area again, and the pressure information obtained by the quartz piezoelectric sensor can be obtained, and the pressure information, speed information, and driving direction information at different times when the vehicle passes through the monitoring area again are input into the pre-trained weight prediction model, and the weight prediction value output again by the weight prediction model is used as the third weight.

[0086] After the vehicle to be weighed passes through the monitoring area again for weighing, the driver of the vehicle to be weighed has probably avoided the abnormal driving behavior that may exist during the previous weighing. For example, changing from accelerating rapidly through the monitoring area to passing through the monitoring area at a constant speed. Therefore, the weight measurement result obtained again can better reflect the actual weight of the vehicle. If the third weight is greater than the preset weight threshold, it means that the vehicle is overweight, and it can be prompted that the weight of the vehicle is greater than the preset weight threshold.

[0087] For example, when weighing the vehicles passing by at the monitoring station, a display device can be set at the monitoring station. When the third weight is greater than the preset weight threshold, the display device can output a second prompt message for prompting that the weight of the vehicle is greater than the preset weight threshold.

[0088] Among them, the preset weight threshold can be determined according to the identification information of the vehicle. For example, it can be determined according to the vehicle type identification information of the vehicle and the permitted load weight pre-bound with the license plate number; or, since the vehicle is weighed after loading goods at the departure place of the vehicle, the user of the vehicle can submit the weighing result at the departure place of the vehicle to the monitoring station, and the monitoring station can determine the preset weight threshold corresponding to the vehicle according to the received weighing result and the vehicle type identification information.

[0089] Figure 2 It is a schematic structural diagram of a dynamic measurement system 1000 shown according to an exemplary embodiment. Refer to Figure 2, the dynamic measurement system 1000 includes: a processor 1100 and a memory 1200. The memory 1200 stores computer program instructions, and when the computer program instructions are executed by the processor 1100, all or part of the steps of the dynamic measurement method in this application are implemented.

[0090] Figure 3 is a schematic structural diagram of a multi-line quartz piezoelectric sensor 2000 shown according to an exemplary embodiment. The multi-line quartz piezoelectric sensor 2000 includes a weighing base 2100 and a signal output component 2200 located in the internal space of the weighing base 2100. The signal output component 2200 may include a plurality of signal output sub-components 2300; the signal output component 2200 can send the acquired pressure information to a signal processing device ( Figure 3 not shown in the figure).

[0091] The multi-line quartz piezoelectric sensor 2000 can be arranged on the ground of the monitoring area. When a vehicle passes through the position where the multi-line quartz piezoelectric sensor 2000 is arranged in the monitoring area, the weighing base 2100 can transmit the received pressure signal to the signal output component 2200, so that the signal output component 2200 converts the pressure signal into pressure information and sends it to the signal processing device.

[0092] The information processing device can be a processor ( Figure 3 not shown in the figure) inside the multi-line quartz piezoelectric sensor 2000, or an external terminal device or server ( Figure 3 not shown in the figure) communicatively connected to the multi-line quartz piezoelectric sensor 2000.

[0093] The connection relationship between the multiple signal output sub-components 2300 included in the signal output component 2200 is Figure 3 not shown in the figure. The multiple signal output sub-components 2300 included in the signal output component 2200 can individually send the monitored pressure information to the information processing device; or, the multiple signal output sub-components 2300 can also be connected to each other, so as to send all the pressure information monitored by the multiple signal output sub-components 2300 to the information processing device together.

[0094] The multi-line quartz piezoelectric sensor 2000 can be integrated with the dynamic measurement system in the embodiments of this application. The dynamic measurement system is used to execute the steps of the dynamic measurement method in the embodiments of this application, so that the multi-line quartz piezoelectric sensor 2000 executes the steps of the dynamic measurement method in the embodiments of this application.

[0095] Alternatively, the multi-line quartz piezoelectric sensor 2000 can measure the weight of the vehicle passing through the monitored area by sending the obtained pressure information of the vehicle passing through the monitored area to the information processing device, so that the information processing device executes the dynamic measurement method provided in the embodiments of the present application, and avoids the parked measurement of the weight of the vehicle.

[0096] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include known common general knowledge or conventional technical means in the technical field not disclosed in the present application. The specification and examples are only illustrative.

[0097] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A dynamic measurement method for measuring the weight of a vehicle passing through a monitored area, wherein a multi-line quartz piezoelectric sensor is arranged on the ground of the monitored area, characterized in that, Including: When a vehicle to be weighed passes through a monitoring area, pressure information is obtained through a multi-line quartz piezoelectric sensor, and speed information and driving direction information of the vehicle when passing through the monitoring area are obtained; The pressure information, speed information, and driving direction information at different times when the vehicle passes through the monitoring area are input into a pre-trained weight prediction model to obtain a weight prediction value of the vehicle output by the weight prediction model, and the weight prediction value is used as the weight measurement result of the vehicle; Among them, the weight prediction model is obtained by training a pre-constructed network model with a plurality of training samples under the supervision of an objective function; The training samples include the actual weight information of the test vehicle, as well as the speed information, driving direction information, and pressure information obtained by the quartz piezoelectric sensor at different times when passing through the monitoring area; the objective function is used to minimize the difference between the actual weight information and the predicted weight information determined according to the training samples during the training process, and is used to maximize the credibility of the training samples.

2. The dynamic measurement method according to claim 1, characterized in that, The credibility of the training samples is obtained through the following method: G i is the credibility of the i-th training sample, Q i is the number of sampling moments in the i-th training sample, norm is the normalization function, A i,j is the first evaluation value of the i-th training sample at the j-th sampling moment, and the first evaluation value is used to characterize the degree of difference in parameter values from other sampling moments; H i,j is the second evaluation value of the j-th sampling moment in the i-th training sample, and the second evaluation value is used to characterize the degree of difference in parameter values from adjacent sampling moments; D i,l is the DTW distance between the i-th training sample and the a-th training sample at multiple sampling moments, N is the number of training samples; the parameter values include the speed information, driving direction information of the test vehicle at the sampling moment, and the pressure information obtained by the quartz piezoelectric sensor.

3. The dynamic measurement method according to claim 2, wherein The first evaluation value is obtained through the following method: A i,j is the first evaluation value of the i-th training sample at the j-th sampling moment, norm is the normalization function, W is the number of types of parameter values, s i,j,k is the value of the k-th parameter of the i-th training sample at the j-th sampling moment, Q i is the number of sampling moments in the i-th training sample.

4. The dynamic measurement method according to claim 2, wherein The second evaluation value is obtained through the following method: Among them, H i,j is the second evaluation value at the j-th sampling moment in the i-th training sample, norm is the normalization function, W is the number of types of parameter values, s i,j,k is the value of the k-th parameter at the j-th sampling moment in the i-th training sample, s i,j+f,k is the value of the k-th parameter at the (j + f)-th sampling moment in the i-th training sample.

5. The dynamic measurement method according to claim 1, characterized in that, The method further includes: Taking the weight prediction value of the vehicle output by the weight prediction model as the first weight; Taking the weight determined according to the pressure information obtained by the multi-line quartz piezoelectric sensor at different times as the second weight of the vehicle to be weighed; Determining the difference information between the first weight and the second weight, and outputting a first prompt message when the difference information is greater than a preset difference threshold, where the first prompt message is used to prompt the vehicle to be weighed to pass through the monitoring area again for weighing.

6. The dynamic measurement method according to claim 5, characterized in that, The method further includes: When the vehicle to be weighed passes through the monitoring area again for weighing, taking the weight prediction value output again by the weight prediction model after the vehicle passes through the monitoring area again as the third weight; When the third weight is greater than a preset weight threshold, outputting a second prompt message, where the second prompt message is used to prompt that the weight of the vehicle is greater than the preset weight threshold.

7. The dynamic measurement method according to claim 1, characterized in that, The weight prediction model is obtained through the following method: Taking the speed information, driving direction information, and pressure information obtained by the multi-line quartz piezoelectric sensor at different times when the test vehicle in the training samples passes through the monitoring area as the input of the pre-constructed network model, taking the actual weight information of the test vehicle in the training samples as the output of the network model, and using the objective function to supervise the training process of the network model; When the training process meets the preset conditions, taking the trained network model as the weight prediction model.

8. The dynamic measurement method according to claim 1, wherein The speed information of the vehicle when passing through the monitoring area is obtained through the following method: Through an image acquisition device arranged above the monitoring area, obtaining multiple frames of images of the vehicle in a top-down view when passing through the monitoring area; According to the position of the vehicle in the multiple frames of images and a preset corresponding relationship, determining the speed information of the vehicle at different times when passing through the monitoring area, where the preset corresponding relationship is used to represent the relationship between the distance in the image coordinate system and the distance in the space coordinate system.

9. The dynamic measurement method according to claim 1, characterized in that The objective function G i is the credibility of the i-th training sample, y i is the actual weight information of the vehicle in the i-th training sample, is the predicted weight information determined according to the i-th training sample during the training process, and N is the number of training samples.

10. A dynamic measurement system, characterized in that, Including: A processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement the dynamic measurement method according to any one of claims 1-9.

Images