Multi-sensor dynamic calibration method and system based on mathematical model

Abstract

The present invention discloses a multi-sensor dynamic calibration method and system based on a mathematical model, which relates to the technical field related to computer systems. The method comprises: obtaining a historical weighing sample data set by building a dynamic weighing transmission structure. A dynamic disturbance filtering model is trained based on the historical weighing sample data set and the weighing error label sample, wherein the weighing error label is the error between the historical weighing transmission data and the actual weight data of the item. By obtaining real-time weighing transmission data, the real-time weighing transmission data is sent to the dynamic disturbance filtering model, weighing compensation data is obtained for compensation calibration, and the calibrated weighing transmission data is output. The technical problem of unstable weighing data and large errors caused by factors such as item movement, conveyor belt acceleration and vibration in the dynamic weighing process in the prior art is solved. A high-precision dynamic weighing result with stable output close to the real weight is achieved, which improves the weighing accuracy and reliability of the system.

Description

Technical Field

[0001] The present application relates to the technical field related to computer systems, and in particular to a multi-sensor dynamic calibration method and system based on a mathematical model. Background Art

[0002] In industrial production and logistics, dynamic weighing, as an important process monitoring tool, is widely used in scenarios such as item sorting, load verification, and inventory management. Common dynamic weighing systems are often based on weighing units deployed on mobile platforms, enabling weighing while items are in motion. However, factors such as the inertia of items on the mobile platform, platform vibration, and changes in acceleration and deceleration can cause unstable or even systematic deviations in weighing readings, seriously affecting the accuracy and reliability of weighing data.

[0003] Therefore, in the prior art, there are technical problems such as unstable weighing data and large errors caused by factors such as object movement, conveyor belt acceleration and vibration during dynamic weighing. Summary of the Invention

[0004] This application provides a multi-sensor dynamic calibration method and system based on a mathematical model, addressing the existing technical issues of unstable weighing data and large errors caused by factors such as object movement, conveyor belt acceleration, and vibration during dynamic weighing. This method achieves stable, high-precision dynamic weighing results close to the true weight in dynamic environments through multi-sensor fusion and disturbance compensation based on Kalman filtering, thereby improving the system's weighing accuracy and reliability.

[0005] The present application provides a multi-sensor dynamic calibration method based on a mathematical model, which includes: building a dynamic weighing transmission structure, which includes a mobile platform and a weighing unit; connecting the dynamic weighing transmission structure to obtain a historical weighing sample data set, which includes historical weighing transmission data of the weighing unit and historical movement control data of the mobile platform; training a dynamic disturbance filtering model based on the historical weighing sample data set and a weighing error label sample, wherein the weighing error label is the error between the historical weighing transmission data and the actual weight data of the item, wherein the dynamic disturbance filtering model includes a Kalman filter, and introduces a mean square error loss to perform supervised training on the Kalman filter based on the historical weighing sample data set and the weighing error label sample; performing sensor integration on the target item through the weighing unit to obtain real-time weighing transmission data, and sending the real-time weighing transmission data to the dynamic disturbance filtering model to obtain weighing compensation data; performing compensation calibration on the weighing result of the target item according to the weighing compensation data, and outputting the calibrated weighing transmission data.

[0006] In the implementation, the weighing unit includes a static weighing unit and a dynamic weighing unit, the static weighing unit is detachably arranged at the front end of the mobile platform, and the dynamic weighing unit is integrated in the mobile platform. The method includes: establishing a CAN bus communication link between the static weighing unit and the dynamic weighing unit and a central control module; placing the item sample on the static weighing unit, and storing the recorded static weighing transmission data as the actual weight data of the item to the central control module through the CAN bus communication link; placing the item sample on the dynamic weighing unit, and storing the recorded dynamic weighing transmission data to the central control module through the CAN bus communication link; obtaining a weighing error label sample of the item sample based on the static weighing transmission data and the dynamic weighing transmission data, for training a dynamic disturbance filtering model.

[0007] In the implementation, the dynamic weighing unit includes a strain sensor or a piezoelectric sensor, the number of the strain sensors or the piezoelectric sensors is at least 2, and they are distributed and integrated in the mobile platform; and is used to integrate the sensor data of the strain sensor or the piezoelectric sensor as dynamic weighing transmission data through the CAN bus communication link.

[0008] In the implementation, the dynamic weighing unit includes a strain sensor and a piezoelectric sensor, the total number of the strain sensors and the piezoelectric sensors is at least 2, and they are distributed and integrated in the mobile platform; and is used to integrate the sensor data of the strain sensor and the piezoelectric sensor as dynamic weighing transmission data through the CAN bus communication link.

[0009] In the implementation, a dynamic disturbance filtering model is trained based on the historical weighing sample data set and the weighing error label samples. The method includes: dividing the dynamic weighing transmission data and historical mobile control data in the historical weighing sample data set into fixed-length time windows, and extracting the state fluctuation characteristics of each window; wherein the state fluctuation characteristics include the acceleration, speed, signal fluctuation standard deviation and response delay of the current window; constructing a dynamic disturbance filtering model based on a Kalman filter, inputting the state fluctuation characteristics of each window to calculate the error estimation value of each window, introducing the mean square error loss to iteratively train the weighing error label samples of the historical weighing sample data set and the error estimation value to obtain a dynamic disturbance filtering model.

[0010] In the implementation method, the modeling of the Kalman filter includes setting state variables, defining state transfer equations and observation equations based on the state variables; and calculating the error estimate of each window based on the prediction of the state fluctuation characteristics of each window according to the state transfer equations and observation equations.

[0011] In the implementation method, after the training of the dynamic disturbance filtering model is completed, the static weighing unit is disabled, and the dynamic weighing unit and the dynamic disturbance filtering model are enabled; the target item is sensed and integrated through the enabled dynamic weighing unit to obtain real-time dynamic weighing transmission data, and the dynamic disturbance filtering model is called to obtain weighing compensation data.

[0012] In the implementation method, when the dynamic weighing unit integrates multiple sensors of the same type, multiple dynamic weighing data corresponding to the multiple sensors of the same type are synchronously received; the channel characteristic vectors of the multiple sensors of the same type are calculated based on the multiple dynamic weighing data, including the weighing average value, the standard deviation of the reaction fluctuation and the difference between each channel; the multiple dynamic weighing data are fused according to the channel characteristic vector, and the real-time weighing transmission data is output.

[0013] In the implementation method, when the dynamic weighing unit integrates multiple sensors of different types, multiple dynamic weighing data corresponding to the multiple sensors of different types are synchronously received; based on the historical stability of the multiple sensors of different types, multiple credibility weights of the multiple sensors of different types are calculated; the multiple dynamic weighing data are fused according to the multiple credibility weights, and the real-time weighing transmission data is output.

[0014] The present application also provides a multi-sensor dynamic calibration system based on a mathematical model, including: a weighing transmission structure building module, used to build a dynamic weighing transmission structure, the dynamic weighing transmission structure includes a mobile platform and a weighing unit; a data acquisition module, used to connect the dynamic weighing transmission structure, and obtain a historical weighing sample data set, the historical weighing sample data set includes the historical weighing transmission data of the weighing unit and the historical movement control data of the mobile platform; a disturbance filtering module, used to train a dynamic disturbance filtering model based on the historical weighing sample data set and a weighing error label sample, the weighing error label is the historical weighing transmission data. and the error between the actual weight data of the item, wherein the dynamic disturbance filtering model includes a Kalman filter, and the mean square error loss is introduced to perform supervised training on the Kalman filter based on the historical weighing sample data set and the weighing error label sample; a weighing compensation module is used to perform sensor integration on the target item through the weighing unit, obtain real-time weighing transmission data, and send the real-time weighing transmission data to the dynamic disturbance filtering model to obtain weighing compensation data; a weighing calibration module is used to compensate and calibrate the weighing result of the target item according to the weighing compensation data, and output the calibrated weighing transmission data.

[0015] The multi-sensor dynamic calibration method and system based on a mathematical model proposed in this application are proposed by building a dynamic weighing transmission structure, which includes a mobile platform and a weighing unit; connecting the dynamic weighing transmission structure to obtain a historical weighing sample data set, which includes the historical weighing transmission data of the weighing unit and the historical movement control data of the mobile platform; training a dynamic disturbance filtering model based on the historical weighing sample data set and the weighing error label sample, wherein the weighing error label is the error between the historical weighing transmission data and the actual weight data of the item, wherein the dynamic disturbance filtering model includes a Kalman filter, and introduces a mean square error loss to perform supervised training on the Kalman filter based on the historical weighing sample data set and the weighing error label sample; performing sensor integration on the target item through the weighing unit to obtain real-time weighing transmission data, and sending the real-time weighing transmission data to the dynamic disturbance filtering model to obtain weighing compensation data; performing compensation calibration on the weighing result of the target item according to the weighing compensation data, and outputting the calibrated weighing transmission data. This solves the existing technical problem of unstable weighing data and large errors caused by factors such as object movement, conveyor belt acceleration, and vibration during dynamic weighing. Through multi-sensor fusion and disturbance compensation based on Kalman filtering, the system outputs stable, high-precision dynamic weighing results close to the true weight in dynamic environments, improving weighing accuracy and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings of the embodiments of the present disclosure are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 A schematic flow chart of a multi-sensor dynamic calibration method based on a mathematical model provided in an embodiment of the present application;

[0018] Figure 2 A schematic diagram of the structure of a multi-sensor dynamic calibration system based on a mathematical model provided in an embodiment of the present application;

[0019] Figure 3 Schematic diagram of weighing compensation of a multi-sensor dynamic calibration method based on a mathematical model provided in an embodiment of the present application.

[0020] Description of the accompanying drawings: weighing transmission structure building module 11, data acquisition module 12, disturbance filtering module 13, weighing compensation module 14, weighing calibration module 15. DETAILED DESCRIPTION

[0021] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0022] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0023] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, and the terms “first\second” involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or that are inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0024] The present application provides a multi-sensor dynamic calibration method and system based on a mathematical model, such as Figure 1 As shown, the method includes:

[0025] Step S100, building a dynamic weighing transmission structure, the dynamic weighing transmission structure includes a mobile platform and a weighing unit; step S200, connecting the dynamic weighing transmission structure, obtaining a historical weighing sample data set, the historical weighing sample data set including the historical weighing transmission data of the weighing unit and the historical movement control data of the mobile platform; step S300, training a dynamic disturbance filtering model based on the historical weighing sample data set and the weighing error label sample, the weighing error label being the error between the historical weighing transmission data and the actual weight data of the item, wherein the dynamic disturbance filtering model includes a Kalman filter, and introducing a mean square error loss to perform supervised training on the Kalman filter based on the historical weighing sample data set and the weighing error label sample.

[0026] Build a dynamic weighing transmission structure, which includes a mobile platform and a weighing unit; the mobile platform is a transmission structure that can perform the weighing function. For example, in a packaging factory, the mobile platform can be an automated conveyor belt with an adjustable speed of up to 2 meters per second to adapt to different production speed requirements. By placing items on the conveyor belt, the weighing of the items is performed by the weighing unit on the transmission structure. However, due to the influence of the movement of the items and the environmental parameters, the stability of the weighing will be affected during this period. Therefore, it is necessary to eliminate the weighing error in the subsequent processing. By connecting the dynamic weighing transmission structure, a historical weighing sample data set is obtained during the historical operation process. The historical weighing sample data set includes the historical weighing transmission data of the weighing unit based on the time series and the historical movement control data of the mobile platform and the corresponding environmental parameters. The environmental parameters include temperature data, humidity data, etc. The historical weighing transmission data is the weight reading of the items collected by the sensor. The historical movement control data is the control parameter of the conveyor belt, including: setting speed, acceleration, transportation slope and other related control data. Furthermore, the acquired historical weighing sample data set and weighing error label samples are used as training data to train a dynamic disturbance filtering model, wherein the weighing error label is the error between the historical weighing transmission data and the actual weight data of the item, wherein the dynamic disturbance filtering model includes a Kalman filter, and the mean square error loss is introduced to obtain supervised training of the Kalman filter based on the historical weighing sample data set and the weighing error label samples.

[0027] The method provided in the embodiment of the present application also includes: establishing a CAN bus communication link between the static weighing unit and the dynamic weighing unit and a central control module; placing an item sample on the static weighing unit, and storing the recorded static weighing transmission data as actual item weight data to the central control module via the CAN bus communication link; placing the item sample on the dynamic weighing unit, and storing the recorded dynamic weighing transmission data to the central control module via the CAN bus communication link; and obtaining a weighing error label sample of the item sample based on the static weighing transmission data and the dynamic weighing transmission data for training a dynamic disturbance filtering model.

[0028] The weighing unit includes a static weighing unit and a dynamic weighing unit. The static weighing unit is detachably arranged at the front end of the mobile platform, and the dynamic weighing unit is integrated into the mobile platform. The method includes: setting a static weighing unit such as a high-precision platform scale near the entrance of the conveyor belt, establishing a CAN bus communication link between the static weighing unit and the dynamic weighing unit and the central control module, and the CAN bus communication link uses a shielded twisted pair to connect each sensor, the static platform scale and the central control module in series. Subsequently, the item sample is placed in the static weighing unit, and the recorded static weighing transmission data is stored as the actual weight data of the item to the central control module through the CAN bus communication link. Subsequently, the item sample is placed in the dynamic weighing unit, and the recorded dynamic weighing transmission data is transmitted to the central control module through the CAN bus communication link. Furthermore, based on the static weighing transmission data and the dynamic weighing transmission data recorded by the central control module, by obtaining sample data in which errors exist in the static weighing transmission data and the dynamic weighing transmission data, a weighing error label sample of the item sample is obtained, wherein the weighing error label sample includes the static weighing transmission data and the dynamic weighing transmission data and corresponding error parameter labels. The weighing error label sample of the item sample is used to train the dynamic disturbance filtering model.

[0029] The method provided in an embodiment of the present application also includes: the dynamic weighing unit includes a strain sensor or a piezoelectric sensor, the number of the strain sensors or the piezoelectric sensors is at least 2, and they are distributed and integrated in the mobile platform; and is used to integrate the sensor data of the strain sensor or the piezoelectric sensor as dynamic weighing transmission data through the CAN bus communication link.

[0030] The dynamic weighing unit includes a strain gauge sensor or a piezoelectric sensor, which is evenly distributed at multiple locations. The number of strain gauge sensors or piezoelectric sensors is at least two, and they are distributed and integrated within the mobile platform. Sensor data from the strain gauge sensors or piezoelectric sensors is integrated via the CAN bus communication link as dynamic weighing transmission data.

[0031] The method provided in an embodiment of the present application also includes: the dynamic weighing unit includes a strain sensor and a piezoelectric sensor, the number of the strain sensors or the piezoelectric sensors is at least 2, and they are distributed and integrated in the mobile platform; and is used to integrate the sensor data of the strain sensor or the piezoelectric sensor as dynamic weighing transmission data through the CAN bus communication link.

[0032] The dynamic weighing unit includes a strain gauge sensor and a piezoelectric sensor. In this case, the dynamic weighing unit is equipped with different sensor types, and the strain gauge sensor and the piezoelectric sensor are evenly distributed in multiple locations. The number of the strain gauge sensor or the piezoelectric sensor is at least two, and they are distributed and integrated within the mobile platform. The sensor data of the strain gauge sensor or the piezoelectric sensor is integrated as dynamic weighing transmission data via the CAN bus communication link.

[0033] The method provided in an embodiment of the present application also includes: dividing the dynamic weighing transmission data and historical mobile control data in the historical weighing sample data set into fixed-length time windows, and extracting the state fluctuation characteristics of each window, wherein the state fluctuation characteristics include the acceleration, speed, signal fluctuation standard deviation and response delay of the current window; constructing a dynamic disturbance filtering model based on a Kalman filter, inputting the state fluctuation characteristics of each window to calculate the error estimate of each window, introducing mean square error loss to iteratively train the weighing error label samples of the historical weighing sample data set with the error estimate to obtain a dynamic disturbance filtering model.

[0034] The dynamic disturbance filtering model is trained according to the historical weighing sample data set and the weighing error label sample, and the method includes: dividing the dynamic weighing transmission data and the historical mobile control data in the historical weighing sample data set into a fixed-length time window. That is, the dynamic weighing transmission data and the historical mobile control data in the historical weighing sample data set are divided into multiple data segments according to the fixed time window. For example, the fixed-length time window can be set to 10S, and the dynamic weighing transmission data and the historical mobile control data in the historical weighing sample data set are divided into multiple data segments through the fixed-length time window. And the state fluctuation characteristics of each window are extracted, and the state fluctuation characteristics include the acceleration, speed, signal fluctuation standard deviation and response delay of the current window. For example, based on the collected historical samples, the state fluctuation characteristics of a window are extracted according to the fixed time window of 10 seconds as follows: temperature 27.6°C, humidity 36%, average acceleration 0.15m / s 2 , average speed 1.0 m / s, signal fluctuation standard deviation 5 g, response delay time 50 ms. The state fluctuation feature is used to measure the disturbance of the data in each window. The acceleration is the average acceleration within the window, the speed is the average speed within the window, the signal fluctuation standard deviation is the standard deviation of the weighing data within the window, reflecting the jitter amplitude, and the response delay is the time difference of the weighing unit's response to the movement command.

[0035] After feature extraction, a dynamic disturbance filtering model is constructed based on the Kalman filter, which serves as the core modeling method for dynamic disturbance filtering. Because different environmental parameters have different effects on weighing, the state fluctuation characteristics of the corresponding windows under different environmental parameters are input into the Kalman filter when constructing the dynamic disturbance filtering model. Initially, the Kalman filter parameters, such as the state covariance matrix and the observation covariance matrix, are set, and the predicted weighing error estimate is calculated based on the current state characteristics of each window. Furthermore, the model predicts an error estimate for each time window, indicating the possible deviation of the weighing result in that window. The mean square error (MSE) loss function is introduced to compare the error estimate with the weighing error label sample under the corresponding environmental parameters of the window in the historical weighing sample data set, that is, the difference between the dynamic weighing data and the actual weight data of the item. By minimizing the mean square error, the parameters of the Kalman filter are iteratively optimized. The iteration is continued until the model reaches stability and convergence on the validation set, thereby obtaining a dynamic disturbance filtering model that can be used for real-time compensation. The dynamic disturbance filtering model for real-time compensation can be set to multiple according to different environmental parameters. Each dynamic disturbance filtering model for real-time compensation processes real-time weighing transmission data within a range of environmental parameters.

[0036] The method provided in an embodiment of the present application also includes: the modeling of the Kalman filter includes setting state variables, defining state transfer equations and observation equations based on the state variables; and calculating the error estimate of each window based on the prediction of the state fluctuation characteristics of each window according to the state transfer equations and observation equations.

[0037] The modeling of the Kalman filter includes setting state variables, which are represented by X t = [w t , g t , v t , a t ]ᵀ, where w t is the actual weight of the item, g t Weighing sensor estimates weight, v t is the speed, a t is the acceleration. According to the state variables, the state transfer equation and observation equation are defined. The state transfer equation is in the form of: t+1 = A×X t + B×u t + c t , where A is the state transfer matrix, B is the control input matrix, t represents the current moment, u t is the control input, c t is the process noise, and the state transition equation predicts the next state from the current state. The observation equation describes the correspondence between the actual observation data of the weighing sensor and the internal state of the system. The observation equation is in the form of: t = H×X t + d t , where H is the observation matrix, d t The current state is predicted by the state transfer equation, and the observation data, i.e. the current weighing signal and motion characteristics, are used to make corrections through the observation equation and adjust the predicted state. The error estimate of the current window is then output, i.e. the estimate of the weighing error. The error estimate is compared with the historical weighing error label samples, and the hyperparameters such as the noise covariance matrix in the Kalman filter are optimized by minimizing the mean square error. By continuously correcting the state transfer matrix A, the observation matrix H, etc., the mean square error is eventually reduced to within 8% of the original error. Through the above steps, the Kalman filter continuously receives new data, updates its state estimate, and effectively extracts errors caused by changes in conveyor belt speed, acceleration or other factors from known dynamic weighing data. This allows the influence of dynamic disturbances on the weighing results to be filtered out in real time and accurately.

[0038] The method provided in an embodiment of the present application also includes: step S400, performing sensor integration on the target item through the weighing unit to obtain real-time weighing transmission data, sending the real-time weighing transmission data to the dynamic disturbance filtering model to obtain weighing compensation data; step S500, performing compensation calibration on the weighing result of the target item according to the weighing compensation data, and outputting the calibrated weighing transmission data.

[0039] After completing the training of the dynamic disturbance filtering model, the model enters the real-time application stage, and the target item is sensed and integrated through the weighing unit to obtain real-time weighing transmission data. The real-time weighing transmission data also includes the environmental data collected in the corresponding time window, namely the average temperature data and humidity data, etc., and the real-time weighing transmission data is divided into fixed-length time windows, so that the divided real-time weighing transmission data is sent to the dynamic disturbance filtering model corresponding to the current environmental parameters to obtain the weighing compensation data under the current environmental parameters. Finally, according to the obtained weighing compensation data, the weighing result of the target item is compensated and calibrated, that is, the weighing compensation data is added or subtracted from the average measurement value in each fixed-length time window to complete the calibration compensation, and the calibrated weighing transmission data is output, such as Figure 3 The figure shows a schematic diagram of a multi-sensor dynamic calibration method for weighing compensation based on a mathematical model. For example, at low speeds (0.5 m / s), the average error before calibration was ±45 g, but after calibration, it was reduced to ±3 g, a reduction of approximately 93%. Table 1 shows an example of a dynamic weighing calibration case.

[0040] Table 1: Dynamic weighing calibration case data

[0041] serial number Sensor Type Speed ​​m / s Acceleration m / s² Signal fluctuation standard deviation Response delay ms Error before calibration g Error after calibration g Percentage reduction in error 1 Strain sensor × 4 0.5 0.1 50g 50 ±45 ±3 93% 2 Piezoelectric sensor × 2 1.2 0.2 80g 80 ±78 ±6 92% 3 Hybrid sensor (strain 2 + piezoelectric 2) 2 0.3 150g 150 ±120 ±8 93% 4 Strain sensor × 6 0.8 0.15 60g 60 ±60 ±4 93% 5 Piezoelectric sensor × 4 1.5 0.25 120g 100 ±95 ±7 92.60%

[0042] This ensures that the final weighing result reflects the actual static weight of the item as closely as possible, offsetting errors caused by dynamic interference. Even at high-speed conveyor belt movement or disturbances caused by mechanical vibration, the system can stably output a weight close to the actual item weight, greatly improving the accuracy and reliability of dynamic weighing.

[0043] The method provided in the embodiment of the present application also includes: performing sensor integration on the target object through the enabled dynamic weighing unit, obtaining real-time dynamic weighing transmission data, and calling the dynamic disturbance filtering model to obtain weighing compensation data.

[0044] After the training of the dynamic disturbance filtering model is completed, the dynamic disturbance filtering model has a certain error estimation capability, and then the static weighing unit is deactivated, and the dynamic weighing unit and the dynamic disturbance filtering model are activated. The activated dynamic weighing unit is used to perform sensor integration on the target object, thereby obtaining real-time dynamic weighing transmission data. By inputting the real-time dynamic weighing transmission data into the dynamic disturbance filtering model according to fixed time length windows, weighing compensation data corresponding to each fixed time length window is obtained, and weighing data compensation is performed.

[0045] The method provided in an embodiment of the present application also includes: calculating the channel characteristic vectors of the multiple sensors of the same type based on the multiple dynamic weighing data, including the weighing average value, the standard deviation of the reaction fluctuation, and the difference between each channel; fusing the multiple dynamic weighing data based on the channel characteristic vector, and outputting the real-time weighing transmission data.

[0046] When the dynamic weighing unit integrates multiple sensors of the same type, multiple dynamic weighing data corresponding to the multiple sensors of the same type are synchronously received at the same time node. The channel characteristic vectors of the multiple sensors of the same type are calculated based on the multiple dynamic weighing data, and the channel characteristic vectors include the weighing average value, the standard deviation of the reaction fluctuation and the difference between each channel. Among them, the weighing average value is the arithmetic mean of the sampling points of the channel in a fixed time length window, and the signal fluctuation standard deviation is the standard deviation of the data of the channel in a fixed time length window, reflecting the noise level. The difference between the channels is the absolute difference between the actual measurement value of each sensor of the channel in a fixed time length and the average value of all channels in a fixed time length. Finally, the multiple dynamic weighing data are fused according to the channel characteristic vector. When performing the channel characteristic vector fusion, the channel characteristic vectors obtained from each channel are weighted and summed, and the weight is obtained based on the historical stability of the sensor, thereby outputting the real-time weighing transmission data.

[0047] The method provided in an embodiment of the present application also includes: calculating multiple credibility weights of the multiple different types of sensors based on the historical stability of the multiple different types of sensors; fusing the multiple dynamic weighing data according to the multiple credibility weights, and outputting the real-time weighing transmission data.

[0048] When the dynamic weighing unit integrates multiple different types of sensors, multiple dynamic weighing data corresponding to the multiple different types of sensors are received synchronously. According to the historical stability of the multiple different types of sensors, the credibility weights of the different types of sensors are calculated, and the historical stability is the ratio of the accurate measurement parameters to all measurement parameters in the historical records. The credibility weight of each different type of sensor is the ratio of the historical stability of each different type of sensor to the sum of the historical stability of all different types of sensors. For example, the credibility weight calculation result of the strain gauge sensor is 0.7, and the credibility weight calculation result of the piezoelectric sensor is 0.3. Weighted summation is performed according to the multiple credibility weights, thereby fusing the multiple dynamic weighing data and outputting the real-time weighing transmission data.

[0049] In the above, refer to Figure 1 The multi-sensor dynamic calibration method based on the mathematical model according to the embodiment of the present invention is described in detail. Figure 2 A multi-sensor dynamic calibration system based on a mathematical model according to an embodiment of the present invention is described.

[0050] The multi-sensor dynamic calibration system based on a mathematical model according to an embodiment of the present invention solves the technical problems of unstable weighing data and large errors caused by factors such as object movement, conveyor belt acceleration and vibration in the dynamic weighing process in the prior art. It achieves the technical effect of outputting stable and high-precision dynamic weighing results close to the actual weight through multi-sensor fusion and disturbance compensation based on Kalman filtering in a dynamic environment, thereby improving the accuracy and reliability of weighing. The multi-sensor dynamic calibration system based on a mathematical model includes: a weighing transmission structure construction module 11, a data acquisition module 12, a disturbance filtering module 13, a weighing compensation module 14, and a weighing calibration module 15.

[0051] The weighing transmission structure building module 11 is used to build a dynamic weighing transmission structure, which includes a mobile platform and a weighing unit; the data acquisition module 12 is used to connect the dynamic weighing transmission structure and obtain a historical weighing sample data set, which includes the historical weighing transmission data of the weighing unit and the historical movement control data of the mobile platform; the disturbance filtering module 13 is used to train a dynamic disturbance filtering model based on the historical weighing sample data set and the weighing error label sample, wherein the weighing error label is the error between the historical weighing transmission data and the actual weight data of the item. Difference, wherein the dynamic disturbance filtering model includes a Kalman filter, and the mean square error loss is introduced to perform supervised training on the Kalman filter based on the historical weighing sample data set and the weighing error label sample; a weighing compensation module 14 is used to perform sensor integration on the target item through the weighing unit, obtain real-time weighing transmission data, and send the real-time weighing transmission data to the dynamic disturbance filtering model to obtain weighing compensation data; a weighing calibration module 15 is used to compensate and calibrate the weighing result of the target item according to the weighing compensation data, and output the calibrated weighing transmission data.

[0052] The specific configuration of the weighing transmission structure building module 11 will be described in detail below. The weighing transmission structure building module 11 may further include: the weighing unit includes a static weighing unit and a dynamic weighing unit, the static weighing unit is detachably arranged at the front end of the mobile platform, and the dynamic weighing unit is integrated into the mobile platform, and the method includes: establishing a CAN bus communication link between the static weighing unit and the dynamic weighing unit and the central control module; placing the item sample on the static weighing unit, and storing the recorded static weighing transmission data as the actual weight data of the item to the central control module through the CAN bus communication link; placing the item sample on the dynamic weighing unit, and storing the recorded dynamic weighing transmission data to the central control module through the CAN bus communication link; obtaining a weighing error label sample of the item sample based on the static weighing transmission data and the dynamic weighing transmission data, for training the dynamic disturbance filtering model.

[0053] The specific configuration of the weighing transmission structure building module 11 will be described in detail below. The weighing transmission structure building module 11 further includes: the dynamic weighing unit includes a strain gauge sensor or a piezoelectric sensor, the number of the strain gauge sensor or the piezoelectric sensor is at least two, and the strain gauge sensor or the piezoelectric sensor is distributed and integrated within the mobile platform; and the sensor data of the strain gauge sensor or the piezoelectric sensor is integrated as dynamic weighing transmission data via the CAN bus communication link.

[0054] The specific configuration of the weighing transmission structure building module 11 will be described in detail below. The weighing transmission structure building module 11 further includes: the dynamic weighing unit includes a strain gauge sensor and a piezoelectric sensor, the number of the strain gauge sensor or the piezoelectric sensor is at least two, and they are distributed and integrated within the mobile platform; and is used to integrate the sensor data of the strain gauge sensor or the piezoelectric sensor as dynamic weighing transmission data via the CAN bus communication link.

[0055] The specific configuration of the disturbance filtering module 13 will be described in detail below. The disturbance filtering module 13 further includes: training a dynamic disturbance filtering model based on the historical weighing sample data set and the weighing error label sample, the method including: dividing the dynamic weighing transmission data and the historical mobile control data in the historical weighing sample data set into fixed-length time windows, and extracting the state fluctuation characteristics of each window; wherein the state fluctuation characteristics include the acceleration, speed, signal fluctuation standard deviation and response delay of the current window; constructing a dynamic disturbance filtering model based on a Kalman filter, inputting the state fluctuation characteristics of each window to calculate the error estimate of each window, introducing the mean square error loss to iteratively train the weighing error label samples of the historical weighing sample data set and the error estimate, and obtaining a dynamic disturbance filtering model.

[0056] The specific configuration of the disturbance filtering module 13 will be described in detail below. The disturbance filtering module 13 further includes: modeling of the Kalman filter includes setting state variables, defining a state transition equation and an observation equation based on the state variables; and calculating an error estimate for each window based on the prediction of the state fluctuation characteristics of each window according to the state transition equation and the observation equation.

[0057] The specific configuration of the weighing compensation module 14 will be described in detail below. The weighing compensation module 14 further includes: after training the dynamic disturbance filtering model is completed, deactivating the static weighing unit and activating the dynamic weighing unit and the dynamic disturbance filtering model; performing sensor integration on the target object through the activated dynamic weighing unit to obtain real-time dynamic weighing transmission data, and calling the dynamic disturbance filtering model to obtain weighing compensation data.

[0058] The specific configuration of the weighing compensation module 14 will be described in detail below. The weighing compensation module 14 further includes: when the dynamic weighing unit integrates multiple sensors of the same type, synchronously receiving multiple dynamic weighing data corresponding to the multiple sensors of the same type; calculating channel feature vectors of the multiple sensors of the same type based on the multiple dynamic weighing data, including the weighing average value, the standard deviation of the reaction fluctuation, and the difference between each channel; fusing the multiple dynamic weighing data based on the channel feature vector, and outputting the real-time weighing transmission data.

[0059] The specific configuration of the weighing compensation module 14 will be described in detail below. The weighing compensation module 14 further includes: when the dynamic weighing unit integrates multiple sensors of different types, synchronously receiving multiple dynamic weighing data corresponding to the multiple sensors of different types; calculating multiple credibility weights of the multiple sensors of different types based on the historical stability of the multiple sensors of different types; fusing the multiple dynamic weighing data according to the multiple credibility weights, and outputting the real-time weighing transmission data.

[0060] The multi-sensor dynamic calibration system based on a mathematical model provided by an embodiment of the present invention can execute the multi-sensor dynamic calibration method based on a mathematical model provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0061] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0062] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. A multi-sensor dynamic calibration method based on a mathematical model, characterized in that: The method comprises: Building a dynamic weighing and transmission structure, which includes a mobile platform and a weighing unit; Connecting the dynamic weighing transmission structure to obtain a historical weighing sample data set, wherein the historical weighing sample data set includes historical weighing transmission data of the weighing unit and historical movement control data of the mobile platform; A dynamic disturbance filtering model is trained based on the historical weighing sample data set and the weighing error label samples, where the weighing error label is the error between the historical weighing transmission data and the actual weight data of the item, wherein the dynamic disturbance filtering model includes a Kalman filter, and a mean square error loss is introduced to perform supervised training on the Kalman filter based on the historical weighing sample data set and the weighing error label samples; Performing sensor integration on the target object through the weighing unit to obtain real-time weighing transmission data, and sending the real-time weighing transmission data to the dynamic disturbance filtering model to obtain weighing compensation data; Performing compensation calibration on the weighing result of the target object according to the weighing compensation data, and outputting calibrated weighing transmission data; The weighing unit includes a static weighing unit and a dynamic weighing unit, the static weighing unit is detachably arranged at the front end of the mobile platform, and the dynamic weighing unit is integrated into the mobile platform. The method includes: Establishing a CAN bus communication link between the static weighing unit and the dynamic weighing unit and a central control module; Placing an item sample on the static weighing unit, and storing the recorded static weighing transmission data as item actual weight data in the central control module via the CAN bus communication link; Placing the article sample on the dynamic weighing unit, and transmitting the recorded dynamic weighing data to the central control module via the CAN bus communication link; Obtaining a weighing error label sample of the item sample according to the static weighing transmission data and the dynamic weighing transmission data, for training a dynamic disturbance filtering model; Training a dynamic disturbance filtering model based on the historical weighing sample data set and the weighing error label samples, the method comprising: The dynamic weighing transmission data and the historical movement control data in the historical weighing sample data set are divided into fixed-length time windows, and the state fluctuation characteristics of each window are extracted; The state fluctuation characteristics include the acceleration, velocity, signal fluctuation standard deviation and response delay of the current window; A dynamic disturbance filtering model based on the Kalman filter is constructed. The state fluctuation characteristics of each window are input to calculate the error estimation value of each window. The mean square error loss is introduced to iteratively train the weighing error label samples of the historical weighing sample data set with the error estimation value to obtain the dynamic disturbance filtering model.

2. The method according to claim 1, wherein The dynamic weighing unit includes a strain sensor or a piezoelectric sensor, the number of the strain sensor or the piezoelectric sensor is at least 2, and they are distributed and integrated in the mobile platform; Used to integrate the sensing data of the strain sensor or the piezoelectric sensor as dynamic weighing transmission data through the CAN bus communication link.

3. The method according to claim 1, wherein The dynamic weighing unit includes a strain sensor and a piezoelectric sensor, the total number of the strain sensor and the piezoelectric sensor is at least 2, and they are distributed and integrated in the mobile platform; Used to integrate the sensing data of the strain sensor and the piezoelectric sensor as dynamic weighing transmission data through the CAN bus communication link.

4. The method according to claim 1, wherein The modeling of the Kalman filter includes setting state variables, and defining a state transfer equation and an observation equation according to the state variables; According to the state transfer equation and the observation equation, an error estimate value of each window is calculated based on the prediction of the state fluctuation characteristics of each window.

5. The method according to claim 1, wherein After the training of the dynamic disturbance filtering model is completed, the static weighing unit is deactivated, and the dynamic weighing unit and the dynamic disturbance filtering model are activated; The target object is subjected to sensor integration by the enabled dynamic weighing unit to obtain real-time dynamic weighing transmission data, and the dynamic disturbance filtering model is called to obtain weighing compensation data.

6. The method according to claim 2, wherein When the dynamic weighing unit integrates multiple sensors of the same type, synchronously receiving multiple dynamic weighing data corresponding to the multiple sensors of the same type; Calculating channel feature vectors of the multiple sensors of the same type based on the multiple dynamic weighing data, including weighing averages, standard deviations of response fluctuations, and differences between each channel; The plurality of dynamic weighing data are fused according to the channel feature vector, and the real-time weighing transmission data is output.

7. The method according to claim 3, wherein When the dynamic weighing unit integrates a plurality of sensors of different types, synchronously receiving a plurality of dynamic weighing data corresponding to the plurality of sensors of different types; Calculating a plurality of credibility weights of the plurality of different types of sensors according to historical stability of the plurality of different types of sensors; The multiple dynamic weighing data are fused according to the multiple credibility weights, and the real-time weighing transmission data is output.

8. A multi-sensor dynamic calibration system based on a mathematical model, characterized in that: The system is used to perform the method according to any one of claims 1 to 7, and the system includes: A weighing and transmission structure building module is used to build a dynamic weighing and transmission structure, which includes a mobile platform and a weighing unit; A data acquisition module, configured to connect to the dynamic weighing transmission structure and acquire a historical weighing sample data set, wherein the historical weighing sample data set includes historical weighing transmission data of the weighing unit and historical movement control data of the mobile platform; A disturbance filtering module is configured to train a dynamic disturbance filtering model based on the historical weighing sample data set and the weighing error label samples, wherein the weighing error label is the error between the historical weighing transmission data and the actual weight data of the item, wherein the dynamic disturbance filtering model includes a Kalman filter, and a mean square error loss is introduced to perform supervised training on the Kalman filter based on the historical weighing sample data set and the weighing error label samples; A weighing compensation module is used to perform sensor integration on the target object through the weighing unit, obtain real-time weighing transmission data, send the real-time weighing transmission data to the dynamic disturbance filtering model, and obtain weighing compensation data; The weighing calibration module is used to perform compensation calibration on the weighing result of the target object according to the weighing compensation data, and output the calibrated weighing transmission data.

Images