Dynamic weighing error self-correction system based on multi-modal edge collaboration

Abstract

The invention relates to the technical field of dynamic weighing, and discloses a dynamic weighing error self-correction system based on multi-modal edge coordination, which comprises a multi-modal data acquisition module, a space-time alignment module, a dynamic error propagation modeling module and a coordination calibration and suppression module. According to the system, accurate positioning of an error source and whole-course tracking of a propagation path are realized through real-time construction of a vibration energy transfer topological graph and dynamic judgment of path priority, error diffusion is directly blocked by combining a piezoelectric ceramic reverse vibration wave neutralization technology, and the industrial problems of fuzzy error traceability and compensation lag in a traditional scheme are solved; through collaborative design of vibration wave velocity correction and temperature signal dynamic interpolation, space-time consistency compensation of cross-modal data is realized, and compensation logic conflicts are avoided in a cold-chain logistics temperature sudden change scene; based on an edge node intelligent dormancy and hidden fault self-sensing mechanism, the long-term stable operation of the system under the conditions of highway continuous weighing and industrial high load is ensured.

Description

Technical Field

[0001] The invention relates to a dynamic weighing error self-correction system based on multi-modal edge collaboration, belonging to the technical field of dynamic weighing. Background Art

[0002] Dynamic weighing is widely used in scenarios such as highway weight toll collection, cold chain logistics cargo monitoring, and industrial production line quality control. Traditional dynamic weighing systems rely on strain sensors to collect weight signals and eliminate environmental interference through algorithms such as temperature compensation and vibration filtering. However, the multi-physical field coupling effect under complex working conditions causes the weighing error to present dynamic propagation characteristics. The existing technology has the following limitations: 1. Existing systems usually perform independent calibration or global mean compensation on a single sensor node, but the vibration energy is transmitted between multiple nodes through the mechanical structure, resulting in the error still spreading along a fixed path after calibration. For example, the local temperature mutation caused by the opening and closing of the cold storage door in cold chain logistics will be transmitted to the adjacent weighing unit through the metal bracket, causing a chain reading jump. 2. In order to improve accuracy, the industry generally adopts multi-sensor (vibration, temperature, weighing) data fusion technology, but the acquisition timing difference between high-frequency vibration signals (1000Hz) and low-frequency temperature signals (10Hz) leads to a mismatch between the temperature compensation coefficient update and the vibration phase. In the weighing scenario of chemical reactors, this asynchronous compensation will cause periodic oscillation of the readings, requiring frequent manual intervention. 3. The mainstream solution adopts a threshold-triggered calibration strategy, but does not consider the dynamic changes of the error propagation path. For example, during peak traffic hours on highway dynamic weighing systems, fixed-cycle calibration causes 90% of edge nodes to waste computing power during inactive periods, while key node calibration lags behind, causing weighing data continuity interruption.

[0003] The traditional method assumes that the mechanical connection state of the weighing platform is constant, but the loosening of bolts and micro-cracks in welding during long-term use will cause changes in the vibration transmission path. In the dynamic weighing scenario of port cranes, such hidden faults will cause sudden weighing inaccuracies, and fault tracing will take hours. To improve the above problems, the industry has tried to improve accuracy by increasing sensor density and optimizing filtering algorithms, but sensor redundancy exacerbates data conflicts, and complex algorithms increase the burden of edge computing. Summary of the invention

[0004] The present invention provides a dynamic weighing error self-correction system based on multimodal edge collaboration, the main purpose of which is to solve the problems of uncontrollable error propagation path, multimodal data compensation conflict and inefficient calibration resource allocation in dynamic weighing.

[0005] To achieve the above-mentioned object, the present invention provides a dynamic weighing error self-correction system based on multimodal edge collaboration, comprising a multimodal data acquisition module: configured to collect vibration signals of a weighing platform at a first sampling frequency through a vibration sensor array, collect temperature signals at a second sampling frequency through a temperature sensor array, and collect weighing signals at a third sampling frequency through a weighing sensor array; Spatiotemporal alignment module: connected to the multimodal data acquisition module, configured to: perform cubic spline interpolation on the temperature signal to generate an interpolated temperature data stream, and dynamically adjust the interpolation node interval according to the main frequency of the vibration signal, which is determined by the spectrum analysis when the weighing platform is running without load; calculate the propagation time difference of the vibration signal from the source node to the target node based on the vibration wave velocity of the weighing platform material and the spatial position coordinates of the sensor node, and align the sampling time of the vibration signal and the weighing signal with the time difference as the offset; output the spatiotemporal synchronized multimodal data stream to the dynamic error propagation modeling module; Dynamic error propagation modeling module: connected to the spatiotemporal alignment module, configured to calculate the vibration energy attenuation rate between nodes in real time based on a predefined mechanical connection topology. The calculation formula of the vibration energy attenuation rate is: ,in, is the integral value of the power spectrum of the vibration signal of the source node, which is calculated by Fourier transforming the vibration signal of the source node in the spatiotemporally synchronized multimodal data stream; is the integral value of the vibration signal power spectrum of the target node, and the calculation method is the same as same; is the spatial distance between the source node and the target node; when the coherence coefficient of the vibration signal between the nodes is detected to be lower than a preset threshold, the vibration coupling weight in the mechanical connection topology is updated; according to the updated vibration coupling weight and energy attenuation rate, a vibration propagation path priority list arranged in ascending order of energy attenuation rate is generated; and the vibration propagation path priority list is output to the collaborative calibration and suppression module; Collaborative calibration and suppression module: connected to the dynamic error propagation modeling module, configured to query the vibration propagation path priority list when the signal deviation of a certain weighing sensor exceeds the preset percentage threshold of its range, and if the sensor is the starting node of the current highest priority path, it is marked as an error source node; trigger the self-calibration procedure of the error source node, the self-calibration procedure includes disconnecting the sensor power supply to reset the zero point, and updating the sensitivity compensation coefficient according to the temperature data in the spatiotemporally synchronized multimodal data stream; send a suppression instruction to all downstream nodes of the error source node, the duration of the suppression instruction is dynamically calculated according to the maximum energy decay time of the propagation path, and drive the piezoelectric ceramic piece of the downstream node to output a reverse vibration wave with a phase opposite to the interfering vibration wave to neutralize the vibration energy transmitted to this node.

[0006] As a preferred embodiment of the present invention, the first sampling frequency is high frequency sampling, and its frequency range is 800Hz to 1200Hz, the third sampling frequency is medium frequency sampling, and its frequency range is 80Hz to 150Hz, and the second sampling frequency is low frequency sampling, and its frequency range is 5Hz to 20Hz.

[0007] As a preferred embodiment of the present invention, the update logic of the vibration coupling weight includes: the initial weight is 1.0, indicating a rigid connection; when the power value of the vibration signal in the preset frequency band rises by more than 25% and the coherence coefficient drops to 0.2 to 0.4, the weight is reduced to 0.4 to 0.6; when the coherence coefficient is lower than 0.2, the weight is reset to zero and the connection relationship between the nodes is removed.

[0008] As a preferred embodiment of the present invention, the time alignment error of the spatiotemporal alignment module is less than 1 millisecond, and the alignment rules include: applying a programmable delay to the vibration signal based on the rising edge of the weighing signal; the delay step accuracy is 0.05 milliseconds to 0.2 milliseconds.

[0009] As a preferred embodiment of the present invention, the zero point reset operation of the self-calibration procedure includes: disconnecting the power supply of the weighing sensor for 3 milliseconds to 10 milliseconds; after the calibration is completed, linear interpolation compensation is performed on the weighing signal during the pause period, and the interpolation window length does not exceed 5 sampling cycles.

[0010] As a preferred embodiment of the present invention, the amplitude error control range of the reverse vibration wave is 3% to 8%, the phase control accuracy is ±5°, and the duration is dynamically adjusted according to the maximum energy decay time of the propagation path, and the adjustment coefficient is 1.1 to 1.3 times.

[0011] As a preferred embodiment of the present invention, a method for generating a driving signal for a piezoelectric ceramic piece includes: extracting the time domain waveform of the currently propagating vibration wave and performing a Hilbert transform to obtain an instantaneous phase; increasing the phase by 180° to generate a reverse driving voltage signal, and pre-compensating the signal amplitude through a calibrated frequency-amplitude curve of the piezoelectric ceramic piece, wherein the amplitude error after compensation is less than 5%.

[0012] As a preferred embodiment of the present invention, the triggering conditions of the self-calibration program include: the weighing platform is in an unloaded state or the static load fluctuation is less than 5% of the rated value; when the dynamic load change exceeds the threshold, the calibration is immediately terminated and the historical valid parameters are restored.

[0013] As a preferred embodiment of the present invention, the dynamic update rule of the main frequency of the vibration signal is: when the load change of the weighing platform exceeds 30% of the rated value, the no-load spectrum analysis is re-executed; the adjustment amplitude of the interpolation node interval after the main frequency is updated does not exceed 5% of the historical value.

[0014] Compared with the problems described in the background technology, the beneficial effects of the present invention are as follows: for scenarios such as error accumulation during continuous weighing on highways or instantaneous weighing distortion caused by sudden temperature changes in cold chain logistics, the real-time construction of the vibration energy transfer topology map and the dynamic determination of the path priority can realize the precise positioning of the error source and the full tracking of the propagation path. Combined with the piezoelectric ceramic reverse vibration wave neutralization technology, the error diffusion is directly blocked at the mechanical structure level, solving the problems of error tracing ambiguity and compensation lag in traditional dynamic weighing. The temperature drift compensation is deeply bound to the vibration phase change, and the millisecond-level self-consistency of the compensation logic is realized in temperature mutation scenarios such as cold chain logistics, avoiding the vicious cycle of compensation conflicts and precision oscillations caused by data asynchrony in traditional multi-sensor systems. The edge node coordination mechanism based on the propagation path priority enables the system to autonomously identify critical paths and dynamically allocate calibration resources. In long-term use, through the detection of abnormal resonance peaks in the vibration spectrum and the dynamic update of the connection weights, the system automatically reconstructs the propagation path model and triggers the early warning mechanism when hidden faults such as loose bolts and slight structural damage occur, so that the error correction system is always synchronized with the real state of the physical equipment, greatly improving the long-term operation reliability in industrial scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a system block diagram of the present invention; Figure 2 It is a schematic diagram of signal and data flow of the present invention; Figure 3 This is a core architecture diagram of the sensor collaborative processing system of the present invention.

[0016] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0017] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0018] The embodiment of the present application provides a dynamic weighing error self-correction system based on multi-modal edge collaboration. It includes a multi-modal data acquisition module: configured to collect vibration signals of a weighing platform at a first sampling frequency through a vibration sensor array, collect temperature signals at a second sampling frequency through a temperature sensor array, and collect weighing signals at a third sampling frequency through a weighing sensor array, wherein the first sampling frequency is higher than the third sampling frequency, and the third sampling frequency is higher than the second sampling frequency; the spatial position coordinates of the vibration sensor array, the temperature sensor array, and the weighing sensor array are pre-stored in a system memory;

[0019] Spatiotemporal alignment module: connected to the multimodal data acquisition module, configured to: perform cubic spline interpolation on the temperature signal to generate an interpolated temperature data stream, and dynamically adjust the interpolation node interval according to the main frequency of the vibration signal, which is determined by the spectrum analysis when the weighing platform is running without load; calculate the propagation time difference of the vibration signal from the source node to the target node based on the vibration wave velocity of the weighing platform material and the spatial position coordinates of the sensor node, and align the sampling time of the vibration signal and the weighing signal with the time difference as the offset; output the spatiotemporal synchronized multimodal data stream to the dynamic error propagation modeling module; Dynamic error propagation modeling module: connected to the spatiotemporal alignment module, configured to calculate the vibration energy attenuation rate between nodes in real time based on a predefined mechanical connection topology. The calculation formula of the vibration energy attenuation rate is: ,in, is the integral value of the power spectrum of the vibration signal of the source node, which is calculated by Fourier transforming the vibration signal of the source node in the spatiotemporally synchronized multimodal data stream; is the integral value of the vibration signal power spectrum of the target node, and the calculation method is the same as same; is the spatial distance between the source node and the target node, in meters; when the coherence coefficient of the vibration signal between the nodes is detected to be lower than the preset threshold, the vibration coupling weight in the mechanical connection topology is updated; according to the updated vibration coupling weight and energy attenuation rate, a vibration propagation path priority list arranged in ascending order of energy attenuation rate is generated; the vibration propagation path priority list is output to the collaborative calibration and suppression module; Collaborative calibration and suppression module: connected to the dynamic error propagation modeling module, configured to query the vibration propagation path priority list when the signal deviation of a certain weighing sensor exceeds the preset percentage threshold of its range, and if the sensor is the starting node of the current highest priority path, it is marked as an error source node; trigger the self-calibration procedure of the error source node, the self-calibration procedure includes disconnecting the sensor power supply to reset the zero point, and updating the sensitivity compensation coefficient according to the temperature data in the spatiotemporally synchronized multimodal data stream; send a suppression instruction to all downstream nodes of the error source node, the duration of the suppression instruction is dynamically calculated according to the maximum energy decay time of the propagation path, and drive the piezoelectric ceramic piece of the downstream node to output a reverse vibration wave with a phase opposite to the interfering vibration wave to neutralize the vibration energy transmitted to this node.

[0020] As a preferred embodiment of the present invention, the first sampling frequency is high frequency sampling, and its frequency range is 800Hz to 1200Hz, the third sampling frequency is medium frequency sampling, and its frequency range is 80Hz to 150Hz, and the second sampling frequency is low frequency sampling, and its frequency range is 5Hz to 20Hz.

[0021] As a preferred embodiment of the present invention, the update logic of the vibration coupling weight includes: the initial weight is 1.0, indicating a rigid connection; when the power value of the vibration signal in the preset frequency band rises by more than 25% and the coherence coefficient drops to 0.2 to 0.4, the weight is reduced to 0.4 to 0.6; when the coherence coefficient is lower than 0.2, the weight is reset to zero and the connection relationship between the nodes is removed.

[0022] As a preferred embodiment of the present invention, the time alignment error of the space-time alignment module is less than 1 millisecond, and the alignment rules include: applying a programmable delay to the vibration signal based on the rising edge of the weighing signal; the delay step accuracy is 0.05 milliseconds to 0.2 milliseconds, which is implemented by FPGA hardware.

[0023] As a preferred embodiment of the present invention, the zero point reset operation of the self-calibration procedure includes: disconnecting the power supply of the weighing sensor for 3 milliseconds to 10 milliseconds; after the calibration is completed, linear interpolation compensation is performed on the weighing signal during the pause period, and the interpolation window length does not exceed 5 sampling cycles.

[0024] As a preferred embodiment of the present invention, the amplitude error control range of the reverse vibration wave is 3% to 8%, the phase control accuracy is ±5°, and the duration is dynamically adjusted according to the maximum energy decay time of the propagation path, and the adjustment coefficient is 1.1 to 1.3 times.

[0025] As a preferred embodiment of the present invention, a method for generating a driving signal for a piezoelectric ceramic piece includes: extracting the time domain waveform of the currently propagating vibration wave and performing a Hilbert transform to obtain an instantaneous phase; increasing the phase by 180° to generate a reverse driving voltage signal, and pre-compensating the signal amplitude through a calibrated frequency-amplitude curve of the piezoelectric ceramic piece, wherein the amplitude error after compensation is less than 5%.

[0026] As a preferred embodiment of the present invention, the triggering conditions of the self-calibration program include: the weighing platform is in an unloaded state or the static load fluctuation is less than 5% of the rated value; when the dynamic load change exceeds the threshold, the calibration is immediately terminated and the historical valid parameters are restored.

[0027] As a preferred embodiment of the present invention, the dynamic update rule of the main frequency of the vibration signal is: when the load change of the weighing platform exceeds 30% of the rated value, the no-load spectrum analysis is re-executed; the adjustment amplitude of the interpolation node interval after the main frequency is updated shall not exceed 5% of the historical value, and the system's mechanical connection topology persistent storage rule is: the current topology map is stored in the non-volatile memory of the edge node every 20 to 60 seconds; the stored data includes node coordinates, directed edge weights and timestamps, and the data format is binary code or JSON array.

[0028] See also Figure 1 — Figure 3 , Figure 1The system block diagram of the dynamic weighing error self-correction system based on multimodal edge collaboration of the present invention is shown in the figure. The main modules of the system are shown in the figure, including: a multimodal data acquisition module, a spatiotemporal alignment module, a dynamic error propagation modeling module, and a collaborative calibration and suppression module. The multimodal data acquisition module collects vibration signals, temperature signals, and weighing signals through a vibration sensor array, a temperature sensor array, and a weighing sensor array, respectively. The spatiotemporal alignment module is connected to the multimodal data acquisition module, responsible for interpolating the temperature signal to generate a temperature data stream, and dynamically adjusting the interval of the interpolation nodes according to the main frequency of the vibration signal to ensure the spatiotemporal synchronization of various types of signals. The dynamic error propagation modeling module is based on the mechanical connection topology, calculates the vibration energy attenuation rate between nodes in real time, updates the vibration coupling weight, and generates a vibration propagation path priority list. The collaborative calibration and suppression module receives the vibration propagation path priority list, triggers the self-calibration program when the error source node is detected, and suppresses the interference signal through the reverse vibration wave to complete the error correction. Figure 2 The figure is a schematic diagram of the signal and data flow of the dynamic weighing error self-correction system based on multimodal edge collaboration of the present invention. The figure shows the flow process of signals and data between various modules. First, the signals from the vibration sensor array, the temperature sensor array and the weighing sensor array are collected by the multimodal data acquisition module and transmitted to the time-space alignment module according to their respective sampling frequencies. The time-space alignment module interpolates the temperature signal and dynamically adjusts it according to the main frequency of the vibration signal to ensure the time-space synchronization of the temperature signal, the vibration signal and the weighing signal. The synchronized data stream is transmitted to the dynamic error propagation modeling module, which calculates the vibration energy attenuation rate, updates the vibration coupling weight, and generates a priority list of vibration propagation paths. Finally, the data stream is sent to the collaborative calibration and suppression module, which triggers the self-calibration process after detecting the error source node according to the priority list, and suppresses the interference signal through the reverse vibration wave technology, thereby achieving error correction and suppression. See Figure 3 , which is the core architecture diagram of the sensor collaborative processing system of the present invention, including three key components: error source node, vibration sensor node and weighing sensor node. The error source node receives the vibration spectrum characteristics from the vibration sensor node through the real-time data interaction channel, and synchronously sends the error compensation parameters to the weighing sensor node. The vibration sensor node is responsible for collecting the three-axis vibration waveform of the mechanical structure. The weighing sensor node performs dynamic load calibration after receiving the compensation parameters. The three form an error suppression topology network through a closed-loop feedback mechanism, accurately realizing vibration source identification, error transfer modeling and multi-modal data collaborative processing.

[0029] Embodiment 1: In this embodiment, the multimodal data acquisition module collects vibration signals, temperature signals and weighing signals through a vibration sensor array, a temperature sensor array and a weighing sensor array respectively. The sampling frequency of each sensor array is dynamically adjusted according to the actual working conditions, that is, the vibration sensor array: dynamically adjusts the sampling frequency according to the changes in the system load to ensure that higher frequency vibration data is provided at higher loads, and reduces the sampling frequency at no load or light load. In this way, the system can reduce unnecessary data processing burdens while ensuring data accuracy. The temperature sensor array: has a low sampling frequency, usually 5Hz to 20Hz, but in an environment with sudden temperature changes, the temperature sensor will enhance its data acquisition accuracy to avoid weighing errors caused by temperature fluctuations. In this way, the system can process sensor data more efficiently, and in actual applications, it can be adjusted according to working conditions, thereby improving system stability and reliability.

[0030] The dynamic error propagation modeling module determines the vibration propagation path by calculating the vibration energy attenuation rate between nodes. In this process, the attenuation rate calculation formula is is the integral value of the power spectrum of the vibration signal of the source node, which is obtained by Fourier transform calculation, and in all calculation processes, it is normalized based on the predetermined sensor sensitivity. is the integral value of the vibration signal power spectrum of the target node, and the calculation method is the same as The same ensures that the vibration difference between the source node and the target node can be compared in actual operation. The physical distance between the source node and the target node is determined by the spatial coordinates of the sensor. The spatial distances between all nodes are pre-stored when the system is initialized to ensure the accuracy of subsequent calculations. This model ensures the degree of vibration coupling between each node and can update the connection weights between nodes according to actual conditions, further improving the accuracy of system error correction.

[0031] Embodiment 2: In this embodiment, in the dynamic error propagation modeling module of the system, the formula for the vibration energy attenuation rate is: ,in: is the integral value of the power spectrum of the vibration signal of the source node, which is derived from the Fourier transform of the vibration signal of the source node. The specific calculation method is obtained through the vibration signal of the spatiotemporal synchronous data stream; is the integral value of the vibration signal power spectrum of the target node, which is calculated by Fourier transform and is consistent with the calculation method of the source node; is the spatial distance between the source node and the target node in meters, which can be calculated by the spatial difference of the sensor position coordinates.

[0032] In this embodiment, the spatiotemporal alignment method of the vibration signal, the temperature signal and the weighing signal is specifically described, especially the accuracy of the temperature signal interpolation. The interpolation temperature data stream is generated by the cubic spline interpolation method, and the node interval is dynamically adjusted according to the main frequency of the vibration signal. The main frequency is obtained by the spectrum analysis of the weighing platform when it is running without load, and the temperature signal interpolation interval is adjusted in combination with the actual data of the vibration signal. In this process, it is ensured that the interpolation accuracy error of the temperature signal does not exceed 0.2 milliseconds, and each interpolation temperature data stream is recalibrated to cope with external temperature changes. In the dynamic error propagation modeling, when constructing the dynamic error propagation path, a more refined weight update rule is used. For example, when the power spectrum ratio of the vibration signal to the target node signal changes significantly, and the coherence coefficient decreases, the vibration coupling weight will be lowered. This update mechanism not only depends on the power difference between the signals, but also makes real-time adjustments in combination with the vibration coupling state between the nodes, ensuring the dynamic adaptability of the calibration path. This avoids the problem of error accumulation and compensation lag caused by the static vibration path in the traditional method.

[0033] To ensure that the self-calibration process can still be accurately performed under high load conditions, this embodiment further optimizes the zero point reset and calibration strategy. For example, when it is found that the signal deviation of a weighing sensor exceeds the preset threshold, the system will automatically enter the self-calibration mode. During this process, the system will first disconnect the power supply of the error source node and perform a power outage of 3 to 10 milliseconds to reset its zero point. In addition, during the calibration, for the weighing signal during the pause period, the system uses a linear interpolation algorithm to compensate for the weighing signal deviation during the period, and the interpolation window length does not exceed 5 sampling cycles. In this way, high accuracy and fast response of the calibration are ensured. And the application path of the vibration wave reverse neutralization technology ensures that the driving signal of the piezoelectric ceramic can produce an anti-phase reaction with the vibration wave. The specific method is to extract the time domain waveform of the current propagating vibration wave, perform a Hilbert transform, obtain the instantaneous phase, and generate a reverse driving voltage signal by phase reversal. The signal amplitude is compensated according to the calibration frequency-amplitude curve to ensure that the amplitude error after compensation is maintained between 3% and 8%, and the phase error is controlled within ±5°. In order to deal with hidden faults that may occur during long-term operation, this embodiment introduces abnormal resonance peak detection technology based on vibration spectrum. When the vibration signal is abnormal, the system automatically updates the vibration coupling weight and recalculates the propagation path. This mechanism can effectively avoid changes in the vibration transmission path caused by aging or microcracks of mechanical parts, thereby improving the long-term stability and reliability of the system.

[0034] Embodiment 3: The core of this embodiment is to deal with the error correction problem of the weighing platform through multimodal data acquisition and time-space alignment. For each sensor (vibration, temperature and weighing), different sampling frequencies are used for data acquisition, and different signals are aligned through the time-space alignment module to achieve accurate fusion of multimodal data. Specifically, the multimodal data acquisition module: each sensor (vibration sensor, temperature sensor, weighing sensor) collects data through an independent sampling frequency. The vibration sensor samples at a high frequency (for example, 800Hz to 1200Hz), the temperature sensor samples at a low frequency (for example, 5Hz to 20Hz), and the weighing sensor samples at an intermediate frequency (for example, 80Hz to 150Hz) for data acquisition. Such a sampling frequency setting helps to fully capture different signals and provide accuracy guarantee for subsequent data processing; time-space alignment module: The task of this module is to align the temperature signal with the vibration signal and the weighing signal. Specifically, the temperature signal generates a temperature data stream through the cubic spline interpolation method, and dynamically adjusts the interpolation node interval. The adjustment of the interpolation node is based on the main frequency of the vibration signal. In order to ensure the time alignment of all signals, the main frequency of the vibration signal can be determined based on the spectrum analysis of the weighing platform when it is unloaded, and the temperature data interpolation interval can be adjusted based on this frequency. These are all extended implementation methods known to ordinary technicians in this field.

[0035] In the error propagation modeling process, this embodiment optimizes the attenuation calculation of vibration energy between nodes, such as the vibration energy attenuation calculation: for each pair of sensor nodes and , we use the following formula to calculate the vibration energy decay rate: ,in, is the power spectrum integral value of the source node vibration signal, is the power spectrum integral value of the target node vibration signal, is the spatial distance between the source node and the target node. The power spectrum of the source node and the target node is calculated by Fourier transform. The integral value of the power spectrum reflects the strength of the signal. is the physical distance between nodes, which can be calculated from the spatial coordinates of the sensor. The purpose of this formula is to quantify the attenuation of the vibration signal during propagation. In practical applications, the power spectrum integral value and During the calculation process, the spatial position coordinates of each node when the system is initialized can be used to store these coordinate information in advance, and the attenuation rate between each pair of nodes can be calculated in combination with the spatial distance. The coupling weights between nodes are dynamically adjusted by the updated vibration attenuation rate, and the weight update mechanism is as follows: at each moment, if the coherence coefficient of the vibration signal between nodes is detected to be lower than the preset threshold, the vibration coupling weights can be dynamically adjusted. Initially, the weights between nodes are set to 1.0, indicating a rigid connection; when the amplitude of the change in the power spectrum of the vibration signal exceeds the set threshold (such as a difference of 25%), and the coherence coefficient drops to between 0.2 and 0.4, the weights between nodes will be reduced to 0.4 to 0.6; when the coherence coefficient is lower than 0.2, the connection relationship between nodes will be removed.

[0036] The self-calibration process starts when the system detects the error source node. In the original calibration logic, a more refined control step for the calibration process can be added to ensure that the zero point reset operation can still be completed quickly and accurately under high load conditions. Zero point reset and interpolation compensation: When it is detected that the deviation of a sensor exceeds the preset threshold of its range, the system will first self-calibrate the sensor. The self-calibration process will first reset the zero point by powering off, and dynamically update the sensitivity compensation coefficient according to the temperature data in the multimodal data stream. For the missing data during the sensor power-off period, the system will use a linear interpolation method to compensate, and the length of the interpolation window is limited to 5 sampling cycles to ensure the continuity and accuracy of the data during the calibration period. And this embodiment further optimizes the use of reverse vibration waves. When the error source node is identified, the system will send a suppression instruction to its downstream node, and output a reverse vibration wave with a phase opposite to the interference vibration wave through the piezoelectric ceramic to neutralize the vibration energy. The amplitude error control range of this process is set to 3% to 8%, the phase control accuracy is ±5°, the duration is dynamically adjusted according to the maximum energy decay time of the propagation path, and the adjustment coefficient is set to 1.1 to 1.3 times. In order to further improve the long-term stability and anti-interference ability of the system, this embodiment improves the fault detection and automatic reconstruction mechanism of the system, such as hidden fault detection and path reconstruction: by introducing the vibration spectrum abnormal resonance peak detection technology, the system can automatically detect hidden faults (such as loose bolts, structural microcracks, etc.) when the vibration signal is abnormal, and automatically update the vibration propagation path model. This mechanism effectively improves the stability of the system in long-term use, avoids error accumulation and system failures caused by mechanical damage, and can send fault reports in extended implementations, which are all extended implementations known to ordinary technicians in this field.

[0037] Embodiment 4: This embodiment specifically defines the calculation method and background of the power spectrum. and It is obtained through Fourier transform. The specific steps are as follows: sampling the vibration signal of each node, and dynamically adjusting the sampling frequency according to the specific environment of the node to ensure the capture accuracy of the vibration signal under high load; using Fourier transform to convert the collected time domain vibration signal into a frequency domain signal to obtain the power spectrum of the vibration signal; and are the integral values ​​of the power spectrum of the source node and the target node respectively, and the calculation formula is: ,in, It is the power spectrum of the vibration signal, which represents the power distribution of the signal at different frequency components. In this system, the vibration signal is transformed by Fourier transform to obtain the power spectrum density, which is used as a parameter to describe the change of vibration intensity with frequency. and are the minimum and maximum frequency values ​​of the signal spectrum (such as minimum 50Hz, maximum 200Hz). The parameters in the formula Represents the physical distance between nodes. Usually, the coordinate information of the nodes is stored in advance by spatially locating the sensors during system initialization. The spatial position coordinates of the sensor are dynamically calculated during data stream transmission.

[0038] The goal of the spatiotemporal alignment module is to ensure that data from different sensors can be accurately synchronized, especially in the alignment of temperature, vibration, and weighing signals. In this embodiment, the interpolation accuracy control of the temperature signal is further optimized, and the main frequency of the vibration signal is obtained based on the no-load spectrum analysis of the weighing platform, and the interpolation node interval of the temperature signal is dynamically adjusted according to the main frequency. Specifically, the main frequency of the vibration signal is recalculated whenever the load changes, and the updated main frequency value will dynamically adjust the time node interval of the temperature signal interpolation. The interpolation method of the temperature signal uses cubic spline interpolation, which can effectively reduce the interpolation error, and can ensure the smoothness and accuracy of the temperature data stream, ensuring that the spatiotemporal alignment error between the low-frequency and high-frequency signals is less than 1 millisecond. Through this dynamic adjustment mechanism, the interpolation of temperature data can effectively avoid data timing conflicts in temperature mutation scenarios, and improve the overall stability and accuracy of the system. During the self-calibration process, when the signal deviation of a weighing sensor exceeds the preset percentage threshold, the system will automatically trigger the self-calibration procedure, and in this embodiment, the missing data during the calibration will be compensated using a linear interpolation method. For example, during the power failure of the sensor, the system will perform interpolation compensation based on the previous and next data points to ensure that the continuity of the data stream will not be affected during a short power failure of 3 milliseconds to 10 milliseconds. The length of the interpolation window does not exceed 5 to 15 sampling cycles. In this way, the signal gaps caused by power failures during the calibration process can be effectively eliminated to ensure the real-time performance of the system and the integrity of the data. In addition, after the calibration is completed, the system will dynamically update the temperature compensation coefficient according to the spatiotemporally synchronized data stream, thereby further improving the accuracy and stability of the self-calibration. And in this embodiment, the generation and adjustment mechanism of the reverse vibration wave is specifically that the amplitude error of the reverse vibration wave is controlled within a range of 3% to 8%, and the phase error is controlled within ±5°. The control accuracy is achieved by real-time monitoring of the vibration state of each node in the system to ensure that the phase of the reverse vibration wave is opposite to the interference wave, suppressing the propagation of the interference signal, and the duration is dynamically calculated based on the maximum energy decay time of the vibration propagation path, and is appropriately adjusted through the adjustment coefficient (usually 1.1 to 1.3 times). This adjustment coefficient is optimized according to the different characteristics of the propagation path, thereby improving the suppression effect of the reverse vibration wave.

[0039] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0040] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A dynamic weighing error self-correction system based on multi-modal edge collaboration, characterized in that: It includes a multimodal data acquisition module: configured to acquire a vibration signal of a weighing platform at a first sampling frequency through a vibration sensor array, acquire a temperature signal at a second sampling frequency through a temperature sensor array, and acquire a weighing signal at a third sampling frequency through a weighing sensor array; Spatiotemporal alignment module: connected to the multimodal data acquisition module, configured to: perform cubic spline interpolation on the temperature signal to generate an interpolated temperature data stream, and dynamically adjust the interpolation node interval according to the main frequency of the vibration signal, which is determined by the spectrum analysis when the weighing platform is running without load; calculate the propagation time difference of the vibration signal from the source node to the target node based on the vibration wave velocity of the weighing platform material and the spatial position coordinates of the sensor node, and align the sampling time of the vibration signal and the weighing signal with the time difference as the offset; output the spatiotemporal synchronized multimodal data stream to the dynamic error propagation modeling module; Dynamic error propagation modeling module: connected to the spatiotemporal alignment module, configured to calculate the vibration energy attenuation rate between nodes in real time based on a predefined mechanical connection topology. The calculation formula of the vibration energy attenuation rate is: ,in, is the integral value of the power spectrum of the vibration signal of the source node, which is calculated by Fourier transforming the vibration signal of the source node in the spatiotemporally synchronized multimodal data stream; is the integral value of the vibration signal power spectrum of the target node, and the calculation method is the same as same; is the spatial distance between the source node and the target node; when the coherence coefficient of the vibration signal between the nodes is detected to be lower than a preset threshold, the vibration coupling weight in the mechanical connection topology is updated; according to the updated vibration coupling weight and energy attenuation rate, a vibration propagation path priority list arranged in ascending order of energy attenuation rate is generated; and the vibration propagation path priority list is output to the collaborative calibration and suppression module; Collaborative calibration and suppression module: connected to the dynamic error propagation modeling module, configured to query the vibration propagation path priority list when the signal deviation of a certain weighing sensor exceeds the preset percentage threshold of its range, and if the sensor is the starting node of the current highest priority path, it is marked as an error source node; trigger the self-calibration procedure of the error source node, the self-calibration procedure includes disconnecting the sensor power supply to reset the zero point, and updating the sensitivity compensation coefficient according to the temperature data in the spatiotemporally synchronized multimodal data stream; send a suppression instruction to all downstream nodes of the error source node, the duration of the suppression instruction is dynamically calculated according to the maximum energy decay time of the propagation path, and drive the piezoelectric ceramic piece of the downstream node to output a reverse vibration wave with a phase opposite to the interfering vibration wave to neutralize the vibration energy transmitted to this node.

2. The dynamic weighing error self-correction system based on multi-modal edge collaboration as claimed in claim 1, characterized in that: The first sampling frequency is high frequency sampling, and its frequency range is 800 Hz to 1200 Hz. The third sampling frequency is medium frequency sampling, and its frequency range is 80 Hz to 150 Hz. The second sampling frequency is low frequency sampling, and its frequency range is 5 Hz to 20 Hz.

3. The dynamic weighing error self-correction system based on multi-modal edge collaboration as claimed in claim 1, characterized in that: The update logic of the vibration coupling weight includes: the initial weight is 1.0, indicating a rigid connection; when the power value of the vibration signal in the preset frequency band rises by more than 25% and the coherence coefficient drops to 0.2 to 0.4, the weight is reduced to 0.4 to 0.6; when the coherence coefficient is lower than 0.2, the weight is reset to zero and the connection relationship between the nodes is removed.

4. The dynamic weighing error self-correction system based on multi-modal edge collaboration as claimed in claim 1, characterized in that: The time alignment error of the space-time alignment module is less than 1 millisecond. The alignment rules include: taking the rising edge of the weighing signal as the reference, applying a programmable delay to the vibration signal; the delay step accuracy is 0.05 milliseconds to 0.2 milliseconds.

5. The dynamic weighing error self-correction system based on multi-modal edge collaboration as claimed in claim 1, characterized in that: The zero reset operation of the self-calibration procedure includes: disconnecting the power supply of the weighing sensor for 3 milliseconds to 10 milliseconds; after the calibration is completed, linear interpolation compensation is performed on the weighing signal during the pause period, and the interpolation window length does not exceed 5 sampling cycles.

6. The dynamic weighing error self-correction system based on multi-modal edge collaboration as claimed in claim 1, characterized in that: The amplitude error control range of the reverse vibration wave is 3% to 8%, the phase control accuracy is ±5°, and the duration is dynamically adjusted according to the maximum energy decay time of the propagation path, with an adjustment factor of 1.1 to 1.3 times.

7. The dynamic weighing error self-correction system based on multi-modal edge collaboration as claimed in claim 1, characterized in that: The driving signal generating method of the piezoelectric ceramic piece includes: extracting the time domain waveform of the currently propagating vibration wave and performing Hilbert transform to obtain the instantaneous phase; generating a reverse driving voltage signal after increasing the phase by 180°, and pre-compensating the signal amplitude through the calibrated frequency-amplitude curve of the piezoelectric ceramic piece, and the amplitude error after compensation is less than 5%.

8. The dynamic weighing error self-correction system based on multi-modal edge collaboration as claimed in claim 1, characterized in that: The triggering conditions of the self-calibration program include: the weighing platform is in an unloaded state or the static load fluctuation is less than 5% of the rated value; when the dynamic load change exceeds the threshold, the calibration is terminated immediately and the historical valid parameters are restored.

9. The dynamic weighing error self-correction system based on multi-modal edge collaboration as claimed in claim 1, characterized in that: The dynamic update rule of the main frequency of the vibration signal is as follows: when the load change of the weighing platform exceeds 30% of the rated value, the no-load spectrum analysis is re-executed; the adjustment range of the interpolation node interval after the main frequency is updated shall not exceed 5% of the historical value.

Images