Integrated sensing module for dynamic weighing system

Abstract

The invention relates to the technical field of measurement, in particular to an integrated sensing module for a dynamic weighing system, which comprises a physical domain, an environmental domain and a virtual domain, and realizes dynamic adjustment of parameters through cross-domain interaction so as to deal with high-frequency vibration and rapid temperature difference change in a complex environment. The physical domain is responsible for collecting multi-source data, the environment domain senses external interference in real time, and the virtual domain realizes time sequence feature extraction and dynamic model updating by combining the optimization capability of a recurrent neural network and reinforcement learning. According to the technical scheme, the real-time performance and adaptability of the system are remarkably improved, the environment change trend can be accurately predicted, the weighing strategy is adjusted in advance, and the error rate is controlled to be at an extremely low level. Meanwhile, by combining a negative feedback mechanism and objective function optimization, the sampling frequency is dynamically adjusted, and the energy consumption is reduced on the basis of guaranteeing the data processing efficiency. And deep fusion of wavelet decomposition, a dynamic normalization algorithm and a neural network model is adopted, so that the accuracy and stability of data processing are greatly enhanced.

Description

Technical Field

[0001] The invention relates to the field of dynamic weighing measurement technology, and in particular to an integrated sensor module for a dynamic weighing system. Background Art

[0002] Dynamic weighing technology is a key technology used to measure the weight of a vehicle in real time while it is moving. It is widely used in logistics, highway toll stations, industrial production lines and other scenarios. Its basic principle is to collect the weight information of the vehicle or object through sensors and transmit it to the data processing unit for calculation and analysis. However, in complex environments, such as rapid temperature changes on highways, vibration interference, and the diverse types of goods in logistics and transportation, traditional dynamic weighing technology faces many challenges in terms of real-time and accuracy.

[0003] At present, in order to solve these problems, the industry usually adopts the following methods: 1. Static optimization model: static optimization of the weighing sensor parameters under fixed conditions to adapt to specific application scenarios. However, this method is difficult to respond to dynamic changes in the external environment in real time, such as drastic fluctuations in temperature or changes in vehicle vibration frequency, which leads to increased weighing errors.

[0004] 2. Sensor array redundancy design: By increasing the number and type of sensors, the comprehensiveness and redundancy of data collection can be improved. However, this approach will significantly increase system cost and maintenance complexity, and the fusion of redundant data may also introduce more noise, further reducing the stability of the system.

[0005] 3. Centralized data processing architecture: All collected data are transferred to the central processing unit for unified analysis and processing. This method has significant delays when processing high-dimensional, multi-source data, and it is difficult to meet the real-time requirements of the dynamic weighing system.

[0006] In addition, in order to address the above problems, some industries have begun to introduce dynamic compensation strategies, such as correcting data through a simple regularized feedback mechanism. However, due to the lack of deep perception and modeling of environmental interference, this strategy cannot achieve accurate compensation in highly complex application scenarios, ultimately resulting in insufficient reliability and adaptability of system operation. Summary of the invention

[0007] The present invention aims at the deficiencies in the prior art and provides the following technical solutions: An integrated sensor module for a dynamic weighing system, the module comprising: The physical domain sensor integration unit is used to collect multi-source data generated during dynamic weighing, including: The multi-source data includes object weighing data, environmental vibration data and temperature data; The physical domain sensor integration unit includes a strain gauge sensor, an acceleration sensor and a temperature sensor; The physical domain sensor integration unit preprocesses the collected data through the edge computing unit, and the preprocessing includes signal filtering, data normalization and frequency domain characteristic extraction; The environmental domain monitoring unit is used to collect and process environmental parameters in real time, including: The environmental parameters include environmental vibration frequency, temperature gradient and humidity fluctuation; The unit extracts the environmental vibration frequency characteristics through short-time Fourier transform (STFT), calculates the temperature gradient and humidity change rate through a differential algorithm, and outputs the environmental interference characteristics; The virtual domain data fusion and optimization unit is used to build a multi-domain collaborative dynamic twin model based on the data of the physical domain sensor integration unit and the environmental domain monitoring unit, wherein: The dynamic twin model includes: A dynamic prediction module based on a recurrent neural network (RNN) is used to predict the impact of vibration on weighing data based on the characteristics of environmental disturbances; An optimization module based on reinforcement learning (RL) is used to generate dynamic compensation strategies, where: The dynamic compensation strategy is generated based on the fusion of historical data and real-time data, and is used to dynamically adjust the sensitivity and sampling frequency of the sensor; The data fusion formula is: in, It refers to the data fusion result after weighted summation, which represents the comprehensive calculation value of multi-source sensor data; Indicates Preprocessing data of sensors, Indicates the weight coefficient of the corresponding sensor, weight coefficient The calculation formula is: ;

[0008] in, represents the sensor sensitivity factor; Indicates different sensor numbers; Indicates the real-time correlation between sensor and environmental data, calculated by the correlation coefficient formula: ;

[0009] in, for and environmental data The covariance of and They are and The standard deviation of The dynamic compensation unit is used to adjust the sampling parameters of the sensor in real time according to the dynamic compensation strategy generated by the virtual domain data fusion and optimization unit, wherein: The dynamic compensation includes adjusting the sensitivity, sampling frequency and data processing priority of the sensor; The dynamic compensation unit and the physical domain sensor integration unit form a closed-loop feedback; Distributed computing units are used to support the collaborative work of various units, including: the edge computing unit is used to process data from the physical domain sensor integration unit and the environmental domain monitoring unit; the central computing unit is used to run the multi-domain collaborative twin model and generate dynamic compensation strategies; the cloud optimization unit is used to integrate historical data and large-scale environmental characteristic data to optimize the twin model.

[0010] As an improvement of the above technical solution, the wavelet decomposition algorithm in the edge computing unit includes at least three levels of decomposition, and the decomposition basis function selects the Daubechies wavelet basis, which is specifically implemented through the following steps: performing discrete wavelet transform on the collected original signal; extracting high-frequency components for vibration feature analysis; combining low-frequency components to perform tilt signal correction, and finally generating a dynamic feature signal.

[0011] As an improvement of the above technical solution, the normalization processing in the environmental domain monitoring unit adopts the maximum and minimum normalization algorithm, through the formula: Calculate, where and The value of is determined based on the real-time data statistics of the environmental domain monitoring unit.

[0012] As an improvement of the above technical solution, the model training method of the recursive neural network combined with the attention mechanism in the virtual domain data fusion and optimization unit includes the following steps: constructing a multidimensional data set containing historical weighing data, vibration characteristics and environmental parameters; designing a recursive neural network structure with an attention mechanism for dynamic weight allocation; optimizing the network weights through the error back propagation algorithm, and the objective function is to minimize the root mean square value of the prediction error.

[0013] As an improvement of the above technical solution, the steps for calculating the weight coefficient include: calculating the mean and standard deviation of the real-time collected data to determine the initial weight; constructing a covariance matrix to analyze the correlation between the input features; and normalizing the weights based on the gradient descent method, with the range limited to between 0 and 1.

[0014] As an improvement of the above technical solution, the sensor sampling frequency adjustment algorithm in the dynamic compensation unit adopts negative feedback control, in which the feedback signal is the deviation between the vibration amplitude and the standard threshold, which is specifically implemented in the following ways: calculating the amplitude of the real-time vibration signal; comparing with the set threshold to determine the sampling frequency adjustment amplitude; dynamically updating the sampling frequency in the range of 100Hz to 1kHz.

[0015] As an improvement of the above technical solution, the message queue mechanism in the distributed computing unit is implemented through an event-driven mode, where event triggering includes the following conditions: the sensor signal exceeds the set threshold; a notification signal is generated after the data fusion task is completed.

[0016] As an improvement of the above technical solution, the cutoff frequency range of the high-pass filter in the physical domain sensor integration unit is 10 Hz to 50 Hz, which is used to remove low-frequency interference signals.

[0017] As an improvement of the above technical solution, the message queue mechanism is implemented based on the MQTT protocol, which specifically includes the following steps: realizing data classification transmission through multi-topic publishing; the subscriber parses and verifies the received data; and ensures data synchronization and consistency of multiple sensor nodes.

[0018] The beneficial effects of the present invention are as follows: Through the multi-domain collaborative twin model of the physical domain, environmental domain and virtual domain, the problem that traditional weighing technology is difficult to respond to complex environmental changes in real time is solved. When dealing with high-frequency vibrations and rapid temperature differences, the model dynamically adjusts parameters through cross-domain interactions, so that the dynamic weighing system can still operate accurately under multi-dimensional interference. This multi-domain collaborative technical design significantly improves the real-time and adaptability of the system; by combining the time series feature extraction capability of the recursive neural network (RNN) and the adaptive optimization capability of reinforcement learning (RL), the real-time update of the dynamic model is achieved, which not only improves the system's processing efficiency for multi-dimensional data, but also can actively predict environmental change trends and adjust the weighing strategy in advance, so that the error rate of the system in complex industrial environments is significantly reduced; and the sampling frequency is dynamically adjusted by combining the negative feedback mechanism with the objective function optimization to ensure data The processing efficiency is improved while reducing energy consumption. In particular, the real-time correction of system deviations through feedback signals avoids the waste of resources in frequent reconfiguration in traditional methods, achieving a high balance between efficiency and energy consumption. The wavelet decomposition is organically combined with the dynamic normalization algorithm and the neural network optimization model to achieve the deep integration of multiple algorithms in dynamic weighing, which greatly improves the accuracy and stability of data processing. A technical closed loop is constructed through the close coordination of the physical domain sensor integration unit, the edge computing unit and the distributed computing unit. In particular, the application of the message queue mechanism in multi-node data synchronization ensures the real-time performance and data consistency of the system, and enhances the reliability of the dynamic weighing system in a complex distributed environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is the architecture diagram of the multi-domain collaborative twin model of the present invention; Figure 2 This is a flow chart of the dynamic weighing system of the present invention. DETAILED DESCRIPTION

[0020] The following describes the embodiments of the present invention through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention.

[0021] The existing battery cabinets are closed storage to prevent the batteries from contacting the outside world. Long-term closed storage can easily lead to the inability to discharge moisture inside the battery cabinet. In addition, closed storage can easily lead to an increase in internal temperature and erosion of the batteries due to the lack of ventilation.

[0022] To resolve this issue, see Figure 1-Figure 2 , an integrated sensor module for a dynamic weighing system, the module comprising: The physical domain sensor integration unit is used to collect multi-source data generated during dynamic weighing, including: The multi-source data includes object weighing data, environmental vibration data and temperature data; The physical domain sensor integration unit includes a strain gauge sensor, an acceleration sensor and a temperature sensor; The physical domain sensor integration unit preprocesses the collected data through the edge computing unit, and the preprocessing includes signal filtering, data normalization and frequency domain characteristic extraction; The environmental domain monitoring unit is used to collect and process environmental parameters in real time, including: The environmental parameters include environmental vibration frequency, temperature gradient and humidity fluctuation; The unit extracts the environmental vibration frequency characteristics through short-time Fourier transform (STFT), calculates the temperature gradient and humidity change rate through a differential algorithm, and outputs the environmental interference characteristics; The virtual domain data fusion and optimization unit is used to build a multi-domain collaborative dynamic twin model based on the data of the physical domain sensor integration unit and the environmental domain monitoring unit, wherein: The dynamic twin model includes: A dynamic prediction module based on a recurrent neural network (RNN) is used to predict the impact of vibration on weighing data based on the characteristics of environmental disturbances; An optimization module based on reinforcement learning (RL) is used to generate dynamic compensation strategies, where: The dynamic compensation strategy is generated based on the fusion of historical data and real-time data, and is used to dynamically adjust the sensitivity and sampling frequency of the sensor; The data fusion formula is: in, It refers to the data fusion result after weighted summation, which represents the comprehensive calculation value of multi-source sensor data; Indicates Preprocessing data of sensors, Indicates the weight coefficient of the corresponding sensor, weight coefficient The calculation formula is: ;

[0023] in, It is The weight of each sensor is calculated by weighting the sensitivity of each sensor. and correlation with environmental data The weight calculation formula is for all sensors (from arrive ) are summed to obtain a normalized result; represents the sensor sensitivity factor; Indicates different sensor numbers or data sources, which can be understood as the index of the sensor, from 1 to n; Indicates the real-time correlation between sensor and environmental data, calculated by the correlation coefficient formula: ;

[0024] in, for and environmental data The covariance of and They are and The standard deviation of Sensor data ( ): represents the pre-processed data of each sensor, including weighing data, environmental vibration data and temperature data; environmental data ( ): refers to various interference factor data related to the environment, including vibration frequency, temperature and humidity; weight coefficient ( ): Dynamically calculated based on sensor sensitivity and correlation with environmental data.

[0025] The dynamic compensation unit is used to adjust the sampling parameters of the sensor in real time according to the dynamic compensation strategy generated by the virtual domain data fusion and optimization unit, wherein: The dynamic compensation includes adjusting the sensitivity, sampling frequency and data processing priority of the sensor; The dynamic compensation unit and the physical domain sensor integration unit form a closed-loop feedback; Distributed computing units are used to support the collaborative work of various units, including: the edge computing unit is used to process data from the physical domain sensor integration unit and the environmental domain monitoring unit; the central computing unit is used to run the multi-domain collaborative twin model and generate dynamic compensation strategies; the cloud optimization unit is used to integrate historical data and large-scale environmental characteristic data to optimize the twin model.

[0026] As an improvement of the above technical solution, the wavelet decomposition algorithm in the edge computing unit includes at least three levels of decomposition, and the decomposition basis function selects the Daubechies wavelet basis, which is specifically implemented through the following steps: performing discrete wavelet transform on the collected original signal; extracting high-frequency components for vibration feature analysis; combining low-frequency components to perform tilt signal correction, and finally generating a dynamic feature signal.

[0027] As an improvement of the above technical solution, the normalization processing in the environmental domain monitoring unit adopts the maximum and minimum normalization algorithm, through the formula: Calculate, where and The value of is determined based on the real-time data statistics of the environmental domain monitoring unit.

[0028] As an improvement of the above technical solution, the model training method of the recursive neural network combined with the attention mechanism in the virtual domain data fusion and optimization unit includes the following steps: constructing a multidimensional data set containing historical weighing data, vibration characteristics and environmental parameters; designing a recursive neural network structure with an attention mechanism for dynamic weight allocation; optimizing the network weights through the error back propagation algorithm, and the objective function is to minimize the root mean square value of the prediction error.

[0029] As an improvement of the above technical solution, the steps for calculating the weight coefficient include: calculating the mean and standard deviation of the real-time collected data to determine the initial weight; constructing a covariance matrix to analyze the correlation between the input features; and normalizing the weights based on the gradient descent method, with the range limited to between 0 and 1.

[0030] As an improvement of the above technical solution, the sensor sampling frequency adjustment algorithm in the dynamic compensation unit adopts negative feedback control, in which the feedback signal is the deviation between the vibration amplitude and the standard threshold, which is specifically implemented in the following ways: calculating the amplitude of the real-time vibration signal; comparing with the set threshold to determine the sampling frequency adjustment amplitude; dynamically updating the sampling frequency in the range of 100Hz to 1kHz.

[0031] As an improvement of the above technical solution, the objective function of the closed-loop control module is: in represents the system error, represents the system energy consumption, and The value of is obtained by fitting the training data. The specific optimization goal is to achieve a balance between system error and energy consumption. The specific way to achieve this balance is to introduce a dynamic optimization process, which combines reinforcement learning (RL) with recurrent neural network (RNN) to optimize both error and energy consumption. The specific optimization path is as follows: The design of the objective function: In this technical solution, the core objective function of system optimization is: ; in, represents the system error, represents the system energy consumption, and are the weight coefficients of error and energy consumption respectively. The design purpose of this objective function is to reduce the energy consumption of the system while ensuring that the system error is as low as possible. Weight coefficient and The specific value of is dynamically adjusted according to the real-time status of the system to achieve the optimal balance between error and energy consumption.

[0032] Dynamic adjustment of weight coefficients: In order to achieve a balance between error and energy consumption, and The weight coefficient needs to be dynamically adjusted according to real-time data. The specific adjustment strategy is as follows:

[0033] Error influence adjustment: When the system error ( ) exceeds the set threshold, the weight coefficient The system will prioritize reducing the error, which may be achieved by increasing the sampling frequency or enhancing the sensor sensitivity. At this time, the energy consumption may increase slightly, but the system accuracy is prioritized.

[0034] Energy consumption impact adjustment: When the system energy consumption ( ) exceeds the set threshold, If the error increases, the system will prioritize reducing energy consumption by lowering the sampling frequency or adjusting the sensor sensitivity, while moderately allowing the error to increase. In this case, the system optimizes the sampling frequency and sensitivity to keep energy consumption within an acceptable range.

[0035] Adaptive adjustment: When the system is in normal operation and the error and energy consumption are within the predetermined range, and The value of will be balanced through historical data learning to ensure that the system always maintains the optimal balance between error and energy consumption under different working conditions.

[0036] Reinforcement learning and objective function optimization: The system optimizes the objective function through reinforcement learning (RL) algorithm. The states in reinforcement learning include sensor sensitivity, sampling frequency, current error and energy consumption. The actions include adjusting the sampling frequency and sensitivity of the sensor. The reward function is based on the objective function. To evaluate the quality of the optimization strategy: ;

[0037] in, and is a balance coefficient used to control the priority of error and energy consumption. When the error or energy consumption is high, the system will dynamically adjust through the RL algorithm. and value, thereby achieving the best balance between error and energy consumption.

[0038] Combination of Recurrent Neural Network (RNN) and Reinforcement Learning, RNN is used for time series feature extraction: Recurrent Neural Network (RNN) is used to analyze the time series features of historical data and real-time data, helping the system predict the impact of environmental changes on weighing data. The output of RNN will serve as the input of the RL algorithm, providing information on how to adjust the sensor sensitivity and sampling frequency.

[0039] RL is used for dynamic policy adjustment: Through reinforcement learning algorithms, the sensitivity and sampling frequency of sensors are dynamically adjusted according to real-time data (such as temperature, humidity, vibration, etc.) and historical data. The output of RL will directly affect the system's balance between error and energy consumption.

[0040] Feedback mechanism and closed-loop control: The system uses a negative feedback control mechanism to monitor the error and energy consumption changes of sensor data in real time, ensuring that the system automatically adjusts parameters during operation to maintain a balance between error and energy consumption. The feedback mechanism calculates the real-time difference between error and energy consumption, adjusts the sampling frequency and sensitivity of the system, and thus achieves dynamic compensation. Through this optimization strategy, the system can significantly reduce energy consumption while ensuring high-precision weighing, ensuring optimal performance and efficiency in complex industrial environments.

[0041] As an improvement of the above technical solution, the message queue mechanism in the distributed computing unit is implemented through an event-driven mode, where event triggering includes the following conditions: the sensor signal exceeds the set threshold; a notification signal is generated after the data fusion task is completed.

[0042] As an improvement of the above technical solution, the cutoff frequency range of the high-pass filter in the physical domain sensor integration unit is 10 Hz to 50 Hz, which is used to remove low-frequency interference signals.

[0043] As an improvement of the above technical solution, the message queue mechanism is implemented based on the MQTT protocol, which specifically includes the following steps: realizing data classification transmission through multi-topic publishing; the subscriber parses and verifies the received data; and ensures data synchronization and consistency of multiple sensor nodes.

[0044] Embodiment 1: This embodiment uses the dynamic weighing system of a highway as a specific application scenario, and explains in detail how the technical solution of the present invention can achieve high-precision dynamic weighing in a complex environment and significantly improve real-time performance and system stability. For example, at a certain highway toll station, vehicles travel at different speeds and the environment changes dramatically, including significant temperature differences between day and night, complex road vibrations and other problems. Traditional static weighing methods cannot meet real-time detection requirements, and existing dynamic weighing technologies have low accuracy and poor stability under high-frequency vibrations and temperature changes. This embodiment solves the above problems based on a multi-domain collaborative dynamic twin model combined with multi-algorithm optimization.

[0045] First, the wheel pressure, road vibration and temperature data are collected in real time through a multi-source sensor network in the physical domain. Specifically, high-sensitivity strain sensors and vibration sensors are embedded in the ground of the toll station, and infrared temperature sensors are set up in the measurement area to ensure the multidimensionality and accuracy of the collected data.

[0046] The collected data is initially processed by the edge computing unit. The vibration signal is de-noised using the wavelet decomposition algorithm, and the multi-dimensional data differences are smoothed using the dynamic normalization algorithm to avoid data distortion. The processed high-priority data is transmitted to the central computing unit in real time, and the low-priority data enters the regular compensation path.

[0047] In the central computing unit, the virtual domain of the twin model calculates the vehicle load in real time. The model extracts time series features based on a recurrent neural network (RNN) and dynamically adjusts model parameters in combination with reinforcement learning (RL) to adapt to the changing state of high-speed vehicles. For example, when a vehicle passes a speed bump, the system quickly identifies interference through a reinforcement learning algorithm and adjusts weight parameters to eliminate the impact of instantaneous vibration.

[0048] In addition, this embodiment introduces the environment domain as a compensation layer, and uses environmental sensors to capture real-time information on the temperature difference between day and night and humidity changes to compensate for the error between the physical domain and the virtual domain. Through the negative feedback mechanism, the real-time parameters of the environment domain directly correct the dynamic calculation process of the twin model, further improving the overall accuracy of the system.

[0049] The multi-domain collaborative architecture of this technical solution, especially with the support of the dynamic resource scheduling mechanism, significantly reduces data processing delay. Experimental data shows that in a high-speed dynamic weighing scenario at 120km / h, the system's weighing error is controlled within 0.03%, data processing delay is reduced by 40%, and energy consumption is reduced by about 25%.

[0050] In summary, this embodiment achieves high precision, low latency and high reliability of the dynamic weighing system in complex scenarios through the deep integration of the physical domain, environmental domain and virtual domain, as well as the real-time dynamic calculation method of multi-algorithm optimization.

[0051] Embodiment 2: For example, in a large intelligent logistics center, materials are dynamically sorted by automated conveyor belts. The ambient temperature varies greatly, and the vibration frequency of the conveyor belt fluctuates significantly due to different loads. Traditional weighing systems cannot effectively eliminate vibration interference, resulting in insufficient data accuracy and poor real-time performance. The present invention solves this problem through a multi-domain collaborative twin model of the physical domain, environmental domain, and virtual domain, combined with multi-level anti-interference and dynamic optimization strategies.

[0052] Experimental setup: For example, high-precision strain sensors and vibration sensors are arranged on the logistics sorting line, and a physical domain data acquisition system is built in combination with temperature and humidity sensors. The edge computing unit uses wavelet decomposition to reduce the noise of the vibration signal and uses a dynamic normalization algorithm to smooth the data difference. The virtual domain extracts the dynamic parameters of the resource through a recursive neural network (RNN) and combines the reinforcement learning (RL) algorithm to achieve adaptive optimization of the model parameters. The environmental domain compensates for the real-time changes in temperature and humidity and dynamically corrects the weighing model in the virtual domain.

[0053] Comparative experiment and results: The experiment compares the performance of the traditional static weighing system, the conventional dynamic weighing system and the dynamic weighing system of the present invention. Under the conditions of ambient temperature fluctuation range of -5°C to 40°C and vibration frequency of 10Hz to 100Hz, the weighing error, data processing delay and energy consumption performance were tested. The results show that the weighing error of the present invention is controlled at 0.02%, which is significantly lower than the 0.15% error of the traditional dynamic weighing system; the data processing delay is reduced by about 45%, from 150ms of the traditional system to 80ms of the system of the present invention; the system energy consumption is reduced by about 30%, thanks to the collaborative work of the edge computing unit and the dynamic resource scheduling mechanism. Through multi-domain collaboration and dynamic optimization, the present embodiment achieves a significant improvement in the accuracy of dynamic weighing, while having extremely high real-time and environmental adaptability. Especially when dealing with high-frequency vibrations and drastic temperature differences, the system dynamically adjusts the weighing strategy through feedback mechanism and model layer compensation, effectively solving the instability problem in the traditional system.

[0054] Embodiment 3: In this embodiment, the physical domain sensor integration unit continues to be responsible for collecting multi-source data generated during the dynamic weighing process. In order to improve the accuracy of data collection, this unit uses strain gauge sensors, acceleration sensors and temperature sensors. Their distribution and layout take into account the interference factors of different environments on the weighing system. The specific layout method is as follows: strain gauge sensors: installed under the weighing platform to detect the weight of the object; acceleration sensors: placed at both ends of the weighing platform to monitor the vibration information of the platform in real time; temperature sensors: used to collect ambient temperature so as to make dynamic compensation in subsequent data processing; data is preprocessed in real time through the edge computing unit. The preprocessing steps include signal filtering, data normalization, frequency domain feature extraction and preliminary application of wavelet decomposition algorithm. Here, the three-level decomposition scheme of wavelet decomposition is particularly emphasized. The Daubechies wavelet basis used can effectively extract the high-frequency part of the vibration signal for feature analysis.

[0055] In order to further improve the perception and adaptability to environmental changes, the environmental domain monitoring unit is responsible for real-time monitoring and processing of external environmental parameters. This includes environmental vibration frequency monitoring: extracting environmental vibration frequency characteristics through short-time Fourier transform (STFT); temperature gradient and humidity fluctuation monitoring: using differential algorithms to calculate temperature gradient and humidity change rates to ensure accurate tracking of environmental changes; all environmental parameter collection and analysis are pre-processed by the edge computing unit to reduce data latency.

[0056] The core of the virtual domain data fusion and optimization unit is to build a multi-domain collaborative dynamic twin model. The compensation and adjustment of dynamic data are realized through the combination of recursive neural network (RNN) and reinforcement learning (RL). The specific process is as follows: Recursive neural network (RNN): used to extract long-term dependencies in time series data and predict the impact of environmental changes on weighing data; Reinforcement learning (RL): based on the fusion of historical data and real-time data, dynamically adjust the sensitivity and sampling frequency of the sensor; Data fusion formula: ;

[0057] in, Indicates Preprocessing data of sensors, is the sensor weight coefficient, and the calculation formula of the weight coefficient is: ;

[0058] in, is the sensor sensitivity factor, Indicates different sensor numbers; is the real-time correlation between the sensor and the environment data. The correlation is calculated by the following covariance formula: ;

[0059] in, is the covariance between sensor data and environmental data, and are the standard deviations of the two respectively.

[0060] The dynamic compensation unit uses a negative feedback control algorithm to adjust the sensor sampling frequency and sensitivity in real time. The compensation unit forms a closed-loop feedback with the physical domain sensor integration unit to ensure real-time adjustment of sensor performance to cope with environmental interference; and sampling frequency adjustment: dynamically adjust the sampling frequency according to the deviation of the vibration amplitude from the preset threshold, ranging from 100Hz to 1kHz.

[0061] The distributed computing unit supports the collaborative work between modules. The edge computing unit performs preliminary data processing, the central computing unit is responsible for running the multi-domain collaborative twin model and generating compensation strategies, and the cloud optimization unit integrates historical data for large-scale optimization. The message queue mechanism is based on the MQTT protocol, and data is published through multiple topics to ensure data synchronization and consistency. In addition, in terms of hardware requirements, the physical domain sensor integration unit requires high-precision strain gauge sensors, acceleration sensors, and temperature sensors, and is equipped with edge computing devices to support real-time preprocessing of data; the software requirement is that the system must support the real-time computing capabilities of RNN and RL algorithms, and have data fusion and feedback control mechanisms. The execution steps are: the first step is that the sensor collects data and preprocesses it through the edge computing unit; the second step is that the environmental domain monitoring unit monitors and processes external interference information in real time; the third step is that the virtual domain data fusion and optimization unit adjusts the compensation strategy according to real-time data; finally, the dynamic compensation unit adjusts the sampling frequency in real time through the negative feedback mechanism to ensure the stability and high accuracy of the system.

[0062] Embodiment 4: This embodiment is based on the technical solution of Example 3, and through experimental verification and supplementary explanation, demonstrates the implementation path and effect of the technical solution in practical application. For example, in a dynamic weighing system of a logistics park, the following experimental design is carried out to verify the effectiveness of the technical solution, and its experimental conditions are: Ambient temperature: -10°C to 50°C; vibration frequency: 5Hz to 200Hz; vehicle speed: 0 to 120km / h; in terms of system settings, sensor configuration: including high-sensitivity strain gauge sensors, three-axis acceleration sensors and temperature and humidity sensors; edge computing unit: running wavelet decomposition algorithm and dynamic normalization algorithm; central computing unit: executing multi-domain collaborative twin model; test data: comparing the weighing accuracy, delay and energy consumption of traditional static weighing systems, existing dynamic weighing systems and the system of the present invention.

[0063] The experimental results show that the weighing accuracy: the weighing error of the system of the present invention is 0.02%, which is better than the traditional system (0.15%) and the existing dynamic system (0.05%); data delay: the delay is reduced from 120ms of the traditional system to 80ms; energy consumption optimization: the dynamic compensation strategy reduces the overall energy consumption by 30%.

[0064] And to further illustrate the implementation path of recurrent neural network (RNN) and reinforcement learning (RL) in dynamic compensation strategy, this embodiment adopts the following specific steps: data preprocessing: the collected weighing data and environmental parameters (vibration frequency, temperature and humidity) are normalized through the edge computing unit; feature extraction: wavelet decomposition is used to reduce the noise of high-frequency signals; RNN model construction: construct a time series feature data set, including historical weighing data and real-time environmental parameters; model structure: the hidden layer of RNN uses GRU (gated recurrent unit) to improve training efficiency; training goal: minimize mean square error (MSE) and optimize the time series prediction of weighing data; and RL strategy optimization, state: current sampling frequency and weighing error of the system; action: adjust the sampling frequency and sensitivity of the sensor; reward function: dynamically balance the system performance according to the weighing error and energy consumption optimization goals. Its combined logic is that RNN predicts the impact of environmental parameter changes on weighing data and provides reference input; RL generates the optimal compensation strategy in real time based on the prediction results of RNN.

[0065] At the same time, in order to adapt to large-scale data calculations, this embodiment simplifies the description of the data fusion formula, clarifies the scope of application and defines the calculation logic. Fusion formula: ;

[0066] in: is the sensor weight, which has been clearly defined in Example 3. When the number of sensors is large, a parallel computing mode is adopted to partition the processing weight coefficient and the weighted sum of the data.

[0067] : No. The weight coefficient of each sensor indicates the importance of the sensor in data fusion. The weight is determined by the sensitivity of the sensor. Its correlation with environmental data Joint decision.

[0068] : No. The correlation between a sensor and environmental data indicates the correlation between the sensor output signal and the environmental interference signal. Its value is usually between 0 and 1, and the larger the value, the higher the correlation.

[0069] : No. The sensitivity factor of a sensor indicates the degree of response of the sensor to the input signal. The range is limited (0.1 to 1.0) to ensure the stability of calculation. The present invention strengthens the following technical effects by introducing experimental data and optimization logic: for example, by combining RNN and RL, the adaptability of the system to environmental changes is significantly improved; the impact of vibration and temperature changes on weighing accuracy can be predicted in advance and the sampling parameters can be adjusted; the dynamic compensation strategy effectively reduces the power consumption of the system, especially in high-frequency vibration scenarios. Experimental results show that the system of the present invention can maintain high accuracy and low latency in a variety of complex scenarios.

[0070] Embodiment 5: This embodiment introduces a multi-objective dynamic compensation strategy generation method, which ensures the accuracy and real-time performance of the system in high-dynamic scenarios through a reinforcement learning (RL) model and a real-time feedback mechanism. For example, in traditional compensation strategies, the main goal is to minimize the error. This embodiment further incorporates system energy consumption optimization into the objective function and adopts the following multi-objective optimization formula: ;

[0071] in: : System error, calculated from the real-time and predicted error of weighing data; : System energy consumption,estimated by sensor sampling frequency and computing node power consumption; and : Represent the weight coefficients of error and energy consumption respectively, which are obtained by dynamic fitting of historical data and range from 0.1 to 1.0.

[0072] The specific implementation steps are: state variable design: taking the current sensor's sensitivity factor, sampling frequency and system error as the input state of the reinforcement learning model; action space design: defining the action as the dynamic adjustment of the sensor sampling frequency and sensitivity; reward function design: in, and is a balance coefficient used to dynamically adjust the priority between error and energy consumption.

[0073] In addition, in another optimization path, such as the dynamic adaptation method of variable weights, in order to improve the fusion accuracy of multi-source data, this embodiment improves the calculation formula of weight coefficients, such as the distributed calculation of weight coefficients, The calculation formula is: ;

[0074] in: : Real-time correlation of sensor data with environmental data; : Sensitivity factor, whose dynamic value is calculated by the following formula: ; : Adjustment coefficient, controls the sensitivity adjustment rate; : standard deviation of sensor data; : The mean of multi-sensor data; in its multi-threaded computing optimization, the weight calculation adopts distributed parallel processing, the sensor data is partitioned and the weights are calculated independently, and finally merged through centralized nodes to reduce computing delays.

[0075] This example uses the logistics sorting center as an experimental scenario to verify the optimized path: Experimental environment, temperature range: -20°C to 50°C; vibration frequency: 10Hz to 120Hz; vehicle speed: 0 to 120km / h; sensor configuration: high-sensitivity strain gauge sensor, triaxial acceleration sensor and temperature and humidity sensor.

[0076] The experimental design and data are as follows: the experimental samples include 10 small cars, medium trucks and heavy trucks, with a load range of 1 ton to 40 tons, and are tested in static, low-speed (10km / h), medium-speed (60km / h) and high-speed (120km / h) scenarios. Each group of conditions is tested 10 times and the average value is taken.

[0077] Experimental results show that weighing accuracy: the error is reduced from 0.03% of the traditional system to 0.015%, and the standard deviation is 0.005%; processing delay: reduced from the traditional 90ms to 60ms, mainly due to the optimization of the distributed computing mechanism; energy consumption: the average energy consumption under multiple conditions is reduced by 20%, up to 30%, especially in high-frequency vibration scenarios.

[0078] Embodiment 6: In order to further optimize the dynamic weighing system mentioned in the present invention, this embodiment proposes a dynamic compensation strategy, which focuses on enhancing the response accuracy to environmental changes and improving its real-time performance and energy efficiency through system-level optimization algorithms. This embodiment pays special attention to how to accurately capture environmental interference and dynamically compensate for weighing results under complex environmental conditions to maximize the reliability and stability of the system.

[0079] In this embodiment, the dynamic weighing system is still based on the physical domain sensor integration unit, environmental domain monitoring unit, virtual domain data fusion and optimization unit, dynamic compensation unit and distributed computing unit to work together. However, in this embodiment, the dynamic compensation algorithm of the data processing part is particularly strengthened, and an environmental adaptive feedback mechanism is introduced, so that the system can automatically adjust parameters when environmental conditions change and maintain high-precision weighing function.

[0080] In this system, the physical domain sensor integration unit continues to undertake the task of collecting multi-source data, including object weighing data, environmental vibration data, and temperature data. All sensors are installed in protective devices that can withstand complex environmental changes to ensure their stability.

[0081] The environmental domain monitoring unit analyzes environmental parameters through short-time Fourier transform (STFT) and differential algorithm, monitors temperature difference, humidity change and vibration frequency in real time, and generates corresponding environmental interference characteristics. These characteristics are then transmitted to the virtual domain data fusion and optimization unit for subsequent compensation strategy design.

[0082] The edge computing unit is responsible for the preliminary preprocessing of the collected data. This process includes operations such as signal filtering, data normalization, and frequency domain feature extraction, especially the denoising of high-frequency vibration signals. The wavelet decomposition algorithm is fully used in this process to separate the high-frequency part of the vibration signal and reduce the error caused by vibration.

[0083] The dynamic compensation unit dynamically adjusts the sampling frequency and sensitivity of the sensor according to the environmental interference data provided by the edge computing unit through a negative feedback control mechanism. The purpose is to ensure that when the environmental interference is large, the system can automatically adjust the sampling frequency and reduce the measurement error. This feedback mechanism ensures that the system has high adaptability and accuracy.

[0084] The virtual domain data fusion and optimization unit combines recurrent neural networks (RNN) and reinforcement learning (RL) algorithms to optimize the data fusion process of sensors. The RNN network extracts the impact of environmental changes on weighing data through time series analysis, while RL optimizes the compensation strategy through training. Specifically, the data fusion formula is: ;

[0085] in, is the preprocessed data of the i-th sensor, is the weight coefficient of the corresponding sensor, and the calculation formula is as follows: ;

[0086] For the real-time correlation between sensor and environmental data, the covariance formula is: ;

[0087] In the above formula, Represents environmental data, is the sensor data, covariance It is used to measure the relationship between environmental interference and sensor data, and the standard deviation and is used to standardize the covariance. And in this embodiment, reinforcement learning (RL) is used to generate a dynamic compensation strategy. The state variables of RL include the current sensor sensitivity, sampling frequency, and system error; the action variables are to adjust the sampling frequency and sensitivity; the reward function combines the system error and energy consumption optimization goals to generate the optimal strategy. The formula is as follows: ;

[0088] in, and is the balance coefficient, which is used to dynamically adjust the priority between error and energy consumption according to the current environmental status and system requirements. At the same time, in order to ensure the real-time performance and data consistency of the system, the distributed computing unit works in conjunction with the message queue mechanism through the event-driven mode. The data in the system is classified and transmitted through the MQTT protocol to ensure data synchronization and consistency among multiple sensor nodes.

[0089] Embodiment 7: This embodiment further optimizes the key parts of the dynamic weighing system, focusing on solving challenges in data fusion, dynamic compensation, feedback regulation and system optimization, ensuring that the system can operate stably, efficiently and accurately under complex environmental conditions. Specifically, the system uses high-precision strain gauge sensors, acceleration sensors and temperature and humidity sensors to collect multi-source data related to weighing in real time. All signals collected by the sensors will be preprocessed by the edge computing unit. The preprocessing steps include:

[0090] Signal filtering: A high-pass filter is used to remove low-frequency noise signals to ensure that only valid information related to the weighing data is transmitted; Data normalization: The output data of all different sensors will be standardized through the maximum and minimum normalization algorithm to ensure that the data of different sensors can be compared at the same scale; Feature extraction: The vibration signal is decomposed into three levels using the wavelet decomposition algorithm to extract high-frequency components for further vibration analysis, while the low-frequency components are used to correct the tilt signal in the data; Through the above steps, the system can eliminate noise and instability in the data and ensure the consistency and reliability of all collected data.

[0091] In order to cope with the impact of external environment (such as temperature changes, humidity fluctuations and vibration interference) on weighing data, the environmental domain monitoring unit collects environmental data in real time, including vibration frequency, temperature gradient and humidity fluctuation. The environmental data is processed by the following methods:

[0092] Short-time Fourier transform (STFT): used to extract the frequency characteristics of environmental vibration, identify and quantify the impact of vibrations of different frequencies on weighing accuracy; Differential algorithm: calculates the temperature gradient and humidity change rate, monitors the changes in environmental conditions in real time, and generates environmental interference characteristics; These environmental data will be fused with the physical domain (sensor data) through the following steps: Weighted fusion: The data of each sensor will be given different weights according to its sensitivity and correlation with environmental interference. Sensors with greater environmental impact will receive higher weights. Data fusion formula: The weighted data will be fused into the final weighing data through weighted averaging to ensure that the weighing results accurately reflect the impact of environmental changes. Through this data fusion technology, the system can more accurately handle the interference of complex environments on weighing data and improve the accuracy of the overall weighing system.

[0093] At the same time, the system introduces a dynamic compensation strategy, which adjusts the sampling frequency and sensitivity of the sensor in real time through a feedback mechanism to ensure that the weighing accuracy is not affected by environmental interference: Dynamic compensation strategy: When the system detects changes in the ambient vibration frequency or temperature fluctuations, the compensation strategy automatically adjusts the sampling frequency of the sensor. For example, when vibration increases, the system increases the sampling frequency to capture more details and ensure accuracy; Negative feedback control: The system continuously monitors the deviation between the sensor data and the standard value through a negative feedback mechanism, and automatically adjusts the parameters to reduce the error. The feedback signal determines the adjustment amplitude of the sampling frequency by calculating the deviation between the amplitude of the real-time vibration signal and the set threshold, and the adjustment range is 100Hz to 1kHz; This mechanism enables the system to respond to environmental changes in real time, automatically adjust the working parameters, and ensure weighing accuracy.

[0094] And on the basis of dynamic compensation, this embodiment introduces an energy efficiency optimization strategy to ensure that the system can reduce energy consumption while maintaining high precision, such as the balance between error and energy consumption: the system monitors the weighing error and energy consumption in real time, and balances the two through adaptive adjustment strategies. Specifically, when the system error increases, the sampling frequency will be increased first to improve the weighing accuracy; and when the energy consumption increases, the sampling frequency will be reduced to save energy; Energy efficiency optimization formula: The system uses an adaptive adjustment mechanism to ensure that low energy consumption is always maintained during the working process without sacrificing accuracy. The adjustment process matches the changes in sampling frequency and sensitivity with real-time data to ensure optimal energy efficiency. This optimization strategy enables the system to work in high-precision mode while reducing unnecessary energy consumption.

[0095] In order to further improve the adaptability and optimization ability of the system, this embodiment combines recursive neural network (RNN) and reinforcement learning (RL). Recursive neural network (RNN): used to analyze time series data, especially to extract long-term dependencies from historical weighing data and environmental parameters, to help the system predict the impact of future environmental changes on weighing results; reinforcement learning (RL): based on the extraction of time series features by RNN, the reinforcement learning algorithm is used to optimize the compensation strategy. The system adaptively adjusts the sensor sensitivity and sampling frequency through reinforcement learning, and dynamically generates the optimal compensation strategy; through the combination of RNN and RL, the system can optimize data collection and compensation strategies under different environmental conditions, and improve the accuracy and efficiency of the system.

[0096] Embodiment 8: This embodiment explains in detail how to use the multi-domain collaborative model to optimize data fusion and dynamic compensation strategies to ensure accurate weighing of the system in complex environments. For example, the data acquisition and preprocessing module is mainly responsible for the acquisition and preprocessing of multi-source data such as the weight of the object, environmental vibration, and temperature during dynamic weighing. To ensure data quality, high-precision strain gauge sensors, acceleration sensors, and temperature sensors are used and installed on the weighing platform, near the vibration source, and in appropriate locations in the environment.

[0097] The collection process is as follows: weighing data collection: the strain gauge sensor is directly installed under the weighing platform to detect the wheel pressure in real time and convert it into weight data; environmental vibration data collection: the acceleration sensor is arranged at both ends of the weighing platform to collect the vibration signal generated by the passing vehicle; temperature data collection: the temperature sensor is installed in the surrounding environment to monitor temperature fluctuations in real time to ensure compensation in the case of temperature difference changes.

[0098] The data preprocessing process is to use the wavelet decomposition algorithm to reduce the noise of the vibration signal and extract the environmental vibration frequency characteristics through short-time Fourier transform (STFT); the data normalization adopts the maximum and minimum normalization algorithm through the formula: Ensure that the collected data from various sensors are compared and fused in the same dimension.

[0099] Then, a multi-domain collaborative data fusion method is used to integrate the collected data from the physical domain, environmental domain, and virtual domain into a unified model. In order to process high-dimensional data and eliminate redundant noise, the weighted average method is used to weight the data of each sensor. The formula is as follows: ;

[0100] in, For the Preprocessing data of sensors, is the weight coefficient of the sensor, defined as: ;

[0101] in, For the Sensors and environmental data The real-time correlation between them is calculated as follows: ;

[0102] After data fusion is completed, the system automatically adjusts the sampling frequency and sensitivity of the sensor based on the combined effect of reinforcement learning (RL) and recurrent neural network (RNN). The compensation process uses negative feedback control to ensure that the system can make real-time adjustments when the environment changes:

[0103] Feedback mechanism: monitor the amplitude of the vibration signal in real time, compare it with the set threshold, and dynamically adjust the sampling frequency of the sensor according to the error to ensure measurement accuracy; Sampling frequency adjustment formula: Assume that the amplitude of the vibration signal is , the standard threshold is , sampling frequency The adjustment range is from 100Hz to 1kHz: ;

[0104] The Adjust function is used to adjust the current data of the sensor and set thresholds The difference between the two dynamically calculates the required sampling frequency The implementation of this function can be based on simple proportional control or adjusting the frequency according to the difference in signal amplitude, with the aim of improving the system's responsiveness in a rapidly changing environment. For example, when the system detects a large signal difference, it will automatically increase the sampling frequency to improve the accuracy of capturing data details.

[0105] The role of reinforcement learning (RL) in this embodiment is to dynamically adjust the weight coefficient, sampling frequency and sensitivity so that the system can achieve the best balance between error and energy consumption. The state variables include the current sensor sensitivity, sampling frequency, error and energy consumption. The reward function is designed as: ;

[0106] in, Represents the weighing error of the system, represents the system energy consumption, and It is the balance coefficient, which adjusts the priority of error and energy consumption according to the real-time environment.

[0107] The role of RNN in this embodiment is to analyze time series data, extract the relationship between historical data and real-time data, and especially predict the impact of environmental changes on weighing data. The output of RNN is passed to the RL module to guide the dynamic adjustment of sampling frequency and sensitivity.

[0108] Its hardware requirements include high-precision strain gauge sensors, acceleration sensors, and temperature and humidity sensors that can collect multi-source data generated during dynamic weighing in real time; the edge computing unit is required to have strong data processing capabilities, capable of processing sensor data in real time and preprocessing; the central computing unit needs to run a multi-domain collaborative twin model and dynamically adjust system parameters in combination with RL optimization strategies. In addition, its software requirements are that the system needs to support real-time calculation of algorithms based on recursive neural networks (RNN) and reinforcement learning (RL), and have data fusion, dynamic compensation, and feedback control mechanisms, and be able to adjust the sensor sampling frequency and sensitivity in real time to ensure the accuracy and stability of the system in complex environments. These are all extended implementation methods that can be known to ordinary technicians in this field.

[0109] The above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them. Anyone familiar with the technology can modify or change the above embodiments without violating the spirit and scope of the present invention. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed by the present invention should still be covered by the claims of the present invention.

Claims

1. An integrated sensor module for a dynamic weighing system, characterized in that: The module includes: a physical domain sensor integration unit, which is used to collect multi-source data generated during dynamic weighing, wherein: the multi-source data includes the weighing data of the object, the environmental vibration data and the temperature data; the physical domain sensor integration unit includes a strain gauge sensor, an acceleration sensor and a temperature sensor; the physical domain sensor integration unit pre-processes the collected data through an edge computing unit, and the pre-processing includes signal filtering, data normalization and frequency domain characteristic extraction; an environmental domain monitoring unit, which is used to collect and process environmental parameters in real time, wherein: the environmental parameters include environmental vibration frequency, temperature gradient and humidity fluctuation; the unit extracts the environmental vibration frequency characteristics through short-time Fourier transform STFT, calculates the temperature gradient and humidity change rate through a differential algorithm, and outputs the environmental interference characteristics; a virtual domain data fusion and optimization unit, which is used to build a multi-domain collaborative dynamic twin model based on the data of the physical domain sensor integration unit and the environmental domain monitoring unit, wherein: the dynamic twin model includes: A dynamic prediction module based on a recurrent neural network (RNN) is used to predict the impact of vibration on weighing data according to the characteristics of environmental interference; an optimization module based on reinforcement learning (RL) is used to generate a dynamic compensation strategy, wherein: the dynamic compensation strategy is generated by fusing historical data with real-time data and is used to dynamically adjust the sensitivity and sampling frequency of the sensor; The data fusion formula is: in, It refers to the data fusion result after weighted summation, which represents the comprehensive calculation value of multi-source sensor data; Indicates Preprocessing data of sensors, Indicates the weight coefficient of the corresponding sensor, weight coefficient The calculation formula is: in, represents the sensor sensitivity factor; Indicates different sensor numbers; Indicates the real-time correlation between sensor and environmental data, calculated by the correlation coefficient formula: in, for and environmental data The covariance of and They are and A dynamic compensation unit is used to adjust the sampling parameters of the sensor in real time according to the dynamic compensation strategy generated by the virtual domain data fusion and optimization unit, wherein: the dynamic compensation includes adjusting the sensitivity, sampling frequency and data processing priority of the sensor; the dynamic compensation unit forms a closed-loop feedback with the physical domain sensor integration unit; Distributed computing units are used to support the collaborative work of various units, including: the edge computing unit is used to process data from the physical domain sensor integration unit and the environmental domain monitoring unit; the central computing unit is used to run the multi-domain collaborative twin model and generate dynamic compensation strategies; the cloud optimization unit is used to integrate historical data and large-scale environmental characteristic data to optimize the twin model.

2. The integrated sensor module for a dynamic weighing system according to claim 1, characterized in that: The wavelet decomposition algorithm in the edge computing unit includes at least three levels of decomposition. The decomposition basis function uses the Daubechies wavelet basis, which is implemented through the following steps: performing discrete wavelet transform on the collected original signal; extracting high-frequency components for vibration feature analysis; and combining low-frequency components to perform tilt signal correction.

3. The integrated sensor module for a dynamic weighing system according to claim 1, characterized in that: The normalization process in the environmental domain monitoring unit adopts the maximum and minimum normalization algorithm, through the formula: Calculate, where and The value is the real-time data of the environmental domain monitoring unit.

4. The integrated sensor module for a dynamic weighing system according to claim 1, characterized in that: The model training method of the recursive neural network combined with the attention mechanism in the virtual domain data fusion and optimization unit includes the following steps: constructing a multidimensional data set containing historical weighing data, vibration characteristics and environmental parameters; designing a recursive neural network structure with an attention mechanism for dynamic weight allocation; optimizing the network weights through the error back propagation algorithm, and the objective function is to minimize the root mean square value of the prediction error.

5. The integrated sensor module for a dynamic weighing system according to claim 4, characterized in that: The calculation steps of the weight coefficient include: calculating the mean and standard deviation of the real-time collected data to determine the initial weight; constructing a covariance matrix to analyze the correlation between the input features; and normalizing the weights based on the gradient descent method, with the range limited to between 0 and 1.

6. The integrated sensor module for a dynamic weighing system according to claim 1, characterized in that: The sensor sampling frequency adjustment algorithm in the dynamic compensation unit adopts negative feedback control, in which the feedback signal is the deviation between the vibration amplitude and the standard threshold. It is implemented in the following ways: calculating the amplitude of the real-time vibration signal; comparing with the set threshold to determine the sampling frequency adjustment amplitude; dynamically updating the sampling frequency in the range of 100Hz to 1kHz.

7. The integrated sensor module for a dynamic weighing system according to claim 1, characterized in that: The message queue mechanism in the distributed computing unit is implemented through an event-driven model, where event triggers include the following conditions: sensor signals exceed the set threshold; A notification signal is generated after the data fusion task is completed.

8. The integrated sensor module for a dynamic weighing system according to claim 1, characterized in that: The cut-off frequency range of the high-pass filter in the physical domain sensor integration unit is 10 Hz to 50 Hz, which is used to remove low-frequency interference signals.

9. The integrated sensor module for a dynamic weighing system according to claim 1, characterized in that: The message queue mechanism is implemented based on the MQTT protocol, which specifically includes the following steps: realizing data classification transmission through multi-topic publishing; the subscriber parses and verifies the received data; and ensures data synchronization and consistency of multiple sensor nodes.

Images