Dynamic data fusion method and system for similar monitoring sensors

Abstract

The invention discloses a data dynamic fusion method and system for similar monitoring sensors. The method comprises the following steps: acquiring monitoring data of similar monitoring sensors to be fused, and performing data cleaning and exception processing to obtain continuous monitoring data; initializing a basic matrix for state prediction and error correction; predicting the state of the current time step and calculating a prediction error covariance; calculating a mean square error between an observed value and a predicted value of each monitoring sensor, and calculating a weight factor; judging the fault state of each monitoring sensor and adjusting the measurement noise covariance; calculating the Kalman gain of each monitoring sensor and obtaining the total Kalman gain; and completing dynamic data fusion of the same kind of monitoring sensors by adopting a weighted summation scheme. According to the method, the weighting factor is adjusted based on Kalman filtering and dynamic weighting fusion, and the abnormal monitoring sensor is isolated by adopting a fault diagnosis scheme, so that data dynamic fusion of similar monitoring sensors is realized, the reliability is high, and the accuracy is good.

Description

Technical Field

[0001] The invention belongs to the field of data processing, and in particular relates to a method and system for dynamic fusion of data of similar monitoring sensors. Background Art

[0002] With the development of economy and technology, sensor networks have been widely used in people's production and life, such as the Internet of Things, autonomous driving, industrial monitoring and other fields, and have brought endless convenience to people's production and life. Therefore, ensuring the accuracy and reliability of sensor network data has become one of the research focuses of researchers.

[0003] In current practical applications, sensor data may be missing or sparse due to unstable network transmission, environmental interference, equipment aging, etc., which in turn affects the continuity and integrity of sensor system data. In addition, sensor systems are prone to failures or measurement errors after long-term operation, which will also lead to a decline in sensor data quality. In this case, after the sensor system performs data fusion, poor quality data will directly affect the reliability and accuracy of the fused data, and thus affect the reliability and accuracy of the sensor system.

[0004] Existing sensor data fusion solutions, such as weighted averaging and Bayesian filtering, can effectively improve data accuracy, but they are insufficient in dealing with missing data, outliers, and sensor failures, especially in terms of real-time performance and fault detection. Summary of the invention

[0005] One of the purposes of the present invention is to provide a method for dynamic fusion of data of similar monitoring sensors with high reliability and good accuracy.

[0006] A second objective of the present invention is to provide a system for realizing the method of dynamic fusion of data of the same type of monitoring sensors.

[0007] The method for dynamic fusion of data of the same type of monitoring sensors provided by the present invention comprises the following steps: S1. Obtain monitoring data of similar monitoring sensors to be fused; S2. Based on the sparse signal recovery method, regularization constraint and linear interpolation method, the monitoring data obtained in step S1 is cleaned and abnormal data is processed to obtain continuous monitoring data; S3. Initializing a basic matrix for state prediction and error correction; the basic matrix includes a state transfer matrix, a process noise covariance matrix, an observation matrix and a measurement noise covariance matrix; S4. Based on the data information obtained in step S2 and step S3, the Kalman filter prediction model is used to predict the state of the current time step, and the prediction error covariance is calculated; S5. For each monitoring sensor, calculate the mean square error between the observed value and the predicted value of the monitoring sensor, and calculate the corresponding weight factor based on the obtained mean square error; S6. Based on the state prediction value and error covariance prediction value of each monitoring sensor, determine the fault state of the monitoring sensor and adjust the corresponding measurement noise covariance; S7. Calculate the Kalman gain of each monitoring sensor according to the measurement noise covariance and weight factor of each monitoring sensor, and combine them by weighted summation to obtain a total Kalman gain; S8. Based on the total Kalman gain obtained in step S7, a weighted summation scheme is used to complete the dynamic fusion of data from similar monitoring sensors.

[0008] The step S2 specifically includes the following steps: For each time step of each monitoring sensor, the sparse signal recovery method is used to process missing values, and the data sparse recovery is achieved through L1 regularization constraints; After the sparse signal is restored, if there are still missing data, the missing data are interpolated using linear interpolation; Finally, continuous monitoring data is obtained.

[0009] The step S4 specifically comprises the following steps: The following formula is used for state prediction: In the formula is the predicted state at time step k; is the predicted state at time step k-1; is the current state transfer matrix; The error covariance prediction is performed using the following formula: In the formula is the prediction error covariance matrix at time step k; is the prediction error covariance matrix of time step k-1; Q is the current process noise covariance matrix.

[0010] The step S5 specifically includes the following steps: The mean square error of the jth monitoring sensor is calculated using the following formula: : In the formula is the observation value of the jth monitoring sensor; is the j-th row of the observation matrix of the j-th monitoring sensor; The weight factor of the jth monitoring sensor is calculated using the following formula: : In the formula The first minimum constant is set to prevent the denominator from being 0; Finally, the weight factors of all monitoring sensors are normalized to ensure that the sum of all weight factors is 1.

[0011] The step S6 comprises the following steps: For each monitoring sensor, the Mahalanobis distance of the monitoring sensor is calculated according to the corresponding state prediction value and error covariance prediction value; According to the obtained Mahalanobis distance, the monitoring sensor is judged: If the Mahalanobis distance is not greater than the set value, the monitoring sensor is judged to be normal; If the Mahalanobis distance is greater than the set value, the monitoring sensor is determined to be abnormal, and the measurement noise covariance of the monitoring sensor is amplified to reduce the impact of the monitoring sensor on the fusion result.

[0012] The step S6 specifically includes the following steps: According to the state prediction value and the error covariance prediction value, the Mahalanobis distance of the jth monitoring sensor is calculated using the following formula: : In the formula is the current measurement noise covariance of the jth monitoring sensor; The second minimum constant is set to prevent the denominator from being 0; According to the obtained Mahalanobis distance, the jth monitoring sensor is judged: If the Mahalanobis distance is not greater than the set value, the jth monitoring sensor is judged to be normal; If the Mahalanobis distance is greater than the set value, the jth monitoring sensor is judged to be abnormal, and the current measurement noise covariance of the jth monitoring sensor is amplified. times, and used as the current measurement noise covariance of the new j-th monitoring sensor; .

[0013] The step S7 specifically includes the following steps: The Kalman gain of the jth monitoring sensor is calculated using the following formula: In the formula is the Kalman gain of the jth monitoring sensor; Based on the weighted summation scheme, the total Kalman gain is calculated using the following formula : Where N is the total number of monitoring sensors.

[0014] The step S8 specifically includes the following steps: Based on the weighted summation scheme, the state estimate of the current time step is calculated using the following formula: In the formula is the state estimate for the current time step; The error covariance of the current time step is calculated using the following formula:

[0015] In the formula is the error covariance of the current time step; S is the total matrix composed of the observation matrices of all monitoring sensors; R is the total matrix composed of the current measurement noise covariance of all monitoring sensors; The state estimate of the current time step is obtained , as the final data fusion result of similar monitoring sensors.

[0016] The present invention also provides a system for implementing the data dynamic fusion method of the similar monitoring sensors, comprising a data acquisition module, a data processing module, a matrix initialization module, a prediction variance calculation module, a weight calculation module, a measurement variance calculation module, a gain calculation module and a data fusion module; the data acquisition module, the data processing module, the matrix initialization module, the prediction variance calculation module, the weight calculation module, the measurement variance calculation module, the gain calculation module and the data fusion module are connected in series in sequence; the data acquisition module is used to acquire the monitoring data of the similar monitoring sensors to be fused, and upload the data information to the data processing module; the data processing module is used to perform data cleaning and abnormal data processing on the acquired monitoring data based on the received data information, based on the sparse signal recovery method, regularization constraint and linear interpolation method, so as to obtain continuous monitoring data, and upload the data information to the matrix initialization module; the matrix initialization module is used to initialize the basic matrix used for state prediction and error correction according to the received data information, the basic matrix including the state transfer matrix, the process noise covariance matrix, the observation matrix and the measurement noise covariance matrix, and upload the data information to the prediction variance calculation module; the prediction variance calculation module is used to According to the received data information, according to the obtained data information, the Kalman filter prediction model is used to predict the state of the current time step, and the prediction error covariance is calculated, and the data information is uploaded to the weight calculation module; the weight calculation module is used to calculate the mean square error between the observation value and the predicted value of each monitoring sensor according to the received data information, and obtain the corresponding weight factor according to the obtained mean square error calculation, and upload the data information to the measurement variance calculation module; the measurement variance calculation module is used to determine the fault state of the monitoring sensor based on the state prediction value and the error covariance prediction value of each monitoring sensor according to the received data information, and adjust the corresponding measurement noise covariance, and upload the data information to the gain calculation module; the gain calculation module is used to calculate the Kalman gain of each monitoring sensor according to the received data information, the measurement noise covariance and the weight factor of each monitoring sensor, and merge them by weighted summation to obtain the total Kalman gain, and upload the data information to the data fusion module; the data fusion module is used to complete the dynamic fusion of data of the same type of monitoring sensors by a weighted summation scheme according to the received data information and the obtained total Kalman gain.

[0017] The method and system for dynamic data fusion of similar monitoring sensors disclosed in the present invention processes data of similar monitoring sensors, and adaptively adjusts the weighting factors of the monitoring sensors based on the sparse signal recovery and dynamic weighted fusion algorithm of Kalman filtering, and isolates abnormal monitoring sensors by adopting a fault diagnosis scheme. This not only realizes the dynamic data fusion of similar monitoring sensors, but also has higher reliability and better accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The figure is a schematic diagram of the method flow of the present invention.

[0019] Figure 2 Schematic diagram of the functional modules of the system of the present invention. DETAILED DESCRIPTION

[0020] like Figure 1 The method flow chart of the method of the present invention is shown as follows: The data dynamic fusion method of the same type of monitoring sensors disclosed in the present invention comprises the following steps: S1. Obtain monitoring data of similar monitoring sensors to be fused; In specific implementation, the data of multiple monitoring sensors can be stored in a file according to time steps to facilitate data fusion and time series analysis; the file structure is designed as follows: the first column of the file is the time step (Time Step), which is used to identify the collection time of each row of monitoring data; the subsequent columns are arranged in order from most to least according to the number (or data quality) of data collected by each monitoring sensor; the sensor column with the largest amount of observation data or the highest data quality is arranged in the second column and is set as the benchmark sensor.

[0021] S2. Based on the sparse signal recovery method, regularization constraint and linear interpolation method, the monitoring data obtained in step S1 is cleaned and abnormal data is processed to obtain continuous monitoring data; specifically comprising the following steps: For each time step of each monitoring sensor, the sparse signal recovery method is used to process missing values, and the data sparse recovery is achieved through L1 regularization constraints; After the sparse signal is restored, if there are still missing data, the missing data are interpolated using linear interpolation; Finally, continuous monitoring data is obtained.

[0022] S3. Initializing a basic matrix for state prediction and error correction; the basic matrix includes a state transfer matrix, a process noise covariance matrix, an observation matrix and a measurement noise covariance matrix.

[0023] S4. Based on the data information obtained in step S2 and step S3, the Kalman filter prediction model is used to predict the state of the current time step and calculate the prediction error covariance; specifically, the following steps are included: The following formula is used for state prediction: In the formula is the predicted state at time step k; is the predicted state at time step k-1; is the current state transfer matrix; The error covariance prediction is performed using the following formula: In the formula is the prediction error covariance matrix at time step k; is the prediction error covariance matrix of time step k-1; Q is the current process noise covariance matrix.

[0024] S5. For each monitoring sensor, calculate the mean square error between the observed value and the predicted value of the monitoring sensor, and calculate the corresponding weight factor based on the obtained mean square error; specifically comprising the following steps: The mean square error of the jth monitoring sensor is calculated using the following formula: : In the formula is the observation value of the jth monitoring sensor; is the j-th row of the observation matrix of the j-th monitoring sensor; The weight factor of the jth monitoring sensor is calculated using the following formula: : In the formula The first minimum constant is set to prevent the denominator from being 0. The weight factor is calculated in such a way that sensors with smaller errors can obtain higher weights to dynamically reflect changes in data quality. Finally, the weight factors of all monitoring sensors are normalized to ensure that the sum of all weight factors is 1.

[0025] S6. Based on the state prediction value and error covariance prediction value of each monitoring sensor, determining the fault state of the monitoring sensor and adjusting the corresponding measurement noise covariance; comprising the following steps: For each monitoring sensor, the Mahalanobis distance of the monitoring sensor is calculated according to the corresponding state prediction value and error covariance prediction value; According to the obtained Mahalanobis distance, the monitoring sensor is judged: If the Mahalanobis distance is not greater than the set value, the monitoring sensor is judged to be normal; If the Mahalanobis distance is greater than the set value, the monitoring sensor is judged to be abnormal, and the measurement noise covariance of the monitoring sensor is amplified to reduce the influence of the monitoring sensor on the fusion result; In specific implementation: According to the state prediction value and the error covariance prediction value, the Mahalanobis distance of the jth monitoring sensor is calculated using the following formula: : In the formula is the current measurement noise covariance of the jth monitoring sensor; The second minimum constant is set to prevent the denominator from being 0; According to the obtained Mahalanobis distance, the jth monitoring sensor is judged: If the Mahalanobis distance is not greater than the set value, the jth monitoring sensor is judged to be normal; If the Mahalanobis distance is greater than the set value, the jth monitoring sensor is judged to be abnormal, and the current measurement noise covariance of the jth monitoring sensor is amplified. times, and used as the current measurement noise covariance of the new j-th monitoring sensor; .

[0026] S7. Calculate the Kalman gain of each monitoring sensor according to the measurement noise covariance and weight factor of each monitoring sensor, and combine them by weighted summation to obtain a total Kalman gain; specifically, the steps include: The Kalman gain of the jth monitoring sensor is calculated using the following formula: In the formula is the Kalman gain of the jth monitoring sensor; Based on the weighted summation scheme, the total Kalman gain is calculated using the following formula : Where N is the total number of monitoring sensors.

[0027] S8. According to the total Kalman gain obtained in step S7, a weighted summation scheme is used to complete the dynamic fusion of data from similar monitoring sensors; specifically comprising the following steps: Based on the weighted summation scheme, the state estimate of the current time step is calculated using the following formula: In the formula is the state estimate for the current time step; The error covariance of the current time step is calculated using the following formula: In the formula is the error covariance of the current time step; S is the total matrix composed of the observation matrices of all monitoring sensors; R is the total matrix composed of the current measurement noise covariance of all monitoring sensors; The state estimate of the current time step is obtained , as the final data fusion result of similar monitoring sensors.

[0028] The effect of the method of the present invention is described below in conjunction with a comparative example: The monitoring data collected during the shield tunnel construction process were selected for experimental comparison, and some data sets are shown in Table 1; Table 1 Schematic diagram of sensor monitoring data during shield tunneling

[0029] The method of the present invention is compared with the existing traditional weighted fusion method, Bayesian filtering method and isolation forest method. The final evaluation index is shown in Table 2: Table 2 Evaluation index table

[0030] It can be seen from Table 2 that the method of the present invention shows obvious advantages in all evaluation indicators. In terms of accuracy, the method of the present invention reaches 93%, which is much higher than other methods, proving that it has higher accuracy after data fusion. In terms of processing efficiency, the processing time of the method of the present invention is 102 seconds, which is significantly shorter than other methods and more efficient. In terms of reliability, the method of the present invention also performs well, reaching 91%, which is significantly better than the weighted method (70%), Bayesian filtering (78%) and isolation forest (72%), showing that it is more stable and fault-tolerant when facing missing or abnormal data. In terms of data recovery ability, the recovery ability of the method of the present invention is 96%, which is higher than 74%-80% of other methods, indicating that it performs best in repairing missing or abnormal data. In summary, the method of the present invention is superior to existing traditional methods in multiple dimensions such as accuracy, efficiency, reliability and data recovery ability, demonstrating its significant advantages in practical applications.

[0031] like Figure 2The functional module schematic diagram of the system of the present invention is shown as follows: the system disclosed in the present invention for realizing the data dynamic fusion method of the same type of monitoring sensors comprises a data acquisition module, a data processing module, a matrix initialization module, a prediction variance calculation module, a weight calculation module, a measurement variance calculation module, a gain calculation module and a data fusion module; the data acquisition module, the data processing module, the matrix initialization module, the prediction variance calculation module, the weight calculation module, the measurement variance calculation module, the gain calculation module and the data fusion module are connected in series in sequence; the data acquisition module is used to acquire the monitoring data of the same type of monitoring sensors to be fused, and upload the data information to the data processing module; the data processing module is used to perform data cleaning and abnormal data processing on the acquired monitoring data based on the received data information, based on the sparse signal recovery method, the regularization constraint and the linear interpolation method, so as to obtain continuous monitoring data, and upload the data information to the matrix initialization module; the matrix initialization module is used to initialize the basic matrix for state prediction and error correction according to the received data information, the basic matrix comprises the state transfer matrix, the process noise covariance matrix, the observation matrix and the measurement noise covariance matrix, and upload the data information to the prediction variance calculation module; the prediction The variance calculation module is used to predict the state of the current time step using the Kalman filter prediction model according to the received data information and the obtained data information, and calculate the prediction error covariance, and upload the data information to the weight calculation module; the weight calculation module is used to calculate the mean square error between the observation value and the predicted value of each monitoring sensor according to the received data information, and obtain the corresponding weight factor according to the obtained mean square error calculation, and upload the data information to the measurement variance calculation module; the measurement variance calculation module is used to determine the fault state of the monitoring sensor based on the state prediction value and the error covariance prediction value of each monitoring sensor according to the received data information, and adjust the corresponding measurement noise covariance, and upload the data information to the gain calculation module; the gain calculation module is used to calculate the Kalman gain of each monitoring sensor according to the received data information, the measurement noise covariance and the weight factor of each monitoring sensor, and merge them by weighted summation to obtain the total Kalman gain, and upload the data information to the data fusion module; the data fusion module is used to complete the dynamic fusion of data of the same type of monitoring sensors by a weighted summation scheme according to the received data information and the obtained total Kalman gain.

Claims

1. A method for dynamic fusion of data from similar monitoring sensors, characterized in that The steps include: S1. Obtain monitoring data of similar monitoring sensors to be fused; S2. Based on the sparse signal recovery method, regularization constraint and linear interpolation method, the monitoring data obtained in step S1 is cleaned and abnormal data is processed to obtain continuous monitoring data; S3. Initializing a basic matrix for state prediction and error correction; the basic matrix includes a state transfer matrix, a process noise covariance matrix, an observation matrix and a measurement noise covariance matrix; S4. Based on the data information obtained in step S2 and step S3, the Kalman filter prediction model is used to predict the state of the current time step, and the prediction error covariance is calculated; S5. For each monitoring sensor, calculate the mean square error between the observed value and the predicted value of the monitoring sensor, and calculate the corresponding weight factor based on the obtained mean square error; S6. Based on the state prediction value and error covariance prediction value of each monitoring sensor, determine the fault state of the monitoring sensor and adjust the corresponding measurement noise covariance; S7. Calculate the Kalman gain of each monitoring sensor according to the measurement noise covariance and weight factor of each monitoring sensor, and combine them by weighted summation to obtain a total Kalman gain; S8. Based on the total Kalman gain obtained in step S7, a weighted summation scheme is used to complete the dynamic fusion of data from similar monitoring sensors.

2. The method for dynamic fusion of data of similar monitoring sensors according to claim 1 is characterized in that The step S2 specifically includes the following steps: For each time step of each monitoring sensor, the sparse signal recovery method is used to process missing values, and the data sparse recovery is achieved through L1 regularization constraints; After the sparse signal is restored, if there are still missing data, the missing data are interpolated using linear interpolation; Finally, continuous monitoring data is obtained.

3. The method for dynamic fusion of data of similar monitoring sensors according to claim 2 is characterized in that The step S4 specifically comprises the following steps: The following formula is used for state prediction: In the formula is the predicted state at time step k; is the predicted state at time step k-1; is the current state transfer matrix; The error covariance prediction is performed using the following formula: In the formula is the prediction error covariance matrix at time step k; is the prediction error covariance matrix of time step k-1; Q is the current process noise covariance matrix.

4. The method for dynamic fusion of data of similar monitoring sensors according to claim 3 is characterized in that The step S5 specifically includes the following steps: The mean square error of the jth monitoring sensor is calculated using the following formula: : In the formula is the observation value of the jth monitoring sensor; is the j-th row of the observation matrix of the j-th monitoring sensor; The weight factor of the jth monitoring sensor is calculated using the following formula: : In the formula The first minimum constant is set to prevent the denominator from being 0; Finally, the weight factors of all monitoring sensors are normalized to ensure that the sum of all weight factors is 1.

5. The method for dynamic fusion of data of similar monitoring sensors according to claim 4 is characterized in that The step S6 comprises the following steps: For each monitoring sensor, the Mahalanobis distance of the monitoring sensor is calculated according to the corresponding state prediction value and error covariance prediction value; According to the obtained Mahalanobis distance, the monitoring sensor is judged: If the Mahalanobis distance is not greater than the set value, the monitoring sensor is judged to be normal; If the Mahalanobis distance is greater than the set value, the monitoring sensor is determined to be abnormal, and the measurement noise covariance of the monitoring sensor is amplified to reduce the impact of the monitoring sensor on the fusion result.

6. The method for dynamic fusion of data of similar monitoring sensors according to claim 5 is characterized in that The step S6 specifically includes the following steps: According to the state prediction value and the error covariance prediction value, the Mahalanobis distance of the jth monitoring sensor is calculated using the following formula: : In the formula is the current measurement noise covariance of the jth monitoring sensor; The second minimum constant is set to prevent the denominator from being 0; According to the obtained Mahalanobis distance, the jth monitoring sensor is judged: If the Mahalanobis distance is not greater than the set value, the jth monitoring sensor is judged to be normal; If the Mahalanobis distance is greater than the set value, the jth monitoring sensor is judged to be abnormal, and the current measurement noise covariance of the jth monitoring sensor is amplified. times, and used as the current measurement noise covariance of the new j-th monitoring sensor; .

7. The method for dynamic fusion of data of similar monitoring sensors according to claim 6 is characterized in that The step S7 specifically includes the following steps: The Kalman gain of the jth monitoring sensor is calculated using the following formula: In the formula is the Kalman gain of the jth monitoring sensor; Based on the weighted summation scheme, the total Kalman gain is calculated using the following formula : Where N is the total number of monitoring sensors.

8. The method for dynamic fusion of data of similar monitoring sensors according to claim 7 is characterized in that The step S8 specifically includes the following steps: Based on the weighted summation scheme, the state estimate of the current time step is calculated using the following formula: In the formula is the state estimate for the current time step; The error covariance of the current time step is calculated using the following formula: In the formula is the error covariance of the current time step; S is the total matrix composed of the observation matrices of all monitoring sensors; R is the total matrix composed of the current measurement noise covariance of all monitoring sensors; The state estimate of the current time step is obtained , as the final data fusion result of similar monitoring sensors.

9. A system for implementing the method for dynamic fusion of data of similar monitoring sensors as claimed in any one of claims 1 to 8, characterized in that It includes a data acquisition module, a data processing module, a matrix initialization module, a prediction variance calculation module, a weight calculation module, a measurement variance calculation module, a gain calculation module and a data fusion module; the data acquisition module, the data processing module, the matrix initialization module, the prediction variance calculation module, the weight calculation module, the measurement variance calculation module, the gain calculation module and the data fusion module are connected in series in sequence; the data acquisition module is used to acquire the monitoring data of the same type of monitoring sensors to be fused, and upload the data information to the data processing module; The data processing module is used to perform data cleaning and abnormal data processing on the acquired monitoring data based on the received data information, based on the sparse signal recovery method, regularization constraint and linear interpolation method, so as to obtain continuous monitoring data, and upload the data information to the matrix initialization module; The matrix initialization module is used to initialize the basic matrix for state prediction and error correction according to the received data information, the basic matrix includes the state transfer matrix, the process noise covariance matrix, the observation matrix and the measurement noise covariance matrix, and upload the data information to the prediction variance calculation module; The prediction variance calculation module is used to predict the state of the current time step based on the received data information, and calculate the prediction error covariance according to the obtained data information, and upload the data information to the weight calculation module; The weight calculation module is used to calculate the mean square error between the observed value and the predicted value of each monitoring sensor according to the received data information, and obtain the corresponding weight factor according to the obtained mean square error, and upload the data information to the measurement variance calculation module; The measurement variance calculation module is used to determine the fault state of the monitoring sensor based on the received data information, the state prediction value and the error covariance prediction value of each monitoring sensor, and adjust the corresponding measurement noise covariance, and upload the data information to the gain calculation module; the gain calculation module is used to calculate the Kalman gain of each monitoring sensor based on the received data information, the measurement noise covariance and the weight factor of each monitoring sensor, and combine them by weighted summation to obtain the total Kalman gain, and upload the data information to the data fusion module; The data fusion module is used to complete the dynamic fusion of data from similar monitoring sensors using a weighted summation scheme based on the received data information and the obtained total Kalman gain.

Images