Construction site intelligent weighing management method and system based on dynamic compensation and medium

Abstract

The invention provides a construction site intelligent weighing management method and system based on dynamic compensation and a medium. The method comprises the steps that zero calibration is carried out by obtaining the weighing state of weighing equipment, or a corresponding original weight data set, a vibration amplitude, a tank rotating speed and a vehicle parking inclination angle are obtained according to a preset sampling frequency, processing is carried out according to the tank rotating speed and the vibration amplitude, and the rotating state of a tank is obtained; self-adaptive filtering compensation processing is carried out on the original weight data set according to the rotation state to obtain final measurement weight data, then abnormal value detection is carried out on the final measurement weight data, and intelligent weighing management is carried out according to the detection result; according to the invention, through real-time determination of the weighing state, evaluation of the rotation state of the tank body, dynamic real-time adaptive filtering compensation processing, obtaining of the final measured weight data, and anomaly detection, intelligent weighing management based on dynamic compensation is realized, and the adaptability and accuracy of weighing are improved.

Description

Technical Field

[0001] The present application relates to the field of engineering measurement technology, and in particular to a method, system and medium for intelligent weighing management of construction sites based on dynamic compensation. Background Art

[0002] In the field of construction engineering, traditional weighing equipment (such as mechanical floor scales and simple electronic scales) has significant technical defects: manual recording leads to inefficient material acceptance (acceptance of a single batch takes >30 minutes); it is impossible to connect to the system, making it difficult to achieve dynamic accounting of project quantities; especially when weighing concrete mixer trucks, since the tank body needs to rotate continuously to maintain the uniformity of the concrete, the centrifugal force generated by the rotation will affect the weight distribution, and the vibration generated will also interfere with the weighing results, resulting in a significant reduction in weighing accuracy and unable to meet the construction site's demand for accurate measurement of material weight; therefore, a new intelligent weighing management method is urgently needed to achieve intelligent weighing management.

[0003] In response to the above problems, effective technical solutions are urgently needed. Summary of the Invention

[0004] The purpose of this application is to provide an intelligent weighing management method, system and medium for construction sites based on dynamic compensation. It can determine the weighing status in real time, evaluate the rotation status of the tank, perform dynamic real-time adaptive filtering and compensation processing, obtain the final measured weight data, and perform anomaly detection, thereby realizing intelligent weighing management based on dynamic compensation and improving the adaptability and accuracy of weighing.

[0005] In a first aspect, the present application provides a construction site intelligent weighing management method based on dynamic compensation, comprising the following steps: Get the weighing status of the weighing device, including whether it is weighing or not; If the weighing status is not weighing, perform zero point calibration; If the weighing status is "weighing", the corresponding raw weight data set, vibration amplitude, tank rotation speed and vehicle parking inclination angle are obtained according to the preset sampling frequency; Processing is performed according to the tank body rotation speed and vibration amplitude to obtain the rotation state of the tank body; performing adaptive filtering and compensation processing on the original weight data set according to the rotation state to obtain final measured weight data; The final measured weight data is subjected to abnormal value detection, and intelligent weighing management is performed based on the detection results.

[0006] Optionally, in the construction site intelligent weighing management method based on dynamic compensation described in the present application, obtaining the weighing status of the weighing device, including whether it is weighing or not weighing, includes: Get real-time weight data from weighing equipment; If the real-time weight data is greater than or equal to the preset weight threshold, the weighing state is weighing; If the real-time weight data is less than the preset weight threshold, the weighing state is not weighing; If the weighing status is not weighing, the real-time weight data is processed to obtain the real-time weight average within a preset time period; If the real-time weight average is greater than the dynamic zero drift threshold, the sensor automatic calibration process is activated.

[0007] Optionally, the construction site intelligent weighing management method based on dynamic compensation described in the present application further includes: Obtain real-time environmental monitoring data of weighing equipment, including real-time temperature and real-time humidity; Comparing the real-time temperature and real-time humidity with the corresponding preset standard temperature and preset standard humidity, respectively, to obtain corresponding temperature deviation values ​​and humidity deviation values; Performing weighted summation processing on the temperature deviation value and the humidity deviation value with the corresponding preset temperature impact gradient value and preset humidity impact gradient value respectively to obtain an environmental impact coefficient; Get the power-on time and preset life of the sensor; Comparing the power-on time with a preset lifespan to obtain a sensor aging evaluation parameter, and multiplying the parameter by a preset aging impact gradient value to obtain an aging impact coefficient; The preset initial zero drift threshold is corrected according to the environmental influence coefficient and the aging influence coefficient in combination with a preset adaptive adjustment factor to obtain a dynamic zero drift threshold.

[0008] Optionally, in the construction site intelligent weighing management method based on dynamic compensation described in the present application, the processing according to the tank rotation speed and vibration amplitude to obtain the rotation state of the tank includes: Performing Fourier transform on the vibration amplitude to obtain the vibration frequency; Perform feature extraction based on the vibration frequency to obtain a main frequency component and a low-frequency energy ratio; Inputting the tank body rotation speed, main frequency component and low frequency energy ratio into a preset tank body rotation state assessment model for processing to obtain the tank body rotation state assessment parameters; The rotation state evaluation parameter is compared with a first preset rotation state parameter threshold and a second preset rotation state parameter threshold respectively to obtain the rotation state of the tank body, including a stationary state, a low-speed rotation state or a high-speed rotation state.

[0009] Optionally, in the construction site intelligent weighing management method based on dynamic compensation described in the present application, the adaptive filtering and compensation processing of the original weight data set according to the rotation state to obtain the final measured weight data includes: The final measured weight data includes static final measured weight data, low-speed final measured weight data or high-speed final measured weight data; Processing the vibration amplitude and the tank rotation speed in combination with a preset compensation coefficient to obtain vibration compensation quality data; If the rotation state is a stationary state, the original weight data set is averaged according to a preset time window to obtain static final weight data; If the rotation state is a low-speed rotation state, querying a preset adaptive filtering compensation processing database to obtain corresponding low-speed process noise covariance and low-speed measurement noise covariance; The original weight data set corresponding to the preset time window is subjected to adaptive filtering compensation processing in combination with the low-speed process noise covariance and the low-speed measurement noise covariance to obtain a low-speed compensated weight data set; Subtracting the low-speed compensation weight data set from the vibration compensation mass data and calculating the average value to obtain low-speed final measurement weight data; If the rotation state is a high-speed rotation state, querying a preset adaptive filtering compensation processing database to obtain corresponding high-speed process noise covariance and high-speed measurement noise covariance; The original weight data set corresponding to the preset time window is respectively combined with the high-speed process noise covariance and the high-speed measurement noise covariance to perform adaptive filtering compensation processing to obtain a high-speed compensated weight data set; The high-speed compensated weight data set is respectively subtracted from the vibration compensated mass data and averaged to obtain high-speed final measured weight data.

[0010] Optionally, in the construction site intelligent weighing management method based on dynamic compensation described in the present application, performing abnormal value detection on the final measured weight data and performing intelligent weighing management according to the detection result include: Extract features from static final weight data, low-speed final weight data, or high-speed final weight data within a preset time period to obtain the corresponding mean and standard deviation; Processing is performed based on the mean and standard deviation to obtain a weight lower limit threshold and a weight upper limit threshold corresponding to the static final measurement weight data, the low-speed final measurement weight data, or the high-speed final measurement weight data; Perform threshold comparison on the static final measurement weight data, the low-speed final measurement weight data or the high-speed final measurement weight data with the corresponding lower weight limit threshold and upper weight limit threshold respectively; If the weight is between the lower weight limit threshold and the upper weight limit threshold, it is determined to be normal data; otherwise, it is determined to be an abnormal value and is eliminated to obtain the corresponding static final measurement weight normal data, low-speed final measurement weight normal data or high-speed final measurement weight normal data within the preset time period; Processing the static final weight normal data, the low-speed final weight normal data, or the high-speed final weight normal data through a preset isolation forest algorithm to obtain a data anomaly score; If the data abnormality score is greater than the preset abnormality warning threshold, the data is eliminated and the corresponding static final weight valid data, low-speed final weight valid data or high-speed final weight valid data within the preset time period are obtained; The static final measurement weight valid data, the low-speed final measurement weight valid data or the high-speed final measurement weight valid data are packaged in a preset format and sent to the management end for display.

[0011] Optionally, the construction site intelligent weighing management method based on dynamic compensation described in the present application further includes: Comparing the parking inclination angle of the vehicle with a preset inclination angle threshold; If the parking inclination angle of the vehicle is greater than a preset inclination angle threshold, a weighing abnormality warning response is output; If the vehicle parking inclination angle is less than or equal to a preset inclination angle threshold, processing is performed according to the vehicle parking inclination angle and the final measured weight data to obtain final measured weight optimization data.

[0012] Optionally, the construction site intelligent weighing management method based on dynamic compensation described in the present application further includes: Averaging the static final measurement weight valid data, the low-speed final measurement weight valid data, or the high-speed final measurement weight valid data corresponding to a preset time period to obtain static final measurement weight average data, low-speed final measurement weight average data, or high-speed final measurement weight average data; Comparing the static final measurement weight average data, the low-speed final measurement weight average data, or the high-speed final measurement weight average data with the corresponding preset mean threshold value to obtain a mean comparison result; Perform peak extraction processing on the static final measurement weight valid data, low-speed final measurement weight valid data or high-speed final measurement weight valid data corresponding to a preset time period to obtain static final measurement weight peak data, low-speed final measurement weight peak data or high-speed final measurement weight peak data; Comparing the static final measurement weight peak data, the low-speed final measurement weight peak data, or the high-speed final measurement weight peak data with the corresponding peak threshold value to obtain a peak comparison result; Comparing and processing the static final weight valid data, the low-speed final weight valid data or the high-speed final weight valid data corresponding to the preset time period to obtain the static final weight change rate, the low-speed final weight change rate or the high-speed final weight change rate; Comparing the static final measurement weight change rate, the low-speed final measurement weight change rate, or the high-speed final measurement weight change rate with corresponding change rate thresholds to obtain a change rate comparison result; If the mean value comparison result, the peak value comparison result and the change rate comparison result are all not greater than the threshold value, no overload warning is output; Otherwise, an overload warning is output.

[0013] In a second aspect, the present application provides a construction site intelligent weighing management system based on dynamic compensation, the system comprising: a memory and a processor, the memory including a program of a construction site intelligent weighing management method based on dynamic compensation, the program of the construction site intelligent weighing management method based on dynamic compensation being executed by the processor to implement the following steps: Get the weighing status of the weighing device, including whether it is weighing or not; If the weighing status is not weighing, perform zero point calibration; If the weighing status is "weighing", the corresponding raw weight data, vibration amplitude, tank rotation speed and vehicle parking inclination angle are obtained according to the preset sampling frequency; Processing is performed according to the tank body rotation speed and vibration amplitude to obtain the rotation state of the tank body; performing adaptive filtering and compensation processing on the original weight data set according to the rotation state to obtain final measured weight data; The final measured weight data is subjected to abnormal value detection, and intelligent weighing management is performed based on the detection results.

[0014] On the third aspect, the present application also provides a computer-readable storage medium, which stores a program for a construction site intelligent weighing management method based on dynamic compensation. When the program for a construction site intelligent weighing management method based on dynamic compensation is executed by a processor, the steps of the construction site intelligent weighing management method based on dynamic compensation as described in any one of the above items are implemented.

[0015] From the above, it can be seen that the intelligent weighing management method, system and medium for construction sites based on dynamic compensation provided by this application can obtain the final weight data by real-time determination of the weighing status, evaluation of the rotation status of the tank, dynamic real-time adaptive filtering compensation processing, and abnormality detection, thereby realizing intelligent weighing management based on dynamic compensation and improving the adaptability and accuracy of weighing.

[0016] Other features and advantages of the present application will be described in the following description, and in part will become apparent from the description, or understood by practicing the embodiments of the present application. The objectives and other advantages of the present application can be achieved and obtained through the structures particularly pointed out in the written description and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A flowchart of a construction site intelligent weighing management method based on dynamic compensation provided in an embodiment of the present application; Figure 2 A flowchart of obtaining the rotation state of a tank body in a construction site intelligent weighing management method based on dynamic compensation provided in an embodiment of the present application; Figure 3 A flowchart of obtaining final weight data for the construction site intelligent weighing management method based on dynamic compensation provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0020] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0021] Please refer to Figure 1 , Figure 1This is a flow chart of a construction site intelligent weighing management method based on dynamic compensation in some embodiments of the present application. The construction site intelligent weighing management method based on dynamic compensation is used in a terminal device, such as a computer, a mobile phone terminal, etc. The construction site intelligent weighing management method based on dynamic compensation includes the following steps: S11, obtaining the weighing status of the weighing device, including whether it is weighing or not weighing; S121. If the weighing status is not weighing, perform zero point calibration; S122. If the weighing status is "weighing", the corresponding raw weight data, vibration amplitude, tank rotation speed and vehicle parking inclination angle are obtained according to the preset sampling frequency; S13, performing processing according to the tank body rotation speed and vibration amplitude to obtain the rotation state of the tank body; S14, performing adaptive filtering and compensation processing on the original weight data set according to the rotation state to obtain final measured weight data; S15. Perform abnormal value detection on the final measured weight data and perform intelligent weighing management based on the detection results.

[0022] It should be noted that in order to achieve accurate weighing in construction engineering scenarios, first of all, calibration is performed based on the two situations of weighing and not weighing. When not weighing, the sensor is zeroed. If it is weighing, it is further comprehensively judged whether the tank is in a static state or a moving state. The moving state is further divided into low speed and high speed. Adaptive filtering compensation processing is performed according to different states. Afterwards, the final measured weight data obtained is detected for abnormalities, and the data that passes the detection generates a corresponding data packet, which is fed back to the management end for inspection, thereby achieving high-precision weighing, efficient interaction and improved work efficiency.

[0023] According to an embodiment of the present invention, obtaining the weighing status of the weighing device, including whether it is weighing or not weighing, includes: Get real-time weight data from weighing equipment; If the real-time weight data is greater than or equal to the preset weight threshold, the weighing state is weighing; If the real-time weight data is less than the preset weight threshold, the weighing state is not weighing; If the weighing status is not weighing, the real-time weight data is processed to obtain the real-time weight average within a preset time period; If the real-time weight average is greater than the dynamic zero drift threshold, the sensor automatic calibration process is activated.

[0024] It should be noted that a threshold comparison is performed based on the real-time weight data of the weighing equipment to determine whether it is weighing or not. If it is not weighing, the multiple real-time weight data collected within the preset time period are further averaged to obtain the real-time weight average, which is then compared with the dynamic zero drift threshold. If it is less than or equal to the dynamic zero drift threshold, it is determined that the weighing equipment does not need to be calibrated. If it is greater than the dynamic zero drift threshold, the sensor is automatically calibrated according to the real-time weight average to ensure the accuracy of the weighing equipment.

[0025] According to an embodiment of the present invention, the further embodiment includes: Obtain real-time environmental monitoring data of weighing equipment, including real-time temperature and real-time humidity; Comparing the real-time temperature and real-time humidity with the corresponding preset standard temperature and preset standard humidity, respectively, to obtain corresponding temperature deviation values ​​and humidity deviation values; Performing weighted summation processing on the temperature deviation value and the humidity deviation value with the corresponding preset temperature impact gradient value and preset humidity impact gradient value respectively to obtain an environmental impact coefficient; Get the power-on time and preset life of the sensor; Comparing the power-on time with a preset lifespan to obtain a sensor aging evaluation parameter, and multiplying the parameter by a preset aging impact gradient value to obtain an aging impact coefficient; The preset initial zero drift threshold is corrected according to the environmental influence coefficient and the aging influence coefficient in combination with a preset adaptive adjustment factor to obtain a dynamic zero drift threshold.

[0026] It should be noted that since most weighing equipment is outdoors, the sensor is easily affected by the environment. Therefore, the real-time temperature and real-time humidity are collected and compared with the corresponding preset standard temperature and preset standard humidity respectively to obtain the corresponding temperature deviation value and humidity deviation value, where the temperature deviation value refers to the absolute value of the difference between the real-time temperature and the preset standard temperature, and the humidity deviation value refers to the absolute value of the difference between the real-time humidity and the preset standard humidity. The temperature deviation value is multiplied by the preset temperature impact gradient value, and the humidity deviation value is multiplied by the preset humidity impact gradient value, and then summed to obtain the environmental impact coefficient. For example, the temperature deviation value is 3°C, the preset temperature impact gradient value is 0.002, the humidity deviation value is 10%, and the preset humidity impact gradient value is 0.001, then 3x0.002+0.1x0.001=0.0061 is the environmental impact coefficient; compare the power-on time of the sensor with the preset lifespan. For example, the power-on time is 100 days and the preset lifespan is 1095 days, then 100 / 1095≈0.09 1 is the sensor aging evaluation parameter, which is then multiplied by the preset aging impact gradient value of 0.3. The aging impact coefficient is 0.091 x 0.3 = 0.0273. Finally, the preset initial zero drift threshold is corrected based on the obtained environmental impact coefficient and aging impact coefficient combined with the preset adaptive adjustment factor to obtain the dynamic zero drift threshold: (1 + 0.0061 + 0.0273) x the preset adaptive adjustment factor x the preset initial zero drift threshold. The dynamic zero drift threshold is calculated as (1 + 0.0061 + 0.0273) x the preset adaptive adjustment factor x the preset initial zero drift threshold. The preset temperature impact gradient value, humidity impact gradient value, and aging impact gradient value are calibrated by those skilled in the art based on a large number of historical weighing equipment operation logs and can be dynamically adjusted. When the weighing error within a preset time period is less than or equal to the preset weighing error threshold, the preset adaptive adjustment factor is 0.95 to increase sensitivity. If the weighing error is greater than the preset weighing error threshold, the preset adaptive adjustment factor is 1 + 0.1 x [(weighing error / preset weighing error threshold) - 1] to increase threshold stability.

[0027] Please refer to Figure 2 , Figure 2 The flowchart of the method for intelligent weighing management of a construction site based on dynamic compensation in some embodiments of the present application is as follows: S21, performing Fourier transform processing on the vibration amplitude to obtain the vibration frequency; S22, performing feature extraction according to the vibration frequency to obtain a main frequency component and a low-frequency energy ratio; S23, inputting the tank body rotation speed, main frequency component and low-frequency energy ratio into a preset tank body rotation state assessment model for processing to obtain the tank body rotation state assessment parameters; S24. Compare the rotation state evaluation parameter with the first preset rotation state parameter threshold and the second preset rotation state parameter threshold respectively to obtain the rotation state of the tank body, including a stationary state, a low-speed rotation state or a high-speed rotation state.

[0028] It should be noted that in the intelligent weighing management of construction sites, accurately identifying the rotation state of the concrete mixer tank is a key link in realizing dynamic weighing compensation. In order to accurately determine the rotation state of the tank, in addition to the tank rotation speed, the vibration amplitude is also comprehensively considered after Fourier transform processing to obtain the vibration frequency. At the same time, the main frequency component and the low-frequency energy ratio are extracted, where the main frequency component refers to the frequency corresponding to the spectrum peak, the low-frequency energy ratio refers to the ratio of the low-frequency band (0-5Hz) to the total energy, and the total energy refers to the sum of the 0-5Hz low-frequency band energy and the 5-20Hz high-frequency band energy. The frequency above 20Hz is judged as noise and is removed. The rotation speed, main frequency component and low-frequency energy ratio are input into a preset tank rotation state evaluation model for processing to obtain the rotation state evaluation parameters of the tank. The preset tank rotation state evaluation model is obtained by training with a large number of historical samples of tank rotation speed, main frequency component and low-frequency energy ratio and corresponding rotation state evaluation parameters; if the rotation state evaluation parameter is less than or equal to a first preset rotation state parameter threshold, the rotation state of the tank is determined to be a stationary state; if the rotation state evaluation parameter is greater than the first preset rotation state parameter threshold and less than or equal to the second preset rotation state parameter threshold, the rotation state of the tank is determined to be a low-speed rotation state, otherwise it is a high-speed rotation state.

[0029] Please refer to Figure 3 , Figure 3 This is a flow chart of obtaining final weight data for a construction site intelligent weighing management method based on dynamic compensation in some embodiments of the present application. According to an embodiment of the present invention, performing adaptive filtering and compensation processing on the original weight data set according to the rotation state to obtain the final weight data includes: S31, the final measured weight data includes static final measured weight data, low-speed final measured weight data or high-speed final measured weight data; S32, processing the vibration amplitude and the tank rotation speed in combination with a preset compensation coefficient to obtain vibration compensation quality data; S33, if the rotation state is a stationary state, averaging the original weight data set according to a preset time window to obtain static final weight data; S34. If the rotation state is a low-speed rotation state, query a preset adaptive filtering compensation processing database to obtain corresponding low-speed process noise covariance and low-speed measurement noise covariance; S35, performing adaptive filtering compensation processing on the original weight data set corresponding to the preset time window in combination with the low-speed process noise covariance and the low-speed measurement noise covariance to obtain a low-speed compensated weight data set; S36, performing subtraction and averaging processing on the low-speed compensation weight data set and the vibration compensation mass data to obtain low-speed final measurement weight data; S37. If the rotation state is a high-speed rotation state, query a preset adaptive filtering compensation processing database to obtain corresponding high-speed process noise covariance and high-speed measurement noise covariance; S38, performing adaptive filtering compensation processing on the original weight data set corresponding to the preset time window in combination with the high-speed process noise covariance and the high-speed measurement noise covariance to obtain a high-speed compensated weight data set; S39: Subtract the high-speed compensated weight data set from the vibration compensated mass data and calculate the average value to obtain high-speed final measured weight data.

[0030] It should be noted that when it is determined to be in a stationary state, no additional compensation is required. The original weight data set within the preset time window is averaged to obtain the static final weight data. For example, if the sampling rate is 10 Hz and the time window is 5, 5 original weight data within 0.5 seconds are covered. When the tank rotates, two main interferences, centrifugal force and vibration, are generated. In order to eliminate the interference, the vibration amplitude and the tank speed are combined with the preset compensation coefficient for processing to obtain vibration-compensated mass data. The preset compensation coefficient includes a vibration compensation coefficient, a speed compensation coefficient and a system reference compensation coefficient, which are determined by technicians in this field based on the conditions of changing the load at a fixed speed and changing the speed at a fixed load through multivariate regression optimization. In this embodiment, the vibration compensation coefficient is 0.05, the speed compensation coefficient is 0.001, and the system reference compensation coefficient (indicating inherent deviation) is 0.1. If the speed is 4 rpm and the vibration amplitude is 0.2, then 0.001x4 2+0.05x0.2+0.1=0.126 is the vibration compensation quality data; when the tank body is in the low-speed rotation state or the high-speed rotation state, the preset adaptive filtering compensation processing database is queried respectively to obtain the corresponding process noise covariance and measurement noise covariance, wherein the preset adaptive filtering compensation processing database is pre-constructed by those skilled in the art based on the weighing log information of a large number of historical samples and can be dynamically adjusted; in this embodiment, the low-speed process noise covariance is 0.02, the low-speed measurement noise covariance is 0.05, the high-speed process noise covariance is 0.05, and the high-speed measurement noise The covariance value is 0.1; if the original weight data is [1001.2, 1002.8, 1000.5, ...], first perform Kalman filter initialization (the initial state value is 1001.2, the initial estimation error covariance is set to 1), and then perform Kalman filter iterative processing, that is, first determine the first filter estimation error covariance (the sum of the initial estimation error covariance and the low-speed process noise covariance is 1.02), and then determine the first Kalman gain, which is the first filter estimation error covariance divided by the sum of the first filter estimation error covariance and the low-speed measurement noise covariance, that is, 1.02 / (1.02+0.0 5)≈0.953, then, determine the first low-speed compensation weight data, that is, 1001.2+0.953x(1001.2-1001.2)=1001.2, and at the same time, output the first filtering error covariance, that is, (1-0.953)x1.02=0.048, for the second iterative processing; during the second Kalman filter iterative processing, the predicted weight is 1001.2, and the second filtering estimation error covariance is 0.048+0.02=0.068, further determining the second Kalman gain, that is, 0.068 / (0.068+0.05)≈0.576, Finally, the second low-speed compensation weight data is determined, that is, 1001.2+0.576x(1002.8-1001.2)=1002.12. At the same time, the second filtering error covariance is output, that is, (1-0.576)x0.068≈0.029, for the third iterative processing. The iterative processing is repeated to obtain the low-speed compensation weight data set. Similarly, the high-speed compensation weight data set can be obtained. Finally, the obtained low-speed compensation weight data set or high-speed compensation weight data set is subtracted from the vibration compensation mass data in turn and the average is calculated to obtain the low-speed final measurement weight data or the high-speed final measurement weight data.

[0031] According to an embodiment of the present invention, the process of detecting abnormal values ​​on the final weight data and performing intelligent weighing management based on the detection results includes: Extract features from static final weight data, low-speed final weight data, or high-speed final weight data within a preset time period to obtain the corresponding mean and standard deviation; Processing is performed based on the mean and standard deviation to obtain a weight lower limit threshold and a weight upper limit threshold corresponding to the static final measurement weight data, the low-speed final measurement weight data, or the high-speed final measurement weight data; Perform threshold comparison on the static final measurement weight data, the low-speed final measurement weight data or the high-speed final measurement weight data with the corresponding lower weight limit threshold and upper weight limit threshold respectively; If the weight is between the lower weight limit threshold and the upper weight limit threshold, it is determined to be normal data; otherwise, it is determined to be an abnormal value and is eliminated to obtain the corresponding static final measurement weight normal data, low-speed final measurement weight normal data or high-speed final measurement weight normal data within the preset time period; Processing the static final weight normal data, the low-speed final weight normal data, or the high-speed final weight normal data through a preset isolation forest algorithm to obtain a data anomaly score; If the data abnormality score is greater than the preset abnormality warning threshold, the data is eliminated and the corresponding static final weight valid data, low-speed final weight valid data or high-speed final weight valid data within the preset time period are obtained; The static final measurement weight valid data, the low-speed final measurement weight valid data or the high-speed final measurement weight valid data are packaged in a preset format and sent to the management end for display.

[0032] It should be noted that, in order to perform anomaly detection on the final weight data obtained by the adaptive filtering compensation process, this embodiment adopts two dimensions of data anomaly score based on 3 times the standard deviation to determine the threshold and based on the isolation forest algorithm to determine the path length for detection, wherein the lower weight threshold is the mean minus 3 times the standard deviation, and the upper weight threshold is the mean plus 3 times the standard deviation; the preset isolation forest algorithm calculates the data anomaly score based on the path length, and the higher the score, the more likely it is an outlier; the combination of the two can not only solve extreme outliers, but also identify local outliers. Finally, the static final weight valid data, low-speed final weight valid data or high-speed final weight valid data that have passed the detection are packaged in a preset format and sent to the management end for display.

[0033] According to an embodiment of the present invention, the further embodiment includes: Comparing the parking inclination angle of the vehicle with a preset inclination angle threshold; If the parking inclination angle of the vehicle is greater than a preset inclination angle threshold, a weighing abnormality warning response is output; If the vehicle parking inclination angle is less than or equal to a preset inclination angle threshold, processing is performed according to the vehicle parking inclination angle and the final measured weight data to obtain final measured weight optimization data.

[0034] It should be noted that the vehicle parking inclination angle directly affects the accuracy of weight measurement, and gravity component correction is required. If the inclination angle is too large, weighing is refused and an early warning response is output; if it is not greater than the preset inclination angle threshold, it is processed according to the vehicle parking inclination angle and the final measurement weight data to obtain the final measurement weight optimization data, where the vehicle parking inclination angle includes the lateral inclination angle θ and the longitudinal inclination angle γ, and the final measurement weight optimization data is the final measurement weight data / (cosθcosγ).

[0035] According to an embodiment of the present invention, the further embodiment includes: Averaging the static final measurement weight valid data, the low-speed final measurement weight valid data, or the high-speed final measurement weight valid data corresponding to a preset time period to obtain static final measurement weight average data, low-speed final measurement weight average data, or high-speed final measurement weight average data; Comparing the static final measurement weight average data, the low-speed final measurement weight average data, or the high-speed final measurement weight average data with the corresponding preset mean threshold value to obtain a mean comparison result; Perform peak extraction processing on the static final measurement weight valid data, low-speed final measurement weight valid data or high-speed final measurement weight valid data corresponding to a preset time period to obtain static final measurement weight peak data, low-speed final measurement weight peak data or high-speed final measurement weight peak data; Comparing the static final measurement weight peak data, the low-speed final measurement weight peak data, or the high-speed final measurement weight peak data with the corresponding peak threshold value to obtain a peak comparison result; Comparing and processing the static final weight valid data, the low-speed final weight valid data or the high-speed final weight valid data corresponding to the preset time period to obtain the static final weight change rate, the low-speed final weight change rate or the high-speed final weight change rate; Comparing the static final measurement weight change rate, the low-speed final measurement weight change rate, or the high-speed final measurement weight change rate with corresponding change rate thresholds to obtain a change rate comparison result; If the mean value comparison result, the peak value comparison result and the change rate comparison result are all not greater than the threshold value, no overload warning is output; Otherwise, an overload warning is output.

[0036] It should be noted that in order to accurately assess the problem of vehicle overloading, this embodiment conducts a comprehensive evaluation from three dimensions: mean comparison, peak comparison and weight change rate, and the mean, peak and change rate are respectively compared with the corresponding thresholds to obtain the threshold comparison results, including greater than the threshold or not greater than the threshold, wherein the change rate refers to the absolute value of the difference between the final measured weight valid data at the latter time point and the final measured weight valid data at the previous time point and the ratio of the final measured weight valid data at the previous time point. Finally, an AND operation is performed. Only when none of them is greater than the threshold, it is determined to be not overloaded. Otherwise, as long as one exceeds the threshold, it is determined to be overloaded.

[0037] It is worth mentioning that according to an embodiment of the present invention, the present invention further includes: Comparing the tank rotation speed with a preset dynamic rotation speed threshold; If the tank rotation speed is less than the preset dynamic rotation speed threshold, the main frequency component is compared with the preset main frequency threshold, and the low frequency energy ratio is compared with the preset low frequency energy ratio threshold; If the main frequency component is greater than or equal to the preset main frequency threshold, or the low frequency energy ratio is less than or equal to the preset low frequency energy ratio threshold, the rotation state of the tank is determined to be a transition state; A corresponding weighing management strategy is determined according to the transition state.

[0038] It should be noted that the transition state refers to the dynamic change process of the equipment from one stable state (stationary, low-speed rotation, high-speed rotation) to another stable state. It is characterized by temporality, dynamism and uncertainty. Accurately identifying the transition state can avoid misjudgment (such as speed fluctuations and sensor data jumps being misjudged as abnormalities in the stable state). First, the tank speed is compared with the threshold to determine that the speed is extremely low (close to stationary), but it is impossible to fully determine whether it is "stable and stationary" based on the speed alone. Then, the main frequency component and the low-frequency energy ratio are compared with the thresholds respectively. As long as the main frequency component is greater than or equal to the preset main frequency threshold, or the low-frequency energy ratio is less than or equal to the preset low-frequency energy ratio threshold, the rotation state of the tank is determined to be a transition state, otherwise it is a stationary state.

[0039] The present invention also discloses a construction site intelligent weighing management system based on dynamic compensation, comprising a memory and a processor. The memory includes a construction site intelligent weighing management method program based on dynamic compensation. When the construction site intelligent weighing management method program based on dynamic compensation is executed by the processor, the following steps are implemented: Get the weighing status of the weighing device, including whether it is weighing or not; If the weighing status is not weighing, perform zero point calibration; If the weighing status is "weighing", the corresponding raw weight data, vibration amplitude, tank rotation speed and vehicle parking inclination angle are obtained according to the preset sampling frequency; Processing is performed according to the tank body rotation speed and vibration amplitude to obtain the rotation state of the tank body; performing adaptive filtering and compensation processing on the original weight data set according to the rotation state to obtain final measured weight data; The final measured weight data is subjected to abnormal value detection, and intelligent weighing management is performed based on the detection results.

[0040] It should be noted that in order to achieve accurate weighing in construction engineering scenarios, first of all, calibration is performed based on the two situations of weighing and not weighing. When not weighing, the sensor is zeroed. If it is weighing, it is further comprehensively judged whether the tank is in a static state or a moving state. The moving state is further divided into low speed and high speed. Adaptive filtering compensation processing is performed according to different states. Afterwards, the final measured weight data obtained is detected for abnormalities, and the data that passes the detection generates a corresponding data packet, which is fed back to the management end for inspection, thereby achieving high-precision weighing, efficient interaction and improved work efficiency.

[0041] According to an embodiment of the present invention, obtaining the weighing status of the weighing device, including whether it is weighing or not weighing, includes: Get real-time weight data from weighing equipment; If the real-time weight data is greater than or equal to the preset weight threshold, the weighing state is weighing; If the real-time weight data is less than the preset weight threshold, the weighing state is not weighing; If the weighing status is not weighing, the real-time weight data is processed to obtain the real-time weight average within a preset time period; If the real-time weight average is greater than the dynamic zero drift threshold, the sensor automatic calibration process is activated.

[0042] It should be noted that a threshold comparison is performed based on the real-time weight data of the weighing equipment to determine whether it is weighing or not. If it is not weighing, the multiple real-time weight data collected within the preset time period are further averaged to obtain the real-time weight average, which is then compared with the dynamic zero drift threshold. If it is less than or equal to the dynamic zero drift threshold, it is determined that the weighing equipment does not need to be calibrated. If it is greater than the dynamic zero drift threshold, the sensor is automatically calibrated according to the real-time weight average to ensure the accuracy of the weighing equipment.

[0043] According to an embodiment of the present invention, the further embodiment includes: Obtain real-time environmental monitoring data of weighing equipment, including real-time temperature and real-time humidity; Comparing the real-time temperature and real-time humidity with the corresponding preset standard temperature and preset standard humidity, respectively, to obtain corresponding temperature deviation values ​​and humidity deviation values; Performing weighted summation processing on the temperature deviation value and the humidity deviation value with the corresponding preset temperature impact gradient value and preset humidity impact gradient value respectively to obtain an environmental impact coefficient; Get the power-on time and preset life of the sensor; Comparing the power-on time with a preset lifespan to obtain a sensor aging evaluation parameter, and multiplying the parameter by a preset aging impact gradient value to obtain an aging impact coefficient; The preset initial zero drift threshold is corrected according to the environmental influence coefficient and the aging influence coefficient in combination with a preset adaptive adjustment factor to obtain a dynamic zero drift threshold.

[0044] It should be noted that since most weighing equipment is outdoors, the sensor is easily affected by the environment. Therefore, the real-time temperature and real-time humidity are collected and compared with the corresponding preset standard temperature and preset standard humidity respectively to obtain the corresponding temperature deviation value and humidity deviation value, where the temperature deviation value refers to the absolute value of the difference between the real-time temperature and the preset standard temperature, and the humidity deviation value refers to the absolute value of the difference between the real-time humidity and the preset standard humidity. The temperature deviation value is multiplied by the preset temperature impact gradient value, and the humidity deviation value is multiplied by the preset humidity impact gradient value, and then summed to obtain the environmental impact coefficient. For example, the temperature deviation value is 3°C, the preset temperature impact gradient value is 0.002, the humidity deviation value is 10%, and the preset humidity impact gradient value is 0.001, then 3x0.002+0.1x0.001=0.0061 is the environmental impact coefficient; compare the power-on time of the sensor with the preset lifespan. For example, the power-on time is 100 days and the preset lifespan is 1095 days, then 100 / 1095≈0.09 1 is the sensor aging evaluation parameter, which is then multiplied by the preset aging impact gradient value of 0.3. The aging impact coefficient is 0.091 x 0.3 = 0.0273. Finally, the preset initial zero drift threshold is corrected based on the obtained environmental impact coefficient and aging impact coefficient combined with the preset adaptive adjustment factor to obtain the dynamic zero drift threshold: (1 + 0.0061 + 0.0273) x the preset adaptive adjustment factor x the preset initial zero drift threshold. The dynamic zero drift threshold is calculated as (1 + 0.0061 + 0.0273) x the preset adaptive adjustment factor x the preset initial zero drift threshold. The preset temperature impact gradient value, humidity impact gradient value, and aging impact gradient value are calibrated by those skilled in the art based on a large number of historical weighing equipment operation logs and can be dynamically adjusted. When the weighing error within a preset time period is less than or equal to the preset weighing error threshold, the preset adaptive adjustment factor is 0.95 to increase sensitivity. If the weighing error is greater than the preset weighing error threshold, the preset adaptive adjustment factor is 1 + 0.1 x [(weighing error / preset weighing error threshold) - 1] to increase threshold stability.

[0045] According to an embodiment of the present invention, the processing according to the rotation speed and vibration amplitude of the tank body to obtain the rotation state of the tank body includes: Performing Fourier transform on the vibration amplitude to obtain the vibration frequency; Perform feature extraction based on the vibration frequency to obtain a main frequency component and a low-frequency energy ratio; Inputting the tank body rotation speed, main frequency component and low frequency energy ratio into a preset tank body rotation state assessment model for processing to obtain the tank body rotation state assessment parameters; The rotation state evaluation parameter is compared with a first preset rotation state parameter threshold and a second preset rotation state parameter threshold respectively to obtain the rotation state of the tank body, including a stationary state, a low-speed rotation state or a high-speed rotation state.

[0046] It should be noted that in the intelligent weighing management of construction sites, accurately identifying the rotation state of the concrete mixer tank is a key link in realizing dynamic weighing compensation. In order to accurately determine the rotation state of the tank, in addition to the tank rotation speed, the vibration amplitude is also comprehensively considered after Fourier transform processing to obtain the vibration frequency. At the same time, the main frequency component and the low-frequency energy ratio are extracted, where the main frequency component refers to the frequency corresponding to the spectrum peak, the low-frequency energy ratio refers to the ratio of the low-frequency band (0-5Hz) to the total energy, and the total energy refers to the sum of the 0-5Hz low-frequency band energy and the 5-20Hz high-frequency band energy. The frequency above 20Hz is judged as noise and is removed. The rotation speed, main frequency component and low-frequency energy ratio are input into a preset tank rotation state evaluation model for processing to obtain the rotation state evaluation parameters of the tank. The preset tank rotation state evaluation model is obtained by training with a large number of historical samples of tank rotation speed, main frequency component and low-frequency energy ratio and corresponding rotation state evaluation parameters; if the rotation state evaluation parameter is less than or equal to a first preset rotation state parameter threshold, the rotation state of the tank is determined to be a stationary state; if the rotation state evaluation parameter is greater than the first preset rotation state parameter threshold and less than or equal to the second preset rotation state parameter threshold, the rotation state of the tank is determined to be a low-speed rotation state, otherwise it is a high-speed rotation state.

[0047] According to an embodiment of the present invention, performing adaptive filtering and compensation processing on the original weight data set according to the rotation state to obtain final measured weight data includes: The final measured weight data includes static final measured weight data, low-speed final measured weight data or high-speed final measured weight data; Processing the vibration amplitude and the tank rotation speed in combination with a preset compensation coefficient to obtain vibration compensation quality data; If the rotation state is a stationary state, the original weight data set is averaged according to a preset time window to obtain static final weight data; If the rotation state is a low-speed rotation state, querying a preset adaptive filtering compensation processing database to obtain corresponding low-speed process noise covariance and low-speed measurement noise covariance; The original weight data set corresponding to the preset time window is subjected to adaptive filtering compensation processing in combination with the low-speed process noise covariance and the low-speed measurement noise covariance to obtain a low-speed compensated weight data set; Subtracting the low-speed compensation weight data set from the vibration compensation mass data and calculating the average value to obtain low-speed final measurement weight data; If the rotation state is a high-speed rotation state, querying a preset adaptive filtering compensation processing database to obtain corresponding high-speed process noise covariance and high-speed measurement noise covariance; The original weight data set corresponding to the preset time window is respectively combined with the high-speed process noise covariance and the high-speed measurement noise covariance to perform adaptive filtering compensation processing to obtain a high-speed compensated weight data set; The high-speed compensated weight data set is respectively subtracted from the vibration compensated mass data and averaged to obtain high-speed final measured weight data.

[0048] It should be noted that when it is determined to be in a stationary state, no additional compensation is required. The original weight data set within the preset time window is averaged to obtain the static final weight data. For example, if the sampling rate is 10 Hz and the time window is 5, 5 original weight data within 0.5 seconds are covered. When the tank rotates, two main interferences, centrifugal force and vibration, are generated. In order to eliminate the interference, the vibration amplitude and the tank speed are combined with the preset compensation coefficient for processing to obtain vibration-compensated mass data. The preset compensation coefficient includes a vibration compensation coefficient, a speed compensation coefficient and a system reference compensation coefficient, which are determined by technicians in this field based on the conditions of changing the load at a fixed speed and changing the speed at a fixed load through multivariate regression optimization. In this embodiment, the vibration compensation coefficient is 0.05, the speed compensation coefficient is 0.001, and the system reference compensation coefficient (indicating inherent deviation) is 0.1. If the speed is 4 rpm and the vibration amplitude is 0.2, then 0.001x4 2+0.05x0.2+0.1=0.126 is the vibration compensation quality data; when the tank body is in the low-speed rotation state or the high-speed rotation state, the preset adaptive filtering compensation processing database is queried respectively to obtain the corresponding process noise covariance and measurement noise covariance, wherein the preset adaptive filtering compensation processing database is pre-constructed by those skilled in the art based on the weighing log information of a large number of historical samples and can be dynamically adjusted; in this embodiment, the low-speed process noise covariance is 0.02, the low-speed measurement noise covariance is 0.05, the high-speed process noise covariance is 0.05, and the high-speed measurement noise The covariance value is 0.1; if the original weight data is [1001.2, 1002.8, 1000.5, ...], first perform Kalman filter initialization (the initial state value is 1001.2, the initial estimation error covariance is set to 1), and then perform Kalman filter iterative processing, that is, first determine the first filter estimation error covariance (the sum of the initial estimation error covariance and the low-speed process noise covariance is 1.02), and then determine the first Kalman gain, which is the first filter estimation error covariance divided by the sum of the first filter estimation error covariance and the low-speed measurement noise covariance, that is, 1.02 / (1.02+0.0 5)≈0.953, then, determine the first low-speed compensation weight data, that is, 1001.2+0.953x(1001.2-1001.2)=1001.2, and at the same time, output the first filtering error covariance, that is, (1-0.953)x1.02=0.048, for the second iterative processing; during the second Kalman filter iterative processing, the predicted weight is 1001.2, and the second filtering estimation error covariance is 0.048+0.02=0.068, further determining the second Kalman gain, that is, 0.068 / (0.068+0.05)≈0.576, Finally, the second low-speed compensation weight data is determined, that is, 1001.2+0.576x(1002.8-1001.2)=1002.12. At the same time, the second filtering error covariance is output, that is, (1-0.576)x0.068≈0.029, for the third iterative processing. The iterative processing is repeated to obtain the low-speed compensation weight data set. Similarly, the high-speed compensation weight data set can be obtained. Finally, the obtained low-speed compensation weight data set or high-speed compensation weight data set is subtracted from the vibration compensation mass data in turn and the average is calculated to obtain the low-speed final measurement weight data or the high-speed final measurement weight data.

[0049] According to an embodiment of the present invention, the process of detecting abnormal values ​​on the final weight data and performing intelligent weighing management based on the detection results includes: Extract features from static final weight data, low-speed final weight data, or high-speed final weight data within a preset time period to obtain the corresponding mean and standard deviation; Processing is performed based on the mean and standard deviation to obtain a weight lower limit threshold and a weight upper limit threshold corresponding to the static final measurement weight data, the low-speed final measurement weight data, or the high-speed final measurement weight data; Perform threshold comparison on the static final measurement weight data, the low-speed final measurement weight data or the high-speed final measurement weight data with the corresponding lower weight limit threshold and upper weight limit threshold respectively; If the weight is between the lower weight limit threshold and the upper weight limit threshold, it is determined to be normal data; otherwise, it is determined to be an abnormal value and is eliminated to obtain the corresponding static final measurement weight normal data, low-speed final measurement weight normal data or high-speed final measurement weight normal data within the preset time period; Processing the static final weight normal data, the low-speed final weight normal data, or the high-speed final weight normal data through a preset isolation forest algorithm to obtain a data anomaly score; If the data abnormality score is greater than the preset abnormality warning threshold, the data is eliminated and the corresponding static final weight valid data, low-speed final weight valid data or high-speed final weight valid data within the preset time period are obtained; The static final measurement weight valid data, the low-speed final measurement weight valid data or the high-speed final measurement weight valid data are packaged in a preset format and sent to the management end for display.

[0050] It should be noted that, in order to perform anomaly detection on the final weight data obtained by the adaptive filtering compensation process, this embodiment adopts two dimensions of data anomaly score based on 3 times the standard deviation to determine the threshold and based on the isolation forest algorithm to determine the path length for detection, wherein the lower weight threshold is the mean minus 3 times the standard deviation, and the upper weight threshold is the mean plus 3 times the standard deviation; the preset isolation forest algorithm calculates the data anomaly score based on the path length, and the higher the score, the more likely it is an outlier; the combination of the two can not only solve extreme outliers, but also identify local outliers. Finally, the static final weight valid data, low-speed final weight valid data or high-speed final weight valid data that have passed the detection are packaged in a preset format and sent to the management end for display.

[0051] According to an embodiment of the present invention, the further embodiment includes: Comparing the parking inclination angle of the vehicle with a preset inclination angle threshold; If the parking inclination angle of the vehicle is greater than a preset inclination angle threshold, a weighing abnormality warning response is output; If the vehicle parking inclination angle is less than or equal to a preset inclination angle threshold, processing is performed according to the vehicle parking inclination angle and the final measured weight data to obtain final measured weight optimization data.

[0052] It should be noted that the vehicle parking inclination angle directly affects the accuracy of weight measurement, and gravity component correction is required. If the inclination angle is too large, weighing is refused and an early warning response is output; if it is not greater than the preset inclination angle threshold, it is processed according to the vehicle parking inclination angle and the final measurement weight data to obtain the final measurement weight optimization data, where the vehicle parking inclination angle includes the lateral inclination angle θ and the longitudinal inclination angle γ, and the final measurement weight optimization data is the final measurement weight data / (cosθcosγ).

[0053] According to an embodiment of the present invention, the further embodiment includes: Averaging the static final measurement weight valid data, the low-speed final measurement weight valid data, or the high-speed final measurement weight valid data corresponding to a preset time period to obtain static final measurement weight average data, low-speed final measurement weight average data, or high-speed final measurement weight average data; Comparing the static final measurement weight average data, the low-speed final measurement weight average data, or the high-speed final measurement weight average data with the corresponding preset mean threshold value to obtain a mean comparison result; Perform peak extraction processing on the static final measurement weight valid data, low-speed final measurement weight valid data or high-speed final measurement weight valid data corresponding to a preset time period to obtain static final measurement weight peak data, low-speed final measurement weight peak data or high-speed final measurement weight peak data; Comparing the static final measurement weight peak data, the low-speed final measurement weight peak data, or the high-speed final measurement weight peak data with the corresponding peak threshold value to obtain a peak comparison result; Comparing and processing the static final weight valid data, the low-speed final weight valid data or the high-speed final weight valid data corresponding to the preset time period to obtain the static final weight change rate, the low-speed final weight change rate or the high-speed final weight change rate; Comparing the static final measurement weight change rate, the low-speed final measurement weight change rate, or the high-speed final measurement weight change rate with corresponding change rate thresholds to obtain a change rate comparison result; If the mean value comparison result, the peak value comparison result and the change rate comparison result are all not greater than the threshold value, no overload warning is output; Otherwise, an overload warning is output.

[0054] It should be noted that in order to accurately assess the problem of vehicle overloading, this embodiment conducts a comprehensive evaluation from three dimensions: mean comparison, peak comparison and weight change rate, and the mean, peak and change rate are respectively compared with the corresponding thresholds to obtain the threshold comparison results, including greater than the threshold or not greater than the threshold, wherein the change rate refers to the absolute value of the difference between the final measured weight valid data at the latter time point and the final measured weight valid data at the previous time point and the ratio of the final measured weight valid data at the previous time point. Finally, an AND operation is performed. Only when none of them is greater than the threshold, it is determined to be not overloaded. Otherwise, as long as one exceeds the threshold, it is determined to be overloaded.

[0055] It is worth mentioning that according to an embodiment of the present invention, the present invention further includes: Comparing the tank rotation speed with a preset dynamic rotation speed threshold; If the tank rotation speed is less than the preset dynamic rotation speed threshold, the main frequency component is compared with the preset main frequency threshold, and the low frequency energy ratio is compared with the preset low frequency energy ratio threshold; If the main frequency component is greater than or equal to the preset main frequency threshold, or the low frequency energy ratio is less than or equal to the preset low frequency energy ratio threshold, the rotation state of the tank is determined to be a transition state; A corresponding weighing management strategy is determined according to the transition state.

[0056] It should be noted that the transition state refers to the dynamic change process of the equipment from one stable state (stationary, low-speed rotation, high-speed rotation) to another stable state. It is characterized by temporality, dynamism and uncertainty. Accurately identifying the transition state can avoid misjudgment (such as speed fluctuations and sensor data jumps being misjudged as abnormalities in the stable state). First, the tank speed is compared with the threshold to determine that the speed is extremely low (close to stationary), but it is impossible to fully determine whether it is "stable and stationary" based on the speed alone. Then, the main frequency component and the low-frequency energy ratio are compared with the thresholds respectively. As long as the main frequency component is greater than or equal to the preset main frequency threshold, or the low-frequency energy ratio is less than or equal to the preset low-frequency energy ratio threshold, the rotation state of the tank is determined to be a transition state, otherwise it is a stationary state.

[0057] The third aspect of the present invention provides a readable storage medium, which stores a program for the intelligent weighing management method for a construction site based on dynamic compensation. When the program for the intelligent weighing management method for a construction site based on dynamic compensation is executed by a processor, the steps of the intelligent weighing management method for a construction site based on dynamic compensation as described in any one of the above items are implemented.

[0058] The method, system and medium for intelligent weighing management of construction sites based on dynamic compensation disclosed by the present invention determine the weighing status in real time, evaluate the rotation status of the tank body, perform dynamic real-time adaptive filtering and compensation processing, obtain final measured weight data, and perform anomaly detection, thereby realizing intelligent weighing management based on dynamic compensation and improving the adaptability and accuracy of weighing.

[0059] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0060] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0061] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0062] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware related to program instructions, and the aforementioned program may be stored in a readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0063] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as standalone products, they can also be stored on a readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This software product, stored on a storage medium, includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as removable storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. The intelligent weighing management method for construction sites based on dynamic compensation is characterized by: The following steps are involved: Get the weighing status of the weighing device, including whether it is weighing or not; If the weighing status is not weighing, perform zero point calibration; If the weighing status is "weighing", the corresponding raw weight data set, vibration amplitude, tank rotation speed and vehicle parking inclination angle are obtained according to the preset sampling frequency; Processing is performed according to the tank body rotation speed and vibration amplitude to obtain the rotation state of the tank body; performing adaptive filtering and compensation processing on the original weight data set according to the rotation state to obtain final measured weight data; The final measured weight data is subjected to abnormal value detection, and intelligent weighing management is performed based on the detection results.

2. The construction site intelligent weighing management method based on dynamic compensation according to claim 1 is characterized in that: The obtaining of the weighing status of the weighing device, including whether the weighing device is weighing or not weighing, includes: Get real-time weight data from weighing equipment; If the real-time weight data is greater than or equal to the preset weight threshold, the weighing state is weighing; If the real-time weight data is less than the preset weight threshold, the weighing state is not weighing; If the weighing status is not weighing, the real-time weight data is processed to obtain the real-time weight average within a preset time period; If the real-time weight average is greater than the dynamic zero drift threshold, the sensor automatic calibration process is activated.

3. The construction site intelligent weighing management method based on dynamic compensation according to claim 2 is characterized in that: Also includes: Obtain real-time environmental monitoring data of weighing equipment, including real-time temperature and real-time humidity; Comparing the real-time temperature and real-time humidity with the corresponding preset standard temperature and preset standard humidity, respectively, to obtain corresponding temperature deviation values ​​and humidity deviation values; Performing weighted summation processing on the temperature deviation value and the humidity deviation value with the corresponding preset temperature impact gradient value and preset humidity impact gradient value respectively to obtain an environmental impact coefficient; Get the power-on time and preset life of the sensor; Comparing the power-on time with a preset lifespan to obtain a sensor aging evaluation parameter, and multiplying the parameter by a preset aging impact gradient value to obtain an aging impact coefficient; The preset initial zero drift threshold is corrected according to the environmental influence coefficient and the aging influence coefficient in combination with a preset adaptive adjustment factor to obtain a dynamic zero drift threshold.

4. The construction site intelligent weighing management method based on dynamic compensation according to claim 3 is characterized in that: The processing according to the tank body rotation speed and vibration amplitude to obtain the rotation state of the tank body includes: Performing Fourier transform on the vibration amplitude to obtain the vibration frequency; Perform feature extraction based on the vibration frequency to obtain a main frequency component and a low-frequency energy ratio; Inputting the tank body rotation speed, main frequency component and low frequency energy ratio into a preset tank body rotation state assessment model for processing to obtain the tank body rotation state assessment parameters; The rotation state evaluation parameter is compared with a first preset rotation state parameter threshold and a second preset rotation state parameter threshold respectively to obtain the rotation state of the tank body, including a stationary state, a low-speed rotation state or a high-speed rotation state.

5. The construction site intelligent weighing management method based on dynamic compensation according to claim 4 is characterized in that: The step of performing adaptive filtering and compensation processing on the original weight data set according to the rotation state to obtain final measured weight data includes: The final measurement weight data includes static final measurement weight data, low-speed final measurement weight data or high-speed final measurement weight data; Processing the vibration amplitude and the tank rotation speed in combination with a preset compensation coefficient to obtain vibration compensation quality data; If the rotation state is a stationary state, the original weight data set is averaged according to a preset time window to obtain static final weight data; If the rotation state is a low-speed rotation state, querying a preset adaptive filtering compensation processing database to obtain corresponding low-speed process noise covariance and low-speed measurement noise covariance; The original weight data set corresponding to the preset time window is subjected to adaptive filtering compensation processing in combination with the low-speed process noise covariance and the low-speed measurement noise covariance to obtain a low-speed compensated weight data set; Subtracting the low-speed compensation weight data set from the vibration compensation mass data and calculating the average value to obtain low-speed final measurement weight data; If the rotation state is a high-speed rotation state, querying a preset adaptive filtering compensation processing database to obtain corresponding high-speed process noise covariance and high-speed measurement noise covariance; The original weight data set corresponding to the preset time window is respectively combined with the high-speed process noise covariance and the high-speed measurement noise covariance to perform adaptive filtering compensation processing to obtain a high-speed compensated weight data set; The high-speed compensated weight data set is respectively subtracted from the vibration compensated mass data and averaged to obtain high-speed final measured weight data.

6. The construction site intelligent weighing management method based on dynamic compensation according to claim 5 is characterized in that: The method of performing abnormal value detection on the final weight data and performing intelligent weighing management according to the detection results includes: Extract features from static final weight data, low-speed final weight data, or high-speed final weight data within a preset time period to obtain the corresponding mean and standard deviation; Processing is performed based on the mean and standard deviation to obtain a weight lower limit threshold and a weight upper limit threshold corresponding to the static final measurement weight data, the low-speed final measurement weight data, or the high-speed final measurement weight data; Perform threshold comparison on the static final measurement weight data, the low-speed final measurement weight data or the high-speed final measurement weight data with the corresponding lower weight limit threshold and upper weight limit threshold respectively; If the weight is between the lower weight limit threshold and the upper weight limit threshold, it is determined to be normal data; otherwise, it is determined to be an abnormal value and is eliminated to obtain the corresponding static final measurement weight normal data, low-speed final measurement weight normal data or high-speed final measurement weight normal data within the preset time period; Processing the static final weight normal data, the low-speed final weight normal data, or the high-speed final weight normal data through a preset isolation forest algorithm to obtain a data anomaly score; If the data abnormality score is greater than the preset abnormality warning threshold, the data is eliminated and the corresponding static final weight valid data, low-speed final weight valid data or high-speed final weight valid data within the preset time period are obtained; The static final measurement weight valid data, the low-speed final measurement weight valid data or the high-speed final measurement weight valid data are packaged in a preset format and sent to the management end for display.

7. The construction site intelligent weighing management method based on dynamic compensation according to claim 6 is characterized in that: Also includes: Comparing the parking inclination angle of the vehicle with a preset inclination angle threshold; If the parking inclination angle of the vehicle is greater than a preset inclination angle threshold, a weighing abnormality warning response is output; If the vehicle parking inclination angle is less than or equal to a preset inclination angle threshold, processing is performed according to the vehicle parking inclination angle and the final measured weight data to obtain final measured weight optimization data.

8. The construction site intelligent weighing management method based on dynamic compensation according to claim 7 is characterized in that: Also includes: The static final measurement weight valid data, the low-speed final measurement weight valid data or the high-speed final measurement weight valid data corresponding to the preset time period are averaged to obtain static final measurement weight average data, low-speed final measurement weight average data or high-speed final measurement weight average data; Comparing the static final measurement weight average data, the low-speed final measurement weight average data, or the high-speed final measurement weight average data with the corresponding preset mean threshold value to obtain a mean comparison result; Perform peak extraction processing on the static final measurement weight valid data, low-speed final measurement weight valid data or high-speed final measurement weight valid data corresponding to a preset time period to obtain static final measurement weight peak data, low-speed final measurement weight peak data or high-speed final measurement weight peak data; Comparing the static final measurement weight peak data, the low-speed final measurement weight peak data, or the high-speed final measurement weight peak data with the corresponding peak threshold value to obtain a peak comparison result; Comparing and processing the static final weight valid data, the low-speed final weight valid data or the high-speed final weight valid data corresponding to the preset time period to obtain the static final weight change rate, the low-speed final weight change rate or the high-speed final weight change rate; Comparing the static final measurement weight change rate, the low-speed final measurement weight change rate, or the high-speed final measurement weight change rate with corresponding change rate thresholds to obtain a change rate comparison result; If the mean value comparison result, the peak value comparison result, and the change rate comparison result are all not greater than the threshold value, no overload warning is output; Otherwise, an overload warning is output.

9. The intelligent weighing management system for construction sites based on dynamic compensation is characterized by: The system comprises a memory and a processor, wherein the memory includes a program of a construction site intelligent weighing management method based on dynamic compensation, and when the program of the construction site intelligent weighing management method based on dynamic compensation is executed by the processor, the following steps are implemented: Get the weighing status of the weighing device, including whether it is weighing or not; If the weighing status is not weighing, perform zero point calibration; If the weighing status is "weighing", the corresponding raw weight data, vibration amplitude, tank rotation speed and vehicle parking inclination angle are obtained according to the preset sampling frequency; Processing is performed according to the tank body rotation speed and vibration amplitude to obtain the rotation state of the tank body; Performing adaptive filtering and compensation processing on the original weight data set according to the rotation state to obtain final measured weight data; The final measured weight data is subjected to abnormal value detection, and intelligent weighing management is performed based on the detection results.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program for the construction site intelligent weighing management method based on dynamic compensation. When the program for the construction site intelligent weighing management method based on dynamic compensation is executed by the processor, the steps of the construction site intelligent weighing management method based on dynamic compensation as described in any one of claims 1 to 8 are implemented.

Images