Weighing monitoring prevention and control instrument prevention and control system and method

Abstract

The invention discloses a weighing monitoring prevention and control instrument prevention and control system and method, and relates to the technical field of prevention and control instrument prevention and control equipment. By integrating the data acquisition module, the LORA wireless module, the single-chip microcomputer control module, the video image monitoring module and the infrared correlation position module, real-time weighing monitoring, wireless data transmission, video and image monitoring and anti-cheating functions are realized; according to the invention, the infrared correlation position module is used to ensure that data acquisition is carried out after the target to be weighed completely enters the wagon balance monitoring area, so that data errors caused by the fact that the target to be weighed is not completely loaded on the scale are avoided, and the data accuracy is improved; according to the method, the abnormal weight fluctuation is monitored, comprehensive judgment is carried out from multiple dimensions of residence time, speed stability and motion trail, potential abnormal risks such as overload, overspeed, long-time residence and abnormal driving paths can be comprehensively recognized, and the monitoring comprehensiveness and effectiveness are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of prevention and control instrument prevention and control equipment, and specifically relates to a weighing monitoring prevention and control instrument prevention and control system and a prevention and control method. Background Art

[0002] In the fields of logistics, transportation, industry, etc., weighing is a common operation, but cheating occurs from time to time. For example, wireless remote control devices are used to interfere with weighing equipment, making the weighing results inaccurate, thereby seeking improper benefits. This cheating behavior not only damages the economic interests of enterprises, but also disrupts the market order.

[0003] The application of weighing monitoring and control instruments and their prevention and control systems can monitor and intercept wireless remote-controlled fraud devices in real time, ensure the authenticity and validity of weighing data, and effectively prevent the occurrence of cheating. Summary of the invention

[0004] In order to overcome the shortcomings and deficiencies of the above-mentioned prior art, the first purpose of the present invention is to provide a weighing monitoring and control instrument prevention and control system; the second purpose of the present invention is to provide a weighing monitoring and control instrument prevention and control method.

[0005] The first object of the present invention adopts the following technical solution:

[0006] A weighing monitoring and prevention and control instrument prevention and control system, including a data acquisition module, a LORA wireless module, a single-chip control module, a video image monitoring module and an infrared shooting position module;

[0007] Data acquisition module: real-time weighing index data collected by sensors;

[0008] LORA wireless module: Through LORA wireless communication technology, data transmission between the data acquisition module and the single-chip control module is realized; and the changed remote control frequency signal is sent according to the instructions of the single-chip control module to prevent cheating;

[0009] Single chip control module: used to control the operation of the entire system, receive the first abnormal signal, the second abnormal signal, the third abnormal signal, and the fourth abnormal signal, generate the first alarm signal, the second alarm signal, the third alarm signal, and the fourth alarm signal respectively, and control the initial alarm threshold and the second alarm threshold setting.

[0010] Preferably, it also includes a video image monitoring module and an infrared beam alignment module;

[0011] Video image monitoring module: used to capture high-definition images and video streams, record the appearance and behavior information of the target to be weighed, and form an image data set; monitor the situation in the weighbridge area in real time, including the first signal abnormality, the second signal abnormality, the third signal abnormality, and the fourth signal abnormality, and send warning information to the user;

[0012] Infrared positioning module: used to locate the target to be weighed that enters the monitoring area of ​​the weighbridge, including the movement trajectory and position of the target to be weighed.

[0013] The second object of the present invention adopts the following technical solution:

[0014] A weighing monitoring and prevention and control method, the method flow is as follows:

[0015] Step 1: System initialization and configuration, including calibration of data acquisition module, configuration of LORA wireless module parameters, and setting of single-chip control logic; according to actual monitoring needs, dynamic monitoring indicator set is configured, which includes cargo type data, weight fluctuation data of the target to be weighed, residence time data, speed data, and motion trajectory data;

[0016] Step 2: Data collection and preprocessing: continuous and real-time index data collection of the target to be weighed that enters the large interval to form an index data set; capture high-definition images and video streams, record the appearance and behavior information of the target to be weighed, and form an image data set; the infrared shooting position module ensures that the target to be weighed completely enters the monitoring area of ​​the weighbridge to improve the accuracy of data collection;

[0017] Step 3: Monitor the first signal abnormality; extract the weight fluctuation data of the target to be weighed, calculate the weight fluctuation coefficient, which is used to quantify the fluctuation of weight over time, and mark the weight fluctuation rate as the first fluctuation coefficient. When the first fluctuation coefficient deviates from the set threshold, the first signal abnormality is generated;

[0018] Step 4: monitor the abnormality of the second signal; quantify the abnormality of the target dwell time, speed stability, and motion trajectory to be weighed, and mark them as the second fluctuation coefficient, the third fluctuation coefficient, and the fourth fluctuation coefficient, respectively.

[0019] The volatility coefficient aggregation characteristic value is calculated based on the second volatility coefficient, the third volatility coefficient, and the fourth volatility coefficient; when any volatility coefficient exceeds its corresponding threshold or the volatility coefficient aggregation characteristic value ρ exceeds the set threshold, it is determined that there is an abnormal risk and marked as the second signal abnormality.

[0020] As a preference, it also includes:

[0021] Step 5: Monitor the abnormality of the third signal; use image recognition technology to process and analyze the image data set, including appearance change detection, loading situation analysis, and dynamic behavior analysis; appearance change detection is used to detect whether abnormal changes have occurred, including cargo damage and packaging damage; loading situation analysis is used to determine whether there is overloading and underloading; dynamic behavior analysis is used to identify abnormal behaviors, including sudden braking, sudden acceleration, and cargo falling; once a violation of the rules is detected, it is immediately marked as abnormal, and abnormal behavior is identified, and abnormal risk is determined, and marked as abnormal third signal;

[0022] Step 6: Threshold setting, including initial alarm threshold setting and second alarm threshold setting;

[0023] Step 7: Real-time monitoring;

[0024] Real-time monitoring of the first signal abnormality, the second signal abnormality, the third signal abnormality, and the fourth signal abnormality, respectively generates the first alarm signal, the second alarm signal, the third alarm signal, and the fourth alarm signal, and sends early warning information to the user through sound and light alarms, SMS notifications, and email reminders.

[0025] As a preference, the weight fluctuation coefficient is calculated as follows:

[0026] Calculate the standard error SEM and mean weight of cargo weight within a set time period

[0027]

[0028] Where n is the number of objects to be weighed in the sample, ω i is the target weight to be weighed, is the sum of the weights of all targets to be weighed;

[0029]

[0030]

[0031] Where s is the sample standard deviation of the original data; is the square of the difference between each target weight to be weighed and the average weight, is the sum of the squares of these differences; n-1 is the degree of freedom;

[0032] The standard error SEM of cargo weight is compared with the mean weight Substitute into the weight fluctuation coefficient calculation formula to obtain the first fluctuation coefficient B1,

[0033]

[0034] The weight fluctuation coefficient B1 is used to quantify the fluctuation of weight over time to reflect the stability or variability of weight;

[0035] When the first fluctuation coefficient exceeds its corresponding maximum threshold or is lower than its corresponding minimum threshold, it is determined that there is an abnormal risk and marked as a first signal abnormality.

[0036] As a preference, step four is specifically as follows:

[0037] Extract real-time position, speed and timestamp data of the object to be weighed;

[0038] A normal residence time range is set for each monitoring area of ​​the weighbridge, including a minimum residence time t1 and a maximum residence time t2; the time points when the weighbridge enters and leaves the monitoring area of ​​the weighbridge are determined through the real-time position data of the weighbridge object, thereby calculating the actual residence time t; the actual residence time t is compared with the preset normal range t1-t2, and when the actual residence time t is greater than the maximum residence time t2 or less than the minimum residence time t1, the residence time abnormality is calculated according to the degree of excess, and the residence time abnormality is marked as the second fluctuation coefficient B2;

[0039]

[0040] Among them, t is the actual residence time; t1 is the minimum residence time; t2 is the maximum residence time;

[0041] According to the formula, when the actual stay time t is greater than the maximum stay time t2 or less than the minimum stay time t1, the stay time abnormality will be calculated according to the degree of excess and marked as the second fluctuation coefficient;

[0042] Collect the speed data of the target to be weighed within the set time period, calculate the standard deviation, coefficient of variation, and speed change rate statistical indicators of the speed data, substitute the statistical indicators into the calculation formula, and obtain the speed stability coefficient B3 of the target to be weighed. The smaller the standard deviation or coefficient of variation, the more stable the speed, and the higher the value of B3. The speed stability coefficient of the target to be weighed is marked as the third fluctuation coefficient B3;

[0043]

[0044] Among them, k is the speed stability coefficient correction factor; ∈ is a very small positive integer, which is the denominator adjustment factor, used to prevent the denominator from being zero. When all speed values ​​are the same, the coefficient of variation is 0; CV is the coefficient of variation, which is the ratio of the standard deviation to the mean value, and is used to compare the degree of dispersion of different data sets or the same data set under different conditions;

[0045] The CV calculation formula is: Among them, σ is the standard deviation of the speed value; μ is the average value of the speed value;

[0046] Preset normal motion trajectory T normal ={(x1,y1),(x2,y2),...,(x n ,y n )}; represents a sequence consisting of multiple points, (x n ,y n ) represents longitude and latitude coordinates;

[0047] Real-time tracking trajectory T actual ={(x1′,y1′), (x2′,y2′),…,(x n ′,y n ′)};

[0048] represents a sequence of multiple points, (x n ′,x n ′) represents the longitude and latitude coordinates;

[0049] For T normal and T actual For each pair of corresponding points (x n ,y n ) and (x n ′,y n ′), calculate its distance deviation

[0050] Calculate the abnormality coefficient of the target's motion trajectory to be weighed

[0051] Where n is the total number of points; i≠j; ω ij is the weight set, ω ij It is a point to P i and P j Based on the weighted average of the total distance deviation D, the total distance deviation weighted average D is calculated using the formula, and the abnormality coefficient of the motion trajectory of the target to be weighed is marked as the fourth fluctuation coefficient B4;

[0052] The residence time abnormality coefficient B2 is used to measure whether the residence time of the target to be weighed in the monitoring area of ​​the weighbridge is abnormal. It is calculated by comparing the actual residence time with the preset normal residence time range. If the actual residence time exceeds the normal range, it indicates that there is an abnormality;

[0053] The speed stability coefficient B3 of the target to be weighed is used to measure the stability of the speed of the target to be weighed. It is calculated based on the standard deviation, coefficient of variation or speed change rate of the target to be weighed to reflect the volatility and stability of the speed of the target to be weighed.

[0054] The abnormality coefficient B4 of the motion trajectory of the target to be weighed is used to detect the abnormality of the motion trajectory of the target to be weighed. It is calculated by comparing the actual motion trajectory of the target to be weighed with the preset normal trajectory. If the difference between the actual trajectory and the normal trajectory exceeds the set threshold, it indicates that there is an abnormality;

[0055] Calculate the second fluctuation coefficient, the third fluctuation coefficient, and finally the fourth fluctuation coefficient covering all key monitoring indicators;

[0056] The second, third and fourth fluctuation coefficients are combined to generate the fluctuation coefficient aggregation characteristic value ρ using the formula. The value of ρ reflects the overall fluctuation of large-interval weighing monitoring. The formula is as follows:

[0057] ρ=(B2*ω2+B3ω3+B4ω4)+σ;

[0058] Among them, B2, B3, B4 are the second fluctuation coefficient, the third fluctuation coefficient, and the fourth fluctuation coefficient respectively, ω2, ω3, ω4 are their corresponding weight coefficients respectively; σ is the error correction factor;

[0059] The first to fourth fluctuation coefficient thresholds and the aggregation characteristic value ρ threshold are set. When any fluctuation coefficient exceeds its corresponding threshold or the fluctuation coefficient aggregation characteristic value ρ exceeds the set threshold, it is determined that there is an abnormal risk and marked as the second signal abnormality.

[0060] As a preference, step six is ​​specifically as follows:

[0061] S601, initial alarm threshold setting, based on historical weighing data and industry standards, preliminarily calculate and set the initial alarm thresholds of the first fluctuation coefficient, the second fluctuation coefficient, the third fluctuation coefficient, and the fourth fluctuation coefficient;

[0062] S602, determining alarm threshold influencing factors, wherein the alarm threshold influencing factor set definition: clarifying factors affecting the alarm threshold, including cargo type, weather conditions, time period, holidays, and special events;

[0063] S603, determining the influencing factors of the period to be set, and determining at least one key influencing factor in the period from the alarm threshold influencing factor set according to the current period;

[0064] S604, factor similarity calculation, using cosine similarity to calculate the similarity between the alarm threshold influencing factor of the historical period and the alarm threshold influencing factor of the period to be set;

[0065] S605, determining the sampling period, if the calculated factor similarity is higher than a preset threshold, determining these historical periods as the sampling period;

[0066] S606, second alarm threshold setting: during the actual operation, based on the real-time identified influencing factors and the preset algorithm, the second alarm thresholds of the first fluctuation coefficient, the second fluctuation coefficient, the third fluctuation coefficient, and the fourth fluctuation coefficient applicable to the current stage are calculated and output.

[0067] As a preference, the factor similarity calculation is specifically as follows:

[0068] Historical cycle vector:

[0069] The period vector to be set:

[0070] Where n is the number of influencing factors; hn and sn are the values ​​of the i-th influencing factor in the historical period and the period to be set, respectively. and the periodic vector to be set Substitute it into the factor similarity calculation formula to obtain the factor similarity Cosine Similarity, the calculation formula is as follows:

[0071]

[0072] in, is the dot product of two vectors, i.e. and They are vectors and The Euclidean length is calculated as and

[0073] Among them, the factor similarity ranges from -1 to 1; the closer the value is to 1, the more similar the two factors are; the closer the value is to -1, the less similar the two factors are; the closer the value is to 0, the two vectors are almost orthogonal, that is, there is no linear relationship between the factors.

[0074] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0075] 1. The present invention realizes all-round, continuous and real-time monitoring of the weight, residence time, speed, movement trajectory and appearance behavior of the weighing target by integrating multiple sensors such as data acquisition module, video image monitoring module, infrared shooting position module, etc., which greatly improves the monitoring accuracy and efficiency.

[0076] 2. The present invention ensures that data collection is not carried out until the target to be weighed has completely entered the monitoring area of ​​the scale through the use of an infrared positioning module, which effectively avoids data errors caused by the target to be weighed not being completely on the scale, and improves data accuracy. The present invention not only monitors abnormal weight fluctuations, but also makes comprehensive judgments from multiple dimensions such as dwell time, speed stability, and motion trajectory, and can more comprehensively identify potential abnormal risks, such as overloading, speeding, long-term dwelling, abnormal driving paths, etc., thereby improving the comprehensiveness and effectiveness of monitoring.

[0077] 3. The present invention supports the setting of the initial alarm threshold and the second alarm threshold. Users can flexibly adjust the threshold according to actual monitoring needs and scene characteristics to adapt to different monitoring needs, thereby improving the flexibility and applicability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0079] Figure 1 A module diagram of a weighing monitoring and prevention and control instrument prevention and control system of the present invention is shown;

[0080] Figure 2 A flow chart of a control method of a weighing monitoring and control instrument of the present invention is shown. DETAILED DESCRIPTION

[0081] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0082] Example 1

[0083] See also Figure 1 As shown, a weighing monitoring and prevention and control instrument prevention and control system of this embodiment includes a data acquisition module, a LORA wireless module, a single-chip control module, a video image monitoring module and an infrared shooting position module;

[0084] Data acquisition module: Based on sensors, it collects real-time weighing index data of large areas, including weight fluctuation data of the target to be weighed, dwell time data, weighing type data of the scale, cargo type data, speed data of the target to be weighed, and motion trajectory data of the target to be weighed;

[0085] LORA wireless module: Through LORA wireless communication technology, data transmission between the data acquisition module and the single-chip control module is realized; and the changed remote control frequency signal is sent according to the instructions of the single-chip control module to prevent cheating;

[0086] Single chip control module: used to control the operation of the whole system, receive the first signal abnormality, the second signal abnormality, the third signal abnormality, and the fourth signal abnormality, respectively generate the first alarm signal, the second alarm signal, the third alarm signal, and the fourth alarm signal, and control the initial alarm threshold and the second alarm threshold setting;

[0087] Video image monitoring module: used to capture high-definition images and video streams, record the appearance and behavior information of the target to be weighed, and form an image data set; monitor the situation in the weighbridge area in real time, including the first signal abnormality, the second signal abnormality, the third signal abnormality, and the fourth signal abnormality, and send warning information to the user;

[0088] Infrared positioning module: used to locate the target to be weighed that enters the monitoring area of ​​the weighbridge, including the movement trajectory and position of the target to be weighed.

[0089] The beneficial effects of this embodiment are: through the data acquisition module, LORA wireless module, single-chip control module, video and image monitoring module and infrared shooting module, by configuring a dynamic monitoring indicator set and in-depth data analysis, comprehensive, real-time and efficient abnormal detection and prevention of cargo or weighing scales in a large area can be achieved.

[0090] Example 2

[0091] See also Figure 2 As shown, a weighing detection prevention and control method of this embodiment has the following process:

[0092] Step 1: System initialization and configuration.

[0093] Initialize the large-interval weighing monitoring and control instrument, including calibrating the data acquisition module, configuring the LORA wireless module parameters, and setting the microcontroller control logic;

[0094] According to actual monitoring needs, a dynamic monitoring indicator set is configured, which includes weight fluctuation data of the target to be weighed, dwell time data, weighing type data of the scale, cargo type data, speed data of the target to be weighed, and movement trajectory data of the target to be weighed.

[0095] Step 2: Data collection and preprocessing.

[0096] Continuous and real-time indicator data collection is carried out on the targets to be weighed that enter the large interval to form an indicator data set. The indicators include weight fluctuation data of the targets to be weighed, residence time data, weighing type data of the scale, cargo type data, speed data of the targets to be weighed, and motion trajectory data of the targets to be weighed; high-definition images and video streams are captured, and the appearance and behavior information of the targets to be weighed are recorded to form an image data set; the infrared shooting position module ensures that the targets to be weighed completely enter the monitoring area of ​​the scale to improve the accuracy of data collection.

[0097] Step 3: monitor the first signal for abnormality.

[0098] Extract the weight fluctuation data of the target to be weighed, calculate the weight fluctuation coefficient, and mark the weight fluctuation coefficient as the first fluctuation coefficient B1;

[0099] Calculate the standard error SEM and average weight of cargo weight within a period of time (e.g. every minute, every half hour)

[0100]

[0101] Where n is the number of objects to be weighed in the sample, ω i is the target weight to be weighed, It is the sum of all the weights of the objects to be weighed.

[0102]

[0103] Where s is the sample standard deviation of the original data; is the square of the difference between each target weight to be weighed and the average weight, is the sum of the squares of these differences; n-1 is the degrees of freedom (for the sample data).

[0104] The standard error SEM of cargo weight is compared with the mean weight Substituting into the weight volatility calculation formula, we get the first volatility coefficient B1,

[0105]

[0106] The weight fluctuation coefficient B1 is used to quantify the fluctuation of weight over time to reflect the stability or variability of weight.

[0107] When the first fluctuation coefficient exceeds its corresponding maximum threshold or is lower than its corresponding minimum threshold, it is determined that there is an abnormal risk and marked as a first signal abnormality.

[0108] Step 4: monitor the second signal for abnormality.

[0109] Extract real-time position, speed and timestamp data of the object to be weighed;

[0110] A normal residence time range is set for each monitoring area of ​​the weighbridge, including a minimum residence time t1 and a maximum residence time t2; the time points when the weighbridge enters and leaves the monitoring area of ​​the weighbridge are determined through the real-time position data of the weighbridge object, thereby calculating the actual residence time t; the actual residence time t is compared with the preset normal range t1-t2, and when the actual residence time t is greater than the maximum residence time t2 or less than the minimum residence time t1, the residence time abnormality is calculated according to the degree of excess, and the residence time abnormality is marked as the second fluctuation coefficient B2;

[0111]

[0112] Among them, t is the actual residence time; t1 is the minimum residence time; t2 is the maximum residence time;

[0113] According to the formula, when the actual stay time t is greater than the maximum stay time t2 or less than the minimum stay time t1, the stay time abnormality will be calculated according to the degree of excess and marked as the second fluctuation coefficient.

[0114] Collect the speed data of the target to be weighed within the set time period, and calculate the standard deviation, coefficient of variation, and speed change rate statistical indicators of the speed data. Based on the statistical indicators, substitute them into the calculation formula to obtain the weighing speed stability coefficient B3 of the scale. The smaller the standard deviation or coefficient of variation, the more stable the speed, and the higher the value of B3. Mark the weighing speed stability coefficient of the scale as the third fluctuation coefficient B3;

[0115]

[0116] Among them, k is the speed stability coefficient correction factor; ∈ is a very small positive integer, which is the denominator adjustment factor, used to prevent the denominator from being zero. When all speed values ​​are the same, the coefficient of variation is 0; CV is the coefficient of variation, which is the ratio of the standard deviation to the mean value, and is used to compare the degree of dispersion of different data sets or the same data set under different conditions;

[0117] The CV calculation formula is: Among them, σ is the standard deviation of the speed value; μ is the average value of the speed value.

[0118] Preset normal motion trajectory T normal ={(x1,y1),(x2,y2),...,(x n ,y n )}; represents a sequence consisting of multiple points, (x n ,y n ) represents longitude and latitude coordinates.

[0119] Real-time tracking trajectory T actual ={(x1′,y1′), (x2′,y2′),…,(xn ′,y n ′)};

[0120] represents a sequence of multiple points, (x n ′,x n ′) represents the longitude and latitude coordinates.

[0121] For T normal and T actual For each pair of corresponding points (x n ,y n ) and (x n ′,y n ′), calculate its distance deviation

[0122] Calculate the abnormality coefficient of weighing motion trajectory of floor scale

[0123] Where n is the total number of points; i≠j; ω ij is the weight set, ω ij It is a point to P i and P j Based on the weighted average of the total distance deviation D, the total distance deviation weighted average D is calculated using the formula, and the abnormality coefficient of the weighing motion trajectory of the floor scale is marked as the fourth fluctuation coefficient B4.

[0124] The residence time abnormality coefficient B2 is used to measure whether the residence time of the target to be weighed in the monitoring area of ​​the scale is abnormal. It is calculated by comparing the actual residence time with the preset normal residence time range. If the actual residence time exceeds the normal range, it indicates an abnormality.

[0125] The weighing speed stability coefficient B3 of the weighing scale is used to measure the stability of the weighing speed of the weighing scale. It is calculated based on the standard deviation, coefficient of variation or speed change rate of the weighing speed of the weighing scale to reflect the volatility and stability of the weighing speed of the weighing scale.

[0126] The abnormality coefficient B4 of the weighing motion trajectory of the floor scale is used to detect the abnormality of the weighing motion trajectory of the floor scale. It is calculated by comparing the actual weighing motion trajectory of the floor scale with the preset normal trajectory. If the actual trajectory and the normal trajectory differ by more than the set threshold, it indicates that an abnormality exists.

[0127] Calculate the second coefficient of fluctuation, the third coefficient of fluctuation, and so on until the fourth coefficient of fluctuation covering all key monitoring indicators.

[0128] The second, third and fourth fluctuation coefficients are combined and the formula is used to generate the fluctuation coefficient aggregation characteristic value ρ. The value of ρ reflects the overall fluctuation of large-interval weighing monitoring. The formula is as follows:

[0129] ρ=(B2*ω2+B3ω3+B4ω4)+σ;

[0130] Among them, B2, B3, B4 are the second fluctuation coefficient, the third fluctuation coefficient, and the fourth fluctuation coefficient respectively, ω2, ω3, ω4 are their corresponding weight coefficients respectively; σ is the error correction factor.

[0131] Set the first to fourth fluctuation coefficient thresholds and the aggregation characteristic value ρ threshold, and optimize them according to historical data and business experience. When any fluctuation coefficient exceeds its corresponding threshold or the fluctuation coefficient aggregation characteristic value ρ exceeds the set threshold, it is determined that there is an abnormal risk and marked as the second signal abnormality.

[0132] Step 5: Monitor the third signal for abnormality.

[0133] Using image recognition technology, the image data set is processed and analyzed to identify key features such as weighing type, license plate number, cargo type, etc., and generate detailed feature recognition results.

[0134] Appearance change detection: Compare and analyze the current image with the image before the goods are loaded, use template matching to identify appearance changes, detect whether the goods are damaged and whether the packaging is damaged. Once the appearance change exceeds the preset threshold, it is judged as an abnormality.

[0135] Loading situation analysis: Use the size and proportion information in the image, combined with the preset cargo volume and weight standards, to estimate the current loading situation, compare the estimated results with the standards, and determine whether there is overloading or underloading. Once overloading or underloading is detected, it is judged as abnormal.

[0136] Dynamic behavior analysis: By analyzing the motion trajectory and speed changes in continuous image sequences, the dynamic behavior of weighing scales and cargo is identified. Abnormal behaviors such as sudden braking, sudden acceleration, and cargo dropping are identified using optical flow methods and motion estimation algorithms. Once abnormal behavior is identified, it is judged as abnormal.

[0137] The detected abnormal behavior is marked as a third signal anomaly, and relevant information is recorded, including time, location, anomaly type, image evidence, etc.

[0138] Step 6: Threshold setting.

[0139] Initial alarm threshold setting: based on historical weighing data and industry standards, the initial alarm thresholds of the first fluctuation coefficient, the second fluctuation coefficient, the third fluctuation coefficient, and the fourth fluctuation coefficient are preliminarily calculated and set;

[0140] Determine the alarm threshold influencing factors, where the alarm threshold influencing factor set definition: clarify the factors that affect the alarm threshold, including cargo type, weather conditions, time period, holidays, and special events;

[0141] Determine the influencing factor of the period to be set, and determine at least one key influencing factor in the period from the alarm threshold influencing factor set according to the current period;

[0142] Factor similarity calculation, calculating the similarity between the alarm threshold influencing factors of the historical period and the alarm threshold influencing factors of the period to be set;

[0143] Historical cycle vector:

[0144] The period vector to be set:

[0145] Where n is the number of influencing factors; hn and sn are the values ​​of the i-th influencing factor in the historical period and the period to be set, respectively. and the periodic vector to be set Substitute it into the factor similarity calculation formula to obtain the factor similarity Cosine Similarity, the calculation formula is as follows:

[0146]

[0147] in, is the dot product of two vectors, i.e. and They are vectors and The Euclidean length is calculated as and

[0148] Among them, the factor similarity ranges from -1 to 1; the closer the value is to 1, the more similar the two factors are; the closer the value is to -1, the less similar the two factors are; the closer the value is to 0, the two vectors are almost orthogonal, that is, there is no linear relationship between the factors.

[0149] If the calculated factor similarity is higher than the preset threshold, these historical periods are determined as sampling periods.

[0150] Second alarm threshold setting: During actual operation, the system continuously monitors the current actual scenarios and identifies the alarm threshold influencing factors corresponding to these scenarios in real time.

[0151] Second alarm threshold calculation: Based on the real-time identified influencing factors and the preset algorithm, the second alarm threshold applicable to the current stage is calculated and output.

[0152] Step 7: Real-time monitoring.

[0153] Real-time monitoring of the first signal abnormality, the second signal abnormality, the third signal abnormality, and the fourth signal abnormality, respectively generates the first alarm signal, the second alarm signal, the third alarm signal, and the fourth alarm signal, and sends early warning information to the user through sound and light alarms, SMS notifications, and email reminders.

[0154] The beneficial effects of this embodiment are: through multi-sensor fusion, multi-dimensional anomaly monitoring, intelligent image recognition and timely early warning notification, the accuracy, efficiency and safety of behavior monitoring of the target to be weighed in a large area are improved, which is of great significance for ensuring road traffic safety and maintaining the order of cargo transportation.

[0155] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0156] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A weighing monitoring and control instrument prevention and control system, characterized in that: Including data acquisition module, LORA wireless module, single chip control module, video image monitoring module and infrared positioning module; Data acquisition module: real-time weighing index data collected by sensors; LORA wireless module: Through LORA wireless communication technology, data transmission between the data acquisition module and the single-chip control module is realized; and the changed remote control frequency signal is sent according to the instructions of the single-chip control module to prevent cheating; Single chip control module: used to control the operation of the entire system, receive the first abnormal signal, the second abnormal signal, the third abnormal signal, and the fourth abnormal signal, generate the first alarm signal, the second alarm signal, the third alarm signal, and the fourth alarm signal respectively, and control the initial alarm threshold and the second alarm threshold setting.

2. A weighing monitoring and prevention and control system according to claim 1, characterized in that: It also includes a video image monitoring module and an infrared beam alignment module; Video image monitoring module: used to capture high-definition images and video streams, record the appearance and behavior information of the target to be weighed, and form an image data set; monitor the situation in the weighbridge area in real time, including the first signal abnormality, the second signal abnormality, the third signal abnormality, and the fourth signal abnormality, and send warning information to the user; Infrared positioning module: used to locate the target to be weighed that enters the monitoring area of ​​the floor scale, including the movement trajectory and position of the target to be weighed.

3. A weighing monitoring and control instrument prevention and control method, characterized in that: Used to implement a weighing monitoring and prevention and control instrument prevention and control system as claimed in claim 1 or 2, the method flow is as follows: Step 1: System initialization and configuration, including calibration of data acquisition module, configuration of LORA wireless module parameters, and setting of single-chip control logic; according to actual monitoring needs, dynamic monitoring indicator set is configured, which includes cargo type data, weight fluctuation data of the target to be weighed, residence time data, speed data, and motion trajectory data; Step 2: Data collection and preprocessing: continuous and real-time index data collection of the target to be weighed to form an index data set; capture high-definition images and video streams, record the appearance and behavior information of the target to be weighed, and form an image data set; the infrared shooting position module ensures that the target to be weighed completely enters the monitoring area of ​​the weighbridge to improve the accuracy of data collection; Step 3: Monitor the first signal abnormality; extract the weight fluctuation data of the target to be weighed, calculate the weight fluctuation coefficient, which is used to quantify the fluctuation of weight over time, and mark the weight fluctuation rate as the first fluctuation coefficient. When the first fluctuation coefficient deviates from the set threshold, the first signal abnormality is generated; Step 4: monitor the second signal for abnormality; Quantify the abnormality of the target's dwell time, speed stability, and motion trajectory, and mark them as the second fluctuation coefficient, the third fluctuation coefficient, and the fourth fluctuation coefficient respectively. Calculate the volatility coefficient aggregation characteristic value according to the second volatility coefficient, the third volatility coefficient, and the fourth volatility coefficient; When any volatility coefficient exceeds its corresponding threshold or the volatility coefficient aggregation characteristic value ρ exceeds the set threshold, it is determined that there is an abnormal risk and marked as the second signal abnormality.

4. A weighing monitoring and prevention and control method according to claim 3, characterized in that: Also includes: Step 5: monitor the third signal for abnormality; Image recognition technology is used to process and analyze image data sets, including appearance change detection, loading situation analysis, and dynamic behavior analysis. Appearance change detection is used to detect whether abnormal changes have occurred, including cargo damage and packaging damage; loading situation analysis is used to determine whether there is overloading or underloading; dynamic behavior analysis is used to identify abnormal behaviors, including sudden braking, sudden acceleration, and cargo falling; once a violation of the rules is detected, it is immediately marked as abnormal, and abnormal behavior is identified and determined to have an abnormal risk, and marked as a third signal abnormality; Step 6: Threshold setting, including initial alarm threshold setting and second alarm threshold setting; Step 7: Real-time monitoring; Real-time monitoring of the first signal abnormality, the second signal abnormality, the third signal abnormality, and the fourth signal abnormality, respectively generates the first alarm signal, the second alarm signal, the third alarm signal, and the fourth alarm signal, and sends early warning information to the user through sound and light alarms, SMS notifications, and email reminders.

5. A weighing monitoring and prevention and control method according to claim 3, characterized in that: The calculation weight fluctuation coefficient is as follows: Calculate the standard error SEM and mean weight of cargo weight within a set time period Where n is the number of objects to be weighed in the sample, ω i is the target weight to be weighed, is the sum of the weights of all targets to be weighed; Where s is the sample standard deviation of the original data; is the square of the difference between each target weight to be weighed and the average weight, is the sum of the squares of these differences; n-1 is the degree of freedom; The standard error SEM of cargo weight is compared with the mean weight Substituting into the weight fluctuation coefficient calculation formula, we get the first fluctuation coefficient B1, The weight fluctuation coefficient B1 is used to quantify the fluctuation of weight over time to reflect the stability or variability of weight; When the first fluctuation coefficient exceeds its corresponding maximum threshold or is lower than its corresponding minimum threshold, it is determined that there is an abnormal risk and marked as a first signal abnormality.

6. A weighing monitoring and prevention and control method according to claim 3, characterized in that: The step 4 is as follows: Extract real-time position, speed and timestamp data of the object to be weighed; Set a normal stay time range for each weighbridge monitoring area, including a minimum stay time t1 and a maximum stay time t2; The time points when the object to be weighed enters and leaves the monitoring area of ​​the weighbridge are determined through the real-time position data of the object to be weighed, thereby calculating the actual residence time t; The actual stay time t is compared with the preset normal range t1-t2. When the actual stay time t is greater than the maximum stay time t2 or less than the minimum stay time t1, the stay time abnormality is calculated according to the degree of excess, and the stay time abnormality is marked as the second fluctuation coefficient B2; Among them, t is the actual residence time; t1 is the minimum residence time; t2 is the maximum residence time; According to the formula, when the actual stay time t is greater than the maximum stay time t2 or less than the minimum stay time t1, the stay time abnormality will be calculated according to the degree of excess and marked as the second fluctuation coefficient; Collect the speed data of the target to be weighed within the set time period, calculate the standard deviation, coefficient of variation, and speed change rate statistical indicators of the speed data, substitute the statistical indicators into the calculation formula, and obtain the speed stability coefficient B3 of the target to be weighed. The smaller the standard deviation or coefficient of variation, the more stable the speed, and the higher the value of B3. The speed stability coefficient of the target to be weighed is marked as the third fluctuation coefficient B3; Among them, k is the speed stability coefficient correction factor; ∈ is a very small positive integer, which is the denominator adjustment factor, used to prevent the denominator from being zero. When all speed values ​​are the same, the coefficient of variation is 0; CV is the coefficient of variation, which is the ratio of the standard deviation to the mean value, and is used to compare the degree of dispersion of different data sets or the same data set under different conditions; The CV calculation formula is: Among them, σ is the standard deviation of the speed value; μ is the average value of the speed value; Preset normal motion trajectory T normal ={(x1,y1),(x2,y2),...,(x n ,y n )}; represents a sequence consisting of multiple points, (x n ,y n ) represents longitude and latitude coordinates; Real-time tracking trajectory T actual ={(x1',y1'),(x2',y2'),...,(x n ',y n ')}; represents a sequence consisting of multiple points, (x n ', x n ') represents the longitude and latitude coordinates; For T normal and T actual For each pair of corresponding points (x n ,y n ) and (x n ',y n '), calculate its distance deviation Calculate the abnormality coefficient of the target's motion trajectory to be weighed Where n is the total number of points; i≠j; ω ij is the weight set, ω ij It is a point to P i and P j Based on the weighted average of the total distance deviation D, the total distance deviation weighted average D is calculated using the formula, and the abnormality coefficient of the motion trajectory of the target to be weighed is marked as the fourth fluctuation coefficient B4; The residence time abnormality coefficient B2 is used to measure whether the residence time of the target to be weighed in the monitoring area of ​​the weighbridge is abnormal. It is calculated by comparing the actual residence time with the preset normal residence time range. If the actual residence time exceeds the normal range, it indicates that there is an abnormality; The speed stability coefficient B3 of the target to be weighed is used to measure the stability of the speed of the target to be weighed. It is calculated based on the standard deviation, coefficient of variation or speed change rate of the target to be weighed to reflect the volatility and stability of the speed of the target to be weighed. The abnormality coefficient B4 of the motion trajectory of the target to be weighed is used to detect the abnormality of the motion trajectory of the target to be weighed. It is calculated by comparing the actual motion trajectory of the target to be weighed with the preset normal trajectory. If the difference between the actual trajectory and the normal trajectory exceeds the set threshold, it indicates that there is an abnormality; Calculate the second fluctuation coefficient, the third fluctuation coefficient, and finally the fourth fluctuation coefficient covering all key monitoring indicators; The second, third and fourth fluctuation coefficients are combined and the formula is used to generate the fluctuation coefficient aggregation characteristic value ρ. The value of ρ reflects the overall fluctuation status of weighing monitoring. The formula is as follows: ρ=(B2*ω2+B3ω3+B4ω4)+σ; Among them, B2, B3, B4 are the second fluctuation coefficient, the third fluctuation coefficient, and the fourth fluctuation coefficient respectively, ω2, ω3, ω4 are their corresponding weight coefficients respectively; σ is the error correction factor; The first to fourth fluctuation coefficient thresholds and the aggregation characteristic value ρ threshold are set. When any fluctuation coefficient exceeds its corresponding threshold or the fluctuation coefficient aggregation characteristic value ρ exceeds the set threshold, it is determined that there is an abnormal risk and marked as the second signal abnormality.

7. A weighing monitoring and prevention and control method according to claim 3, characterized in that: The step six is ​​as follows: S601, initial alarm threshold setting, based on historical weighing data and industry standards, preliminarily calculate and set the initial alarm thresholds of the first fluctuation coefficient, the second fluctuation coefficient, the third fluctuation coefficient, and the fourth fluctuation coefficient; S602, determining alarm threshold influencing factors, wherein the alarm threshold influencing factor set definition: clarifying factors affecting the alarm threshold, including cargo type, weather conditions, time period, holidays, and special events; S603, determining the influencing factors of the period to be set, and determining at least one key influencing factor in the period from the alarm threshold influencing factor set according to the current period; S604, factor similarity calculation, using cosine similarity to calculate the similarity between the alarm threshold influencing factor of the historical period and the alarm threshold influencing factor of the period to be set; S605, determining the sampling period, if the calculated factor similarity is higher than a preset threshold, determining these historical periods as the sampling period; S606, second alarm threshold setting: during the actual operation, based on the real-time identified influencing factors and the preset algorithm, the second alarm thresholds of the first fluctuation coefficient, the second fluctuation coefficient, the third fluctuation coefficient, and the fourth fluctuation coefficient applicable to the current stage are calculated and output.

8. A weighing monitoring and prevention and control method according to claim 7, characterized in that: The factor similarity calculation is specifically as follows: Historical cycle vector: The period vector to be set: Where n is the number of influencing factors; hn and sn are the values ​​of the i-th influencing factor in the historical period and the period to be set, respectively. and the periodic vector to be set Substitute it into the factor similarity calculation formula to obtain the factor similarity Cosine Similarity, the calculation formula is as follows: in, is the dot product of two vectors, i.e. and They are vectors and The Euclidean length is calculated as and Among them, the factor similarity ranges from -1 to 1; the closer the value is to 1, the more similar the two factors are; the closer the value is to -1, the less similar the two factors are; the closer the value is to 0, the two vectors are almost orthogonal, that is, there is no linear relationship between the factors.

Images