A self-learning metal detection security gate with intelligent adjustment capabilities

Abstract

This invention relates to the field of intelligent security inspection equipment technology, and in particular to a self-learning metal detection security gate capable of intelligent adjustment. The security gate includes a frame; a signal acquisition module for acquiring magnetic field change information of the total magnetic field; a signal amplification module for amplifying the electrical signal; a signal filtering module for filtering the amplified electrical signal; an alarm module for analyzing whether the amplitude of the filtered electrical signal meets metal warning standards; a recording module for recording the time node of the alarm signal and the processing log for the alarm signal; and an analysis module for analyzing whether the operation of the security gate is qualified based on the proportion of passage time nodes, and determining the cause of non-compliance based on the variance of the amplitude of the electrical signal at the passage time nodes. This invention combines traditional metal detection technology with intelligent analysis algorithms, improving security inspection efficiency and reducing operation and maintenance costs.

Description

Technical Field

[0001] This invention relates to the field of intelligent security inspection equipment technology, and in particular to a self-learning metal detection security gate that can be intelligently adjusted. Background Technology

[0002] Traditional metal detector security gates are mainly based on the principle of electromagnetic induction. They generate an alternating magnetic field through a transmitting coil. When a metal object enters the magnetic field, eddy currents are generated, which are then detected by the receiving coil. However, these devices are susceptible to environmental interference and are prone to triggering alarms, resulting in a high false alarm rate. Existing technologies only optimize sensitivity or specific frequencies and do not form a closed-loop feedback system. They cannot automatically adjust parameters according to actual usage scenarios and require manual calibration by professionals on a regular basis, which increases maintenance costs.

[0003] Chinese Patent Application No. CN115524752A discloses a metal detection device and security gate based on zoned sensing, which solves the problem of missed detection when security gates detect metal objects in the prior art. In the metal detection device, the transmitting winding is used to transmit an alternating magnetic field to the receiving winding; the receiving winding includes multiple receiving coils, which are stacked along a first direction to form multiple sensing blocks. The orthographic projections of the multiple sensing blocks in a reference plane perpendicular to the first direction are matrix-distributed and arranged adjacent to each other. Each receiving coil contains one or more sensing blocks, and the alternating magnetic field in each receiving coil is the sum of the alternating magnetic fields in the sensing blocks it contains. Each receiving coil generates a sensing signal based on the change of the alternating magnetic field in the corresponding area; the detection unit is used to determine the metal object information in the detection area based on the change of the sensing signal generated by each receiving coil.

[0004] However, existing technologies still have the following problems:

[0005] The impact of environmental interference on the detection results was not effectively addressed, resulting in a high false alarm rate; optimization was only performed on a single parameter without forming a closed-loop feedback system that links multiple parameters, making it impossible to automatically adjust according to real-time scenarios; it was difficult to quickly locate the root cause of performance degradation (such as coil offset or abnormal signal processing), relying on manual inspection and calibration. Summary of the Invention

[0006] To address these issues, this invention provides a self-learning metal detector security gate with intelligent adjustment capabilities. This overcomes the problems of existing technologies that fail to effectively address the impact of environmental interference on detection results, leading to high false alarm rates; optimize only a single parameter without forming a closed-loop feedback system that links multiple parameters, making it impossible to automatically adjust according to real-time scenarios; and make it difficult to quickly pinpoint the root cause of performance degradation (such as coil offset or signal processing abnormalities), relying on manual inspection and calibration.

[0007] To achieve the above objectives, this invention provides a self-learning metal detection security gate capable of intelligent adjustment. It includes:

[0008] The frame includes a transmitting coil for generating an initial magnetic field and a receiving coil for detecting the total magnetic field;

[0009] A signal acquisition module, which is connected to the frame, is used to acquire magnetic field change information of the total magnetic field and convert the magnetic field change information into an electrical signal. The magnetic field change information includes changes in magnetic field strength and changes in magnetic field phase.

[0010] A signal amplification module, which is connected to the signal acquisition module, is used to amplify the electrical signal;

[0011] A signal filtering module, which is connected to the signal amplification module, is used to filter the amplified electrical signal.

[0012] An alarm module, which is connected to the signal filtering module, is used to analyze whether the filtered electrical signal amplitude meets the metal warning standard, and when the electrical signal amplitude is higher than the preset electrical signal amplitude, it is determined that the metal warning standard is met and an alarm signal is issued.

[0013] A recording module, connected to the alarm module, is used to record the time point when the alarm signal is issued and the processing log for the alarm signal. The log types include passage and interception.

[0014] The analysis module, which is connected to the frame, the signal acquisition module, the signal amplification module, the signal filtering module, the alarm module, and the recording module, is used to analyze whether the operation of the security gate is qualified based on the proportion of passage time nodes, and to determine the reasons for non-compliance based on the variance of the amplitude of the electrical signal at the passage time nodes.

[0015] Furthermore, the analysis module is used to determine the proportion of passing time nodes based on the ratio of the number of passing time nodes marked as passing in the processing log to the total number of time nodes that issued alarm signals, wherein,

[0016] If the proportion of passage time nodes is less than or equal to the preset proportion, the security gate is deemed to be operating successfully.

[0017] If the proportion of the number of passage time nodes is greater than the preset proportion, the operation of the security gate is determined to be unqualified, and the reason for the unqualified operation of the security gate is determined based on the variance of the electrical signal amplitude of the passage time nodes.

[0018] Furthermore, the analysis module determines the reason for the security gate's malfunction based on the variance of the electrical signal amplitude at the passage time node, wherein...

[0019] If the variance of the electrical signal amplitude at the passage time node is less than or equal to the preset variance, then the preset electrical signal amplitude is adjusted based on the variance.

[0020] If the variance of the electrical signal amplitude at the passage time node is greater than the preset variance, the reason for the security gate's failure to operate is determined based on the phase change at the marked time node.

[0021] Furthermore, the analysis module is also used to calculate the difference between the preset variance and the variance of the electrical signal amplitude at the passage time node, wherein the increase in the preset electrical signal amplitude is positively correlated with the difference.

[0022] Furthermore, the analysis module re-detects the variance of the electrical signal amplitude at the passage time node, and determines to repeatedly adjust the preset electrical signal amplitude based on the comparison result that the variance of the electrical signal amplitude at the re-detected passage time node is less than a preset variance.

[0023] If the preset amplitude after repeated adjustment is greater than or equal to the preset amplitude, then the filtering parameters of the adjustment signal filtering module are determined.

[0024] Furthermore, the analysis module is also used to calculate the average value of the electrical signal amplitude at each of the passage time nodes, wherein the reduction in the passband bandwidth of the signal filtering module is positively correlated with the average value.

[0025] Furthermore, the analysis module is also used to correct the amplification factor of the signal amplification module based on the adjusted passband bandwidth, wherein the increase in amplification factor is positively correlated with the decrease in passband bandwidth.

[0026] Furthermore, the analysis module is used to determine the reasons for the security gate's operational failure based on the phase changes at the marked time points, including: calculating the average phase value of each passage time point to obtain the average phase value.

[0027] If the average phase value is greater than or equal to the preset average phase value, the reason for the failure of the security gate is that the magnetic field frequency in the transmitting coil and receiving coil does not meet the standard.

[0028] If the average phase value is less than the preset average phase value, the reason for the security gate's failure to operate is determined to be a security gate malfunction, and a malfunction notification is issued.

[0029] Furthermore, the analysis module is also used to calculate the difference between the average phase value and the preset average phase value when the magnetic field frequency in the transmitting coil and the receiving coil does not meet the standard, to obtain the average phase difference, and to adjust the magnetic field frequency based on the average phase difference, wherein the reduction in magnetic field frequency is positively correlated with the average phase difference.

[0030] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention can quickly determine the operating status by the proportion of passage time nodes, simplify the basic judgment process, and ensure efficient screening of abnormal equipment; for unqualified cases, the cause can be analyzed by the variance of the electrical signal amplitude of the passage time nodes; for qualified equipment, unnecessary maintenance can be reduced, and the waste of operation and maintenance resources can be reduced; for unqualified equipment, the cause can be quickly located by variance, which can guide maintenance personnel to take precise measures, shorten the maintenance cycle, and reduce the troubleshooting cost; this hierarchical logic can reduce ineffective troubleshooting and improve the efficiency of fault location.

[0031] Furthermore, this invention first performs preliminary screening by comparing the variance with the preset variance, and then adopts different processing strategies based on the results. If the variance is less than or equal to the preset variance, it indicates that the signal fluctuation is within a controllable range, but the alarms are frequent. In this case, the false alarms are resolved by adjusting the preset electrical signal amplitude threshold. If the variance is greater than the preset variance, it indicates that the signal fluctuation is abnormal. Further analysis of phase changes is needed to locate hardware faults or external interference. By continuously monitoring the variance and phase changes, the system can provide early warnings of potential faults, achieve preventive maintenance, and avoid security inspection interruptions caused by sudden faults.

[0032] Furthermore, this invention calculates the difference between the preset variance and the variance of the passage time node, and makes the increase in the preset electrical signal amplitude positively correlated with this difference, thereby achieving precise adjustment of the threshold. When the difference is large (indicating that the actual fluctuation is far beyond expectations), the detection threshold is significantly increased to reduce false alarms; when the difference is small (indicating that the fluctuation is close to expectations), the threshold is finely adjusted to balance sensitivity and accuracy. As new data accumulates and the historical database is continuously updated, the optimal separation point and proportional coefficient can be recalculated periodically, enabling continuous optimization of system performance.

[0033] Furthermore, this invention gradually approaches the optimal threshold by repeatedly adjusting the preset electrical signal amplitude. After the first adjustment, if the variance is still higher than the preset value, the system automatically performs a second adjustment until the variance meets the standard. Each adjustment amplitude is positively correlated with the variance difference and is controlled by a linear regression model to avoid missed or false detections due to excessively large single adjustment amplitudes. If the threshold increases too much after the initial adjustment, small-volume dangerous metals may be missed. Iterative adjustment allows for fine-tuning, balancing sensitivity and accuracy. This division of labor enables the system to cope with different types of interference and improves the overall anti-interference capability.

[0034] Furthermore, this invention dynamically adjusts the passband bandwidth of the signal filtering module by calculating the average value of the electrical signal amplitude at the passage time node, so that the reduction in bandwidth is positively correlated with the average value. When the average value is high (indicating strong signal strength and high interference tolerance), the passband bandwidth is reduced to enhance the suppression of interference at specific frequencies; when the average value is low (indicating weak signal and the need to retain more frequency components), a wider passband is maintained to avoid excessive filtering of useful signals.

[0035] Furthermore, this invention analyzes the cause of the fault by comparing the average phase value with a preset average phase value. If the average phase value is greater than or equal to the preset value, it indicates an abnormal magnetic field frequency (such as coil aging or frequency shift caused by power supply fluctuations). If the average phase value is less than the preset value, it indicates a hardware fault (such as coil breakage or poor contact). It automatically distinguishes between "abnormal frequency" and "hardware fault", reducing manual troubleshooting steps. Traditional maintenance requires checking components such as power supply, coil, and sensor in sequence. Phase analysis directly locates the fault type, and by continuously monitoring the trend of the average phase value, it provides early warning of potential faults.

[0036] Furthermore, the fourth proportional coefficient of this invention is obtained by simulating the scenario of "high magnetic field frequency leading to abnormal phase mean", collecting corresponding data of "phase mean difference" and "optimal frequency reduction range", and then fitting it through linear regression (such as the least squares method). This coefficient determination method based on empirical data makes the adjustment of the magnetic field frequency reduction range more accurate, ensuring that the frequency adjustment range is precisely matched with the degree of phase anomaly, avoiding the problems of "over-adjustment" or "under-adjustment", and significantly improving the accuracy of frequency correction. When the magnetic field frequency does not meet the standard, the system directly calculates the adjustment range by multiplying the phase mean difference and the fourth proportional coefficient, without the need for repeated trial and error or gradually approaching the target frequency, greatly shortening the frequency correction cycle, enabling the security gate to quickly recover from the abnormal state to the standard working state, reducing downtime or inefficient operation time caused by frequency anomalies, and ensuring continuous and stable operation of the equipment. Attached Figure Description

[0037] Figure 1 This is a structural block diagram of the self-learning metal detector security gate that can intelligently adjust according to the present invention;

[0038] Figure 2 A flowchart for determining whether the operation of a security gate is up to standard;

[0039] Figure 3 A flowchart for determining the cause of a security gate's operational failure based on the variance of the electrical signal amplitude at passage time points;

[0040] Figure 4 A flowchart for determining the cause of a security gate's operational failure based on phase changes at marked time points. Detailed Implementation

[0041] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0042] It should be noted that the data in this embodiment are all derived from a comprehensive analysis and evaluation of historical data from the six months prior to this determination and the corresponding historical determination results by the system described in this invention. Those skilled in the art will understand that the system described in this invention can determine the above-mentioned parameters for a single item by selecting the value with the highest proportion based on the data distribution as the preset standard parameter, using weighted summation to obtain the value as the preset standard parameter, substituting each historical data point into a specific formula and using the value obtained by that formula as the preset standard parameter, or other selection methods, as long as the system described in this invention can clearly define different specific situations in the single-item determination process through the obtained values.

[0043] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0044] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0045] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0046] Please see Figures 1-4 As shown, Figure 1 This is a structural block diagram of the self-learning metal detector security gate that can intelligently adjust according to the present invention. Figure 2 To analyze the flowchart for determining whether the operation of the security gate is up to standard, Figure 3 A flowchart for determining the cause of a security gate's operational failure based on the variance of the electrical signal amplitude at passage time points. Figure 4 A flowchart for determining the cause of a security gate's operational failure based on phase changes at marked time points.

[0047] The frame includes a transmitting coil for generating an initial magnetic field and a receiving coil for detecting the total magnetic field;

[0048] A signal acquisition module, which is connected to the frame, is used to acquire magnetic field change information of the total magnetic field and convert the magnetic field change information into an electrical signal. The magnetic field change information includes changes in magnetic field strength and changes in magnetic field phase.

[0049] A signal amplification module, which is connected to the signal acquisition module, is used to amplify the electrical signal;

[0050] A signal filtering module, which is connected to the signal amplification module, is used to filter the amplified electrical signal.

[0051] An alarm module, which is connected to the signal filtering module, is used to analyze whether the filtered electrical signal amplitude meets the metal warning standard, and when the electrical signal amplitude is higher than the preset electrical signal amplitude, it is determined that the metal warning standard is met and an alarm signal is issued.

[0052] A recording module, connected to the alarm module, is used to record the time point when the alarm signal is issued and the processing log for the alarm signal. The log types include passage and interception.

[0053] The analysis module, which is connected to the frame, the signal acquisition module, the signal amplification module, the signal filtering module, the alarm module, and the recording module, is used to analyze whether the operation of the security gate is qualified based on the proportion of passage time nodes, and to determine the reasons for non-compliance based on the variance of the amplitude of the electrical signal at the passage time nodes.

[0054] Specifically, there are no restrictions on the specific structure of the analysis module; it can be composed of logic components, including field-programmable processors, computers, and microprocessors within computers.

[0055] Specifically, the analysis module determines the proportion of passing time nodes based on the ratio of the number of passing time nodes marked as passing in the processing log to the total number of time nodes that issued alarm signals.

[0056] If the proportion of passage time nodes is less than or equal to the preset proportion, the security gate is deemed to be operating successfully.

[0057] If the proportion of the number of passage time nodes is greater than the preset proportion, the operation of the security gate is determined to be unqualified, and the reason for the unqualified operation of the security gate is determined based on the variance of the electrical signal amplitude of the passage time nodes.

[0058] In this embodiment of the invention, the preset quantity ratio is the average quantity ratio of passage time nodes within the maintenance cycle interval of security gates under several similar application scenarios. However, the above value is not limited to this, and those skilled in the art can adjust it according to the actual situation.

[0059] This invention quickly determines the operating status by the proportion of passage time nodes, simplifying the basic judgment process and ensuring efficient screening of abnormal equipment. For non-compliant situations, the cause is analyzed by the variance of the electrical signal amplitude at the passage time nodes. For compliant equipment, unnecessary maintenance can be reduced, thus reducing the waste of operation and maintenance resources. For non-compliant equipment, the cause can be quickly located through variance analysis, which can guide maintenance personnel to take precise measures, shorten the maintenance cycle, and reduce troubleshooting costs. This hierarchical logic can reduce ineffective troubleshooting and improve fault location efficiency.

[0060] Specifically, the analysis module determines the reasons for the security gate's operational failure based on the variance of the electrical signal amplitude at the passage time node, wherein...

[0061] If the variance of the electrical signal amplitude at the passage time node is less than or equal to the preset variance, then the preset electrical signal amplitude is adjusted based on the variance.

[0062] If the variance of the electrical signal amplitude at the passage time node is greater than the preset variance, the reason for the security gate's failure to operate is determined based on the phase change at the marked time node.

[0063] The preset variance mentioned in this embodiment of the invention can be determined by the following method: In a controlled laboratory environment, a scenario of "no dangerous metal but triggering an alarm" is simulated. The amplitude data of the electrical signal is collected and the variance is calculated as the preset variance. A false alarm scenario is simulated by using non-dangerous metals that are carried daily. Testers are asked to carry these items through the security gate multiple times (e.g., 100-500 times) to ensure that the alarm is triggered each time but is ultimately judged as passing (i.e., simulating a false alarm in a real scenario). The amplitude data of the electrical signal at each false alarm is recorded by the signal acquisition module. The variance of the above data is calculated. After repeating 3-5 sets of tests, the average value is taken as the preset variance. However, the above value is not limited to this. Those skilled in the art can adjust it according to the actual situation.

[0064] This invention first performs preliminary screening by comparing the variance with the preset variance, and then adopts different processing strategies based on the results. If the variance is less than or equal to the preset variance, it indicates that the signal fluctuation is within a controllable range, but the alarms are frequent. In this case, the false alarms can be resolved by adjusting the preset electrical signal amplitude threshold. If the variance is greater than the preset variance, it indicates that the signal fluctuation is abnormal. Further analysis of phase changes is needed to locate hardware faults or external interference. By continuously monitoring the variance and phase changes, the system can provide early warnings of potential faults, achieve preventive maintenance, and avoid security inspection interruptions caused by sudden faults.

[0065] Specifically, the analysis module is also used to calculate the difference between the preset variance and the variance of the electrical signal amplitude at the passage time node, wherein the increase in the preset electrical signal amplitude is positively correlated with the difference.

[0066] The preset electrical signal amplitude in this embodiment of the invention can be determined by the following method: based on the historical operation data of the same type of security gate in similar scenarios, the distribution range of "actually intercepted dangerous metal signal amplitude" and "false alarm non-dangerous metal signal amplitude" is statistically analyzed, and the optimal separation point between the two is taken as the preset value; historical data is extracted from the recording module, and the electrical signal amplitudes corresponding to the two types of logs, namely "interception" and "passage", are filtered out; the probability density functions of the two types of signal amplitudes are plotted.

[0067] Find the intersection point or minimum overlap region of two probability density function curves, and use the amplitude value corresponding to the point as the preset electrical signal amplitude. The increase in the preset electrical signal amplitude is the product of a first proportional coefficient and the difference, where the difference is a non-negative number. The first proportional coefficient can be determined by obtaining several sets of data (different differences and corresponding optimal electrical signal amplitude increases) through controlled experiments. Use linear regression (such as the least squares method) to fit the relationship curve between different differences and the corresponding optimal electrical signal amplitude increases. The slope is the first proportional coefficient. However, the above value is not limited to this, and those skilled in the art can adjust it according to the actual situation.

[0068] This invention achieves precise threshold adjustment by calculating the difference between the preset variance and the variance of the passage time node, and by making the increase in the preset electrical signal amplitude positively correlated with this difference. When the difference is large (indicating that the actual fluctuation is far beyond expectations), the detection threshold is significantly increased to reduce false alarms; when the difference is small (indicating that the fluctuation is close to expectations), the threshold is finely adjusted to balance sensitivity and accuracy. As new data accumulates and the historical database is continuously updated, the optimal separation point and proportional coefficient can be recalculated periodically, enabling continuous optimization of system performance.

[0069] Specifically, the analysis module re-detects the variance of the electrical signal amplitude at each passage time node, and determines to repeatedly adjust the preset electrical signal amplitude based on the comparison result that the variance of the electrical signal amplitude at the re-detected passage time node is less than a preset variance.

[0070] If the preset amplitude after repeated adjustment is greater than or equal to the preset amplitude, then the filtering parameters of the adjustment signal filtering module are determined.

[0071] This invention gradually approaches the optimal threshold by repeatedly adjusting the preset electrical signal amplitude. After the first adjustment, if the variance is still higher than the preset value, the system automatically performs a second adjustment until the variance meets the standard. Each adjustment amplitude is positively correlated with the variance difference and is controlled by a linear regression model to avoid missed or false detections due to excessively large single adjustment amplitudes. If the threshold increases too much after the initial adjustment, small-volume dangerous metals may be missed. Iterative adjustment allows for fine-tuning, balancing sensitivity and accuracy. This division of labor enables the system to cope with different types of interference and improves its overall anti-interference capability.

[0072] Specifically, the analysis module is also used to calculate the average value of the electrical signal amplitude at each of the passage time nodes, wherein the reduction in the passband bandwidth of the signal filtering module is positively correlated with the average value.

[0073] In this embodiment of the invention, the reduction in passband bandwidth is the product of the average value of the electrical signal amplitude and a second proportional coefficient. The second proportional coefficient can be determined by simulating typical interference sources in a laboratory environment, testing the false alarm rate under different bandwidths, and back-deriving the optimal coefficient. A fixed interference source is set, the average value of the electrical signal amplitude is adjusted, the corresponding optimal passband bandwidth is recorded, and the average value of the ratio of the difference between the initial passband bandwidth and the optimal passband bandwidth of several sets of data to the average value of the electrical signal amplitude is recorded as the second proportional coefficient. However, the above value is not limited to this, and those skilled in the art can adjust it according to the actual situation.

[0074] This invention dynamically adjusts the passband bandwidth of the signal filtering module by calculating the average value of the electrical signal amplitude at the passage time node, so that the reduction in bandwidth is positively correlated with the average value. When the average value is high (indicating strong signal strength and high interference tolerance), the passband bandwidth is reduced to enhance the suppression of interference at specific frequencies; when the average value is low (indicating weak signal and the need to retain more frequency components), a wider passband is maintained to avoid excessive filtering of useful signals.

[0075] Specifically, the analysis module is also used to correct the amplification factor of the signal amplification module based on the adjusted passband bandwidth, wherein the increase in amplification factor is positively correlated with the decrease in passband bandwidth.

[0076] In this embodiment of the invention, the increase in amplification is the product of the decrease in passband bandwidth and a third proportionality coefficient. This third proportionality coefficient can be determined by constructing a standardized test scenario in a laboratory environment, fixing the basic parameters of the equipment and typical interference conditions, acquiring data using the controlled variable method, and setting variables and observation targets: using the decrease in passband bandwidth as the independent variable (e.g., setting a series of gradient values ​​ΔB1, ΔB2…ΔB). n The observation focuses on the increase in amplification required to maintain signal detection sensitivity (i.e., ensuring that the recognition rate of normal metal signals is not lower than a preset threshold and that the false alarm rate is controlled within an allowable range) (corresponding to ΔG1, ΔG2…ΔG). n For each pair of ΔBᵢ and ΔGᵢ, calculate the ratio ΔGᵢ / ΔBᵢ; fit the relationship curve between ΔG and ΔB through linear regression (such as the least squares method), and its slope is the third proportionality coefficient. However, the above values ​​are not limited to these, and those skilled in the art can adjust them according to the actual situation.

[0077] Specifically, the analysis module is used to determine the reasons for the security gate's operational failure based on the phase changes at the marked time points, including: calculating the average phase value of each passage time point to obtain the average phase value.

[0078] If the average phase value is greater than or equal to the preset average phase value, the reason for the failure of the security gate is that the magnetic field frequency in the transmitting coil and receiving coil does not meet the standard.

[0079] If the average phase value is less than the preset average phase value, the reason for the security gate's failure to operate is determined to be a security gate malfunction, and a malfunction notification is issued.

[0080] The preset average phase value mentioned in this embodiment of the invention can be determined based on the phase characteristics of the security gate during normal operation, and the phase differences under two scenarios: "the magnetic field frequency of the transmitting and receiving coils does not meet the standard" and "security gate malfunction". This is achieved through a combination of experimental statistics and threshold optimization. The process includes: obtaining the average phase value range during normal operation; conducting multiple tests on the same type of security gate under standard conditions (no interference, coil frequency conforming to factory settings, and no equipment malfunction), allowing personnel without metal objects to pass through normally, and recording the phase value at each passage time point; calculating the average phase value from multiple tests to obtain the "average phase value range during normal operation"; simulating the two scenarios of "magnetic field frequency not meeting the standard" and "security gate malfunction", collecting the corresponding average phase values, adjusting the frequency of the transmitting / receiving coils to deviate from the standard value (e.g., higher or lower than the rated frequency range), testing in an interference-free environment, and recording the average phase value at this time to obtain the "average phase value distribution under abnormal frequency conditions". (Usually, electromagnetic coupling anomalies caused by frequency shifts will result in a higher average phase value); Simulate typical equipment failures (such as coil breakage, poor interface contact, magnetic core aging, etc.), test at a standard frequency, and record the average phase value at this time to obtain the "phase mean distribution during equipment failure" (usually, the average phase value will be lower due to coil coupling failure); Perform statistical analysis on the collected "average phase value of frequency anomalies" and "average phase value of equipment failure"; Plot the probability density curves of the average phase values ​​of the two scenarios, and find the phase value corresponding to the intersection point or the minimum overlap area of ​​the two curves, which is the preset average phase value; If the intersection point is not obvious, it can be optimized by the principle of "minimizing the misjudgment rate", for example, setting multiple candidate thresholds, calculating the probability of "misjudging frequency anomalies as equipment failure" and "misjudging equipment failure as frequency anomalies" under each threshold, and selecting the threshold with the lowest total misjudgment rate as the preset average phase value, but the above values ​​are not limited to these, and those skilled in the art can adjust them according to the actual situation.

[0081] This invention analyzes the cause of faults by comparing the average phase value with a preset average phase value. If the average phase value is greater than or equal to the preset value, it indicates an abnormal magnetic field frequency (such as coil aging or frequency shift caused by power supply fluctuations). If the average phase value is less than the preset value, it indicates a hardware fault (such as coil breakage or poor contact). It automatically distinguishes between "abnormal frequency" and "hardware fault", reducing manual troubleshooting steps. Traditional maintenance requires checking components such as power supply, coil, and sensor in sequence. Phase analysis directly locates the fault type, and by continuously monitoring the trend of the average phase value, it provides early warning of potential faults.

[0082] Specifically, the analysis module is also used to calculate the difference between the average phase value and the preset average phase value when the magnetic field frequency in the transmitting coil and the receiving coil does not meet the standard, to obtain the average phase difference, and to adjust the magnetic field frequency based on the average phase difference, wherein the reduction in magnetic field frequency is positively correlated with the average phase difference.

[0083] In this embodiment of the invention, the reduction in magnetic field frequency is the product of the phase mean difference and a fourth proportional coefficient. This fourth proportional coefficient can be determined by simulating a scenario where "a high magnetic field frequency leads to an abnormal phase mean," collecting corresponding data on the "phase mean difference" and the "optimal frequency reduction," and establishing a quantitative relationship between them; determining the standard operating frequency of the security gate and its corresponding preset phase mean; gradually increasing the magnetic field frequency, allowing a tester without metal objects to pass through the security gate after each adjustment, recording the phase mean at this time, and calculating the phase mean difference; for each phase mean difference, gradually decreasing the magnetic field frequency until the phase mean returns to the initial phase mean, recording the frequency reduction after the initial abnormal frequency adjustment; for each group of phase mean differences and frequency reduction, calculating the ratio of the frequency reduction to the phase mean difference, fitting the relationship curve through linear regression (such as the least squares method), and its slope is the fourth proportional coefficient. However, the above values ​​are not limited to these, and those skilled in the art can adjust them according to actual conditions.

[0084] The fourth proportional coefficient of this invention is obtained by simulating a scenario where "a high magnetic field frequency leads to an abnormal phase mean," collecting corresponding data on the "phase mean difference" and the "optimal frequency reduction range," and then fitting the data through linear regression (such as the least squares method). This method of determining coefficients based on empirical data makes the adjustment of the magnetic field frequency reduction range more accurate, ensuring that the frequency adjustment range is precisely matched with the degree of phase anomaly, avoiding the problems of "over-adjustment" or "under-adjustment," and significantly improving the accuracy of frequency correction. When the magnetic field frequency does not meet the standard, the system directly calculates the adjustment range by multiplying the phase mean difference by the fourth proportional coefficient, without the need for repeated trial and error or gradually approaching the target frequency. This greatly shortens the frequency correction cycle, enabling the security gate to quickly recover from the abnormal state to the standard working state, reducing downtime or inefficient operation time caused by frequency anomalies, and ensuring continuous and stable operation of the equipment.

[0085] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0086] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A self-learning metal detection security gate capable of intelligent adjustment, characterized in that, The application relates to a security door, which comprises the following parts: a frame, which comprises a transmitting coil for generating an initial magnetic field and a receiving coil for detecting a total magnetic field; a signal collecting module connected with the frame, which is used for collecting magnetic field change information of the total magnetic field and converting the magnetic field change information into an electric signal, wherein the magnetic field change information comprises magnetic field intensity change and magnetic field phase change; a signal amplifying module connected with the signal collecting module, which is used for amplifying the electric signal; a signal filtering module connected with the signal amplifying module, which is used for filtering the amplified electric signal; an alarm module connected with the signal filtering module, which is used for analyzing whether the electric signal amplitude after filtering meets a metal early warning standard and determining that the metal early warning standard is met and an alarm signal is sent when the electric signal amplitude is higher than a preset electric signal amplitude; a recording module connected with the alarm module, which is used for recording a time node of sending the alarm signal and a processing log of the alarm signal, and the log type comprises passing and intercepting; an analysis module connected with the frame, the signal collecting module, the signal amplifying module, the signal filtering module, the alarm module and the recording module, which is used for analyzing whether the operation of the security door is qualified based on a quantity proportion of passing time nodes and determining an unqualified reason based on a variance of the electric signal amplitude of the passing time nodes; the analysis module is used for determining the quantity proportion of the passing time nodes based on a ratio of the number of the passing time nodes marked in the processing log to the total number of the time nodes of sending the alarm signal, wherein if the quantity proportion of the passing time nodes is less than or equal to a preset quantity proportion, it is determined that the operation of the security door is qualified; if the quantity proportion of the passing time nodes is greater than the preset quantity proportion, it is determined that the operation of the security door is unqualified, and a reason for the unqualified operation of the security door is determined according to the variance of the electric signal amplitude of the passing time nodes; the analysis module determines the reason for the unqualified operation of the security door according to the variance of the electric signal amplitude of the passing time nodes, wherein if the variance of the electric signal amplitude of the passing time nodes is less than or equal to a preset variance, the preset electric signal amplitude is adjusted based on the variance; if the variance of the electric signal amplitude of the passing time nodes is greater than the preset variance, the reason for the unqualified operation of the security door is determined according to the phase change in the marked time node.

2. The self-learning metal detection security gate capable of intelligent adjustment according to claim 1, wherein, The analysis module further calculates a difference value between the preset variance and the variance of the electric signal amplitude of the passing time nodes, wherein the increase amount of the preset electric signal amplitude is positively correlated with the difference value.

3. The self-learning metal detection security gate capable of intelligent adjustment according to claim 2, characterized in that, The analysis module re-detects the variance of the electric signal amplitude of the passing time nodes, and determines whether to repeatedly adjust the preset electric signal amplitude based on the comparison result that the re-detected variance of the electric signal amplitude of the passing time nodes is less than the preset variance, wherein if the preset amplitude after the repeated adjustment is greater than or equal to a preset amplitude, the filtering parameter of the signal filtering module is adjusted.

4. The self-learning metal detection security gate capable of intelligent adjustment according to claim 3, characterized in that, The analysis module is further configured to calculate an average value of the amplitudes of the electric signals of the transit time nodes, and the reduction of the passband bandwidth of the signal filtering module is positively correlated with the average value.

5. The self-learning metal detection security gate capable of intelligent adjustment according to claim 4, characterized in that, The analysis module is further configured to correct an amplification factor of the signal amplification module based on the adjusted passband bandwidth, and the increase of the amplification factor is positively correlated with the reduction of the passband bandwidth.

6. The self-learning metal detection security gate with intelligent adjustment capability of claim 1, wherein, The analysis module is configured to determine the cause of the unqualified operation of the security door according to the phase change in the marker time node, including: calculating an average value of the phase values of the transit time nodes to obtain a phase average value, If the phase average value is greater than or equal to a preset phase average value, it is determined that the cause of the unqualified operation of the security door is that the magnetic field frequency in the transmitting coil and the receiving coil does not meet the standard. If the phase average value is less than the preset phase average value, it is determined that the cause of the unqualified operation of the security door is that the security door is faulty, and a fault notification is sent.

7. The self-learning metal detection security gate with intelligent adjustment capability according to claim 6, characterized in that, The analysis module is further configured to calculate a phase average value difference between the phase average value and the preset phase average value under the condition that it is determined that the magnetic field frequency in the transmitting coil and the receiving coil does not meet the standard, and adjust the magnetic field frequency based on the phase average value difference, and the reduction of the magnetic field frequency is positively correlated with the phase average value difference.

Images