A multi-parameter fusion intelligent double-hook safety early warning method and system

Abstract

The application provides a multi-parameter fusion intelligent double-hook safety early warning method and system, relates to the technical field of safety protection, and comprises the following steps: acquiring multi-source detection information of a target hook; the multi-source detection information comprises infrared signals, three-axis attitude information and displacement trajectory information; determining infrared risk coefficients, attitude risk coefficients and displacement risk coefficients based on the relationship between the infrared signals, the three-axis attitude information, the displacement trajectory information and corresponding threshold values, and combining the current detection scene to query a preset weight mapping list, acquire the weights corresponding to the infrared risk coefficients, the attitude risk coefficients and the displacement risk coefficients respectively, and generate corresponding comprehensive risk values through weighted fusion; the preset weight mapping list comprises the mapping relationship between each risk coefficient and the corresponding weight under different scene categories; and determining the current alarm level according to the threshold interval where the comprehensive risk value is located.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of safety protection, in particular to a multi-parameter fusion intelligent double-hook safety early warning method and system. BACKGROUND

[0002] Traditional high-altitude operation of power grid generally adopts mechanical double-hook protection device, which relies on experience of operating personnel to judge hook body opening and closing state and hooking effectiveness, and has hidden dangers such as hook body closing without penetrating tower material and failure of anti-dropping structure, and lacks real-time state monitoring means. The existing technology adopts single sensor to detect hook body closing, cannot identify invalid hooking behavior, has high misjudgment rate, and the monitoring data is stored locally without remote early warning capability, which is difficult to intervene in risks in time.

[0003] Although part of the intelligent safety hook introduces Internet of Things technology, the parameter collection dimension is single, and parameters such as hook body posture, displacement trajectory and environmental interference are not fused, which is difficult to cope with the problem of false triggering caused by weak signal and complex scene in mountainous area, and cannot well and timely find safety hazards and protect personnel safety. SUMMARY

[0004] Therefore, the present application provides a multi-parameter fusion intelligent double-hook safety early warning method and system.

[0005] The technical scheme of the present application is implemented as follows: the present application provides a multi-parameter fusion intelligent double-hook safety early warning method in the first aspect, comprising:

[0006] obtaining multi-source detection information of a target hook; the multi-source detection information includes infrared signal, three-axis posture information and displacement trajectory information;

[0007] determining infrared risk coefficient, posture risk coefficient and displacement risk coefficient based on the relationship between the infrared signal, the three-axis posture information and the displacement trajectory information and corresponding threshold values, and obtaining the respective weights of the infrared risk coefficient, the posture risk coefficient and the displacement risk coefficient by querying a preset weight mapping list in combination with the current detection scene, and generating a corresponding comprehensive risk value by weighted fusion; the preset weight mapping list includes the mapping relationship between each risk coefficient and the corresponding weight under different scene categories;

[0008] determining the current alarm level according to the threshold interval where the comprehensive risk value is located.

[0009] On the basis of the above technical scheme, preferably, the obtaining of the multi-source detection information of the target hook comprises:

[0010] obtaining the signal intensity difference value corresponding to the target hook by using an infrared pair tube detection unit;

[0011] An acceleration, an angular velocity and an inclination angle corresponding to the target hook are acquired by using a three-axis attitude sensor;

[0012] A displacement trajectory corresponding to the target hook is acquired by using a photoelectric displacement encoder.

[0013] On the basis of the above technical solutions, preferably, the relationship between the infrared signal, the three-axis attitude information and the displacement trajectory information and corresponding threshold values is used to determine an infrared risk coefficient, an attitude risk coefficient and a displacement risk coefficient, including:

[0014] The position information of the target hook is determined based on the size relationship between the signal intensity difference and a first threshold value, and the infrared risk coefficient is acquired based on the position information;

[0015] The position information of the target hook is determined based on the size relationship between the acceleration and the angular velocity and a second threshold value and a third threshold value, and the attitude risk coefficient is acquired based on the position information;

[0016] The attitude stability of the target hook is determined based on the size relationship between the displacement trajectory and a fourth threshold value, and the displacement risk coefficient is acquired based on the attitude stability.

[0017] On the basis of the above technical solutions, preferably, the preset weight mapping list is queried in combination with a current detection scene, the respective weights of the infrared risk coefficient, the attitude risk coefficient and the displacement risk coefficient are acquired, a corresponding comprehensive risk value is generated through weighted fusion, including:

[0018] In a motion operation scene, the weight of the infrared risk coefficient is less than a normal infrared weight, and the weights of the attitude risk coefficient and the displacement risk coefficient are greater than a normal attitude weight and a normal displacement weight;

[0019] In a static operation scene, the weights of the infrared risk coefficient and the attitude risk coefficient are greater than a normal infrared weight and a normal attitude weight, and the weight of the displacement risk coefficient is less than a normal displacement weight.

[0020] On the basis of the above technical solutions, preferably, the preset weight mapping list is queried in combination with a current detection scene, the respective weights of the infrared risk coefficient, the attitude risk coefficient and the displacement risk coefficient are acquired, a corresponding comprehensive risk value is generated through weighted fusion, and the method further includes:

[0021] In the case where any one of the infrared risk coefficient, the attitude risk coefficient and the displacement risk coefficient is greater than a preset risk threshold value, the other two risk coefficients in a preset historical period are acquired;

[0022] If the other two risk coefficients in the preset historical period do not exceed the corresponding preset risk threshold, it is determined that the current situation is normal.

[0023] On the basis of the above technical solutions, preferably, the current alarm level is determined according to the threshold interval in which the comprehensive risk value is located, including:

[0024] According to historical alarm data, the prior probability of the target hook being abnormal under different historical comprehensive risk values is determined;

[0025] The confidence of the current comprehensive risk value is determined by using the Bayes formula combined with the prior probability;

[0026] The current alarm level is determined based on the confidence.

[0027] On the basis of the above technical solutions, preferably, the current alarm level is determined according to the threshold interval in which the comprehensive risk value is located, including:

[0028] When the comprehensive risk value is located in the first threshold interval, it is determined that the current situation is normal; the maximum value of the first threshold interval is the upper limit of the safety threshold;

[0029] When the comprehensive risk value is located in the second threshold interval, a first-level warning is triggered; the minimum value of the second threshold interval is greater than the upper limit of the safety threshold;

[0030] When the comprehensive risk value is located in the third threshold interval, a second-level warning is triggered; the minimum value of the third threshold interval is greater than the maximum value of the second threshold interval.

[0031] Further preferably, the second aspect of the present application provides a multi-parameter fusion intelligent double-hook safety warning system, comprising: an information acquisition module, a weighted fusion module and an alarm determination module; wherein,

[0032] The information acquisition module is configured to acquire multi-source detection information of the target hook; the multi-source detection information includes infrared signals, three-axis attitude information and displacement trajectory information;

[0033] The weighted fusion module is configured to determine infrared risk coefficients, attitude risk coefficients and displacement risk coefficients based on the relationship between the infrared signals, the three-axis attitude information and the displacement trajectory information and the corresponding threshold values, and to acquire the respective weights of the infrared risk coefficients, the attitude risk coefficients and the displacement risk coefficients by querying a preset weight mapping list in combination with the current detection scene, and to generate corresponding comprehensive risk values by weighted fusion; the preset weight mapping list includes the mapping relationship between each risk coefficient and the corresponding weight under different scene categories;

[0034] The alarm determination module is configured to determine a current alarm level according to a threshold interval in which the comprehensive risk value is located.

[0035] Further preferably, the third aspect of the present application provides an electronic device comprising a processor and a memory; the memory has a computer program stored therein, wherein the computer program, when executed by the processor, implements the multi-parameter fusion intelligent double-hook safety early warning method of the first aspect.

[0036] Further preferably, the fourth aspect of the present application provides a computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the multi-parameter fusion intelligent double-hook safety early warning method of the first aspect.

[0037] The multi-parameter fusion intelligent double-hook safety early warning method and system of the present application have the following beneficial effects relative to the prior art:

[0038] 1. By comprehensively utilizing three different types of detection signals, i.e., infrared signals, three-axis attitude information and displacement trajectory information, to complement each other, the running state of the target hook can be more comprehensively understood, the limitations and misjudgments that may exist in a single information source are avoided, and thus the risk condition of the target hook can be more accurately evaluated. In combination with a scene-adaptive weighted fusion mode, various risk factors can be more reasonably considered in combination, and the accuracy of risk evaluation is further improved.

[0039] 2. By comprehensively considering multiple risk coefficients, when an abnormality occurs in a certain risk coefficient, the historical situation of other risk coefficients is referred to, and according to the other two risk coefficients within a preset historical period, the influence of a single point failure on detection and judgment can be reduced, the stability and reliability of detection can be improved, the detection can better adapt to complex and changeable environments, the real state of the target hook can be accurately judged, and the reliability and stability of the detection result in a complex environment are enhanced.

[0040] 3. Different levels of alarms correspond to different degrees of risk, and the alarm level determined according to the confidence degree can guide the reasonable allocation of human and material resources. For high-level alarms, due to the greater risk, more manpower needs to be immediately invested for emergency treatment and investigation to prevent accidents from occurring or expanding, and for low-level alarms, fewer personnel can be arranged for regular observation and monitoring to avoid excessive waste of resources. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to make the technical solutions in the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description only aim to some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort.

[0042] Figure 1 A flowchart of a multi-parameter fusion intelligent double-hook safety warning method provided by an embodiment of the present application is shown in the figure.

[0043] Figure 2 A structural diagram of a multi-parameter fusion intelligent double-hook safety warning system provided by an embodiment of the present application is shown in the figure.

[0044] Figure 3 A structural diagram of an electronic device provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort fall within the scope of the present application.

[0046] In some embodiments, as shown in Figure 1 , Figure 1 A flowchart of a multi-parameter fusion intelligent double-hook safety warning method provided by an embodiment of the present application is shown in the figure. The multi-parameter fusion intelligent double-hook safety warning method provided by the present application comprises:

[0047] S110, acquiring multi-source detection information of a target hook; the multi-source detection information comprises infrared signals, three-axis attitude information and displacement trajectory information.

[0048] Here, the controller (STM32H743VI) synchronously collects data of the three types of sensors through I2C / SPI interfaces, and the sampling frequency is unified to 100Hz. A 1ms precision timestamp is added to each data frame to ensure that the infrared (1ms response), attitude (5ms update) and displacement (10ms sampling) data are aligned in the time dimension.

[0049] In some embodiments, S110, acquiring multi-source detection information of a target hook, comprises:

[0050] Acquiring a signal strength difference value corresponding to the target hook by using an infrared pair tube detection unit;

[0051] An acceleration, an angular velocity and an inclination angle corresponding to the target hook are acquired by using a three-axis attitude sensor.

[0052] A displacement trajectory corresponding to the target hook is acquired by using a photoelectric displacement encoder.

[0053] In the embodiment, the hook is equipped with a multi-sensor array including an infrared pair tube detection unit, a three-axis attitude sensor and a photoelectric displacement encoder to cooperatively collect hooking state data. The infrared pair tube detection unit can accurately locate the position and state of the hook by measuring the infrared signal intensity difference at a specific position on the target hook. The three-axis attitude sensor can simultaneously measure the acceleration, angular velocity and inclination angle of the target hook in three axial directions, and can comprehensively monitor the motion state of the hook. The photoelectric displacement encoder has high-precision displacement measurement capability, and can accurately acquire the displacement trajectory of the target hook in real time. By analyzing the displacement trajectory, the motion law and characteristics of the target hook can be understood. Here, the infrared pair tube detection unit can be an MJT-GP2Y0E03 (Meijiate) infrared pair tube module, the three-axis attitude sensor can be an SC7A20 type attitude sensor, the three-axis attitude sensor can collect inclination angle (accuracy ±0.5°) and vibration frequency (sampling rate 100 Hz), and the photoelectric displacement encoder can record displacement trajectory (resolution 0.1 mm).

[0054] When the signal intensity difference between the infrared transmitting end and the receiving end is ≥30%, it is determined that the hook body effectively penetrates the tower material. The specific principle is as follows: if the hook body does not penetrate the tower material, such as being hooked on the surface of the tower material or not being completely closed, the infrared light will be reflected or blocked by the metal surface of the tower material, resulting in a small difference between the signal intensity of the receiving end and the transmitting end; if the hook body penetrates the tower material, the infrared light propagates through the gap between the tower materials, and the signal intensity of the receiving end attenuates to meet the preset threshold, and the difference is ≥30%, so it is determined that the hooking is effective. The displacement trajectory collected by the photoelectric displacement encoder is matched and analyzed by a standard component spacing model of the power transmission tower built in the controller, such as a standard size database of angle steel and cross arm. The displacement encoder records the moving trajectory coordinates of the hook body after hooking, and the edge computing unit compares the trajectory data with the standard component spacing in the database, such as adjacent tower material spacing of 0.8 m, 1.2 m, etc. If the continuous unhooking moving distance in the trajectory exceeds 0.5 m and there is no corresponding standard spacing matching, it is determined that there is an unhooking moving risk.

[0055] In S120, the infrared risk coefficient, the attitude risk coefficient and the displacement risk coefficient are determined based on the relationship between the infrared signal, the three-axis attitude information and the displacement trajectory information and the corresponding threshold, and the corresponding weights of the infrared risk coefficient, the attitude risk coefficient and the displacement risk coefficient are obtained by querying a preset weight mapping list according to the current detection scene, and a corresponding comprehensive risk value is generated by weighted fusion; the preset weight mapping list includes the mapping relationship between each risk coefficient and the corresponding weight under different scene categories.

[0056] By comparing infrared signals, three-axis attitude information, and displacement trajectory information with corresponding thresholds, the system determines the corresponding risk coefficients, achieving precise quantification of different types of risks. Since the weights of each risk coefficient can be adjusted according to actual conditions, when a certain risk factor becomes more prominent in the current scenario, the system can promptly increase the weight of its corresponding risk coefficient, thereby more effectively responding to risk changes.

[0057] In some embodiments, the infrared risk coefficient, attitude risk coefficient, and displacement risk coefficient are determined based on the relationship between infrared signals, three-axis attitude information, and displacement trajectory information and corresponding thresholds, including:

[0058] The location information of the target hook is determined based on the relationship between the signal strength difference and the first threshold, and the infrared risk coefficient is obtained based on the location information.

[0059] The attitude stability of the target hook is determined based on the relationship between acceleration and angular velocity and the second and third thresholds, and the attitude risk coefficient is obtained based on the attitude stability.

[0060] The trajectory error of the target hook is determined based on the relationship between the displacement trajectory and the fourth threshold, and the displacement risk coefficient is obtained based on the trajectory error.

[0061] In this embodiment, risk coefficients are determined through threshold comparisons, thus quantifying risk. For example, the infrared risk coefficient can be set to 0 when the signal strength difference is greater than 30%, indicating no risk; the infrared risk coefficient can be set to 1 when the signal strength difference is within a certain range of the first threshold, indicating low risk; and the infrared risk coefficient can be set to 2 when the difference exceeds this range, indicating high risk. Similarly, similar quantification methods can be used for attitude risk coefficients and displacement risk coefficients. In addition, other quantification methods can be used in combination.

[0062] In one optional embodiment, before obtaining the infrared risk coefficient, attitude risk coefficient, and displacement risk coefficient, normalization is performed in advance to ensure that the scale of each risk coefficient is consistent and to avoid the effect of some risk coefficients being ignored. For the infrared risk coefficient, the distance between the target hook and the device is detected by an infrared sensor. Combined with preset safe distance threshold and dynamic adjustment coefficient Calculate the infrared risk coefficient :

[0063] ;

[0064] For attitude risk factors, the angular velocities of the target hook along the X, Y, and Z axes can be obtained using a three-axis attitude sensor. , , ) and acceleration ( , , ), calculate the posture stability index , and map it to the posture risk coefficient .

[0065] The posture stability index :

[0066] ;

[0067] The posture risk coefficient :

[0068] ;

[0069] Here, and are the low and high risk thresholds, respectively.

[0070] For the displacement risk coefficient, the displacement trajectory of the target hook can be obtained by an optical-electric displacement encoder, and the error of the trajectory deviating from the preset path and the rate of change of speed are calculated to generate a risk value :

[0071] ;

[0072] wherein is the path error weight, is the rate of change of speed, and are the maximum allowed error and the maximum rate of change of speed.

[0073] Finally, the corresponding comprehensive risk value is generated by weighted fusion:

[0074] ;

[0075] wherein , , are the weights of the infrared risk coefficient, the posture risk coefficient and the displacement risk coefficient, respectively, which can be adaptively adjusted according to the current scene, and can be obtained by querying a preset weight mapping list in combination with the current detection scene.

[0076] In some embodiments, the weights of the infrared risk coefficient, the posture risk coefficient and the displacement risk coefficient are obtained by querying a preset weight mapping list in combination with the current detection scene, and the corresponding comprehensive risk value is generated by weighted fusion, including:

[0077] In the moving operation scene, the weight of the infrared risk coefficient is less than the normal infrared weight, and the weights of the posture risk coefficient and the displacement risk coefficient are greater than the normal posture weight and the normal displacement weight.

[0078] In the static operation scene, the weights of the infrared risk coefficient and the posture risk coefficient are greater than the normal infrared weight and the normal posture weight, and the weight of the displacement risk coefficient is less than the normal displacement weight.

[0079] In the moving operation scene, the target hook is in a dynamic state, and the displacement and posture of the target hook change more frequently. The infrared signal may be more disturbed, such as the rapid movement of surrounding objects, changes in light, etc., resulting in unstable signal intensity difference. Reducing the weight of the infrared risk coefficient can avoid misjudging the risk due to accidental fluctuations of the infrared signal. In the static operation scene, the displacement of the hook is relatively fixed, and the main risks are concentrated in the abnormal infrared signal, such as being blocked, equipment failure, etc., and the unstable posture, such as the inclination of the hook causing the goods to slide. Increasing the weights of the infrared risk coefficient and the posture risk coefficient helps to more accurately assess these static risks. Since the displacement changes less in the static state, the influence on the overall risk is relatively reduced. Reducing the weight of the displacement risk coefficient can avoid the system paying too much attention to the relatively unimportant factor of displacement, improving the pertinence and accuracy of risk assessment.

[0080] In one example, in the climbing scene (displacement change rate > 0.2 m / s): preferentially adopt the linkage of "posture sensor + displacement encoder", when the posture anomaly (inclination angle > 15° and vibration frequency > 5 Hz) and the displacement overrun (continuous unhooking movement > 0.3 m) are triggered at the same time, it is determined as a risk (avoiding misjudgment of climbing action), at this time the infrared weight is reduced to 40%. In the static operation scene (displacement change rate < 0.05 m / s): start the dual verification of "infrared penetration + posture stability", if the infrared signal difference < 30% and the inclination angle fluctuation of the posture sensor within 30 seconds > 5°, it is determined as "surface hooking risk", at this time, the displacement weight is reduced to 5%.

[0081] In some embodiments, the preset weight mapping list is queried in combination with the current detection scene to obtain the weights corresponding to the infrared risk coefficient, the posture risk coefficient and the displacement risk coefficient respectively, and a corresponding comprehensive risk value is generated by weighted fusion, and further comprising:

[0082] In the case that any one of the infrared risk coefficient, the posture risk coefficient and the displacement risk coefficient is greater than the preset risk threshold, the other two risk coefficients in the preset historical period are obtained;

[0083] If the other two risk coefficients in the preset historical period do not exceed the corresponding preset risk threshold, it is determined that the current situation is normal.

[0084] In a complex operation environment, a single risk coefficient exceeding the threshold value can be an isolated event caused by accidental factors, and does not necessarily represent a serious problem with the overall system. For example, in a sports operation scenario, the infrared risk coefficient can suddenly increase due to temporary obstruction, but the attitude and displacement risk coefficients are normal. By obtaining the other two risk coefficients in a preset historical period for comprehensive judgment, it can be distinguished whether this is an isolated risk or a real systemic risk. If the other two risk coefficients do not exceed the corresponding threshold value in the preset historical period, it means that only the current risk indicator is abnormal, which can be a local and temporary problem, rather than a failure of the entire system, thereby avoiding misjudgment of isolated events as systemic risks.

[0085] In one example, when a certain sensor data triggers a risk warning, the historical data of the other two types of sensors in the previous 5 seconds is automatically traced back, such as the infrared determination "not penetrated". If it is found that there is "0.5m continuous unconnected movement" in the same period displacement trajectory and the attitude inclination angle is stable (<5°), the risk is confirmed; if the attitude data shows that there is climbing vibration (frequency 8Hz) in the same period, it is determined as "infrared false alarm under vibration interference", and the warning is cancelled. Here, 5 seconds is only an example, and it can also be 10 seconds, 20 seconds, and no specific limitation is made.

[0086] S130, determining the current alarm level according to the threshold interval where the comprehensive risk value is located.

[0087] Different alarm levels correspond to different response measures, and through hierarchical alarm, resources can be reasonably allocated. For low risk levels, less resources can be invested for monitoring and processing; for high risk levels, resources are concentrated for emergency rescue and fault elimination, improving resource utilization efficiency.

[0088] In some embodiments, S130 determines the current alarm level according to the threshold interval where the comprehensive risk value is located, including:

[0089] According to the statistical history alarm data, the prior probability of the target hook appearing abnormal under different historical comprehensive risk values is determined;

[0090] Using the Bayes formula, the confidence of the comprehensive risk value is determined in combination with the prior probability;

[0091] The current alarm level is determined based on the confidence.

[0092] In this embodiment, after cleaning the collected historical data to remove repeated, incorrect or incomplete data records, the value range of the comprehensive risk value is divided into several intervals, for example, if the range of the comprehensive risk value is 0-100, it can be divided into 0-20, 21-40, 41-60, 61-80, 81-100 five intervals. For each interval of the comprehensive risk value, the number of abnormalities in the interval and the total number of records in the interval are counted. Divide the number of abnormalities by the total number of records to get the frequency of abnormalities in the interval, that is, the prior probability. Using Bayes formula: Here, A represents an abnormal event, and B represents the current comprehensive risk value. The confidence of the comprehensive risk value can be determined, and thus the current alarm level is determined, which improves the accuracy of the evaluation of the current comprehensive risk value and reduces false positives and false negatives.

[0093] In some embodiments, S130 determines the current alarm level according to the threshold interval in which the comprehensive risk value is located, comprising:

[0094] When the comprehensive risk value is located in the first threshold interval, it is determined that the current situation is normal; the maximum value of the first threshold interval is the upper limit of the safety threshold;

[0095] When the comprehensive risk value is located in the second threshold interval, a first level of early warning is triggered; the minimum value of the second threshold interval is greater than the upper limit of the safety threshold;

[0096] When the comprehensive risk value is located in the third threshold interval, a second level of early warning is triggered; the minimum value of the third threshold interval is greater than the maximum value of the second threshold interval.

[0097] In one example, if the comprehensive risk value is less than 0.7, it indicates that the current situation is normal and no early warning is triggered; if the comprehensive risk value is greater than 0.7 and less than 0.9, a first level of early warning is triggered; if the comprehensive risk value is greater than or equal to 0.9, a second level of early warning is triggered.

[0098] In another example, when the infrared signal intensity is less than the corresponding threshold value, and the displacement encoder detects that the continuous unhooked moving distance is greater than 0.5m, a first level of early warning is triggered; if the hook body inclination angle is greater than 15° and the vibration frequency exceeds the safety range (2-5Hz) at the same time, it is determined as a composite risk scenario, and a second level of early warning is started. Here, the early warning signal can be uploaded to the server and the ground monitoring center through the LoRa module set on the hook. In addition, when the current altitude of the hook is high, the controller on the hook can switch the spreading factor of the LoRa module to SF to increase the transmission range of the signal.

[0099] In some embodiments, please refer to Figure 2 , Figure 2A structure schematic diagram of a multi-parameter fusion intelligent double-hook safety early warning system provided for an embodiment of the present application. The present application provides a multi-parameter fusion intelligent double-hook safety early warning system 200, comprising: an information acquisition module 210, a weighted fusion module 220 and an alarm determination module 230; wherein,

[0100] The information acquisition module 210 is configured to acquire multi-source detection information of a target hook; the multi-source detection information comprises infrared signals, three-axis attitude information and displacement trajectory information;

[0101] The weighted fusion module 220 is configured to determine infrared risk coefficients, attitude risk coefficients and displacement risk coefficients based on the relationship between the infrared signals, the three-axis attitude information and the displacement trajectory information and corresponding threshold values, and to acquire respective weights of the infrared risk coefficients, the attitude risk coefficients and the displacement risk coefficients by querying a preset weight mapping list in combination with a current detection scene, and to generate corresponding comprehensive risk values through weighted fusion; the preset weight mapping list comprises a mapping relationship between each risk coefficient and a corresponding weight under different scene categories;

[0102] The alarm determination module 230 is configured to determine a current alarm level according to a threshold interval of the comprehensive risk values.

[0103] In some embodiments, the information acquisition module 210 is specifically configured to:

[0104] acquire a signal intensity difference value corresponding to the target hook by using an infrared pair tube detection unit;

[0105] acquire acceleration, angular velocity and inclination angle corresponding to the target hook by using a three-axis attitude sensor;

[0106] acquire a displacement trajectory corresponding to the target hook by using an optical-electric displacement encoder.

[0107] In some embodiments, the weighted fusion module 220 is specifically configured to:

[0108] determine position information of the target hook based on the size relationship between the signal intensity difference value and a first threshold value, and acquire the infrared risk coefficient based on the position information;

[0109] determine attitude stability of the target hook based on the size relationship between the acceleration and the angular velocity and a second threshold value and a third threshold value, and acquire the attitude risk coefficient based on the attitude stability;

[0110] determine trajectory error of the target hook based on the size relationship between the displacement trajectory and a fourth threshold value, and acquire the displacement risk coefficient based on the trajectory error.

[0111] In some embodiments, the weighted fusion module 220 is specifically configured to:

[0112] In the motion operation scenario, the weight of the infrared risk coefficient is less than the normal infrared weight, and the weights of the posture risk coefficient and the displacement risk coefficient are greater than the normal posture weight and the normal displacement weight.

[0113] In the static operation scenario, the weights of the infrared risk coefficient and the posture risk coefficient are greater than the normal infrared weight and the normal posture weight, and the weight of the displacement risk coefficient is less than the normal displacement weight.

[0114] In some embodiments, the weighted fusion module 220 is specifically configured to:

[0115] In the case that any one of the infrared risk coefficient, the posture risk coefficient and the displacement risk coefficient is greater than the preset risk threshold, the other two risk coefficients in the preset historical period are acquired;

[0116] If the other two risk coefficients in the preset historical period do not exceed the corresponding preset risk threshold, it is determined that the current situation is normal.

[0117] In some embodiments, the alarm determination module 230 is specifically configured to:

[0118] According to the historical alarm data, the prior probability of the target hook appearing abnormal under different historical comprehensive risk values is determined;

[0119] The confidence of the current comprehensive risk value is determined by using the Bayes formula combined with the prior probability;

[0120] The current alarm level is determined based on the confidence.

[0121] In some embodiments, the alarm determination module 230 is specifically configured to:

[0122] When the comprehensive risk value is located in the first threshold interval, it is determined that the current situation is normal; the maximum value of the first threshold interval is the upper limit of the safety threshold;

[0123] When the comprehensive risk value is located in the second threshold interval, a first-level early warning is triggered; the minimum value of the second threshold interval is greater than the upper limit of the safety threshold;

[0124] When the comprehensive risk value is located in the third threshold interval, a second-level early warning is triggered; the minimum value of the third threshold interval is greater than the maximum value of the second threshold interval.

[0125] It should be noted that the multi-parameter fusion intelligent double-hook safety early warning system provided by the embodiments of the present application and the multi-parameter fusion intelligent double-hook safety early warning method provided by the embodiments of the present application are based on the same application concept, so the specific implementation of this embodiment can be referred to the implementation of the aforementioned multi-parameter fusion intelligent double-hook safety early warning method, and the repeated parts will not be described herein.

[0126] In some embodiments, please refer toFigure 3 , Figure 3 A structural schematic diagram of an electronic device is provided in the embodiments of the present application. The electronic device 300 provided in the embodiments of the present application comprises a processor 310 and a memory 320; the memory 320 stores a computer program, wherein the computer program, when executed by the processor, implements the multi-parameter fusion intelligent double-hook safety early warning method described above.

[0127] Specifically, the processor 310 may, for example, include a general-purpose microprocessor, an instruction set processor, and / or a related chipset, and / or a special-purpose microprocessor (such as an application-specific integrated circuit (ASIC)), etc. The processor 310 can also include on-board memory for cache use. The processor 310 can be a single processing unit or a plurality of processing units for performing different actions of the method process according to the embodiments of the present application.

[0128] The memory 320 may, for example, be any medium capable of containing, storing, communicating, propagating or transmitting instructions. For example, the memory 320 may, but is not limited to, include electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices, devices or propagation media. Specific examples of the memory 320 include magnetic storage devices such as magnetic tapes or hard disk drives (HDDs); optical storage devices such as compact discs (CD-ROMs); and random access memories (RAMs) or flash memories; and / or wired / wireless communication links.

[0129] The present application also provides a computer readable medium having a computer program stored thereon, which, when executed by a processor, implements the multi-parameter fusion intelligent double-hook safety early warning method described above. The computer readable medium can be included in the device / apparatus / system described in the above embodiments; or it can exist separately and not be assembled into the device / apparatus / system. The above computer readable medium carries one or more programs, which, when executed, implement the method according to the embodiments of the present application.

[0130] According to embodiments of the present application, the computer readable medium can be a computer readable signal medium or a computer readable storage medium or any combination thereof. The computer readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, the computer readable storage medium can be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, the computer readable signal medium can include a computer readable program code that can be transmitted or propagated over a computer readable medium, in baseband or as part of a carrier wave. Such a computer readable program code can take many forms, including but not limited to, an electromagnetic signal, an optical signal, or any suitable combination of the foregoing. The computer readable signal medium can also be any computer readable medium that can be transitory, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer readable medium can be transmitted or propagated using any suitable medium, including but not limited to wireless, wired, optical fiber cable, RF, and the like, or any suitable combination of the foregoing.

[0131] It is to be understood that the features mentioned herein can be combined in various ways without departing from the application. Although the application has been described with reference to specific examples, it will be appreciated that the application can be practiced otherwise than is specifically described. For example, the order of various steps can be changed, or replaced or eliminated altogether. It is also possible to use a combination of steps from different examples. It is intended to include all such modifications and alterations insofar as they come within the scope of the appended claims.

Claims

1. A multi-parameter fusion intelligent double-hook safety early warning method, characterized in that, The method comprises: acquiring multi-source detection information of a target hook; the acquiring multi-source detection information of the target hook comprises: acquiring a signal strength difference value corresponding to the target hook by using an infrared pair tube detection unit; acquiring acceleration, angular velocity and inclination angle corresponding to the target hook by using a three-axis attitude sensor; and acquiring a displacement trajectory corresponding to the target hook by using a photoelectric displacement encoder; determining position information of the target hook based on a size relationship between the signal strength difference value and a first threshold value, acquiring an infrared risk coefficient based on the position information, determining attitude stability of the target hook based on size relationships between the acceleration and the angular velocity and second and third threshold values, acquiring an attitude risk coefficient based on the attitude stability, determining a trajectory error of the target hook based on a size relationship between the displacement trajectory and a fourth threshold value, acquiring a displacement risk coefficient based on the trajectory error, and querying a preset weight mapping list in combination with a current detection scene to acquire weights corresponding to the infrared risk coefficient, the attitude risk coefficient and the displacement risk coefficient respectively, and generating a corresponding comprehensive risk value through weighted fusion; the preset weight mapping list comprises a mapping relationship between each risk coefficient and a corresponding weight under different scene categories; determining a current alarm level according to a threshold interval in which the comprehensive risk value is located.

2. The multi-parameter fused smart dual-hook safety warning method of claim 1, wherein, The method further comprises: in a motion operation scene, the weight of the infrared risk coefficient is less than a normal infrared weight, and the weights of the attitude risk coefficient and the displacement risk coefficient are greater than normal attitude and displacement weights; in a static operation scene, the weights of the infrared risk coefficient and the attitude risk coefficient are greater than normal infrared and attitude weights, and the weight of the displacement risk coefficient is less than a normal displacement weight.

3. The multi-parameter fused smart dual-hook safety warning method of claim 1, wherein, The method further comprises: in a case where any one of the infrared risk coefficient, the attitude risk coefficient and the displacement risk coefficient is greater than a preset risk threshold value, acquiring another two risk coefficients in a preset historical period; if the other two risk coefficients in the preset historical period do not exceed corresponding preset risk threshold values, determining that a current situation is normal.

4. The multi-parameter fused smart dual-hook safety warning method of claim 1, wherein, The method further comprises: determining a prior probability that the target hook appears abnormal under different historical comprehensive risk values by performing statistics on historical alarm data; determining a confidence degree of the current comprehensive risk value in combination with the prior probability by using a Bayes formula; determining a current alarm level based on the confidence degree.

5. The multi-parameter fused smart dual-hook safety warning method of claim 4, wherein, The method further comprises: When the comprehensive risk value is located in a first threshold interval, it is determined that the current situation is normal; a maximum value of the first threshold interval is an upper limit of a safety threshold; When the comprehensive risk value is located in a second threshold interval, a first-level warning is triggered; a minimum value of the second threshold interval is greater than the upper limit of the safety threshold; When the comprehensive risk value is located in a third threshold interval, a second-level warning is triggered; a minimum value of the third threshold interval is greater than a maximum value of the second threshold interval.

6. A multi-parameter fusion intelligent double-hook safety warning system, characterized in that, Comprise: An information acquisition module, a weighted fusion module, and an alarm determination module; wherein The information acquisition module is configured to acquire multi-source detection information of a target hook, including: acquiring a signal strength difference value corresponding to the target hook by using an infrared pair tube detection unit; acquiring acceleration, angular velocity, and an inclination angle corresponding to the target hook by using a three-axis attitude sensor; and acquiring a displacement trajectory corresponding to the target hook by using an optical-electric displacement encoder; the weighted fusion module is configured to determine position information of the target hook based on a size relationship between the signal strength difference value and a first threshold value, acquire an infrared risk coefficient based on the position information, determine attitude stability of the target hook based on a size relationship between the acceleration and the angular velocity and a second threshold value and a third threshold value, acquire an attitude risk coefficient based on the attitude stability, determine a trajectory error of the target hook based on a size relationship between the displacement trajectory and a fourth threshold value, acquire a displacement risk coefficient based on the trajectory error, and query a preset weight mapping list in combination with a current detection scene to acquire weights corresponding to the infrared risk coefficient, the attitude risk coefficient, and the displacement risk coefficient respectively, and generate a corresponding comprehensive risk value through weighted fusion; the preset weight mapping list includes a mapping relationship between each risk coefficient and a corresponding weight under different scene categories; The alarm determination module is configured to determine a current alarm level according to a threshold interval in which the comprehensive risk value is located.

7. An electronic device comprising a processor and a memory; said memory having stored a computer program, wherein, The computer program, when executed by the processor, implements the multi-parameter fusion intelligent double-hook safety warning method of any one of claims 1 to 5.

8. A computer storage medium, characterized in that, A computer program is stored thereon, wherein the computer program, when executed by a processor, implements the multi-parameter fusion intelligent double-hook safety warning method of any one of claims 1 to 5.

Images