Design method and system of fall arrestor based on lightweight composite structure and multidirectional locking

Abstract

The present application relates to the technical field of fall arrestor design, and is a fall arrestor design method and system based on a lightweight composite structure and multi-directional locking, comprising: constructing a fall arrest platform based on an original fall arrestor, setting a test environment parameter group, performing a multi-directional locking test on the fall arrest platform based on the test environment parameter group, obtaining a test locking data set, changing the test environment parameter group to obtain a target environment parameter group, and performing a multi-directional locking test again to obtain multiple test locking data sets and multiple test environment parameter groups, training a neural network model using the multiple test locking data sets and the multiple test environment parameter groups to obtain a locking decision model, and embedding the locking decision model into the original fall arrestor to obtain a target fall arrestor. The present application can improve the intelligence level of the fall arrestor and improve the safety of the fall arrestor in complex environments.

Description

Technical Field

[0001] This invention relates to the field of fall arrester design technology, and in particular to a fall arrester design method and system based on a lightweight composite structure and multi-directional locking. Background Technology

[0002] In high-altitude operations, fall arresters are key equipment to ensure the safety of operators. With the development of industries such as construction, power, and communications, high-altitude operation scenarios are becoming increasingly complex and changeable. Operators face various risks such as lateral swaying and wind load impact. Therefore, developing a fall arrester with multi-directional locking and intelligent control has become an urgent need for industry development.

[0003] Traditional fall arrestors mostly use a single traction rope connection method, relying solely on mechanical braking to achieve the locking function. Although this method can achieve basic fall protection, it cannot effectively suppress lateral swaying, making it difficult to guarantee the safety of operators in complex environments. Furthermore, the locking strength of this method is fixed and cannot be dynamically adjusted according to real-time environmental changes, which can easily lead to sudden stop impact or insufficient cushioning. Summary of the Invention

[0004] This invention provides a design method and system for a fall arrester based on a lightweight composite structure and multi-directional locking, the main purpose of which is to improve the intelligence level of the fall arrester and enhance its safety in complex environments.

[0005] To achieve the above objectives, the present invention provides a fall arrestor design method based on a lightweight composite structure and multi-directional locking, comprising:

[0006] Receive the design instructions for the fall arrester, and determine the original fall arrester based on the design instructions. The original fall arrester includes a communication unit, a control unit, and a battery unit, and the original fall arrester is a lightweight composite structure.

[0007] A fall protection platform is constructed based on the original fall protection devices. The fall protection platform includes: the original fall protection device group, the test weight unit, sensors and imaging devices. The sensors include: acceleration sensors, displacement sensors and tension sensors. The original fall protection device group includes three original fall protection devices.

[0008] Set a test environment parameter set, wherein the test environment parameter set includes: ambient wind speed, ambient wind direction and fall height;

[0009] A multi-directional locking test was performed on the fall arrestor platform based on the test environment parameter set, and the test locking dataset was obtained. The test locking dataset includes: sensor dataset, attitude feature dataset and locking strength dataset.

[0010] The test environment parameter set is modified to obtain the target environment parameter set. The target environment parameter set is used as the test environment parameter set, and the steps of performing multi-directional locking test on the fall arrest platform based on the test environment parameter set are returned until a preset stop test command is received.

[0011] The test lockout datasets and test environment parameter groups are summarized separately to obtain multiple test lockout datasets and multiple test environment parameter groups, wherein the test lockout datasets and test environment parameter groups correspond one-to-one;

[0012] A pre-built neural network model is trained using multiple experimental locking datasets and multiple sets of experimental environment parameters to obtain a locking decision model, wherein the output value of the locking decision model is the locking strength group of the original fall arrestor group;

[0013] The locking decision model is embedded into the control unit of the original fall arrester to obtain the target fall arrester. Based on the target fall arrester, a fall arrester design based on a lightweight composite structure and multi-directional locking is completed.

[0014] Optionally, the construction of the fall protection platform based on the original fall arrestor includes:

[0015] The original weight unit is obtained based on the preset test quality;

[0016] Sensors are installed in the original weight unit to obtain the test weight unit, wherein the sensor installation refers to the installation of pre-constructed acceleration sensors and pre-constructed displacement sensors;

[0017] A plurality of the original fall arresters are obtained, and a pre-built tension sensor is installed in each of the plurality of original fall arresters to obtain an original fall arrester group, wherein the original fall arrester group includes three original fall arresters, and each original fall arrester is equipped with a tension sensor.

[0018] Using the pre-acquired traction rope, the original fall arrestor group is connected to the test weight unit to obtain the fall arrestor platform. The original fall arrestor group and the test weight unit are connected by traction ropes, and each original fall arrestor in the original fall arrestor group corresponds to one traction rope.

[0019] Optionally, the process of obtaining the original weight unit based on a preset test quality includes:

[0020] The original weight is obtained based on the test mass, where the mass of the original weight is the test mass;

[0021] A marked weight is obtained by marking the original weight using a preset set of marker points. The set of marker points includes multiple marker points, and the marker points are marked on the surface of the original weight.

[0022] The marked weight is placed in a pre-constructed sealed basket to obtain the original weight unit. The sealed basket is equipped with a camera device that can capture images of one or more of the marked points on the surface of the marked weight.

[0023] Optionally, the multi-directional locking test performed on the fall arrestor platform based on the test environment parameter set yields a test locking dataset, including:

[0024] The fall arrestor platform is installed based on the preset side length of the fall arrestor triangle to obtain the test platform. The side length of the fall arrestor triangle is the side length of the equilateral triangle formed by the original fall arrestor group in the test platform, and the height of the test platform is the fall height.

[0025] Under the test environment parameter set, a drop test was conducted using the test platform to obtain sensor data set, attitude feature data set and locking strength data set. Among them, the locking strength data set includes the side length of the fall arrestor triangle.

[0026] The target fall arrester triangle side length is calculated based on the preset side length change formula and the fall height. The target fall arrester triangle side length is used as the fall arrester triangle side length, and the process returns to the step of installing the fall arrester platform based on the preset fall arrester triangle side length, until the ratio of the fall arrester triangle side length to the fall height is greater than the preset maximum ratio.

[0027] The sensor data set, attitude feature data set, and locking strength data set are merged to obtain the sensor dataset, attitude feature dataset, and locking strength dataset. Based on the sensor dataset, attitude feature dataset, and locking strength dataset, the experimental locking dataset is obtained.

[0028] Optionally, the drop test conducted using the test platform to obtain sensor data sets, attitude feature data sets, and locking strength data sets includes:

[0029] Set the start time of the fall, and based on the start time of the fall, change all the original fall arresters in the original fall arrester group in the test platform from the preset locked state to the preset relaxed state, and record the real-time fall time after the change from the preset locked state to the preset relaxed state.

[0030] The intensity adjustment time is calculated based on the start time of descent and the preset time difference of data acquisition.

[0031] If the real-time drop time is equal to the strength adjustment time, then the locking strength of the test platform is adjusted to obtain the adjustment platform, sensor data, weight posture image and locking strength data;

[0032] The adjustment platform and intensity adjustment time are respectively used as the test platform and the start of the fall. The process is then repeated until the test platform is completely on the ground. When the test platform is completely on the ground, the fall test is completed.

[0033] The intensity adjustment time, sensor data, weight posture image and locking strength data in the drop test are summarized to obtain the intensity adjustment time group, sensor data group, weight posture image group and original locking strength data group. The side length of the fall arrestor triangle is added to the original locking strength data group to obtain the locking strength data group.

[0034] Attitude feature analysis was performed based on the image set of the weight's attitude and the intensity adjustment time set to obtain the attitude feature data set.

[0035] Optionally, the step of adjusting the locking strength of the test platform to obtain the platform adjustment, sensor data, weight posture image, and locking strength data includes:

[0036] Read the sensor data from the test platform, including: current acceleration, current displacement, and current tension of the traction rope.

[0037] Based on sensor data and a preset intensity adjustment function, an adjustable locking intensity group is generated. The adjustable locking intensity group includes three adjustable locking intensities, and each adjustable locking intensity corresponds one-to-one with the original fall arrestor.

[0038] Based on the adjustment of the locking strength group, the strength of the original fall arrestor group in the test platform is adjusted to obtain the adjustment platform;

[0039] The marked weight is photographed using the imaging device in the adjustment platform to obtain an image of the weight's posture.

[0040] Optionally, the step of generating an adjustable locking intensity group based on sensor data and a preset intensity adjustment function includes:

[0041] Extract the original fall arresters sequentially from the original fall arrester group, obtain the current locking strength of the original fall arresters, and determine the current traction rope tension corresponding to the original fall arresters in the current traction rope tension group.

[0042] Set a set of fall thresholds, which includes: acceleration threshold and locking strength threshold;

[0043] The locking strength is adjusted based on the current locking strength, the current acceleration from the sensor data, the current displacement from the sensor data, the current tension of the traction rope, the fall threshold group, and the strength adjustment function.

[0044] The locking strength is adjusted to obtain the locking strength adjustment group.

[0045] Optionally, the posture feature analysis based on the weight posture image set and intensity adjustment time set yields a posture feature data set, including:

[0046] A reference weight image is obtained and recorded as the comparison weight image, wherein the reference weight image is an image taken before the drop test and has a coordinate system;

[0047] Identify the set of contrast markers in the image of the heavy object and obtain the set of contrast coordinates corresponding to the set of contrast markers;

[0048] Extract the current adjustment time from the intensity adjustment time group, and obtain the current attitude image corresponding to the current adjustment time from the weight attitude image group. The current adjustment time is the intensity adjustment time that is ranked first in the intensity adjustment time group.

[0049] Identify the current group of marker points in the current pose image and determine the current coordinate group corresponding to the current group of marker points, wherein the current coordinate group includes one or more current coordinates;

[0050] Based on the current coordinate set and the comparison coordinate set, the attitude of the heavy object is analyzed to obtain the attitude change characteristics;

[0051] Remove the current adjustment time from the intensity adjustment time group to obtain the removed adjustment time group;

[0052] The current pose image and the elimination adjustment time group are respectively used as the comparison weight image and the intensity adjustment time group, and the step of identifying the comparison marker point group in the comparison weight image is returned until the elimination adjustment time group is an empty set.

[0053] The posture change features are summarized to obtain a posture change feature group, which is then denoted as the posture feature data group.

[0054] Optionally, the step of performing attitude analysis on the weight based on the current coordinate set and the comparison coordinate set to obtain attitude change characteristics includes:

[0055] Identify the reference marker point group in the reference weight image and obtain the reference coordinate group corresponding to the reference marker point group;

[0056] In the reference coordinate group, identify the reference coordinate group corresponding to the comparison coordinate group and the current reference coordinate group corresponding to the current coordinate group respectively;

[0057] Calculate the attitude deviation between the reference coordinate group and the reference coordinate group, and the attitude deviation between the current reference coordinate group and the current coordinate group.

[0058] Identify a common coordinate group of the comparison coordinate group in the current coordinate group, wherein the common coordinate group includes: one common coordinate or multiple common coordinates, or the common coordinate group is an empty set;

[0059] Determine whether the comparison attitude deviation value is greater than the current attitude deviation value;

[0060] If the current attitude deviation value is not greater than the comparison attitude deviation value, then the positive attitude change value is calculated based on the common coordinate group and the current coordinate group, where the positive attitude change value is a positive value;

[0061] If the current attitude deviation value is greater than the comparison attitude deviation value, the reverse attitude change value is calculated based on the common coordinate group and the current coordinate group, where the reverse attitude change value is negative.

[0062] The positive attitude change value or the negative attitude change value is recorded as the attitude change feature.

[0063] To achieve the above objectives, the present invention also provides a fall arrestor design system based on a lightweight composite structure and multi-directional locking, comprising:

[0064] The test platform construction module is used to receive the fall arrestor design instructions and determine the original fall arrestor based on the design instructions. The original fall arrestor includes a communication unit, a control unit, and a battery unit. The original fall arrestor is a lightweight composite structure. The fall arrestor platform is constructed based on the original fall arrestor. The fall arrestor platform includes an original fall arrestor group, a test weight unit, sensors, and an imaging device. The sensors include an acceleration sensor, a displacement sensor, and a tension sensor. The original fall arrestor group includes three original fall arrestors.

[0065] The test data acquisition module is used to set the test environment parameter set, which includes: ambient wind speed, ambient wind direction and fall height. Based on the test environment parameter set, a multi-directional locking test is performed on the fall arrest platform to obtain the test locking dataset, which includes: sensor dataset, attitude feature dataset and locking strength dataset.

[0066] The environmental parameter change module is used to modify the test environment parameter group to obtain the target environment parameter group. The target environment parameter group is used as the test environment parameter group, and the steps of performing multi-directional locking test on the fall arrest platform based on the test environment parameter group are returned until a preset stop test command is received. The test locking dataset and the test environment parameter group are summarized respectively to obtain multiple test locking datasets and multiple test environment parameter groups, wherein the test locking datasets correspond one-to-one with the test environment parameter groups.

[0067] The decision model training module is used to train a pre-built neural network model using multiple experimental locking datasets and multiple experimental environment parameter sets to obtain a locking decision model. The output value of the locking decision model is the locking strength group of the original fall arrester group. The locking decision model is embedded into the control unit in the original fall arrester to obtain the target fall arrester.

[0068] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0069] Memory, storing at least one instruction; and

[0070] The processor executes the instructions stored in the memory to implement the aforementioned design method for a fall arrester based on a lightweight composite structure and multi-directional locking.

[0071] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned design method for a fall arrester based on a lightweight composite structure and multi-directional locking.

[0072] To address the problems described in the background art, this invention first employs a lightweight composite structure to assemble the original fall arrestor, significantly reducing its overall weight while maintaining high strength and corrosion resistance. A fall arrest platform comprising multiple original fall arrestors is then constructed. This step utilizes the stability of a triangle to suppress swaying in multiple directions, improving operator safety in complex environments. Next, by setting various test environment parameter sets, different actual working scenarios can be simulated, enriching the diversity of test data and aiding in the training of subsequent neural network models, enabling them to better adapt to various complex working conditions. Finally, multi-directional locking tests are used to obtain a rich experimental locking dataset. This dataset reflects the locking strength of the original fall arrestor under different environments, providing comprehensive data support for the training of subsequent locking decision models and improving model accuracy. To further enhance reliability, the neural network model is trained using multiple experimental locking datasets and multiple sets of experimental environmental parameters to obtain a locking decision model. This locking decision model can quickly and accurately output the optimal locking strength set based on real-time input environmental parameters and sensor data, realizing intelligent control of the fall arrester and improving its safety and adaptability in practical applications. Finally, the locking decision model is embedded into the control unit of the original fall arrester to obtain the target fall arrester. This step of embedding the locking decision model into the control unit of the original fall arrester gives the target fall arrester strong environmental adaptability and intelligent control capabilities. The target fall arrester can automatically adjust the locking strength based on real-time monitored data, effectively improving the safety of operators working at heights and reducing the risk of accidents caused by environmental changes. Therefore, this invention can improve the intelligence level of fall arresters and enhance their safety in complex environments. Attached Figure Description

[0073] Figure 1 A flowchart illustrating a design method for a fall arrester based on a lightweight composite structure and multi-directional locking, provided in an embodiment of the present invention.

[0074] Figure 2 A functional block diagram of a fall arrestor design system based on a lightweight composite structure and multi-directional locking, provided in an embodiment of the present invention;

[0075] Figure 3 This is a schematic diagram of an electronic device that implements the fall arrestor design method based on a lightweight composite structure and multi-directional locking, according to an embodiment of the present invention.

[0076] Explanation of reference numerals in the attached figures:

[0077] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0078] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0079] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0080] This application provides a fall arrester design method based on a lightweight composite structure and multi-directional locking. The execution entity of this fall arrester design method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the fall arrester design method based on a lightweight composite structure and multi-directional locking can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0081] Reference Figure 1 The diagram shown is a flowchart illustrating a fall arrestor design method based on a lightweight composite structure and multi-directional locking, according to an embodiment of the present invention. In this embodiment, the fall arrestor design method based on a lightweight composite structure and multi-directional locking includes:

[0082] S1. Receive the fall arrestor design instructions and determine the original fall arrestor based on the fall arrestor design instructions. The original fall arrestor includes a communication unit, a control unit, and a battery unit, and the original fall arrestor is a lightweight composite structure.

[0083] Understandably, the "fall arrestor design instruction" refers to a human-initiated instruction to design the fall arrestor, and the "original fall arrestor" refers to a fall arrestor that needs optimization and modification. The "communication unit" refers to a wireless signal transceiver module, which can receive instruction signals initiated by the operator and guide the control unit to operate; this communication unit is, for example, a Bluetooth module. The "control unit" refers to a mechanical braking actuator, which can quickly lock the traction rope; this control unit is, for example, an electromagnetic clutch or a hydraulic braking system. The "battery unit" refers to an energy storage device that provides electrical energy to the fall arrestor; optionally, a lithium polymer battery is used as the battery unit. The "lightweight composite structure" refers to a shell structure made of lightweight composite materials, wherein the lightweight composite material refers to carbon fiber reinforced polymer (CFRP), which has the characteristics of high strength, low density, and corrosion resistance. Therefore, using lightweight composite materials as the manufacturing material of this original fall arrestor can significantly reduce the overall weight and improve structural reliability. Optionally, the lightweight composite material is an aramid fiber composite material.

[0084] S2. Construct a fall protection platform based on the original fall protection devices. The fall protection platform includes: the original fall protection device group, the test weight unit, sensors and imaging devices. The sensors include: acceleration sensors, displacement sensors and tension sensors. The original fall protection device group includes three original fall protection devices.

[0085] It is clear that the aforementioned original fall arrestor group refers to a combination of three original fall arrestors, which form an equilateral triangle in practical applications. In existing applications, typically only one traction rope and one fall arrestor are used to connect the operator. While this single-rope connection method can achieve rapid fall prevention in the longitudinal direction, if the operator is subjected to lateral forces resulting in significant lateral swaying, the fall arrestor cannot suppress this lateral swaying, posing a risk of injury to the operator. Therefore, this solution introduces an original fall arrestor group, which includes three original fall arrestors. The three original fall arrestors are positioned to form an equilateral triangle in practical applications. Utilizing the stability of an equilateral triangle, by changing the different locking strengths of the three original fall arrestors, the purpose of suppressing swaying in multiple directions can be achieved.

[0086] Furthermore, due to the triangular structure, the locking strength of each original fall arrester in the original fall arrester group varies. Therefore, for the safety of operators in actual operation, it is necessary to individually control the locking strength of each original fall arrester in the original fall arrester group. The communication unit in each original fall arrester can receive the command corresponding to this individual control (such as the locking strength). The locking strength refers to the magnitude of the braking force applied by the fall arrester to the traction rope. The greater the locking strength, the greater the sliding resistance of the traction rope. The control unit then executes the corresponding action according to the received command. To ensure the accuracy and speed of locking strength control in practical applications, this scheme introduces deep learning computation. By training a neural network using a large number of pre-acquired feature parameters, it obtains the locking strength that each original fall arrester needs to execute in real time, based on parameters obtained from sensor parameters. The parameters obtained from the sensor parameters refer to the multiple experimental locking datasets involved in subsequent steps.

[0087] Specifically, the construction of the fall protection platform based on the original fall arrestor includes:

[0088] The original weight unit is obtained based on the preset test quality;

[0089] Sensors are installed in the original weight unit to obtain the test weight unit, wherein the sensor installation refers to the installation of pre-constructed acceleration sensors and pre-constructed displacement sensors;

[0090] A plurality of the original fall arresters are obtained, and a pre-built tension sensor is installed in each of the plurality of original fall arresters to obtain an original fall arrester group, wherein the original fall arrester group includes three original fall arresters, and each original fall arrester is equipped with a tension sensor.

[0091] Using the pre-acquired traction rope, the original fall arrestor group is connected to the test weight unit to obtain the fall arrestor platform. The original fall arrestor group and the test weight unit are connected by traction ropes, and each original fall arrestor in the original fall arrestor group corresponds to one traction rope.

[0092] Understandably, the test mass refers to a manually set constant, and the original weight unit refers to the object suspended by the original fall arrestor assembly in the fall arrestor platform. The test weight unit refers to the original weight unit after the sensors are installed. Specifically, the accelerometer is a device used to measure the acceleration of the weight's motion, such as a MEMS accelerometer; the displacement sensor is a device used to detect changes in the weight's position, such as a laser displacement sensor; and the tension sensor is a device used to measure the tension of the traction rope, such as a strain gauge tension sensor. The traction rope refers to a high-strength synthetic fiber rope (such as ultra-high molecular weight polyethylene rope) used to connect the fall arrestor assembly to the test weight unit.

[0093] Specifically, the method for obtaining the original weight unit based on a preset test quality includes:

[0094] The original weight is obtained based on the test mass, where the mass of the original weight is the test mass;

[0095] A marked weight is obtained by marking the original weight using a preset set of marker points. The set of marker points includes multiple marker points, and the marker points are marked on the surface of the original weight.

[0096] The marked weight is placed in a pre-constructed sealed basket to obtain the original weight unit. The sealed basket is equipped with a camera device that can capture images of one or more of the marked points on the surface of the marked weight.

[0097] It is clear that the original weight refers to the weight used to simulate the operator carried by the fall arrestor in actual applications, such as a standardized cylindrical steel counterweight (mass 50kg). The markers are identifiable markings attached to the surface of the weight, such as red reflective circular markers, used to track changes in the weight's posture using image analysis algorithms. The sealed basket refers to a closed test container used to isolate external environmental interference and fix the test weight unit. A high-speed industrial camera is installed in this sealed basket to photograph the marked weight. When the fall arrestor platform falls, the posture of the marked weight will change. Since the locking strength of different original fall arrestors in the original fall arrestor group will vary, this photographic device is used to detect the posture of the marked weight during the fall in order to determine the effect of different locking strengths on suppressing the lateral sway during the current fall.

[0098] S3. Set the test environment parameter group, wherein the test environment parameter group includes: ambient wind speed, ambient wind direction and fall height.

[0099] It should be explained that the experimental environment parameter set refers to a combination of multiple constants set by the user. Here, the ambient wind speed refers to a parameter simulating the airflow speed in a real working scenario, which can be changed using a wind tunnel device; the ambient wind direction refers to airflow direction parameters (such as horizontal, vertical, or tilt angle); and the fall height refers to the vertical distance from the initial position of the fall arrestor platform to the landing point. By setting different experimental environment parameter sets, the diversity of data sources in subsequent neural network training can be improved, thereby enabling the locking decision model to adapt to complex and changing actual working conditions.

[0100] S4. Perform a multi-directional locking test on the fall arrestor platform based on the test environment parameter set to obtain the test locking dataset, which includes: sensor dataset, attitude feature dataset and locking strength dataset.

[0101] Understandably, the multi-directional locking test refers to: under a set of environmental parameters (the height of the multi-directional locking test is the fall height, and the wind speed and direction are the ambient wind speed and direction, respectively), allowing the fall arrestor platform to perform free fall motion, and detecting the test locking dataset during this free fall motion. The sensor dataset includes data from multiple sensors, which are parameters collected by various sensors in the fall arrestor platform during the multi-directional locking test. The attitude feature dataset includes multiple attitude feature data, which are numerical values ​​that quantify the attitude change characteristics of the weight during the multi-directional locking test. The locking strength dataset includes multiple locking strength data, which are combinations of locking strengths of the original fall arrestor assembly in the fall arrestor platform at different times during the multi-directional locking test.

[0102] Specifically, the multi-directional locking test performed on the fall arrestor platform based on the test environment parameter set yields a test locking dataset, including:

[0103] The fall arrestor platform is installed based on the preset side length of the fall arrestor triangle to obtain the test platform. The side length of the fall arrestor triangle is the side length of the equilateral triangle formed by the original fall arrestor group in the test platform, and the height of the test platform is the fall height.

[0104] Under the test environment parameter set, a drop test was conducted using the test platform to obtain sensor data set, attitude feature data set and locking strength data set. Among them, the locking strength data set includes the side length of the fall arrestor triangle.

[0105] The target fall arrester triangle side length is calculated based on the preset side length change formula and the fall height. The target fall arrester triangle side length is used as the fall arrester triangle side length, and the process returns to the step of installing the fall arrester platform based on the preset fall arrester triangle side length, until the ratio of the fall arrester triangle side length to the fall height is greater than the preset maximum ratio.

[0106] The sensor data set, attitude feature data set, and locking strength data set are merged to obtain the sensor dataset, attitude feature dataset, and locking strength dataset. Based on the sensor dataset, attitude feature dataset, and locking strength dataset, the experimental locking dataset is obtained.

[0107] Understandably, the test platform refers to the fall arrestor platform after installation, and the fall test refers to free fall motion. The formula for the change in side length is as follows: L m = L0 + a × H, where L m The target fall arrester triangle side length is represented by L0, the fall arrester triangle side length is represented by 'a', and an adjustable coefficient (optionally set to 0.05) is represented by 'H', where H represents the fall height. The target fall arrester triangle side length refers to the calculated side length of the fall arrester triangle. The maximum ratio refers to a manually set constant.

[0108] Furthermore, since the installation position of the original fall arrestor assembly (i.e., the side length of the fall arrestor triangle) will affect the effectiveness of the fall arrestor to a certain extent, the purpose of this step is to obtain the effect of the fall arrestor under different installation positions.

[0109] Specifically, the drop test conducted using the test platform yields sensor data sets, attitude characteristic data sets, and locking strength data sets, including:

[0110] Set the start time of the fall, and based on the start time of the fall, change all the original fall arresters in the original fall arrester group in the test platform from the preset locked state to the preset relaxed state, and record the real-time fall time after the change from the preset locked state to the preset relaxed state.

[0111] The intensity adjustment time is calculated based on the start time of descent and the preset time difference of data acquisition.

[0112] If the real-time drop time is equal to the strength adjustment time, then the locking strength of the test platform is adjusted to obtain the adjustment platform, sensor data, weight posture image and locking strength data;

[0113] The adjustment platform and intensity adjustment time are respectively used as the test platform and the start of the fall. The process is then repeated until the test platform is completely on the ground. When the test platform is completely on the ground, the fall test is completed.

[0114] The intensity adjustment time, sensor data, weight posture image and locking strength data in the drop test are summarized to obtain the intensity adjustment time group, sensor data group, weight posture image group and original locking strength data group. The side length of the fall arrestor triangle is added to the original locking strength data group to obtain the locking strength data group.

[0115] Attitude feature analysis was performed based on the image set of the weight's attitude and the intensity adjustment time set to obtain the attitude feature data set.

[0116] It should be explained that the "start of descent time" refers to the manually set time to begin the descent test. The "locked state" refers to the mode where the fall arrestor completely restricts the movement of the traction rope, and the "relaxed state" refers to the mode where the fall arrestor allows the traction rope to slide freely. The locking strength corresponding to the locked state is the maximum strength, and the locking strength corresponding to the relaxed state is 0. The "acquisition time difference" refers to the manually set time difference between two parameter acquisitions. The "strength adjustment time" refers to the time obtained by adding the acquisition time difference to the start of descent time. The "adjustment platform" refers to the test platform after locking strength adjustment. The "weight attitude image" refers to the image of the marked weight captured by the imaging device when the real-time descent time equals the strength adjustment time. The "attitude feature analysis" refers to the operation of extracting the weight's attitude features from the midday attitude image.

[0117] In detail, the process of adjusting the locking strength of the test platform to obtain the platform, sensor data, weight posture image, and locking strength data includes:

[0118] Read the sensor data from the test platform, including: current acceleration, current displacement, and current tension of the traction rope.

[0119] Based on sensor data and a preset intensity adjustment function, an adjustable locking intensity group is generated. The adjustable locking intensity group includes three adjustable locking intensities, and each adjustable locking intensity corresponds one-to-one with the original fall arrestor.

[0120] Based on the adjustment of the locking strength group, the strength of the original fall arrestor group in the test platform is adjusted to obtain the adjustment platform;

[0121] The marked weight is photographed using the imaging device in the adjustment platform to obtain an image of the weight's posture.

[0122] It is clear that the current acceleration refers to the instantaneous acceleration value of the test weight at the moment of strength adjustment; the current displacement refers to the distance the test weight has moved relative to its initial position (the position before falling); and the current traction rope tension refers to the magnitude of the tension borne by a single traction rope. The adjusted locking strength refers to the locking strength generated by the strength adjustment function.

[0123] Specifically, the generation of the adjustable locking strength group based on sensor data and a preset intensity adjustment function includes:

[0124] Extract the original fall arresters sequentially from the original fall arrester group, obtain the current locking strength of the original fall arresters, and determine the current traction rope tension corresponding to the original fall arresters in the current traction rope tension group.

[0125] Set a set of fall thresholds, which includes: acceleration threshold and locking strength threshold;

[0126] The locking strength is adjusted based on the current locking strength, the current acceleration from the sensor data, the current displacement from the sensor data, the current tension of the traction rope, the fall threshold group, and the strength adjustment function.

[0127] The locking strength is adjusted to obtain the locking strength adjustment group.

[0128] Understandably, the current locking strength refers to the locking strength at the moment of strength adjustment, and the current traction rope tension refers to the current traction rope tension corresponding to the original fall arrestor in the current traction rope tension group. The acceleration threshold, displacement threshold, and locking strength threshold refer to the maximum values ​​set manually for acceleration, displacement, and locking strength, respectively.

[0129] Specifically, the intensity adjustment function includes:

[0130]

[0131] Among them, F Q Q represents the intensity adjustment function. d This indicates the current locking strength, and T indicates the current tension of the traction rope. Q represents the average value of all original traction rope tensions in the original traction rope tension group. max This represents the lock-in strength threshold, and 'a' represents the current acceleration. max K represents the acceleration threshold, s represents the current displacement, and K represents the acceleration threshold.T K a and K s These represent the preset tension coefficient, acceleration coefficient, and displacement coefficient, respectively.

[0132] It is clear that the tension coefficient, acceleration coefficient, and displacement coefficient mentioned above refer to artificially set weighting constants related to the tension, acceleration, and displacement of the traction rope. In the strength adjustment function: by setting... This allows the locking strength to be automatically reduced when the acceleration approaches a dangerous threshold (i.e., the acceleration threshold), preventing the operator from being subjected to sudden stop shock. This can be achieved by setting... The locking strength can be gradually increased as the descent depth increases to ensure end-of-fall cushioning.

[0133] In detail, the posture feature analysis based on the weight posture image group and intensity adjustment time group yields a posture feature data group, including:

[0134] A reference weight image is obtained and recorded as the comparison weight image, wherein the reference weight image is an image taken before the drop test and has a coordinate system;

[0135] Identify the set of contrast markers in the image of the heavy object and obtain the set of contrast coordinates corresponding to the set of contrast markers;

[0136] Extract the current adjustment time from the intensity adjustment time group, and obtain the current attitude image corresponding to the current adjustment time from the weight attitude image group. The current adjustment time is the intensity adjustment time that is ranked first in the intensity adjustment time group.

[0137] Identify the current group of marker points in the current pose image and determine the current coordinate group corresponding to the current group of marker points, wherein the current coordinate group includes one or more current coordinates;

[0138] Based on the current coordinate set and the comparison coordinate set, the attitude of the heavy object is analyzed to obtain the attitude change characteristics;

[0139] Remove the current adjustment time from the intensity adjustment time group to obtain the removed adjustment time group;

[0140] The current pose image and the elimination adjustment time group are respectively used as the comparison weight image and the intensity adjustment time group, and the step of identifying the comparison marker point group in the comparison weight image is returned until the elimination adjustment time group is an empty set.

[0141] The posture change features are summarized to obtain a posture change feature group, which is then denoted as the posture feature data group.

[0142] It is understood that the comparison marker group includes multiple comparison markers, and each comparison marker refers to a marker in the marker group contained in the comparison weight image. The comparison coordinates refer to the coordinate values ​​of the comparison markers. The current attitude image refers to the weight attitude image captured at the current adjustment time. The current marker group includes multiple current markers, and each current marker refers to a marker in the marker group contained in the current attitude image. The current coordinates refer to the coordinate values ​​of the current markers in the current attitude image. The attitude change feature refers to a numerical value that quantifies the degree of attitude change of the marked weight between the comparison image and the current image. If the attitude change feature is positive, it indicates that the attitude of the marked weight in the current image has a positive change compared to the attitude in the comparison image. A positive change means that the attitude of the marked weight is close to that in the reference image, indicating that the adjusted locking strength group has a positive effect on suppressing the swaying of the weight. The larger the positive value, the greater the positive effect. Conversely, if the attitude change feature is negative, it indicates that the attitude of the marked weight in the current image has a negative change compared to the attitude in the comparison image, indicating that the adjusted locking strength group has a negative effect on suppressing the swaying of the weight. If the current adjusted locking strength group is maintained, the lateral swaying of the marked weight will become increasingly severe. To enable the subsequent neural network model to learn the influence of different locking strengths on the weight's attitude, it is necessary to obtain the attitude change feature so that the neural network model can output the adjusted locking strength group with a positive effect.

[0143] Understandably, the elimination adjustment time group refers to the intensity adjustment time after the current adjustment time has been eliminated.

[0144] In detail, the process of performing attitude analysis on the weight based on the current coordinate set and the comparison coordinate set to obtain attitude change characteristics includes:

[0145] Identify the reference marker point group in the reference weight image and obtain the reference coordinate group corresponding to the reference marker point group;

[0146] In the reference coordinate group, identify the reference coordinate group corresponding to the comparison coordinate group and the current reference coordinate group corresponding to the current coordinate group respectively;

[0147] Calculate the attitude deviation between the reference coordinate group and the reference coordinate group, and the attitude deviation between the current reference coordinate group and the current coordinate group.

[0148] Identify a common coordinate group of the comparison coordinate group in the current coordinate group, wherein the common coordinate group includes: one common coordinate or multiple common coordinates, or the common coordinate group is an empty set;

[0149] Determine whether the comparison attitude deviation value is greater than the current attitude deviation value;

[0150] If the current attitude deviation value is not greater than the comparison attitude deviation value, then the positive attitude change value is calculated based on the common coordinate group and the current coordinate group, where the positive attitude change value is a positive value;

[0151] If the current attitude deviation value is greater than the comparison attitude deviation value, the reverse attitude change value is calculated based on the common coordinate group and the current coordinate group, where the reverse attitude change value is negative.

[0152] The positive attitude change value or the negative attitude change value is recorded as the attitude change feature.

[0153] It is clear that the reference marker point group refers to the group of marker points in the reference weight image, and the reference coordinate group refers to the combination of coordinate values ​​corresponding to the reference marker point group. The comparison reference coordinate group refers to the combination of coordinates of the same marker points in the reference coordinate group and the comparison coordinate group. For example, if the reference coordinate group is: (coordinates of marker point 1 in the reference weight image: A, coordinates of marker point 2 in the reference weight image: B), and the comparison coordinate group is: (coordinates of marker point 2 in the comparison weight image: C), then the comparison reference coordinate group is: (coordinates of marker point 2 in the reference weight image: B). The current reference coordinate group refers to the combination of coordinates of the same marker points in the reference coordinate group and the current coordinate group. The comparison attitude deviation value refers to the numerical value that quantifies the difference in the attitude of the marked weight in the reference weight image and the comparison weight image. The larger the comparison attitude deviation value, the greater the difference in the attitude of the marked weight in the reference weight image and the comparison weight image. The current attitude deviation value refers to the numerical value that quantifies the difference in the attitude of the marked weight in the reference weight image and the current weight image. The common coordinate group refers to the combination of coordinates in the current coordinate group that have the same marked points as the comparison coordinate group.

[0154] It should be explained that if the current attitude deviation value is not greater than the comparison attitude deviation value, it means that under the action of adjusting the locking strength group, the difference between the attitude of the marked weight and the attitude of the marked weight in the reference weight image becomes smaller. That is, the current adjustment of the locking strength group has a positive effect on suppressing the lateral sway of the marked weight. In other words, the attitude change characteristic at this time is a positive number, which can be recorded as a positive attitude change value. Conversely, if the current attitude deviation value is greater than the comparison attitude deviation value, it means that the current adjustment of the locking strength group has a negative effect on suppressing the lateral sway of the marked weight. That is, the attitude change characteristic at this time is a negative number, which can be recorded as a negative attitude change value.

[0155] Specifically, the calculation of the comparison attitude deviation value between the comparison reference coordinate set and the comparison coordinate set includes:

[0156] The attitude deviation value is calculated using the following formula:

[0157]

[0158] Among them, P d This represents the comparison attitude deviation value, where N represents the number of reference coordinates in the reference coordinate group, and m represents the number of comparison reference coordinates in the comparison reference coordinate group or the number of comparison coordinates in the comparison coordinate group. This represents the x-coordinate of the i-th reference coordinate in the reference coordinate group. This represents the x-coordinate of the i-th coordinate in the comparison coordinate set. This represents the ordinate of the i-th reference coordinate in the reference coordinate group. This represents the ordinate of the i-th comparison coordinate group in the comparison coordinate group;

[0159] Understandably, the method for calculating the current attitude deviation between the current reference coordinate group and the current coordinate group is the same as the method for calculating the comparative attitude deviation.

[0160] Specifically, the calculation of the positive attitude change value based on the common coordinate set and the current coordinate set includes:

[0161] The positive attitude change value is calculated using the following formula, including:

[0162]

[0163] Among them, P z This represents the positive attitude change value, where n represents the number of common coordinate groups in the common coordinate group or the number of current coordinates in the current coordinate group. and Let x and y represent the x and y coordinates of the j-th common coordinate in the common coordinate set, respectively. and These represent the x-coordinate and y-coordinate of the j-th current coordinate in the current coordinate group, respectively.

[0164] S5. Modify the test environment parameter group to obtain the target environment parameter group, use the target environment parameter group as the test environment parameter group, and return to the step of performing a multi-directional locking test on the fall arrest platform based on the test environment parameter group until a preset stop test command is received.

[0165] Understandably, to make the experimental lockout dataset more diverse and comprehensive, the experimental environment parameter set can be modified. The method of modification is determined manually, and the target environment parameter set will have different values ​​for different application environments. The stop-test command refers to a manually initiated command to stop the test.

[0166] S6. Summarize the test lockout dataset and test environment parameter group respectively to obtain multiple test lockout datasets and multiple test environment parameter groups, wherein the test lockout datasets and test environment parameter groups correspond one-to-one.

[0167] It is clear that since the experimental environment parameter set has a significant impact on the determination of the locking strength, it is necessary to use the experimental environment parameter set as one of the training data for the subsequent training of the neural network model.

[0168] S7. Train the pre-built neural network model using multiple test locking datasets and multiple test environment parameter sets to obtain a locking decision model, wherein the output value of the locking decision model is the locking strength group of the original fall arrestor group.

[0169] It should be explained that the neural network model refers to a machine learning model used to establish the mapping relationship between input parameters and output locking strength. In this scheme, a multilayer perceptron (MLP) or a long short-term memory network (LSTM) can be selected as the neural network model. The locking decision model can directly output the locking strength group corresponding to the original fall arrestor group based on the input set of test environment parameters, acceleration, displacement, tension, and the side length of the fall arrestor triangle.

[0170] S8. Embed the locking decision model into the control unit of the original fall arrester to obtain the target fall arrester, and complete the design of a fall arrester based on a lightweight composite structure and multi-directional locking based on the target fall arrester.

[0171] To clarify, embedding the locking decision model into the control unit of the original fall arrester refers to compiling the trained neural network model (i.e., the locking decision model) into embedded code and burning it into the microprocessor of the control unit. By embedding the locking decision model into the original fall arrester, the original fall arrester can automatically change the locking strength based on real-time collected data. The target fall arrester refers to the original fall arrester after the locking decision model has been embedded. For example, an operator needs to perform a task at a height. The operator is suspended at a height by a target fall arrestor assembly. The operator wears an acceleration sensor and a displacement sensor. The side length of the equilateral triangle formed by the target fall arrestor assembly is known (denoted as the actual side length). Relevant personnel measure the current ambient wind speed, ambient wind direction, and the required descent height. During the descent, the acceleration sensor and displacement sensor will collect the actual acceleration and actual displacement in real time. During this process, the communication unit in the target fall arrestor will receive the actual acceleration and actual displacement. The locking decision model embedded in the control unit can output the locking strength of each target fall arrestor in real time based on the actual acceleration, actual displacement, ambient wind speed, ambient wind direction, descent height, and actual side length, thereby completing intelligent multi-directional locking.

[0172] To address the problems described in the background art, this invention first employs a lightweight composite structure to assemble the original fall arrestor, significantly reducing its overall weight while maintaining high strength and corrosion resistance. A fall arrest platform comprising multiple original fall arrestors is then constructed. This step utilizes the stability of a triangle to suppress swaying in multiple directions, improving operator safety in complex environments. Next, by setting various test environment parameter sets, different actual working scenarios can be simulated, enriching the diversity of test data and aiding in the training of subsequent neural network models, enabling them to better adapt to various complex working conditions. Finally, multi-directional locking tests are used to obtain a rich experimental locking dataset. This dataset reflects the locking strength of the original fall arrestor under different environments, providing comprehensive data support for the training of subsequent locking decision models and improving model accuracy. To further enhance reliability, the neural network model is trained using multiple experimental locking datasets and multiple sets of experimental environmental parameters to obtain a locking decision model. This locking decision model can quickly and accurately output the optimal locking strength set based on real-time input environmental parameters and sensor data, realizing intelligent control of the fall arrester and improving its safety and adaptability in practical applications. Finally, the locking decision model is embedded into the control unit of the original fall arrester to obtain the target fall arrester. This step of embedding the locking decision model into the control unit of the original fall arrester gives the target fall arrester strong environmental adaptability and intelligent control capabilities. The target fall arrester can automatically adjust the locking strength based on real-time monitored data, effectively improving the safety of operators working at heights and reducing the risk of accidents caused by environmental changes. Therefore, this invention can improve the intelligence level of fall arresters and enhance their safety in complex environments.

[0173] like Figure 2 The diagram shown is a functional block diagram of a fall arrestor design system based on a lightweight composite structure and multi-directional locking, provided by an embodiment of the present invention.

[0174] The fall arrestor design system 100 based on a lightweight composite structure and multi-directional locking described in this invention can be installed in an electronic device. Depending on the functions implemented, the fall arrestor design system 100 may include a test platform construction module 101, a test data acquisition module 102, an environmental parameter change module 103, and a decision model training module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, stored in the memory of the electronic device.

[0175] The test platform construction module 101 is used to receive fall arrestor design instructions and determine the original fall arrestor based on the fall arrestor design instructions. The original fall arrestor includes a communication unit, a control unit, and a battery unit. The original fall arrestor is a lightweight composite structure. A fall arrestor platform is constructed based on the original fall arrestor. The fall arrestor platform includes an original fall arrestor group, a test weight unit, sensors, and an imaging device. The sensors include an acceleration sensor, a displacement sensor, and a tension sensor. The original fall arrestor group includes three original fall arrestors.

[0176] The test data acquisition module 102 is used to set a test environment parameter group, which includes: ambient wind speed, ambient wind direction and fall height. Based on the test environment parameter group, a multi-directional locking test is performed on the fall arrest platform to obtain a test locking dataset, which includes: sensor dataset, attitude feature dataset and locking strength dataset.

[0177] The environmental parameter change module 103 is used to modify the test environment parameter group to obtain the target environment parameter group, use the target environment parameter group as the test environment parameter group, and return to the step of performing a multi-directional locking test on the fall arrest platform based on the test environment parameter group until a preset stop test command is received. The test locking dataset and the test environment parameter group are summarized respectively to obtain multiple test locking datasets and multiple test environment parameter groups, wherein the test locking datasets correspond one-to-one with the test environment parameter groups.

[0178] The decision model training module 104 is used to train a pre-constructed neural network model using multiple experimental locking datasets and multiple experimental environment parameter groups to obtain a locking decision model. The output value of the locking decision model is the locking strength group of the original fall arrester group. The locking decision model is embedded into the control unit in the original fall arrester to obtain the target fall arrester.

[0179] In detail, the modules in the fall arrester design system 100 based on a lightweight composite structure and multi-directional locking described in this embodiment of the invention employ the same principles as described above during use. Figure 1 The design method of the lightweight composite structure and multi-directional locking fall arrestor described in the article uses the same technical means and can produce the same technical effect, so it will not be repeated here.

[0180] like Figure 3 The diagram shown is a structural schematic of an electronic device that implements a fall arrestor design method based on a lightweight composite structure and multi-directional locking, according to an embodiment of the present invention.

[0181] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a design method program for a fall arrester based on a lightweight composite structure and multi-directional locking.

[0182] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as code for a fall arrester design method based on a lightweight composite structure and multi-directional locking, but also to temporarily store data that has been output or will be output.

[0183] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a design method program for a fall arrester based on a lightweight composite structure and multi-directional locking), and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0184] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0185] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0186] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, thereby enabling functions such as charging management, discharging management, and power consumption management through the power management system. The power supply may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0187] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0188] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0189] The program for a fall arrester design method based on a lightweight composite structure and multi-directional locking, stored in the memory 11 of the electronic device 1, is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0190] Receive the design instructions for the fall arrester, and determine the original fall arrester based on the design instructions. The original fall arrester includes a communication unit, a control unit, and a battery unit, and the original fall arrester is a lightweight composite structure.

[0191] A fall protection platform is constructed based on the original fall protection devices. The fall protection platform includes: the original fall protection device group, the test weight unit, sensors and imaging devices. The sensors include: acceleration sensors, displacement sensors and tension sensors. The original fall protection device group includes three original fall protection devices.

[0192] Set a test environment parameter set, wherein the test environment parameter set includes: ambient wind speed, ambient wind direction and fall height;

[0193] A multi-directional locking test was performed on the fall arrestor platform based on the test environment parameter set, and the test locking dataset was obtained. The test locking dataset includes: sensor dataset, attitude feature dataset and locking strength dataset.

[0194] The test environment parameter set is modified to obtain the target environment parameter set. The target environment parameter set is used as the test environment parameter set, and the steps of performing multi-directional locking test on the fall arrest platform based on the test environment parameter set are returned until a preset stop test command is received.

[0195] The test lockout datasets and test environment parameter groups are summarized separately to obtain multiple test lockout datasets and multiple test environment parameter groups, wherein the test lockout datasets and test environment parameter groups correspond one-to-one;

[0196] A pre-built neural network model is trained using multiple experimental locking datasets and multiple sets of experimental environment parameters to obtain a locking decision model, wherein the output value of the locking decision model is the locking strength group of the original fall arrestor group;

[0197] The locking decision model is embedded into the control unit of the original fall arrester to obtain the target fall arrester. Based on the target fall arrester, a fall arrester design based on a lightweight composite structure and multi-directional locking is completed.

[0198] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0199] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0200] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0201] Receive the design instructions for the fall arrester, and determine the original fall arrester based on the design instructions. The original fall arrester includes a communication unit, a control unit, and a battery unit, and the original fall arrester is a lightweight composite structure.

[0202] A fall protection platform is constructed based on the original fall protection devices. The fall protection platform includes: the original fall protection device group, the test weight unit, sensors and imaging devices. The sensors include: acceleration sensors, displacement sensors and tension sensors. The original fall protection device group includes three original fall protection devices.

[0203] Set a test environment parameter set, wherein the test environment parameter set includes: ambient wind speed, ambient wind direction and fall height;

[0204] A multi-directional locking test was performed on the fall arrestor platform based on the test environment parameter set, and the test locking dataset was obtained. The test locking dataset includes: sensor dataset, attitude feature dataset and locking strength dataset.

[0205] The test environment parameter set is modified to obtain the target environment parameter set. The target environment parameter set is used as the test environment parameter set, and the steps of performing multi-directional locking test on the fall arrest platform based on the test environment parameter set are returned until a preset stop test command is received.

[0206] The test lockout datasets and test environment parameter groups are summarized separately to obtain multiple test lockout datasets and multiple test environment parameter groups, wherein the test lockout datasets and test environment parameter groups correspond one-to-one;

[0207] A pre-built neural network model is trained using multiple experimental locking datasets and multiple sets of experimental environment parameters to obtain a locking decision model, wherein the output value of the locking decision model is the locking strength group of the original fall arrestor group;

[0208] The locking decision model is embedded into the control unit of the original fall arrester to obtain the target fall arrester. Based on the target fall arrester, a fall arrester design based on a lightweight composite structure and multi-directional locking is completed.

[0209] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0210] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0211] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0212] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0213] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A design method of a fall arrestor based on lightweight composite structure and multidirectional locking, characterized in that, The method comprises: receiving a fall protector design instruction, determining an original fall protector based on the fall protector design instruction, wherein the original fall protector comprises a communication unit, a control unit and a battery unit, and the original fall protector is a lightweight composite structure; constructing a fall protection platform based on the original fall protector, wherein the fall protection platform comprises an original fall protector group, a test weight unit, a sensor and a camera, the sensor comprises an acceleration sensor, a displacement sensor and a tension sensor, and the original fall protector group comprises three original fall protectors, which are arranged in an equilateral triangle in actual application; setting a test environment parameter group, wherein the test environment parameter group comprises environmental wind speed, environmental wind direction and falling height; performing a multi-directional locking test on the fall protection platform based on the test environment parameter group to obtain a test locking data set, wherein the test locking data set comprises a sensor data set, an attitude feature data set and a locking strength data set; the step of performing a multi-directional locking test on the fall protection platform based on the test environment parameter group to obtain a test locking data set comprises: installing the fall protection platform based on a preset fall protector triangle side length to obtain a test platform, wherein the fall protector triangle side length is the side length of the equilateral triangle formed by the original fall protector group in the test platform, and the height of the position of the test platform is the falling height; performing a falling test on the test platform under the test environment parameter group to obtain a sensor data set, an attitude feature data set and a locking strength data set, wherein the locking strength data set includes the fall protector triangle side length; calculating a target fall protector triangle side length based on a preset side length change formula and the falling height, taking the target fall protector triangle side length as the fall protector triangle side length, and returning to the step of installing the fall protection platform based on the preset fall protector triangle side length until the ratio of the fall protector triangle side length to the falling height is greater than a preset maximum ratio; merging the sensor data set, the attitude feature data set and the locking strength data set respectively to obtain a sensor data set, an attitude feature data set and a locking strength data set, and obtaining a test locking data set based on the sensor data set, the attitude feature data set and the locking strength data set; changing the test environment parameter group to obtain a target environment parameter group, taking the target environment parameter group as the test environment parameter group, and returning to the step of performing a multi-directional locking test on the fall protection platform based on the test environment parameter group until a preset stop test instruction is received; summarizing the test locking data set and the test environment parameter group respectively to obtain a plurality of test locking data sets and a plurality of test environment parameter groups, wherein the test locking data set and the test environment parameter group correspond one by one; training a pre-constructed neural network model using the plurality of test locking data sets and the plurality of test environment parameter groups to obtain a locking decision model, wherein the output value of the locking decision model is a locking strength group of the original fall protector group; embedding the locking decision model into the control unit in the original fall protector to obtain a target fall protector, and completing the fall protector design based on the lightweight composite structure and the multi-directional locking based on the target fall protector.

2. The design method of a fall arrestor based on lightweight composite structure and multidirectional locking as claimed in claim 1, wherein, the step of constructing a fall protection platform based on the original fall protector comprises: obtaining an original weight unit based on a preset test mass; installing a sensor in the original weight unit to obtain a test weight unit, wherein the sensor installation refers to installing a pre-constructed acceleration sensor and a pre-constructed displacement sensor; obtaining a plurality of original arresters, and installing a pre-constructed tension sensor in each of the plurality of original arresters to obtain an original arrester group, wherein the original arrester group includes three original arresters, and each of the original arresters is installed with a tension sensor; connecting the original arrester group to the test weight unit by using a pre-obtained traction rope to obtain an arrestment platform, wherein the original arrester group and the test weight unit are connected by the traction rope, and each of the original arresters in the original arrester group corresponds to a traction rope.

3. The method of designing a fall arrestor based on lightweight composite structure and multidirectional locking as claimed in claim 2, wherein, The original weight unit is obtained based on a preset test mass, comprising: obtaining an original weight based on a test mass, wherein the mass of the original weight is the test mass; marking the original weight by using a pre-set marker point group to obtain a marked weight, wherein the marker point group includes a plurality of marker points, and the marker points are marked on the surface of the original weight; placing the marked weight in a pre-constructed closed basket to obtain an original weight unit, wherein a shooting device is installed in the closed basket, and the shooting device can shoot one or more marker points in the marker point group on the surface of the marked weight.

4. The method of designing a fall arrestor based on lightweight composite structure and multidirectional locking as claimed in claim 3, wherein, The falling test is performed by using the test platform to obtain a sensor data group, an attitude feature data group, and a locking strength data group, comprising: setting a starting falling time, and based on the starting falling time, changing all original arresters in the original arrester group in the test platform from a preset locking state to a preset relaxed state, and recording a real-time falling time after the change from the preset locking state to the preset relaxed state; calculating a strength adjustment time according to the starting falling time and a preset collection time difference; if the real-time falling time is equal to the strength adjustment time, adjusting the locking strength of the test platform to obtain an adjusted platform, sensor data, weight attitude images, and locking strength data; taking the adjusted platform and the strength adjustment time as the test platform and the starting falling time respectively, and returning to the step of calculating the strength adjustment time according to the starting falling time and the preset collection time difference, until the test platform completely lands, and the falling test is completed when the test platform completely lands; collecting the strength adjustment time, the sensor data, the weight attitude images, and the locking strength data in the falling test respectively to obtain a strength adjustment time group, a sensor data group, a weight attitude image group, and an original locking strength data group, and supplementing an arrester triangle side length to the original locking strength data group to obtain a locking strength data group; performing attitude feature analysis based on the weight attitude image group and the strength adjustment time group to obtain an attitude feature data group.

5. The design method of a fall arrestor based on lightweight composite structure and multidirectional locking as claimed in claim 4, wherein, The locking strength of the test platform is adjusted to obtain an adjusted platform, sensor data, weight attitude images, and locking strength data, comprising: reading sensor data in the test platform, wherein the sensor data includes: current acceleration, current displacement, and current traction rope tension group; Generate an adjusted locking strength set based on sensor data and a preset strength adjustment function, wherein the adjusted locking strength set includes three adjusted locking strengths, and each adjusted locking strength corresponds to an original fall arrester; Adjust the strength of the original fall arrester set in the test platform according to the adjusted locking strength set to obtain an adjusted platform; Use a shooting device in the adjusted platform to shoot the marked heavy object to obtain a heavy object posture image.

6. The method of designing a fall arrestor based on lightweight composite structure and multidirectional locking as claimed in claim 5, wherein, The generation of the adjusted locking strength set based on the sensor data and the preset strength adjustment function includes: Extract the original fall arresters in the original fall arrester set in turn, obtain the current locking strength of the original fall arrester, and determine the current traction rope tension corresponding to the original fall arrester in the current traction rope tension set; Set a falling threshold set, wherein the falling threshold set includes an acceleration threshold and a locking strength threshold; Calculate the adjusted locking strength according to the current locking strength, the current acceleration in the sensor data, the current displacement in the sensor data, the current traction rope tension, the falling threshold set, and the strength adjustment function; Summarize the adjusted locking strengths to obtain the adjusted locking strength set.

7. The design method of a fall arrestor based on lightweight composite structure and multidirectional locking as claimed in claim 6, wherein, The posture feature analysis based on the heavy object posture image set and the strength adjustment time set to obtain the posture feature data set includes: Obtain a reference heavy object image and record the reference heavy object image as a comparison heavy object image, wherein the reference heavy object image is an image taken before the falling test, and has a coordinate system in the reference heavy object image; Identify the comparison marker point set in the comparison heavy object image and obtain the comparison coordinate set corresponding to the comparison marker point set; Extract the current adjustment time in the strength adjustment time set and obtain the current posture image corresponding to the current adjustment time in the heavy object posture image set, wherein the current adjustment time is the strength adjustment time arranged at the first position in the strength adjustment time set; Identify the current marker point set in the current posture image and determine the current coordinate set corresponding to the current marker point set, wherein the current coordinate set includes one or more current coordinates; Based on the current coordinate set and the comparison coordinate set, analyze the heavy object posture to obtain the posture change feature; Remove the current adjustment time from the strength adjustment time set to obtain a removed adjustment time set; Take the current posture image and the removed adjustment time set as the comparison heavy object image and the strength adjustment time set, respectively, and return to the step of identifying the comparison marker point set in the comparison heavy object image until the removed adjustment time set is empty; Summarize the posture change features to obtain a posture change feature set, and record the posture change feature set as the posture feature data set.

8. The method of designing a fall arrestor based on lightweight composite structure and multidirectional locking as claimed in claim 7, wherein, The heavy object posture analysis based on the current coordinate set and the comparison coordinate set to obtain the posture change feature includes: Identify the reference marker point set in the reference heavy object image and obtain the reference coordinate set corresponding to the reference marker point set; Identify the comparison reference coordinate set corresponding to the comparison coordinate set and the current reference coordinate set corresponding to the current coordinate set in the reference coordinate set, respectively; Calculate the comparison posture deviation value between the comparison reference coordinate set and the comparison coordinate set, and the current posture deviation value between the current reference coordinate set and the current coordinate set, respectively; identifying a common coordinate set of the contrast coordinate set in the current coordinate set, wherein the common coordinate set comprises one common coordinate or a plurality of common coordinates, or the common coordinate set is an empty set; determining whether the contrast attitude deviation value is greater than the current attitude deviation value; if the current attitude deviation value is not greater than the contrast attitude deviation value, calculating a positive attitude change value based on the common coordinate set and the current coordinate set, wherein the positive attitude change value is a positive value; if the current attitude deviation value is greater than the contrast attitude deviation value, calculating a negative attitude change value based on the common coordinate set and the current coordinate set, wherein the negative attitude change value is a negative value; record the positive attitude change value or the negative attitude change value as an attitude change feature.

9. A system for designing a fall arrestor based on a lightweight composite structure and multidirectional locking, using the method according to any one of claims 1 to 8, characterized in that, The system comprises: The test platform construction module is used for receiving a fall protector design instruction, determining an original fall protector based on the fall protector design instruction, wherein the original fall protector comprises a communication unit, a control unit and a battery unit, and the original fall protector is a lightweight composite structure, and constructing a fall platform based on the original fall protector, wherein the fall platform comprises an original fall protector group, a test heavy object unit, a sensor and a shooting device, the sensor comprises an acceleration sensor, a displacement sensor and a tension sensor, and the original fall protector group comprises three original fall protectors; The test data acquisition module is used for setting a test environment parameter set, wherein the test environment parameter set comprises an environmental wind speed, an environmental wind direction and a falling height, performing a multi-directional locking test on the fall platform based on the test environment parameter set to obtain a test locking data set, wherein the test locking data set comprises a sensor data set, an attitude feature data set and a locking strength data set; The environmental parameter change module is used for changing the test environment parameter set to obtain a target environment parameter set, taking the target environment parameter set as the test environment parameter set, and returning to the step of performing the multi-directional locking test on the fall platform based on the test environment parameter set until a preset stop test instruction is received, respectively summarizing the test locking data set and the test environment parameter set to obtain a plurality of test locking data sets and a plurality of test environment parameter sets, wherein the test locking data set and the test environment parameter set correspond one by one; The decision model training module is used for training a pre-constructed neural network model using a plurality of test locking data sets and a plurality of test environment parameter sets to obtain a locking decision model, wherein the output value of the locking decision model is a locking strength set of the original fall protector group, and the locking decision model is embedded into the control unit in the original fall protector to obtain a target fall protector.

Images