Worker tumble detection system, method and device and medium

Abstract

The invention provides a worker falling detection system, method and device and a medium, and belongs to the technical field of falling detection. The system comprises a motion sensor module, a microprocessor module, a communication module and a power supply module. The method comprises the following steps: acquiring acceleration data of a worker in a motion posture in real time through a motion sensor module; transmitting the acceleration data to a microprocessor module, and performing interference elimination processing on the acceleration data by using a Kalman filtering algorithm; judging whether the worker falls down or not according to the processed acceleration data; and if falling is detected, alarm information is sent to related personnel of the construction site through the communication module. According to the invention, comprehensive motion data of a worker in different postures can be obtained in real time, advanced Kalman filtering algorithm is used to carry out deep processing on acceleration data, various interference factors are effectively eliminated, and high-accuracy fall detection is realized.

Description

Technical Field

[0001] The invention relates to a worker fall detection system, method, device and medium, belonging to the technical field of fall detection. Background Art

[0002] With the acceleration of industrialization, workers' safety in the working environment has received increasing attention. Especially in high-altitude operations, heavy machinery operations and complex production environments, workers often fall due to various reasons (such as physical fatigue, operating errors, environmental changes, etc.). These accidental falls not only affect the health and safety of workers, but may also bring economic losses and legal risks to the company. Therefore, it is particularly important to develop a detection system that can monitor workers' behavior in real time, accurately judge and promptly report fall events.

[0003] Traditional fall detection systems mostly use a single sensor, such as an accelerometer or a pressure sensor. Although such systems can identify falls to a certain extent, they are limited by the limitations of sensor types and insufficient algorithm processing capabilities, and their detection accuracy and reliability are often unsatisfactory. For example, a single accelerometer is easily disturbed by external environmental vibrations and workers' daily movements (such as running and jumping), resulting in a high false alarm rate; while a single pressure sensor cannot effectively distinguish between falls and other changes in body posture. Summary of the invention

[0004] The purpose of the present invention is to provide a worker fall detection system, method, device and medium, which can accurately and timely determine whether a worker has fallen, and actively send alarm information to relevant personnel on the construction site.

[0005] In order to achieve the above object, the present invention is implemented through the following technical solutions: A worker fall detection system, comprising: Motion sensor module, used to obtain acceleration data of workers in motion posture in real time; The microprocessor module is connected to the motion sensor module and is used to receive and process acceleration data and perform interference elimination processing on the acceleration data through a Kalman filter algorithm; A communication module, connected to the microprocessor module, is used to send an alarm message to relevant personnel on the construction site when a worker falls; The power module provides power support for the entire system.

[0006] Preferably, the motion sensor module adopts an MPU9250 nine-axis sensor, the microprocessor module adopts an STM32F103C8T6 microprocessor, and the communication module adopts a SIM800A communication module.

[0007] Preferably, the microprocessor module also includes an SD card module for storing sensor data, and a configuration module for system initialization, wherein the configuration module performs clock, GPIO, IIC initialization configuration, and reset initialization of the MPU9250 motion sensor and SIM800A communication module after the system is powered on.

[0008] Preferably, when processing acceleration data, the Kalman filter algorithm, for a nonlinear system, uses Taylor's formula to convert nonlinear data into approximate linear data before performing filtering processing.

[0009] A method for detecting a worker falling, comprising: The motion sensor module is used to obtain the acceleration data of the worker's motion posture in real time; The acceleration data is transmitted to the microprocessor module, and the acceleration data is subjected to interference elimination processing using the Kalman filter algorithm; Determine whether a worker has fallen based on the processed acceleration data; If a fall is detected, an alarm message is sent to relevant personnel on the construction site through the communication module.

[0010] Preferably, when processing a nonlinear system, the Kalman filter algorithm uses the Taylor formula to convert nonlinear data into approximate linear data and then performs filtering processing.

[0011] Preferably, the specific method of using Taylor's formula to convert nonlinear data into approximate linear data is as follows: Obtain nonlinear acceleration data; Select a reference point for linearization, which is a maximum value, a minimum value, or a midpoint of the data; Calculate the acceleration and its derivative at the reference point; Establish a linearized acceleration model, use Taylor's formula for linearization, and use the first-order term of Taylor expansion to obtain a linear approximate model of acceleration; Calculate linearized data, use the linearized model to calculate approximate acceleration values, and obtain linearized acceleration data; Replace or compare original data, compare linearized data to original nonlinear acceleration data, or use linearized data directly in model analysis.

[0012] A device for worker fall detection comprises a processor and a memory storing program instructions, wherein the processor is configured to execute the worker fall detection method when running the program instructions.

[0013] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method for detecting worker falls.

[0014] The advantages of the present invention are that the system of the present invention can obtain the comprehensive motion data of workers in different postures in real time, and use advanced Kalman filtering algorithm to deeply process the acceleration data, effectively eliminate various interference factors, and achieve high-accuracy fall detection.

[0015] In order to further improve the detection accuracy and adaptability of the system, the present invention introduces the Taylor formula in the design to perform linearization processing of nonlinear systems, solving the application problem of the Kalman filter algorithm in nonlinear systems. In addition, by collecting a large amount of acceleration data under different actions, the system model is continuously improved and optimized, and the automatic learning and adaptive functions of the system are realized, so that good detection performance can be maintained in different working environments and personal behavior characteristics. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0017] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] A worker fall detection system uses the MPU9250 nine-axis sensor to obtain acceleration data in different postures, obtains workers' behavior data information in real time, uses a microprocessor to process and analyze the data obtained by the sensor, and uses the Kalman filter algorithm to eliminate acceleration interference data. Through a large number of experiments, the three-axis acceleration data in different postures are obtained. The system can use this data to determine whether the worker has fallen, and send text messages to notify relevant personnel on the construction site to provide safety protection for the workers.

[0020] include: Motion sensor module, used to obtain acceleration data of workers in motion posture in real time; The microprocessor module is connected to the motion sensor module and is used to receive and process acceleration data and perform interference elimination processing on the acceleration data through a Kalman filter algorithm; A communication module, connected to the microprocessor module, is used to send an alarm message to relevant personnel on the construction site when a worker falls; The power module provides power support for the entire system.

[0021] As a refinement of the above embodiment, the motion sensor module adopts the MPU9250 nine-axis sensor, the microprocessor module adopts the STM32F103C8T6 microprocessor, and the communication module adopts the SIM800A communication module.

[0022] As a refinement of the above embodiment, the microprocessor module also includes an SD card module for storing sensor data, and a configuration module for system initialization. After the system is powered on, the configuration module performs clock, GPIO, IIC initialization configuration, and reset initialization of the MPU9250 motion sensor and SIM800A communication module.

[0023] As a refinement of the above embodiment, when processing acceleration data, the Kalman filter algorithm, for a nonlinear system, uses the Taylor formula to convert nonlinear data into approximate linear data before performing filtering processing.

[0024] The system operation process is as follows: Initialization, after the system is powered on, it first enters the system initialization startup. The startup process mainly includes the initialization configuration of the STM32 microprocessor (clock, GPIO, IIC, etc.), the reset initialization of the MPU9250 motion sensor, and the initialization of the SIM800A communication module.

[0025] Human body data reading, collects data generated by human body movement through MPU9250 sensor, receives data length through three serial ports, and displays human body movement data on three axes.

[0026] Preprocessing, the STM32F103C8T6 microprocessor is connected to the MPU9250 motion sensor, and the data in the sensor is read through the IIC bus. The MPU9250 motion sensor is responsible for real-time acquisition of acceleration data generated during human motion behavior, and transmits it to the microprocessor through the IIC bus. When actually collecting and acquiring data, there will be many interference factors. When actually collecting data, due to the influence of mechanical vibration, high-frequency noise points will be generated in the collected human motion data, which will have a significant impact on the performance of the acceleration and gyroscope, and will reduce the accuracy of system detection. Therefore, the use of the Kalman filter algorithm to perform denoising and filtering on the data collected by the system can improve the accuracy of the fall detection system.

[0027] Example 2 A method for detecting a worker falling, comprising: S1: Obtain the acceleration data of workers in motion posture in real time through the motion sensor module; S2: Transmit the acceleration data to the microprocessor module and use the Kalman filter algorithm to eliminate interference from the acceleration data; S3: Determine whether the worker falls based on the processed acceleration data; S4: If a fall is detected, an alarm message is sent to relevant personnel on the construction site through the communication module.

[0028] As a refinement of the above embodiment, the acceleration data of workers under different actions are detected by the system's nine-axis motion sensor, and the data is transmitted to the microprocessor to process the data using the Kalman filter algorithm; in order to reduce model dependence, it is necessary to collect a large amount of acceleration data under different actions, such as falling, walking, running, jumping, going up and down stairs, bending over, sitting up, etc. Falling is divided into the occurrence of falling, the falling stage, the impact stage, and the recovery stage. It is also necessary to test the acceleration data of these actions under different weather environments, and the acceleration data of these actions under different genders and age groups.

[0029] As a refinement of the above embodiment, the Kalman filter algorithm in the microprocessor performs interference elimination processing on the human motion data obtained by the sensor and then records it in the SD card. After obtaining these large amounts of data, first check whether the obtained data is linear data. If it is nonlinear, use the optimization idea to first use the Taylor formula to take the values ​​of these data nearby to obtain an anti-linear system. Then process the model dependency. After these large amounts of data obtain the anti-linear system, use these linear data to make models under different postures. In the code, it is implemented to allow the system to automatically realize the conversion of these models after obtaining different acceleration data. No manual conversion is required to finally realize the interference elimination of human motion data using the Kalman filter algorithm.

[0030] Specifically, the method of using Taylor's formula to convert nonlinear data into approximate linear data is as follows: Obtain nonlinear acceleration data; Select a reference point for linearization, which is a maximum value, a minimum value, or a midpoint of the data; Calculate the acceleration and its derivative at the reference point; Establish a linearized acceleration model, use Taylor's formula for linearization, and use the first-order term of Taylor expansion to obtain a linear approximate model of acceleration; Calculate linearized data and use the linearized model to calculate approximate acceleration values , and obtain the linearized acceleration data; the public statement is as follows: , is the acceleration, is the acceleration and its first-order derivative with respect to time, For time, as a reference point.

[0031] Replace or compare original data, compare linearized data to original nonlinear acceleration data, or use linearized data directly in model analysis.

[0032] This linearization process can simplify the complexity in many engineering problems and make nonlinear systems easier to analyze in a local area.

[0033] Examples: = 2 seconds, acceleration a(2)=5m / s2; (i.e. the rate of change of acceleration with time at t=2) According to the linearization formula, the linearized acceleration at t = 3 seconds is: .

[0034] The above example uses Taylor's formula to approximate a nonlinear system to a linear system. Therefore, in this design, if the data is nonlinear after the nine-axis sensor obtains the acceleration, this method can be used to linearize the data.

[0035] The embodiment of the present disclosure also provides a device for worker fall detection, including a processor and a memory. Optionally, the device may also include a communication interface and a bus. The processor, the communication interface, and the memory may communicate with each other through the bus. The communication interface may be used for information transmission. The processor may call the logic instructions in the memory to execute the method for worker fall detection of the above embodiment.

[0036] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0037] The memory, as a computer-readable storage medium, can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor executes the function application and data processing by running the program instructions / modules stored in the memory, that is, implementing the method for detecting worker falls in the above embodiment.

[0038] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory may include a high-speed random access memory and may also include a non-volatile memory.

[0039] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned method for detecting a worker fall.

[0040] The computer-readable storage medium mentioned above may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0041] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A worker fall detection system, characterized in that: include: Motion sensor module, used to obtain acceleration data of workers in motion posture in real time; The microprocessor module is connected to the motion sensor module and is used to receive and process acceleration data and perform interference elimination processing on the acceleration data through a Kalman filter algorithm; A communication module, connected to the microprocessor module, is used to send an alarm message to relevant personnel on the construction site when a worker falls; The power module provides power support for the entire system.

2. The worker fall detection system according to claim 1, characterized in that: The motion sensor module adopts the MPU9250 nine-axis sensor, the microprocessor module adopts the STM32F103C8T6 microprocessor, and the communication module adopts the SIM800A communication module.

3. The worker fall detection system according to claim 1, characterized in that: The microprocessor module also includes an SD card module for storing sensor data, and a configuration module for system initialization. After the system is powered on, the configuration module performs clock, GPIO, IIC initialization configuration, and reset initialization of the MPU9250 motion sensor and SIM800A communication module.

4. The worker fall detection system according to claim 1, characterized in that: When processing acceleration data, the Kalman filter algorithm, for a nonlinear system, uses the Taylor formula to convert nonlinear data into approximate linear data before performing filtering processing.

5. A method for detecting worker falls using the system according to any one of claims 1 to 4, characterized in that: include: The motion sensor module is used to obtain the acceleration data of the worker's motion posture in real time; The acceleration data is transmitted to the microprocessor module, and the acceleration data is subjected to interference elimination processing using the Kalman filter algorithm; Determine whether a worker has fallen based on the processed acceleration data; If a fall is detected, an alarm message is sent to relevant personnel on the construction site through the communication module.

6. The method for detecting worker falls according to claim 5, characterized in that: When dealing with nonlinear systems, the Kalman filter algorithm uses the Taylor formula to convert nonlinear data into approximate linear data and then performs filtering.

7. The method for detecting worker falls according to claim 6, characterized in that: The specific method of using Taylor's formula to convert nonlinear data into approximate linear data is as follows: Obtain nonlinear acceleration data; Select a reference point for linearization, which is a maximum value, a minimum value, or a midpoint of the data; Calculate the acceleration and its derivative at the reference point; Establish a linearized acceleration model, use Taylor's formula for linearization, and use the first-order term of Taylor expansion to obtain a linear approximate model of acceleration; Calculate linearized data, use the linearized model to calculate approximate acceleration values, and obtain linearized acceleration data; Replace or compare original data, compare linearized data to original nonlinear acceleration data, or use linearized data directly in model analysis.

8. A device for detecting a worker falling, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the method for worker fall detection as described in any one of claims 1-6 when running the program instructions.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the method as described in any one of claims 1 to 6 is implemented.

Images