Forklift framework safety detection system based on ultrasonic waves

Abstract

The invention discloses a forklift framework safety detection system based on ultrasonic waves. According to the system, by using the ultrasonic sensor module, the system can accurately detect the defects, such as cracks and abrasion, of the forklift framework, and potential faults and accidents can be prevented. And the data analysis module is particularly beneficial to the performance of the whole system, and has the following specific beneficial effects that the signal filtering module smoothes an ultrasonic signal through a first-order low-pass filter, so that noise interference is reduced, and the signal quality is improved. And the signal enhancement module further enhances the visual effect of the signal through denoising, gain control and signal segmentation, thereby facilitating more accurate identification of signal features. The machine learning prediction module predicts the safety degree of the forklift framework through historical data, predictive maintenance can be achieved, the accidental shutdown time is shortened, the service life of a forklift is prolonged, a decision whether maintenance or shutdown is needed or not is rapidly made through comparison with a preset safety standard, and the operation efficiency and safety are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of forklift frame detection systems, and in particular relates to an ultrasonic-based forklift frame safety detection system. Background Art

[0002] Forklift skeleton safety inspection refers to the regular inspection of the forklift body structure, main load-bearing components and safety protection devices to ensure that they are safe and reliable during use. Forklift skeleton safety inspection is a key link to ensure the safe operation of forklifts, and is of great significance for preventing accidents and protecting the lives and property of operators. Through forklift skeleton safety inspection, the safety risks of forklifts in use can be effectively reduced and the safety level of enterprise production can be improved. At the same time, the test results also provide an important basis for the repair and maintenance of forklifts. In short, forklift skeleton safety inspection is an important means to ensure the safe operation of forklifts. Enterprises should attach great importance to the safety inspection of forklift skeletons to ensure that forklifts serve production safely and stably. In the future, with the development of science and technology, forklift skeleton safety inspection will be more intelligent and convenient, providing strong guarantee for the development of my country's logistics industry.

[0003] However, existing technologies may not integrate data analysis modules, especially machine learning prediction modules, so they cannot use historical data to predict potential failures, and can only perform post-fault troubleshooting rather than prevention. At the same time, in terms of signal processing, existing technologies may lack effective signal amplification, filtering and conversion methods, resulting in noise interference on the detection signal, affecting the accuracy of the detection results. Summary of the invention

[0004] The purpose of the present invention is to provide a forklift frame safety detection system based on ultrasound in order to solve the above-mentioned problems.

[0005] The technical solution adopted by the present invention is as follows: a forklift skeleton safety detection system based on ultrasonic wave, the system comprises: an ultrasonic sensor module, a signal processing module, a data analysis module, an alarm and display module, a communication module and a power management module;

[0006] The data analysis module is internally provided with a signal filtering module, a signal enhancement module, a machine learning prediction module and a data transmission module;

[0007] The transmitter of the ultrasonic sensor module is connected to the trigger circuit of the signal processing module;

[0008] The receiver of the ultrasonic sensor module is connected to the signal input end of the signal processing module;

[0009] The amplifier of the signal processing module receives the signal from the ultrasonic receiver and outputs it to the filter;

[0010] The filter of the signal processing module receives the signal from the amplifier and outputs it to the ADC; the ADC converts the filtered analog signal into a digital signal and outputs it to the data analysis module;

[0011] The data analysis module receives the digital signal from the ADC, performs calculation and analysis, and outputs the result to the alarm and display module;

[0012] The alarm and display module receives the data and alarm signal from the data analysis module and drives the alarm and display screen;

[0013] The communication module receives data from the alarm and display module and sends it to the remote monitoring system wirelessly or wiredly;

[0014] The power management module provides necessary power to all the above modules to ensure stable operation of the system.

[0015] In a preferred embodiment, the ultrasonic sensor module is composed of an ultrasonic transmitter and a receiver. The transmitter is responsible for transmitting ultrasonic waves of a certain frequency, which will generate echoes when encountering defects in the forklift frame; the receiver captures these echoes and converts them into electrical signals; the operating mechanism of the module is to monitor any changes in the frame by continuously or periodically transmitting and receiving ultrasonic waves; in terms of structure, it includes an ultrasonic probe, a transmitting / receiving circuit and a control unit;

[0016] The ultrasonic transmitter uses TCT40-16T ultrasonic transmitting transducer, which has a center frequency of 40kHz and is suitable for detecting defects in metal structures;

[0017] The ultrasonic receiver uses a TCT40-16R ultrasonic receiving transducer, which matches the transmitter and is used to receive reflected waves;

[0018] The control unit uses an STM32F103RCT6 microcontroller to control the timing of transmission and reception and data processing.

[0019] In a preferred embodiment, the signal processing module optimizes the signal collected by the sensor module; it includes an amplifier, a filter and an ADC; the amplifier enhances the strength of the signal, the filter removes unnecessary noise, and the ADC converts the analog signal into a digital signal;

[0020] The amplifier uses AD825 operational amplifier, which has high gain and low noise characteristics and is suitable for amplifying weak ultrasonic signals;

[0021] The filter adopts MAX291 switched capacitor filter, which can provide low-pass, high-pass, band-pass and band-stop filtering functions;

[0022] The ADC uses the ADS1255 24-bit ADC.

[0023] In a preferred embodiment, the signal filtering module uses a first-order low-pass filter to smooth the ultrasonic signal; first, a LowPassFilter class is defined, which includes a method filter for applying a first-order low-pass filter; then, an instance is created and used to process a series of ultrasonic sampling data;

[0024] The specific steps include:

[0025] The first step is to use the first-order low-pass filter technology to obtain the filter configuration result by initializing the filter parameters according to the sampling rate of the ultrasonic signal and the filter cutoff frequency data;

[0026] The second step is to use the first-order low-pass filter technology to filter each sampling point based on the collected ultrasonic sampling data, and obtain the filtered ultrasonic signal data;

[0027] Step 3: Using Python programming language, according to the filtered ultrasonic signal data, the filtered data array is obtained by traversing the data array and applying the filter method of the filter instance to process each sample;

[0028] Step 4: Output the filtered data array obtained in step 3 for further data analysis or processing.

[0029] In a preferred embodiment, the signal enhancement module includes denoising, gain control and signal segmentation; the Python programming language is used, and a NumPy array containing ultrasonic signal data is set, and two signal processing techniques are used: Weiner filter and Savitzky-Golay filter, which are used for denoising and smoothing signals respectively; the dynamic range of the signal is adjusted by calculating the average value of the signal and performing normalized gain, thereby enhancing the visual effect of the signal;

[0030] The specific steps include:

[0031] S301, using a Weiner filter to perform denoising on the original ultrasonic signal; the Weiner filter is an adaptive filter that adjusts the filter parameters according to the local characteristics of the signal to effectively remove random noise in the signal;

[0032] S302. The denoised signal may have some uneven areas, so the window length and window type are set, and the denoised signal is smoothed using a Savitzky-Golay filter; the Savitzky-Golay filter is a method for local polynomial fitting of data points in the time domain, which well preserves the shape and trend of the signal while reducing the impact of noise;

[0033] S303, in order to further adjust the strength of the signal, the average value of the smoothed signal is calculated and normalized to obtain an enhanced signal; this means that each point in the signal will be adjusted according to its difference from the average value to improve the contrast and distinguishability of the signal;

[0034] S304: This helps to analyze different features of the signal or perform local processing on the signal.

[0035] In a preferred embodiment, the machine learning prediction module uses historical data and machine learning technology to predict the safety level of the forklift frame, specifically:

[0036] S401, reading historical data from a CSV file, the data including forklift operation time, load size, ambient temperature, forklift maintenance record and vibration level;

[0037] S402, taking the safety degree of the forklift frame as the evaluation index, storing the evaluation index as features in the variable "features", and storing the safety degree of the forklift frame as the target variable in the variable "target";

[0038] S403, converting the features and target variables into numerical types for algorithm processing; if there are missing values ​​in the data, they need to be processed, including filling or deleting the missing values;

[0039] S404, dividing the data set into a training set and a test set according to a set ratio (8:2);

[0040] S405, creating a linear regression model and storing it in the variable "model"; using the training set to train the linear regression model to obtain a trained linear regression model;

[0041] S406, inputting the ultrasonic forklift skeleton safety detection data into the trained linear regression model, and obtaining the linear relationship of the ultrasonic forklift skeleton safety detection through operation;

[0042] S407, using the obtained linear relationship to predict the features of the test set, and storing the prediction results in the variable "predictions";

[0043] S408, calculating the difference between the actual safety level of the forklift skeleton of the test set and the predicted safety level of the forklift skeleton, obtaining the prediction error, and using the mean square error as an error evaluation indicator;

[0044] S409: Input the safety degree data of the forklift frame into the trained linear regression model to obtain the safety degree prediction result of the forklift frame.

[0045] In a preferred embodiment, the data transmission module uses an API or data transmission tool provided by a cloud service provider to transmit data from the skeleton safety detection device to the cloud, and creates a database or file storage bucket in a cloud storage account to store the data; the data is stored in unstructured data.

[0046] In a preferred embodiment, when the data analysis module detects a potential safety problem, the alarm system will immediately issue a warning, which is a sound, visual signal or a combination of the two; at the same time, the display screen will provide real-time detection data to help the operator understand the status of the forklift frame; the operation of this module depends on sensor data and alarm logic, and its composition includes an alarm device and a display screen;

[0047] The alarm device uses PCF8574T I / O expander, with buzzer and LED light, to realize sound and light alarm;

[0048] The display uses a 4.3-inch LCD display, Atrimoni AT043TN24 model, to display real-time data and system status.

[0049] In a preferred embodiment, the system of the communication module can remotely transmit the detection data and alarm information to the monitoring center; it realizes data transmission by wireless or wired means; the composition of the communication module includes a wireless or wired communication interface, a modem and a related communication protocol stack;

[0050] The wireless communication interface uses the ESP8266 Wi-Fi module, supports TCP / IP protocol, and realizes remote data transmission;

[0051] The wired communication interface uses an RJ45 Ethernet interface and is paired with a WIZnetW5100 network chip to achieve a stable network connection.

[0052] In a preferred embodiment, the power management module provides a stable power supply for the entire system to ensure that the system can operate normally under various working conditions; it includes a power adapter, a power distributor and a backup battery management system;

[0053] The power adapter uses a MeanWell RSP-300-12 switching power supply, which provides a 12V DC output;

[0054] The power distributor uses the LM2596S step-down module to provide stable 5V or 3.3V power to different modules;

[0055] The battery management system uses a Texas Instruments BQ24725 battery charging and management IC.

[0056] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0057] 1. In the present invention, by using an ultrasonic sensor module, the system can accurately detect defects in the forklift frame, such as cracks and wear, which helps prevent potential failures and accidents. The data analysis module is particularly beneficial to the performance of the entire system, and the following are its specific beneficial effects: The signal filtering module smoothes the ultrasonic signal through a first-order low-pass filter, reduces noise interference, and improves signal quality. The signal enhancement module further enhances the visual effect of the signal through denoising, gain control, and signal segmentation, which helps to more accurately identify signal features. The machine learning prediction module uses historical data to predict the safety level of the forklift frame, which can achieve predictive maintenance, reduce unexpected downtime, and extend the service life of the forklift. The data analysis module can monitor the status of the forklift frame in real time, and by comparing with the preset safety standards, quickly make decisions on whether maintenance or shutdown is required, thereby improving operating efficiency and safety.

[0058] 2. In the present invention, when the data analysis module detects a potential safety problem, the alarm and display module can immediately issue a warning and provide real-time data, so that the operator can take prompt action to avoid accidents. Remote monitoring and data transmission: The communication module allows the system to remotely transmit detection data and alarm information to the monitoring center, which is convenient for centralized management and record keeping, and improves management efficiency and response speed. Power management and system stability: The power management module ensures the stable operation of the system under various working conditions, whether it is powered by an external power supply or a backup battery, to ensure the continuous availability of the system. Thereby, the system improves the accuracy and reliability of the detection signal and reduces false alarms and missed alarms. Through predictive analysis, preventive maintenance is achieved, reducing maintenance costs and downtime. Real-time monitoring and rapid response improve the safety management level of the work site. It provides a scientific basis for the safety assessment of the forklift frame and helps to formulate reasonable maintenance plans and strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 is the overall system block diagram of the present invention;

[0060] Figure 2 This is a system block diagram of the data analysis module in the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0062] Reference Figure 1-2 ,

[0063] Example:

[0064] A forklift frame safety detection system based on ultrasonic wave, the system comprises: an ultrasonic sensor module, a signal processing module, a data analysis module, an alarm and display module, a communication module and a power management module;

[0065] The data analysis module is internally provided with a signal filtering module, a signal enhancement module, a machine learning prediction module and a data transmission module;

[0066] Transmitter of Ultrasonic Sensor Module: Connected to the trigger circuit of the signal processing module.

[0067] Receiver of the ultrasonic sensor module: connected to the signal input terminal of the signal processing module.

[0068] Amplifier of the signal processing module: receives the signal from the ultrasonic receiver and outputs it to the filter.

[0069] The filter of the signal processing module receives the signal from the amplifier and outputs it to the ADC. The ADC converts the filtered analog signal into a digital signal and outputs it to the data analysis module.

[0070] The data analysis module receives the digital signal from the ADC, performs calculation and analysis, and outputs the result to the alarm and display module.

[0071] The alarm and display module receives the data and alarm signals from the data analysis module and drives the alarm and display screen.

[0072] The communication module receives data from the alarm and display module and sends it to the remote monitoring system via wireless or wired means.

[0073] The power management module provides necessary power for all the above modules to ensure stable operation of the system.

[0074] The ultrasonic sensor module consists of an ultrasonic transmitter and a receiver. The transmitter is responsible for emitting ultrasonic waves of a certain frequency. These waves will generate echoes when they encounter defects in the forklift frame. The receiver captures these echoes and converts them into electrical signals. The operating mechanism of this module is to monitor any changes in the frame by continuously or periodically emitting and receiving ultrasonic waves. In terms of structure, it includes an ultrasonic probe, a transmitting / receiving circuit, and a control unit;

[0075] The ultrasonic transmitter uses a TCT40-16T ultrasonic transmitting transducer, which has a center frequency of 40kHz and is suitable for detecting defects in metal structures.

[0076] The ultrasonic receiver uses a TCT40-16R ultrasonic receiving transducer, which matches the transmitter and is used to receive reflected waves.

[0077] The control unit uses an STM32F103RCT6 microcontroller to control the timing of transmission and reception and data processing.

[0078] The signal processing module optimizes the signals collected by the sensor module. It contains amplifiers, filters, and ADCs. The amplifiers enhance the signal strength, the filters remove unnecessary noise, and the ADCs convert analog signals into digital signals for subsequent analysis. The operation of this module depends on precise electrical signal processing, and its components include electronic amplifiers, digital filters, and analog-to-digital conversion hardware;

[0079] The amplifier uses AD825 operational amplifier, which has high gain and low noise characteristics and is suitable for amplifying weak ultrasonic signals.

[0080] The filter adopts MAX291 switched capacitor filter, which can provide low-pass, high-pass, band-pass and band-stop filtering functions.

[0081] The ADC uses the ADS1255 24-bit ADC, which has high resolution and low noise, suitable for accurate signal conversion.

[0082] The signal filtering module uses a first-order low-pass filter to smooth the ultrasonic signal. First, a LowPassFilter class is defined, which contains a method filter for applying a first-order low-pass filter. Then, an instance is created and used to process a series of ultrasonic sampling data.

[0083] The specific steps include:

[0084] The first step is to use the first-order low-pass filter technology, according to the sampling rate of the ultrasonic signal and the cutoff frequency data of the filter, and obtain the configuration result of the filter by initializing the filter parameters; the second step is based on the result of the first step, using the first-order low-pass filter technology, according to the collected ultrasonic sampling data, filtering each sampling point through the filter to obtain the filtered ultrasonic signal data.

[0085] The third step is to use Python programming language to obtain the filtered data array by traversing the data array and applying the filter method of the filter instance to process each sample according to the filtered ultrasonic signal data.

[0086] Step 4: Output the filtered data array obtained in step 3 for further data analysis or processing.

[0087] The signal enhancement module includes denoising, gain control and signal segmentation. The Python programming language is used, and a NumPy array containing ultrasonic signal data is set. Two signal processing techniques are used: Weiner filter and Savitzky-Golay filter, which are used for denoising and smoothing signals respectively. The dynamic range of the signal is adjusted by calculating the average value of the signal and performing normalized gain, thereby enhancing the visual effect of the signal.

[0088] The specific steps include:

[0089] S301, using a Wiener filter to perform denoising on the original ultrasonic signal; the Wiener filter is an adaptive filter that can adjust the filter parameters according to the local characteristics of the signal to effectively remove random noise in the signal;

[0090] S302. The denoised signal may have some uneven areas, so the window length and window type are set, and the denoised signal is smoothed using a Savitzky-Golay filter; the Savitzky-Golay filter is a method for local polynomial fitting of data points in the time domain, which can well preserve the shape and trend of the signal while reducing the impact of noise;

[0091] S303, in order to further adjust the strength of the signal, the average value of the smoothed signal is calculated and normalized to obtain an enhanced signal; this means that each point in the signal will be adjusted according to its difference from the average value to improve the contrast and distinguishability of the signal;

[0092] S304: This helps to analyze different features of the signal or perform local processing on the signal.

[0093] The machine learning prediction module uses historical data and machine learning technology to predict the safety level of the forklift frame. The specific contents are as follows:

[0094] S401, reading historical data from a CSV file, the data including operating time, load size, ambient temperature, maintenance records, and vibration level;

[0095] S402, using the skeleton safety form as evaluation indicators, storing the evaluation indicators as features in the variable "features", and storing the forklift skeleton safety detection degree as a target variable in the variable "target";

[0096] S403, convert the features and target variables into numerical types so that the algorithm can process them; if there are missing values ​​in the data, they need to be processed, such as filling or deleting the missing values;

[0097] S404, dividing the data set into a training set and a test set according to a set ratio (8:2);

[0098] S405, creating a linear regression model and storing it in the variable "model"; using the training set to train the linear regression model to obtain a trained linear regression model;

[0099] S406, inputting the ultrasonic forklift skeleton safety detection data into the trained linear regression model, and obtaining the linear relationship of the ultrasonic forklift skeleton safety detection through operation;

[0100] S407, using the obtained linear relationship to predict the features of the test set, and storing the prediction results in the variable "predictions";

[0101] S408, calculating the difference between the actual safety level of the forklift skeleton of the test set and the predicted safety level of the forklift skeleton, obtaining the prediction error, and using the mean square error (MSE) as an error evaluation indicator;

[0102] S409: Input the safety degree data of the forklift frame into the trained linear regression model to obtain the safety degree prediction result of the forklift frame.

[0103] The data transmission module uses the API or data transmission tool provided by the cloud service provider to transfer data from the skeleton safety detection device to the cloud, and creates a database or file storage bucket in the cloud storage account to store the data; the data is stored in unstructured data.

[0104] Alarm and Display Module When the data analysis module detects a potential safety problem, the alarm system will immediately issue a warning, which can be a sound, visual signal or a combination of both. At the same time, the display screen will provide real-time detection data to help the operator understand the status of the forklift frame. The operation of this module depends on sensor data and alarm logic, and its composition includes an alarm device and a display screen;

[0105] The alarm device uses PCF8574T I / O expander, with buzzer and LED light, to realize sound and light alarm.

[0106] The display uses a 4.3-inch LCD display, Atrimoni AT043TN24 model, to display real-time data and system status.

[0107] The communication module system can remotely transmit the detection data and alarm information to the monitoring center. It can achieve data transmission through wireless or wired methods; the communication module consists of a wireless or wired communication interface, a modem, and related communication protocol stacks;

[0108] The wireless communication interface uses the ESP8266 Wi-Fi module, supports TCP / IP protocol, and realizes remote data transmission.

[0109] The wired communication interface uses an RJ45 Ethernet interface and is paired with a WIZnetW5100 network chip to achieve a stable network connection.

[0110] The power management module provides a stable power supply for the entire system, ensuring that the system can operate normally under various working conditions. It includes a power adapter, a power distributor, and a backup battery management system;

[0111] The power adapter uses a MeanWell RSP-300-12 switching power supply, which provides a 12V DC output.

[0112] The power distributor uses the LM2596S step-down module to provide stable 5V or 3.3V power to different modules.

[0113] The battery management system uses the Texas Instruments BQ24725 battery charging and management IC, which is suitable for lithium-ion batteries.

[0114] In the present invention, by using an ultrasonic sensor module, the system can accurately detect defects in the forklift frame, such as cracks and wear, which helps prevent potential failures and accidents. The data analysis module is particularly beneficial to the performance of the entire system, and the following are its specific beneficial effects: The signal filtering module smoothes the ultrasonic signal through a first-order low-pass filter, reduces noise interference, and improves signal quality. The signal enhancement module further enhances the visual effect of the signal through denoising, gain control, and signal segmentation, which helps to more accurately identify signal features. The machine learning prediction module uses historical data to predict the safety level of the forklift frame, which can achieve predictive maintenance, reduce unexpected downtime, and extend the service life of the forklift. The data analysis module can monitor the status of the forklift frame in real time, and by comparing with the preset safety standards, quickly make decisions on whether maintenance or shutdown is required, thereby improving operating efficiency and safety.

[0115] In the present invention, when the data analysis module detects a potential safety problem, the alarm and display module can immediately issue a warning and provide real-time data, so that the operator can take prompt action to avoid accidents. Remote monitoring and data transmission: The communication module allows the system to remotely transmit detection data and alarm information to the monitoring center, which is convenient for centralized management and record keeping, and improves management efficiency and response speed. Power management and system stability: The power management module ensures the stable operation of the system under various working conditions, whether it is powered by an external power supply or a backup battery, to ensure the continuous availability of the system. Thereby, the system improves the accuracy and reliability of the detection signal and reduces false alarms and missed alarms. Through predictive analysis, preventive maintenance is achieved, reducing maintenance costs and downtime. Real-time monitoring and rapid response improve the safety management level of the work site. It provides a scientific basis for the safety assessment of the forklift frame and helps to formulate reasonable maintenance plans and strategies.

[0116] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or still includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0117] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A forklift frame safety detection system based on ultrasound, characterized in that: The system includes: an ultrasonic sensor module, a signal processing module, a data analysis module, an alarm and display module, a communication module and a power management module; The data analysis module is internally provided with a signal filtering module, a signal enhancement module, a machine learning prediction module and a data transmission module; The transmitter of the ultrasonic sensor module is connected to the trigger circuit of the signal processing module; The receiver of the ultrasonic sensor module is connected to the signal input end of the signal processing module; The amplifier of the signal processing module receives the signal from the ultrasonic receiver and outputs it to the filter; The filter of the signal processing module receives the signal from the amplifier and outputs it to the ADC; the ADC converts the filtered analog signal into a digital signal and outputs it to the data analysis module; The data analysis module receives the digital signal from the ADC, performs calculation and analysis, and outputs the result to the alarm and display module; The alarm and display module receives the data and alarm signal from the data analysis module and drives the alarm and display screen; The communication module receives data from the alarm and display module and sends it to the remote monitoring system wirelessly or wiredly; The power management module provides necessary power to all the above modules to ensure stable operation of the system.

2. The ultrasonic-based forklift frame safety detection system according to claim 1, characterized in that: The ultrasonic sensor module consists of an ultrasonic transmitter and a receiver. The transmitter is responsible for emitting ultrasonic waves of a certain frequency. These waves will generate echoes when encountering defects in the forklift frame. The receiver captures these echoes and converts them into electrical signals. The operating mechanism of the module is to monitor any changes in the frame by continuously or periodically emitting and receiving ultrasonic waves. In terms of structure, it includes an ultrasonic probe, a transmitting / receiving circuit and a control unit. The ultrasonic transmitter uses TCT40-16T ultrasonic transmitting transducer, which has a center frequency of 40kHz and is suitable for detecting defects in metal structures; The ultrasonic receiver uses a TCT40-16R ultrasonic receiving transducer, which matches the transmitter and is used to receive reflected waves; The control unit uses an STM32F103RCT6 microcontroller to control the timing of transmission and reception and data processing.

3. The ultrasonic-based forklift frame safety detection system according to claim 1, characterized in that: The signal processing module optimizes the signal collected by the sensor module; it includes an amplifier, a filter and an ADC; the amplifier enhances the strength of the signal, the filter removes unnecessary noise, and the ADC converts the analog signal into a digital signal; The amplifier uses AD825 operational amplifier, which has high gain and low noise characteristics and is suitable for amplifying weak ultrasonic signals; The filter adopts MAX291 switched capacitor filter, which can provide low-pass, high-pass, band-pass and band-stop filtering functions; The ADC uses the ADS1255 24-bit ADC.

4. The ultrasonic-based forklift frame safety detection system according to claim 1, characterized in that: The signal filtering module uses a first-order low-pass filter to smooth the ultrasonic signal. First, a LowPassFilter class is defined, which contains a method filter for applying a first-order low-pass filter. Then, an instance is created and used to process a series of ultrasonic sampling data. The specific steps include: The first step is to use the first-order low-pass filter technology to obtain the filter configuration result by initializing the filter parameters according to the sampling rate of the ultrasonic signal and the filter cutoff frequency data; The second step is to use the first-order low-pass filter technology to filter each sampling point based on the collected ultrasonic sampling data, and obtain the filtered ultrasonic signal data; Step 3: Using Python programming language, according to the filtered ultrasonic signal data, the filtered data array is obtained by traversing the data array and applying the filter method of the filter instance to process each sample; Step 4: Output the filtered data array obtained in step 3 for further data analysis or processing.

5. The ultrasonic-based forklift frame safety detection system according to claim 1, characterized in that: The signal enhancement module includes denoising, gain control and signal segmentation; the Python programming language is used, and a NumPy array containing ultrasonic signal data is set, and two signal processing techniques are used: Weiner filter and Savitzky-Golay filter, which are used for denoising and smoothing signals respectively; the dynamic range of the signal is adjusted by calculating the average value of the signal and performing normalized gain, thereby enhancing the visual effect of the signal; The specific steps include: S301, using a Weiner filter to perform denoising on the original ultrasonic signal; the Weiner filter is an adaptive filter that adjusts the filter parameters according to the local characteristics of the signal to effectively remove random noise in the signal; S302. The denoised signal may have some uneven areas, so the window length and window type are set, and the denoised signal is smoothed using a Savitzky-Golay filter; the Savitzky-Golay filter is a method for local polynomial fitting of data points in the time domain, which well preserves the shape and trend of the signal while reducing the impact of noise; S303, in order to further adjust the strength of the signal, the average value of the smoothed signal is calculated and normalized to obtain an enhanced signal; this means that each point in the signal will be adjusted according to its difference from the average value to improve the contrast and distinguishability of the signal; S304: This helps to analyze different features of the signal or perform local processing on the signal.

6. The ultrasonic-based forklift frame safety detection system according to claim 1, characterized in that: The machine learning prediction module uses historical data and machine learning technology to predict the safety level of the forklift frame. The specific contents are as follows: S401, reading historical data from a CSV file, the data including forklift operation time, load size, ambient temperature, forklift maintenance record and vibration level; S402, taking the safety degree of the forklift frame as the evaluation index, storing the evaluation index as features in the variable "features", and storing the safety degree of the forklift frame as the target variable in the variable "target"; S403, converting the features and target variables into numerical types for algorithm processing; if there are missing values ​​in the data, they need to be processed, including filling or deleting the missing values; S404, dividing the data set into a training set and a test set according to a set ratio (8:2); S405, creating a linear regression model and storing it in the variable "model"; using the training set to train the linear regression model to obtain a trained linear regression model; S406, inputting the ultrasonic forklift skeleton safety detection data into the trained linear regression model, and obtaining the linear relationship of the ultrasonic forklift skeleton safety detection through operation; S407, using the obtained linear relationship to predict the features of the test set, and storing the prediction results in the variable "predictions"; S408, calculating the difference between the actual safety level of the forklift skeleton of the test set and the predicted safety level of the forklift skeleton, obtaining the prediction error, and using the mean square error as an error evaluation indicator; S409: Input the safety degree data of the forklift frame into the trained linear regression model to obtain the safety degree prediction result of the forklift frame.

7. The ultrasonic-based forklift frame safety detection system according to claim 1, characterized in that: The data transmission module uses an API or data transmission tool provided by a cloud service provider to transmit data from the skeleton safety detection device to the cloud, and creates a database or file storage bucket in a cloud storage account to store the data; Data is stored in unstructured data.

8. The ultrasonic-based forklift frame safety detection system according to claim 1, characterized in that: When the data analysis module detects a potential safety problem, the alarm system will immediately issue a warning, which is a sound, visual signal or a combination of the two; at the same time, the display screen will provide real-time detection data to help the operator understand the status of the forklift frame; the operation of this module depends on sensor data and alarm logic, and its composition includes an alarm device and a display screen; The alarm device uses PCF8574T I / O expander, with buzzer and LED light, to realize sound and light alarm; The display uses a 4.3-inch LCD display, Atrimoni AT043TN24 model, to display real-time data and system status.

9. The ultrasonic-based forklift frame safety detection system according to claim 1, characterized in that: The communication module system can remotely transmit detection data and alarm information to the monitoring center; it realizes data transmission by wireless or wired means; the communication module is composed of a wireless or wired communication interface, a modem and a related communication protocol stack; The wireless communication interface uses the ESP8266 Wi-Fi module, supports TCP / IP protocol, and realizes remote data transmission; The wired communication interface uses an RJ45 Ethernet interface and is paired with a WIZnetW5100 network chip to achieve a stable network connection.

10. The ultrasonic-based forklift frame safety detection system according to claim 1, characterized in that: The power management module provides a stable power supply for the entire system, ensuring that the system can operate normally under various working conditions; it includes a power adapter, a power distributor and a backup battery management system; The power adapter uses a MeanWell RSP-300-12 switching power supply, which provides a 12V DC output; The power distributor uses the LM2596S step-down module to provide stable 5V or 3.3V power to different modules; The battery management system uses a Texas Instruments BQ24725 battery charging and management IC.

Images