A centrifugal release safety performance detection system

Abstract

The application relates to the technical field of centrifugal release device detection, and discloses a centrifugal release device safety performance detection system, which comprises a data acquisition module, a data preprocessing module, a data interaction module, a data fusion module, a diagnosis module and a result output module; through the collaborative design of multiple modules and the deep application of frontier technologies, the detection system comprehensively improves the detection performance; the data acquisition module utilizes a multi-sensor array and a time synchronization algorithm to ensure the acquisition of multi-dimensional data of the centrifugal release device operation, thereby laying a solid foundation for accurate detection; the preprocessing module utilizes Kalman filtering and short-time Fourier transform to efficiently remove data noise, extract key features and reduce the subsequent processing pressure; the data interaction module is based on the Internet of Things and edge computing to realize fast data transmission and local processing, reduce network load and guarantee real-time performance; these designs are closely linked, so that the system can quickly and accurately acquire and process data, and the detection efficiency is greatly improved.

Description

Technical Field

[0001] This invention relates to the field of centrifugal release device testing technology, and more specifically discloses a centrifugal release device safety performance testing system. Background Technology

[0002] A centrifugal release device is a device that works on the principle of centrifugal force. It is mainly used in braking systems. Centrifugal release devices are simple in structure, small in size, flexible and reliable, and are widely used in the safety braking systems of mine auxiliary transportation equipment. At the same time, it is necessary to conduct safety performance testing on centrifugal release devices, mainly for the following reasons: to ensure the normal operation and safety of the equipment, preventive maintenance, and to ensure the continuity and stability of production.

[0003] Existing detection systems use only a single sensor to collect data, which cannot comprehensively acquire equipment operation data and is prone to deviations in detection results due to data gaps. In addition, the collected data is transmitted directly without preprocessing, which not only increases network pressure but also reduces processing efficiency. Furthermore, when simulating operating conditions, they rely only on simple physical tests or virtual simulations, making it difficult to reproduce complex scenarios and causing the detection results to deviate from the actual operating conditions. Finally, the lack of a dynamic weight allocation mechanism makes it difficult to eliminate differences in multi-source data or relies on human experience and simple algorithms, making it impossible to automatically and accurately identify potential faults. Summary of the Invention

[0004] The main technical problem solved by this invention is to provide a safety performance testing system for centrifugal release devices, which can solve the problems existing in the background art.

[0005] To address the aforementioned technical problems, according to one aspect of the present invention, more specifically, a centrifugal release device safety performance testing system includes a data acquisition module, a data preprocessing module, a data interaction module, a data fusion module, a diagnostic module, and a result output module. The system performs the testing through the following steps:

[0006] S1: With the help of the data acquisition module, the operation data of the centrifugal releaser is collected from all directions using multiple types of sensors to ensure that various information during the operation of the equipment can be obtained, providing a rich and comprehensive data foundation for subsequent testing and avoiding inaccurate test results due to missing data.

[0007] S2: The data preprocessing module performs preliminary processing on the collected data, removing noise and redundant information. This not only reduces the data transmission pressure but also quickly extracts key data features, significantly improving data processing efficiency and reducing the computational burden on subsequent modules.

[0008] S3: The data interaction module acts as a bridge, enabling smooth data flow between different modules. This allows data to be transmitted to where it is needed in a timely and accurate manner, ensuring the collaborative work of all parts of the system and enhancing the system's integrity and coherence.

[0009] S4: The simulation module simulates the operation of the centrifugal release device under various actual working conditions and verifies it with real data. This makes up for the shortcomings of relying solely on actual testing or virtual simulation, greatly improving the realism and accuracy of the working condition simulation, so that the test results are more in line with the actual operating conditions of the equipment.

[0010] S5: The data fusion module deeply integrates the preprocessed virtual simulation data with the physical simulation data, eliminates differences and contradictions between the data, unifies the data format and standards, and provides more accurate and reliable data support for subsequent analysis;

[0011] S6: The diagnostic module uses intelligent algorithms to analyze the fused data, automatically identify potential equipment faults, and generate diagnostic reports.

[0012] Furthermore, the simulation module includes: a virtual simulation module and a physical simulation module;

[0013] Virtual simulation module: Utilizes the computer simulation software ANSYS to construct a three-dimensional virtual model of the centrifugal release device, inputs actual physical parameters and operating conditions, and performs simulation analysis;

[0014] Physical simulation module: Using variable frequency motors, programmable controllers and hydraulic systems, a physical testing platform is built to simulate different slopes, speeds and loads to obtain operating data under real-world conditions.

[0015] Furthermore, the data acquisition module employs a multi-sensor array, including a MEMS accelerometer, a Hall effect speed sensor, and a piezoresistive pressure sensor. Each sensor uses a time synchronization algorithm to achieve precise triggering of data acquisition.

[0016] Furthermore, the data preprocessing module integrates the Kalman filter algorithm and short-time Fourier transform to denoise and extract time-frequency domain features from the original data, thereby achieving data dimensionality reduction.

[0017] Furthermore, the data fusion module adopts a dynamic weight allocation mechanism, which adjusts the fusion weight of sensor data and virtual simulation data in real time according to the operating parameters, and realizes the synchronous processing of multi-source data through a timestamp alignment algorithm.

[0018] Furthermore, the diagnostic module constructs a fault identification model based on convolutional neural networks and long short-term memory networks.

[0019] Furthermore, the result output module presents the test results in the form of visual charts and text descriptions based on the diagnostic report generated by the diagnostic module.

[0020] The beneficial effects of the centrifugal release device safety performance testing system of the present invention are as follows: Through multi-module collaborative design and in-depth application of cutting-edge technologies, the testing system achieves a comprehensive improvement in testing performance. The data acquisition module utilizes a multi-sensor array and time synchronization algorithm to ensure the acquisition of multi-dimensional data on the operation of the centrifugal release device, laying a solid foundation for accurate testing. The data preprocessing module uses Kalman filtering and short-time Fourier transform to efficiently remove data noise and extract key features, reducing the pressure of subsequent processing. The data interaction module is based on the Internet of Things and edge computing to achieve rapid data transmission and local processing, reducing network load and ensuring real-time performance. These interconnected designs enable the system to quickly and accurately acquire and process data, greatly improving testing efficiency.

[0021] Through the organic combination of virtual simulation and physical simulation, and the innovative application of intelligent algorithms, the system's detection accuracy and reliability are significantly enhanced. In the simulation module, virtual simulation and physical simulation verify each other, highly restoring the operating state of the equipment under complex working conditions. The data fusion module adopts dynamic weight allocation and timestamp alignment to eliminate differences in multi-source data and provide accurate data support. The diagnostic module is based on convolutional neural networks and long short-term memory networks to automatically identify potential faults. Combined with the visualized result output module, it provides a scientific basis for equipment maintenance, ensuring that the test results of the centrifugal release device's safety performance are more realistic and reliable. Attached Figure Description

[0022] The present invention will now be described in further detail with reference to the accompanying drawings and specific implementation methods.

[0023] Figure 1 This is a schematic diagram of the system principle;

[0024] Figure 2 This is a flowchart illustrating the steps. Detailed Implementation

[0025] The present invention will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the present application can be combined with each other.

[0026] According to one aspect of the invention, such as Figures 1-2As shown, a safety performance testing system for centrifugal release devices is provided, including: a data acquisition module employing a multi-sensor array, including a MEMS accelerometer (such as ADI ADXL345, range ±16g, resolution 13-bit, sampling frequency 10kHz), a Hall effect speed sensor (such as Allegro A1302, response frequency 0-100kHz, measurement error ±0.5%), and a piezoresistive pressure sensor (accuracy ±0.5% FS, range 0-10MPa). Each sensor achieves precise triggering of data acquisition through a time synchronization algorithm.

[0027] The conversion relationship between the accelerometer output voltage and the physical acceleration is as follows:

[0028]

[0029] in For output voltage, For reference voltage, For the range, For sensitivity (e.g., ADXL345 has a sensitivity of 3.9 mg / LSB). This refers to the supply voltage (in volts).

[0030] The time synchronization algorithm is based on the Network Time Protocol (NTP) framework and uses sliding window interpolation to perform time-series calibration on sensor data with different sampling frequencies. It first obtains a unified reference timestamp through the NTP protocol. Then, the original data acquisition timestamps from the sensors... The correction is made, and the correction formula is:

[0031]

[0032] in The sensor uses its local reference time, and a linear interpolation formula is used to account for time axis differences between multi-source data:

[0033]

[0034] in Align the target time point, and For adjacent original time points, and To correspond with the original data, sensor data collected at different frequencies are resampled to a unified time scale, ensuring accurate temporal matching of multi-dimensional data and laying the foundation for subsequent processing. The data preprocessing module performs preliminary processing on the collected data, removing noise and redundant information. This not only reduces data transmission pressure but also quickly extracts key data features, significantly improving data processing efficiency and reducing the computational burden on subsequent modules. Specifically, the data preprocessing module integrates Kalman filtering and Short-Time Fourier Transform (STFT) algorithms to denoise the original data and extract time-frequency domain features, achieving data dimensionality reduction.

[0035] The Kalman filter algorithm constructs a state-space model, predicts the current state using the state from the previous time step, and then corrects it using observations. Its core formula is:

[0036] State update equation:

[0037]

[0038] Observation equation:

[0039]

[0040] And Kalman gain calculation:

[0041]

[0042] in For state vectors, For the observed values, Here is the state transition matrix. For the observation matrix, To observe the noise covariance, thereby effectively filtering data noise and making the data closer to the true state;

[0043] Meanwhile, the short-time Fourier transform performs local analysis of the signal, as shown in the formula:

[0044]

[0045] By converting time-domain data to the time-frequency domain and extracting key features such as rotational speed fluctuations and vibration spectra, data dimensionality reduction is achieved, laying a solid foundation for efficient data processing in subsequent modules.

[0046] The data interaction module acts as a bridge, enabling smooth data flow between different modules. This allows data to be transmitted to where it is needed in a timely and accurate manner, ensuring the collaborative work of all parts of the system and enhancing the system's integrity and coherence.

[0047] This module constructs a wireless communication network based on IoT technology and uses the MQTT protocol (Message Queuing Telemetry Transport) to achieve data interaction between edge computing devices, virtual simulation modules, physical simulation modules, and diagnostic modules. It reduces network bandwidth usage through a publish / subscribe mechanism, and data transmission latency can be controlled within 50ms. Its transmission efficiency formula is:

[0048]

[0049] Furthermore, by employing compression algorithms (such as LZ77), the compression ratio of the raw data is increased to 3:1, ensuring stable transmission of multi-source data in heterogeneous network environments and solving the data silo problem of traditional detection systems. Simultaneously, the data interaction module integrates edge computing nodes (based on ARM architecture processors), adhering to the principle of "local processing + cloud collaboration." It performs feature extraction and filtering on the collected raw data locally, uploading only key parameters (such as fault feature vectors and operating condition indicators) to the cloud. The local processing logic of the edge nodes can be represented as follows:

[0050]

[0051] in The preprocessing function includes operations such as Kalman filtering for noise reduction and feature dimensionality reduction. This reduces the load on the cloud server and ensures the timeliness of data processing through the 10ms real-time response capability of edge nodes, avoiding network congestion and latency issues in the traditional centralized cloud processing mode.

[0052] The simulation module simulates the operation of the centrifugal release device under various actual working conditions, cross-validating the results with real data. This overcomes the shortcomings of relying solely on actual testing or virtual simulation, significantly improving the realism and accuracy of the simulation, thus making the test results more closely match the actual operating conditions of the equipment. This module includes: a virtual simulation module, which uses the computer simulation software ANSYS to construct a three-dimensional virtual model of the centrifugal release device, inputting actual physical parameters and operating conditions for simulation analysis;

[0053] The virtual simulation module, based on finite element analysis (FEA) and multibody dynamics simulation technology, constructs the structural mechanical equations of the centrifugal release device.

[0054]

[0055] in Here is the stiffness matrix. It is a displacement vector. Let the external force vector be the vector, and let it be related to the multibody dynamics equations:

[0056]

[0057] in For the quality matrix, Here is the damping matrix. As a generalized coordinate vector, it enables accurate calculation of stress distribution and motion state under centrifugal force. For example, it simulates the maximum stress of a spring sheet under centrifugal force by mesh generation (minimum element size 0.1mm).

[0058] Physical simulation module: Using a variable frequency motor, programmable controller and hydraulic system, a physical test platform is built to simulate different slopes, speeds and loads to obtain operating data under real environment;

[0059] The physical simulation module implements PID closed-loop control through a programmable logic controller (PLC), and the control algorithm is as follows:

[0060]

[0061] in, To control the output, This refers to the systematic error (i.e., the difference between the target value and the actual value). , , These are the proportional, integral, and differential coefficients, respectively.

[0062] The data fusion module deeply integrates the preprocessed data with the virtual physical simulation data, eliminating differences and contradictions between the data, unifying the data format and standards, and providing more accurate and reliable data support for subsequent analysis.

[0063] The data fusion module employs a dynamic weight allocation mechanism, adjusting the fusion weights of sensor data and virtual simulation data in real time based on operating parameters. The weight calculation follows the formula:

[0064]

[0065] in To establish confidence levels for data sources (e.g., confidence levels for physical sensors are determined by accuracy calibration, while confidence levels for virtual data are determined by simulation errors), and to achieve multi-source data synchronization using a timestamp alignment algorithm, a linear interpolation formula is employed:

[0066]

[0067] in Align the target time point, and For adjacent original time points, and To correspond with the original data, preprocessed data and virtual physical simulation data collected at different frequencies are resampled to ensure accurate matching of multi-dimensional data in terms of time series and feature dimensions, and to build a high-quality fusion dataset.

[0068] The diagnostic module constructs a fault identification model based on convolutional neural networks (CNN) and long short-term memory networks (LSTM);

[0069] This module extracts the time-frequency domain features of the vibration signal through one-dimensional convolution operations, as shown in the formula:

[0070]

[0071] in For the first Layer The output of each neuron As weight, For bias, The ReLU activation function is used, and LSTM gating is combined to achieve temporal feature learning. The forgetting gate formula is as follows:

[0072]

[0073] in For the Sigmoid function, The state was hidden in the previous moment. Using the current input, the fault classification is ultimately completed through the Softmax function:

[0074]

[0075] in For the output of the fully connected layer, The number of fault categories enables automatic identification of faults such as bearing wear and spring failure.

[0076] The results output module presents the test results in the form of visual charts and text descriptions based on the diagnostic report generated by the diagnostic module.

[0077] This module transforms the fault probability vector (e.g., bearing wear probability 0.92, normal state probability 0.08) output by CNN+LSTM into a dynamic line graph, with the horizontal axis representing the time series and the vertical axis representing the fault confidence. It also generates a text report (e.g., the detection shows that the spring sheet stress exceeds the threshold by 23%, and it is recommended to replace it within 48 hours) through the feature importance matrix.

[0078] Of course, the above description is not a limitation of the present invention, and the present invention is not limited to the examples given above. Any changes, modifications, additions or substitutions made by those skilled in the art within the scope of the present invention are also within the protection scope of the present invention.

Claims

1. A safety performance testing system for centrifugal release devices, characterized in that, The system includes a data acquisition module, a data preprocessing module, a data interaction module, a data fusion module, a diagnostic module, and a result output module. The system performs detection through the following steps: S1: With the help of the data acquisition module, the operation data of the centrifugal releaser is collected from all directions using multiple types of sensors to ensure that various information during the operation of the equipment can be obtained, providing a rich and comprehensive data foundation for subsequent testing and avoiding inaccurate test results due to missing data. S2: The data preprocessing module performs preliminary processing on the collected data, denoising and extracting time-frequency domain features from the raw data to achieve data dimensionality reduction, remove noise and redundant information, which not only reduces the data transmission pressure, but also quickly extracts key data features, significantly improves data processing efficiency, and reduces the computational burden of subsequent modules. S3: The data interaction module acts as a bridge, enabling smooth data flow between different modules. This allows data to be transmitted to where it is needed in a timely and accurate manner, ensuring the collaborative work of all parts of the system and enhancing the system's integrity and coherence. S4: The simulation module simulates the operation of the centrifugal release device under various actual working conditions and verifies it with real data. This makes up for the shortcomings of relying solely on actual testing or virtual simulation, greatly improving the realism and accuracy of the working condition simulation, so that the test results are more in line with the actual operating conditions of the equipment. S5: The data fusion module deeply integrates the preprocessed virtual simulation data with the physical simulation data, eliminates differences and contradictions between the data, unifies the data format and standards, and provides more accurate and reliable data support for subsequent analysis; S6: The diagnostic module uses intelligent algorithms to analyze the fused data, automatically identify potential equipment faults, and generate diagnostic reports; S7: The simulation module includes: a virtual simulation module and a physical simulation module; Virtual simulation module: Utilizes the computer simulation software ANSYS to construct a three-dimensional virtual model of the centrifugal release device, inputs actual physical parameters and operating conditions, and performs simulation analysis; Physical simulation module: Using variable frequency motors, programmable controllers and hydraulic systems, a physical testing platform is built to simulate different slopes, speeds and loads to obtain operating data under real-world conditions.

2. The centrifugal release device safety performance testing system according to claim 1, characterized in that: The data acquisition module employs a multi-sensor array, including a MEMS accelerometer, a Hall effect speed sensor, and a piezoresistive pressure sensor. Each sensor uses a time synchronization algorithm to achieve precise triggering of data acquisition.

3. The centrifugal release device safety performance testing system according to claim 1, characterized in that: The data preprocessing module integrates the Kalman filter algorithm and short-time Fourier transform to denoise and extract time-frequency domain features from the original data, thereby achieving data dimensionality reduction.

4. The centrifugal release device safety performance testing system according to claim 1, characterized in that: The data fusion module adopts a dynamic weight allocation mechanism, which adjusts the fusion weight of sensor data and virtual simulation data in real time according to the operating parameters, and realizes the synchronous processing of multi-source data through a timestamp alignment algorithm.

5. The centrifugal release device safety performance testing system according to claim 1, characterized in that: The diagnostic module constructs a fault identification model based on convolutional neural networks and long short-term memory networks.

6. The centrifugal release device safety performance testing system according to claim 1, characterized in that: The result output module presents the test results in the form of visual charts and text descriptions based on the diagnostic report generated by the diagnostic module.

Images