Remote opening and closing control method and system for barrier of automatic lane closing machine

Abstract

The invention provides a remote opening and closing control method and system for a barrier of an automatic gateway machine, and relates to the technical field of remote control of the automatic gateway machine. Equipment operation monitoring parameters and environment information are regularly acquired, and online prediction is performed by using a multi-modal data processing and deep learning model; according to the method, real-time monitoring of the automatic gateway machine railing is realized, so that the system can quickly respond when an abnormal condition occurs, and an event early warning type and a corresponding disposal suggestion are generated in time, thereby reducing the fault processing time, improving the overall response speed of the system, capturing time dependence and extracting local features by the pre-trained LSTM-CNN hybrid model, and improving the fault handling efficiency. The event early warning type and the corresponding disposal suggestion are generated in combination with the mapping table, the intelligent decision support system can provide scientific and reasonable disposal suggestions for operators, errors caused by manual judgment are reduced, and the accuracy and efficiency of decision making are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of remote control of automatic road gate machines, and in particular to a remote switch control method and system for a barrier of an automatic road gate machine. Background Art

[0002] The automatic lane-closing machine is deployed in the front area of ​​the toll island. It can integrate fog lights, electric barriers, LED displays and other functions. It is used to close the toll lane, display the lane open / closed status, speed limit and other scene applications. Traditional automatic lane-closing machine barriers mainly rely on manual monitoring and simple sensors to achieve basic switch control. They cannot respond to emergencies in real time, resulting in delayed response in emergency situations. In addition, the data collected by traditional systems are often only used for simple status monitoring, and fail to fully utilize these data for more in-depth analysis and prediction, making it difficult to timely discover potential equipment failures. Due to the lack of an effective fault warning mechanism, equipment maintenance usually relies on regular inspections, which increases maintenance costs. Due to remote control, it is impossible to judge the on-site situation when an abnormal situation occurs, resulting in a lack of scientific and effective decision-making suggestions, affecting the efficiency of abnormal handling.

[0003] Therefore, it is necessary to provide a remote switch control method and system for an automatic road gate barrier to solve the above technical problems. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a remote switch control method and system for an automatic gate barrier, which can achieve the beneficial effects of real-time rapid response, efficient fault warning and intelligent disposal decision-making.

[0005] The present invention provides a remote switch control method for an automatic road gate barrier, comprising: S1: Regularly obtain the equipment operation monitoring parameters of the automatic road gate barrier and the environmental information around the automatic road gate barrier; S2: Extract the time domain characteristics, frequency domain characteristics and time series characteristics of equipment operation monitoring parameters; S3: Combine equipment operation monitoring parameters, extracted time domain features, frequency domain features, time series features and environmental information into a comprehensive data set; S4: inputting the comprehensive data set into the pre-trained LSTM-CNN hybrid model for online prediction, generating event warning types and corresponding disposal suggestions; S5: According to the generated event warning type and corresponding disposal suggestions, select the corresponding disposal instruction to remotely control the operating status of the gate barrier.

[0006] Preferably, in step S1, the equipment operation monitoring parameters include motor current, railing operation time, operating temperature, vibration frequency, noise level, railing angle, and the environmental information includes weather information and traffic flow information.

[0007] Preferably, the weather information includes temperature, humidity, wind speed, air pressure, and light.

[0008] Preferably, step S2 comprises the following steps: S201: extracting time domain features of equipment operation monitoring parameters, wherein the time domain features include mean, variance, peak value and slope; S202: Convert the equipment operation monitoring parameters into the frequency domain by using Fourier transform, and extract frequency domain features; S203: extracting time series characteristics of equipment operation monitoring parameters using autocorrelation functions and cross-correlation functions.

[0009] Preferably, step S3 comprises the following steps: S301: Standardizing equipment operation monitoring parameters, extracted time domain features, frequency domain features, time series features and environmental information; S302: performing multimodal data alignment on the standardized equipment operation monitoring parameters, time domain features, frequency domain features, time series features and environmental information; S303: Classify and combine the aligned multimodal data into a comprehensive data set.

[0010] Preferably, in step S302, the multimodal data alignment adopts a linear interpolation method.

[0011] Preferably, step S4 comprises the following steps: S401: Input the comprehensive dataset into the pre-trained LSTM-CNN hybrid model through multiple channel input networks; S402: The LSTM-CNN hybrid model processes the input comprehensive data set, extracts local features through the convolution layer, captures time dependencies through the long short-term memory network, and performs nonlinear transformation through the fully connected layer, and finally outputs the event warning probability value; S403: Based on the generated event warning probability value and in combination with a predefined mapping table, an event warning type and a corresponding handling suggestion are generated.

[0012] Preferably, the mapping table includes a mapping relationship between a preset event warning probability threshold, an event warning type, and a corresponding handling suggestion.

[0013] Preferably, a Dropout layer is added between the layers of the LSTM-CNN hybrid model, wherein the dropout rate of the Dropout layer is preset based on an empirical rule.

[0014] The present invention also provides a remote switch control system for an automatic road gate barrier, which is applied to a remote switch control method for an automatic road gate barrier. The remote switch control system includes: A data acquisition module is used to regularly obtain equipment operation monitoring parameters of the automatic road gate barrier and environmental information around the automatic road gate barrier; Feature extraction module, used to extract time domain features, frequency domain features and time series features of equipment operation monitoring parameters; A data processing module is used to combine equipment operation monitoring parameters, extracted time domain features, frequency domain features, time series features and environmental information into a comprehensive data set; A prediction module, used to input the comprehensive data set into a pre-trained LSTM-CNN hybrid model for online prediction, and generate event warning types and corresponding disposal suggestions; The control module is used to select corresponding disposal instructions to remotely control the operating status of the gate barrier according to the generated event warning type and corresponding disposal suggestions.

[0015] Compared with the related art, the automatic road gate barrier remote switch control method and system provided by the present invention has the following beneficial effects: The present invention realizes real-time monitoring of the automatic gate barrier by regularly acquiring equipment operation monitoring parameters and environmental information, and using multimodal data processing and deep learning models for online prediction. This enables the system to respond quickly when an abnormal situation occurs, and timely generate event warning types and corresponding disposal suggestions, thereby reducing fault handling time and improving the overall response speed of the system. Through comprehensive analysis of equipment operation monitoring parameters and environmental information, the present invention can detect potential fault signs in advance and generate corresponding warning information, which helps to take maintenance measures in time to avoid equipment failures, thereby extending the service life of the equipment and reducing maintenance costs. The pre-trained LSTM-CNN hybrid model can capture time dependency and extract local features, and generate event warning types and corresponding disposal suggestions in combination with a mapping table. This intelligent decision support system can provide operators with scientific and reasonable disposal suggestions, reduce errors in human judgment, and improve the accuracy and efficiency of decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic flow chart of a method for controlling the remote opening and closing of a barrier of an automatic road gate according to the present invention; Figure 2 The present invention is a schematic diagram of the module structure of a remote switch control system for an automatic road gate barrier. DETAILED DESCRIPTION

[0017] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only the parts related to the present invention, rather than all structures, are shown in the accompanying drawings. In addition, the embodiments of the present invention and the features in the embodiments may be combined with each other without conflict.

[0018] It should also be noted that, for ease of description, only the parts related to the present invention, but not all of the contents, are shown in the accompanying drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the various operations (or steps) as being processed sequentially, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the various operations can be rearranged. The processing can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The processing can correspond to methods, functions, procedures, subroutines, subprograms, etc.

[0019] Embodiment 1 A remote switch control method for an automatic road barrier, in the specific implementation process, such as Figure 1 As shown, it shows a schematic flow chart of a method for controlling the remote switch of an automatic road barrier, including: Step S1: Regularly obtain equipment operation monitoring parameters of the automatic road gate barrier and environmental information around the automatic road gate barrier.

[0020] Specifically, in step S1, the equipment operation monitoring parameters include motor current, barrier operation time, operating temperature, vibration frequency, noise level, and barrier angle, and the environmental information includes weather information and traffic flow information.

[0021] Specifically, weather information includes temperature, humidity, wind speed, air pressure, and light.

[0022] During the specific implementation process, the sensor for monitoring the operation status of the automatic road-closing machine railing installed inside the road-closing machine railing regularly obtains the operation monitoring parameters of the road-closing machine equipment, which include motor current, railing operation time, operating temperature, vibration frequency, noise level, and railing angle. Exemplarily, the working current of the motor is monitored in real time by a current sensor installed on the motor; the time from opening to closing, or from closing to opening, is recorded by a timer; the operating temperature of the motor and other key components is monitored by a thermocouple or thermistor sensor; the vibration of the railing and its supporting structure is monitored by an accelerometer; the noise generated during the operation of the equipment is monitored by a microphone array; the angle change of the railing is monitored by a rotary encoder or an angle sensor. These data reflect the operation status of the road-closing machine railing. Abnormalities in the road-closing machine railing can be reflected by these data, so they are important monitoring data. In addition, the environment around the road-closing machine railing will also affect the operation of the road-closing machine railing, so environmental information must also be monitored. Environmental information includes weather information and traffic information, and weather information includes temperature, humidity, wind speed, air pressure, and light. Temperature, humidity, wind speed, air pressure, and light data are acquired through various meteorological sensors, and traffic information is acquired through video surveillance systems and vehicle detection sensors. The collected data is transmitted to a central server or cloud platform for subsequent data processing and analysis.

[0023] Step S2: extracting the time domain features, frequency domain features and time series features of the equipment operation monitoring parameters.

[0024] In the specific implementation process, time domain features, frequency domain features and time series features are methods of analyzing signals from different angles, which help to fully describe the characteristics of signals. Time domain features refer to the features obtained by directly analyzing the signal on the time axis, which usually reflects the temporal variation characteristics of the signal; frequency domain features are the features obtained by analyzing the frequency components of the signal after converting the signal from the time domain to the frequency domain through Fourier transform. Frequency domain features help to understand the frequency distribution and energy distribution of the signal; time series features are the features obtained by performing statistical analysis and correlation analysis on time series data, which help to understand the time dependence and dynamic characteristics of the signal.

[0025] Specifically, step S2 includes the following steps: S201: Extracting time domain features of equipment operation monitoring parameters, wherein the time domain features include mean, variance, peak value and slope.

[0026] During the specific implementation process, the mean, variance, peak and slope of the equipment operation monitoring parameters within a certain time window are calculated. The mean reflects the average level within a time window, the variance reflects the degree of fluctuation of the data within a certain time window, the peak refers to the maximum value within a certain time window, and the slope reflects the rate of change of the data within a certain time window. These statistical features together provide a multi-dimensional data view, which helps the subsequent model to more comprehensively understand and evaluate the operating status of the equipment.

[0027] S202: Convert the equipment operation monitoring parameters into the frequency domain using Fourier transform, and extract frequency domain features.

[0028] During the specific implementation process, Fourier transform is used to convert the equipment operation monitoring parameters into the frequency domain, and the frequency domain information is extracted. For example, the frequency distribution of the signal is obtained through the spectrum diagram, and then the main frequency component of the signal is determined, that is, the frequency with the highest energy in the spectrum diagram, and the harmonic ratio is calculated. The energy ratio of the fundamental frequency and its harmonics can be used to reflect the periodicity and complexity of the signal.

[0029] S203: extracting time series characteristics of equipment operation monitoring parameters using autocorrelation functions and cross-correlation functions.

[0030] During the specific implementation process, the autocorrelation function measures the correlation of the same time series at different time points, that is, the correlation between the time series and its own series after a certain period of time lag; the cross-correlation function is used to measure the correlation between two different time series at different time points. Specifically, it can calculate the cross-correlation between motor current and operating temperature, motor current and vibration frequency, motor current and noise level, motor current and railing angle, operating temperature and vibration frequency, operating temperature and noise level, operating temperature and railing angle, vibration frequency and noise level, vibration frequency and railing angle, and noise level and railing angle.

[0031] S3: Combine equipment operation monitoring parameters, extracted time domain features, frequency domain features, time series features and environmental information into a comprehensive data set.

[0032] In the specific implementation process, step S3 combines the equipment operation monitoring parameters, the extracted time domain features, frequency domain features, time series features and environmental information into a complete comprehensive data set, which provides a reliable data basis for subsequent model prediction and also facilitates data storage.

[0033] Specifically, step S3 includes the following steps: S301: Standardize the equipment operation monitoring parameters, extracted time domain features, frequency domain features, time series features and environmental information.

[0034] In the specific implementation process, in order to eliminate the dimensional differences between different data and improve the prediction effect of the model, all data need to be standardized. For example, Z-Score standardization is used to standardize equipment operation monitoring parameters, extracted time domain features, frequency domain features, time series features and environmental information.

[0035] S302: Perform multimodal data alignment on the standardized equipment operation monitoring parameters, time domain features, frequency domain features, time series features and environmental information.

[0036] Specifically, in step S302, the multimodal data alignment adopts a linear interpolation method.

[0037] In the specific implementation process, since the timestamps of different sensors and data sources may be inconsistent, it is necessary to align the data to a unified time axis through linear interpolation. First, a unified time axis should be determined to ensure that all data can be compared and analyzed within a common time frame. Select a suitable time interval. For example, assuming that the length of the time axis is one minute and the time interval is 5 seconds, the generated time axis , the time axis of the operating temperature data in the equipment operation monitoring parameters is The temperature value corresponding to the time point on the time axis of the working temperature data itself is , in order to align the data, it is necessary to interpolate at 5 seconds. The temperature at sec is , of which 35 are The monitored temperature value at 38 is The temperature value monitored at It is the ratio of the time difference from 0 to 5 seconds to the time difference from 0 to 10 seconds on the time axis. The interpolation value at 5 seconds on the generated time axis is calculated to be 36.5, and so on, until all time points are aligned. In practical applications, real timestamps are used to construct the time axis, which can ensure that the time alignment of the data is more accurate and can better reflect the actual operation. For the extracted feature data, such as the mean, variance, and peak values, which are calculated values ​​and have no timestamps themselves, timestamps can be added to them according to the time window in which they are calculated. For example, if the mean is calculated based on 1-minute window data, the timestamp of the mean can be the middle moment of the time period. Linear interpolation is used to ensure that all data are on a unified time axis, providing a reliable data basis for subsequent model predictions.

[0038] S303: Classify and combine the aligned multimodal data into a comprehensive data set.

[0039] During the specific implementation process, the data after the multimodal data alignment is classified. For example, the equipment operation monitoring parameters are usually high-frequency time series data. These data reflect the operating status of the equipment at different time points and are an important basis for real-time monitoring and early warning. They are divided into one category. The extracted time domain features provide statistical information about the equipment operation status within a certain time window, which helps to identify the average behavior and fluctuation of the equipment. They are divided into one category. The frequency domain features reveal the distribution of data in the frequency domain, which helps to identify the periodic components and frequency characteristics in the equipment operation. They are divided into one category. The time series features provide the correlation and periodicity information of the equipment operation status in the time series, which helps to identify the time dependence in the equipment operation. They are divided into one category. The environmental information can be provided to the model as context information. Therefore, the environmental information as a whole is divided into one category to prepare for the subsequent multi-channel input model. The classified data are combined in a set to form a comprehensive data set.

[0040] S4: The comprehensive dataset is input into the pre-trained LSTM-CNN hybrid model for online prediction to generate event warning types and corresponding disposal suggestions.

[0041] During the specific implementation process, when the comprehensive data set is provided to the pre-trained LSTM-CNN hybrid model, these data are usually input through different channels and processed at different layers of the model, and finally the event warning type and corresponding disposal suggestions are generated.

[0042] Specifically, step S4 includes the following steps: S401: Input the comprehensive dataset into the pre-trained LSTM-CNN hybrid model through multiple channel input networks.

[0043] During the specific implementation process, the comprehensive data set is input into the model through multiple channels, the equipment operation monitoring parameters are input into the LSTM layer, the time domain features are input into the fully connected layer, the frequency domain features are input into the CNN layer, the time series features are input into the LSTM layer, and the environmental information is also input into the LSTM layer as context information. Through multi-channel input, the model can simultaneously utilize these complementary information to improve the accuracy and comprehensiveness of the prediction. Multi-channel input enables the model to rely on other data sources for effective prediction when facing anomalies or missing of a certain data source, thereby improving the robustness of the system.

[0044] S402: The LSTM-CNN hybrid model processes the input comprehensive data set, extracts local features through the convolution layer, captures time dependencies through the long short-term memory network, and performs nonlinear transformation through the fully connected layer, and finally outputs the event warning probability value.

[0045] During the specific implementation process, the LSTM layer processes equipment operation monitoring parameters and time series features to capture long-term dependencies in time series data. At the same time, environmental information is processed as context to provide additional background information for the model; the CNN layer processes frequency domain features to extract local patterns and features in the frequency domain features; the fully connected layer processes time domain features, performs nonlinear transformations, and extracts high-level features; finally, the fusion layer fuses the outputs of the LSTM layer, CNN layer, and fully connected layer to form a comprehensive feature vector, and finally generates the final event warning probability value through the output layer acted upon by the fully connected layer.

[0046] S403: Based on the generated event warning probability value and in combination with a predefined mapping table, an event warning type and a corresponding handling suggestion are generated.

[0047] Specifically, the mapping table includes a mapping relationship between a preset event warning probability threshold, an event warning type, and a corresponding handling suggestion.

[0048] In the specific implementation process, the event warning probability value generated by the model output layer is a vector, and each element represents the probability of a specific event type. When the warning probability value of the specific event type is greater than the corresponding event warning probability threshold preset in the mapping table, it is considered that there is a significant warning signal. When the specific event type generates a warning signal, the event warning type, description and disposal suggestions are combined into a formatted report output according to the mapping relationship between the event type and the corresponding description and disposal suggestions in the mapping table. The background operator selects the corresponding control instructions based on the report output to remotely control the operating status of the gate barrier.

[0049] Specifically, a Dropout layer is added between each layer of the LSTM-CNN hybrid model, where the dropout rate of the Dropout layer is preset based on an empirical rule.

[0050] In the specific implementation process, a Dropout layer is added between each layer of the LSTM-CNN hybrid model to prevent the model from overfitting. The Dropout layer reduces the model's dependence on specific input features by randomly discarding the output of a part of neurons, thereby improving the generalization ability of the model. Since different neurons are randomly discarded during each training, the model is forced to learn a wider range of feature combinations, making the model more robust. The drop rate is the proportion of randomly discarded neurons in each training batch. It is preset based on empirical rules and is usually set according to experience and recommended values ​​in the literature. For most tasks, a drop rate between 0.2 and 0.5 is a common range. According to the specific circumstances of the task and the size of the data set, select a suitable drop rate to effectively prevent the model from overfitting.

[0051] The working principle of the remote switch control method of the automatic road gate barrier provided by the present invention is as follows: First, the equipment operation monitoring parameters of the automatic road gate barrier are collected regularly, including motor current, barrier operation time, working temperature, vibration frequency, noise level, barrier angle and environmental information, including weather information and vehicle flow information. Weather information includes temperature, humidity, wind speed, air pressure and light. The equipment operation monitoring parameters reflect the operation status of the equipment. Through this information, we can understand whether there are abnormalities in the operation of the automatic road gate barrier. Environmental information will interfere with and affect the operation of the automatic road gate barrier. It is an important influencing factor, so it also needs to be collected; then, extract time domain features from these data, including mean, variance, peak and slope, frequency domain features, extracted by Fourier transform, time series features, extracted by autocorrelation function and cross-correlation function; then, these data are standardized and processed by multimodal data The data are aligned and combined into a comprehensive dataset; secondly, the comprehensive dataset is input into the pre-trained LSTM-CNN hybrid model through multiple channels, in which the LSTM layer captures time dependency, the CNN layer extracts local features, and the fully connected layer performs nonlinear transformation. The model outputs event warning probability values, and generates specific event warning types and disposal suggestions in combination with the pre-defined mapping table; finally, based on these disposal suggestions, the background operator selects the corresponding disposal instructions to remotely control the operating status of the gate barrier, realize intelligent equipment monitoring and management, and improve the reliability, safety and robustness of the system. Through the combination of this multimodal data processing and deep learning technology, the system can more comprehensively understand and predict the operating status of the equipment, thereby giving early warning of potential faults and taking corresponding measures to ensure the safe and stable operation of the equipment.

[0052] Embodiment 2 A remote switch control system for an automatic road-closing machine railing is applied to a remote switch control method for an automatic road-closing machine railing. In the specific implementation process, Figure 2 As shown, it shows a schematic diagram of the module structure of an automatic road barrier remote switch control system, including: The data acquisition module 100 is used to regularly obtain the equipment operation monitoring parameters of the automatic road gate barrier and the environmental information around the automatic road gate barrier; The feature extraction module 200 is used to extract the time domain features, frequency domain features and time series features of the equipment operation monitoring parameters; The data processing module 300 is used to combine the equipment operation monitoring parameters, the extracted time domain features, frequency domain features, time series features and environmental information into a comprehensive data set; Prediction module 400, used to input the comprehensive data set into the pre-trained LSTM-CNN hybrid model for online prediction, and generate event warning types and corresponding disposal suggestions; The control module 500 is used to select corresponding handling instructions to remotely control the operating status of the gate barrier according to the generated event warning type and corresponding handling suggestions.

[0053] The working principle of the automatic road gate barrier remote switch control system provided by the present invention is as follows: First, the equipment operation monitoring parameters are regularly acquired through the data acquisition module 100, and the equipment operation monitoring parameters include motor current, railing operation time, working temperature, vibration frequency, noise level, railing angle and environmental information, and the environmental information includes weather information and traffic flow information. These raw data are then passed to the feature extraction module 200; then, the feature extraction module 200 extracts time domain features such as mean, variance, peak and slope, frequency domain features, extracts the main frequency and frequency band energy through Fourier transform, and time series features, which are extracted using autocorrelation function and cross-correlation function; secondly, the data processing module 300 standardizes these raw data and extracted features, and aligns them to a unified time axis through linear interpolation, and combines them into a comprehensive data set; Then, the prediction module 400 inputs this comprehensive data set into the pre-trained LSTM-CNN hybrid model, and inputs different types of data in the comprehensive data set into the LSTM-CNN hybrid model through different input channel networks. The model captures time dependency through the LSTM layer, extracts local features through the CNN layer, and performs nonlinear transformations through the fully connected layer. Finally, the event warning probability value is output, and a specific event warning type and disposal suggestion are generated in combination with a pre-defined mapping table. Finally, according to the generated event warning type and disposal suggestion, the backstage operator selects the corresponding disposal instruction through the control module 500 to remotely control the operating status of the gate gate railing, thereby realizing intelligent remote control of the operation of the gate gate railing and improving the reliability, safety and robustness of the system.

[0054] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0055] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, the storage medium including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically-erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0056] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. A remote switch control method for an automatic road gate barrier, characterized in that: The remote switch control method comprises the following steps: S1: Regularly obtain the equipment operation monitoring parameters of the automatic road gate barrier and the environmental information around the automatic road gate barrier; S2: Extract the time domain features, frequency domain features and time series features of equipment operation monitoring parameters; S3: Combine equipment operation monitoring parameters, extracted time domain features, frequency domain features, time series features and environmental information into a comprehensive data set; S4: inputting the comprehensive data set into the pre-trained LSTM-CNN hybrid model for online prediction, generating event warning types and corresponding disposal suggestions; S5: According to the generated event warning type and corresponding disposal suggestions, select the corresponding disposal instruction to remotely control the operating status of the gate barrier.

2. The method for remotely controlling the opening and closing of an automatic road gate barrier according to claim 1, characterized in that: In step S1, the equipment operation monitoring parameters include motor current, barrier operation time, operating temperature, vibration frequency, noise level, and barrier angle, and the environmental information includes weather information and traffic flow information.

3. The remote switch control method of the automatic road gate barrier according to claim 2 is characterized in that: The weather information includes temperature, humidity, wind speed, air pressure, and light.

4. The method for remotely controlling the opening and closing of an automatic road gate barrier according to claim 3 is characterized in that: Step S2 includes the following steps: S201: extracting time domain features of equipment operation monitoring parameters, wherein the time domain features include mean, variance, peak value and slope; S202: Convert the equipment operation monitoring parameters into the frequency domain by using Fourier transform, and extract frequency domain features; S203: extracting time series characteristics of equipment operation monitoring parameters using autocorrelation functions and cross-correlation functions.

5. The method for remotely controlling the opening and closing of an automatic road gate barrier according to claim 4 is characterized in that: Step S3 includes the following steps: S301: Standardizing equipment operation monitoring parameters, extracted time domain features, frequency domain features, time series features and environmental information; S302: performing multimodal data alignment on the standardized equipment operation monitoring parameters, time domain features, frequency domain features, time series features and environmental information; S303: Classify and combine the aligned multimodal data into a comprehensive data set.

6. The method for remotely controlling the opening and closing of an automatic road gate barrier according to claim 5, characterized in that: In step S302, the multimodal data alignment adopts linear interpolation method.

7. The method for remotely controlling the opening and closing of an automatic road gate barrier according to claim 6, characterized in that: Step S4 includes the following steps: S401: Input the comprehensive dataset into the pre-trained LSTM-CNN hybrid model through multiple channel input networks; S402: The LSTM-CNN hybrid model processes the input comprehensive data set, extracts local features through the convolution layer, captures time dependencies through the long short-term memory network, and performs nonlinear transformation through the fully connected layer, and finally outputs the event warning probability value; S403: Based on the generated event warning probability value and in combination with a predefined mapping table, an event warning type and a corresponding handling suggestion are generated.

8. The method for remotely controlling the opening and closing of an automatic road gate barrier according to claim 7, characterized in that: The mapping table includes a mapping relationship between a preset event warning probability threshold, an event warning type, and a corresponding handling suggestion.

9. The method for remotely controlling the opening and closing of an automatic road gate barrier according to claim 8, characterized in that: A Dropout layer is added between each layer of the LSTM-CNN hybrid model, wherein the dropout rate of the Dropout layer is preset based on an empirical rule.

10. A remote switch control system for an automatic road gate barrier, characterized in that: The remote switch control method for an automatic road gate barrier according to any one of claims 1 to 9 is applied, wherein the remote switch control system comprises: A data acquisition module is used to regularly obtain equipment operation monitoring parameters of the automatic road gate barrier and environmental information around the automatic road gate barrier; Feature extraction module, used to extract time domain features, frequency domain features and time series features of equipment operation monitoring parameters; A data processing module is used to combine equipment operation monitoring parameters, extracted time domain features, frequency domain features, time series features and environmental information into a comprehensive data set; A prediction module, used to input the comprehensive data set into a pre-trained LSTM-CNN hybrid model for online prediction, and generate event warning types and corresponding disposal suggestions; The control module is used to select corresponding disposal instructions to remotely control the operating status of the gate barrier according to the generated event warning type and corresponding disposal suggestions.

Images