Host Remote Control Terminal

Abstract

The present application provides a host remote control terminal, which relates to the technical field of remote control. The terminal includes: a monitoring sequence acquisition module for acquiring multiple combustible gas concentration sequences and humidity sequences monitored and remotely transmitted by a combustible gas monitoring host; an integrated restoration generation module for obtaining multiple generated combustible gas concentration sequence sets and generated humidity sequence sets; an accuracy offset analysis module for obtaining accuracy offset parameters; and a host calibration module for remotely controlling the combustible gas monitoring host to perform calibration according to a calibration period. Through the present application, the technical problems of great difficulty and long cycle in the remote control and accuracy calibration of the combustible gas monitoring host caused by environmental factors and the influence of the transmission process can be solved, and the technical effects of improving the monitoring accuracy and efficiency and reducing the complexity and time consumption of on-site operations can be achieved through remote accuracy offset analysis and calibration of the combustible gas monitoring host.

Description

Technical Field

[0001] This application relates to the technical field of remote control, and particularly to a host remote control terminal. Background Art

[0002] With the continuous improvement of industrial automation and intelligence levels, various monitoring hosts have been widely used in multiple fields, especially in safety fields such as fire protection, electrical fire, and combustible gas monitoring. These hosts are usually used for real-time monitoring and control of important equipment to ensure the safety of industrial production, buildings, etc. However, traditional monitoring and control devices have some limitations. Especially when it is necessary to remotely operate and accurately calibrate monitoring hosts of multiple brands and models, many technical obstacles are faced.

[0003] The accuracy of the monitoring host is easily affected by environmental factors (such as temperature, humidity, etc.) and the usage time. Existing calibration methods mostly rely on manual intervention and need to be carried out on-site, with a long cycle and low efficiency. This not only increases the operation and maintenance costs but also raises the risks brought by human operations. Summary of the Invention

[0004] The purpose of this application is to provide a host remote control terminal to solve the technical problems of difficult and long-cycle remote control and accuracy calibration of combustible gas monitoring hosts due to the influence of environmental factors and the transmission process.

[0005] In view of the above problems, this application provides a host remote control terminal.

[0006] This application provides a host remote control terminal, which includes: a monitoring sequence acquisition module for acquiring multiple combustible gas concentration sequences and humidity sequences monitored and remotely transmitted by a combustible gas monitoring host; an integrated restoration generation module for performing integrated restoration generation on the multiple combustible gas concentration sequences and humidity sequences to obtain multiple generated combustible gas concentration sequence sets and generated humidity sequence sets; an accuracy offset analysis module for performing accuracy offset analysis of the combustible gas monitoring host based on the multiple generated combustible gas concentration sequence sets and generated humidity sequence sets to obtain accuracy offset parameters, where the accuracy offset analysis includes fluctuation accuracy offset analysis and humidity accuracy offset analysis; and a host calibration module for configuring a calibration cycle according to the accuracy offset parameters and remotely controlling the combustible gas monitoring host to perform calibration according to the calibration cycle.

[0007] The technical solution provided in this application has at least the following technical effects or advantages:

[0008] The above-mentioned host remote control terminal first obtains various combustible gas concentration sequences and humidity sequences monitored and remotely transmitted by the combustible gas monitoring host, and then integrates and restores the various combustible gas concentration sequences and humidity sequences to obtain a plurality of generated combustible gas concentration sequence sets and generated humidity sequence sets; then, according to the plurality of generated combustible gas concentration sequence sets and generated humidity sequence sets, perform accuracy deviation analysis on the combustible gas monitoring host to obtain accuracy deviation parameters, where the accuracy deviation analysis includes fluctuation accuracy deviation analysis and humidity accuracy deviation analysis; finally, configure a calibration period according to the accuracy deviation parameters, and remotely control the combustible gas monitoring host to perform calibration according to the calibration period; through the above steps, the technical effect of improving the monitoring accuracy and efficiency and reducing the complexity and time consumption of on-site operations can be achieved by remotely analyzing and calibrating the accuracy deviation of the combustible gas monitoring host.

[0009] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically illustrates the embodiments of the present application. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only exemplary, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0011] Figure 1 It is a schematic structural diagram of the host remote control terminal of the present application.

[0012] Figure 2 It is a schematic flow diagram of the host remote control terminal of the present application for obtaining various combustible gas concentration sequences and humidity sequences monitored and remotely transmitted by the combustible gas monitoring host.

[0013] Description of the reference numerals: Monitoring sequence acquisition module 11, integration and restoration generation module 12, accuracy deviation analysis module 13, host calibration module 14. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] By providing a host remote control terminal, the present application solves the technical problems of difficult and time-consuming remote control and accuracy calibration of combustible gas monitoring hosts due to environmental factors and the influence of the transmission process, and achieves the technical effect of improving the monitoring accuracy and efficiency and reducing the complexity and time consumption of on-site operations through remote accuracy offset analysis and calibration of combustible gas monitoring hosts.

[0015] Next, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application. Additionally, it should be noted that for the sake of description, only the parts related to the present application are shown in the drawings rather than all of them.

[0016] Embodiment, please refer to the attached Figure 1 , the present application provides a host remote control terminal, and the terminal specifically includes the following modules:

[0017] A monitoring sequence acquisition module 11, configured to acquire multiple combustible gas concentration sequences and humidity sequences monitored and remotely transmitted by a combustible gas monitoring host.

[0018] Specifically, in the monitoring sequence acquisition module 11, a combustible gas monitoring host is used to monitor multiple combustible gases (such as methane) and humidity in the surrounding environment in real time, and the measured data is transmitted to the control terminal remotely. These data will form multiple combustible gas concentration sequences and humidity sequences, and these sequences respectively include the combustible gas concentrations and environmental humidity values at multiple time points. The monitoring host regularly acquires these data according to a preset monitoring frequency and sends them to the remote control terminal in the form of digital signals to ensure that the control terminal can receive information on environmental changes in real time.

[0019] Further, as Figure 2 shown, the present application provides a method for acquiring multiple combustible gas concentration sequences and humidity sequences monitored and remotely transmitted by a combustible gas monitoring host, including:

[0020] According to a preset monitoring and transmission frequency, acquire the concentrations of multiple combustible gases and the environmental humidity monitored and remotely transmitted by the combustible gas monitoring host within multiple recent timestamps, where the multiple combustible gases include methane, propane, and hydrogen; arrange the concentrations of the multiple combustible gases and the environmental humidity according to the multiple timestamps to obtain multiple combustible gas concentration sequences and humidity sequences.

[0021] In a preferred embodiment, according to the actual business requirements, the control terminal will preset the monitoring transmission frequency in advance, such as per second, per minute or per hour. The combustible gas monitoring host collects the concentrations of various combustible gases (such as methane, propane, hydrogen) in the environment and the corresponding environmental humidity according to the set monitoring transmission frequency. At each timestamp, the host collects the concentrations of various combustible gases and the environmental humidity at the current moment, forms an original data set, and transmits the monitoring data to the control terminal through a remote transmission interface (such as RS232, RS485, CAN interface, etc.) for further processing. After receiving the data within multiple timestamps, the control terminal sorts and arranges the data in timestamp order, classifies the concentrations and humidities of each combustible gas into independent sequences respectively, so as to form multiple combustible gas concentration sequences and humidity sequences. These sequences can ensure alignment in timestamps and are used for subsequent integrated restoration generation and accuracy offset analysis.

[0022] The integrated restoration generation module 12 is used to perform integrated restoration generation on the multiple combustible gas concentration sequences and humidity sequences to obtain multiple generated combustible gas concentration sequence sets and generated humidity sequence sets.

[0023] Specifically, in the integrated restoration generation module 12, after obtaining the multiple combustible gas concentration sequences and humidity sequences, due to environmental factors, errors of the combustible gas monitoring host itself, etc., there will be certain deviations in these data. To ensure the accuracy of the data, the control terminal performs integrated restoration on the multiple combustible gas concentration sequences and humidity sequences. Specifically, the obtained multiple combustible gas concentration sequences and humidity sequences are input into a pre-constructed restoration generation channel. Each channel restores different combustible gas or humidity data. These channels use integrated machine learning methods and process the data through multiple restoration paths to simulate and correct the influence of environmental factors, self-errors, etc. on the monitoring data. For example, some paths process minor measurement errors (such as tiny deviations caused by sensor drift), while other paths process larger deviations (such as large fluctuations caused by signal noise or environmental changes). These restoration paths make the finally generated concentration sequences and humidity sequences more accurate and reliable by repairing inaccurate data. After processing, these restoration generation channels output multiple generated combustible gas concentration sequence sets and generated humidity sequence sets. These data can be further used for accuracy offset analysis to ensure the accuracy and consistency of the monitoring data, and also provide a basis for subsequent remote control and calibration.

[0024] Furthermore, this application provides integrated restoration generation for the multiple combustible gas concentration sequences and humidity sequences to obtain multiple generated combustible gas concentration sequence sets and generated humidity sequence sets, including:

[0025] Based on integrated machine learning, multiple combustible gas restoration and generation channels and humidity restoration and generation channels are constructed. Among them, each restoration and generation channel includes multiple restoration and generation paths; the multiple combustible gas concentration sequences and humidity sequences are respectively input into the multiple combustible gas restoration and generation channels and humidity restoration and generation channels, and multiple generated combustible gas concentration sequence sets and generated humidity sequence sets are obtained through restoration and generation.

[0026] In a preferred embodiment, through an integrated machine learning method, multiple restoration and generation channels are constructed for different combustible gas and humidity data respectively. Each channel focuses on processing a certain type of data, such as the concentration of combustible gas or humidity. Each channel contains multiple restoration and generation paths, which are responsible for correcting data according to different data deviations. For example, some paths correct minor errors, while other paths correct larger deviations; subsequently, the obtained multiple combustible gas concentration sequences and humidity sequences are input into these constructed restoration and generation channels. Each data sequence is respectively transmitted into the corresponding combustible gas restoration and generation channel or humidity restoration and generation channel. The multiple restoration and generation paths in the channel will process the data in parallel, correct it according to the training model, and eliminate or reduce the errors and fluctuations in the data; in this way, multiple combustible gas concentration sequences and humidity sequences are restored and generated, and finally multiple generated combustible gas concentration sequence sets and generated humidity sequence sets are obtained. These generated sequence sets contain more accurate and reliable monitoring data, providing a more precise basis for subsequent analysis, calibration, and control.

[0027] Furthermore, the present application provides a method for constructing multiple combustible gas restoration and generation channels and humidity restoration and generation channels based on integrated machine learning, including:

[0028] Using integrated learning and generative adversarial networks, a first combustible gas restoration and generation channel for the first combustible gas is constructed, where the first combustible gas restoration and generation channel includes multiple first combustible gas restoration and generation paths; continue to construct multiple combustible gas restoration and generation channels and humidity restoration and generation channels corresponding to other various combustible gases.

[0029] In an alternative embodiment, in order to construct a restoration generation channel for the first combustible gas (e.g., methane), a framework that can simultaneously capture the influence of environmental factors and the characteristics of measurement errors needs to be designed based on the method of integrated learning and generative adversarial network. The framework contains multiple restoration generation paths, and each path is corrected according to different deviation degrees of the data. Specifically, first, the monitoring records of the first combustible gas are collected from the historical records to construct the first combustible gas concentration restoration training samples, including the transmitted concentration sequence and the original concentration sequence at the host end; subsequently, based on the training mechanism of the generative adversarial network, through the adversarial learning between the generator and the discriminator, the deviation in the transmitted data is corrected. The generator is responsible for generating restoration data close to the true value, while the discriminator is used to evaluate the quality of the generated data. After independent training, each first combustible gas restoration generation path can focus on correcting the data errors with different deviation degrees; then, multiple independently trained first combustible gas restoration generation paths are combined in parallel to form a complete first combustible gas restoration generation channel. After the construction of the first combustible gas restoration generation channel is completed, using a similar method, continue to construct the corresponding restoration generation channels for other combustible gases (such as propane, hydrogen) and humidity data respectively. Each channel also contains multiple restoration generation paths inside, and the paths can be optimally configured based on specific data characteristics and influencing factors; finally, all channels are integrated into the control terminal, which can process the corresponding combustible gas concentration and humidity data respectively, providing high-precision restoration generation data support for subsequent accuracy offset analysis and calibration.

[0030] Furthermore, the present application provides a first combustible gas restoration generation channel for the first combustible gas by using integrated learning and generative adversarial network, including:

[0031] According to the monitoring remote transmission records of the first combustible gas in the historical time, collect the set of sample first combustible gas concentration sequences after remote transmission, and collect the set of sample first original combustible gas concentration sequences recorded in the combustible gas monitoring host; divide the set of sample first combustible gas concentration sequences and the set of sample first original combustible gas concentration sequences to obtain multiple first combustible gas concentration restoration training samples; respectively use the multiple first combustible gas concentration restoration training samples, and based on the generative adversarial network, train multiple first combustible gas restoration generation paths until the training verification converges; combine the multiple first combustible gas restoration generation paths to obtain the first combustible gas restoration generation channel.

[0032] In an alternative embodiment, when constructing the first combustible gas restoration generation channel, first, through the combustible gas monitoring host, obtain the remote transmission records of the first combustible gas (such as methane) over a historical period. These records include the concentration data transmitted from the host to the control terminal. By organizing these data, a sample set of the first combustible gas concentration sequences can be constructed, which reflects the concentration changes of the combustible gas at different time points. In addition, the original combustible gas concentrations are collected from the local records of the host to construct a sample set of the first original combustible gas concentration sequences, which are the unprocessed original measurement results. Then, based on the deviation between the sample set of the first combustible gas concentration sequences and the sample set of the first original combustible gas concentration sequences, the collected sample set of the first combustible gas concentration sequences and the sample set of the first original combustible gas concentration sequences are divided to form multiple training sample sets. For example, those with an average deviation between 1% and 5% are divided into one training sample set, those with an average deviation between 5% and 15% are divided into one training sample set, and those with an average deviation above 15% are divided into one training sample set. Each training sample is composed of a pair of remote transmission data and original data, aiming to help learn how to recover more accurate measurement results from the transmission data. Then, use these divided training samples to train a generative adversarial network (GAN). The generative adversarial network consists of a generator and a discriminator. The generator is responsible for generating the restored combustible gas concentration data according to the input training samples, while the discriminator is used to determine whether the generated concentration data is close to the real data. During the training process, the generator continuously generates the restored combustible gas concentration data according to the input training samples and gradually optimizes the quality of the generated data through adversarial learning with the discriminator. The task of the discriminator is to evaluate the gap between the generated data and the real data and determine whether it is real enough. The generator and the discriminator are jointly optimized through backpropagation. The generator adjusts its parameters to make the generated data closer to the real data, while the discriminator continuously improves its judgment ability to identify the differences between the generated data and the real data. After multiple rounds of adversarial training, until the generator can generate restored data very similar to the real data and the judgment ability of the discriminator reaches the best, the training process is completed. Through this training process, the generator learns how to effectively recover more accurate monitoring data from the original concentration data. The correction methods learned by the generator are embodied in multiple first combustible gas restoration generation paths, and each path corresponds to a different deviation range. Finally, the multiple fully trained restoration generation paths are combined into a complete restoration generation channel, which can be used to process the concentration data of the first combustible gas. This channel can generate a more accurate concentration sequence according to the input data for subsequent accuracy analysis and calibration.

[0033] An accuracy offset analysis module is used to perform accuracy offset analysis on the combustible gas monitoring host according to the multiple generated combustible gas concentration sequence sets and humidity sequence sets, and obtain accuracy offset parameters. Among them, the accuracy offset analysis includes fluctuation accuracy offset analysis and humidity accuracy offset analysis.

[0034] Specifically, in the accuracy offset analysis module 13, the fluctuations of gas concentration and the changes in environmental humidity will affect the sensor data in the combustible gas monitoring host, thereby affecting the accuracy of the monitoring data. To ensure that the monitoring host can still provide accurate data under various environmental conditions, it is necessary to perform accuracy offset analysis to evaluate the specific impacts of these fluctuations and humidity changes on the monitoring results. During this process, the control terminal analyzes multiple generated combustible gas concentration sequences and humidity sequences, calculates the changes in each data sequence within a unit time (such as 30 minutes), and the analysis process will evaluate the impacts of the fluctuations of gas concentration and the changes in humidity on the accuracy of the monitoring host within this period. The accuracy offset analysis includes fluctuation accuracy offset analysis and humidity accuracy offset analysis. Among them, the fluctuation analysis focuses on the impact of gas concentration fluctuations on the sensor detection results and is carried out through steps such as mean calculation, deviation calculation, and accuracy offset analysis channel calculation, while the humidity analysis focuses on the impact of humidity changes on the monitoring accuracy and is carried out through steps such as mean calculation and accuracy offset analysis channel calculation; finally, through these analyses, accuracy offset parameters can be obtained, which represent the change range of monitoring accuracy within a unit time, help the control terminal understand the error range of the monitoring host under specific environmental changes, and provide a basis for subsequent calibration and adjustment.

[0035] Furthermore, this application provides performing accuracy offset analysis on the combustible gas monitoring host according to the multiple generated combustible gas concentration sequence sets and humidity sequence sets, and obtaining accuracy offset parameters, including:

[0036] Randomly select an initial first generated combustible gas concentration within multiple first generated combustible gas concentration sequences in the first combustible gas; randomly select several first generated combustible gas concentrations within the multiple first generated combustible gas concentration sequences, calculate the concentration deviation percentage between the mean of the several first generated combustible gas concentrations and the initial first generated combustible gas concentration, and obtain a first initial combustible gas concentration fluctuation parameter; continue to calculate and obtain multiple first initial combustible gas concentration fluctuation parameters, and calculate the mean to obtain a first combustible gas concentration fluctuation parameter; continue to calculate and obtain multiple combustible gas concentration fluctuation parameters according to other multiple generated combustible gas concentration sequence sets; calculate the humidity mean within the humidity sequence set; respectively perform accuracy offset analysis on the combustible gas monitoring host according to the multiple combustible gas concentration fluctuation parameters and the humidity mean to obtain multiple fluctuation accuracy offset parameters and humidity accuracy offset parameters; calculate the mean of the multiple fluctuation accuracy offset parameters and humidity accuracy offset parameters to obtain an accuracy offset parameter.

[0037] In an alternative embodiment, from among the multiple first generated combustible gas concentration sequences that generate a combustible gas concentration sequence set, a random initial first generated combustible gas concentration value is selected as a reference, and this initial first generated combustible gas concentration value will serve as the benchmark point for deviation analysis; subsequently, from among the multiple first generated combustible gas concentration sequences, several first generated combustible gas concentrations are randomly selected, the mean of these concentration values is calculated, and the specific data volume is determined according to actual business requirements. Then, the deviation between the mean and the initial first generated combustible gas concentration value is calculated, and the calculated deviation is divided by the initial first generated combustible gas concentration value to obtain the concentration deviation percentage. This concentration deviation percentage reflects the fluctuation of the concentration values within the sequence. Through this method, a first initial combustible gas concentration fluctuation parameter (i.e., the concentration deviation percentage) can be obtained, representing the degree of fluctuation of the combustible gas concentration during this time period; thereafter, the same calculation is continued for other first generated combustible gas concentration sequences until each combustible gas concentration sequence has been calculated, thereby obtaining multiple first initial combustible gas concentration fluctuation parameters. Then, the mean of all first initial combustible gas concentration fluctuation parameters is calculated to obtain the first combustible gas concentration fluctuation parameter, representing the average level of concentration fluctuation of all concentration sequences in this combustible gas concentration sequence set; then, for other combustible gas concentration sequence sets, the same calculation as above is performed to obtain multiple combustible gas concentration fluctuation parameters, including the second combustible gas concentration fluctuation parameter, the third combustible gas concentration fluctuation parameter, etc. After calculating the combustible gas concentration fluctuation parameter for each combustible gas concentration sequence set, the control terminal will also calculate the mean of the humidity sequence set to obtain the humidity mean within the humidity sequence set, reflecting the overall level of the environmental humidity; further, based on multiple combustible gas concentration fluctuation parameters and the humidity mean, the accuracy offset analysis channel pre-constructed is used to perform accuracy offset analysis on the combustible gas monitoring host respectively. The accuracy offset analysis channel will use multiple internal fluctuation accuracy offset analysis branches to perform fluctuation accuracy offset analysis on multiple combustible gas concentration fluctuation parameters to generate multiple fluctuation accuracy offset parameters, indicating the impact of concentration fluctuation on monitoring accuracy, and use the internal humidity accuracy offset analysis branch to perform humidity accuracy offset analysis on the humidity mean to generate a humidity accuracy offset parameter, reflecting the impact of humidity change on monitoring accuracy; finally, the mean of all fluctuation accuracy offset parameters and humidity accuracy offset parameters is calculated to obtain the final accuracy offset parameter. This parameter represents the overall deviation of monitoring accuracy caused by concentration fluctuation and humidity change within a certain period of time, serving as the basis for subsequent calibration and adjustment. Through the above process, it is possible to comprehensively analyze and quantify the monitoring accuracy deviation caused by concentration fluctuation and humidity change, providing a basis for further optimizing the stability and accuracy of the combustible gas monitoring host.

[0038] Further, the present application provides an accuracy offset analysis for the combustible gas monitoring host respectively according to the multiple combustible gas concentration fluctuation parameters and the humidity mean value, and obtains a plurality of fluctuation accuracy offset parameters and humidity accuracy offset parameters, including:

[0039] According to the monitoring accuracy test data of the combustible gas monitoring host, collect a plurality of sample combustible gas concentration fluctuation parameter sets and sample humidity mean value sets, and obtain the change range of the monitoring accuracy of the combustible gas monitoring host per unit time under different sample combustible gas concentration fluctuation parameters and sample humidity mean values, which is marked as the sample accuracy offset parameter set; respectively use the plurality of sample combustible gas concentration fluctuation parameter sets and sample humidity mean value sets as input features, use the sample accuracy offset parameter set as the output feature, train a plurality of fluctuation accuracy offset analysis branches and humidity accuracy offset analysis branches, and combine them to obtain an accuracy offset analysis channel; input the multiple combustible gas concentration fluctuation parameters and humidity mean values into the accuracy offset analysis channel respectively, and obtain a plurality of fluctuation accuracy offset parameters and humidity accuracy offset parameters.

[0040] In an alternative embodiment, based on the monitoring accuracy test data of the combustible gas monitoring host, multiple sets of sample combustible gas concentration fluctuation parameters and sets of sample humidity means are collected. Among them, each set of sample combustible gas concentration fluctuation parameters corresponds to a kind of combustible gas. These sample data reflect the influence of combustible gas concentration fluctuation and humidity on monitoring accuracy under different environmental conditions. Subsequently, calculate the change range of the monitoring accuracy of the host corresponding to the combustible gas concentration fluctuation parameters and humidity means of each sample per unit time. These change ranges are the sample accuracy offset parameters, which represent the change range of the monitoring accuracy of the combustible gas monitoring host per unit time under specific concentration fluctuation and humidity conditions. After that, use these sets of sample combustible gas concentration fluctuation parameters and sets of sample humidity means as input features, and at the same time use the previously obtained set of sample accuracy offset parameters as output features to train and generate multiple analysis branches. Each branch is trained respectively for the influence of combustible gas concentration fluctuation and humidity, that is, the fluctuation accuracy offset analysis branch and the humidity accuracy offset analysis branch are trained respectively. These branches can effectively analyze and predict the change of monitoring accuracy under different concentration fluctuation and humidity conditions by learning the relationship between input features and output features. The construction methods of multiple fluctuation accuracy offset analysis branches and humidity accuracy offset analysis branches are the same, and they are all constructed by a fully connected neural network, and can also be constructed based on decision trees, random forests, deep neural networks, etc. Taking the fully connected neural network as an example, use this network to construct a structure of a fluctuation accuracy offset analysis branch, including an input layer, a hidden layer, an output layer, etc. Then, use a standard initialization method (such as Xavier or He initialization) to initialize the weights of the network, and use the set of sample combustible gas concentration fluctuation parameters of a certain combustible gas as input features to be passed to the neural network. In the forward propagation process, the input features are passed layer by layer through the input layer and the hidden layer (using the ReLU activation function), and the predicted fluctuation accuracy offset parameters are calculated through the output layer. Then, use the mean squared error (MSE) loss function to calculate the loss between the predicted fluctuation accuracy offset parameters and the actual values, and calculate the gradient of the loss with respect to the weights of each layer through the backpropagation algorithm. Then, use the Adam optimizer to optimize the parameters of the neural network, adjust the weights and biases of each layer to minimize the value of the loss function, and repeat this process until the set maximum number of training times is reached or the loss stops decreasing. After the training is completed, use the data not used for training to evaluate the performance of the neural network to ensure that the neural network can accurately predict the influence of combustible gas concentration fluctuation and humidity change on the monitoring accuracy offset. If the accuracy rate reaches the preset accuracy, the current neural network is used as a fluctuation accuracy offset analysis branch. If the accuracy rate does not meet the requirements, continue to optimize by adjusting hyperparameters such as the learning rate and batch size to improve the prediction ability.In the same manner as described above, multiple fluctuation accuracy offset analysis branches will be trained using the remaining set of sample combustible gas concentration fluctuation parameters and the set of sample accuracy offset parameters, and a humidity accuracy offset analysis branch will be trained using the set of sample humidity means and the set of sample accuracy offset parameters. Then, these branches will be combined in parallel to construct an accuracy offset analysis channel. Finally, multiple combustible gas concentration fluctuation parameters and humidity means will be input into the accuracy offset analysis channel, and through the analysis channel, multiple fluctuation accuracy offset parameters and humidity accuracy offset parameters will be obtained. These parameters reflect the accuracy offset situation of the monitoring host under different fluctuation and humidity conditions, providing a basis for subsequent calibration and adjustment. Through this process, it is possible to comprehensively evaluate and analyze the offset situation of monitoring accuracy under different environmental conditions, thereby providing support for further improving the monitoring accuracy.

[0041] A host calibration module, configured to configure a calibration period according to the accuracy offset parameters and remotely control the combustible gas monitoring host to perform calibration according to the calibration period.

[0042] Specifically, in the host calibration module 14, according to the obtained accuracy offset parameters, the control terminal will determine an appropriate calibration period. The accuracy offset parameters reflect how much the accuracy of the monitoring host has changed within a certain period of time, so they can be used to judge when to perform calibration to maintain the accuracy of monitoring. If the accuracy offset parameters are large, a shorter calibration period will be set; conversely, if the accuracy offset is small, a longer calibration period will be set. Finally, the control terminal will remotely control the combustible gas monitoring host to automatically perform calibration operations according to the configured calibration period to ensure the continuous accuracy and reliability of its monitoring results.

[0043] Furthermore, this application provides configuring a calibration period according to the accuracy offset parameters and remotely controlling the combustible gas monitoring host to perform calibration according to the calibration period, including:

[0044] Calculating and obtaining the time when the accuracy offset amplitude reaches a preset accuracy offset threshold according to the accuracy offset parameters as the offset calibration time; using the offset calibration time as the calibration period and remotely controlling the combustible gas monitoring host to perform calibration according to the calibration period.

[0045] In a preferred embodiment, the calculated accuracy offset parameter, i.e., the change amplitude of the monitoring accuracy per unit time (e.g., the change amplitude every 30 minutes), is used as the basic index for evaluating the accuracy change of the monitoring host. According to the set preset accuracy offset threshold (such as the allowable maximum accuracy offset range), the time required to reach this threshold is calculated by the ratio of the preset accuracy offset threshold to the accuracy offset parameter. This time represents the maximum time interval allowed before the accuracy offset of the monitoring host may exceed the acceptable range. Subsequently, the calculated offset calibration time is used as the calibration period to ensure that the monitoring host completes the calibration operation before the deviation exceeds the acceptable range. This can not only ensure the monitoring accuracy but also avoid the waste of resources caused by overly frequent calibration. After that, according to the set calibration period, a calibration instruction is sent to the combustible gas monitoring host in a remote control manner, enabling it to automatically perform the calibration operation at the end of each calibration period. Remote control ensures the automation and efficiency of the operation and reduces the need for manual intervention. Through the above process, the calibration period can be flexibly adjusted according to the actual accuracy change amplitude, ensuring that the monitoring host always maintains a high-precision working state while optimizing the utilization rate of calibration resources.

[0046] In summary, the host remote control terminal provided by the present application has the following technical effects:

[0047] The present application obtains multiple combustible gas concentration sequences and humidity sequences monitored and remotely transmitted by the combustible gas monitoring host through the monitoring sequence acquisition module, integrates and restores the multiple combustible gas concentration sequences and humidity sequences through the integrated restoration generation module to obtain multiple generated combustible gas concentration sequence sets and generated humidity sequence sets, and performs accuracy offset analysis on the combustible gas monitoring host according to the multiple generated combustible gas concentration sequence sets and humidity sequence sets through the accuracy offset analysis module to obtain the accuracy offset parameter. Among them, the accuracy offset analysis includes fluctuating accuracy offset analysis and humidity accuracy offset analysis. The host calibration module configures the calibration period according to the accuracy offset parameter and remotely controls the combustible gas monitoring host to perform calibration according to the calibration period. These technical effects together solve the technical problems of the large difficulty and long period in the remote control and accuracy calibration of the combustible gas monitoring host due to the influence of environmental factors and the transmission process, and achieve the technical effects of improving the monitoring accuracy and efficiency and reducing the complexity and time consumption of on-site operations through the remote accuracy offset analysis and calibration of the combustible gas monitoring host.

[0048] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but rather is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0049] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. Host remote control terminal, characterized in that, The terminal includes: A monitoring sequence acquisition module, configured to acquire multiple combustible gas concentration sequences and humidity sequences monitored and remotely transmitted by a combustible gas monitoring host; An integrated restoration generation module, configured to perform integrated restoration generation on the multiple combustible gas concentration sequences and humidity sequences to obtain multiple generated combustible gas concentration sequence sets and generated humidity sequence sets; An accuracy deviation analysis module, configured to perform accuracy deviation analysis on the combustible gas monitoring host according to the multiple generated combustible gas concentration sequence sets and generated humidity sequence sets to obtain accuracy deviation parameters, where the accuracy deviation analysis includes fluctuation accuracy deviation analysis and humidity accuracy deviation analysis; A host calibration module, configured to configure a calibration period according to the accuracy deviation parameters and remotely control the combustible gas monitoring host to perform calibration according to the calibration period; Performing integrated restoration generation on the multiple combustible gas concentration sequences and humidity sequences to obtain multiple generated combustible gas concentration sequence sets and generated humidity sequence sets, includes: Based on integrated machine learning, constructing multiple combustible gas restoration generation channels and humidity restoration generation channels, where each restoration generation channel includes multiple restoration generation paths; Inputting the multiple combustible gas concentration sequences and humidity sequences into the multiple combustible gas restoration generation channels and humidity restoration generation channels respectively, and performing restoration generation to obtain multiple generated combustible gas concentration sequence sets and generated humidity sequence sets; Based on integrated machine learning, constructing multiple combustible gas restoration generation channels and humidity restoration generation channels, includes: Using integrated learning and a generative adversarial network to construct a first combustible gas restoration generation channel for a first combustible gas, where the first combustible gas restoration generation channel includes multiple first combustible gas restoration generation paths; Continuing to construct multiple combustible gas restoration generation channels and humidity restoration generation channels corresponding to other multiple combustible gases.

2. The host remote control terminal according to claim 1, characterized in that, Acquiring multiple combustible gas concentration sequences and humidity sequences monitored and remotely transmitted by a combustible gas monitoring host, includes: According to a preset monitoring and transmission frequency, acquiring the concentrations of multiple combustible gases and the ambient humidity monitored and remotely transmitted by the combustible gas monitoring host within multiple recent timestamps, where the multiple combustible gases include methane, propane, and hydrogen; Arranging the concentrations of multiple combustible gases and the ambient humidity according to the multiple timestamps to obtain multiple combustible gas concentration sequences and humidity sequences.

3. The host remote control terminal according to claim 1, characterized in that, Using integrated learning and a generative adversarial network to construct a first combustible gas restoration generation channel for a first combustible gas, includes: According to the monitoring and remote transmission records of the first combustible gas in historical time, collecting a sample first combustible gas concentration sequence set after remote transmission, and collecting a sample first original combustible gas concentration sequence set recorded in the combustible gas monitoring host; Dividing the sample first combustible gas concentration sequence set and the sample first original combustible gas concentration sequence set to obtain multiple first combustible gas concentration restoration training samples; Respectively using the multiple first combustible gas concentration restoration training samples to train multiple first combustible gas restoration generation paths based on a generative adversarial network until the training verification converges; Combine the multiple first flammable gas restoration generation paths to obtain a first flammable gas restoration generation channel.

4. The host remote control terminal according to claim 1, characterized in that, According to the multiple generated flammable gas concentration sequence sets and humidity sequence sets, perform accuracy offset analysis on the flammable gas monitoring host to obtain accuracy offset parameters, including: Randomly select an initial first generated flammable gas concentration within the multiple first generated flammable gas concentration sequences in the first flammable gas; Randomly select several first generated flammable gas concentrations within the multiple first generated flammable gas concentration sequences, calculate the concentration deviation percentage of the mean of the several first generated flammable gas concentrations from the initial first generated flammable gas concentration, and obtain a first initial flammable gas concentration fluctuation parameter; Continue to calculate to obtain multiple first initial flammable gas concentration fluctuation parameters, and calculate the mean to obtain a first flammable gas concentration fluctuation parameter; Continue to calculate to obtain multiple flammable gas concentration fluctuation parameters according to other multiple generated flammable gas concentration sequence sets; Calculate the humidity mean within the humidity sequence set; According to the multiple flammable gas concentration fluctuation parameters and humidity mean, respectively perform accuracy offset analysis on the flammable gas monitoring host to obtain multiple fluctuation accuracy offset parameters and humidity accuracy offset parameters; Calculate the mean of the multiple fluctuation accuracy offset parameters and humidity accuracy offset parameters to obtain accuracy offset parameters.

5. The host remote control terminal according to claim 4, wherein According to the multiple flammable gas concentration fluctuation parameters and humidity mean, respectively perform accuracy offset analysis on the flammable gas monitoring host to obtain multiple fluctuation accuracy offset parameters and humidity accuracy offset parameters, including: According to the monitoring accuracy test data of the flammable gas monitoring host, collect multiple sample flammable gas concentration fluctuation parameter sets and sample humidity mean sets, and obtain the change range of the monitoring accuracy of the flammable gas monitoring host per unit time under different sample flammable gas concentration fluctuation parameters and sample humidity means, marked as a sample accuracy offset parameter set; Respectively use the multiple sample flammable gas concentration fluctuation parameter sets and sample humidity mean sets as input features, use the sample accuracy offset parameter set as the output feature, train multiple fluctuation accuracy offset analysis branches and humidity accuracy offset analysis branches, and combine to obtain an accuracy offset analysis channel; Input the multiple flammable gas concentration fluctuation parameters and humidity mean into the accuracy offset analysis channel respectively to obtain multiple fluctuation accuracy offset parameters and humidity accuracy offset parameters.

6. The host remote control terminal according to claim 1, wherein, According to the accuracy offset parameters, configure a calibration period, and remotely control the flammable gas monitoring host to perform calibration according to the calibration period, including: According to the accuracy offset parameters, calculate and obtain the time when the accuracy offset amplitude reaches a preset accuracy offset threshold as the offset calibration time; Use the offset calibration time as the calibration period, and remotely control the flammable gas monitoring host to perform calibration according to the calibration period.

Images