Intelligent control method and intelligent control device for gas charging and distributing system

Abstract

The invention relates to the technical field of artificial intelligence, in particular to an intelligent control method and an intelligent control device of a gas charging and distributing system. The intelligent control method of the gas filling and distributing system comprises the steps that the number of gas filling cylinders is obtained, and a task scheme and a process are formulated based on a pre-trained intelligent allocation model; the preparation process module, the mixing process module and the filling process module are allocated to work according to a task scheme and a flow; monitoring the work progress in real time, judging whether the work progress meets the requirements of the task scheme and the process or not, and if not, adjusting the scheme and the process based on the intelligent deployment model; operating parameters of the preparation process module, the mixing process module and the filling process module are collected in real time, and whether faults exist or not and whether parts need to be maintained or not are judged based on a pre-trained fault diagnosis model; if a fault exists, the fault is positioned, a maintenance scheme is formulated, the work of the preparation process module, the mixing process module and the filling process module is stopped, and if part maintenance is needed, a corresponding maintenance plan is formulated.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an intelligent control method and an intelligent control device for a gas filling and distribution system. Background Art

[0002] The gas filling system mainly includes three processes: preparation, mixing, and filling of different gases (such as nitrogen, helium, oxygen, etc.) according to a predetermined ratio. The preparation stage is to prepare the mixed gas into the gas cylinder according to the ratio of helium, nitrogen, oxygen or helium-oxygen mixed gas by partial pressure method or mass method; the mixing stage is to mix the prepared mixed gas evenly; the filling stage is to fill the mixed gas and pure oxygen into the gas cylinder. The process accuracy, efficiency and connection efficiency of each process stage directly affect the accuracy and efficiency of the gas filling system.

[0003] For example, if the partial pressure method is used in the preparation process, a booster device is needed to pressurize the gas. Compressing the gas will increase the gas temperature. The temperature changes during the preparation process and is nonlinear, which makes the partial pressure method preparation accuracy low. If the mass method is used to prepare the mixed gas, the calculation is complicated and the operation is cumbersome. In order to ensure the preparation accuracy and efficiency, consider using a fully automatic control device to prepare the mixed gas. Similarly, the mixing and filling processes can also use fully automatic control devices to improve process efficiency and accuracy, and can improve the connection efficiency of the three process stages.

[0004] However, the automated gas filling and dispensing system has the following problems: each process stage (preparation, mixing, filling) can only be carried out independently, and the equipment in other stages is inactive during a certain stage. This leads to inefficient use of equipment, and it is impossible to prepare, mix and fill at the same time, and there is limited room for improving the overall system efficiency. In addition, the existing system lacks effective fault diagnosis and preventive maintenance functions, which are crucial to ensure the safe operation of the system. Summary of the invention

[0005] In order to improve the equipment utilization and fault diagnosis capability of a gas charging and distributing system, the embodiments described herein provide an intelligent control method and an intelligent control device of a gas charging and distributing system, and a computer-readable storage medium storing a computer program.

[0006] According to a first aspect of the present invention, an intelligent control method for a gas filling and dispensing system is provided, wherein the gas filling and dispensing system comprises a preparation process module, a mixing process module, and a filling process module, which comprises: Obtain the number of gas cylinders to be filled, formulate task plans and processes based on the pre-trained intelligent deployment model, and deploy the preparation process module, mixing process module, and filling process module according to the task plan and process; monitor the progress of the preparation process, mixing process, and filling process in real time to determine whether they meet the requirements of the task plan and process. If not, adjust the plan and process based on the intelligent deployment model; if they meet, determine whether the task requirements are met. If not, deploy the preparation process module, mixing process module, and filling process module according to the current plan and process until the task requirements are met. Collect the operating parameters of the preparation process module, mixing process module, and filling process module in real time, and determine whether there is a fault and whether the component needs maintenance based on the pre-trained fault diagnosis model; if there is a fault, locate the fault and formulate a maintenance plan, stop the preparation process module, mixing process module, and filling process module, and formulate a corresponding maintenance plan if component maintenance is required.

[0007] In some embodiments of the present disclosure, the operating parameters collected in real time include voltage, current, and frequency signals of electrical equipment and pressure, quality, temperature, duration, and sound data of mechanical equipment.

[0008] In some embodiments of the present disclosure, the intelligent deployment model is trained based on the following steps: The historical data of the three process stages of preparation, mixing and filling in the gas filling operation are obtained, including pressure, quality, temperature and duration; the historical data are converted into image data, and the image data and gas cylinder filling tasks of different quantities and types are input into the convolutional neural network for training to obtain a pre-trained intelligent deployment model.

[0009] In some embodiments of the present disclosure, the fault diagnosis model is trained by the following steps: During the operation of the gas charging and distributing system, time series data including voltage, current, frequency, pressure, mass, temperature, duration, and sound data are collected; the time series data is converted into images, and the convolutional neural network is trained using images and labeled fault samples to obtain a pre-trained fault diagnosis model.

[0010] In some embodiments of the present disclosure, the fault diagnosis model includes an electrical fault model, a mechanical fault model and a maintenance database. The electrical fault model is obtained through deep learning training by forming an image of voltage, current and frequency signal data output by the electrical equipment; the mechanical fault model is obtained through deep learning training by forming an image of pressure, mass, temperature, duration and sound data; the maintenance database stores data on maintenance time intervals and last maintenance time of various components.

[0011] According to a second aspect of the present disclosure, there is provided an intelligent control device for a gas charging and distribution system, comprising: a data acquisition module, a preparation process module, a mixing process module, a filling process module, an intelligent mixing equipment module and a fault diagnosis module; the data acquisition module is used for collecting various parameters of the preparation process module, the mixing process module and the filling process module in real time, monitoring the process progress in real time, and transmitting the various parameters and process progress to the intelligent mixing equipment model and the fault diagnosis module; the intelligent mixing equipment module is used for formulating task plans and processes based on the intelligent mixing model, and adjusting the task plans and processes according to the various parameters and process progress; the fault diagnosis module is used for judging whether there are faults and components that need maintenance in the gas charging and distribution system based on the various parameters and the fault diagnosis model, determining the fault location and formulating a repair plan and maintenance plan.

[0012] In some embodiments of the present disclosure, the intelligent batching equipment module is used to obtain historical data of the three process stages of preparation, mixing and filling in the gas filling operation, and the historical data includes pressure, quality, temperature, and duration; the historical data is converted into image data, and the image data and gas cylinder filling tasks of different quantities and types are input into a convolutional neural network for training to obtain a pre-trained intelligent batching model.

[0013] In some embodiments of the present disclosure, the fault diagnosis module is used to collect time series data including voltage, current, frequency, pressure, mass, temperature, duration, and sound data during the operation of the filling and distribution system; convert the time series data into images, and use the images and labeled fault samples to train the convolutional neural network to obtain a pre-trained fault diagnosis model.

[0014] In some embodiments of the present disclosure, the preparation process module is used to prepare materials according to the task plan, the mixing process module is used to mix the prepared materials according to the plan requirements, and the filling process module is used to fill the prepared and mixed materials into gas cylinders.

[0015] According to a third aspect of the present disclosure, a computer-readable storage medium storing a computer program is provided, wherein the computer program, when executed by a processor, implements the steps of the intelligent control method of the charging and distributing gas system according to the first aspect of the present disclosure.

[0016] In summary, the intelligent control method and device of the gas charging and distributing system provided by the present invention can at least achieve the following technical effects: By using the intelligent equipment module to monitor and adjust the task progress in real time, the entire gas filling process can be ensured to proceed smoothly, human intervention and operational errors can be minimized, and the flexibility and efficiency of the system can be improved. Using deep learning and artificial intelligence technology, real-time fault detection, accurate positioning, and automatic generation of maintenance plans can be achieved, thereby improving the reliability and safety of the system. By analyzing the use status of the equipment's wearing parts, operators can be reminded to perform maintenance in a timely manner to ensure that the equipment always maintains the best operating state and extends the service life of the equipment. Once a fault is detected, the system will automatically stop the relevant functional modules to prevent equipment failures from causing larger-scale damage and ensure production safety.

[0017] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments will be briefly described below. It should be noted that the drawings described below only relate to some embodiments of the present disclosure, but are not intended to limit the present disclosure, wherein: Figure 1 A schematic diagram showing the structure of an intelligent control device for a gas charging and distributing system according to an embodiment of the present invention is shown; Figure 2 A schematic diagram of the working process of the intelligent allocation device module according to an embodiment of the present disclosure is shown; Figure 3 A schematic diagram showing the working process of the fault diagnosis module according to an embodiment of the present disclosure is shown. Figure 4 A schematic flow chart of an intelligent control method for a gas charging and distributing system according to an embodiment of the present disclosure is shown.

[0019] It should be noted that the elements in the drawings are schematic and not drawn to scale. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work also fall within the scope of protection of the present disclosure.

[0021] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which the subject matter of the present disclosure belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meanings in the context of the specification and the relevant art, and will not be interpreted in an idealized or overly formal form unless otherwise explicitly defined herein. In addition, terms such as "first" and "second" are only used to distinguish one component (or a portion of a component) from another component (or another portion of a component).

[0022] The present invention adds an intelligent adjustment equipment module and a fault diagnosis module on the basis of the existing automatic control device of the gas filling system. Figure 1 FIG. 2 shows a schematic diagram of the structure of an intelligent control device for a gas filling system according to an embodiment of the present invention. Figure 1 As shown, the intelligent control device of the gas charging and dispensing system includes not only a data acquisition module, a preparation process module, a mixing process module and a filling process module, but also an intelligent dispensing equipment module and a fault diagnosis module.

[0023] Among them, the preparation process module is responsible for preparing materials (helium-nitrogen-oxygen mixed gas or helium-oxygen mixed gas) according to the task plan to ensure the accuracy of the ratio. During the execution of the task, the preparation process module provides real-time feedback on pressure, temperature, duration and other data for analysis and adjustment by the artificial intelligence equipment model.

[0024] The mixing process module is responsible for mixing the prepared materials (helium, nitrogen and oxygen mixed gas or helium and oxygen mixed gas) according to the requirements of the plan to ensure the uniformity of the materials. During the mixing process, the temperature, time and other parameters of the mixing process are fed back in real time, and the mixing speed and time are adjusted in real time to ensure that the mixing effect is optimal.

[0025] The filling process module is responsible for filling the prepared and mixed materials (helium, nitrogen and oxygen mixed gas or helium, oxygen and pure oxygen) into the gas cylinder. The filling process requires precise control of parameters such as pressure, temperature and duration, and adjustments are made based on real-time feedback data to ensure that the filling process meets the mission requirements.

[0026] The data acquisition module is responsible for real-time collection of various operating parameters in the preparation, mixing and filling processes (such as pressure: pressure data of equipment or gas; quality: gas quality or mass flow rate of filling gas; temperature: temperature data of equipment and gas; duration: operation duration of each process stage; sound, etc.), real-time monitoring of process progress, and transmission of these data to the intelligent mixing equipment model and fault diagnosis module.

[0027] The intelligent deployment equipment module is used to intelligently generate the task plan and process of preparation, mixing and filling based on the input task requirements (number of filled gas cylinders) based on the intelligent deployment model (deep learning algorithm), and analyze the operating status of each process module based on the various parameters and process progress provided by the data acquisition module, and adjust the task plan and process. By optimizing the intelligent deployment model in real time, it can accurately determine whether the progress of each module is consistent with the task requirements, and adjust the plan in time when progress or task conflicts are found to ensure the smooth progress of the process.

[0028] Figure 2 FIG. 1 shows a schematic diagram of the workflow of the intelligent allocation device module according to an embodiment of the present disclosure. Figure 2 As shown, the intelligent allocation equipment module first obtains the number of gas cylinders to be filled, formulates a task plan and process based on the pre-trained intelligent allocation model, and allocates the preparation process module, the mixing process module, and the filling process module according to the task plan and process; Monitor the progress of the preparation process, mixing process, and filling process in real time to determine whether they meet the requirements of the task plan and process. If not, adjust the plan and process based on the intelligent deployment model; if they meet, determine whether the task requirements are met. If not, deploy the three functional modules of preparation process, mixing process, and filling process according to the current plan and process until the task requirements are met. Among them, the intelligent deployment model uses the convolutional neural network deep learning algorithm (CNN) to deeply train the images formed by the pressure, quality, temperature, duration and other data of the three process stages of preparation, mixing, and filling, and can make deployment plans and processes according to the number of gas cylinders to be filled.

[0029] The fault diagnosis module is responsible for real-time analysis of the equipment's operating status, judging whether there are faults in the gas filling system and parts that need maintenance based on various parameters, and performing fault diagnosis. After the fault is located, an alarm is issued to prompt the operator and provide a maintenance plan. For the vulnerable parts of the equipment, a maintenance plan is formulated to ensure timely maintenance to prevent equipment failures due to lack of maintenance.

[0030] Figure 3 FIG. 1 is a schematic diagram showing the working process of the fault diagnosis module according to an embodiment of the present disclosure. Figure 3 As shown, the fault diagnosis module determines whether there is a fault and whether the component needs maintenance based on the fault diagnosis model according to the pressure, quality, temperature, duration, and sound data of the preparation process, mixing process, and filling process collected in real time; if there is a fault, the fault is located and a maintenance plan is formulated, and the preparation process module, mixing process module, and filling process module are stopped; if component maintenance is required, a maintenance plan is formulated.

[0031] For example, the fault diagnosis module can analyze the use of the equipment's wearing parts, such as whether the seals, valves and other components have reached the critical value that requires maintenance. If a component requires maintenance, the system will automatically generate a maintenance plan and remind the operator to perform maintenance to avoid equipment failures caused by neglecting maintenance. If a serious fault occurs, the system will automatically stop the preparation, mixing, filling and other functional modules to prevent the fault from spreading further and affecting other modules.

[0032] Among them, the fault diagnosis model uses the convolutional neural network deep learning algorithm (CNN) to deeply train the images formed by the output signals, pressure, quality, temperature, duration, sound and other data of electrical equipment. It is composed of electrical fault model, mechanical fault model and maintenance database. The electrical fault model is formed by the fault of electrical equipment and the image formed by the output signal data of electrical equipment through deep learning training. The mechanical fault model is formed by the image formed by the pressure, quality, temperature, duration, sound and other data through deep learning training. The maintenance database is a database established with data such as the maintenance time interval of various components and the last maintenance time.

[0033] Figure 4 The figure shows a flow chart of an intelligent control method of a gas charging and distributing system according to an embodiment of the present disclosure. Figure 4 As shown, first obtain the number of gas cylinders to be filled, formulate a task plan and process based on the pre-trained intelligent deployment model, and deploy the preparation process module, mixing process module, and filling process module according to the task plan and process. That is, by sending instructions to control the solenoid valve, electric valve, motor and other equipment to complete the filling tasks of the three process stages of preparation, mixing, and filling.

[0034] Monitor the progress of the preparation process, mixing process, and filling process in real time to determine whether they meet the requirements of the task plan and process. If not, adjust the plan and process based on the intelligent deployment model; if they meet, determine whether the task requirements are met. If not, deploy the three functional modules of preparation process, mixing process, and filling process according to the current plan and process until the task requirements are met.

[0035] The pressure, quality, temperature, duration, and sound data of the preparation process, mixing process, and filling process are collected in real time. Based on the real-time collected data, the fault diagnosis model is used to determine whether there is a fault and whether the component needs maintenance. If there is a fault, the fault is located and a maintenance plan is formulated. The preparation process module, mixing process module, and filling process module are stopped. If component maintenance is required, a maintenance plan is formulated to prompt the operator to check and perform maintenance according to the plan. If no component needs maintenance or there is no fault, the fault diagnosis model is returned to continue monitoring the system and equipment.

[0036] In some embodiments of the present disclosure, the intelligent mixing model uses a convolutional neural network (CNN) deep learning algorithm to train historical data (such as pressure, quality, temperature, duration, etc.) of the three process stages of preparation, mixing and filling in the gas filling operation, to generate highly precise and intelligent mixing plans and processes, which can adaptively optimize the gas filling process in a dynamically changing production environment.

[0037] Historical data including electrical signals, pressure, quality, temperature, duration, and sound can be converted into image data. This conversion is achieved by using data of different dimensions as different channels of the image or by visualizing the time-data relationship. For example, feature extraction is performed on the time series data generated in each process stage and mapped into a two-dimensional image. Each image can represent the evolution of data in the process (such as an image of pressure changes over time, an image of temperature changes over time, etc.). Each process stage (preparation, mixing, filling) forms an image, which can include pressure change graphs: showing changes in pressure at different stages; temperature curve graphs: showing temperature fluctuations in the process; mass distribution graphs: reflecting the mass distribution of each material in the mixing process; duration change graphs: showing changes in duration of each process stage.

[0038] You can also perform data enhancement operations on the collected image data to increase data diversity, improve the generalization ability of the model, and ensure that the model can handle data changes in different operating environments.

[0039] The obtained image data and gas cylinder filling tasks of different quantities and types are input into a convolutional neural network for training to obtain a pre-trained intelligent deployment model.

[0040] According to the embodiments of the present disclosure, the training data set includes the changes in various parameters (such as pressure, temperature, time, etc.) during the process, the optimization effects of the process parameters under different task schemes, and the abnormal or deviation patterns that occur in the process. By performing deep learning on these data, the model can identify and optimize the process flow. For example, the model can determine which parameter changes under specific conditions will most affect the final result based on historical data, thereby predicting and optimizing the process.

[0041] Specifically, the convolutional neural network (CNN) model includes convolutional layers, pooling layers, and fully connected layers. CNN extracts local features in data images through multiple convolutional layers. The convolutional layer convolves the image through a sliding convolution kernel to extract important features of different data dimensions (such as pressure, mass, temperature, and duration). The pooling layer performs dimensionality reduction processing on the feature map output by the convolutional layer to reduce the dimension of the data and retain the most important feature information to reduce the amount of calculation and prevent overfitting. The extracted features are comprehensively analyzed through the fully connected layer to obtain the final output result (i.e., the prediction of the deployment plan and process).

[0042] Using nonlinear activation functions such as ReLU (Rectified Linear Unit) enables the network to capture more complex nonlinear relationships. A loss function suitable for this task (such as mean square error MSE or cross entropy loss) is used to measure the difference between the model output and the actual target.

[0043] The collected process data images are used as the input of CNN, and the parameters in the network are trained through the back propagation algorithm. During the training process, the model adjusts the weights so that the output mixing plan and process are close to the actual task requirements. The training data set contains data from different process stages (preparation, mixing, filling), as well as different numbers and types of gas cylinder filling tasks. After multiple rounds of training, the model can gradually optimize the prediction accuracy.

[0044] After the model is trained, it is evaluated on the validation set to test the generalization ability of the model on new data. Through multiple experiments and tests, the parameters of CNN (such as convolution kernel size, number of layers, etc.) are adjusted to improve accuracy. Once the convolutional neural network (CNN) model is trained, it can formulate a deployment plan and process flow based on the number of gas cylinders to be filled and the corresponding filling task requirements (such as gas type, filling volume, etc.).

[0045] When a filling task is given, the corresponding task plan and process are developed through the trained CNN model according to the number of gas cylinders to be filled. These task plans include the specific operating steps of the preparation, mixing and filling processes, as well as their control parameters such as time, pressure, temperature, etc. The data output of the preparation process stage (such as the required raw materials and gas ratio) will guide the start of the mixing process, and the successful output of the mixing process will serve as the input condition of the filling process. Once the preparation plan and process are determined, the intelligent preparation equipment module will pass it to the preparation, mixing and filling process modules for execution.

[0046] During the execution of each module, real-time data will be collected and transmitted back to the intelligent control system for tracking. Through data feedback, the CNN model continuously obtains new real-time data and analyzes whether the process stage is running as expected. If there is a deviation (for example, the pressure during the filling process of the gas cylinder does not meet the set value), the model can provide adjustment instructions to optimize the operation process in real time. For example, if there are multiple gas cylinders that need to be filled, the model can intelligently plan which gas cylinders to be filled first and which to be filled later, so as to balance the workload of each process module and avoid conflicts or waste of resources. If an abnormality occurs during the filling and distribution process (such as unstable pressure and temperature deviation from the standard), the possible impact is predicted based on the trained model and the filling strategy is adjusted. The adjusted plan is input into the preparation, mixing, and filling process modules again, and the optimized operation continues to be executed until the task requirements are met.

[0047] The adaptive capability of the model enables it to not only provide the best deployment plan before the task begins, but also make adjustments during the operation to cope with dynamically changing production environments and equipment conditions.

[0048] In some embodiments of the present disclosure, the fault diagnosis model uses a convolutional neural network (CNN) deep learning algorithm to perform intelligent diagnosis of faults in electrical equipment and mechanical equipment. The model first receives a variety of sensor data from the data acquisition module, including time series data such as electrical signals, pressure, quality, temperature, duration, and sound. The time series data is converted into images, such as heat maps or time-frequency images, and the convolutional neural network is trained using images and labeled fault samples to obtain a pre-trained fault diagnosis model. Among them, the convolution layer extracts features from the electrical signal image, the pooling layer performs dimensionality reduction and feature screening, and finally the fully connected layer outputs the fault type (such as overcurrent, short circuit, equipment aging, gas leakage, pump body operation failure, valve body switch failure, etc.) according to the extracted features.

[0049] Through deep learning training with historical data and labeled fault samples, the fault diagnosis model is gradually optimized and can identify the key features of equipment failures. Through a large number of positive and negative samples, different patterns before and after the failure can be learned to accurately predict the type of equipment failure.

[0050] In some embodiments of the present disclosure, the maintenance database contains information such as the maintenance cycle, last maintenance time, and fault history of each component of the equipment. By managing and analyzing the maintenance database, the fault diagnosis model can combine the maintenance history of the equipment to predict whether there is a potential fault risk.

[0051] During the operation of the gas filling and distribution system, based on various data collected in real time, the fault diagnosis model will monitor the operating status of the equipment in real time and diagnose faults. If the diagnosis results show that there is a fault in the equipment, the system will immediately locate the specific location of the fault and send out an alarm signal to prompt the operator of the fault type and location. Based on the historical fault records of the equipment, it provides maintenance suggestions while diagnosing the fault, predicts the components that may fail, and helps the operator to repair the fault. Automatically stop the functional modules involved in the fault (such as preparation, mixing, and filling modules) to avoid further damage to the equipment or product quality.

[0052] If the model does not detect a fault, it checks the working status of each component to determine if any component needs maintenance. Based on the information in the maintenance database, if a component is approaching or has exceeded its scheduled maintenance time, the system will prompt the operator to perform maintenance. Based on factors such as the maintenance cycle and the last maintenance time, a maintenance plan is developed and reminders are sent to the operator to ensure that the equipment is running in good working condition.

[0053] If no fault is found and maintenance is not required, the system will continue to return to the artificial intelligence fault diagnosis model for continuous monitoring. The fault diagnosis module continuously obtains new real-time data from the data acquisition module to perform real-time fault detection and maintenance prediction.

[0054] As equipment operation data accumulates and fault cases increase, the fault diagnosis model can be continuously trained and optimized to improve its recognition accuracy. When a new fault mode or new fault type occurs in the equipment, the new fault data can be manually annotated and the model can be retrained with this data to continuously adapt to new changes and improve diagnostic capabilities.

[0055] In other embodiments of the present disclosure, a computer-readable storage medium storing a computer program is further provided, wherein the computer program can achieve the following when executed by a processor: Figure 4 The steps of the intelligent control method of the filling and distribution system are shown.

[0056] In summary, the intelligent control method and device of the gas charging and distributing system provided by the present invention can at least achieve the following technical effects: By using the intelligent equipment module to monitor and adjust the task progress in real time, the entire gas filling process can be ensured to proceed smoothly, human intervention and operational errors can be minimized, and the flexibility and efficiency of the system can be improved. Using deep learning and artificial intelligence technology, real-time fault detection, accurate positioning, and automatic generation of maintenance plans can be achieved, thereby improving the reliability and safety of the system. By analyzing the use status of the equipment's wearing parts, operators can be reminded to perform maintenance in a timely manner to ensure that the equipment always maintains the best operating state and extends the service life of the equipment. Once a fault is detected, the system will automatically stop the relevant functional modules to prevent equipment failures from causing larger-scale damage and ensure production safety.

[0057] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0058] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0059] Those skilled in the art will appreciate that the modules or units or components of the devices in the examples disclosed herein may be arranged in the devices described in the embodiment, or alternatively may be located in one or more devices different from the devices in the examples. The modules in the foregoing examples may be combined into one module or may be divided into multiple submodules.

[0060] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device so disclosed may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0061] In addition, some of the embodiments are described herein as methods or combinations of method elements that can be implemented by a processor of a computer system or by other devices that perform the functions. Therefore, a processor with necessary instructions for implementing the method or method elements forms a device for implementing the method or method elements. In addition, the elements described herein of the device embodiments are examples of devices for implementing the functions performed by the elements for the purpose of implementing the invention.

[0062] Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is selected primarily for readability and teaching purposes, rather than for explaining or defining the subject matter of the present invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is illustrative and not restrictive with respect to the scope of the present invention, and the scope of the present invention is defined by the appended claims.

Claims

1. An intelligent control method for a gas filling and dispensing system, the gas filling and dispensing system comprising a preparation process module, a mixing process module, and a filling process module, characterized in that: The method comprises: Obtain the number of filled gas cylinders and formulate task plans and processes based on the pre-trained intelligent deployment model; Arrange the preparation process module, mixing process module and filling process module to work according to the task plan and process; Monitor the progress of the preparation process, mixing process, and filling process in real time to determine whether the requirements of the task plan and process are met. If not, adjust the plan and process based on the intelligent deployment model; If it meets the requirements, it is determined whether the task requirements are met. If not, the preparation process module, the mixing process module, and the filling process module are adjusted according to the current plan and process until the task requirements are met; Collect the operating parameters of the preparation process module, mixing process module, and filling process module in real time, and determine whether there is a fault and whether the component needs maintenance based on the pre-trained fault diagnosis model; If there is a fault, locate the fault and develop a maintenance plan, stop the preparation process module, mixing process module, and filling process module, and if component maintenance is required, develop a corresponding maintenance plan.

2. The intelligent control method according to claim 1, characterized in that: The operating parameters include voltage, current, frequency signals of electrical equipment and pressure, quality, temperature, duration, and sound data of mechanical equipment.

3. The intelligent control method according to claim 1, characterized in that: The intelligent deployment model is trained based on the following steps: Obtain historical data of the three process stages of preparation, mixing and filling in the gas filling operation, including pressure, quality, temperature and duration; The historical data is converted into image data, and the image data and gas cylinder filling tasks of different quantities and types are input into a convolutional neural network for training to obtain a pre-trained intelligent deployment model.

4. The intelligent control method according to claim 2, characterized in that: The fault diagnosis model is trained by the following steps: During the operation of the gas filling and distribution system, time series data including voltage, current, frequency, pressure, quality, temperature, duration, and sound data are collected; The time series data is converted into images, and a convolutional neural network is trained using the images and labeled fault samples to obtain a pre-trained fault diagnosis model.

5. The intelligent control method according to claim 4, characterized in that: The fault diagnosis model includes an electrical fault model, a mechanical fault model and a maintenance database, wherein the electrical fault model is obtained through deep learning training using an image formed by voltage, current and frequency signals of electrical equipment; The mechanical fault model is obtained through deep learning training using an image formed by pressure, mass, temperature, duration, and sound data; the maintenance database stores data on maintenance time intervals and last maintenance time for various components.

6. An intelligent control device for a gas filling system, characterized in that: include: In addition to data acquisition module, preparation process module, mixing process module, filling process module, intelligent mixing equipment module and fault diagnosis module; The data acquisition module is used to collect various parameters of the preparation process module, the mixing process module, and the filling process module in real time, monitor the process progress in real time, and transmit the various parameters and process progress to the intelligent preparation equipment model and the fault diagnosis module; The intelligent deployment equipment module is used to formulate task plans and processes based on the intelligent deployment model, and adjust the task plans and processes according to the various parameters and process progress; The fault diagnosis module is used to determine whether there is a fault in the gas filling system and a component that needs maintenance based on the fault diagnosis model according to the various parameters, determine the fault location and formulate a repair plan and maintenance plan.

7. The intelligent control device according to claim 6, characterized in that: The intelligent deployment equipment module is used to obtain historical data of the three process stages of preparation, mixing and filling in the gas filling operation, and the historical data includes pressure, quality, temperature and duration; the historical data is converted into image data, and the image data and gas cylinder filling tasks of different quantities and types are input into a convolutional neural network for training to obtain a pre-trained intelligent deployment model.

8. The intelligent control device according to claim 6, characterized in that: The fault diagnosis module is used to collect time series data including voltage, current, frequency, pressure, quality, temperature, duration, and sound data during the operation of the gas charging and distributing system; The time series data is converted into images, and a convolutional neural network is trained using the images and labeled fault samples to obtain a pre-trained fault diagnosis model.

9. The intelligent control device according to claim 6, characterized in that: The preparation process module is used to prepare materials according to the task plan, the mixing process module is used to mix the prepared materials according to the plan requirements, and the filling process module is used to fill the prepared and mixed materials into gas cylinders.

10. A computer-readable storage medium storing a computer program, characterized in that: The computer program implements the steps of the method according to any one of claims 1 to 5 when executed by a processor.

Images