Intelligent filling control method and system based on industrial gas

Abstract

The invention relates to an intelligent filling control method and system based on industrial gas, and belongs to the technical field of gas filling control. The method comprises the following steps: acquiring pressure data of a placing table, presetting a pressure threshold value of the placing table, judging according to the pressure data of the placing table and the pressure threshold value of the placing table, and performing corresponding processing according to a judgment result; the number of cleaning requirements, the pressure maintaining test ratio and the pressure maintaining duration are preset, the pressure maintaining gas amount is calculated according to the total storage amount and the pressure maintaining test ratio, and a diagnosis result is calculated through a diagnosis model according to the number of cleaning requirements, the pressure maintaining duration and the pressure maintaining gas amount; the diagnosis result is judged, and if the diagnosis result is that the test is qualified, filling operation is executed; if the diagnosis result is that the test is unqualified, generating a pressure maintaining unqualified alarm signal; and performing a leakage test on the gas storage tank through an infrared gas imaging technology to obtain a leakage test result. Intelligent filling of special gas is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of gas filling control, and in particular relates to an intelligent filling control method and system based on industrial gas. Background Art

[0002] After the production of special gases is completed, gas manufacturers need to fill the gases into cylinders of various specifications for storage before they can be sold. At present, many gas companies in the market use some old processes, and the filling process is done manually. Because the special gas industry is extremely dangerous and requires high technical personnel, it takes a lot of experience and time to train a qualified technician, which invisibly increases the company's operating costs. During the manual filling process, due to human uncontrollability, it will affect the filling volume of each cylinder and the purity of the gas after filling. If the operation is improper, it will also cause gas leakage, resulting in personal safety and environmental pollution. Summary of the invention

[0003] In order to solve the above problems existing in the prior art, the present invention provides an intelligent filling control method and system based on industrial gas. The purpose of the present invention can be achieved through the following technical solutions: S1: Obtaining the platform pressure data through the built-in pressure sensor of the gas storage tank platform, presetting the platform pressure threshold, and making a judgment based on the platform pressure data and the platform pressure threshold. If the platform pressure data is greater than the platform pressure threshold, obtaining the total storage amount of the gas storage tank; if the platform pressure data is not greater than the platform pressure threshold, no processing is performed; S2: Preset the required number of cleaning times, the pressure holding test ratio, and the pressure holding time, calculate the pressure holding gas volume according to the total storage volume and the pressure holding test ratio, and calculate the diagnosis result according to the required number of cleaning times, the pressure holding time, and the pressure holding gas volume through the diagnosis model; S3: judging the diagnosis result, if the diagnosis result is that the test is qualified, performing the filling operation; if the diagnosis result is that the test is unqualified, generating a pressure maintenance unqualified alarm signal; The filling operation includes: S201: The intelligent terminal generates an adaptive signal according to the diagnosis result to control the opening of the special gas supply valve and the inlet electronic valve of the gas storage tank, collects the internal pressure data of the gas tank through the pressure sensor, collects the gas temperature data through the temperature sensor, and calculates the internal storage capacity of the gas tank according to the internal pressure data of the gas tank and the gas temperature data; S202: adding a timestamp according to the internal reserve of the gas tank to obtain a time series reserve, storing the time series reserve to obtain a time series reserve sequence, calculating a preprocessing sequence according to the time series reserve sequence through a preprocessing model, and calculating a prediction result according to the preprocessing sequence through a grey prediction model; S203: judging according to the prediction result and the total storage amount, if the prediction result is less than the total storage amount, repeating steps S201-S203; if the prediction result is greater than or equal to the total storage amount, the intelligent terminal generates an adaptive signal to control the gas transmission valve and the gas storage tank interface valve to close; The calculation steps of the grey prediction model are: Accumulating and generating an accumulated sequence according to the preprocessing sequence; Performing next-to-next generation according to the accumulated sequence to obtain a next-to-next sequence; Constructing a whitening equation according to the quasi-exponential law of the cumulative sequence; constructing a grey differential equation according to the whitening equation and the immediate neighbor sequence; According to the whitening equation and the grey differential equation, the development coefficient and the grey action are calculated by the least square method; The prediction result is obtained by calculating the prediction formula according to the development coefficient, the grey action amount and the preprocessing sequence; S4: Performing a leakage test on the gas storage tank by infrared gas imaging technology to obtain a leakage test result, and transmitting the leakage test result to a human-computer interaction interface.

[0004] Specifically, the preprocessing model includes: A smoothness test is performed on the time series reserve sequence to obtain a test result. If the test result is qualified, the time series reserve sequence is output to obtain the preprocessing sequence; if the test result is unqualified, the preprocessing sequence is calculated by a logarithmic operator based on the time series reserve sequence.

[0005] Specifically, obtaining the total storage amount of the gas storage tank includes: S301: collecting nameplate image data of the gas storage tank through a visual sensor, and performing preprocessing on the nameplate image data to obtain image preprocessing data; S302: Obtain image information data by calculating the image preprocessing data through the PP-ChatOCR model; S303: Perform information retrieval according to the image information data to obtain a retrieval result. If the retrieval result is successful, the total storage amount is output; if the retrieval result is failed, the intelligent terminal generates a retrieval failure alarm signal and obtains the total storage amount through the human-computer interaction interface.

[0006] Specifically, the preprocessing includes grayscale, histogram equalization, normalization, noise removal, edge enhancement, and binarization.

[0007] Specifically, the diagnostic model calculation step includes: S401: Obtaining a pressure change threshold, the intelligent terminal generates an adaptive signal to open the nitrogen supply valve and the inlet electronic valve, fills the gas storage tank with an equal amount of gas according to the pressure-maintaining gas volume, and records the filling completion time; S402: judging according to the filling completion time and the pressure holding time, if the filling completion time is equal to the pressure holding time, obtaining the internal pressure data of the gas storage tank through the pressure sensor, judging according to the internal pressure data of the gas storage tank and the pressure change threshold, if the internal pressure data of the gas storage tank is not less than the pressure change threshold, the intelligent terminal generates an adaptive signal to control the outlet electronic valve of the gas storage tank to open; if the internal pressure data of the gas storage tank is less than the pressure change threshold, outputting that the test is unqualified; S403: The intelligent terminal generates an adaptive signal to control the closing of the outlet electronic valve, obtains the number of cleaning executions, and makes a judgment based on the cleaning requirement number and the cleaning execution number. If the cleaning execution number is not less than the cleaning requirement number, the output test is qualified; if the cleaning execution number is less than the cleaning requirement number, repeat steps S401-S403.

[0008] An intelligent filling control system based on industrial gas, comprising: a collection module, a diagnosis module, an execution module, and a detection module; The acquisition module is used to obtain the placement table pressure data through the built-in pressure sensor of the gas storage tank placement table, preset the placement table pressure threshold, and make a judgment based on the placement table pressure data and the placement table pressure threshold. If the placement table pressure data is greater than the placement table pressure threshold, the total storage amount of the gas storage tank is obtained; if the placement table pressure data is not greater than the placement table pressure threshold, no processing is performed; The diagnostic module is used to preset the required number of cleaning times, the pressure holding test ratio, and the pressure holding time, and obtain the pressure holding gas volume by calculation according to the total storage volume and the pressure holding test ratio, and obtain the diagnostic result by calculation according to the required number of cleaning times, the pressure holding time, and the pressure holding gas volume through the diagnostic model; The execution module is used to judge the diagnosis result, and if the diagnosis result is that the test is qualified, the filling operation is performed; if the diagnosis result is that the test is unqualified, a pressure maintenance unqualified alarm signal is generated; The filling operation includes: S201: The intelligent terminal generates an adaptive signal according to the diagnosis result to control the opening of the special gas supply valve and the inlet electronic valve of the gas storage tank, collects the internal pressure data of the gas tank through the pressure sensor, collects the gas temperature data through the temperature sensor, and calculates the internal storage capacity of the gas tank according to the internal pressure data of the gas tank and the gas temperature data; S202: adding a timestamp according to the internal reserve of the gas tank to obtain a time series reserve, storing the time series reserve to obtain a time series reserve sequence, calculating a preprocessing sequence according to the time series reserve sequence through a preprocessing model, and calculating a prediction result according to the preprocessing sequence through a grey prediction model; S203: judging according to the prediction result and the total storage amount, if the prediction result is less than the total storage amount, repeating steps S201-S203; if the prediction result is greater than or equal to the total storage amount, the intelligent terminal generates an adaptive signal to control the gas transmission valve and the gas storage tank interface valve to close; The calculation steps of the grey prediction model are: Accumulating and generating an accumulated sequence according to the preprocessing sequence; Performing next-to-next generation according to the accumulated sequence to obtain a next-to-next sequence; Constructing a whitening equation according to the quasi-exponential law of the cumulative sequence; constructing a grey differential equation according to the whitening equation and the immediate neighbor sequence; According to the whitening equation and the grey differential equation, the development coefficient and the grey action are calculated by the least square method; The prediction result is obtained by calculating the prediction formula according to the development coefficient, the grey action amount and the preprocessing sequence; The detection module is used to perform a leakage test on the gas storage tank by infrared gas imaging technology to obtain a leakage test result, and transmit the leakage test result to a human-computer interaction interface.

[0009] An electronic device comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein when the processor executes the program, the intelligent filling control method based on industrial gas as described above is implemented.

[0010] A storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute the intelligent filling control method based on industrial gas as described above when executed by a computer processor.

[0011] The beneficial effects of the present invention are: (1) By setting up the acquisition module, diagnosis module, execution module and detection module, the cleaning, pressure test, filling and leakage detection processes in the gas filling process are fully automated, reducing manual involvement and effectively avoiding losses caused by manual errors.

[0012] (2) Obtain a nameplate image of the gas storage tank through a visual sensor, extract information based on the nameplate image through the PP-ChatOCR model, and retrieve the total storage amount of the information to obtain a retrieval result. If the retrieval is successful, the total storage amount is output; if the retrieval result is a failure, the intelligent terminal generates a retrieval failure alarm signal and obtains the total storage amount through the human-computer interaction interface, thereby realizing intelligent extraction of important data of the intelligent gas storage tank.

[0013] (3) During the gas filling process, the pressure data in the gas storage tank is obtained through the pressure sensor, and the gas storage capacity in the storage tank is calculated based on the pressure data. The time series storage capacity sequence is obtained by adding a timestamp based on the gas storage capacity in the storage tank. The prediction result is calculated by the grey prediction model based on the storage capacity sequence. The intelligent terminal dynamically adjusts the closure of the gas pipeline valve according to the prediction result, thereby avoiding the residual large amount of special gas in the gas pipeline caused by the real-time measurement of the storage data of the storage tank, thereby reducing the leakage of special gas. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0015] Figure 1 The figure is a flow chart of an intelligent filling control method based on industrial gas according to the present invention. DETAILED DESCRIPTION

[0016] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0017] See also Figure 1 , an intelligent filling control method based on industrial gas, S1: Obtaining the platform pressure data through the built-in pressure sensor of the gas storage tank platform, presetting the platform pressure threshold, and making a judgment based on the platform pressure data and the platform pressure threshold. If the platform pressure data is greater than the platform pressure threshold, obtaining the total storage amount of the gas storage tank; if the platform pressure data is not greater than the platform pressure threshold, no processing is performed; S2: Preset the required number of cleaning times, the pressure holding test ratio, and the pressure holding time, calculate the pressure holding gas volume according to the total storage volume and the pressure holding test ratio, and calculate the diagnosis result according to the required number of cleaning times, the pressure holding time, and the pressure holding gas volume through the diagnosis model; S3: judging the diagnosis result, if the diagnosis result is that the test is qualified, performing the filling operation; if the diagnosis result is that the test is unqualified, generating a pressure maintenance unqualified alarm signal; The filling operation includes: S201: The intelligent terminal generates an adaptive signal according to the diagnosis result to control the opening of the special gas supply valve and the inlet electronic valve of the gas storage tank, collects the internal pressure data of the gas tank through the pressure sensor, collects the gas temperature data through the temperature sensor, and calculates the internal storage capacity of the gas tank according to the internal pressure data of the gas tank and the gas temperature data; The calculation formula for the internal gas reserves is: , in, V is the internal storage capacity of the gas tank, n is the number of moles of gas, R is the gas constant, T is the gas temperature data, P It is the internal pressure data of the gas tank; S202: adding a timestamp according to the internal reserve of the gas tank to obtain a time series reserve, storing the time series reserve to obtain a time series reserve sequence, calculating a preprocessing sequence according to the time series reserve sequence through a preprocessing model, and calculating a prediction result according to the preprocessing sequence through a grey prediction model; S203: judging according to the prediction result and the total storage amount, if the prediction result is less than the total storage amount, repeating steps S201-S203; if the prediction result is greater than or equal to the total storage amount, the intelligent terminal generates an adaptive signal to control the gas transmission valve and the gas storage tank interface valve to close; The calculation steps of the grey prediction model are: Accumulating and generating an accumulated sequence according to the preprocessing sequence; Performing next-to-next generation according to the accumulated sequence to obtain a next-to-next sequence; Constructing a whitening equation according to the quasi-exponential law of the cumulative sequence; The whitening equation is expressed as: , in, a is the development coefficient, b is the grey action, t For time,X 1 （t） is a cumulative sequence; constructing a grey differential equation according to the whitening equation and the immediate neighbor sequence; The grey differential equation expression is: , in, X 0 （k） is the preprocessing sequence, a is the development coefficient, b is the grey action, Z 1 （k） is an adjacent sequence; According to the whitening equation and the grey differential equation, the development coefficient and the grey action are calculated by the least square method; It should be noted that the least squares method is a mathematical optimization technique that finds the best function match for data by minimizing the sum of squares of errors. In linear regression analysis, it is used to estimate the parameters of the linear model. The prediction result is obtained by calculating the prediction formula according to the development coefficient, the grey action amount and the preprocessing sequence; The prediction result calculation formula is: , in, X(k+1) To predict the results, X 1 （1） is the first value in the cumulative sequence, k is a variable parameter, a is the development coefficient, b is the grey action; S4: Performing a leakage test on the gas storage tank by infrared gas imaging technology to obtain a leakage test result, and transmitting the leakage test result to a human-computer interaction interface.

[0018] It should be noted that the leakage test results include leakage test pass and leakage test fail.

[0019] In this embodiment, the execution steps of an intelligent filling control system based on industrial gas are as follows: Step 1: The built-in pressure sensor of the gas storage tank placement table obtains the placement table pressure data, presets the placement table pressure threshold, and makes a judgment based on the placement table pressure data and the placement table pressure threshold. If the placement table pressure data is greater than the placement table pressure threshold, it means that there is a gas storage tank on the gas storage tank placement table, and the smart terminal wakes up the visual sensor to collect the nameplate image of the gas storage tank; Step 2: The visual sensor transmits the nameplate image back to the processor, which performs preprocessing and data extraction based on the nameplate image to obtain the storage tank information data, and retrieves the total storage volume data of the storage tank information data. If the retrieval is successful, it is output; if the retrieval fails, an alarm signal is generated and transmitted to the human-computer interaction interface, and the total storage volume data is manually input; Step 3: After successfully acquiring the total storage volume data, start the cleaning procedure and the pressure maintenance procedure. The intelligent terminal closes the storage tank outlet electronic valve, opens the storage tank inlet electronic valve, opens the nitrogen gas supply valve, and performs quantitative nitrogen input. After the input is completed, the storage tank outlet electronic valve, the storage tank inlet electronic valve, and the nitrogen gas supply valve are closed and maintained for thirty minutes. After the end, measure whether the pressure in the storage tank is greater than the preset threshold. If the pressure in the storage tank is greater than the preset threshold, it means that the pressure maintenance test is qualified. Repeat step 3 six times; Step 4: After the cleaning and pressure-maintaining test steps are completed, the filling step is started. The intelligent terminal controls the special gas output valve to open, the storage tank inlet valve to open, and the storage tank outlet to close. The storage tank storage is monitored in real time. The predicted value is calculated by the gray prediction model according to the storage sequence. The predicted value is compared with the maximum storage capacity of the storage tank. If the predicted value is equal to the maximum storage capacity, the special gas filling is stopped, and the special gas output valve and the storage tank inlet valve are closed to complete the special gas filling; Step 5: Use infrared gas imaging technology to detect leaks in storage tanks and transmit the detection results to the human-computer interaction interface.

[0020] Specifically, the preprocessing model includes: A smoothness test is performed on the time series reserve sequence to obtain a test result. If the test result is qualified, the time series reserve sequence is output to obtain the preprocessing sequence; if the test result is unqualified, the preprocessing sequence is calculated by a logarithmic operator based on the time series reserve sequence.

[0021] Specifically, the smoothness detection expression is: , in, P(k) is the smoothness ratio of the time series reserve sequence constructed by the first k time series reserves in the time series reserve sequence, k is a variable parameter, X(k) represents the kth time series reserve in the time series reserve sequence, i is a variable parameter, a is the confidence interval.

[0022] Specifically, obtaining the total storage amount of the gas storage tank includes: S301: collecting nameplate image data of the gas storage tank through a visual sensor, and performing preprocessing on the nameplate image data to obtain image preprocessing data; S302: Obtain image information data by calculating the image preprocessing data through the PP-ChatOCR model; It should be noted that the PP-ChatOCR model is a general image key information extraction model based on the Wenxin model. It combines OCR text recognition and the Wenxin Yiyanda speech model, and can extract key information from images in a variety of scenarios; S303: Perform information retrieval according to the image information data to obtain a retrieval result. If the retrieval result is successful, the total storage amount is output; if the retrieval result is failed, the intelligent terminal generates a retrieval failure alarm signal and obtains the total storage amount through the human-computer interaction interface.

[0023] Specifically, the preprocessing includes grayscale, histogram equalization, normalization, noise removal, edge enhancement, and binarization.

[0024] Specifically, the diagnostic model calculation step includes: S401: Obtaining a pressure change threshold, the intelligent terminal generates an adaptive signal to open the nitrogen supply valve and the inlet electronic valve, fills the gas storage tank with an equal amount of gas according to the pressure-maintaining gas volume, and records the filling completion time; S402: judging according to the filling completion time and the pressure holding time, if the filling completion time is equal to the pressure holding time, obtaining the internal pressure data of the gas storage tank through the pressure sensor, judging according to the internal pressure data of the gas storage tank and the pressure change threshold, if the internal pressure data of the gas storage tank is not less than the pressure change threshold, the intelligent terminal generates an adaptive signal to control the outlet electronic valve of the gas storage tank to open; if the internal pressure data of the gas storage tank is less than the pressure change threshold, outputting that the test is unqualified; S403: The intelligent terminal generates an adaptive signal to control the closing of the outlet electronic valve, obtains the number of cleaning executions, and makes a judgment based on the cleaning requirement number and the cleaning execution number. If the cleaning execution number is not less than the cleaning requirement number, the output test is qualified; if the cleaning execution number is less than the cleaning requirement number, repeat steps S401-S403.

[0025] An intelligent filling control system based on industrial gas, comprising: a collection module, a diagnosis module, an execution module, and a detection module; The acquisition module is used to obtain the placement table pressure data through the built-in pressure sensor of the gas storage tank placement table, preset the placement table pressure threshold, and make a judgment based on the placement table pressure data and the placement table pressure threshold. If the placement table pressure data is greater than the placement table pressure threshold, the total storage amount of the gas storage tank is obtained; if the placement table pressure data is not greater than the placement table pressure threshold, no processing is performed; The diagnostic module is used to preset the required number of cleaning times, the pressure holding test ratio, and the pressure holding time, and obtain the pressure holding gas volume by calculation according to the total storage volume and the pressure holding test ratio, and obtain the diagnostic result by calculation according to the required number of cleaning times, the pressure holding time, and the pressure holding gas volume through the diagnostic model; The execution module is used to judge the diagnosis result, and if the diagnosis result is that the test is qualified, the filling operation is performed; if the diagnosis result is that the test is unqualified, a pressure maintenance unqualified alarm signal is generated; The filling operation includes: S201: The intelligent terminal generates an adaptive signal according to the diagnosis result to control the opening of the special gas supply valve and the inlet electronic valve of the gas storage tank, collects the internal pressure data of the gas tank through the pressure sensor, collects the gas temperature data through the temperature sensor, and calculates the internal storage capacity of the gas tank according to the internal pressure data of the gas tank and the gas temperature data; The calculation formula for the internal gas reserves is: , in, V is the internal storage capacity of the gas tank, n is the number of moles of gas, R is the gas constant, T is the gas temperature data, P It is the internal pressure data of the gas tank; S202: adding a timestamp according to the internal reserve of the gas tank to obtain a time series reserve, storing the time series reserve to obtain a time series reserve sequence, calculating a preprocessing sequence according to the time series reserve sequence through a preprocessing model, and calculating a prediction result according to the preprocessing sequence through a grey prediction model; S203: judging according to the prediction result and the total storage amount, if the prediction result is less than the total storage amount, repeating steps S201-S203; if the prediction result is greater than or equal to the total storage amount, the intelligent terminal generates an adaptive signal to control the gas transmission valve and the gas storage tank interface valve to close; The calculation steps of the grey prediction model are: Accumulating and generating an accumulated sequence according to the preprocessing sequence; Performing next-to-next generation according to the accumulated sequence to obtain a next-to-next sequence; Constructing a whitening equation according to the quasi-exponential law of the cumulative sequence; The whitening equation is expressed as: , in, a is the development coefficient, b is the grey action, t For time, X 1 （t） is a cumulative sequence; constructing a grey differential equation according to the whitening equation and the immediate neighbor sequence; The grey differential equation expression is: , in, X 0 （k） is the preprocessing sequence, a is the development coefficient, b is the grey action, Z 1 （k） is an adjacent sequence; According to the whitening equation and the grey differential equation, the development coefficient and the grey action are calculated by the least square method; It should be noted that the least squares method is a mathematical optimization technique that finds the best function match for data by minimizing the sum of squares of errors. In linear regression analysis, it is used to estimate the parameters of the linear model. The prediction result is obtained by calculating the prediction formula according to the development coefficient, the grey action amount and the preprocessing sequence; The prediction result calculation formula is: , in, X(k+1) To predict the results, X 1 （1） is the first value in the cumulative sequence, k is a variable parameter, a is the development coefficient, b is the grey action; The detection module is used to perform a leakage test on the gas storage tank by infrared gas imaging technology to obtain a leakage test result, and transmit the leakage test result to a human-computer interaction interface.

[0026] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the intelligent filling control method based on industrial gas as described above is implemented.

[0027] A storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute the intelligent filling control method based on industrial gas as described above when executed by a computer processor.

[0028] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0029] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0030] The program code included in the computer-readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written with one or more programming languages ​​or their combination, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0031] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An intelligent filling control method based on industrial gas, characterized in that: include: S1: Obtaining the platform pressure data through the built-in pressure sensor of the gas storage tank platform, presetting the platform pressure threshold, and making a judgment based on the platform pressure data and the platform pressure threshold. If the platform pressure data is greater than the platform pressure threshold, obtaining the total storage amount of the gas storage tank; If the placement table pressure data is not greater than the placement table pressure threshold, no processing is performed; S2: Preset the required number of cleaning times, the pressure holding test ratio, and the pressure holding time, calculate the pressure holding gas volume according to the total storage volume and the pressure holding test ratio, and calculate the diagnosis result according to the required number of cleaning times, the pressure holding time, and the pressure holding gas volume through the diagnosis model; S3: judging the diagnosis result, and if the diagnosis result is that the test is qualified, performing the filling operation; If the diagnosis result is that the test is unqualified, a pressure maintenance unqualified alarm signal is generated; The filling operation includes: S201: The intelligent terminal generates an adaptive signal according to the diagnosis result to control the opening of the special gas supply valve and the inlet electronic valve of the gas storage tank, collects the internal pressure data of the gas tank through the pressure sensor, collects the gas temperature data through the temperature sensor, and calculates the internal storage capacity of the gas tank according to the internal pressure data of the gas tank and the gas temperature data; S202: adding a timestamp according to the internal reserve of the gas tank to obtain a time series reserve, storing the time series reserve to obtain a time series reserve sequence, calculating a preprocessing sequence according to the time series reserve sequence through a preprocessing model, and calculating a prediction result according to the preprocessing sequence through a grey prediction model; S203: judging according to the prediction result and the total storage amount, if the prediction result is less than the total storage amount, repeating steps S201-S203; if the prediction result is greater than or equal to the total storage amount, the intelligent terminal generates an adaptive signal to control the gas transmission valve and the gas storage tank interface valve to close; The calculation steps of the grey prediction model are: Accumulating and generating an accumulated sequence according to the preprocessing sequence; Performing next-to-next generation according to the accumulated sequence to obtain a next-to-next sequence; Constructing a whitening equation according to the quasi-exponential law of the cumulative sequence; constructing a grey differential equation according to the whitening equation and the immediate neighbor sequence; According to the whitening equation and the grey differential equation, the development coefficient and the grey action are calculated by the least square method; The prediction result is obtained by calculating the prediction formula according to the development coefficient, the grey action amount and the preprocessing sequence; S4: Performing a leakage test on the gas storage tank by infrared gas imaging technology to obtain a leakage test result, and transmitting the leakage test result to a human-computer interaction interface.

2. The intelligent filling control method based on industrial gas according to claim 1 is characterized in that: The preprocessing model includes: A smoothness test is performed on the time series reserve sequence to obtain a test result. If the test result is qualified, the time series reserve sequence is output to obtain the preprocessing sequence; if the test result is unqualified, the preprocessing sequence is calculated by a logarithmic operator based on the time series reserve sequence.

3. The intelligent filling control method based on industrial gas according to claim 1 is characterized in that: The obtaining of the total storage volume of the gas storage tank comprises: S301: collecting nameplate image data of the gas storage tank through a visual sensor, and preprocessing the nameplate image data to obtain image preprocessing data; S302: Obtain image information data by calculating the image preprocessing data through the PP-ChatOCR model; S303: Perform information retrieval based on the image information data to obtain a retrieval result. If the retrieval result is successful, the total storage amount is output; if the retrieval result is failed, the intelligent terminal generates a retrieval failure alarm signal and obtains the total storage amount through the human-computer interaction interface.

4. The intelligent filling control method based on industrial gas according to claim 3 is characterized in that: The preprocessing includes grayscale, histogram equalization, normalization, noise removal, edge enhancement, and binarization.

5. The intelligent filling control method based on industrial gas according to claim 1 is characterized in that: The diagnostic model calculation step comprises: S401: Obtaining a pressure change threshold, the intelligent terminal generates an adaptive signal to open the nitrogen supply valve and the inlet electronic valve, fills the gas storage tank with an equal amount of gas according to the pressure-maintaining gas volume, and records the filling completion time; S402: judging according to the filling completion time and the pressure holding time, if the filling completion time is equal to the pressure holding time, obtaining the internal pressure data of the gas storage tank through the pressure sensor, judging according to the internal pressure data of the gas storage tank and the pressure change threshold, if the internal pressure data of the gas storage tank is not less than the pressure change threshold, the intelligent terminal generates an adaptive signal to control the outlet electronic valve of the gas storage tank to open; if the internal pressure data of the gas storage tank is less than the pressure change threshold, outputting that the test is unqualified; S403: The intelligent terminal generates an adaptive signal to control the closing of the outlet electronic valve, obtains the number of cleaning executions, and makes a judgment based on the cleaning requirement number and the cleaning execution number. If the cleaning execution number is not less than the cleaning requirement number, the output test is qualified; if the cleaning execution number is less than the cleaning requirement number, repeat steps S401-S403.

6. An intelligent filling control system based on industrial gas, characterized in that: include: Acquisition module, diagnosis module, execution module, detection module; The acquisition module is used to obtain the placement table pressure data through the built-in pressure sensor of the gas storage tank placement table, preset the placement table pressure threshold, and make a judgment based on the placement table pressure data and the placement table pressure threshold. If the placement table pressure data is greater than the placement table pressure threshold, the total storage amount of the gas storage tank is obtained; If the placement table pressure data is not greater than the placement table pressure threshold, no processing is performed; The diagnostic module is used to preset the required number of cleaning times, the pressure holding test ratio, and the pressure holding time, and obtain the pressure holding gas volume by calculation according to the total storage volume and the pressure holding test ratio, and obtain the diagnostic result by calculation according to the required number of cleaning times, the pressure holding time, and the pressure holding gas volume through the diagnostic model; The execution module is used to judge the diagnosis result, and if the diagnosis result is that the test is qualified, execute the filling operation; If the diagnosis result is that the test is unqualified, a pressure maintenance unqualified alarm signal is generated; The filling operation includes: S201: The intelligent terminal generates an adaptive signal according to the diagnosis result to control the opening of the special gas supply valve and the inlet electronic valve of the gas storage tank, collects the internal pressure data of the gas tank through the pressure sensor, collects the gas temperature data through the temperature sensor, and calculates the internal storage capacity of the gas tank according to the internal pressure data of the gas tank and the gas temperature data; S202: adding a timestamp according to the internal reserve of the gas tank to obtain a time series reserve, storing the time series reserve to obtain a time series reserve sequence, calculating a preprocessing sequence according to the time series reserve sequence through a preprocessing model, and calculating a prediction result according to the preprocessing sequence through a grey prediction model; S203: judging according to the prediction result and the total storage amount, if the prediction result is less than the total storage amount, repeating steps S201-S203; if the prediction result is greater than or equal to the total storage amount, the intelligent terminal generates an adaptive signal to control the gas transmission valve and the gas storage tank interface valve to close; The calculation steps of the grey prediction model are: Accumulating and generating an accumulated sequence according to the preprocessing sequence; Performing next-to-next generation according to the accumulated sequence to obtain a next-to-next sequence; Constructing a whitening equation according to the quasi-exponential law of the cumulative sequence; constructing a grey differential equation according to the whitening equation and the immediate neighbor sequence; According to the whitening equation and the grey differential equation, the development coefficient and the grey action are calculated by the least square method; The prediction result is obtained by calculating the prediction formula according to the development coefficient, the grey action amount and the preprocessing sequence; The detection module is used to perform a leakage test on the gas storage tank by infrared gas imaging technology to obtain a leakage test result, and transmit the leakage test result to a human-computer interaction interface.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor executes the program, the intelligent filling control method based on industrial gas as described in any one of claims 1-5 is implemented.

8. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the intelligent filling control method based on industrial gas as described in any one of claims 1-5 when executed by a computer processor.

Images