Rotor flow meter automatic verification system and control method and device

Through the combination of deep learning technology and industrial cameras, combined with standard flow generation devices and micro-regulating valves, the automatic tracking readings and flow display recognition of the rotor flowmeter is realized, solving the problems of large errors and low efficiency in manual verification, and improving the accuracy of verification , and efficiency, suitable for a wide range of rotor flowmeter specifications and types.

CN118913410APending Publication Date: 2024-11-08CHINA JILIANG UNIV
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202410916907.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-09
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

During the automatic verification process of existing rotor flow meters, there are problems such as large manual interpretation error, low efficiency, and susceptible to operator skill level. Inaccurate flow verification, it is difficult to accurately identify flow indicators under uneven lighting and complex backgrounds. .

Method used

Deep learning technology is used to combine industrial cameras and lifting mechanisms, and feature learning and recognition is carried out by building a multi-layer neural network to realize the identification of the automatic tracking readings and flow indicators of the rotor flowmeter, and the precise control of the standard flow generator and micro-regulating valve Traffic, reduce human intervention.

Benefits of technology

It improves the accuracy and efficiency of the rotor flowmeter verification, reduces human interpretation errors, and realizes fully automatic verification of various specifications and types of rotor flowmeters, without requiring high professional knowledge to operate, saving human resources and time.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118913410A_ABST
    Figure CN118913410A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of deep learning, researches an automatic identification technology based on deep learning, discusses an automatic verification system of a rotor flow meter and a control method and device, controls a pressure air source through combination of a pressure PID controller and a piezoelectric proportional valve, and achieves the purpose of flow stabilization by adjusting a micro-adjusting valve. A plurality of independent channels are output, and gas and liquid flow meters of various sizes and specifications can be detected; in the aspect of recognition, an industrial camera is used for collecting images, a target detection network model is imported for analysis, and a lifting mechanism is controlled to realize tracking reading of a rotor; and finally, the numerical value of the mass reading electronic balance is used as a standard value for comparison. According to the invention, indicating value identification and automatic verification of rotor flow meters of different specifications can be realized, the operation is convenient, and the efficiency and the accuracy are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0002] The present invention relates to the field of deep learning technology, and in particular to a rotor flowmeter automatic calibration system and control method and device. Background Art

[0003] The rotor flowmeter is an instrument that measures flow based on the throttling principle. It keeps the differential pressure above and below the rotor constant by changing the flow area of ​​the fluid. It has the advantages of simple structure, intuitive scale value, easy use and maintenance, small and constant pressure loss, etc. It is widely used in the field of industrial flow measurement and needs to be regularly traced (calibrated or calibrated) to ensure the accuracy of its indication. However, during the calibration process, the gas medium is easily affected by conditions such as pressure and temperature, which makes the measurement difficult and the work efficiency is not high; in addition, it also involves the problem of inaccurate calibration of small flow rates. Manual calibration of rotor flowmeters has problems such as large reading errors and low efficiency. It is easily affected by the operator's skill level and subjective judgment, resulting in unstable calibration results. Therefore, a more efficient and accurate automatic calibration technology is needed to improve the calibration accuracy and efficiency of rotor flowmeters. The present invention incorporates deep learning technology to solve this problem.

[0004] Traditional automatic meter reading recognition algorithms are based on computer image processing algorithms, which cannot solve problems such as uneven lighting, large lighting changes, complex backgrounds, image blur, meter tilt, scale changes, and cumbersome image preprocessing. In recent years, deep learning technology has gradually shown great potential in the field of computer vision. Deep learning methods build multi-layer neural networks and use nonlinear mapping relationships to learn and represent features of input data, thereby achieving recognition and understanding of complex patterns. Deep learning methods have powerful feature learning and abstraction capabilities, can effectively handle complex visual tasks, and have good robustness.

[0005] In the process of using an industrial camera to read the rotor flowmeter, it is important to align the line of sight with the tangent of the rotor, and the rotor will move during the flow change process. The present invention uses a lifting mechanism to track the horizontal rotor, which can further improve the accuracy of the reading. Summary of the invention

[0006] The object of the present invention is to provide a rotor flowmeter automatic calibration system and control method and device, which can provide a controllable and stable flow, realize automatic tracking and identification of the rotor flowmeter indication, achieve the purpose of automatic calibration of the rotor flowmeter, facilitate operation, and improve efficiency and accuracy.

[0007] In order to achieve the above purpose, the following technical solutions are proposed:

[0008] A first aspect of an embodiment of the present invention discloses a standard flow generating device, comprising:

[0009] The standard flow generating device is mainly composed of a high-pressure gas source, a pressure reducing valve, a pressure stabilizing tank, a pressure transmitter, a piezoelectric proportional valve, a PID controller, a micro-regulating valve, and a liquid storage tank;

[0010] The pressure reducing valve is installed at the outlet of the high-pressure gas source to achieve the effect of initially stabilizing the pressure;

[0011] The high-pressure gas in the gas source flows through the pressure reducing valve into the pressure stabilizing tank, and the pressure sensor is installed on the pressure stabilizing tank to detect the pressure in the tank in real time and feed back the pressure data to the PID controller;

[0012] The PID controller is connected to the piezoelectric proportional valve for calculating and adjusting the output control signal, and calculates the adjustment amount according to the deviation between the pressure feedback and the set value;

[0013] The piezoelectric proportional valve is installed between the pressure reducing valve and the pressure stabilizing tank to directly and effectively control the gas flow rate entering the pressure stabilizing tank;

[0014] The piezoelectric proportional valve is a valve that can accurately adjust the flow rate. It adjusts the opening by receiving the control signal of the PID controller, thereby changing the flow rate of the fluid entering the pressure-stabilizing tank and further adjusting the pressure in the tank. By continuously adjusting the opening of the piezoelectric proportional valve, the pressure increases when it is in positive action and decreases when it is in negative action. The PID controller modifies its action mode and corresponding parameters to achieve the role in the present invention, so that the pressure in the pressure-stabilizing tank gradually approaches the set value, thereby achieving the purpose of pressure stability.

[0015] The liquid storage tank adopts the drainage method to provide a stable flow for the liquid rotor flowmeter, and the pressure sensor is installed at the bottom of the liquid storage tank to detect the tank bottom pressure in real time and feedback control the liquid pressure to be stable;

[0016] The liquid level of the liquid storage tank is calculated by measuring the tank bottom pressure. When the liquid level is lower than the alarm value, the water pump starts to add water, and when it is higher than the alarm value, the water pump stops adding water.

[0017] The micro-regulating valve is installed downstream of the rotor flowmeter to accurately control the flow rate by adjusting the valve opening;

[0018] A motor caliper assembly is provided above the micro-regulating valve, and the caliper is embedded in the groove of the regulating valve;

[0019] The opening adjustment of the micro-regulating valve is controlled by a combination of a motor and a caliper, and a PWM signal is sent by a single chip microcomputer to drive the motor to rotate, and the change of the valve opening is adjusted to further convert the stable pressure into a stable flow;

[0020] The standard value of the rotor flowmeter verification result adopts an electronic balance as a standard instrument;

[0021] The flow generated by the standard flow generating device is directed to a water storage container, and after the flow value stabilizes, it is switched to an electronic balance channel through a switching valve, and a timer is started at the same time.

[0022] A second aspect of an embodiment of the present invention discloses a tracking reading device for a rotor flowmeter, comprising:

[0023] The tracking reading device of the rotor flowmeter automatic calibration system is mainly composed of a rotor flowmeter, an industrial camera, a sliding guide rail, a stepper motor, a motor drive, a single-axis controller, and a host computer;

[0024] The center coordinate value of the rotor is subtracted from the center coordinate value of the industrial camera screen, and the difference is judged to control the start and stop of the lifting mechanism;

[0025] The lifting mechanism is composed of a sliding guide rail and an industrial camera;

[0026] The lifting mechanism is installed right in front of the rotor flowmeter;

[0027] If the difference is greater than the upper warning value, the host computer algorithm determines and sends a command to the single-axis controller to control the motor to rotate forward, and the slide rail carrying the industrial camera rises;

[0028] If the difference is less than the lower limit warning value, the host computer algorithm determines and sends a command to the single-axis controller to control the motor to reverse, and the slide rail carrying the industrial camera descends;

[0029] If it is between the upper warning limit and the lower warning limit, the motor stops and it is judged as a horizontal rotor;

[0030] The algorithm is continuously cycled to control the rail carrying the industrial camera to move up and down, so as to achieve tracking and level viewing of the rotor;

[0031] When the lifting mechanism shown carries the industrial camera and reaches the eye-level height, the industrial camera is connected to the host computer for communication, and the image of the rotor flowmeter is collected and uploaded;

[0032] The image after the preliminary processing is imported into the target detection network model to obtain the bounding box information of the rotor flowmeter indication. According to the rotor center coordinates and the coordinates of each scale line, the flow range of the rotor position is determined, and then the current flow indication can be calculated using the proportional method. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The following drawings show specific examples of the technical solutions of the present invention, and are used to explain the content, principle and effect of the present invention.

[0034] Unless otherwise specified or defined, the same reference numerals in different drawings represent the same or similar technical features, and the same or similar technical features may also be represented by different reference numerals.

[0035] Figure 1 It is a flow chart of the automatic calibration system of the rotor flowmeter disclosed in the embodiment of the present invention;

[0036] Figure 2 It is a schematic diagram of a rotor flowmeter automatic calibration system disclosed in an embodiment of the present invention;

[0037] Figure 3 The present invention discloses a pressure control flow chart of a rotor flowmeter automatic calibration system.

[0038] Description of reference numerals:

[0039] 201. High-pressure gas source; 202. Pressure reducing valve; 203. Pressure controller; 204. Water pump; 205. Liquid storage tank; 206. Computer; 207. Thermal gas mass flowmeter; 208. Sliding guide; 209. Industrial camera; 210. Proportional valve; 211. Rotor flowmeter; 212. Pressure transmitter; 213. Temperature transmitter; 214. Motor caliper; 215. Electronic balance; 216. Multi-way switching valve.

[0040] Beneficial effects of the present invention: Compared with traditional manual calibration, the present invention can greatly reduce human interpretation errors, improve the accuracy and reliability of calibration, and the deep learning model has strong adaptability and versatility, and can realize full-automatic calibration of rotor flow meters of various specifications and two types without manual intervention, which will greatly improve the efficiency of the calibration process and save human resources and time costs. In addition, the use of deep learning target detection can reduce the professional knowledge requirements for operators, making operations simpler and more standardized. With the continuous development and improvement of deep learning technology, its application in the field of target detection will continue to evolve, providing more functions and possibilities for instrument calibration. Specific implementation plan

[0041] In order to facilitate the understanding of the present invention, specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings.

[0042] Unless otherwise specified or defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art. In combination with the technical solution of the present invention in a realistic scenario, all technical and scientific terms used herein may also have meanings corresponding to the technical solution for implementing the present invention. The "first, second..." used herein is merely used to distinguish the names and does not represent a specific quantity or order. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0043] Unless otherwise specified or defined, the “said” and “the” used in this document refer to the technical features or contents mentioned or described before the corresponding position, and the technical features or technical contents may be the same as or similar to the technical features or technical contents mentioned therein.

[0044] Undoubtedly, technical contents or technical features that are contrary to the purpose of the present invention or are obviously contradictory should be excluded.

[0045] like Figure 2 As shown, the embodiment of the present invention discloses a rotor flowmeter automatic calibration system, comprising:

[0046] Under the condition that the connection and communication of each module are guaranteed to be normal, the specific verification process is as follows:

[0047] Step 1: First, turn on the power, select the gas-liquid type and specification channel, open the pressure control device and the corresponding electromagnetic valve, set the appropriate pressure parameters, and turn on the PID self-tuning mode to obtain the PID adjustment parameter value under the pressure stabilization condition.

[0048] Step 2: If Figure 3 As shown, the high-pressure gas in the gas source flows through the pressure reducing valve to initially reduce the pressure and enter the pressure regulating tank. The pressure sensor detects the pressure value in the tank in real time and feeds it back to the PID controller. The PID calculates the adjustment amount based on the deviation between the pressure feedback and the set value, and sends the corresponding current signal to the piezoelectric proportional valve.

[0049] Step 3: The piezoelectric proportional valve adjusts its opening by receiving the control signal of the PID controller, thereby changing the flow rate of the fluid entering the pressure regulating tank, and then adjusting the pressure in the tank, gradually approaching the set value.

[0050] Step 4: After the pipeline pressure stabilizes, control the motor caliper through the flow value fed back by the standard flow meter, and continue to turn the micro-adjusting valve to obtain the required stable flow value.

[0051] Step 5: After the pipeline flow is stable, enable the switching valve to switch to the electronic balance channel. At the same time, the timer is triggered. The program receives the electronic balance signal and the timer signal, and can calculate the mass flow value in real time.

[0052] Step 6: The computer program will process the images captured by the industrial camera, and then import them into the target detection network model for analysis to obtain the bounding box information of each target.

[0053] Step 7: The rotor position is captured through bounding box information and geometric relationship algorithm, and the center coordinate value of the rotor is subtracted from the center coordinate value of the industrial camera image. The difference is used to control the start and stop of the lifting mechanism. After the slide rail continuously adjusts its height, the camera's line of sight is aligned with the rotor to achieve tracking and identification of the rotor.

[0054] Step 8: Extract the center coordinates of the rotor boundary box, compare them with the boundaries located by digital identification, determine the small range of the rotor, and calculate the current flow indication by proportional method.

[0055] Step 9: The standard flow value corresponding to the rotor flowmeter can be converted through the temperature and pressure values ​​fed back by the sensor and the standard formula.

[0056] Step 10: According to the calibration procedures, the rotor flowmeter needs to be calibrated at the five flow points in the upper and lower strokes. After the calibration is completed, the device is turned off and the data is analyzed and evaluated in the program interface to generate a report.

[0057] The purpose of the above embodiments is to exemplarily reproduce and deduce the technical solution of the present invention, and to fully describe the technical solution, purpose and effect of the present invention. Its purpose is to enable the public to have a more thorough and comprehensive understanding of the disclosed content of the present invention, and it does not limit the protection scope of the present invention.

[0058] The above embodiments are not exhaustive enumerations of the present invention, and there may be multiple other implementations not listed. Any replacement and improvement made without violating the concept of the present invention shall fall within the protection scope of the present invention.

Claims

1. A rotor flowmeter automatic calibration system and control method and device, characterized in that: It includes a standard flow generating device and a rotor tracking reading device; The standard flow generating device of the rotor flowmeter automatic calibration system is mainly composed of a high-pressure gas source, a pressure reducing valve, a pressure stabilizing tank, a pressure transmitter, a piezoelectric proportional valve, a PID controller, a micro-regulating valve, and a liquid storage tank; The standard flow generating device contains multiple PID controllers and switching valves, which can generate multiple channels and realize multi-channel control; The standard flow generating device is provided with a liquid storage tank and a water pump at the rear, which can provide liquid flow for the device; The tracking and reading device of the rotor flowmeter automatic calibration system is mainly composed of a rotor flowmeter, an industrial camera, a sliding guide rail, a stepper motor, a motor drive, a single-axis controller, and a host computer. The industrial camera is connected to the computer via a USB to obtain image information in real time. The stepper motor drives the slide rail carrying the industrial camera to move up and down to track and identify the rotor flowmeter to obtain the reading.

2. The standard flow generating device according to claim 1, characterized in that: During the standard flow process, flow control is achieved by the cooperation of pressure PID and micro-regulating valve. The high-pressure gas reaches pressure stability after PID control, and then the motor caliper is controlled to rotate the micro-regulating valve according to the flow data fed back by the standard device to achieve the flow stability effect, that is, the pressure stability is converted into flow stability through the micro-regulating valve.

3. The standard flow generating device according to claim 2, characterized in that: The PID controller is a device for calculating and adjusting the output control signal, and the adjustment amount is calculated based on the deviation between the pressure feedback and the set value; The piezoelectric proportional valve is a valve that can accurately adjust the flow rate. It adjusts the opening by receiving the control signal of the PID controller, thereby changing the flow rate of the fluid entering the pressure-stabilizing tank, and then adjusting the pressure in the tank. By continuously adjusting the opening of the piezoelectric proportional valve, the pressure in the pressure-stabilizing tank gradually approaches the set value.

4. The standard flow generating device according to claim 1, characterized in that: The liquid storage tank adopts the drainage method to provide a stable flow for the liquid rotor flowmeter. The pressure sensor is installed at the bottom of the liquid storage tank to detect the tank bottom pressure in real time and feedback control the liquid pressure to be stable.

5. The standard flow generating device according to claim 4, characterized in that: The liquid level height problem of the liquid storage tank drainage method can be calculated by taking the difference between the indications of the two pressure sensors at the top and the bottom, and the liquid level height value can be calculated by a formula. When the liquid level is lower than the alarm value, the water pump is started to add water, and when the liquid level is higher than the alarm value, the water pump is stopped.

6. The standard flow generating device according to claim 1, characterized in that: The device uses an electronic balance as a standard device. First, liquid is passed into a water storage container. After the flow rate stabilizes, a switching valve is used to switch the flow rate. At the same time, a timer is started. The program can calculate the mass flow value in real time by receiving the electronic balance signal and the timer signal, and use the flow rate as the standard value for comparison.

7. The tracking reading device of the rotor flowmeter according to claim 1, characterized in that: The lifting device for tracking the head-up rotor uses a sliding guide rail and an industrial camera combination. The camera is fixed on the guide rail to face the rotor flowmeter. The host computer judges and sends instructions to the single-axis controller. The controller sends PWM waves to the motor for forward and reverse rotation, and controls the guide rail to move the camera at different speeds to track the head-up rotor. Two high and low limiters are added to the sliding guide rail and camera combination, and the heights correspond to the top and bottom ends of the rotor flow meter, thereby improving the efficiency of finding the rotor boundary box.

Citation Information

Cited By

  • Natural gas energy metering device

    CN119958663A

  • Automatic control method and system for supergravity desulfurization reaction, electronic equipment and medium

    CN120346649A