Real-time monitoring oiling machine working parameter detection method

Abstract

The invention relates to the technical field of oiling machine parameter detection, in particular to a real-time monitoring oiling machine working parameter detection method. The detection method comprises the following steps: acquiring to-be-detected working parameters of each position of the oiling machine, wherein the to-be-detected working parameters comprise an oil gun working parameter, an oil pipe working parameter, an oil tank working parameter and a duration working parameter; preprocessing the working parameters to be detected to obtain preprocessed working parameters; the preprocessed working parameters are input into a constructed detection model group, a detection result is obtained, and the detection model group comprises a first detection model, a second detection model, a third detection model and a fourth detection model corresponding to all positions of the oiling machine; and inputting the detection result into a cloud platform monitoring center for monitoring and alarming. According to the invention, the to-be-detected working parameters of each position of the oiling machine can be obtained in real time, so that the monitoring process has timeliness, and the detection efficiency of the working parameters of the oiling machine is remarkably improved.

Description

Technical fields:

[0001] This invention relates to the field of fuel dispenser parameter detection technology, and in particular to a method for real-time monitoring and detection of fuel dispenser operating parameters. Background technology:

[0002] With the continuous increase in car ownership, the performance and safety of fuel dispensers, as crucial equipment at gas stations, are paramount. Currently, the operating parameters of fuel dispensers (such as fuel flow rate, pressure, and temperature) typically rely on mechanical metering and manual inspection, making real-time monitoring difficult. Furthermore, traditional detection methods suffer from low efficiency and data lag, hindering timely responses to malfunctions or safety hazards during operation. Summary of the Invention:

[0003] The technical problem to be solved by the present invention is to provide a method for real-time monitoring of fuel dispenser operating parameters. This device can acquire the operating parameters to be detected at various locations of the fuel dispenser in real time, making the monitoring process timely and significantly improving the efficiency of fuel dispenser operating parameter detection.

[0004] The technical solution adopted in this invention is: a method for real-time monitoring and detection of operating parameters of a fuel dispenser, comprising:

[0005] The working parameters to be detected at each position of the fuel dispenser are obtained, including: fuel nozzle working parameters, fuel pipe working parameters, fuel tank working parameters, and duration working parameters.

[0006] The working parameters to be detected are preprocessed to obtain the preprocessed working parameters;

[0007] The preprocessed working parameters are input into the constructed detection model group to obtain the detection results. The detection model group consists of a first detection model, a second detection model, a third detection model, and a fourth detection model corresponding to each position of the fuel dispenser.

[0008] The detection results are input into the cloud platform monitoring center for monitoring and alarm.

[0009] Furthermore, the acquisition of the detection parameters for each position of the fuel dispenser includes:

[0010] Collect the physical parameters of the flow measurement converter, and establish a correlation model between the measured flow and piston operation based on the physical parameters of the flow measurement converter;

[0011] Install the piston movement detector on the flow measurement converter;

[0012] When the fuel dispenser starts refueling, the piston inside the flow measurement converter moves, and the piston movement detector detects the piston movement and obtains the piston movement signal.

[0013] The piston movement signal is filtered to obtain piston movement filtering information;

[0014] A fuel dispenser metering model is jointly established based on piston operation filtering information and a model of flow rate and piston operation correlation values. A first set of operating parameters is obtained based on the fuel dispenser metering model.

[0015] Pressure sensors, temperature sensors, and oil quality sensors are installed at various locations on the fuel dispenser to obtain a second subset of operating parameters. The operating parameters of the fuel nozzle, fuel line, and fuel tank all include the first subset of operating parameters and the second subset of operating parameters.

[0016] The system uses dual cameras to take pictures of the vehicle to be refueled, obtaining images of the vehicle before and after refueling, and then obtains the operating parameters of the refueling machine based on the images.

[0017] The working parameters to be detected are obtained based on the duration working parameters, the first subset of working parameters, and the second subset of working parameters.

[0018] Furthermore, the expression for the correlation model between the measured flow rate and piston operation is as follows:

[0019] Q = 0.8·A·v p ;

[0020] Where Q is the flow rate, representing the amount of oil passing through the flow meter transducer, A is the effective cross-sectional area of ​​the piston, and v p This represents the average speed of the piston.

[0021] Furthermore, the expression for the fuel dispenser metering model is:

[0022] M = Q·(1 + 0.6(TT)) ref )+0.9(PP ref ))·ρ;

[0023] Where M is the measurement result, representing the total amount of fuel dispensed by the fuel dispenser, and T is the fuel temperature. ref P represents the average operating temperature, P represents the oil pressure, and P0 represents the average operating temperature. ref ρ is the average oil pressure, and ρ is the oil density.

[0024] Further, the filtering of the piston running signal to obtain piston running filtered information includes:

[0025] The piston running signal is sampled according to the preset signal sampling frequency to obtain the sampled data sequence;

[0026] The sampled data sequence is decomposed into low-frequency and high-frequency sequences by using wavelet transform or short-time Fourier transform.

[0027] The low-frequency sequence is digitally filtered using a first comb filter to obtain the first filtered data sequence.

[0028] The first filtered data sequence is input into the second comb filter for two-stage digital filtering to obtain the second filtered data sequence.

[0029] The high-frequency sequence is input into the first low-pass filter for three-stage digital filtering to obtain the third filtered data sequence.

[0030] The third filtered data sequence is input into the second low-pass filter for four-stage digital filtering to obtain the fourth filtered data sequence.

[0031] The fourth filtered data sequence is post-processed to obtain the final filtered data sequence;

[0032] Feature values ​​are extracted from the piston running signal, and piston running filtering information is obtained based on the final filtered data sequence.

[0033] Furthermore, the method for constructing the first detection model is as follows:

[0034] Obtain historical flow and pressure data for the oil gun;

[0035] The first detection model is constructed based on machine learning algorithms and the historical flow and pressure data of the oil guns.

[0036] Furthermore, the method for constructing the second detection model is as follows:

[0037] Acquire historical data on pressure, flow, and temperature sensors within the tubing;

[0038] The second detection model is constructed based on the state-space model and the historical pressure, flow, and temperature sensor data in the tubing.

[0039] Furthermore, the method for constructing the third detection model is as follows:

[0040] Acquire historical data on oil level, temperature, and pressure within the oil tank;

[0041] The third detection model is constructed based on a linear regression model and the historical oil level, temperature, and pressure data in the oil tank.

[0042] Furthermore, the method for constructing the fourth detection model is as follows:

[0043] Acquire images of vehicles before and after refueling from historical refueling records;

[0044] The fourth detection model is constructed based on the image recognition and time series analysis model, using images of historical vehicles before and after refueling.

[0045] The beneficial effects of this invention are:

[0046] This invention enables timely monitoring by acquiring the operational parameters to be detected at various locations on the refueling pump in real time. Compared to traditional methods, which typically require periodic inspections or manual patrols, this method significantly improves efficiency. Employing multiple targeted detection models (models one through four) allows for parallel processing of parameters from different locations, providing rapid response and accurate detection results even in complex working environments. This modular design enhances the overall operational efficiency of the system. Attached image description:

[0047] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0048] Figure 1 A flowchart illustrating a real-time monitoring method for detecting the operating parameters of a fuel dispenser, as provided in an embodiment of the present invention. Detailed implementation method:

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0051] like Figure 1 As shown, the present invention provides a method for real-time monitoring and detection of operating parameters of a fuel dispenser, comprising:

[0052] Step 100: Obtain the working parameters to be detected at each position of the fuel dispenser, including: fuel nozzle working parameters, fuel pipe working parameters, fuel tank working parameters, and duration working parameters;

[0053] Step 200: Preprocess the working parameters to be detected to obtain preprocessed working parameters;

[0054] Step 300: Input the preprocessed working parameters into the constructed detection model group to obtain the detection results, wherein the detection model group consists of a first detection model, a second detection model, a third detection model, and a fourth detection model corresponding to each position of the fuel dispenser;

[0055] Step 400: Input the detection results into the cloud platform monitoring center for monitoring and alarm.

[0056] Specifically, the acquired parameter data is uploaded to the cloud platform via wireless networks (such as Wi-Fi, 4G / 5G, etc.), and this process employs encryption technology to protect data security. The data upload frequency can be set according to actual needs (e.g., real-time upload or upload at regular intervals). Users can log in to the cloud platform monitoring system via computer or mobile device to view the fuel dispenser's operating parameters in real time. The system provides an early warning function based on set thresholds; if the monitored operating parameters exceed the normal range, the system will automatically push an alarm to prompt the administrator to check.

[0057] Furthermore, the acquisition of the working parameters to be detected at each position of the refueling machine includes:

[0058] Collect the physical parameters of the flow measurement converter, and establish a correlation model between the measured flow and piston operation based on the physical parameters of the flow measurement converter;

[0059] Install the piston movement detector on the flow measurement converter;

[0060] When the fuel dispenser starts refueling, the piston inside the flow measurement converter moves, and the piston movement detector detects the piston movement and obtains the piston movement signal.

[0061] The piston movement signal is filtered to obtain piston movement filtering information;

[0062] A fuel dispenser metering model is jointly established based on piston operation filtering information and a model of flow rate and piston operation correlation values. A first set of operating parameters is obtained based on the fuel dispenser metering model.

[0063] Specifically, the physical parameters of the flow measurement converter are collected, and a model of the correlation between the measured flow and piston operation is established based on the physical parameters of the flow measurement converter. The parameters of this model are derived from the physical parameters of the flow measurement converter, so the correlation between the measured flow and piston operation corresponding to different flow measurement converters can be obtained through this model.

[0064] A piston movement detector is installed on the flow measurement transducer. The piston movement detector detects piston movement through vibration or magnetic field induction. The piston movement detector uses an EMS sensor. The inlet pipe is connected to the inlet, and the outlet pipe is connected to the outlet. Oil enters the flow measurement transducer through the inlet and outlet, and exits through the outlet and outlet. The flow of oil within the flow measurement transducer drives the mechanical piston.

[0065] Specifically, based on the piston operation detector, a redundant detection mechanism, such as an ultrasonic sensor or a photoelectric sensor, is added to ensure that the piston's operating status can still be accurately detected under different environmental conditions (such as high temperature, low temperature, oil vapor interference, etc.).

[0066] Thresholds and algorithms are set to determine abnormal piston operating conditions (such as jamming or failure) and to issue timely alarms.

[0067] When the fuel dispenser starts refueling, the piston inside the flow measurement converter moves, and the piston movement detector detects the piston movement and obtains the piston movement signal.

[0068] Pressure sensors, temperature sensors, and oil quality sensors are installed at various locations on the fuel dispenser to obtain a second subset of operating parameters. The operating parameters of the fuel nozzle, fuel line, and fuel tank all include the first subset of operating parameters and the second subset of operating parameters.

[0069] Specifically, the first subset of operating parameters includes basic parameters such as flow rate and pressure, while the second subset of operating parameters should include secondary influencing factors such as temperature and oil quality.

[0070] The system uses dual cameras to take pictures of the vehicle to be refueled, obtaining images of the vehicle before and after refueling, and then obtains the operating parameters of the refueling machine based on the images.

[0071] Specifically, when taking photos with dual cameras, a control system is added to ensure the standardization of shooting conditions (such as light, angle, and distance) in order to obtain clear images that can be used for analysis.

[0072] By using computer vision technology to process the obtained images, we can not only obtain the refueling time, but also further analyze information such as the vehicle's location, the connection status of the fuel nozzle, and changes in the fuel level.

[0073] The working parameters to be detected are obtained based on the duration working parameters, the first subset of working parameters, and the second subset of working parameters.

[0074] Furthermore, the expression for the correlation model between the measured flow rate and piston operation is as follows:

[0075] Q = 0.8·A·v p ;

[0076] Where Q is the flow rate, representing the amount of oil passing through the flow meter transducer, A is the effective cross-sectional area of ​​the piston, and v p This represents the average speed of the piston.

[0077] Furthermore, the expression for the fuel dispenser metering model is:

[0078] M = Q·(1 + 0.6(TT))ref )+0.9(PP ref ))·ρ;

[0079] Where M is the measurement result, representing the total amount of fuel dispensed by the fuel dispenser, and T is the fuel temperature. ref P represents the average operating temperature, P represents the oil pressure, and P0 represents the average operating temperature. ref ρ is the average oil pressure, and ρ is the oil density.

[0080] Furthermore, the filtering of the piston running signal to obtain piston running filtered information includes:

[0081] The piston running signal is sampled according to the preset signal sampling frequency to obtain the sampled data sequence;

[0082] The sampled data sequence is decomposed into low-frequency and high-frequency sequences by using wavelet transform or short-time Fourier transform.

[0083] The low-frequency sequence is digitally filtered using a first comb filter to obtain the first filtered data sequence.

[0084] The first filtered data sequence is input into the second comb filter for two-stage digital filtering to obtain the second filtered data sequence.

[0085] The high-frequency sequence is input into the first low-pass filter for three-stage digital filtering to obtain the third filtered data sequence.

[0086] The third filtered data sequence is input into the second low-pass filter for four-stage digital filtering to obtain the fourth filtered data sequence.

[0087] The fourth filtered data sequence is post-processed to obtain the final filtered data sequence;

[0088] Specifically, adaptive filters are applied to the extracted low-frequency and high-frequency components to adjust the dynamically changing filter parameters in real time.

[0089] Low-frequency components are processed by the first and second comb filters in a parallel manner to enhance selectivity at specific frequencies.

[0090] High-frequency components are processed by the parallel processing of the first and second low-pass filters to attenuate high-frequency noise.

[0091] Feature values ​​are extracted from the piston running signal, and piston running filtering information is obtained based on the final filtered data sequence.

[0092] Specifically, feature values ​​are extracted from the reconstructed filtered signal. Depending on the specific requirements, features such as mean, standard deviation, peak value, and frequency components can be extracted.

[0093] Machine learning algorithms (such as random forests and support vector machines) are used to analyze features in order to automatically identify the piston's operating status and failure mode.

[0094] Furthermore, the method for constructing the first detection model is as follows:

[0095] Obtain historical flow and pressure data for the oil gun;

[0096] The first detection model is constructed based on machine learning algorithms and the historical flow and pressure data of the oil guns.

[0097] Furthermore, the method for constructing the second detection model is as follows:

[0098] Acquire historical data on pressure, flow, and temperature sensors within the tubing;

[0099] The second detection model is constructed based on the state-space model and the historical pressure, flow, and temperature sensor data in the tubing.

[0100] Furthermore, the method for constructing the third detection model is as follows:

[0101] Acquire historical data on oil level, temperature, and pressure within the oil tank;

[0102] The third detection model is constructed based on a linear regression model and the historical oil level, temperature, and pressure data in the oil tank.

[0103] Furthermore, the method for constructing the fourth detection model is as follows:

[0104] Acquire images of vehicles before and after refueling from historical refueling records;

[0105] The fourth detection model is constructed based on the image recognition and time series analysis model, using images of historical vehicles before and after refueling.

[0106] Specifically, the expression for the first detection model is:

[0107] P 枪 = f(Q1,P1,T1,S);

[0108] Among them, P 枪 To indicate the working status of the oil gun, S represents the historical flow and pressure data of the oil gun, Q1 represents the flow rate of the oil gun, P1 represents the pressure of the oil gun, and T1 represents the oil temperature of the oil gun.

[0109] Specifically, the expression for the second detection model is:

[0110]

[0111] Where P2 is the pressure inside the tubing, Q2 is the flow rate of the tubing, T2 is the temperature of the tubing, F is the external factor, and A and B are the system matrices, reflecting the dynamic characteristics of the tubing.

[0112] Specifically, the expression for the third detection model is:

[0113] H 罐 =g(L,P 罐 ,T 罐 );

[0114] Among them, H 罐 For the operating parameters of the oil tank, P 罐 For the pressure of the oil tank, T 罐 L represents the pressure of the oil tank, and L represents the oil level in the tank.

[0115] Specifically, the expression for the fourth detection model is:

[0116] T 工作 =h(I 前 ,I 后 ,D);

[0117] Among them, T 工作 For refueling time, I 前 ,I 后 These represent image data before and after refueling, respectively, with D representing the vehicle's position and dynamic parameters.

[0118] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0119] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for detecting the operating parameters of a fuel dispenser in real time, characterized in that: include: The working parameters to be detected at each position of the fuel dispenser are obtained, including: fuel nozzle working parameters, fuel pipe working parameters, fuel tank working parameters, and duration working parameters. The working parameters to be detected are preprocessed to obtain the preprocessed working parameters; The preprocessed working parameters are input into the constructed detection model group to obtain the detection results. The detection model group consists of a first detection model, a second detection model, a third detection model, and a fourth detection model corresponding to each position of the fuel dispenser. The detection results are input into the cloud platform monitoring center for monitoring and alarm.

2. The method for detecting real-time monitoring operating parameters of a fuel dispenser according to claim 1, characterized in that: The acquisition of the working parameters to be detected at each position of the fuel dispenser includes: Collect the physical parameters of the flow measurement converter, and establish a correlation model between the measured flow and piston operation based on the physical parameters of the flow measurement converter; Install the piston movement detector on the flow measurement converter; When the fuel dispenser starts refueling, the piston inside the flow measurement converter moves, and the piston movement detector detects the piston movement and obtains the piston movement signal. The piston movement signal is filtered to obtain piston movement filtering information; A fuel dispenser metering model is jointly established based on piston operation filtering information and a model of flow rate and piston operation correlation values. A first set of operating parameters is obtained based on the fuel dispenser metering model. Pressure sensors, temperature sensors, and oil quality sensors are installed at various locations on the fuel dispenser to obtain a second subset of operating parameters. The operating parameters of the fuel nozzle, fuel line, and fuel tank all include the first subset of operating parameters and the second subset of operating parameters. The system uses dual cameras to take pictures of the vehicle to be refueled, obtaining images of the vehicle before and after refueling, and then obtains the operating parameters of the refueling machine based on the images. The working parameters to be detected are obtained based on the duration working parameters, the first subset of working parameters, and the second subset of working parameters.

3. The method for detecting real-time monitoring operating parameters of a fuel dispenser according to claim 2, characterized in that: The expression for the correlation model between the measured flow rate and piston operation is as follows: Q = 0.8 * A * vp; Where Q is the flow rate, representing the amount of oil passing through the flow meter converter, A is the effective cross-sectional area of ​​the piston, and vp is the average speed of the piston.

4. The method for detecting real-time monitoring operating parameters of a fuel dispenser according to claim 3, characterized in that: The expression for the fuel dispenser metering model is: M=Q·(1+0.6(T-·Tref)+0.9(P-Pref))·ρ; Where M is the measurement result, representing the total amount of fuel dispensed by the fuel dispenser, T is the fuel temperature, and Tre is the fuel temperature. f The average operating temperature is P, the oil pressure is Pre. f ρ is the average oil pressure, and ρ is the oil density.

5. The method for detecting real-time monitoring operating parameters of a fuel dispenser according to claim 3, characterized in that: The filtering of the piston movement signal to obtain piston movement filtering information includes: The piston running signal is sampled according to the preset signal sampling frequency to obtain the sampled data sequence; The sampled data sequence is decomposed into low-frequency and high-frequency sequences by using wavelet transform or short-time Fourier transform. The low-frequency sequence is digitally filtered using a first comb filter to obtain the first filtered data sequence. The first filtered data sequence is input into the second comb filter for two-stage digital filtering to obtain the second filtered data sequence. The high-frequency sequence is input into the first low-pass filter for three-stage digital filtering to obtain the third filtered data sequence. The third filtered data sequence is input into the second low-pass filter for four-stage digital filtering to obtain the fourth filtered data sequence. The fourth filtered data sequence is post-processed to obtain the final filtered data sequence; Feature values ​​are extracted from the piston running signal, and piston running filtering information is obtained based on the final filtered data sequence.

6. The method for detecting real-time monitoring operating parameters of a fuel dispenser according to claim 1, characterized in that: The method for constructing the first detection model is as follows: Obtain historical flow and pressure data for the oil gun; The first detection model is constructed based on machine learning algorithms and the historical flow and pressure data of the oil guns.

7. The method for detecting real-time monitoring operating parameters of a fuel dispenser according to claim 1, characterized in that: The method for constructing the second detection model is as follows: Acquire historical data on pressure, flow, and temperature sensors within the tubing; The second detection model is constructed based on the state-space model and the historical pressure, flow, and temperature sensor data in the tubing.

8. The method for detecting real-time monitoring operating parameters of a fuel dispenser according to claim 1, characterized in that: The method for constructing the third detection model is as follows: Acquire historical data on oil level, temperature, and pressure within the oil tank; The third detection model is constructed based on a linear regression model and the historical oil level, temperature, and pressure data in the oil tank.

9. The method for detecting real-time monitoring operating parameters of a fuel dispenser according to claim 2, characterized in that: The method for constructing the fourth detection model is as follows: Acquire images of vehicles before and after refueling from historical refueling records; The fourth detection model is constructed based on the image recognition and time series analysis model, using images of historical vehicles before and after refueling.

Images