Flowmeter transit condition monitoring method, system, electronic device, and storage medium

Abstract

This invention discloses a method, system, electronic device, and storage medium for monitoring the transportation status of flow meters, relating to the field of equipment transportation technology. The method involves dividing the transportation route into smooth and complex road conditions based on the transportation route. When traveling on smooth road conditions, only a small number of sensors providing basic functions are activated; when traveling on complex road conditions, a large number of other sensors providing multi-dimensional data are activated. In transporting standard flow meter devices, this invention first determines whether the road conditions are smooth or complex based on the transportation route map. For smooth road conditions, fewer sensors are activated for transportation status monitoring, while for complex road conditions, more sensors are activated, thereby reducing the overall energy consumption of the monitoring system. Furthermore, when traveling on complex road conditions, a deep learning model receives real-time data input from the sensors and outputs corresponding road condition prediction results, thus eliminating most unstable factors in advance.

Description

Technical Field

[0001] This invention relates to the field of equipment transportation technology, and in particular to a method, system, electronic device, and storage medium for monitoring the transportation status of flow meters. Background Technology

[0002] In the processes of oil and gas extraction, storage, and transportation, the accuracy of flow meter monitoring data is obtained by comparing it with a flow meter standard device, which is used to calibrate the flow meter. When the flow meter standard device malfunctions, the reliability of the flow meter data cannot be determined, and the incidence of production accidents and economic losses will increase significantly.

[0003] During long-distance transportation of flow meters and flow meter standard devices, changes in ambient temperature and humidity, changes in motion, and vibration and shock can significantly affect the accuracy of the equipment and may cause measurement errors in the flow meter standard device during operation.

[0004] To effectively analyze and diagnose faults in flow meter standard devices during transportation, there is an urgent need for a monitoring method and system capable of real-time monitoring of the multi-dimensional status and motion trajectory of flow meter standard devices, as well as processing, storing, transmitting, analyzing, and presenting the data. Simultaneously, the monitoring process should consume as little energy as possible, facilitate retrospective querying of the device's operating status, provide a reliable basis for judging the working accuracy of the flow meter standard device, and promptly issue alarms in case of instability, prompting transportation personnel to take immediate action. Summary of the Invention

[0005] To address the aforementioned problems, a first aspect of the present invention provides a method for monitoring the transport status of a flow meter, comprising the following steps: S1: Determine the road conditions based on the transportation operation route map, and classify the road conditions involved in the route map into two categories: smooth road conditions and complex road conditions; S2: When the transportation operation route map indicates that the driving route is in smooth road conditions, the first sensor set is activated to monitor the smooth road conditions; then proceed to S4. S3: When the transportation operation route map indicates that the driving route is in complex road conditions, the second sensor set is activated to monitor the complex road conditions, and then proceeds to S5; S4: Compare the deviation values ​​of the data collected by various sensors in the first sensor set with the corresponding threshold values, and determine whether to issue an alarm based on the deviation values; S5: Based on the current data monitored by the vibration sensor and acceleration sensor in the second sensor set, predict the data for the next moment. If the predicted data for the next moment exceeds the corresponding threshold, issue an alarm.

[0006] Furthermore, in S1, the road conditions are judged based on the road surface smoothness and traffic density. The method for determining complex road conditions is as follows: the road surface smoothness is lower than the first set threshold, and the traffic flow density is higher than the second set threshold; The method for determining smooth road conditions is: all road conditions except for the complex road conditions.

[0007] Furthermore, in S2, the first sensor set includes: a GPS sensor, a temperature sensor, a humidity sensor, and a vibration sensor.

[0008] Furthermore, in S3, the second sensor set includes: a GPS sensor, a temperature sensor, a humidity sensor, a vibration sensor, and an acceleration sensor.

[0009] Furthermore, in step S4, an alarm is issued based on the deviation between the data collected by various sensors in the first sensor set and the corresponding threshold. The specific determination method is as follows: If the value collected by the temperature sensor is greater than the first temperature threshold, an alarm will be issued; If the value collected by the humidity sensor is greater than the first humidity threshold, an alarm will be issued; If the value collected by the vibration sensor is greater than the first vibration threshold, an alarm will be issued.

[0010] Furthermore, the system determines whether to issue an alarm based on the deviation between the data collected by various sensors in the second sensor set and the corresponding threshold. The specific determination method is as follows: If the value collected by the temperature sensor is greater than the second temperature threshold, an alarm will be issued; If the value collected by the humidity sensor is greater than the second humidity threshold, an alarm will be issued; If the value collected by the vibration sensor is greater than the second vibration threshold, an alarm will be issued.

[0011] Furthermore, in S5, the current sensor data monitored by various sensors in the second sensor set includes: vibration sensor data and acceleration sensor data.

[0012] Furthermore, in step S5, the data for the next time step is predicted using a deep learning model, wherein the deep learning model is a convolutional neural network model. The input data for the convolutional neural network model are: the current speed of the transport vehicle, the current road surface smoothness score, the current route vehicle density score, the current acceleration, and the current vibration level. The output of the convolutional neural network model is a prediction: the acceleration at the next moment and the vibration at the next moment.

[0013] Secondly, the present invention also discloses a flow meter transportation status monitoring system, which uses the flow meter transportation status monitoring method described above, and includes the following modules: The sensor activation module is used to control the switching on and off of various sensors according to different road conditions. The road condition classification module, connected to the sensor activation module, is used to determine whether the current road condition is a stable road condition or a complex road condition based on the transportation operation route map. The road condition monitoring module is connected to the road condition classification module and is used to compare the data collected by various sensors with the corresponding thresholds to determine whether to issue an alarm. The prediction module, connected to the sensor activation module, is used to predict the sensor data for the next moment based on the current sensor data when driving in complex road conditions, and to determine whether an alarm should be triggered.

[0014] Thirdly, the present invention also provides an electronic device comprising: a processor and a memory; the memory being used to store a computer program, which, when executed by the processor, causes the electronic device to perform the method described in any of the implementations of the first aspect.

[0015] Fourthly, the present invention also provides a storage medium comprising: a computer program or instructions; which, when executed on a computer, causes the computer to perform the method described in any of the possible implementations of the first aspect.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) When the standard device for transporting the flow meter is used, the present invention first determines whether the road condition is stable or complex based on the transport operation route map. For stable road conditions, fewer sensors are turned on for transport status monitoring, and for complex road conditions, more sensors are turned on for transport status monitoring, thereby reducing the energy consumption of the overall monitoring system.

[0017] (2) In the case of monitoring stable road conditions, the present invention compares the real-time collected sensor monitoring value with the corresponding threshold value, and issues an alarm when the sensor monitoring value exceeds the threshold value. (3) In view of the fact that there are many factors that can cause stability risks to the flow meter standard device due to complex road conditions, a deep learning model is used to predict the acceleration value and vibration value at the next moment, and then issue an early warning, thereby eliminating most of the unstable factors in advance and improving the safety of the flow meter standard device during transportation. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 Here is a flowchart of the transportation status monitoring method in Example 1; Figure 2 This is a diagram of the transportation status monitoring system in Example 2. Detailed Implementation

[0020] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0021] Example 1 The following is combined Figure 1 As shown, this embodiment of the invention provides a method for monitoring the transportation status of a flow meter, including the following steps: Step S1: Determine the road conditions based on the transportation operation route map, and classify the road conditions involved in the route map into two categories: smooth road conditions and complex road conditions.

[0022] It is worth emphasizing that the operation route map can be the entire operation route map, which can be evaluated and divided into smooth road conditions and complex road conditions; in addition, the operation route map can also be a segment operation route map. For example, the transportation personnel can manually divide the operation route map into several segments according to the characteristics of the route map, and make judgments on the road conditions of each segment operation route map.

[0023] In the standard device for transporting flow meters, the present invention first determines whether the road conditions are stable or complex based on the transport operation route map. For stable road conditions, fewer sensors are activated for transport status monitoring, while for complex road conditions, more sensors are activated for transport status monitoring, thereby reducing the overall energy consumption of the monitoring system.

[0024] In step S1, the road conditions are judged based on the road surface smoothness and traffic density. The method for determining complex road conditions is as follows: the road surface smoothness is lower than the first set threshold, and the traffic flow density is higher than the second set threshold; The method for determining smooth road conditions is: all road conditions except for the complex road conditions.

[0025] Step S2: When the transportation operation route map indicates that the driving route is in smooth road conditions, the first sensor set is activated to monitor the smooth road conditions; then proceed to step S4.

[0026] Specifically, when the transportation route map indicates that the driving route is in a stable condition, the road conditions are relatively simple compared to complex road conditions. There are fewer factors that could cause stability risks to the flow meter standard device. In order to reduce power consumption and the generation of redundant data, only various sensors that can meet the basic monitoring functions are turned on, thereby reducing the energy consumption of the entire monitoring system. At the same time, since the number of sensors turned on is small, less monitoring data is generated, which greatly reduces the amount of data to be processed, and also reduces the energy consumption of the monitoring system in processing redundant data.

[0027] In step S2, the first sensor set includes: GPS sensor, temperature sensor, humidity sensor, and vibration sensor.

[0028] Step S3: When the transportation operation route map indicates that the driving route is in complex road conditions, activate the second sensor set to monitor the complex road conditions, and then proceed to step S5.

[0029] Specifically, when the transportation operation route map indicates a complex road condition, the road condition is more complex than that of a smooth road condition. There are many factors that can cause stability risks to the flow meter standard device. Therefore, it is necessary to monitor the transportation status of the flow meter standard device in multiple dimensions. At this time, more types of sensors are activated to monitor the transportation status in multiple dimensions.

[0030] In step S3, the second sensor set includes: a GPS sensor, a temperature sensor, a humidity sensor, a vibration sensor, and an acceleration sensor.

[0031] Step S4: Compare the data collected by various sensors in the first sensor set with the deviation values ​​of the corresponding thresholds, and determine whether to issue an alarm based on the deviation values.

[0032] In monitoring stable road conditions, this invention addresses the fact that there are few factors that could pose a risk to the flow meter standard device under stable road conditions. It compares the real-time sensor monitoring values ​​with corresponding thresholds and issues an alarm when the sensor monitoring values ​​exceed the thresholds.

[0033] In step S4, whether to issue an alarm is determined based on the deviation between the data collected by various sensors in the first sensor set and the corresponding threshold. The specific determination method is as follows: If the value collected by the temperature sensor is greater than the first temperature threshold, an alarm will be issued; If the value collected by the humidity sensor is greater than the first humidity threshold, an alarm will be issued; If the value collected by the vibration sensor is greater than the first vibration threshold, an alarm will be issued.

[0034] Whether to issue an alarm is determined based on the deviation between the data collected by various sensors in the second sensor set and the corresponding threshold. The specific determination method is as follows: If the value collected by the temperature sensor is greater than the second temperature threshold, an alarm will be issued; If the value collected by the humidity sensor is greater than the second humidity threshold, an alarm will be issued; If the value collected by the vibration sensor is greater than the second vibration threshold, an alarm will be issued.

[0035] Step S5: Predict the data for the next moment based on the current data monitored by the vibration sensor and acceleration sensor in the second sensor set. If the predicted data for the next moment exceeds the corresponding threshold, an alarm is issued.

[0036] Specifically, the vibration data currently monitored by the vibration sensor and the acceleration data monitored by the acceleration sensor are both obtained by filtering after sensor measurement and have a certain time delay. Due to the complex characteristics of the complex road conditions, the vibration and acceleration data transported by the flow meter standard device are random time series data. Therefore, it is difficult to realize alarms by relying solely on sensor measurements to adapt to the data monitoring of complex road conditions. It is necessary to predict subsequent data based on the current sensor data to replace the real-time measurement of the current data and issue an alarm.

[0037] This invention addresses the current situation where complex road conditions pose numerous risks to flow meter standard devices. It not only assesses real-time sensor readings to trigger alarms but also employs a deep learning model to predict acceleration and vibration values ​​at the next moment, thereby issuing early warnings and eliminating most unstable factors in advance, thus improving the safety of flow meter standard devices during transportation.

[0038] In step S5, the data for the next time step is predicted using a deep learning model, wherein the deep learning model is a convolutional neural network model. Convolutional Neural Network (CNN) is a widely used type of neural network. Its widespread application is inseparable from the development of deep learning technology. Furthermore, its multi-dimensional structure and specially designed multi-perceptron features enable it to classify a wide variety of features.

[0039] The input data for the convolutional neural network model are: the current speed of the transport vehicle, the current road surface smoothness score, the current route vehicle density score, the current acceleration, and the current vibration level. The output of the convolutional neural network model is a prediction: the acceleration at the next moment and the vibration at the next moment; Furthermore, the convolutional neural network model consists of three parts: an input layer, convolutional layers, and fully connected layers. Each convolutional layer includes eight convolutional pooling layers. The first two convolutional layers have 64 filters, and the last two have 128 filters. The filter size for all four convolutional layers is uniformly set to 2, and the stride is uniformly set to 1. Each convolutional layer is followed by a pooling layer with the same parameters. Max pooling is used for inter-layer data processing, and the filter size and stride of the pooling layer are both set to 2. Additionally, the same padding is selected as the padding attribute for all convolutional pooling layers to ensure that the dimensions of the data remain consistent before and after passing through a hidden layer.

[0040] Example 2 The flow meter transportation status monitoring system uses the flow meter transportation status monitoring method described above, such as... Figure 2 As shown, it includes the following modules: The sensor activation module is used to control the switching on and off of various sensors according to different road conditions. The road condition classification module, connected to the sensor activation module, is used to determine whether the current road condition is a stable road condition or a complex road condition based on the transportation operation route map. The road condition monitoring module is connected to the road condition classification module and is used to compare the data collected by various sensors with the corresponding thresholds to determine whether to issue an alarm. The prediction module, connected to the sensor activation module, is used to predict the sensor data for the next moment based on the current sensor data when driving in complex road conditions, and to determine whether to issue an alarm.

[0041] Example 3 The present invention also provides an electronic device. The electronic device includes a processor and a memory; the memory is used to store a computer program, which, when executed by the processor, causes the electronic device to perform the method described in any implementation of the first aspect.

[0042] Example 4 The present invention also provides a storage medium comprising: a computer program or instructions; which, when executed on a computer, causes the computer to perform the method described in any of the possible implementations of the first aspect.

[0043] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring the transport status of a flow meter, characterized in that, Includes the following steps: S1: Determine the road conditions based on the transportation operation route map, and classify the road conditions involved in the route map into two categories: smooth road conditions and complex road conditions; S2: When the transportation operation route map indicates that the driving route is in smooth road conditions, the first sensor set is activated to monitor the smooth road conditions; then proceed to S4. S3: When the transportation operation route map indicates that the driving route is in complex road conditions, the second sensor set is activated to monitor the complex road conditions, and then proceeds to S5; S4: Compare the deviation values ​​of the data collected by various sensors in the first sensor set with the corresponding threshold values, and determine whether to issue an alarm based on the deviation values; S5: Based on the current data monitored by the vibration sensor and acceleration sensor in the second sensor set, predict the data for the next moment. If the predicted data for the next moment exceeds the corresponding threshold, issue an alarm. Predict the data for the next time step using a deep learning model, wherein the deep learning model is a convolutional neural network model; The input data for the convolutional neural network model are: the current speed of the transport vehicle, the current road surface smoothness score, the current route vehicle density score, the current acceleration, and the current vibration level. The output of the convolutional neural network model is a prediction: the acceleration at the next moment and the vibration at the next moment.

2. The flow meter transportation status monitoring method according to claim 1, characterized in that, In step S1, the road conditions are judged based on the road surface smoothness and traffic density. The method for determining complex road conditions is as follows: the road surface smoothness is lower than the first set threshold, and the traffic flow density is higher than the second set threshold; The method for determining smooth road conditions is: all road conditions except for the complex road conditions.

3. The method for monitoring the transport status of a flow meter according to claim 1, characterized in that, In S2, the first sensor set includes: GPS sensor, temperature sensor, humidity sensor, and vibration sensor.

4. The flow meter transportation status monitoring method according to claim 1, characterized in that, In S3, the second sensor set includes: a GPS sensor, a temperature sensor, a humidity sensor, a vibration sensor, and an acceleration sensor.

5. The flow meter transportation status monitoring method according to claim 4, characterized in that, In step S4, an alarm is issued based on the deviation between the data collected by various sensors in the first sensor set and the corresponding threshold. The specific determination method is as follows: If the value collected by the temperature sensor is greater than the first temperature threshold, an alarm will be issued; If the value collected by the humidity sensor is greater than the first humidity threshold, an alarm will be issued; If the value collected by the vibration sensor is greater than the first vibration threshold, an alarm will be issued.

6. The method for monitoring the transport status of a flow meter according to claim 4, characterized in that, Whether to issue an alarm is determined based on the deviation between the data collected by various sensors in the second sensor set and the corresponding threshold. The specific determination method is as follows: If the value collected by the temperature sensor is greater than the second temperature threshold, an alarm will be issued; If the value collected by the humidity sensor is greater than the second humidity threshold, an alarm will be issued; If the value collected by the vibration sensor is greater than the second vibration threshold, an alarm will be issued.

7. A flow meter transportation status monitoring system, using the flow meter transportation status monitoring method as described in any one of claims 1-6, characterized in that, Includes the following modules: The sensor activation module is used to control the switching on and off of various sensors according to different road conditions. The road condition classification module, connected to the sensor activation module, is used to determine whether the current road condition is a stable road condition or a complex road condition based on the transportation operation route map. The road condition monitoring module is connected to the road condition classification module and is used to compare the data collected by various sensors with the corresponding thresholds to determine whether to issue an alarm. The prediction module, connected to the sensor activation module, is used to predict the sensor data for the next moment based on the current sensor data when driving in complex road conditions, and to determine whether to issue an alarm.

8. An electronic device, characterized in that, include: Processor, the processor being coupled to memory; The processor is configured to execute a computer program stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-6.

9. A storage medium, characterized in that, The storage medium includes a computer program or instructions that, when run on a computer, cause the method as described in any one of claims 1-6 to be performed.

Images