Artificial intelligence system for meter reading content verification

Abstract

The invention relates to an artificial intelligence system for verifying meter reading content, which comprises a hourly detection mechanism, a data processing mechanism, a data processing mechanism, a data processing mechanism and a data processing mechanism, wherein the hourly detection mechanism is used for acquiring each part of gas meter reading data corresponding to each time of meter reading before the current meter reading of a current gas meter; the gas consumption meter reading data obtained by each time of meter reading is a gas consumption value within a preset time length range before the meter reading action; and the intelligent identification equipment is used for intelligently analyzing a leakage identifier representing whether gas leakage exists in the current meter reading by adopting a Hough neural network model. According to the method and the device, whether gas leakage exists in the current meter reading can be judged by adopting the Hough neural network model with a customized structural design, and the Hough neural network model is the Hough neural network after multiple times of learning is executed; and the number of learning times of the Hough neural network is monotonically and positively associated with the use time of the current gas meter, so that the reliability of the current meter reading data of the current gas meter and intelligent exploration of fault causes are completed.

Description

Technical Field

[0001] The present invention relates to the field of gas meter management, and in particular to an artificial intelligence system for verifying meter reading content. Background Art

[0002] The same technology as the steam engine is used in the gas meter, so that when the membrane and the hard core move to the far left or right, the gas meter can continue to move. Specifically, two sets of bellows and membranes are used, and their hard cores are connected to the same vertical shaft with rods. There are two cranks on this shaft, and the two cranks are also 90 degrees apart, so that the movement of the two hard cores is half a step apart. When one moves to the end, the other is exactly in the middle and will never stop. The upper half of the gas meter is the crankshaft and connecting rod that you see when you look straight ahead, and the lower half is the top-down view, from which you can observe that the rotation of the crankshaft drives the roller counter, thereby accumulating the amount of gas consumed.

[0003] However, due to various reasons such as gas leakage, network data transmission deviation and meter body failure during the use of the gas meter, each meter reading data is inaccurate. Among them, the cause of gas leakage, in particular, requires key monitoring to effectively identify safety accidents and carry out rapid rescue. Obviously, the existing technology cannot complete the fault judgment of whether there is a gas leakage based on each meter reading data, resulting in the safety of the gas meter during use cannot be fully guaranteed. Summary of the invention

[0004] In order to solve the technical problems in the related fields, the present invention provides an artificial intelligence system for meter reading content verification, which introduces a network acquisition mechanism to parse out a Hoffet neural network model, wherein the Hoffet neural network model is a Hoffet neural network after executing multiple learnings, and the number of learnings of the Hoffet neural network is monotonically positively correlated with the usage time of the current gas meter, thereby customizing artificial intelligence models of different structures for different gas meters, and then synchronously inputting the preset time length, the maximum working pressure, maximum flow, minimum flow and volume of the installation environment of the current gas meter, and the gas meter reading data corresponding to each meter reading before the current meter reading of the current gas meter into the Hoffet neural network model, and executing the Hoffet neural network model to obtain the leakage mark output by the Hoffet neural network model indicating whether there is a gas leakage in the current meter reading, thereby completing the reliability of the current meter reading data of the current gas meter and the intelligent exploration of the cause of the fault.

[0005] According to the present invention, an artificial intelligence system for meter reading content verification is provided, the system comprising: A network acquisition mechanism, used for parsing out a Hoffet neural network model, wherein the Hoffet neural network model is a Hoffet neural network after executing multiple learnings, and the number of times the Hoffet neural network is learned is monotonically positively correlated with the current use time of the gas meter; The meter body capture mechanism is used to obtain various setting parameters of the current gas meter, wherein the various setting parameters of the current gas meter are the maximum working pressure, maximum flow rate, minimum flow rate and volume of the installation environment of the current gas meter; The hourly detection mechanism is used to obtain the gas meter reading data corresponding to each meter reading before the current meter reading. The gas meter reading data obtained at each meter reading is the gas usage value within a preset time range before the current meter reading action; An intelligent identification device is connected to the network acquisition mechanism, the meter body capture mechanism and the hourly detection mechanism respectively, and is used to synchronously input the preset time length, the maximum working pressure, maximum flow rate, minimum flow rate and volume of the installation environment of the current gas meter, and the gas meter reading data corresponding to each meter reading before the current meter reading into the Hoffet neural network model, and execute the Hoffet neural network model to obtain the leakage mark output by the Hoffet neural network model indicating whether there is a gas leakage in the current meter reading; Among them, the preset time length, the maximum working pressure, maximum flow, minimum flow and volume of the installation environment of the current gas meter, and the gas meter reading data corresponding to each meter reading before the current meter reading of the current gas meter are synchronously input into the Hoffet neural network model, and the Hoffet neural network model is executed to obtain the leakage mark output by the Hoffet neural network model indicating whether there is a gas leakage in the current meter reading, including: the leakage mark output by the Hoffet neural network model indicating whether there is a gas leakage in the current meter reading is a binary value, and two different binary values ​​are used to represent two different results of whether there is a gas leakage in the current meter reading; Among them, the gas meter reading data corresponding to each meter reading before the current meter reading are obtained. The gas meter reading data obtained for each meter reading is the gas usage value within a preset time range before the meter reading action, including: the number of each meter reading is monotonically positively correlated with the usage time of the current gas meter.

[0006] It can be seen that the present invention has at least the following important inventive concepts: Firstly: a network acquisition mechanism is introduced to parse out a Hoffet neural network model, wherein the Hoffet neural network model is a Hoffet neural network after multiple learnings are performed, and the number of times the Hoffet neural network is learned is monotonically positively correlated with the usage time of the current gas meter, thereby customizing artificial intelligence models with different structures for different gas meters; Secondly: the preset time length, the maximum working pressure, maximum flow, minimum flow and volume of the installation environment of the current gas meter, and the gas meter reading data corresponding to each meter reading before the current meter reading are synchronously input into the Hoffet neural network model, and the Hoffet neural network model is executed to obtain the leakage mark output by the Hoffet neural network model indicating whether there is a gas leakage in the current meter reading, thereby completing the reliability of the current meter reading data of the current gas meter and the intelligent exploration of the cause of the fault; Again: In each learning performed by the Hoffet neural network, the leakage mark of whether there is a gas leak in a known historical meter reading is used as the output data of the Hoffet neural network, and the preset time length, the maximum working pressure, maximum flow, minimum flow and volume of the installation environment of the current gas meter, and the gas meter reading data corresponding to each meter reading before the said historical meter reading are used as the input data of the Hoffet neural network to execute this learning of the Hoffet neural network, thereby ensuring the learning effect of each learning performed by the Hoffet neural network. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:

[0008] Figure 1 The figure is a schematic diagram of the internal structure of an artificial intelligence system for meter reading content verification according to the first embodiment of the present invention.

[0009] Figure 2 The figure is a schematic diagram of the internal structure of an artificial intelligence system for meter reading content verification according to the second embodiment of the present invention.

[0010] Figure 3 FIG. 4 is a schematic diagram of the internal structure of an artificial intelligence system for meter reading content verification according to a third embodiment of the present invention. DETAILED DESCRIPTION

[0011] The following will describe in detail an embodiment of an artificial intelligence system for meter reading content verification according to the present invention with reference to the accompanying drawings.

[0012] Figure 1 This is a schematic diagram of the internal structure of an artificial intelligence system for meter reading content verification according to a first embodiment of the present invention, wherein the system comprises: A network acquisition mechanism, used for parsing out a Hoffet neural network model, wherein the Hoffet neural network model is a Hoffet neural network after executing multiple learnings, and the number of times the Hoffet neural network is learned is monotonically positively correlated with the current use time of the gas meter; For example, the network acquisition mechanism is used to parse out a Hoffitt neural network model, wherein the Hoffitt neural network model is a Hoffitt neural network after multiple learnings are performed, and the number of times the Hoffitt neural network is learned is monotonically positively correlated with the current use time of the gas meter, including: using a numerical simulation mode to parse out a Hoffitt neural network model, wherein the Hoffitt neural network model is a Hoffitt neural network after multiple learnings are performed, and the number of times the Hoffitt neural network is learned is monotonically positively correlated with the current use time of the gas meter. The simulation and testing of the model establishment process; The meter body capture mechanism is used to obtain various setting parameters of the current gas meter, wherein the various setting parameters of the current gas meter are the maximum working pressure, maximum flow rate, minimum flow rate and volume of the installation environment of the current gas meter; The hourly detection mechanism is used to obtain the gas meter reading data corresponding to each meter reading before the current meter reading. The gas meter reading data obtained at each meter reading is the gas usage value within a preset time range before the current meter reading action; An intelligent identification device is connected to the network acquisition mechanism, the meter body capture mechanism and the hourly detection mechanism respectively, and is used to synchronously input the preset time length, the maximum working pressure, maximum flow rate, minimum flow rate and volume of the installation environment of the current gas meter, and the gas meter reading data corresponding to each meter reading before the current meter reading into the Hoffet neural network model, and execute the Hoffet neural network model to obtain the leakage mark output by the Hoffet neural network model indicating whether there is a gas leakage in the current meter reading; Among them, the preset time length, the maximum working pressure, maximum flow, minimum flow and volume of the installation environment of the current gas meter, and the gas meter reading data corresponding to each meter reading before the current meter reading of the current gas meter are synchronously input into the Hoffet neural network model, and the Hoffet neural network model is executed to obtain the leakage mark output by the Hoffet neural network model indicating whether there is a gas leakage in the current meter reading, including: the leakage mark output by the Hoffet neural network model indicating whether there is a gas leakage in the current meter reading is a binary value, and two different binary values ​​are used to represent two different results of whether there is a gas leakage in the current meter reading; Among them, obtaining each gas meter reading data corresponding to each meter reading before the current meter reading, the gas meter reading data obtained for each meter reading is the gas usage value within a preset time range before the meter reading action, including: the number of each meter reading is monotonically positively correlated with the usage time of the current gas meter; And wherein, the network acquisition mechanism is used to parse out the Hoffitt neural network model, the Hoffitt neural network model is the Hoffitt neural network after executing multiple learnings, and the number of learnings of the Hoffitt neural network is monotonically positively correlated with the usage time of the current gas meter, including: in each learning performed by the Hoffitt neural network, a leakage mark of whether there is a gas leakage in a known historical meter reading is used as the output data of the Hoffitt neural network, and a preset time length, the maximum working pressure, maximum flow, minimum flow and volume of the installation environment of the current gas meter, and each gas meter reading data corresponding to each meter reading before the historical meter reading of the current gas meter are used as the input data of the Hoffitt neural network to execute this learning of the Hoffitt neural network.

[0013] Figure 2 The figure is a schematic diagram of the internal structure of an artificial intelligence system for meter reading content verification according to the second embodiment of the present invention.

[0014] and Figure 1 different, Figure 2 The artificial intelligence system for meter reading content verification may also include the following components: The liquid crystal display mechanism is used to receive the user's input information for the intelligent identification device, the network collection mechanism, the watch body capture mechanism and the hourly detection mechanism according to the user's operation.

[0015] Figure 3 FIG. 4 is a schematic diagram of the internal structure of an artificial intelligence system for meter reading content verification according to a third embodiment of the present invention.

[0016] and Figure 1 different, Figure 3 The artificial intelligence system for meter reading content verification may also include the following components: A data analysis mechanism, arranged on the housing of the intelligent identification device, the network collection mechanism, the body capture mechanism and the hourly detection mechanism, and used to measure the instantaneous pressure currently borne by the housing of any of the intelligent identification device, the network collection mechanism, the body capture mechanism and the hourly detection mechanism; Wherein, the data analysis mechanism is arranged on the housing of the intelligent identification device, the network collection mechanism, the body capture mechanism and the hourly detection mechanism, and is used to measure the instantaneous pressure currently borne by the housing of any of the intelligent identification device, the network collection mechanism, the body capture mechanism and the hourly detection mechanism, including: the data analysis mechanism has a built-in pressure analysis device, which is used to issue a pressure alarm instruction when the received instantaneous pressure currently borne by the housing of any of the intelligent identification device, the network collection mechanism, the body capture mechanism and the hourly detection mechanism exceeds the limit; Wherein, the data analysis mechanism is arranged on the housing of the intelligent identification device, the network collection mechanism, the body capture mechanism and the hourly detection mechanism, and is used to measure the instantaneous pressure currently borne by the housing of any device of the intelligent identification device, the network collection mechanism, the body capture mechanism and the hourly detection mechanism, and further includes: the data analysis mechanism has a built-in pressure analysis device, which is used to issue a pressure safety instruction when the instantaneous pressure currently borne by the housing of each device of the intelligent identification device, the network collection mechanism, the body capture mechanism and the hourly detection mechanism is within the limit; Wherein, the data analysis mechanism is arranged on the shell of the intelligent identification device, the network collection mechanism, the watch body capture mechanism and the hourly detection mechanism, and is used to measure the instantaneous pressure currently borne by the shell of any device of the intelligent identification device, the network collection mechanism, the watch body capture mechanism and the hourly detection mechanism, and further comprises: the data analysis mechanism adopts a plurality of pressure detection units, and is used to respectively measure the instantaneous pressure currently borne by the shell of the intelligent identification device, the network collection mechanism, the watch body capture mechanism and the hourly detection mechanism; Wherein, the data analysis mechanism uses a plurality of pressure detection units for respectively measuring the instantaneous pressure currently borne by the shells of the intelligent identification device, the network collection mechanism, the body capture mechanism and the hourly detection mechanism, including: the internal structures of the plurality of pressure detection units are the same; The data analysis mechanism uses a plurality of pressure detection units for respectively measuring the instantaneous pressure currently borne by the housing of the intelligent identification device, the network collection mechanism, the body capture mechanism and the hourly detection mechanism, and further comprises: the pressure measurement upper limit value and the pressure measurement lower limit value of the plurality of pressure detection units are respectively equal; The pressure measurement upper limit values ​​and the pressure measurement lower limit values ​​of the plurality of pressure detection units being equal respectively include: the pressure measurement upper limit value is greater than the pressure measurement lower limit value; And wherein, the data analysis mechanism adopts multiple pressure detection units for respectively measuring the instantaneous pressure currently borne by the shells of the intelligent identification device, the network acquisition mechanism, the watch body capture mechanism and the hourly detection mechanism, and also includes: the multiple pressure detection units are respectively installed at the bottom position of the top of the shells of the intelligent identification device, the network acquisition mechanism, the watch body capture mechanism and the hourly detection mechanism and are located in the center of the bottom.

[0017] In addition, in the artificial intelligence system for meter reading content verification, in each learning performed by the Hoffet neural network, a leakage mark indicating whether there is a gas leakage in a known historical meter reading is used as the output data of the Hoffet neural network, and a preset time length, the maximum working pressure, maximum flow, minimum flow and volume of the installation environment of the current gas meter, and each gas meter reading data corresponding to each meter reading before the historical meter reading of the current gas meter are used as the input data of the Hoffet neural network. The execution of this learning of the Hoffet neural network includes: using the MATLAB toolbox to implement testing and simulation of each learning performed by the Hoffet neural network.

[0018] The artificial intelligence system for meter reading content verification of the present invention is used to solve the technical problem in the prior art that it is impossible to judge whether there is a gas leakage fault on the gas meter site based on the remote meter reading data of the gas meter. By using a Hoffitt neural network model with a customized structure design, it is judged whether there is a gas leakage in the current meter reading. The Hoffitt neural network model is a Hoffitt neural network after executing multiple learnings, and the number of learning times of the Hoffitt neural network is monotonically positively correlated with the current use time of the gas meter, thereby solving the above technical problem.

[0019] As many apparently widely different embodiments of the present invention can be made without departing from the spirit and scope of the present invention, it is to be understood that the invention is not limited to the specific embodiments except as defined in the appended claims.

Claims

1. An artificial intelligence system for meter reading content verification, characterized in that: The system comprises: A network acquisition mechanism, used for parsing out a Hoffet neural network model, wherein the Hoffet neural network model is a Hoffet neural network after executing multiple learnings, and the number of times the Hoffet neural network is learned is monotonically positively correlated with the current use time of the gas meter; The meter body capture mechanism is used to obtain various setting parameters of the current gas meter, wherein the various setting parameters of the current gas meter are the maximum working pressure, maximum flow rate, minimum flow rate and volume of the installation environment of the current gas meter; The hourly detection mechanism is used to obtain the gas meter reading data corresponding to each meter reading before the current meter reading. The gas meter reading data obtained at each meter reading is the gas usage value within a preset time range before the meter reading action, including: the number of each meter reading is monotonically positively correlated with the usage time of the current gas meter; The intelligent identification device is respectively connected to the network acquisition mechanism, the meter body capture mechanism and the hourly detection mechanism, and is used to synchronously input the preset time length, the maximum working pressure, maximum flow, minimum flow and volume of the installation environment of the current gas meter, and the gas meter reading data corresponding to each meter reading before the current meter reading of the current gas meter into the Hoffet neural network model, and execute the Hoffet neural network model to obtain the leakage mark output by the Hoffet neural network model indicating whether there is a gas leakage in the current meter reading, including: the leakage mark output by the Hoffet neural network model indicating whether there is a gas leakage in the current meter reading is a binary value, and two different binary values ​​are used to represent two different results of whether there is a gas leakage in the current meter reading.

2. The artificial intelligence system for meter reading content verification as claimed in claim 1, characterized in that: The network acquisition mechanism is used to parse out a Hoffet neural network model, wherein the Hoffet neural network model is a Hoffet neural network after executing multiple learnings, and the number of learnings of the Hoffet neural network is monotonically positively correlated with the usage time of the current gas meter, including: in each learning performed by the Hoffet neural network, a leakage mark of whether there is a gas leakage in a known historical meter reading is used as the output data of the Hoffet neural network, and a preset time length, the maximum working pressure, maximum flow, minimum flow and volume of the installation environment of the current gas meter, and each gas meter reading data corresponding to each meter reading before the historical meter reading of the current gas meter are used as the input data of the Hoffet neural network to execute this learning of the Hoffet neural network.

3. The artificial intelligence system for meter reading content verification as claimed in claim 2, characterized in that: The system further comprises: The liquid crystal display mechanism is used to receive the user's input information for the intelligent identification device, the network collection mechanism, the watch body capture mechanism and the hourly detection mechanism according to the user's operation.

4. The artificial intelligence system for meter reading content verification as claimed in claim 2, characterized in that: The system further comprises: The data analysis mechanism is arranged on the outer shell of the intelligent identification device, the network collection mechanism, the body capture mechanism and the hourly detection mechanism, and is used to measure the instantaneous pressure currently borne by the outer shell of any device of the intelligent identification device, the network collection mechanism, the body capture mechanism and the hourly detection mechanism.

5. The artificial intelligence system for meter reading content verification as claimed in claim 4, characterized in that: The data analysis mechanism is arranged on the shell of the intelligent identification device, the network acquisition mechanism, the body capture mechanism and the hourly detection mechanism, and is used to measure the instantaneous pressure currently borne by the shell of any device of the intelligent identification device, the network acquisition mechanism, the body capture mechanism and the hourly detection mechanism, including: the data analysis mechanism has a built-in pressure analysis device, which is used to issue a pressure alarm instruction when the received instantaneous pressure currently borne by the shell of any device of the intelligent identification device, the network acquisition mechanism, the body capture mechanism and the hourly detection mechanism exceeds the limit.

6. The artificial intelligence system for meter reading content verification as claimed in claim 5, characterized in that: The data analysis mechanism is arranged on the shell of the intelligent identification device, the network acquisition mechanism, the body capture mechanism and the hourly detection mechanism, and is used to measure the instantaneous pressure currently borne by the shell of any device of the intelligent identification device, the network acquisition mechanism, the body capture mechanism and the hourly detection mechanism. It also includes: the data analysis mechanism has a built-in pressure analysis device, which is used to issue a pressure safety instruction when the received instantaneous pressure currently borne by the shell of each device of the intelligent identification device, the network acquisition mechanism, the body capture mechanism and the hourly detection mechanism is within the limit.

7. The artificial intelligence system for meter reading content verification according to claim 6, characterized in that: The data analysis mechanism is arranged on the shell of the intelligent identification device, the network acquisition mechanism, the body capture mechanism and the hourly detection mechanism, and is used to measure the instantaneous pressure currently borne by the shell of any one of the intelligent identification device, the network acquisition mechanism, the body capture mechanism and the hourly detection mechanism. The data analysis mechanism also includes: the data analysis mechanism uses multiple pressure detection units to respectively measure the instantaneous pressure currently borne by the shell of the intelligent identification device, the network acquisition mechanism, the body capture mechanism and the hourly detection mechanism.

8. The artificial intelligence system for meter reading content verification as claimed in claim 7, characterized in that: Also includes: The data analysis mechanism uses multiple pressure detection units to respectively measure the instantaneous pressure currently borne by the shells of the intelligent identification device, the network collection mechanism, the body capture mechanism and the hourly detection mechanism, including: the internal structures of the multiple pressure detection units are the same.

9. The artificial intelligence system for meter reading content verification as claimed in claim 8, characterized in that: Also includes: The data analysis mechanism uses a plurality of pressure detection units for respectively measuring the instantaneous pressure currently borne by the housing of the intelligent identification device, the network acquisition mechanism, the body capture mechanism and the hourly detection mechanism, and further includes: the pressure measurement upper limit value and the pressure measurement lower limit value of the plurality of pressure detection units are respectively equal; The pressure measurement upper limit values ​​and the pressure measurement lower limit values ​​of the plurality of pressure detection units being equal respectively include: the pressure measurement upper limit value is greater than the pressure measurement lower limit value; Among them, the data analysis mechanism adopts multiple pressure detection units to respectively measure the instantaneous pressure currently borne by the shells of the intelligent identification device, the network acquisition mechanism, the watch body capture mechanism and the hourly detection mechanism, and also includes: the multiple pressure detection units are respectively installed at the bottom position of the top of the shells of the intelligent identification device, the network acquisition mechanism, the watch body capture mechanism and the hourly detection mechanism and are located in the center of the bottom.

Images