Acquisition and transmission system based on low power consumption LoRa-NB wireless gateway

Abstract

The invention relates to the technical field of data acquisition and processing, in particular to an acquisition and transmission system based on a low power consumption LoRa-NB wireless gateway, which comprises a sensing module, an edge operation module, a data collection module, a central processing module and a database, according to the invention, a plurality of transmission mechanisms are combined, and the system can dynamically select a transmission strategy according to the priority of data and network conditions. Under the condition that the network quality is unstable or a plurality of high-priority data packets exist, a balanced transmission mechanism can ensure that key data are transmitted preferentially and with low delay; real-time pressure and flow data abnormity sensing is carried out through an edge operation module, through real-time monitoring of all preset positions, pressure and flow abnormity conditions are accurately judged and marked, and early warning is triggered in time; further feature extraction and calculation are completed through the central processing module, and distribution features of pressure and flow data are deeply analyzed.

Description

Technical Field

[0001] The present invention relates to the technical field of data acquisition and processing, and in particular to an acquisition and transmission system based on a low-power consumption LoRa-NB wireless gateway. Background Art

[0002] LoRa (Low Power Wide Area Network) is a low power wide area network technology, which is mainly used to achieve low power wireless data transmission. In the LoRa+NB-IoT acquisition and transmission system, LoRa technology is used in low power wireless pressure transmitters to collect wellhead oil pressure, casing pressure, annular pressure and other data, and transmit these data wirelessly to the LoRa-NB wireless gateway in the station. With its low power consumption and wide coverage, LoRa technology enables the system to transmit data over a long distance while ensuring long-term operation of the equipment.

[0003] NB-IoT (Narrow Bandwidth Internet of Things) is an IoT technology based on cellular communication networks. It is specially designed to connect various IoT devices such as sensors, meters and trackers to achieve remote monitoring, data transmission and intelligent control.

[0004] However, the existing oilfield data transmission system still has many shortcomings. First, the traditional oilfield data transmission system usually relies on a single communication method and may face problems such as unstable signals, data loss or delays. Especially in areas far away from base stations or with poor signals, the real-time transmission and high reliability of key data cannot be guaranteed.

[0005] Secondly, the existing oilfield data transmission system often transmits all data directly to the central processing module for analysis, which can easily lead to network congestion and increase transmission delays when the data volume is large. At the same time, data analysis mainly relies on central servers and lacks real-time local processing capabilities, resulting in slow anomaly detection and early warning responses.

[0006] In view of the above problems, it is necessary to propose a collection and transmission system based on low-power LoRa-NB wireless gateway. Summary of the invention

[0007] The purpose of the present invention is to solve the problems existing in the background technology and to propose a collection and transmission system based on a low-power LoRa-NB wireless gateway.

[0008] The purpose of the present invention can be achieved through the following technical solutions: The data collection and transmission system based on the low-power LoRa-NB wireless gateway includes a perception module, an edge computing module, a data collection module, a central processing module and a database.

[0009] The sensing module obtains the pressure P and flow Q of the preset position through the sensor group at every preset time interval t. The preset positions include: collection wellhead, oil production pipeline, distribution station pipeline, oil storage tank, water distribution station, water injection network, water injection well, oil and gas separator, pump station and key liquid level monitoring point.

[0010] Generate time series data for each preset position, including pressure data and traffic data . Where i is the number of the preset position, and i=1, 2, 3, ..., n; where t is the time mark.

[0011] Each perception module transmits the collected pressure data and flow data to the edge computing module.

[0012] The edge computing module performs filtering, noise reduction and abnormal perception operations on the pressure data and flow data sent by the perception module.

[0013] The filtering and noise reduction operation is specifically as follows: Every preset statistical period T, the moving equalization filter is used to perform time window equalization on the continuously collected pressure data and flow data. The moving equalization filter formula is: Where w is the time sequence number, is the pressure data within the time window, It is the traffic data within the time window. and They are respectively the pressure and flow data obtained after filtering calculation.

[0014] The abnormality perception operation is specifically as follows: By formula Calculate the first moment of pressure data and the first moment of flow data ; By formula Calculate the second moment of pressure data and the second moment of flow data .

[0015] Get the condition that satisfies: the distance between the value and the first-order moment is greater than one times the second-order moment, that is, the condition is satisfied Pressure monitoring data The number is recorded as the first-level abnormal point count value U1; Get the condition that satisfies: The distance between the value and the first-order moment is greater than twice the second-order moment, that is, the condition is satisfied Pressure monitoring data The number is recorded as the secondary abnormal point count value U2; As a preferred method of the present invention, the condition is satisfied: the distance between the value and the first-order moment is greater than three times the second-order moment, that is, the condition is satisfied. Pressure monitoring data The number is recorded as the third-level abnormal point count value U3; By formula Calculate the pressure anomaly index at the preset position i within the statistical period T , where K1, K2 and K3 are preset weight factors.

[0016] Get the condition that satisfies: the distance between the value and the first-order moment is greater than one times the second-order moment, that is, the condition is satisfied Traffic monitoring data The number is recorded as the first-level abnormal point count value V1; Get the condition that satisfies: The distance between the value and the first-order moment is greater than twice the second-order moment, that is, the condition is satisfied Traffic monitoring data The number is recorded as the secondary abnormal point count value V2; As a preferred method of the present invention, the condition is satisfied: the distance between the value and the first-order moment is greater than three times the second-order moment, that is, the condition is satisfied. Traffic monitoring data The number is recorded as the third-level abnormal point count value V3; By formula Calculate the traffic anomaly index of the preset location i within the statistical period T , where K1, K2 and K3 are preset weight factors.

[0017] At every preset statistical period T, the calculation is performed on all the number symbols i to obtain the pressure anomaly index and flow anomaly index of all preset positions.

[0018] A warning index Ai(T) with an initial value of 0 is preset for each preset position i.

[0019] When the pressure abnormality index of a preset position i is detected within a monitoring period T, When it is greater than the preset threshold δMax, the warning index Ai (T) is increased by a reference value d; When the flow anomaly index of a preset location i is detected within a monitoring period T, When it is greater than the preset threshold δMax, the warning index Ai (T) is increased by a reference value d; After each monitoring period T, the warning index Ai(T) of each preset position i is decayed at a preset decay rate β, that is, Among them, Count1 is the over-limit count value of the pressure criterion; Count2 is the over-limit count value of the flow criterion; As a preferred embodiment of the present invention, the warning index Ai(T) is converted into a priority label of the pressure data and flow data of each preset position i within the statistical period T.

[0020] Specifically, the data with a larger warning index Ai (T) has a higher transmission priority.

[0021] The data collection module assigns priorities to different pressure data and flow data according to the size of the warning index Ai (T). , the calculation formula is: .

[0022] As a preferred embodiment of the present invention, according to the allocation priority The data packets with priority greater than the preset threshold are allocated with QoS1 mechanism to perform data transmission tasks; the data packets with priority less than the preset threshold are allocated with QoS2 mechanism to perform data transmission tasks; if there are multiple data packets with high allocation priority at the same time, the condition is met: there are m allocation priorities with preset position number i at the same time When m is greater than the preset threshold and m is greater than the preset threshold imax, a balanced transmission mechanism is used to ensure low-latency transmission of high-priority data.

[0023] The QoS1 mechanism uses the cellular network structure of NB-IoT to establish a network connection with the central processing module. The transmission strategy is at least one transmission to ensure the successful transmission of data packets of flow data and pressure data, and to quickly report abnormal flow data and pressure data.

[0024] The QoS2 mechanism uses the LoRaWAN protocol to connect to the central processing module over a wide area network, and the transmission strategy is exactly once transmission to ensure the complete transmission of data packets for flow data and pressure data.

[0025] The balanced transmission mechanism is specifically: through transmission quality detection, transmission quality evaluation and dynamic mechanism adjustment are performed on QoS1 and QoS2. The specific process is as follows: Data packets with a priority greater than a preset threshold are assigned a QoS1 mechanism to perform data transmission tasks; data packets with a priority less than a preset threshold are assigned a QoS2 mechanism to perform data transmission tasks; As a preferred method of the present invention, the maximum allocation priority is obtained. The number symbol i; Get the signal strength w11 of the NB-IoT network at node i. Get the overall packet loss rate w12 and network delay w13 of the NB-IoT network.

[0026] By formula Calculate the transmission quality parameter η1 of the NB-IoT network, where λ1, λ2 and λ3 are preset weight factors.

[0027] Get the signal strength w21 of the LoRaWAN network at node i. Get the overall packet loss rate W22 and network delay W23 of the LoRaWAN network.

[0028] By formula Calculate the transmission quality parameter η2 of the LoRaWAN network, where λ1, λ2 and λ3 are preset weight factors.

[0029] The transmission balancing coefficient r is calculated by the formula r=η1 / η2. When the transmission balancing coefficient is greater than the preset threshold, the data transmission task with the transmission mechanism QoS1 is switched to the mechanism QoS2; when the transmission balancing coefficient is less than or equal to the preset threshold, the data transmission task with the transmission mechanism QoS2 is switched to the mechanism QoS1; The central processing module saves the pressure data, flow data, first-order moment and second-order moment of pressure data of each preset position i, and first-order moment and second-order moment of flow data of each preset position i sent through the QoS1 mechanism, QoS2 mechanism and balanced transmission mechanism. Generate a pressure-time graph and flow-time graph every preset statistical period T. Obtain the function expression of the pressure-time graph of each preset position i in the statistical period T =fi(t); obtain the function expression of the flow-time diagram of each preset position i within the statistical period T =gi(t); and output the pressure-time diagram and flow-time diagram to the database.

[0030] As a preferred embodiment of the present invention, the function expression of the pressure-time diagram of each preset position i within the statistical period T is: = fi(t) and the functional expression of the flow-time diagram =gi(t) for feature extraction, specifically: By formula

[0031] Calculate the third moment of pressure data and the third moment of the flow data .in is the first moment of the pressure data, is the first moment of the flow data.

[0032] By formula Calculate the fourth moment of pressure data and the fourth moment of the flow data .in is the first moment of the pressure data, is the first moment of the flow data.

[0033] Every preset statistical period T, record the first-order moment of the pressure data at each preset position i , second-order moment of pressure data , pressure data third moment And the fourth moment of pressure data , generate the pressure data feature vector of each preset position .

[0034] Every preset statistical period T, record the first-order moment of the flow data at each preset location i , the second moment of flow data , the third moment of flow data and the fourth moment of flow data , generate the traffic data feature vector of each preset location .

[0035] As a preferred embodiment of the present invention, whenever the change value of an element in the pressure data feature vector or the flow rate feature vector compared with the corresponding element in the previous statistical period exceeds a preset threshold, the element is marked as abnormal data.

[0036] The elements include the first-order moment of pressure data, the second-order moment of pressure data, the third-order moment of pressure data, the fourth-order moment of pressure data, the first-order moment of flow data, the second-order moment of flow data, the third-order moment of flow data and the fourth-order moment of flow data.

[0037] The database stores all pressure-time graphs, flow-time graphs, and pressure data feature vectors sent by the central processing module. and traffic data feature vector .

[0038] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention combines multiple transmission mechanisms. The system can dynamically select transmission strategies based on data priority and network conditions. When the network quality is unstable or there are multiple high-priority data packets, the balanced transmission mechanism can ensure that key data is transmitted with priority and low latency, improving the reliability and real-time performance of the data. This mechanism greatly reduces the problem of data loss or delay, ensures that important monitoring data is reported in a timely and accurate manner, and improves the reliability and efficiency of data transmission; 2. The present invention uses the edge computing module to perform real-time abnormal perception of pressure and flow data, calculates the abnormal index using the first-order moment and the second-order moment, and generates an early warning index according to the preset threshold. Through real-time monitoring of each preset position, it can accurately judge and mark the abnormal conditions of pressure and flow, trigger early warnings in time, help identify potential fault points in time and take countermeasures, and ensure the safety and stability of system operation.

[0039] 3. Through feature extraction and moment calculation (including third-order moment and fourth-order moment), the system can deeply analyze the distribution characteristics of pressure and flow data, reflecting the symmetry and sharpness of the data. These feature information provides rich data support for subsequent data analysis, trend prediction and fault diagnosis, and can effectively support the long-term stable operation of the system and accurate decision-making. At the same time, the historical data and feature vectors stored in the database also provide strong support for subsequent data mining and pattern recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings: Figure 1 is a system block diagram of the present invention; DETAILED DESCRIPTION The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] See also Figure 1 As shown, the data collection and transmission system based on the low-power LoRa-NB wireless gateway includes a perception module, an edge computing module, a data collection module, a central processing module and a database.

[0042] The sensing module obtains the pressure P and flow Q of the preset position through the sensor group at every preset time interval t. The preset positions include: collection wellhead, oil production pipeline, distribution station pipeline, oil storage tank, water distribution station, water injection network, water injection well, oil and gas separator, pump station and key liquid level monitoring point.

[0043] Generate time series data for each preset position, including pressure data and traffic data . Where i is the number of the preset position, and i=1, 2, 3, ..., n; where t is the time mark.

[0044] Each perception module transmits the collected pressure data and flow data to the edge computing module.

[0045] The edge computing module performs filtering, noise reduction and abnormal perception operations on the pressure data and flow data sent by the perception module.

[0046] The filtering and noise reduction operation is specifically as follows: Every preset statistical period T, the moving equalization filter is used to perform time window equalization on the continuously collected pressure data and flow data. The moving equalization filter formula is: Where w is the time sequence number, is the pressure data within the time window, It is the traffic data within the time window. and They are respectively the pressure and flow data obtained after filtering calculation.

[0047] The abnormality perception operation is specifically as follows: By formula Calculate the first moment of pressure data and the first moment of flow data ; By formula Calculate the second moment of pressure data and the second moment of flow data .

[0048] Get the condition that satisfies: the distance between the value and the first-order moment is greater than one times the second-order moment, that is, the condition is satisfied Pressure monitoring data The number is recorded as the first-level abnormal point count value U1; Get the condition that satisfies: The distance between the value and the first-order moment is greater than twice the second-order moment, that is, the condition is satisfied Pressure monitoring data The number is recorded as the secondary abnormal point count value U2; Furthermore, the condition is satisfied: the distance between the value and the first-order moment is greater than three times the second-order moment, that is, the condition is satisfied Pressure monitoring data The number is recorded as the third-level abnormal point count value U3; By formula Calculate the pressure anomaly index at the preset position i within the statistical period T , where K1, K2 and K3 are preset weight factors.

[0049] Get the condition that satisfies: the distance between the value and the first-order moment is greater than one times the second-order moment, that is, the condition is satisfied Traffic monitoring data The number is recorded as the first-level abnormal point count value V1; Get the condition that satisfies: The distance between the value and the first-order moment is greater than twice the second-order moment, that is, the condition is satisfied Traffic monitoring data The number is recorded as the secondary abnormal point count value V2; Furthermore, the condition is satisfied: the distance between the value and the first-order moment is greater than three times the second-order moment, that is, the condition is satisfied Traffic monitoring data The number is recorded as the third-level abnormal point count value V3; By formula Calculate the traffic anomaly index of the preset location i within the statistical period T , where K1, K2 and K3 are preset weight factors.

[0050] At every preset statistical period T, the calculation is performed on all the number symbols i to obtain the pressure anomaly index and flow anomaly index of all preset positions.

[0051] A warning index Ai(T) with an initial value of 0 is preset for each preset position i.

[0052] When the pressure abnormality index of a preset position i is detected within a monitoring period T, When it is greater than the preset threshold δMax, the warning index Ai (T) is increased by a reference value d; When the flow anomaly index of a preset location i is detected within a monitoring period T, When it is greater than the preset threshold δMax, the warning index Ai (T) is increased by a reference value d; After each monitoring period T, the warning index Ai(T) of each preset position i is decayed at a preset decay rate β, that is, Among them, Count1 is the over-limit count value of the pressure criterion; Count2 is the over-limit count value of the flow criterion; Furthermore, the warning index Ai(T) is converted into a priority label of the pressure data and flow data of each preset position i within the statistical period T.

[0053] Specifically, the data with a larger warning index Ai (T) has a higher transmission priority.

[0054] The data collection module assigns priorities to different pressure data and flow data according to the size of the warning index Ai (T). , the calculation formula is: .

[0055] Furthermore, according to the allocation priority The data packets with priority greater than the preset threshold are allocated with QoS1 mechanism to perform data transmission tasks; the data packets with priority less than the preset threshold are allocated with QoS2 mechanism to perform data transmission tasks; if there are multiple data packets with high allocation priority at the same time, the condition is met: there are m allocation priorities with preset position number i at the same time When m is greater than the preset threshold and m is greater than the preset threshold imax, a balanced transmission mechanism is used to ensure low-latency transmission of high-priority data.

[0056] The QoS1 mechanism uses the cellular network structure of NB-IoT to establish a network connection with the central processing module. The transmission strategy is at least one transmission to ensure the successful transmission of data packets of flow data and pressure data, and to quickly report abnormal flow data and pressure data.

[0057] The QoS2 mechanism uses the LoRaWAN protocol to connect to the central processing module over a wide area network, and the transmission strategy is exactly once transmission to ensure the complete transmission of data packets for flow data and pressure data.

[0058] The balanced transmission mechanism is specifically: through transmission quality detection, transmission quality evaluation and dynamic mechanism adjustment are performed on QoS1 and QoS2. The specific process is as follows: Data packets with a priority greater than a preset threshold are assigned a QoS1 mechanism to perform data transmission tasks; data packets with a priority less than a preset threshold are assigned a QoS2 mechanism to perform data transmission tasks; Furthermore, get the maximum allocation priority The number symbol i; Get the signal strength w11 of the NB-IoT network at node i. Get the overall packet loss rate w12 and network delay w13 of the NB-IoT network.

[0059] By formula Calculate the transmission quality parameter η1 of the NB-IoT network, where λ1, λ2 and λ3 are preset weight factors.

[0060] Get the signal strength w21 of the LoRaWAN network at node i. Get the overall packet loss rate W22 and network delay W23 of the LoRaWAN network.

[0061] By formula Calculate the transmission quality parameter η2 of the LoRaWAN network, where λ1, λ2 and λ3 are preset weight factors.

[0062] The transmission balancing coefficient r is calculated by the formula r=η1 / η2. When the transmission balancing coefficient is greater than the preset threshold, the data transmission task with the transmission mechanism QoS1 is switched to the mechanism QoS2; when the transmission balancing coefficient is less than or equal to the preset threshold, the data transmission task with the transmission mechanism QoS2 is switched to the mechanism QoS1; The central processing module saves the pressure data, flow data, first-order moment and second-order moment of pressure data of each preset position i, and first-order moment and second-order moment of flow data of each preset position i sent through the QoS1 mechanism, QoS2 mechanism and balanced transmission mechanism. Generate a pressure-time graph and flow-time graph every preset statistical period T. Obtain the function expression of the pressure-time graph of each preset position i in the statistical period T =fi(t); obtain the function expression of the flow-time diagram of each preset position i within the statistical period T =gi(t); and output the pressure-time diagram and flow-time diagram to the database.

[0063] Furthermore, the function expression of the pressure-time diagram of each preset position i within the statistical period T is: = fi(t) and the functional expression of the flow-time diagram =gi(t) for feature extraction, specifically: By formula

[0064] Calculate the third moment of pressure data and the third moment of the flow data .in is the first moment of the pressure data, is the first moment of the flow data.

[0065] It should be noted that the third-order moment of pressure data and flow data reflects the symmetry of data distribution. If the third-order moment is zero, it means that the data distribution is symmetrical; if the third-order moment is positive, it means that the data distribution is biased to the right; conversely, if the third-order moment is negative, it means that the data is biased to the left.

[0066] By formula Calculate the fourth moment of pressure data and the fourth moment of the flow data .in is the first moment of the pressure data, is the first moment of the flow data.

[0067] It should be noted that the fourth-order moment of pressure data and flow data reflects the sharpness of data distribution. If the fourth-order moment is large, it means that the data distribution has a large peak, that is, there are more extreme values ​​of the data; if the fourth-order moment is small, it means that the data distribution is relatively flat and there is no obvious peak.

[0068] Every preset statistical period T, record the first-order moment of the pressure data at each preset position i , second-order moment of pressure data , pressure data third moment And the fourth moment of pressure data , generate the pressure data feature vector of each preset position .

[0069] Every preset statistical period T, record the first-order moment of the flow data at each preset location i , the second moment of flow data , the third moment of flow data and the fourth moment of flow data , generate the traffic data feature vector of each preset location .

[0070] Furthermore, whenever the change value of a certain element in the pressure data feature vector or the flow rate feature vector compared with the corresponding element in the previous statistical period exceeds a preset threshold, the element is marked as abnormal data.

[0071] The elements include the first-order moment of pressure data, the second-order moment of pressure data, the third-order moment of pressure data, the fourth-order moment of pressure data, the first-order moment of flow data, the second-order moment of flow data, the third-order moment of flow data and the fourth-order moment of flow data.

[0072] The database stores all pressure-time graphs, flow-time graphs, and pressure data feature vectors sent by the central processing module. and traffic data feature vector .

[0073] It should be understood that the terms “include” and “comprising” used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0074] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and the claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and the claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations; The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. The data collection and transmission system based on the low-power LoRa-NB wireless gateway includes an edge computing module and a data collection module, which is characterized by: The edge computing module performs filtering, noise reduction and anomaly sensing operations on the pressure data and flow data sent by the perception module, and calculates the first-level anomaly point count value, the second-level anomaly point count value and the third-level anomaly point count value according to the anomaly sensing operation results. The pressure anomaly index and flow anomaly index are obtained by data fusion of the first-level, second-level and third-level anomaly point count values; Every preset statistical period T, the calculation is traversed over all number symbols i to obtain the pressure abnormality index and flow abnormality index of all preset positions; a warning index with an initial value of 0 is preset for each preset position i, and the warning index is dynamically adjusted through the pressure abnormality index, flow abnormality index and attenuation rate; Convert the warning index into the priority label of the pressure data and flow data of each preset position i within the statistical period T; The data collection module assigns priorities to the transmission tasks of different pressure data and flow data according to the size of the warning index. The data packets with a priority greater than the preset threshold are preferentially assigned the QoS1 mechanism to perform the data transmission task; the data packets with a priority less than the preset threshold are assigned the QoS2 mechanism to perform the data transmission task; If there are multiple data packets with high allocation priority at the same time, that is, the condition is met: when there are m preset position number symbols i with allocation priorities greater than the preset threshold and m is greater than the preset threshold imax, a balanced transmission mechanism is used to ensure low-latency transmission of high-priority data.

2. The acquisition and transmission system based on the low-power consumption LoRa-NB wireless gateway according to claim 1 is characterized in that: It also includes a perception module, a central processing module and a database; The sensing module obtains the pressure P and flow Q of the preset position through the sensor group at every preset time interval t. The preset positions include: collection wellhead, oil production pipeline, distribution station pipeline, oil storage tank, water distribution station, water injection network, water injection well, oil and gas separator, pump station and key liquid level monitoring point; Generate time series data for each preset position, including pressure data and traffic data ; Where i is the number of the preset position, and i=1, 2, 3, ..., n; Where t is the time mark; Each sensing module transmits the collected pressure data and flow data to the edge computing module; The central processing module saves the pressure data, flow data, first-order moment and second-order moment of pressure data of each preset position i, and first-order moment and second-order moment of flow data of each preset position i sent through the QoS1 mechanism, QoS2 mechanism and balanced transmission mechanism; generates a pressure-time graph and a flow-time graph every preset statistical period T; obtains the function expression of the pressure-time graph of each preset position i within the statistical period T =fi(t); obtain the function expression of the flow-time diagram of each preset position i within the statistical period T =gi(t); and output the pressure-time diagram and flow-time diagram to the database; Perform feature extraction on the function expression of the pressure-time diagram and the function expression of the flow-time diagram at each preset position i within the statistical period T, obtain the third-order moment of pressure data, the fourth-order moment of pressure data, the third-order moment of flow data and the fourth-order moment of flow data, and generate a pressure data feature vector and a flow feature vector; Whenever the change value of an element in the pressure data feature vector or flow feature vector compared with the corresponding element in the previous statistical period exceeds a preset threshold, the element is marked as abnormal data; The elements include the first-order moment of pressure data, the second-order moment of pressure data, the third-order moment of pressure data, the fourth-order moment of pressure data, the first-order moment of flow data, the second-order moment of flow data, the third-order moment of flow data and the fourth-order moment of flow data; The database stores all pressure-time graphs, flow-time graphs, and pressure data feature vectors sent by the central processing module. and traffic data feature vector .

3. The acquisition and transmission system based on the low-power LoRa-NB wireless gateway according to claim 1 is characterized in that: The filtering and noise reduction operation is specifically as follows: Every preset statistical period T, the moving equalization filter is used to perform time window equalization on the continuously collected pressure data and flow data. The moving equalization filter formula is: Where w is the time sequence number, is the pressure data within the time window, is the traffic data within the time window; and They are respectively the pressure and flow data obtained after filtering calculation.

4. The acquisition and transmission system based on the low-power LoRa-NB wireless gateway according to claim 1 is characterized in that: The abnormality perception operation is specifically as follows: By formula Calculate the first moment of pressure data and the first moment of flow data ; By formula Calculate the second moment of pressure data and the second moment of flow data .

5. The acquisition and transmission system based on the low-power consumption LoRa-NB wireless gateway according to claim 1 or 4, characterized in that: The specific process of calculating the abnormal point count value and obtaining the pressure abnormality index and flow abnormality index by data fusion of the abnormal point count value is as follows: Get the condition that satisfies: the distance between the value and the first-order moment is greater than one times the second-order moment, that is, the condition is satisfied Pressure monitoring data The number is recorded as the first-level abnormal point count value U1; Get the condition that satisfies: The distance between the value and the first-order moment is greater than twice the second-order moment, that is, the condition is satisfied Pressure monitoring data The number is recorded as the secondary abnormal point count value U2; Get the condition that satisfies: The distance between the value and the first-order moment is greater than three times the second-order moment, that is, the condition is satisfied Pressure monitoring data The number is recorded as the third-level abnormal point count value U3; By formula Calculate the pressure anomaly index at the preset position i within the statistical period T , where K1, K2 and K3 are preset weight factors; Get the condition that satisfies: the distance between the value and the first-order moment is greater than one times the second-order moment, that is, the condition is satisfied Traffic monitoring data The number is recorded as the first-level abnormal point count value V1; Get the condition that satisfies: The distance between the value and the first-order moment is greater than twice the second-order moment, that is, the condition is satisfied Traffic monitoring data The number is recorded as the secondary abnormal point count value V2; Get the condition that satisfies: The distance between the value and the first-order moment is greater than three times the second-order moment, that is, the condition is satisfied Traffic monitoring data The number is recorded as the third-level abnormal point count value V3; By formula Calculate the traffic anomaly index of the preset location i within the statistical period T , where K1, K2 and K3 are preset weight factors.

6. The acquisition and transmission system based on the low-power consumption LoRa-NB wireless gateway according to claim 5 is characterized in that: The specific process of dynamically adjusting the warning index through the pressure abnormality index and flow abnormality index is as follows: When the pressure abnormality index of a preset position i is detected within a monitoring period T, When it is greater than the preset threshold δMax, the warning index Ai (T) is increased by a reference value d; When the flow anomaly index of a preset location i is detected within a monitoring period T, When it is greater than the preset threshold δMax, the warning index Ai (T) is increased by a reference value d; After each monitoring period T, the warning index Ai(T) of each preset position i is decayed at a preset decay rate β, that is, Count1 is the pressure criterion over-limit count value; Count2 is the flow criterion over-limit count value.

7. The acquisition and transmission system based on the low-power LoRa-NB wireless gateway according to claim 1 is characterized in that: The QoS1 mechanism is specifically: The cellular network structure of NB-IoT is used to connect to the central processing module. The transmission strategy is to transmit at least once to ensure the successful transmission of data packets of flow data and pressure data, and to quickly report abnormal flow data and pressure data.

8. The acquisition and transmission system based on the low-power consumption LoRa-NB wireless gateway according to claim 1 is characterized in that: The QoS2 mechanism is specifically: The LoRaWAN protocol is used to connect to the central processing module for a wide area network, and the transmission strategy is exactly once transmission to ensure the complete transmission of data packets for flow data and pressure data.

9. The acquisition and transmission system based on the low-power LoRa-NB wireless gateway according to claim 1, characterized in that: The balanced transmission mechanism is specifically as follows: Through transmission quality detection, QoS1 and QoS2 are evaluated for transmission quality and dynamically adjusted. Packets with a priority greater than a preset threshold are assigned to use the QoS1 mechanism to perform data transmission tasks; packets with a priority less than a preset threshold are assigned to use the QoS2 mechanism to perform data transmission tasks. At the same time, get the highest allocation priority The number symbol i; Get the signal strength w11 of the NB-IoT network at node i; get the overall packet loss rate w12 and network delay w13 of the NB-IoT network; By formula Calculate the transmission quality parameter η1 of the NB-IoT network, where λ1, λ2 and λ3 are preset weight factors; Get the signal strength w21 of the LoRaWAN network at node i; Get the overall packet loss rate W22 and network delay W23 of the LoRaWAN network; By formula Calculate the transmission quality parameter η2 of the LoRaWAN network, where λ1, λ2 and λ3 are preset weight factors; The transmission balancing coefficient r is calculated by the formula r=η1 / η2. When the transmission balancing coefficient is greater than the preset threshold, the data transmission task with the transmission mechanism QoS1 is switched to the mechanism QoS2; when the transmission balancing coefficient is less than or equal to the preset threshold, the data transmission task with the transmission mechanism QoS2 is switched to the mechanism QoS1.

10. The acquisition and transmission system based on low-power consumption LoRa-NB wireless gateway according to claim 1, characterized in that: The specific process of feature extraction for the function expression of the pressure-time graph and the function expression of the flow-time graph is as follows: By formula Calculate the third moment of pressure data and the third moment of the flow data ;in is the first moment of the pressure data, is the first moment of the flow data; By formula Calculate the fourth moment of pressure data and the fourth moment of the flow data ;in is the first moment of the pressure data, is the first moment of the flow data; Every preset statistical period T, record the first-order moment of the pressure data at each preset position i , second-order moment of pressure data , third-order moment of pressure data And the fourth moment of pressure data , generate the pressure data feature vector of each preset position ; Every preset statistical period T, record the first-order moment of the flow data at each preset location i , the second moment of flow data , the third moment of flow data and the fourth moment of flow data , generate the traffic data feature vector of each preset location .

Images