Data collection, monitoring and early warning method for smart water pipe network

Abstract

The present invention discloses a data collection, monitoring and early warning method for a smart water pipe network, and relates to the field of smart pipe networks. The technical solution of the present invention constructs a topological structure of a water pipe network, obtains real-time sensor data and historical sensor data of periodic pipe network data at a data collection node in the structure, and determines the operating state of the sensor device at the data collection node according to the acquired sensor data. When it is determined that the operating state of the sensor device at the data collection node at the current moment is abnormal, the data collection node coordinates are obtained, and an abnormal device alarm signal is generated. When the operating state of the sensor device is determined to be normal, the data state of the acquired real-time sensor data is further determined, and when the real-time sensor data is determined to be abnormal, a data abnormality alarm signal is generated, which can solve the problem of inaccurate monitoring of the operating state of the urban water supply and drainage system due to failure of the sensor device during the monitoring process of the water pipe network.

Description

Technical Field

[0001] The present invention relates to the field of smart pipe networks, and in particular to a data collection, monitoring and early warning method for smart water pipe networks. Background Art

[0002] Smart water management is a transformation of the water industry by information technology, which enables water management to operate in a more intelligent way. Through online monitoring equipment such as data acquisition instruments, wireless networks, water quality and water pressure meters, the operating status of urban water supply and drainage systems can be perceived in real time, and water management departments and water supply and drainage facilities can be organically integrated in a visual way to form an "urban water Internet of Things". Massive water information can be analyzed and processed in a timely manner, and corresponding processing results can be made to assist decision-making suggestions, so as to manage the entire production, management and service process of the water system in a more refined and dynamic way, thus achieving a "smart" state. The core and foundation of smart water management is pipe network data. By embedding advanced sensor technology and Internet of Things technology into each link of the water business system, data collection is completed, and the water business system is fully digitized through network transmission. By utilizing the inherent collaborative operation relationship of each link of the water system, each business unit can be more integrated and operated efficiently, realizing the collaborative operation of the water system at different levels such as data, business process, decision information, and portal.

[0003] At present, the pipe network data in the smart water system is mostly collected through the perception layer equipment, such as installing corresponding sensor equipment at the pipe network connection node or in the pipe network. The complexity of the internal environment of the pipe network leads to the inevitable environmental interference and physical damage during operation, which increases the possibility of its failure, making the collected data inconsistent with the actual situation. The pipe network data collected by the failed sensor cannot effectively monitor the operation status of the urban water supply and drainage system. To this end, we propose a data collection, monitoring and early warning method for the smart water pipe network. Summary of the invention

[0004] The main purpose of the present invention is to provide a data collection, monitoring and early warning method for a smart water pipe network, which can effectively solve the problems in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] The data collection, monitoring and early warning methods of the smart water pipe network include:

[0007] Constructing a topological structure of a water pipe network, acquiring real-time sensor data and historical sensor data of periodic pipe network data at data collection nodes in the structure, wherein the pipe network data includes at least one of water pressure, water flow velocity, water temperature, pH value, turbidity, instantaneous flow rate, and dissolved oxygen content at the data collection nodes;

[0008] The operating state of the sensor device at the data collection node is determined according to the acquired sensor data, and the determination method includes the following steps:

[0009] S21: Acquire periodic real-time sensing data and historical sensing data of the i-th type of sensing device;

[0010] S22: Construct a change curve of the historical sensor data of the i-th type of sensor equipment in the k-th operation cycle, recorded as: , where d ikt It is represented as the real-time sensor data collected by the i-th type of sensor equipment at time t in the k-th operation cycle;

[0011] S23: Calculate the maximum difference of the historical sensor data change curve within k operation cycles according to the formula , the calculation formula is:

[0012] ,

[0013] In the formula, max{} means taking the maximum value in the brackets; q, p are both ∈ k, and q≠p; T is the amount of data collected;

[0014] S24: Construct a curve of the change of the real-time sensing data of the i-th type of sensing device in a complete cycle, recorded as: , where d it It is represented as the real-time sensor data collected by the i-th sensor device at time t;

[0015] S25: Calculate the maximum difference between the change curve of real-time sensor data and the change curve of historical sensor data according to the formula , the calculation formula is:

[0016] ;

[0017] S26: The maximum difference of the change curve and The quantitative relationship between them is used as the basis to determine the operating status of the sensor equipment, specifically:

[0018] like ≤ , then the operating state of the sensor device is determined to be abnormal;

[0019] like > , then the operating status of the sensor device is determined to be normal;

[0020] When it is determined that the operating state of the sensor device at the data collection node at the current moment is abnormal, the coordinates of the data collection node are obtained and an alarm is issued;

[0021] When it is determined that the operating state of the sensor device at the data collection node at the current moment is normal, the data state of the acquired real-time sensor data is determined, and when it is determined that the real-time sensor data is abnormal data, an alarm is issued. The data state determination method includes the following steps:

[0022] S31: Acquire real-time sensor data of the i-th sensor device;

[0023] S32: Build a prediction model based on the acquired real-time sensor data. The expression of the model is:

[0024] ,

[0025] In the formula, It is represented as the predicted value of the real-time sensor data of the i-th sensor device at the λ-th sampling period, It is represented as the real-time sensor data sampling value of the i-th sensor device at the λ-1-th sampling period, a is a constant coefficient, and a∈(0,1), φ∈λ and φ<λ;

[0026] S33: Obtain the predicted value and sampled value of the real-time sensor data of the i-th sensor device in the λ-th sampling period Based on the quantitative relationship between them, the data state of the real-time sensor data sampling value of the sensor device is determined, specifically:

[0027] like ∈[ -∆s, +∆s], then determine the real-time sensor data sampling value The data status is normal;

[0028] like > +∆s or < -∆s, then determine the real-time sensor data sampling value The data status is abnormal;

[0029] Where ∆s is the fluctuation coefficient, and ∆s>0. The fluctuation coefficient ∆s is determined according to the following formula: .

[0030] The data collection, monitoring and early warning system of the smart water pipe network includes a pipe network structure acquisition module, a pipe network data collection module, a sensor equipment status determination module, a pipe network data status determination module, and an abnormal alarm module;

[0031] The pipe network structure acquisition module constructs the topological structure of the water pipe network based on BIM technology, and uses GIS technology to mark each node in the water pipe network to obtain the positioning coordinates of the data collection node to be measured;

[0032] The pipe network data acquisition module is used to collect real-time sensor data and historical sensor data of periodic pipe network data at data acquisition nodes in the water pipe network topology structure, wherein the pipe network data includes at least one of water pressure, water flow velocity, water temperature, pH value, turbidity, instantaneous flow rate, and dissolved oxygen content at the data acquisition node;

[0033] The sensor device state determination module is used to determine the operating state of the sensor device at the data collection node according to the acquired sensor data, and generate a device abnormality alarm signal when the operating state of the sensor device is determined to be abnormal;

[0034] The pipe network data status determination module is used to determine the data status of the acquired real-time sensor data when the operating status of the sensor equipment at the collection node is normal, and to generate a data abnormality alarm signal when the real-time sensor data is determined to be abnormal data;

[0035] In response to the equipment abnormality alarm signal generated by the sensor equipment state determination module and the data abnormality alarm signal generated by the pipe network data state determination module, the abnormality alarm module issues an abnormality alarm;

[0036] The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0037] The present invention has the following beneficial effects:

[0038] Compared with the prior art, the technical solution of the present invention constructs a topological structure of a water pipe network, obtains real-time sensor data and historical sensor data of periodic pipe network data at data acquisition nodes in the structure, and determines the operating status of the sensor equipment at the data acquisition node based on the acquired sensor data. When it is determined that the operating status of the sensor equipment at the data acquisition node at the current moment is abnormal, the data acquisition node coordinates are obtained, and an equipment abnormality alarm signal is generated. When it is determined that the operating status of the sensor equipment is normal, the data status of the acquired real-time sensor data is further determined, and when the real-time sensor data is determined to be abnormal, a data abnormality alarm signal is generated. This can effectively solve the problem of inaccurate monitoring of the operating status of urban water supply and drainage systems due to failure of sensor equipment during water pipe network monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a flow chart of the data collection, monitoring and early warning method for the smart water pipe network of the present invention;

[0040] Figure 2 This is the structural block diagram of the data collection, monitoring and early warning system for the smart water network. DETAILED DESCRIPTION

[0041] The present invention will be further described below in conjunction with specific implementation methods, wherein the accompanying drawings are only used for exemplary descriptions and represent only schematic diagrams rather than actual drawings, and should not be understood as limiting the present invention. In order to better illustrate the specific implementation methods of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0042] Example 1: Figure 1-Figure 2 As shown, the specific implementation process of the technical solution of the present invention includes the following steps:

[0043] Step 1: Construct the topological structure of the water pipe network based on BIM technology, and use GIS technology to mark each node in the water pipe network to obtain the positioning coordinates of the data collection nodes to be measured;

[0044] Step 2: Acquire real-time sensor data and historical sensor data of periodic pipe network data at data collection nodes in the structure;

[0045] It should be noted that the pipe network data includes at least one of water pressure, water flow velocity, water temperature, pH value, turbidity, instantaneous flow rate, and dissolved oxygen content at the data collection node. When the pipe network data type is one, in this embodiment, the water pressure value of the water pipe network node is used as the sampling data for illustration. By setting a water pressure sensor at the data collection node to be measured, the real-time sensing data and historical sensing data of the periodic water pressure data at the data collection node are obtained;

[0046] Step 3: Determine the operating status of the water pressure sensing device at the data collection node based on the acquired water pressure sensor data. The determination method includes the following steps:

[0047] S21: Obtain periodic real-time sensing data and historical sensing data of the water pressure sensing device at the data collection node to be tested. In the urban water supply system, the water pressure in the pipe network changes periodically over time. Therefore, in this embodiment, 1d can be used as the sensing data collection period, and the data collection time interval is set to 1h;

[0048] S22: Construct a change curve of the historical sensing data of the water pressure sensing device in the kth operation cycle, recorded as: , where d kt It is represented as the real-time sensing data collected by the water pressure sensing device at time t in the kth operation cycle, and the change curve of k groups of historical sensing data is obtained;

[0049] S23: Calculate the maximum difference of the historical sensor data change curve within k operation cycles according to the formula , which is the maximum value of the difference between any two change curves, and the calculation formula is:

[0050] ,

[0051] In the formula, max{} means taking the maximum value in the brackets; q, p are both ∈ k, and q≠p; T is the amount of data collected;

[0052] S24: Construct a curve of the change of the real-time sensing data of the water pressure sensing device within a complete cycle, that is, within a 1-day period, recorded as: , where d t It is represented by the real-time sensing data collected by the water pressure sensing device at time t;

[0053] S25: Calculate the maximum difference between the change curve of the real-time sensor data and the change curve of the historical sensor data of the data collection node to be tested in the current operation cycle according to the formula , the calculation formula is:

[0054] ;

[0055] S26: The maximum difference of the change curve and The quantitative relationship between them is used as the basis to determine the operating status of the sensor equipment, specifically:

[0056] like ≤ , then the operating state of the sensor device is determined to be abnormal, and when the operating state of the sensor device is determined to be abnormal, an equipment abnormality alarm signal is generated, and the coordinates of the data collection node are obtained to issue an alarm;

[0057] like > , then the operating status of the sensor device is determined to be normal;

[0058] Step 4: When it is determined that the operating state of the sensor device at the data collection node at the current moment is normal, the data state of the acquired real-time sensor data is determined, and when the real-time sensor data is determined to be abnormal data, an alarm is issued, wherein the data state determination method includes the following steps:

[0059] S31: Acquire real-time sensor data of the water pressure sensor device at the current data collection node to be tested;

[0060] S32: Build a prediction model based on the acquired real-time sensor data. The expression of the model is:

[0061] , where It is represented as the predicted value of the real-time sensing data of the water pressure sensing device at the λth sampling period, It is represented by the real-time sensing data sampling value of the water pressure sensing device at the λ-1th sampling period, a is a constant coefficient, and a∈(0,1), φ∈λ and φ<λ;

[0062] S33: Obtain the real-time sensor data prediction value and sampling value of the water pressure sensor device at the λth sampling period Based on the quantitative relationship between them, the data status of the real-time sensing data sampling value of the water pressure sensing device is determined, specifically:

[0063] like ∈[ -∆s, +∆s], then determine the real-time sensor data sampling value The data status is normal;

[0064] like > +∆s or < -∆s, then determine the real-time sensor data sampling value When the data state of the real-time sensor data is determined to be abnormal data, a data abnormality alarm signal is generated and an alarm is issued;

[0065] Where ∆s is the fluctuation coefficient, and ∆s>0. The fluctuation coefficient ∆s is determined according to the following formula: .

[0066] Example 2: Figure 1-Figure 2 As shown, when there is more than one type of pipe network data to be monitored, the specific implementation process of the technical solution of the present invention is different from that of Example 1 in that the operating status of one of the sensor devices is first determined, and then the data status is determined based on the operating status of the device. The specific steps of the determination method are as described in Example 1 and will not be repeated here. Then, the operating status of another sensor device and the collected data status are determined. When there is an abnormality in the operating status or data status of any sensor device, a corresponding abnormal alarm signal is generated, and the coordinates of the data acquisition node are located to perform an alarm action.

[0067] The technical solution proposed by the present invention can effectively solve the problem of inaccurate monitoring of the operating status of the urban water supply and drainage system due to failure of the sensor equipment during the water pipe network monitoring process.

[0068] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A data collection, monitoring and early warning method for a smart water pipe network, characterized in that: include: Construct the topological structure of the water pipe network and obtain the real-time sensor data and historical sensor data of the periodic pipe network data at the data collection nodes in the structure; Determine the operating status of the sensor equipment at the data collection node based on the acquired sensor data; When it is determined that the operating state of the sensor equipment at the data collection node at the current moment is abnormal, the coordinates of the data collection node are obtained and an alarm is issued; When it is determined that the operating state of the sensor device at the data collection node at the current moment is normal, the data state of the acquired real-time sensor data is determined, and when it is determined that the real-time sensor data is abnormal data, an alarm is issued; The method for determining the operating status of a sensing device comprises the following steps: S21: Acquire periodic real-time sensing data and historical sensing data of the i-th type of sensing device; S22: Construct a change curve of the historical sensor data of the i-th type of sensor equipment in the k-th operation cycle, recorded as: , where d ikt It is represented as the real-time sensor data collected by the i-th sensor device at time t in the k-th operation cycle; S23: Calculate the maximum difference of the historical sensor data change curve within k operation cycles according to the formula , the calculation formula is: ， In the formula, max{} means taking the maximum value in the brackets; q, p are both ∈ k, and q≠p; T is the amount of data collected; S24: Construct a curve of the change of the real-time sensing data of the i-th type of sensing device in a complete cycle, recorded as: , where d it It is represented as the real-time sensor data collected by the i-th sensor device at time t; S25: Calculate the maximum difference between the change curve of real-time sensor data and the change curve of historical sensor data according to the formula , the calculation formula is: ； S26: The maximum difference of the change curve and The quantitative relationship between them is used as the basis to determine the operating status of the sensor equipment, specifically: like ≤ , then the operating state of the sensor device is determined to be abnormal; like > , then the operating status of the sensor device is determined to be normal; The data state determination method of real-time sensor data comprises the following steps: S31: Acquire real-time sensor data of the i-th sensor device; S32: Build a prediction model based on the acquired real-time sensor data. The expression of the model is: ， In the formula, It is represented as the predicted value of the real-time sensor data of the i-th sensor device at the λ-th sampling period, It is represented as the real-time sensor data sampling value of the i-th sensor device at the λ-1-th sampling period, a is a constant coefficient, and a∈(0,1), φ∈λ and φ<λ; S33: Obtain the predicted value and sampled value of the real-time sensor data of the i-th sensor device in the λ-th sampling period Based on the quantitative relationship between them, the data state of the real-time sensor data sampling value of the sensor device is determined, specifically: like ∈[ -∆s, +∆s], then determine the real-time sensor data sampling value The data status is normal; like > +∆s or < -∆s, then determine the real-time sensor data sampling value The data status is abnormal; Where ∆s is the fluctuation coefficient, and ∆s>0; The pipe network data includes at least one of water pressure, water flow velocity, water temperature, pH value, turbidity, instantaneous flow rate, and dissolved oxygen content at the data collection node.

2. The data collection, monitoring and early warning method for the smart water pipe network according to claim 1 is characterized in that: The fluctuation coefficient ∆s is determined according to the following formula: .

Images