An automatic monitoring pump station system

Abstract

The present invention provides an automatic monitoring pump station system, which belongs to the field of automatic monitoring of pump stations, and includes a pump station, a peripheral security monitoring unit of the pump station, an internal environment monitoring unit of the pump station, a pump station pumping power adaptive monitoring unit, and a pump station related parameter monitoring unit. By fully automating the monitoring of the entire pump station, unmanned monitoring can be achieved, and at the same time, the optimal environment operation of the pump station can be achieved, and the optimal efficiency can be achieved.

Description

Technical Field

[0001] The invention relates to the field of automatic monitoring of pumping stations, and in particular to an automatic monitoring pumping station system. Background Art

[0002] Water conservancy projects are projects built to control and allocate natural surface water and groundwater to achieve the purpose of promoting benefits and eliminating harm. In water conservancy projects, when it is necessary to dispatch water resources from low water levels to high water levels, it is often necessary to achieve this through a pumping station system. Some large pumping station systems often include multi-stage pumping stations located at different heights, and there is often a certain height difference between the pumping stations at each level. When the water pump is pumping water to a high place, if some emergency failure occurs and the water pump cannot continue to pump water, the direction of the water flow will change rapidly. Since the pipeline system of the pump station is relatively closed, it is easy to cause the water flow to change sharply instantly, which will cause the water hammer effect, which will cause greater impact and damage to the pipelines and water pumps in the pumping station system.

[0003] Existing pumping stations often have long construction periods and become clogged during the pumping process, requiring manual inspection and management, which is very time-consuming and labor-intensive, and the pumping stations cannot be remotely controlled and managed. Since pumping stations require a large amount of electricity, they often break down or consume a lot of electricity in some rural mountains, which cannot meet the real-time pumping needs of pumping stations.

[0004] At the same time, many pumping stations are built on uninhabited mountains in mountainous areas, so it is troublesome to manage the pumping stations. Pumping management, fault management and maximum pumping efficiency output management all require a lot of manpower to supervise. Therefore, it is necessary to design an automatic supervision pumping station. Summary of the invention

[0005] The purpose of the present invention is to provide an automatic monitoring pump station system to solve the technical problem that the pump station cannot be automatically monitored and requires a lot of manpower and material resources.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0007] An automatically supervised pump station system comprises a pump station, a pump station peripheral security supervision unit, a pump station internal environment monitoring unit, a pump station pumping power adaptive supervision unit and a pump station related parameter monitoring unit. The pump station peripheral security supervision unit is arranged around the pump station for real-time defense deployment without supervision, intrusion defense deployment, proximity alarm and dangerous area intrusion alarm. The pump station internal environment monitoring unit is arranged inside the pump station for detecting the ambient temperature and humidity inside the pump station, the vibration data of the water pump, the temperature data and the water tank liquid level data, and detecting the flow, water volume and pressure in real time. The pump station pumping power adaptive supervision unit is used to set the initial pumping power of the pump station and track the most efficient output in real time according to the changes in the pumping parameters. The pump station related parameter monitoring unit is arranged on the pump station for detecting the motor current, voltage, power, power factor and inverter output frequency in real time.

[0008] Furthermore, the pump station includes an outer box body, a pump station body device and a control cabinet. The pump station body device and the control cabinet are arranged in the outer box body of the pump station. The control cabinet is connected to the pump station body device control. The control cabinet is connected to the remote control terminal and the client via wireless. The outer box body of the pump station is used to install and fix the pump station body device and the control cabinet in the outer box body of the pump station in advance. The outer box body of the pump station is installed in a modular design, and then the pump station body device and the control cabinet are installed in different modular boxes in the factory. Then, the output water volume and power data are debugged and tested according to the parameters of different pump stations. The modular boxes are transported to the destination by truck and then the modular boxes are spliced. The user remotely views the working status data of the pump station body device and remotely through the client.

[0009] Furthermore, the pump station peripheral security monitoring unit includes a plurality of security cameras. A plurality of camera mounting holes are arranged on the outer side of the pump station outer box, and the security cameras are installed in the camera mounting holes.

[0010] Furthermore, the outer box of the pump station includes several water pump box modules and a control box module. The water pump box module is used to install the pump station body device. The pump station body device is installed and fixed in the water pump box module before leaving the factory. When installing at the factory, the site to be installed is first inspected to determine the flow range and height of the pumping station, and then the pump station body device with an adaptable range is selected for installation. The sides of the water pump box module and the control box module or between the water pump box modules are directly connected.

[0011] Furthermore, the specific supervision process of the pump station pumping power adaptive supervision unit includes the following steps:

[0012] Step 1: Collect some data of pumping station pumping to obtain the pumping station pumping data set DB, which is expressed as DB = {S i |i=1,2,…,m}, m is the number of data samples;

[0013] Step 2: Use the existing data samples in the DB as reference objects.

[0014] Step 3: Take the existing data samples in DB as reference objects, find out K neighboring samples that are close to the parameters of the initial commissioning of the pumping station, and determine the influence weights according to the distances between the K neighboring samples and the parameters of the initial commissioning of the pumping station. Then, use the weighted regression values ​​of the corresponding pumping power parameters of the K neighboring samples as the initial design values ​​of the pumping power parameters of the pumping station. Suppose the highest efficiency power of the i-th sample and the initial pumping power of the pumping station are y i1 and i2 , let the pumping station be O, and the corresponding pumping influence factor of the pumping station is {o1, o2, ..., o θ}, the maximum efficiency power of the pumping station and the initial pumping power of the pumping station are y o1 and o2 ;

[0015] Step 4: Correct the power of the pumping station. Based on the selected data set DB, the data is analyzed to find out the influencing factors other than the pumping influencing factors of the pumping station, and the correction model structure based on the initial pumping power of the pumping station is obtained. The error correction model can be obtained through sample training. The error correction amount of the model fitting is summed with the initial value of the pumping power of the pumping station to complete the design of the initial pumping power of the pumping station.

[0016] Step 5: The control cabinet takes the initial value of the pumping power of the pumping station as the benchmark value and converts it into a benchmark efficiency value. In the subsequent pumping process, since the influencing factors of the pumping station will change, the actual pumping power of the pumping station will be converted into an actual efficiency value, and the actual efficiency value will be compared with the benchmark efficiency value in real time. When the actual efficiency value is less than the benchmark efficiency value, the actual power value will be used as the subsequent benchmark efficiency value.

[0017] Furthermore, the specific process of step 1 is as follows: the attribute variables of the pumping station related parameters, pump related data and water demand data of each pumping station are divided into the influencing factors X of the pumping station related parameters according to the properties. k , k = 1, 2, ..., t, t represents the number of process influencing factors, pump station related parameters Y j , j = 1, 2, ..., n, n represents the number of pump station related parameters, pump station pumping data sample S i The corresponding attribute data are x ik and ij ,The pump station related parameters include terrain difference pressure, the number of water pipe elbows, pumping power and output efficiency of the pump station.

[0018] Furthermore, the specific process of step 2 is:

[0019] Step 2.1: Preprocess the data and use data normalization method to eliminate the influence of different dimensions between different related attributes:

[0020]

[0021] In the formula, max(k) and min(k) represent the maximum and minimum values ​​of the kth column data in the pump station related parameter database, respectively;

[0022] Step 2.2: Calculate the distance between the pumping station pumping data. The distance between the pumping station pumping data in the feature space is measured by calculating the Euclidean distance, and K samples that are close to the target pumping station pumping data are taken according to the size of the distance. The pumping station pumping data sample distance calculation is as follows:

[0023]

[0024] Step 2.3: According to the distance d i The size of , in order from small to large, select K samples with the smallest distance from the pumping station O's pumping data, that is, the nearest neighbor clustering sample set CS, CS = {S i′ |i′=1,2…,K}, and determine the weight ω of each cluster sample according to the distance relationship i′ , represents the degree of similarity to O, and the sample weight calculation is shown as follows:

[0025]

[0026] ω i′ is the weight of the i′th cluster sample, d i′ is the calculated distance between the i′th cluster sample and the pumping data of the target pumping station;

[0027] Step 2.4: According to the sample weights obtained in step 2.3, the required pump station related parameters are weighted summed to obtain the pump station related parameters required for the target pump station pumping data. The relevant parameters of the target pump station pumping data are calculated as shown in the following formula:

[0028]

[0029]

[0030] The optimal K value is obtained according to the KNN algorithm to construct the optimal clustering scale. After optimization, when K is a certain value, the relative error and mean square error of the initial pumping power of the pumping station are close to the lowest level when the initial value of the pumping power of the pumping station is summed up. At this time, the prediction effect of the KNN model is the most accurate and stable.

[0031] Furthermore, the specific process of step 3 is:

[0032] Step 3.1: According to the classification, count the number of samples in the pumping station water pumping data set DB that belong to the category, and calculate the arithmetic mean of the efficiency values ​​of the pumping station water pumping data of the same type as the efficiency of the pumping station water pumping data of this type. On this basis, use the least squares method to fit the relationship between the corresponding relevant attributes and the initial value of the pumping power of the pumping station. The actual correlation is judged by the goodness of fit result. The most relevant factor with a goodness of fit exceeding 85% is taken as the input, and then the least squares method is fitted. The goodness of fit is calculated as follows:

[0033]

[0034] In the formula, is the initial value of the pumping power of the pumping station fitted by the least square method;

[0035] Step 3.2: Select the relevant factors of the initial value of the pumping power of the pumping station and establish an error correction model. The error correction model includes an input layer, a pattern layer, a summation layer and an output layer. The input layer is the influencing factor variable. The pattern layer is used to calculate the distance information between the test and training sample input vectors. The number of neurons in the pattern layer is the same as the number of training samples of the model, that is, each pattern layer neuron corresponds to a training sample, and is fully connected with the input layer neurons. The summation layer uses two types of neurons for summation, namely, type A neurons and type B neurons. There is only one type A neuron, and the calculated value is the output arithmetic sum of all pattern layer neurons. The number of type B neurons is the same as the dimension of the output vector. It is necessary to perform weighted summation on all neurons in the pattern layer. The connection weight of the Nth type B neuron in the summation layer and the λth neuron in the pattern layer is the Nth element l in the output vector of the learning sample corresponding to the neuron in the pattern layer. λN , N is a positive integer, and the output layer is the correction value of the initial value of the pumping power of the pumping station according to the obtained output.

[0036] Furthermore, the pump station device includes a water pump inlet pipe, an exhaust valve, a water collection pipe, a water pump, a sand and gravel filter, a first sewage pipe, a second sewage pipe, a mesh filter, a water outlet, an ultrasonic flowmeter, a check valve, a pressure-reducing valve, a butterfly valve, an air valve and a pressure gauge. The water pump inlet pipe is arranged at the water inlet end of the water pump, the water collection pipe is arranged at the water outlet end of the water pump, the exhaust valve is arranged at the upper end of the water collection pipe, the input end of the sand and gravel filter is connected to the water collection pipe, the first sewage pipe is connected to the filtered waste port of the sand and gravel filter, the input end of the mesh filter is connected to the clean water output end of the sand and gravel filter, the second sewage pipe is connected to the waste outlet of the mesh filter, an ultrasonic flowmeter, a check valve, a pressure-reducing valve, a butterfly valve, an air valve and a pressure gauge are arranged between the output end of the mesh filter and the water outlet, and the water pump, sand and gravel filter, mesh filter, ultrasonic flowmeter, check valve, pressure-reducing valve, butterfly valve, air valve and pressure gauge are all connected to the control cabinet.

[0037] Furthermore, a solar panel is arranged on the top of the outer box of the pump station, and an energy storage unit is arranged on the control box module. The energy storage unit includes a daily power supply solar cell and an emergency power supply battery. When the daily power supply solar cell is out of power and the city power cannot supply power, the emergency power supply battery is started to supply power. When the internal environment monitoring unit of the pump station controls the water pump, when the water flow rate is detected to be within a preset range, the output power of the motor is adjusted to maintain the highest efficiency for output. When it is detected that the power of the daily power supply solar cell is full and the solar light intensity is greater than the set value, the output power of the water pump is increased, and the water output flow rate is adjusted to the maximum value of the preset range. All the electrical energy converted by the solar panel is utilized. When the power grid is in a low power consumption period, the energy storage unit charges energy from the power grid or starts the water pump to pump Water, at the same time, the internal environment monitoring unit of the pump station detects the real-time filter pressure of the sand and gravel filter and the mesh filter in real time. When the filter pressure is greater than the preset value, the backwash pressure water pump arranged on the sand and gravel filter and the mesh filter is turned on, and the switch arranged on the water inlet end of the sand and gravel filter and the mesh filter is closed at the same time. The impurities on the filter are reversely flushed out by the water pressure sprayed by the flushing pressure water pump, and flow out from the first sewage pipe or the second sewage pipe, so as to realize automatic detection of the amount of impurities in the filter and then automatically clean it. The specific process of detecting the real-time pressure of the filter is to first detect the water inlet pressure at the front end of the filter, and then detect the initial water inlet pressure of the cleaned filter, and then compare the difference between the detected filter pressure and the initial water inlet pressure. When the difference is greater than the preset value, it indicates that the filter is blocked and needs to be backwashed.

[0038] The present invention has the following beneficial effects due to the adoption of the above technical solution:

[0039] (1) The present invention can realize unmanned supervision by fully automating the supervision of the entire pump station, and at the same time, it can realize the optimal environment operation of the pump station and achieve the optimal efficiency. The pump station modularizes the outer box of the pump station to make the installation and transportation process more efficient. The traditional time to build a pump station is about 42 days, but the pump station of the present application can be installed and constructed in two days, which greatly improves the efficiency. The standardized pump room and modular components can be quickly installed and put into use. The overall standardized design and production are carried out, and strict testing is carried out to ensure that the various indicators of the pump station are qualified and stable, and the high-efficiency water supply indicators are ensured. The high-efficiency operation of the pump station is ensured through technical means such as equipment selection, pipeline design and intelligent linkage. It is equipped with a digital information management platform, supports PC-side, smart large screen, mobile phone-side and other human-computer interaction modes, can strongly supervise the pump station, intelligent operation, reduce the risk of human error operation, automatic fault inspection, self-recovery ability, stable system performance, intelligent security system, equipment operation protection and personnel operation protection functions, and has warning and alarm functions for external intrusion, big data analysis, and can obtain various operation data and data analysis reports of the pump station at any time.

[0040] (2) The pumping power adaptive supervision unit of the pumping station corrects the initial power data of the existing pumping station according to the original data of some pumping stations, and then combines it with the actual efficiency output, so as to use the original big data to improve the automatic design of the pumping data of a newly designed pumping station, realize automatic detection and automatic correction, avoid the need for manual settings, and automatically adjust according to the changes in different parameters, so as to maximize the output efficiency, achieve maximum energy saving, and realize an adaptive work control process. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a block diagram of the system module of the present invention;

[0042] Figure 2 It is a schematic diagram of the external three-dimensional structure of the pump station of the present invention;

[0043] Figure 3 is a top view of the interior of the pump station of the present invention;

[0044] Figure 4 It is a schematic diagram of the left three-dimensional structure of the present invention;

[0045] Figure 5 It is a schematic diagram of the three-dimensional structure on the right side of the present invention.

[0046] In the attached drawings, 1-pump station outer box, 2-control box module, 3-water pump box module, 4-water pump inlet pipe, 5-exhaust valve, 6-water collecting pipe, 7-water pump, 8-sand filter, 9-first sewage pipe, 10-second sewage pipe, 11-mesh filter, 12-water outlet, 13-ultrasonic flow meter, 14-check valve, 15-pressure holding and reducing valve, 16-dish valve, 17-air valve, 18-pressure gauge, 19-control cabinet, 20-camera installation hole. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and preferred embodiments. However, it should be noted that many details listed in the specification are only for the purpose of enabling the reader to have a thorough understanding of one or more aspects of the present invention, and these aspects of the present invention can be implemented even without these specific details.

[0048] like Figure 1As shown, an automatically supervised pump station system includes a pump station, a peripheral security supervision unit of the pump station, an internal environment monitoring unit of the pump station, a pump station pumping power adaptive supervision unit and a pump station related parameter monitoring unit. The peripheral security supervision unit of the pump station is arranged around the pump station for unsupervised real-time defense, intrusion defense, proximity alarm and dangerous area intrusion alarm. The internal environment monitoring unit of the pump station is arranged inside the pump station for detecting the ambient temperature and humidity inside the pump station, the vibration data of the water pump, the temperature data and the water tank liquid level data, and the flow, water volume and pressure are detected in real time. The pump station pumping power adaptive supervision unit is used to set the initial pumping power of the pump station, and track the most efficient output in real time according to the changes in the pumping parameters. The pump station related parameter monitoring unit is arranged on the pump station for real-time detection of the motor current, voltage, power, power factor and inverter output frequency.

[0049] In an embodiment of the present invention, a pump station includes an outer box body 1 of a pump station, a pump station body device and a control cabinet 19. The pump station body device and the control cabinet 19 are arranged in the outer box body 1 of the pump station. The control cabinet 19 is connected to the control of the pump station body device. The control cabinet 19 is connected to the remote control terminal and the client via wireless. The outer box body 1 of the pump station is used to install and fix the pump station body device and the control cabinet 19 in the outer box body 1 of the pump station in advance. The outer box body 1 of the pump station is installed in a modular design, and then the pump station body device and the control cabinet 19 are installed in different modular boxes in the factory, and then the output water volume and power data are debugged and tested according to the parameters of different pump stations. The modular boxes are transported to the destination by truck and then the modular boxes are spliced. The user remotely views the working status data of the pump station body device and the remote through the client.

[0050] In the embodiment of the present invention, the pump station peripheral security monitoring unit includes a plurality of security cameras. A plurality of camera mounting holes 20 are provided on the outer side of the pump station outer box 1. The security cameras are installed in the camera mounting holes 20.

[0051] In an embodiment of the present invention, the outer box body 1 of the pump station includes a plurality of water pump box modules 3 and a control box module 2. The water pump box module 3 is used to install the pump station body device. The pump station body device is installed and fixed in the water pump box module 3 before leaving the factory. When installed at the factory, the site to be installed is first inspected to determine the flow range and height of the pumping of the pump station, and then the pump station body device within the applicable range is selected for installation. The sides of the water pump box module 3 and the control box module 2 or the sides of the water pump box module 3 and the water pump box module 3 are directly connected.

[0052] The specific supervision process of the pumping power adaptive supervision unit of the pumping station includes the following steps:

[0053] Step 1: Collect some data of pumping station pumping to obtain the pumping station pumping data set DB, which is expressed as DB = {S i|i=1,2,…,m}, m is the number of data samples;

[0054] Step 2: Use the existing data samples in the DB as reference objects.

[0055] Step 3: Take the existing data samples in DB as reference objects, find out K neighboring samples that are close to the parameters of the initial commissioning of the pumping station, and determine the influence weights according to the distances between the K neighboring samples and the parameters of the initial commissioning of the pumping station. Then, use the weighted regression values ​​of the corresponding pumping power parameters of the K neighboring samples as the initial design values ​​of the pumping power parameters of the pumping station. Suppose the highest efficiency power of the i-th sample and the initial pumping power of the pumping station are y i1 and i2 , let the pumping station be O, and the corresponding pumping influence factor of the pumping station is {o1, o2, ..., o θ}, the maximum efficiency power of the pumping station and the initial pumping power of the pumping station are y o1 and o2 ;

[0056] Step 4: Correct the power of the pumping station. Based on the selected data set DB, the data is analyzed to find out the influencing factors other than the pumping influencing factors of the pumping station, and the correction model structure based on the initial pumping power of the pumping station is obtained. The error correction model can be obtained through sample training. The error correction amount of the model fitting is summed with the initial value of the pumping power of the pumping station to complete the design of the initial pumping power of the pumping station.

[0057] Step 5: The control cabinet (19) uses the initial value of the pumping power of the pumping station as a reference value and converts it into a reference efficiency value. In the subsequent pumping process, since the influencing factors of the pumping station will change, the actual pumping power of the pumping station is converted into an actual efficiency value, and the actual efficiency value is compared with the reference efficiency value in real time. When the actual efficiency value is less than the reference efficiency value, the actual power value is used as the subsequent reference efficiency value.

[0058] In the embodiment of the present invention, the specific process of step 1 is: attribute variables of pump station related parameters, pump related data and water demand data of each pump station pumping data, and the attributes of the pump station pumping data are divided into influencing factors X of the pump station related parameters according to their properties. k , k = 1, 2, ..., t, t represents the number of process influencing factors, pump station related parameters Y j , j = 1, 2, ..., n, n represents the number of pump station related parameters, pump station pumping data sample S i The corresponding attribute data are x ik and ij ,The pump station related parameters include terrain difference pressure, the number of water pipe elbows, pumping power and output efficiency of the pump station.

[0059] In the embodiment of the present invention, the specific process of step 2 is:

[0060] Step 2.1: Preprocess the data and use data normalization method to eliminate the influence of different dimensions between different related attributes:

[0061]

[0062] In the formula, max(k) and min(k) represent the maximum and minimum values ​​of the kth column data in the pump station related parameter database, respectively;

[0063] Step 2.2: Calculate the distance between the pumping station pumping data. The distance between the pumping station pumping data in the feature space is measured by calculating the Euclidean distance, and K samples that are close to the target pumping station pumping data are taken according to the size of the distance. The pumping station pumping data sample distance calculation is as follows:

[0064]

[0065] Step 2.3: According to the distance d i The size of , in order from small to large, select K samples with the smallest distance from the pumping station O's pumping data, that is, the nearest neighbor clustering sample set CS, CS = {S i′ |i′=1,2…,K}, and determine the weight ω of each cluster sample according to the distance relationship i′ , represents the degree of similarity to O, and the sample weight calculation is shown as follows:

[0066]

[0067] ω i′ is the weight of the i′th cluster sample, d i′ is the calculated distance between the i′th cluster sample and the pumping data of the target pumping station;

[0068] Step 2.4: According to the sample weights obtained in step 2.3, the required pump station related parameters are weighted summed to obtain the pump station related parameters required for the target pump station pumping data. The relevant parameters of the target pump station pumping data are calculated as shown in the following formula:

[0069]

[0070]

[0071] The optimal K value is obtained according to the KNN algorithm to construct the optimal clustering scale. After optimization, when K is a certain value, the relative error and mean square error of the initial pumping power of the pumping station are close to the lowest level when the initial value of the pumping power of the pumping station is summed up. At this time, the prediction effect of the KNN model is the most accurate and stable.

[0072] In the embodiment of the present invention, the specific process of step 3 is:

[0073] Step 3.1: According to the classification, count the number of samples in the pumping station water pumping data set DB that belong to the category, and calculate the arithmetic mean of the efficiency values ​​of the pumping station water pumping data of the same type as the efficiency of the pumping station water pumping data of this type. On this basis, use the least squares method to fit the relationship between the corresponding relevant attributes and the initial value of the pumping power of the pumping station. The actual correlation is judged by the goodness of fit result. The most relevant factor with a goodness of fit exceeding 85% is taken as the input, and then the least squares method is fitted. The goodness of fit is calculated as follows:

[0074]

[0075] In the formula, is the initial value of the pumping power of the pumping station fitted by the least square method;

[0076] Step 3.2: Select the relevant factors of the initial value of the pumping power of the pumping station and establish an error correction model. The error correction model includes an input layer, a pattern layer, a summation layer and an output layer. The input layer is the influencing factor variable. The pattern layer is used to calculate the distance information between the test and training sample input vectors. The number of neurons in the pattern layer is the same as the number of training samples of the model, that is, each pattern layer neuron corresponds to a training sample, and is fully connected with the input layer neurons. The summation layer uses two types of neurons for summation, namely, type A neurons and type B neurons. There is only one type A neuron, and the calculated value is the output arithmetic sum of all pattern layer neurons. The number of type B neurons is the same as the dimension of the output vector. It is necessary to perform weighted summation on all neurons in the pattern layer. The connection weight of the Nth type B neuron in the summation layer and the λth neuron in the pattern layer is the Nth element l in the output vector of the learning sample corresponding to the neuron in the pattern layer. λN , N is a positive integer, and the output layer is the correction value of the initial value of the pumping power of the pumping station according to the obtained output.

[0077] In the embodiment of the present invention, the pump station device includes a water pump inlet pipe 4, an exhaust valve 5, a water collection pipe 6, a water pump 7, a gravel filter 8, a first sewage pipe 9, a second sewage pipe 10, a mesh filter 11, a water outlet 12, an ultrasonic flow meter 13, a check valve 14, a pressure-reducing valve 15, a butterfly valve 16, an air valve 17 and a pressure gauge 18. The water pump inlet pipe 4 is arranged at the water inlet end of the water pump 7, the water collection pipe 6 is arranged at the water outlet end of the water pump 7, the exhaust valve 5 is arranged at the upper end of the water collection pipe 6, the input end of the gravel filter 8 is connected to the water collection pipe 6, and the first sewage pipe 9 is connected to the gravel filter 8. The filter waste port is connected, the input end of the mesh filter 11 is connected to the clean water output end of the sand and gravel filter 8, the second sewage pipe 10 is connected to the waste outlet of the mesh filter 11, and an ultrasonic flowmeter 13, a check valve 14, a pressure-maintaining and reducing valve 15, a butterfly valve 16, an air valve 17 and a pressure gauge 18 are arranged between the output end of the mesh filter 11 and the water outlet 12. The water pump 7, the sand and gravel filter 8, the mesh filter 11, the ultrasonic flowmeter 13, the check valve 14, the pressure-maintaining and reducing valve 15, the butterfly valve 16, the air valve 17 and the pressure gauge 18 are all connected to the control cabinet 19.

[0078] The pump station is equipped with electrical intelligent protection devices, quick-break protection, overload protection, three-phase unbalance protection, low voltage / overvoltage protection, grounding / leakage protection, lightning protection, stall protection, current loss protection, preheating start overheating protection. The floor is equipped with metal floor to prevent the equipment from being damaged by static electricity.

[0079] In the embodiment of the present invention, a solar panel is arranged on the top of the outer box body 1 of the pump station, and an energy storage unit is arranged on the control box module 2. The energy storage unit includes a daily power supply solar cell and an emergency power supply battery. When the daily power supply solar cell is out of power and the city power cannot supply power, the emergency power supply battery is started to supply power. When the internal environment monitoring unit of the pump station controls the water pump, when the water flow rate is detected to be within a preset range, the output power of the motor is adjusted to maintain the highest efficiency for output. When it is detected that the power of the daily power supply solar cell is full and the solar light intensity is greater than the set value, the output power of the water pump is increased, and the water output flow rate is adjusted to the maximum value of the preset range. All the electric energy converted by the solar panel is utilized. When the power grid is in a low power consumption period, the energy storage unit charges and stores energy from the power grid or starts the water pump to pump water. The internal environment monitoring unit of the pump station detects the real-time filter pressure of the sand and gravel filter 8 and the mesh filter 11 in real time. When the filter pressure is greater than the preset value, the backwashing pressure water pump arranged on the sand and gravel filter 8 and the mesh filter 11 is turned on, and the switch arranged at the water inlet end of the sand and gravel filter 8 and the mesh filter 11 is closed at the same time. The impurities on the filter are reversely flushed out by the water pressure sprayed by the flushing pressure water pump, and flow out from the first sewage pipe 9 or the second sewage pipe 10, so as to automatically detect the amount of impurities in the filter and then automatically clean it. The specific process of detecting the real-time pressure of the filter is to first detect the water inlet pressure at the front end of the filter, and then detect the initial water inlet pressure of the cleaned filter, and then compare the difference between the detected filter pressure and the initial water inlet pressure. When the difference is greater than the preset value, it indicates that the filter is blocked and needs to be backwashed.

[0080] The water supply pressure is guaranteed by the frequency converter, and the frequency converter is controlled according to the valve position and switching time to stabilize the liquid level in the anti-water hammer air chamber, forming a relationship model of water pressure, valve position, valve action and air chamber water level. The water hammer is effectively prevented through data analysis and model optimization control strategy. The water supply efficiency is related to the water supply pressure and water supply position. The water supply position includes the network and height. At the same water supply point, the current water supply pressure and water supply flow are constantly sought to form the relationship between energy consumption and water supply flow, and the water supply pressure value of the energy consumption flow ratio is constantly sought. The water supply pressure corresponding to the last optimal energy consumption and flow ratio will be automatically called at the next startup to ensure that it runs at a better position this time. Continuous fine-tuning is made to seek the optimal water supply pressure to achieve the best effect of energy saving and carbon reduction.

[0081] Traditional pumping stations have low energy efficiency, and there is no unified standard for pump group selection, equipment connection, and control mode, resulting in high energy consumption of pumping stations. Low operating efficiency, control: more than 90% manual control, maintenance: 100% repair after failure, management: 90% manual ledger, high overall operating costs and low efficiency. System supervision is difficult, the level of informatization is low, there is no remote early warning alarm function, and it is difficult to supervise manually. Land reclamation is difficult, and the construction of concrete pump rooms must be carried out according to the requirements of house construction. It is difficult to reclaim concrete structures in the field. The failure rate is high. Due to the lack of standards, on-site DIY has a high failure rate of finished products due to human factors.

[0082] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An automatic supervision pump station system, Features: It includes a pump station, a pump station periphery security supervision unit, a pump station internal environment monitoring unit, a pump station pumping power adaptive supervision unit and a pump station related parameter monitoring unit. The pump station periphery security supervision unit is set up around the pump station for real-time defense without supervision, intrusion defense, proximity alarm, and dangerous area intrusion alarm. The pump station internal environment monitoring unit is set up inside the pump station for detecting the ambient temperature and humidity inside the pump station, the vibration data of the water pump, the temperature data and the water tank liquid level data, and for real-time detection of the flow, water volume and pressure. The pump station pumping power adaptive supervision unit is used to set the initial pumping power of the pump station, and to track the most efficient output in real time according to the changes in the pumping parameters. The pump station related parameter monitoring unit is set up on the pump station for real-time detection of the motor current, voltage, power, power factor and inverter output frequency; The specific supervision process of the pumping power adaptive supervision unit of the pumping station includes the following steps: Step 1: Collect some data of pumping station pumping to obtain the pumping station pumping data set DB, which is expressed as DB = {S i i=1,2,…,m}, m is the number of data samples; Step 2: Use the existing data samples in the DB as reference objects. Step 3: Take the existing data samples in DB as reference objects, find out K neighboring samples that are close to the parameters of the initial commissioning of the pumping station, and determine the influence weights according to the distances between the K neighboring samples and the parameters of the initial commissioning of the pumping station. Then, use the weighted regression values ​​of the corresponding pumping power parameters of the K neighboring samples as the initial design values ​​of the pumping power parameters of the pumping station. Suppose the highest efficiency power of the i-th sample and the initial pumping power of the pumping station are y i1 and i2 , let the pumping station be O, the corresponding pumping influence factor of the pumping station is {o 1 ,o 2 ,…,o θ }, the maximum efficiency power of the pumping station and the initial pumping power of the pumping station are y o1 and o2 ; Step 4: Correct the power of the pumping station. Based on the selected data set DB, the data is analyzed to find out the influencing factors other than the pumping influencing factors of the pumping station, and the correction model structure based on the initial pumping power of the pumping station is obtained. The error correction model can be obtained through sample training. The error correction amount of the model fitting is summed with the initial value of the pumping power of the pumping station to complete the design of the initial pumping power of the pumping station. Step 5: The control cabinet (19) uses the initial value of the pumping power of the pumping station as a reference value and converts it into a reference efficiency value. In the subsequent pumping process, since the influencing factors of the pumping station will change, the actual pumping power of the pumping station is converted into an actual efficiency value, and the actual efficiency value is compared with the reference efficiency value in real time. When the actual efficiency value is less than the reference efficiency value, the actual power value is used as the subsequent reference efficiency value; The specific process of step 1 is: attribute variables of pumping station related parameters, pump related data and water demand data of each pumping station pumping data, and the attributes of pumping station pumping data are divided into influencing factors X of pumping station related parameters according to their properties. k , k = 1, 2, ..., t, t represents the number of process influencing factors, pump station related parameters Y j , j = 1, 2, ..., n, n represents the number of pump station related parameters, pump station pumping data sample S i The corresponding attribute data are x ik and ij ,The pump station related parameters include the terrain difference pressure, the number of water pipe elbows, the pumping power and output efficiency of the pump station; The specific process of step 2 is: Step 2.1: Preprocess the data and use data normalization method to eliminate the influence of different dimensions between different related attributes: In the formula, max(k) and min(k) represent the maximum and minimum values ​​of the kth column data in the pump station related parameter database, respectively; Step 2.2: Calculate the distance between the pumping station pumping data. The distance between the pumping station pumping data in the feature space is measured by calculating the Euclidean distance, and K samples that are close to the target pumping station pumping data are taken according to the size of the distance. The pumping station pumping data sample distance calculation is as follows: Step 2.3: According to the distance d i The size of , in order from small to large, select K samples with the smallest distance from the pumping station O's pumping data, that is, the nearest neighbor clustering sample set CS, CS = {S i′ i′=1,2…,K}, and determine the weight ω of each cluster sample according to the distance relationship i′ , represents the degree of similarity to O, and the sample weight calculation is shown as follows: ω i′ is the weight of the i′th cluster sample, d i' is the calculated distance between the i′th cluster sample and the pumping data of the target pumping station; Step 2.4: According to the sample weights obtained in step 2.3, the required pump station related parameters are weighted summed to obtain the pump station related parameters required for the target pump station pumping data. The relevant parameters of the target pump station pumping data are calculated as shown in the following formula: The optimal K value is obtained according to the KNN algorithm to construct the optimal clustering scale. After optimization, when K is a certain value, the relative error and mean square error of the initial pumping power of the pumping station are close to the lowest level. At this time, the prediction effect of the KNN model is the most accurate and stable. The specific process of step 3 is: Step 3.1: According to the classification, count the number of samples in the pumping station water pumping data set DB that belong to the category, and calculate the arithmetic mean of the efficiency values ​​of the pumping station water pumping data of the same type as the efficiency of the pumping station water pumping data of this type. On this basis, use the least squares method to fit the relationship between the corresponding relevant attributes and the initial value of the pumping power of the pumping station. The actual correlation is judged by the goodness of fit result. The most relevant factor with a goodness of fit exceeding 85% is taken as the input, and then the least squares method is fitted. The goodness of fit is calculated as follows: In the formula, y is the initial value of the pumping power of the pumping station fitted by the least squares method; Step 3.2: Select the relevant factors of the initial value of the pumping power of the pumping station and establish an error correction model. The error correction model includes an input layer, a pattern layer, a summation layer and an output layer. The input layer is the influencing factor variable. The pattern layer is used to calculate the distance information between the test and training sample input vectors. The number of neurons in the pattern layer is the same as the number of training samples of the model, that is, each pattern layer neuron corresponds to a training sample, and is fully connected with the input layer neurons. The summation layer uses two types of neurons for summation, namely, type A neurons and type B neurons. There is only one type A neuron, and the calculated value is the output arithmetic sum of all pattern layer neurons. The number of type B neurons is the same as the dimension of the output vector. It is necessary to perform weighted summation on all neurons in the pattern layer. The connection weight of the Nth type B neuron in the summation layer and the λth neuron in the pattern layer is the Nth element l in the output vector of the learning sample corresponding to the neuron in the pattern layer. λN , N is a positive integer, and the output layer is the correction value of the initial value of the pumping power of the pumping station according to the obtained output.

2. An automatic monitoring pump station system according to claim 1, Features: The pump station comprises an outer box (1) of the pump station, a pump station device and a control cabinet (19), wherein the pump station device and the control cabinet (19) are arranged in the outer box (1) of the pump station, the control cabinet (19) is connected to the control of the pump station device, and the control cabinet (19) is connected to the remote control terminal and the client via wireless. The outer box (1) of the pump station is used to install and fix the pump station device and the control cabinet (19) in the outer box (1) of the pump station in advance, and the outer box (1) of the pump station is installed in a modular design, and then the pump station device and the control cabinet (19) are respectively installed in different modular boxes in the factory, and then the output water volume and power data are debugged and tested according to the parameters of different pump stations, and the modular boxes are transported to the destination by truck and then the modular boxes are spliced, and the user remotely checks the working status data of the pump station device and the remote through the client.

3. An automatic monitoring pump station system according to claim 2, Features: The pump station peripheral security monitoring unit comprises a plurality of security cameras. A plurality of camera mounting holes (20) are arranged on the outside of the pump station outer box (1), and the security cameras are mounted in the camera mounting holes (20).

4. An automatic monitoring pump station system according to claim 3, Features: The outer box body (1) of the pump station includes a plurality of water pump box modules (3) and a control box module (2). The water pump box module (3) is used to install a pump station body device. The pump station body device is installed and fixed in the water pump box module (3) before leaving the factory. When installing at the factory, the site to be installed is first inspected to determine the flow range and height of the pumping water of the pump station, and then a pump station body device within the applicable range is selected for installation. The sides of the water pump box module (3) and the control box module (2) or the sides of the water pump box module (3) and the water pump box module (3) are directly connected.

5. An automatically supervised pump station system according to claim 1, Features: The pump station device comprises a water pump inlet pipe (4), an exhaust valve (5), a water collection pipe (6), a water pump (7), a gravel filter (8), a first sewage discharge pipe (9), a second sewage discharge pipe (10), a mesh filter (11), a water outlet (12), an ultrasonic flow meter (13), a check valve (14), a pressure-reducing valve (15), a butterfly valve (16), an air valve (17) and a pressure gauge (18). The water pump inlet pipe (4) is arranged at the water inlet end of the water pump (7), the water collection pipe (6) is arranged at the water outlet end of the water pump (7), the exhaust valve (5) is arranged at the upper end of the water collection pipe (6), the input end of the gravel filter (8) is connected to the water collection pipe (6), the first sewage discharge pipe (9) is connected to the sand filter (8), and the outlet end of the gravel filter (8) is connected to the sand filter (8). The filter waste port is connected, the input end of the mesh filter (11) is connected to the clean water output end of the sand and gravel filter (8), the second sewage discharge pipe (10) is connected to the waste outlet of the mesh filter (11), an ultrasonic flow meter (13), a check valve (14), a pressure-maintaining and reducing valve (15), a butterfly valve (16), an air valve (17) and a pressure gauge (18) are arranged between the output end of the mesh filter (11) and the water outlet (12), and the water pump (7), the sand and gravel filter (8), the mesh filter (11), the ultrasonic flow meter (13), the check valve (14), the pressure-maintaining and reducing valve (15), the butterfly valve (16), the air valve (17) and the pressure gauge (18) are all connected to the control cabinet (19).

6. An automatically supervised pump station system according to claim 5, Features: A solar panel is arranged on the top of the outer box body (1) of the pump station, and an energy storage unit is arranged on the control box module (2). The energy storage unit includes a daily power supply solar cell and an emergency power supply battery. When the daily power supply solar cell is out of power and the city power cannot supply power, the emergency power supply battery is started to supply power. When the internal environment monitoring unit of the pump station controls the water pump, when the water flow rate is detected to be within a preset range, the output power of the motor is adjusted so that the output is maintained at the highest efficiency. When it is detected that the power of the daily power supply solar cell is full and the solar light intensity is greater than a set value, the output power of the water pump is increased and the water output flow rate is adjusted to the maximum value within the preset range. All the electric energy converted by the solar panel is utilized. When the power grid is at a low power consumption, the energy storage unit charges energy from the power grid or starts the water pump to pump water. At the same time, the internal environment monitoring unit of the pump station The method detects the real-time filter pressure of the sand and gravel filter (8) and the mesh filter (11) in real time. When the filter pressure is greater than a preset value, the backwash pressure water pumps provided on the sand and gravel filter (8) and the mesh filter (11) are turned on, and the switches provided on the water inlet ends of the sand and gravel filter (8) and the mesh filter (11) are turned off at the same time. The impurities on the filter are reversely flushed out by the water pressure sprayed by the flushing pressure water pump and flow out from the first sewage pipe (9) or the second sewage pipe (10), thereby automatically detecting the amount of impurities on the filter and then automatically cleaning it. The specific process of detecting the real-time filter pressure is to first detect the water inlet pressure at the front end of the filter, and then detect the initial water inlet pressure of the cleaned filter, and then compare the difference between the detected filter pressure and the initial water inlet pressure. When the difference is greater than the preset value, it indicates that the filter is clogged and needs to be backwashed.

Images