CN115182416A - Automatic pump station system of supervision - Google Patents

Abstract

The invention provides an automatic supervision pump station system, which belongs to the field of automatic supervision of pump stations and comprises a pump station, a pump station peripheral security supervision unit, a pump station internal environment monitoring unit, a pump station pumping power self-adaptive supervision unit and a pump station related parameter monitoring unit. The whole pump station is automatically supervised through full automation, so that unmanned supervision can be realized, the optimal environment operation of the pump station can be realized, and the optimal efficiency is realized.

Description

An Automatically Supervised Pumping Station System

technical field

The invention relates to the field of automatic supervision of pump stations, in particular to an automatic supervision pump station system.

Background technique

A water conservancy project is a project built to control and allocate natural surface water and groundwater to achieve the purpose of benefiting and eliminating harm. In water conservancy projects, when it is necessary to dispatch water resources from low water level to high water level, it often needs to be realized through the pumping station system. Some large-scale 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 pump is pumping water to a high place, if some emergency failure occurs and the pump cannot continue to pump water, the direction of the water flow will change rapidly. Because the pipeline system of the pump station is relatively closed, it is easy to cause the water flow to change rapidly in an instant, and then It will cause water hammer effect, which will cause greater impact damage to the pipelines and pumps in the pumping station system.

Existing pumping stations often suffer from long construction periods and blockage during pumping, requiring manual inspection and management, which is time-consuming and labor-intensive, and cannot be remotely controlled and managed. Because the pumping station requires a large amount of electricity, in some rural mountains, there are often interruptions or high power consumption, which cannot well meet the real-time pumping needs of the pumping station.

At the same time, many pumping stations are built on uninhabited mountains in mountainous areas, so it is more troublesome to manage pumping stations. It takes a lot of manpower to supervise pumping management, fault management and maximum pumping efficiency output management. Therefore, it is necessary to design a pumping station. A self-regulated pumping station.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide an automatic supervision pumping station system, which solves the technical problem that the pumping station cannot be automatically supervised and requires a large amount of manpower and material resources.

In order to achieve the above object, the technical scheme adopted in the present invention is as follows:

An automatic monitoring pumping station system, comprising a pumping station, a peripheral security monitoring unit of the pumping station, an internal environment monitoring unit of the pumping station, an adaptive monitoring unit for the pumping power of the pumping station, and a monitoring unit for related parameters of the pumping station, and the peripheral security monitoring unit of the pumping station is set Around the pumping station, it is used for unsupervised real-time arming, intrusion arming, proximity alarm, and dangerous area intrusion alarm. The internal environment monitoring unit of the pumping station is set inside the pumping station to detect the ambient temperature and humidity inside the pumping station. Vibration data, temperature data and water tank level data of the pump, and real-time detection of flow, water volume and pressure. The pumping power adaptive supervision unit of the pumping station is used to set the initial pumping power of the pumping station, and real-time according to the change of pumping parameters, real-time To track the most efficient output, the pump station related parameter monitoring unit is set on the pump station to detect the current, voltage, power, power factor and frequency converter output frequency of the motor in real time.

Further, the pumping station includes an outer box of the pumping station, a pumping station body device and a control cabinet, the pumping station body device and the control cabinet are arranged in the outer casing of the pumping station, the control cabinet is controlled and connected to the pumping station body device, and the control cabinet is connected to the pumping station through wireless. The remote control terminal is connected to the client. The outer box of the pump station is used to install and fix the pump station body device and the control cabinet in the outer box of the pump station in advance. The outer box of the pump station is installed in a modular design, and then the pump station is installed in the factory. The body device and the control cabinet are installed in different modular boxes, and then debug and test the output water and power data according to the parameters of different pump stations. The box is spliced together, and the user can remotely view the working status data and remote control of the pump station device through the client.

Further, the peripheral security supervision unit of the pumping station includes several security cameras, the outer side of the outer box of the pumping station is provided with several camera installation holes, and the security cameras are installed in the camera installation holes,

Further, the outer box of the pump station includes several pump box modules and control box modules. The pump box module is used to install the pump station body device. The pump station body device is installed and fixed in the pump box module before leaving the factory. , firstly inspect the site to be installed, determine the flow range and height of the pumping station, and then select the pumping station body device that adapts to the range for installation, between the pump box module and the control box module or between the pump box module and the pump box module. The sides between the pump box modules are directly connected.

Further, the specific supervision process of the pumping power adaptive supervision unit of the pumping station includes the following steps:

Step 1: Collect several data of pumping water to obtain the pumping data set DB of the pumping station, which is expressed as DB={S _i |i=1, 2, ..., m}, where m is the number of data samples;

Step 2: Take the existing data samples in the DB as reference objects,

Step 3: Take the existing data samples in the DB as the reference object, find out K neighboring samples that are similar to the parameters of the initial commissioning of the pumping station, and determine the influence weight according to the distance between the K neighboring samples and the parameters of the initial commissioning of the pumping station , and then take the weighted regression value of the corresponding pumping power parameters of the K nearest neighbor samples as the initial design value of the pumping power parameters of the pumping station, and set the highest efficiency power of the ith sample and the initial pumping power of the pumping station as y _i1 and y respectively _i2 , let the pumping station be O, the pumping influence factor of the corresponding pumping station is {o ₁ , o ₂ , ..., o _θ }, the highest efficiency power of the pumping station and the initial pumping power of the pumping station are _yo1 and _yo2 respectively;

Step 4: Correct the power of the pumping station, based on the selected data set DB, analyze the influencing factors except the pumping influence factor of the pumping station, and obtain the modified model structure based on the initial pumping power of the pumping station, which can be obtained through sample training. Error correction model, summing the error correction amount fitted by the model and the initial value of pumping power of the pumping station to complete the design of the initial pumping power of the pumping station;

Step 5: The control cabinet takes the initial value of the pumping power of the pumping station as the reference value, and converts the reference efficiency value. In the subsequent pumping process, since the influence factor of the pumping station will change, the actual power of the pumping station will be converted into the actual pumping power. Efficiency value, compare the actual efficiency value 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.

Further, the specific process of the step 1 is: the pumping station-related parameters of each pumping station's pumping data, the pumping pump-related data and the attribute variables of the pump water demand data, and the attributes of the pumping data of the pumping station are divided into pumping station-related attributes according to their properties. The influencing factors of parameters X _k , k=1, 2,..., t, t represent the number of process influencing factors, and the relevant parameters of the pump station Y _j , j=1, 2,..., n, n represent the pump The number of relevant parameters of the station, the corresponding attribute data of the pumping data sample Si of the pumping station are x _ik and y _{ij respectively} , and the relevant parameters of the pumping station include the terrain difference pressure, the number of water pipe elbows, the pumping power and the output efficiency of the pumping station.

Further, the specific process of step 2 is:

Step 2.1: Preprocess the data, and use the 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 data in the kth column of the pump station related parameter database, respectively;

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

Step 2.3: According to the size of the distance d _i , in the order from small to large, take the K samples with the smallest distance from the pump-related data of the pumping station O, that is, the nearest neighbor clustering sample set CS, CS = {S _i' |i' =1, 2..., K}, and determine the weight ω _i' of each clustered sample according to the distance relationship, which represents the degree of similarity to O, and the sample weight is calculated as follows:

ω _i′ is the weight of the i′-th cluster sample, and 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 weight obtained in step 2.3, weighted and summed the relevant parameters of the pumping station to obtain the relevant parameters of the pumping station required by the pumping data of the target pumping station. The calculation of the relevant parameters of the pumping data of the target pumping station is shown in the following formula :

According to the KNN algorithm, the optimal K value is obtained to construct the optimal cluster scale. After optimization, when K is a certain value, the initial value of the pumping power of the pumping station is summed to complete the relative error and the mean square error of the initial pumping power of the pumping station are close to the lowest level, and the prediction effect of the KNN model is the most accurate and stable at this time.

Further, the specific process of step 3 is:

Step 3.1: According to the classification category, count the number of existing samples in the pumping station data set DB belonging to the category, and calculate the arithmetic mean of the pumping data efficiency values of the same type of pumping station as the pumping data efficiency of this type of pumping station. On this basis , using the least squares method to fit the relationship between the corresponding attributes and the initial value of the pumping power of the pumping station, judge the actual correlation through the goodness of fit results, take the most relevant factor with the goodness of fit exceeding 85%, and list it as the input quantity , and then perform least squares fitting, and the goodness of fit is calculated as follows:

为最小二乘法拟合的泵站抽水功率始值；In the formula,

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 model layer, a summation layer and an output layer. The input layer is the influencing factor variable, and the model layer is used to calculate the test and The distance information of the training sample input vector The number of neurons in the pattern layer is the same as the number of training samples in the model, that is, each pattern layer neuron corresponds to a training sample, which is fully connected with the input layer neurons, and the summation layer uses two types of neural The sum of the neurons is the A-type neuron and the B-type neuron respectively. There is only one A-type neuron. The calculated value is the output arithmetic sum of all the mode layer neurons. The number of B-type neurons is the same as the dimension of the output vector. All neurons in the pattern layer need to be weighted and summed. The connection weight between the Nth B-type neuron in the summation layer and the λth neuron in the pattern layer is the Nth in the output vector of the learning sample corresponding to the neuron in the pattern layer. There are elements l _λN , N is a positive integer, and the output layer is the corrected value of the initial value of pumping power of the pumping station according to the obtained output.

Further, the pump station body device includes a water pump inlet pipe, an exhaust valve, a water collection pipe, a water pump, a sand filter, a first sewage pipe, a second sewage pipe, a mesh filter, a water outlet, an ultrasonic flowmeter, a check Valve, pressure reducing valve, butterfly valve, air valve and pressure gauge, the water inlet pipe of the water pump is set at the water inlet end of the water pump, the water collecting pipe is arranged at the water outlet end of the pump, the exhaust valve is arranged on the upper end of the water collecting pipe, and the sand and gravel filter The input end of the filter is connected with the water collection pipe, the first sewage pipe is connected with the filtering waste port of the sand and gravel filter, the input end of the mesh filter is connected with the clean water output end of the sand and gravel filter, and the second sewage pipe is connected with the mesh filter The waste outlet of the filter is connected to the waste outlet of the filter, and an ultrasonic flowmeter, a check valve, a pressure-sustaining pressure reducing valve, a butterfly valve, an air valve and a pressure gauge, a water pump, a sand and gravel filter are arranged between the output end of the mesh filter and the water outlet. , mesh filter, ultrasonic flowmeter, check valve, pressure-sustaining pressure reducing valve, butterfly valve, air valve and pressure gauge are all connected with the control cabinet.

Further, 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 battery and an emergency power supply battery. When supplying power, start the emergency power supply battery to supply power. When the internal environment monitoring unit of the pump station controls the water pump, when the detected water flow is within the preset range, it adjusts the output power of the motor to keep the highest efficiency for output. When the daily power supply of the solar battery is full and the solar light intensity is detected to be greater than the set value, the output power of the water pump is increased, the water output flow is adjusted to the maximum value of the preset range, and all the electric energy converted by the solar panel is used. When the power consumption of the power grid is at a low point, the energy storage unit charges and stores energy from the power grid or turns on the water pump to pump water. At the same time, the environmental monitoring unit inside the pump station detects the real-time pressure of the sand filter and the mesh filter in real time. When it is larger than the preset value, turn on the backwashing pressure water pump set on the sand and gravel filter and the mesh filter, and close the switch set at the water inlet end of the sand and gravel filter and the mesh filter. The outgoing water pressure flushes out the impurities on the filter screen in reverse, and flows out from the first sewage pipe or the second sewage pipe, so as to automatically detect the amount of impurities in the filter screen, and then automatically clean it. The specific process of detecting the real-time pressure of the filter screen is: First detect the inlet water pressure at the front end of the filter screen, and then detect the initial inlet water pressure of the cleaned filter screen, then compare the difference between the detected filter screen pressure and the initial inlet water pressure. When the value is set, it means that the filter screen is blocked and needs to be back flushed.

The present invention has the following beneficial effects due to the adoption of the above-mentioned technical solutions:

(1) The present invention can realize unmanned supervision by fully automatic supervision of the whole pumping station, and at the same time, it can realize the optimal environmental operation of the pumping station, and at the same time realize the optimal efficiency. The modularization of the box makes the installation and transportation process more efficient. The traditional time to build a pumping station is about 42 days, but the pumping station of this application can be installed and constructed in two days, the efficiency is greatly improved, and the standardization The 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 indicators of the pump station are qualified and stable, and the indicators of high-efficiency water supply are selected through equipment selection and pipeline design. With technical means such as intelligent linkage to ensure the efficient operation of the pumping station, it is equipped with a digital information supervision platform, and supports human-computer interaction modes such as PC terminal, intelligent large screen, and mobile phone terminal, which can carry out strong supervision and intelligent operation of the pumping station. Reduce the risk of human error operation, automatic fault inspection, with self-recovery ability, stable system performance, intelligent security system, with equipment operation protection and personnel operation protection function, warning drive away and alarm function for external intrusion, big data analysis , to obtain various operating data and data analysis reports of the pumping station at any time.

(2) The pumping power adaptive supervision unit of the pumping station corrects the initial power data of the existing designed pumping station according to the original data of some pumping stations, and then combines the actual efficiency output, so as to achieve the improvement of using the original big data. The automatic design of the pumping number data of a newly designed pump station realizes automatic detection and automatic correction, avoiding the need for manual settings, and at the same time, according to the changes of different parameters, automatic adjustment is carried out, so that the output efficiency is the maximum value and the maximum value is achieved. energy saving and realize adaptive work control process.

Description of drawings

Fig. 1 is the system module block diagram of the present invention;

2 is a schematic diagram of the external three-dimensional structure of the pump station of the present invention;

Fig. 3 is the internal top view of the pumping station of the present invention;

4 is a schematic diagram of the left side three-dimensional structure of the present invention;

FIG. 5 is a schematic diagram of the right side three-dimensional structure of the present invention.

In the 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 and gravel filter device, 9-first sewage pipe, 10-second sewage pipe, 11-mesh filter, 12-water outlet, 13-ultrasonic flowmeter, 14-check valve, 15-pressure-sustaining pressure reducing valve, 16- Butterfly valve, 17-air valve, 18-pressure gauge, 19-control cabinet, 20-camera mounting hole.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail below with reference to the accompanying drawings and preferred embodiments. It is to be understood, however, that many of the details set forth in the specification are merely provided to provide the reader with a thorough understanding of one or more aspects of the invention, and that aspects of the invention may be practiced without these specific details.

As shown in Figure 1, an automatically supervised pumping station system includes a pumping station, a peripheral security monitoring unit of the pumping station, an internal environmental monitoring unit of the pumping station, an adaptive monitoring unit of the pumping power of the pumping station, and a monitoring unit of the relevant parameters of the pumping station. The security monitoring unit at the periphery of the station is set around the pumping station, which is used for unsupervised real-time arming, intrusion arming, proximity alarm, and dangerous area intrusion alarm. The internal environment monitoring unit of the pumping station is set inside the pumping station to detect the pumping station. Internal ambient temperature and humidity, pump vibration data, temperature data and water tank level data, and real-time detection of flow, water volume and pressure, the pumping power adaptive monitoring unit is used to set the initial pumping power of the pumping station, and real-time based on the pumping power The most efficient output is tracked in real time. The pump station related parameter monitoring unit is set on the pump station to detect the current, voltage, power, power factor and frequency converter output frequency of the motor in real time.

In the embodiment of the present invention, the pump station includes a pump station outer casing 1, a pump station body device and a control cabinet 19, the pump station body device and the control cabinet 19 are arranged in the pump station outer casing 1, and the control cabinet 19 is connected to the pump station body. Device control connection, the control cabinet 19 is connected to the remote control terminal and the client through wireless, and the outer box 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 1 of the pump station in advance. The outer box 1 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 box is transported to the destination by truck and then spliced together. The user can remotely view the working status data and remote control of the pump station device through the client.

In the embodiment of the present invention, the peripheral security monitoring unit of the pump station includes several security cameras, the outer side of the pump station outer box 1 is provided with several camera installation holes 20, and the security camera is installed in the camera installation hole 20,

In the embodiment of the present invention, the outer box body 1 of the pump station includes several pump box modules 3 and a control box module 2. The pump box module 3 is used to install the pump station body device, and the pump station body device is installed and fixed to the water pump box before leaving the factory. In module 3, when the factory is installed, first inspect the site to be installed to determine the range and height of the pumping water flow rate of the pumping station, and then select the suitable range of pumping station body devices for installation, and the pump box module 3 and the control The sides between the tank modules 2 or between the water pump tank modules 3 and the water pump tank modules 3 are directly connected.

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

Step 1: Collect several data of pumping water to obtain the pumping data set DB of the pumping station, which is expressed as DB={S _i |i=1, 2, ..., m}, where m is the number of data samples;

Step 2: Take the existing data samples in the DB as reference objects,

Step 3: Take the existing data samples in the DB as the reference object, find out K neighboring samples that are similar to the parameters of the initial commissioning of the pumping station, and determine the influence weight according to the distance between the K neighboring samples and the parameters of the initial commissioning of the pumping station , and then take the weighted regression value of the corresponding pumping power parameters of the K nearest neighbor samples as the initial design value of the pumping power parameters of the pumping station, and set the highest efficiency power of the ith sample and the initial pumping power of the pumping station as y _i1 and y respectively _i2 , let the pumping station be O, the pumping influence factor of the corresponding pumping station is {o ₁ , o ₂ , ..., o _θ }, the highest efficiency power of the pumping station and the initial pumping power of the pumping station are _yo1 and _yo2 respectively;

Step 4: Correct the power of the pumping station, based on the selected data set DB, analyze the influencing factors except the pumping influence factor of the pumping station, and obtain the modified model structure based on the initial pumping power of the pumping station, which can be obtained through sample training. Error correction model, summing the error correction amount fitted by the model and the initial value of 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) takes the initial value of the pumping power of the pumping station as the reference value, and converts the reference efficiency value. In the subsequent pumping process, since the influence factor of the pumping station will change, the actual power of the pumping station will be changed. Convert it into the actual efficiency value, and compare the actual efficiency value 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.

In the embodiment of the present invention, the specific process of the step 1 is as follows: the pumping station-related parameters of the pumping data of each pumping station, the pumping pump-related data and the attribute variables of the water demand data of the pump, and the attributes of the pumping data of the pumping station are divided into Influencing factors of pump station related parameters X _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 relevant parameters of the pumping station. The corresponding attribute data of the pumping data sample Si of the pumping station are x _ik and y _{ij respectively} . The relevant parameters of the pumping station include the terrain difference pressure, the number of water pipe elbows, the pumping power and the output efficiency of the pumping station .

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

Step 2.1: Preprocess the data, and use the 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 data in the kth column of the pump station related parameter database, respectively;

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

Step 2.3: According to the size of the distance d _i , in the order from small to large, take the K samples with the smallest distance from the pump-related data of the pumping station O, that is, the nearest neighbor clustering sample set CS, CS = {S _i' |i' =1, 2..., K}, and determine the weight ω _i' of each clustered sample according to the distance relationship, which represents the degree of similarity to O, and the sample weight is calculated as follows:

ω _i′ is the weight of the i′-th cluster sample, and 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 weight obtained in step 2.3, weighted and summed the relevant parameters of the pumping station to obtain the relevant parameters of the pumping station required by the pumping data of the target pumping station. The calculation of the relevant parameters of the pumping data of the target pumping station is shown in the following formula :

According to the KNN algorithm, the optimal K value is obtained to construct the optimal cluster scale. After optimization, when K is a certain value, the initial value of the pumping power of the pumping station is summed to complete the relative error and the mean square error of the initial pumping power of the pumping station are close to the lowest level, and the prediction effect of the KNN model is the most accurate and stable at this time.

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

Step 3.1: According to the classification category, count the number of existing samples in the pumping station data set DB belonging to the category, and calculate the arithmetic mean of the pumping data efficiency values of the same type of pumping station as the pumping data efficiency of this type of pumping station. On this basis , using the least squares method to fit the relationship between the corresponding attributes and the initial value of the pumping power of the pumping station, judge the actual correlation through the goodness of fit results, take the most relevant factor with the goodness of fit exceeding 85%, and list it as the input quantity , and then perform least squares fitting, and the goodness of fit is calculated as follows:

为最小二乘法拟合的泵站抽水功率始值；In the formula,

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 model layer, a summation layer and an output layer. The input layer is the influencing factor variable, and the model layer is used to calculate the test and The distance information of the training sample input vector The number of neurons in the pattern layer is the same as the number of training samples in the model, that is, each pattern layer neuron corresponds to a training sample, which is fully connected with the input layer neurons, and the summation layer uses two types of neural The sum of the neurons is the A-type neuron and the B-type neuron respectively. There is only one A-type neuron. The calculated value is the output arithmetic sum of all the mode layer neurons. The number of B-type neurons is the same as the dimension of the output vector. All neurons in the pattern layer need to be weighted and summed. The connection weight between the Nth B-type neuron in the summation layer and the λth neuron in the pattern layer is the Nth in the output vector of the learning sample corresponding to the neuron in the pattern layer. There are elements l _λN , N is a positive integer, and the output layer is the corrected value of the initial value of pumping power of the pumping station according to the obtained output.

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

The pump station is equipped with electrical intelligent protection device, quick-break protection, overload protection, three-phase unbalance protection, low-voltage/over-voltage protection, grounding/leakage protection, lightning protection, locked-rotor protection, loss-of-current protection, and overheating during preheating. Protect. The floor is equipped with a metal floor to prevent the equipment from being damaged by static electricity.

In the embodiment of the present invention, a solar panel is arranged on the top of the outer box 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 battery and an emergency power supply battery. When the daily power supply solar battery is out of power , and when the city power fails to supply power, start the emergency power supply battery to supply power. When the internal environment monitoring unit of the pump station controls the pump, when the detected water flow is within the preset range, the output power of the motor is adjusted to maintain the highest efficiency. Output, when it is detected that the daily power supply solar battery is full, and the solar light intensity is greater than the set value, increase the output power of the water pump, adjust the water output flow to the maximum value of the preset range, and use the solar panel All the converted electrical energy, when the power grid is at low power, the energy storage unit charges energy from the grid or turns on the water pump to pump water, and the internal environment monitoring unit of the pump station detects the filters of the sand filter 8 and the mesh filter 11 in real time. Real-time pressure, when the filter screen pressure is greater than the preset value, the backwash pressure pump set on the sand filter 8 and the mesh filter 11 will be turned on, and the sand filter 8 and the mesh filter 11 will be closed at the same time. The switch on the water inlet end of the sieve is used to flush out the impurities on the filter screen reversely through the water pressure sprayed by the flushing pressure 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 screen, and then The specific process of automatic cleaning and detecting the real-time pressure of the filter screen is to first detect the inlet water pressure at the front end of the filter screen, then detect the initial inlet water pressure of the cleaned filter screen, and then compare the detected filter screen pressure with the initial inlet water pressure. The water pressure is compared with the difference value. When the difference value is greater than the preset value, it means that the filter screen is blocked and needs to be back flushed.

The water supply pressure is guaranteed by the frequency converter, and the frequency converter is controlled according to the valve position and switching time, so that the liquid level in the waterproof air chamber is stable, and the relationship model between water pressure, valve position, valve action and air chamber water level is formed, and the control is optimized through data analysis and model. The strategy can effectively prevent the occurrence of water hammer. The water supply efficiency is related to the water supply pressure and the water supply location. The water supply location includes the network and height. At the same water supply point, the current water supply pressure and water supply flow are continuously sought to form energy consumption and water supply. The relationship between the flow rate, constantly seek the water supply pressure value of the energy consumption-flow ratio, and automatically call the water supply pressure corresponding to the last best energy consumption and flow ratio at the next startup to ensure that the operation is in the best position this time. Seek the best water supply pressure to achieve the best effect of energy saving and carbon reduction.

The energy efficiency of traditional pumping stations is low, and there is no unified standard for pump group selection, equipment connection, control mode, etc., resulting in high energy consumption of pumping stations. Low operating efficiency, control: more than 90% manual control, maintenance: 100% repaired if broken, management: 90% manual ledger, the overall operating cost is high and the efficiency is low. It is difficult to supervise the system, the level of informatization is low, and there is no remote warning and alarm function, and it is difficult to supervise in place manually. It is difficult to re-cultivate the land. The construction of the concrete pump house needs to be constructed according to the requirements of housing construction. It is difficult to re-cultivate the concrete structure in the field. The failure rate is high, limited by the lack of standards, and the on-site DIY has a high failure rate of finished products due to human factors.

The above are only the preferred embodiments of the present invention. It should be pointed out that for those skilled in the art, without departing from the principles of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be It is regarded as the protection scope of the present invention.

Claims (10)

1. a pumping station system of automatic supervision, it is characterized in that: comprise pumping station, pumping station peripheral security monitoring unit, pumping station internal environment monitoring unit, pumping station pumping power self-adaptive monitoring unit and pumping station related parameter monitoring unit, pump The security monitoring unit at the periphery of the station is set around the pumping station, which is used for unsupervised real-time arming, intrusion arming, proximity alarm, and dangerous area intrusion alarm. The internal environment monitoring unit of the pumping station is set inside the pumping station to detect the pumping station. Internal ambient temperature and humidity, pump vibration data, temperature data and water tank level data, and real-time detection of flow, water volume and pressure, the pumping power adaptive monitoring unit is used to set the initial pumping power of the pumping station, and real-time based on the pumping power The most efficient output is tracked in real time. The pump station related parameter monitoring unit is set on the pump station to detect the current, voltage, power, power factor and frequency converter output frequency of the motor in real time. 2. The pumping station system of a kind of automatic supervision according to claim 1 is characterized in that: the pumping station comprises the outer casing (1) of the pumping station, the pumping station body device and the control cabinet (19), the pumping station body device and the control cabinet (19). The control cabinet (19) is arranged in the outer casing (1) of the pumping station, the control cabinet (19) is controlled and connected with the pumping station body device, the control cabinet (19) is connected with the remote control terminal and the client through wireless, and the outer casing of the pumping station The body (1) is used to install and fix the pump station body device and the control cabinet (19) in the pump station outer box (1) in advance, install the pump station outer box (1) in a modular design, and then install the pump in the factory. The station device and the control cabinet (19) are respectively installed in different modular boxes, and then debug and test the output water volume and power data according to the parameters of different pump stations, and transport the modular boxes to the destination by trucks Then the modular boxes are spliced together, and the user can remotely view the working status data and remote control of the pump station device through the client. 3. the pumping station system of a kind of automatic supervision according to claim 2, it is characterized in that: pumping station peripheral security supervision unit comprises several security cameras, and the outside of pumping station outer casing (1) is provided with several camera installations A hole (20), the security camera is installed in the camera installation hole (20). 4. The pumping station system of a kind of automatic supervision according to claim 3 is characterized in that: the outer casing (1) of the pumping station comprises several water pump box modules (3) and control box modules (2), and the water pump box module (3) It is used to install the pump station body device. The pump station body device is installed and fixed in the pump box module (3) before leaving the factory. When it is installed at the factory, first inspect the site to be installed to determine the pumping capacity of the pump station. What is the flow range and height, and then select the pump station body device suitable for the range for installation, between the water pump box module (3) and the control box module (2) or between the water pump box module (3) and the water pump box module (3) The sides of the room are directly connected. 5. The pumping station system of a kind of automatic supervision according to claim 1 is characterized in that: the specific supervision process of the pumping power self-adaptive supervision unit of the pumping station comprises the following steps: Step 1: Collect several data of pumping water to obtain the pumping data set DB of the pumping station, which is expressed as DB={S _i |i=1, 2, ..., m}, where m is the number of data samples; Step 2: Take the existing data samples in the DB as reference objects, Step 3: Take the existing data samples in the DB as the reference object, find out K neighboring samples that are similar to the parameters of the initial commissioning of the pumping station, and determine the influence weight according to the distance between the K neighboring samples and the parameters of the initial commissioning of the pumping station , and then take the weighted regression value of the corresponding pumping power parameters of the K nearest neighbor samples as the initial design value of the pumping power parameters of the pumping station, and set the highest efficiency power of the ith sample and the initial pumping power of the pumping station as y _i1 and y respectively _i2 , let the pumping station be O, the pumping influence factor of the corresponding pumping station is {o ₁ , o ₂ , ..., o _θ }, the highest efficiency power of the pumping station and the initial pumping power of the pumping station are _yo1 and _yo2 respectively; Step 4: Correct the power of the pumping station, based on the selected data set DB, analyze the influencing factors except the pumping influence factor of the pumping station, and obtain the modified model structure based on the initial pumping power of the pumping station, which can be obtained through sample training. Error correction model, summing the error correction amount fitted by the model and the initial value of 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) takes the initial value of the pumping power of the pumping station as the reference value, and converts the reference efficiency value. In the subsequent pumping process, since the influence factor of the pumping station will change, the actual power of the pumping station will be changed. Convert it into the actual efficiency value, and compare the actual efficiency value 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. 6. The pumping station system of a kind of automatic supervision according to claim 5, it is characterized in that: the concrete process of described step 1 is: the pumping station-related parameters of each pumping station pumping data, pumping pump-related data and water pump requirements. The attribute variable of water quantity data, according to the nature, the pumping data attribute of the pumping station is divided into the influencing factors of the relevant parameters of the pumping station X _k , k=1, 2, ..., t, t represents the number of process influencing factors, the pumping station is related The _parameters Y _j , _.j =1, ₂ , . Including the terrain difference pressure, the number of water pipe elbows, the pumping power and output efficiency of the pumping station. 7. the pumping station system of a kind of automatic supervision according to claim 6 is characterized in that: the concrete process of step 2 is: Step 2.1: Preprocess the data, and use the 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 data in the kth column of the pump station related parameter database, respectively; Step 2.2: Calculate the distance between the pumping data of the pumping station, measure the distance between the pumping data of the pumping station in the feature space by calculating the Euclidean distance, and take K samples that are close to the pumping data of the target pumping station according to the size of the distance. The distance calculation of the station pumping data sample distance is as follows:

Step 2.3: According to the size of the distance d _i , in the order from small to large, take the K samples with the smallest distance from the pump-related data of the pumping station O, that is, the nearest neighbor clustering sample set CS, CS = {S _i' |i' =1, 2..., K}, and determine the weight ω _i' of each clustered sample according to the distance relationship, which represents the degree of similarity to O, and the sample weight is calculated as follows:

ω _i′ is the weight of the i′-th cluster sample, and 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 weight obtained in step 2.3, weighted and summed the relevant parameters of the pumping station to obtain the relevant parameters of the pumping station required by the pumping data of the target pumping station. The calculation of the relevant parameters of the pumping data of the target pumping station is shown in the following formula :

According to the KNN algorithm, the optimal K value is obtained to construct the optimal cluster scale. After optimization, when K is a certain value, the initial value of the pumping power of the pumping station is summed to complete the relative error and the mean square error of the initial pumping power of the pumping station are close to the lowest level, and the prediction effect of the KNN model is the most accurate and stable at this time. 8. the pumping station system of a kind of automatic supervision according to claim 7, is characterized in that: the concrete process of step 3 is: Step 3.1: According to the classification category, count the number of existing samples in the pumping station data set DB belonging to the category, and calculate the arithmetic mean of the pumping data efficiency values of the same type of pumping station as the pumping data efficiency of this type of pumping station. On this basis , using the least squares method to fit the relationship between the corresponding attributes and the initial value of the pumping power of the pumping station, judge the actual correlation through the goodness of fit results, take the most relevant factor with the goodness of fit exceeding 85%, and list it as the input quantity , and then perform least squares fitting, and the goodness of fit is calculated as follows:

In the formula,

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 model layer, a summation layer and an output layer. The input layer is the influencing factor variable, and the model layer is used to calculate the test and The distance information of the training sample input vector The number of neurons in the pattern layer is the same as the number of training samples in the model, that is, each pattern layer neuron corresponds to a training sample, which is fully connected with the input layer neurons, and the summation layer uses two types of neural The sum of the neurons is the A-type neuron and the B-type neuron respectively. There is only one A-type neuron. The calculated value is the output arithmetic sum of all the mode layer neurons. The number of B-type neurons is the same as the dimension of the output vector. All neurons in the pattern layer need to be weighted and summed. The connection weight between the Nth B-type neuron in the summation layer and the λth neuron in the pattern layer is the Nth in the output vector of the learning sample corresponding to the neuron in the pattern layer. There are elements l _λN , N is a positive integer, and the output layer is the corrected value of the initial value of pumping power of the pumping station according to the obtained output. 9. The automatic supervision pumping station system according to claim 4, characterized in that: the pumping station body device comprises a water pump inlet pipe (4), an exhaust valve (5), a water collecting pipe (6), a water pump (7) ), sand filter (8), first sewage pipe (9), second sewage pipe (10), mesh filter (11), water outlet (12), ultrasonic flowmeter (13), check valve (14), pressure sustaining pressure reducing valve (15), butterfly valve (16), air valve (17) and pressure gauge (18), the water inlet pipe (4) of the water pump is arranged at the water inlet end of the water pump (7), and the water collecting 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 sand filter (8) is communicated with the water collection pipe (6), and the first sewage discharge The pipe (9) is connected to the filtering waste port of the sand and gravel filter (8), the input end of the mesh filter (11) is connected to the clean water output end of the sand and gravel filter (8), and the second sewage pipe (10) is connected to the The waste outlet of the mesh filter (11) is connected, and between the output end of the mesh filter (11) and the water outlet (12), an ultrasonic flowmeter (13), a check valve (14), a pressure reducing Pressure valve (15), butterfly valve (16), air valve (17) and pressure gauge (18), water pump (7), sand filter (8), mesh filter (11), ultrasonic flowmeter (13) ), check valve (14), pressure sustaining pressure reducing valve (15), butterfly valve (16), air valve (17) and pressure gauge (18) are all connected to the control cabinet (19). 10. A pumping station system for automatic supervision according to claim 9, characterized in that: the top of the outer box (1) of the pumping station is provided with a solar panel, and the control box module (2) is provided with an energy storage unit, The energy storage unit includes the daily power supply solar battery and the emergency power supply battery. When the daily power supply solar battery is out of power and the mains cannot supply power, the emergency power supply battery is activated. When the internal environment monitoring unit of the pump station controls the water pump, it detects the water When the flow rate is in the preset range, adjust the output power of the motor to keep the highest efficiency for output. When it is detected that the daily power supply solar battery is full, and the solar light intensity is greater than the set value, the pump will be increased. The output power is adjusted to the maximum value of the preset range, and all the electrical energy converted by the solar panel is used. When the power grid is at a low power consumption, the energy storage unit charges energy from the grid or turns on the water pump to pump water. At the same time, the pump station The internal environment monitoring unit detects the real-time pressure of the sand and gravel filter (8) and the mesh filter (11). The backwash pressure water pump on the filter (11) is turned on, and at the same time, the switches arranged at the water inlet ends of the sand filter (8) and the mesh filter (11) are closed, and the water pressure sprayed by the wash pressure water pump is used to remove the filter net. The impurities in the filter are flushed out in reverse, 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 screen, and then automatically clean it. The specific process of detecting the real-time pressure of the filter screen is as follows: Detect the inlet water pressure at the front end of the filter screen, and then detect the initial inlet water pressure of the cleaned filter screen, and then compare the difference between the detected filter screen pressure and the initial inlet water pressure. When the difference is greater than the preset value value, it means the filter is clogged and needs to be back flushed.

Images