CN118375600A - Variable-pressure control optimization system and method for residential secondary water supply variable-frequency pump set - Google Patents
Variable-pressure control optimization system and method for residential secondary water supply variable-frequency pump set Download PDFInfo
- Publication number
- CN118375600A CN118375600A CN202410805367.4A CN202410805367A CN118375600A CN 118375600 A CN118375600 A CN 118375600A CN 202410805367 A CN202410805367 A CN 202410805367A CN 118375600 A CN118375600 A CN 118375600A
- Authority
- CN
- China
- Prior art keywords
- variable
- flow fluctuation
- variable frequency
- data
- frequency pump
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 193
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000005457 optimization Methods 0.000 title claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 33
- 238000011217 control strategy Methods 0.000 claims abstract description 26
- 239000013589 supplement Substances 0.000 claims abstract description 7
- 238000004590 computer program Methods 0.000 claims description 15
- 238000011176 pooling Methods 0.000 claims description 10
- 230000004913 activation Effects 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 claims 2
- 230000006641 stabilisation Effects 0.000 abstract 1
- 238000011105 stabilization Methods 0.000 abstract 1
- 230000008859 change Effects 0.000 description 7
- 230000001276 controlling effect Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004134 energy conservation Methods 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 238000005314 correlation function Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Control Of Non-Positive-Displacement Pumps (AREA)
Abstract
The invention belongs to the technical field of secondary water supply, and provides a variable-pressure control optimization system and method of a residential secondary water supply variable-frequency pump set. The method comprises the following steps: collecting first flow fluctuation data of each water consumption node of a target house, constructing a training data set, and fine-tuning a general large model by using the training data set to obtain a flow fluctuation prediction model special for the target house; receiving second flow fluctuation data of each water consumption node of the target residence, inputting the second flow fluctuation data into a flow fluctuation prediction model to obtain third flow fluctuation data at an outlet of the variable frequency pump set, and determining a water pressure drop amplitude value according to the third flow fluctuation data and a flow-pressure fluctuation comparison table; and generating a variable frequency control strategy of the variable frequency pump unit according to the water pressure drop amplitude value, and executing the variable frequency control strategy by the secondary water supply variable frequency pump unit to supplement the water pressure drop amplitude value so that the water pressure in the secondary water supply pipeline is constant. The invention can realize the continuous stabilization of the secondary water supply pressure.
Description
Technical Field
The invention relates to the technical field of secondary water supply, in particular to a variable-pressure control optimization system and method of a residential secondary water supply variable-frequency pump set.
Background
The variable frequency control of the pump set in the secondary water supply system is an advanced technology, and the running state of the pump set can be automatically adjusted according to the water consumption change of a user so as to keep the water supply pressure constant. The working principle of the variable-frequency water supply pump is that the number of running water pumps and the rotation speed of one water pump are automatically regulated according to the water consumption change of a user, so that the outlet pressure of the water pump is kept constant. When the water consumption of a user is smaller than the water consumption of a variable-frequency pump, the system is provided with a variable-frequency pump for variable-frequency speed regulation operation according to the change of the water consumption, when the water consumption is increased, the pressure in the pipeline system is reduced, at the moment, the pressure sensor transmits the detected signal to the microcomputer control unit, the microcomputer operation judgment is carried out, an instruction is sent to the frequency converter, the variable-frequency water supply pump motor is controlled, the rotating speed is increased to ensure the constant pressure of the system, and otherwise, when the water consumption is reduced, the rotating speed of the variable-frequency pump is reduced to keep the constant pressure. When the water consumption is larger than the water output of one variable-frequency pump, the first pump is switched to power frequency operation, the second pump starts variable-frequency speed regulation operation, and when the water consumption is smaller than the water output of two pumps, one or two pumps can be automatically stopped.
The control strategy of the existing variable-frequency pump unit only depends on the change of the water pressure in the pipeline, but the change of the water pressure in the residential building may be short-time, for example, the water consumption is increased at the current moment to cause the water pressure in the pipeline to be reduced, but the water consumption is suddenly reduced or restored to be normal at the next period, and the variable-frequency pump unit is frequently switched according to the existing control mode, so that the work load of the variable-frequency pump unit is increased, the energy conservation is not facilitated, and the health of the water supply pipeline is not facilitated. The optimal scheme for variable-pressure control of the variable-frequency pump unit for secondary water supply of the residence is provided.
Disclosure of Invention
In view of the above, the present invention provides a method, a system, an electronic device, a computer storage medium and a computer program product for optimizing the variable-pressure control of a residential secondary water supply variable-frequency pump unit, so as to solve at least one of the above technical problems.
The invention provides a variable-pressure control optimization method of a residential secondary water supply variable-frequency pump set, which comprises the following method steps: collecting first flow fluctuation data of each water consumption node of a target house, constructing a training data set, and performing fine adjustment on a general large model by using the training data set to obtain a flow fluctuation prediction model special for the target house; receiving second flow fluctuation data of each water consumption node of the target residence, inputting the flow fluctuation prediction model to obtain third flow fluctuation data at the outlet of the variable frequency pump set, and determining a water pressure drop amplitude value according to the third flow fluctuation data and a flow-pressure fluctuation comparison table; and generating a variable frequency control strategy of the variable frequency pump unit according to the water pressure drop amplitude value, and executing the variable frequency control strategy by the secondary water supply variable frequency pump unit to supplement the water pressure drop amplitude value, so that the water pressure in the secondary water supply pipeline is constant.
Optionally, collecting first flow fluctuation data of each water node of the target residence to construct a training data set includes: collecting first flow fluctuation data and corresponding fourth flow fluctuation data of each water consumption node of a target residence, and dividing each first flow fluctuation data into outdoor data and indoor data according to the attribute of the acquisition point; the fourth flow fluctuation data are flow data at the outlet of the variable-frequency pump set, which correspond to the third flow fluctuation data; constructing the training data set by taking the outdoor data as a main body and taking the indoor data as an auxiliary strategy; wherein the training data set comprises a high duty cycle of the outdoor data and a low duty cycle of the indoor data.
Optionally, the time of collection of the fourth flow fluctuation data is determined by the following manner: calculating the shortest pipeline distance between the acquisition point of each first flow fluctuation data and the outlet of the variable frequency pump set, determining a weighted weight of the first acquisition time of the first flow fluctuation data according to the shortest pipeline distance, and calculating a weighted average of the first acquisition time according to the weighted weight to obtain an equivalent acquisition time; calculating the variance of the distance between the shortest pipelines, and determining the duration of the interference deviation according to the variance; and adding the interference deviation time length to the equivalent acquisition time to obtain the acquisition time of the fourth flow fluctuation data, namely a second acquisition time.
Optionally, the variable frequency control strategy for generating the variable frequency pump set according to the water pressure drop value comprises the following steps: acquiring a first number of currently running variable frequency pumps, real-time rotating speeds of all variable frequency pumps and an adjustable rotating speed interval of a single variable frequency pump; and performing predictive analysis on the data and the water pressure drop value by using a convolution network to obtain the second number of variable frequency pumps to be started and the target rotating speed of each variable frequency pump, and obtaining the variable frequency control strategy.
Optionally, the convolution network comprises a convolution layer, an activation layer, a pooling layer and a full connection layer which are sequentially connected; the convolution layer is used for carrying out first feature extraction on the first quantity, each real-time rotating speed and the adjustable rotating speed interval; the activation layer is used for introducing a nonlinear function to perform function mapping on the first characteristic extraction and the water pressure drop value so as to obtain a second characteristic; the pooling layer is used for reducing the space dimension of the second feature; the full-connection layer is used for comprehensively processing the first characteristics and the second characteristics processed by the pooling layer to obtain prediction results, namely the second number of variable frequency pumps needing to be started and the target rotating speed of each variable frequency pump.
Optionally, the convolutional network is a residual convolutional network. The invention also provides an electronic device, which comprises: at least one processor, a memory and a computer program stored in the memory and executable on the at least one processor, which when executed by the processor, performs the method steps for the processing apparatus as described in any of the preceding claims.
The invention also provides a transformation control optimization system of the residential secondary water supply variable-frequency pump unit, which comprises a training module, a prediction module and a variable-frequency pump unit control module; the training module is used for collecting first flow fluctuation data of each water consumption node of the target residence, constructing a training data set, and performing fine adjustment on the general large model by using the training data set to obtain a flow fluctuation prediction model special for the target residence; the prediction module is used for receiving second flow fluctuation data of each water consumption node of the target residence, inputting the flow fluctuation prediction model to obtain third flow fluctuation data at the outlet of the variable frequency pump set, and determining a water outlet pressure drop amplitude value according to the third flow fluctuation data and a flow-pressure fluctuation comparison table; the variable frequency pump set control module is used for generating a variable frequency control strategy of the variable frequency pump set according to the water pressure drop amplitude value, and the secondary water supply variable frequency pump set executes the variable frequency control strategy to supplement the water pressure drop amplitude value, so that the water pressure in the secondary water supply pipeline is constant.
The invention also provides an electronic device, which comprises: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, which when executed by the processor, implements the method of any of the preceding claims.
The invention also provides a computer storage medium storing a computer program executable by a processor to implement a method as claimed in any one of the preceding claims.
The invention also provides a computer program product comprising a computer program executable by a processor to implement a method as claimed in any preceding claim.
The invention has the beneficial effects that: compared with the traditional mode of controlling the variable-frequency pump set by depending on water pressure, the scheme of the invention has the improvement points that the water flow fluctuation at the total secondary water supply node is predicted based on the water flow fluctuation of all water consumption nodes, and the predicted water flow fluctuation is converted into the water pressure drop amplitude value at the total secondary water supply node, so that the constant water pressure in the secondary water supply pipeline can be realized by regulating and controlling the variable-frequency pump set to compensate the water pressure drop amplitude value. Because the fluctuation of water flow is slower than the fluctuation of water pressure, the scheme of the invention can effectively reduce the switching frequency of the variable-frequency pump set, thereby reducing the work load of the variable-frequency pump set, and being beneficial to energy conservation and health of a water supply pipeline.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a variable-pressure control optimization method of a residential secondary water supply variable-frequency pump unit, which is disclosed by the embodiment of the invention.
FIG. 2 is a flow chart of a method of constructing a training data set in accordance with an embodiment of the present invention.
Fig. 3 is a flowchart of a method for generating a variable frequency control strategy according to an embodiment of the present invention.
Fig. 4 is a schematic structural diagram of a variable-pressure control optimizing system of a residential secondary water supply variable-frequency pump unit according to an embodiment of the invention.
Detailed Description
Other advantages and advantages of the present application will become apparent to those skilled in the art from the following detailed description, which, by way of illustration, is to be read in connection with certain specific embodiments, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In addition, the technical features of the different embodiments of the present application described below may be combined with each other as long as they do not collide with each other.
As shown in fig. 1, the embodiment of the invention discloses a variable-pressure control optimization method of a residential secondary water supply variable-frequency pump set, which comprises the following method steps: collecting first flow fluctuation data of each water consumption node of a target house, constructing a training data set, and performing fine adjustment on a general large model by using the training data set to obtain a flow fluctuation prediction model special for the target house; receiving second flow fluctuation data of each water consumption node of the target residence, inputting the flow fluctuation prediction model to obtain third flow fluctuation data at the outlet of the variable frequency pump set, and determining a water pressure drop amplitude value according to the third flow fluctuation data and a flow-pressure fluctuation comparison table; and generating a variable frequency control strategy of the variable frequency pump unit according to the water pressure drop amplitude value, and executing the variable frequency control strategy by the secondary water supply variable frequency pump unit to supplement the water pressure drop amplitude value, so that the water pressure in the secondary water supply pipeline is constant.
The method acquires the water flow fluctuation values of all water nodes of the target residence, and all the water flow fluctuation values form a flow fluctuation map of the target residence, wherein the flow fluctuation map characterizes real-time and global detailed fluctuation dynamics of the target residence; meanwhile, the overall fluctuation dynamic is processed by using a pre-trained flow fluctuation prediction model, so that the flow fluctuation at the outlet of the variable-frequency pump set corresponding to the overall fluctuation dynamic is predicted, namely, the flow fluctuation at the total secondary water supply node is predicted according to the flow fluctuation of all water nodes; and then, performing comparison matching according to a flow-pressure fluctuation comparison table to obtain the water pressure drop amplitude value at the total secondary water supply node. After the water pressure drop amplitude value at the secondary water supply total node is determined, a variable frequency control strategy of the variable frequency pump set can be adaptively generated, and the variable frequency control strategy is executed by the secondary water supply variable frequency pump set to compensate the water pressure drop amplitude value, so that the water pressure in the secondary water supply pipeline is constant.
Compared with the traditional mode of controlling the variable-frequency pump set by depending on water pressure, the scheme of the invention has the improvement points that the water flow fluctuation at the total secondary water supply node is predicted based on the water flow fluctuation of all water consumption nodes, and the predicted water flow fluctuation is converted into the water pressure drop amplitude value at the total secondary water supply node, so that the constant water pressure in the secondary water supply pipeline can be realized by regulating and controlling the variable-frequency pump set to compensate the water pressure drop amplitude value. Because the fluctuation of water flow is slower than the fluctuation of water pressure, the scheme of the invention can effectively reduce the switching frequency of the variable-frequency pump set, thereby reducing the work load of the variable-frequency pump set, and being beneficial to energy conservation and health of a water supply pipeline.
Each water node refers to all water nodes belonging to a secondary water supply area (e.g., 7 or more floors) in the target house. The main indoor pipeline is internally provided with water flow sensors, each indoor water consumption node is provided with a water flow sensor, and the water flow sensors can transmit the flow fluctuation data obtained by detection to the secondary water supply control equipment in a wired or wireless mode.
The general large model in the present invention refers to an existing model such as GPT (GENERATIVE PRE-trained Transformer) series 、Claude-3、GLM (Generative Language Model)-4、BERT (Bidirectional Encoder Representations from Transformers)、PaLM (Pathways Language Model)、LLaMA (Large Language Model Meta AI). These generic large models need to be trained using specialized training data to achieve fine tuning before they can be used to arrive at the flow fluctuation predictive model of the present invention.
Optionally, as shown in fig. 2, collecting first flow fluctuation data of each water node of the target residence to construct a training data set includes: collecting first flow fluctuation data and corresponding fourth flow fluctuation data of each water consumption node of a target residence, and dividing each first flow fluctuation data into outdoor data and indoor data according to the attribute of the acquisition point; the fourth flow fluctuation data are flow data at the outlet of the variable-frequency pump set, which correspond to the third flow fluctuation data; constructing the training data set by taking the outdoor data as a main body and taking the indoor data as an auxiliary strategy; wherein the training data set comprises a high duty cycle of the outdoor data and a low duty cycle of the indoor data.
In this embodiment, in order to implement fine tuning of the general large model, the present invention collects first flow fluctuation data of the target residence and corresponding fourth flow fluctuation data, where the first flow fluctuation data refers to flow fluctuation values of water nodes of the target residence, and the fourth flow fluctuation data refers to flow fluctuation values at outlets of the secondary water supply variable frequency pump units corresponding to the flow fluctuation values, and corresponds to the aforementioned third flow fluctuation data. Meanwhile, the water flow sensor can be arranged at a main household pipeline, namely a main household pipeline, or at each subduction in a house, so that the first flow fluctuation data can be divided into outdoor data and indoor data according to the attribute of the acquisition point.
Since both types of data exist, the invention mixes the two types of data to make the flow fluctuation prediction model have more accurate prediction capability. Meanwhile, when the number of data nodes in the flow fluctuation map is too large, the calculation load of the third flow fluctuation data is obviously increased, the prediction timeliness is insufficient, and the timely compensation of the water pressure is not facilitated, so that the outdoor data is taken as the main data, the indoor data is taken as the auxiliary data, namely, the outdoor data is in a higher proportion in the training data set.
Optionally, the time of collection of the fourth flow fluctuation data is determined by the following manner: calculating the shortest pipeline distance between the acquisition point of each first flow fluctuation data and the outlet of the variable frequency pump set, determining a weighted weight of the first acquisition time of the first flow fluctuation data according to the shortest pipeline distance, and calculating a weighted average of the first acquisition time according to the weighted weight to obtain an equivalent acquisition time; calculating the variance of the distance between the shortest pipelines, and determining the duration of the interference deviation according to the variance; and adding the interference deviation time length to the equivalent acquisition time to obtain the acquisition time of the fourth flow fluctuation data, namely a second acquisition time.
In this embodiment, since the fluctuation of the water flow has a certain hysteresis, that is, when the water flow of the downstream water node fluctuates, the upstream water supply point will detect the water flow fluctuation after a certain delay, so that the fourth flow fluctuation data detected after the delay appropriately can more truly represent the influence of the water flow fluctuation of the downstream water node on the water flow fluctuation caused by the upstream water supply point.
The method comprises the steps of determining a weighted weight corresponding to first collection time according to the shortest pipeline distance between the collection point of each first flow fluctuation data and the outlet of a variable frequency pump set, and carrying out weighted averaging on each first collection time by using the weighted weight to obtain an equivalent collection time which can represent the whole collection time of all the first flow fluctuation data. Meanwhile, the backward influence of the water flow is also influenced by the pipeline distances, so the invention also calculates the fluctuation of each shortest pipeline distance, namely the variance, determines the interference deviation time length (for example, 1.5 s) according to the variance, and obtains the second acquisition time of the fourth flow fluctuation data by adding the equivalent acquisition time to the interference deviation time length.
The relation between the interference deviation time length and the variance should conform to a positive correlation function, namely, the larger the variance is, the larger the difference representing the length of the shortest pipe is, the larger the influence of the pipe distance on the water flow is on the back transmission, and the larger the interference deviation time length is correspondingly set, namely, the fourth flow fluctuation data is acquired after the delay. The positive correlation function may also take the form of a look-up table, which is not limited.
It should be noted that, the hysteresis of the water flow fluctuation is affected by factors such as the length of the pipe, the layout of the pipe (bending, branching, changing of height, etc.), the operation of the valve (opening or closing of the valve changes the water flow path and speed, affects the time difference), and the like, in addition, the hysteresis is affected by the accuracy of the water flow sensor at the secondary water supply device, when the accuracy of the water flow sensor is insufficient, the initial time of the water flow change at the secondary water supply device cannot be detected in time, but only when the water flow change is large enough, so that hysteresis occurs.
Optionally, as shown in fig. 3, the variable-frequency control strategy for generating the variable-frequency pump set according to the water pressure drop value includes: acquiring a first number of currently running variable frequency pumps, real-time rotating speeds of all variable frequency pumps and an adjustable rotating speed interval of a single variable frequency pump; and performing predictive analysis on the data and the water pressure drop value by using a convolution network to obtain the second number of variable frequency pumps to be started and the target rotating speed of each variable frequency pump, and obtaining the variable frequency control strategy.
In this embodiment, the first number of currently running variable frequency pumps, the real-time rotational speed of each variable frequency pump, is available in real time, while the adjustable rotational speed interval of a single variable frequency pump is nominal. And processing the data and the obtained water pressure drop value by using a preset convolution network to obtain a variable frequency control strategy, wherein the variable frequency control strategy comprises a second number of variable frequency pumps which need to be started and target rotating speeds of all the variable frequency pumps.
Optionally, the convolution network comprises a convolution layer, an activation layer, a pooling layer and a full connection layer which are sequentially connected; the convolution layer is used for carrying out first feature extraction on the first quantity, each real-time rotating speed and the adjustable rotating speed interval; the activation layer is used for introducing a nonlinear function to perform function mapping on the first characteristic extraction and the water pressure drop value so as to obtain a second characteristic; the pooling layer is used for reducing the space dimension of the second feature; the full-connection layer is used for comprehensively processing the first characteristics and the second characteristics processed by the pooling layer to obtain prediction results, namely the second number of variable frequency pumps needing to be started and the target rotating speed of each variable frequency pump.
In this embodiment, the convolution network in the present invention includes a convolution layer, an activation layer, a pooling layer, and a full connection layer that are sequentially connected. Through the mutual cooperation of the layers, the relation between the number of the variable frequency pumps, the rotating speed and the water pressure compensation capacity can be excavated by the convolution network, and the adjustable rotating speed interval of the single water variable frequency pump is further considered, so that the second number of the variable frequency pumps which need to be started and the target rotating speed of each variable frequency pump can be determined. For example, when a single variable frequency pump can compensate the water pressure drop value by increasing the rotation speed, other variable frequency pumps are not required to be started, otherwise, other variable frequency pumps are required to be started.
Optionally, the convolutional network is a residual convolutional network.
In the embodiment, the convolution network comprises a plurality of convolution types such as standard convolution, deep convolution, deconvolution, residual convolution network and the like, and actual tests show that the residual convolution network solves the gradient disappearance problem in deep network training by adding jump connection, so that the actual prediction accuracy is obviously higher. Therefore, the present invention preferably uses a residual convolution network to predict the second number of variable frequency pumps that need to be turned on, the target rotational speed of each variable frequency pump.
Referring to FIG. 4, the invention also discloses a variable-pressure control optimizing system of the residential secondary water supply variable-frequency pump unit, which comprises a training module, a prediction module and a variable-frequency pump unit control module; the training module is used for collecting first flow fluctuation data of each water consumption node of the target residence, constructing a training data set, and performing fine adjustment on the general large model by using the training data set to obtain a flow fluctuation prediction model special for the target residence; the prediction module is used for receiving second flow fluctuation data of each water consumption node of the target residence, inputting the flow fluctuation prediction model to obtain third flow fluctuation data at the outlet of the variable frequency pump set, and determining a water outlet pressure drop amplitude value according to the third flow fluctuation data and a flow-pressure fluctuation comparison table; the variable frequency pump set control module is used for generating a variable frequency control strategy of the variable frequency pump set according to the water pressure drop amplitude value, and the secondary water supply variable frequency pump set executes the variable frequency control strategy to supplement the water pressure drop amplitude value, so that the water pressure in the secondary water supply pipeline is constant.
The invention also discloses an electronic device, which comprises: at least one processor, a memory and a computer program stored in the memory and executable on the at least one processor, which when executed by the processor, performs the method steps for the processing apparatus as described in any of the preceding claims.
The invention also discloses a computer storage medium storing a computer program executable by a processor to implement the method of any one of the preceding claims.
The invention also discloses a computer program product comprising a computer program executable by a processor to implement the method according to any of the preceding claims.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The present invention is not limited to the above embodiments, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the present invention, and these modifications and substitutions are intended to be included in the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. The variable-pressure control optimization method of the residential secondary water supply variable-frequency pump set is characterized by comprising the following steps of: collecting first flow fluctuation data of each water consumption node of a target house, constructing a training data set, and performing fine adjustment on a general large model by using the training data set to obtain a flow fluctuation prediction model special for the target house; receiving second flow fluctuation data of each water consumption node of the target residence, inputting the flow fluctuation prediction model to obtain third flow fluctuation data at the outlet of the variable frequency pump set, and determining a water pressure drop amplitude value according to the third flow fluctuation data and a flow-pressure fluctuation comparison table; and generating a variable frequency control strategy of the variable frequency pump unit according to the water pressure drop amplitude value, and executing the variable frequency control strategy by the secondary water supply variable frequency pump unit to supplement the water pressure drop amplitude value, so that the water pressure in the secondary water supply pipeline is constant.
2. The method for optimizing the variable-pressure control of the residential secondary water supply variable-frequency pump unit according to claim 1, which is characterized in that: collecting first flow fluctuation data of each water consumption node of the target house to construct a training data set, comprising: collecting first flow fluctuation data and corresponding fourth flow fluctuation data of each water consumption node of a target residence, and dividing each first flow fluctuation data into outdoor data and indoor data according to the attribute of the acquisition point; the fourth flow fluctuation data are flow data at the outlet of the variable-frequency pump set, which correspond to the third flow fluctuation data; constructing the training data set by taking the outdoor data as a main body and taking the indoor data as an auxiliary strategy; wherein the training data set comprises a high duty cycle of the outdoor data and a low duty cycle of the indoor data.
3. The method for optimizing the variable-pressure control of the residential secondary water supply variable-frequency pump unit according to claim 2, which is characterized in that: the collection time of the fourth flow fluctuation data is determined by the following method: calculating the shortest pipeline distance between the acquisition point of each first flow fluctuation data and the outlet of the variable frequency pump set, determining a weighted weight of the first acquisition time of the first flow fluctuation data according to the shortest pipeline distance, and calculating a weighted average of the first acquisition time according to the weighted weight to obtain an equivalent acquisition time; calculating the variance of the distance between the shortest pipelines, and determining the duration of the interference deviation according to the variance; and adding the interference deviation time length to the equivalent acquisition time to obtain the acquisition time of the fourth flow fluctuation data, namely a second acquisition time.
4. The method for optimizing the variable-pressure control of the residential secondary water supply variable-frequency pump unit according to claim 3, wherein the method comprises the following steps of: the frequency conversion control strategy for generating the frequency conversion pump set according to the water pressure drop value comprises the following steps: acquiring a first number of currently running variable frequency pumps, real-time rotating speeds of all variable frequency pumps and an adjustable rotating speed interval of a single variable frequency pump; and performing predictive analysis on the data and the water pressure drop value by using a convolution network to obtain the second number of variable frequency pumps to be started and the target rotating speed of each variable frequency pump, and obtaining the variable frequency control strategy.
5. The method for optimizing the variable-pressure control of the residential secondary water supply variable-frequency pump unit according to claim 4, which is characterized in that: the convolution network comprises a convolution layer, an activation layer, a pooling layer and a full connection layer which are sequentially connected; the convolution layer is used for carrying out first feature extraction on the first quantity, each real-time rotating speed and the adjustable rotating speed interval; the activation layer is used for introducing a nonlinear function to perform function mapping on the first characteristic extraction and the water pressure drop value so as to obtain a second characteristic; the pooling layer is used for reducing the space dimension of the second feature; the full-connection layer is used for comprehensively processing the first characteristics and the second characteristics processed by the pooling layer to obtain prediction results, namely the second number of variable frequency pumps needing to be started and the target rotating speed of each variable frequency pump.
6. The method for optimizing the variable-pressure control of the residential secondary water supply variable-frequency pump unit according to claim 5, which is characterized in that: the convolutional network is a residual convolutional network.
7. A transformation control optimizing system of a residential secondary water supply variable frequency pump set is characterized in that: the system comprises a training module, a prediction module and a variable frequency pump set control module; the training module is used for collecting first flow fluctuation data of each water consumption node of the target residence, constructing a training data set, and performing fine adjustment on the general large model by using the training data set to obtain a flow fluctuation prediction model special for the target residence; the prediction module is used for receiving second flow fluctuation data of each water consumption node of the target residence, inputting the flow fluctuation prediction model to obtain third flow fluctuation data at the outlet of the variable frequency pump set, and determining a water outlet pressure drop amplitude value according to the third flow fluctuation data and a flow-pressure fluctuation comparison table; the variable frequency pump set control module is used for generating a variable frequency control strategy of the variable frequency pump set according to the water pressure drop amplitude value, and the secondary water supply variable frequency pump set executes the variable frequency control strategy to supplement the water pressure drop amplitude value, so that the water pressure in the secondary water supply pipeline is constant.
8. An electronic device, characterized in that: the electronic device includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, which when executed by the processor, implements the method of any of claims 1-6.
9. A computer storage medium, characterized by: the computer storage medium stores a computer program executable by a processor to implement the method of any of claims 1-6.
10. A computer program product, characterized by: the computer program product comprising a computer program executable by a processor to implement the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410805367.4A CN118375600B (en) | 2024-06-21 | 2024-06-21 | Variable-pressure control optimization system and method for residential secondary water supply variable-frequency pump set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410805367.4A CN118375600B (en) | 2024-06-21 | 2024-06-21 | Variable-pressure control optimization system and method for residential secondary water supply variable-frequency pump set |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118375600A true CN118375600A (en) | 2024-07-23 |
| CN118375600B CN118375600B (en) | 2024-09-06 |
Family
ID=91906015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410805367.4A Active CN118375600B (en) | 2024-06-21 | 2024-06-21 | Variable-pressure control optimization system and method for residential secondary water supply variable-frequency pump set |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118375600B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105951931A (en) * | 2016-05-12 | 2016-09-21 | 平玉兰 | Intelligent secondary water supply equipment based on internet of things |
| US20190390445A1 (en) * | 2018-06-21 | 2019-12-26 | Grundfos Holding A/S | Control system and method for controlling a water supply from at least two separate input lines into a sector of a water supply network |
| CN111325306A (en) * | 2020-02-05 | 2020-06-23 | 河北工程大学 | ABC-PSO hybrid algorithm-based water supply pump set scheduling method |
| CN112526868A (en) * | 2020-11-17 | 2021-03-19 | 海南蓝宇科技有限公司 | Control method of secondary pressurization domestic water supply system |
| CN113688973A (en) * | 2021-07-13 | 2021-11-23 | 同济大学 | Water supply pump station scheduling method based on deep neural network |
| CN117313948A (en) * | 2023-10-23 | 2023-12-29 | 河海大学 | Optimal allocation method for secondary water supply pump set |
-
2024
- 2024-06-21 CN CN202410805367.4A patent/CN118375600B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105951931A (en) * | 2016-05-12 | 2016-09-21 | 平玉兰 | Intelligent secondary water supply equipment based on internet of things |
| US20190390445A1 (en) * | 2018-06-21 | 2019-12-26 | Grundfos Holding A/S | Control system and method for controlling a water supply from at least two separate input lines into a sector of a water supply network |
| CN111325306A (en) * | 2020-02-05 | 2020-06-23 | 河北工程大学 | ABC-PSO hybrid algorithm-based water supply pump set scheduling method |
| CN112526868A (en) * | 2020-11-17 | 2021-03-19 | 海南蓝宇科技有限公司 | Control method of secondary pressurization domestic water supply system |
| CN113688973A (en) * | 2021-07-13 | 2021-11-23 | 同济大学 | Water supply pump station scheduling method based on deep neural network |
| CN117313948A (en) * | 2023-10-23 | 2023-12-29 | 河海大学 | Optimal allocation method for secondary water supply pump set |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118375600B (en) | 2024-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109708258B (en) | Refrigeration house temperature feedforward-fuzzy control system and control method based on load dynamic change | |
| CN108916986B (en) | Information physical fusion secondary pipe network variable flow hydraulic balance regulation and control method and system | |
| CN101901014B (en) | Method for controlling forecast pressure regulation in air compression stations | |
| CN103912966B (en) | A kind of earth source heat pump refrigeration system optimal control method | |
| CN110392515A (en) | A kind of Cooling and Heat Source equipment room energy-conserving control method and system based on historical data | |
| CN110793173B (en) | Water pump frequency conversion control method based on dynamic change of worst air conditioner tail end | |
| CN101526260A (en) | Variable-frequency air-conditioner control method and control device thereof | |
| CN102003772A (en) | Energy-saving optimized control method of water source heat pump | |
| CN104636800A (en) | Freezing station system neural network optimization unit based on least square weighted and method thereof | |
| CN116680661A (en) | Multi-dimensional data-based automatic gas regulator pressure monitoring method | |
| CN111972991A (en) | Hot water treatment device and control method and device thereof | |
| CN110928215B (en) | Intelligent control system and control method for oilfield water mixing pipe network | |
| CN118375600B (en) | Variable-pressure control optimization system and method for residential secondary water supply variable-frequency pump set | |
| CN110779132A (en) | Water pump equipment operation control system of air conditioning system based on reinforcement learning | |
| Li et al. | Improving room temperature stability and operation efficiency using a model predictive control method for a district heating station | |
| CN113899125A (en) | High-temperature steam heat pump control method based on economic prediction control | |
| CN111664560B (en) | Intelligent energy-saving control method for central air-conditioning host | |
| CN118111078A (en) | Control method and device of air conditioning system, storage medium and air conditioning system | |
| CN109983284B (en) | Air conditioning system based on variable frequency compressor and control method thereof | |
| CN107421190A (en) | The control method and device of refrigerator and wherein condensation fan | |
| US20240288179A1 (en) | Acquiring a user consumption pattern of domestic hot water and controlling domestic hot water production based thereon | |
| CN109189030A (en) | A kind of accumulation of heat tele-control system towards multipotency source supply system | |
| EP3839359A1 (en) | Monitoring and controlling domestic hot water production and distribution | |
| CN208205284U (en) | A kind of air-conditioning system based on region energy balance | |
| CN117606129B (en) | Control method and device for parallel connection of multiple variable-frequency chilled water pumps with same model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |