GB2608476A - Intelligent parallel pumping system and optimal regulating method thereof - Google Patents

Intelligent parallel pumping system and optimal regulating method thereof Download PDF

Info

Publication number
GB2608476A
GB2608476A GB2116859.6A GB202116859A GB2608476A GB 2608476 A GB2608476 A GB 2608476A GB 202116859 A GB202116859 A GB 202116859A GB 2608476 A GB2608476 A GB 2608476A
Authority
GB
United Kingdom
Prior art keywords
pumping system
optimization
pump
vibration
data
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
Application number
GB2116859.6A
Other versions
GB202116859D0 (en
GB2608476B (en
Inventor
Wenjie Wang
Xiaobo Gong
Ji Pei
Shouqi Yuan
Xing Cheng Gan
Qifan Deng
Chenying Zhang
Jinfeng Zhang
Jianping Yuan
Yanjun Li
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu University
Original Assignee
Jiangsu University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu University filed Critical Jiangsu University
Publication of GB202116859D0 publication Critical patent/GB202116859D0/en
Publication of GB2608476A publication Critical patent/GB2608476A/en
Application granted granted Critical
Publication of GB2608476B publication Critical patent/GB2608476B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
    • F04D—NON-POSITIVE-DISPLACEMENT PUMPS
    • F04D15/00—Control, e.g. regulation, of pumps, pumping installations or systems
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
    • F04D—NON-POSITIVE-DISPLACEMENT PUMPS
    • F04D15/00—Control, e.g. regulation, of pumps, pumping installations or systems
    • F04D15/02—Stopping of pumps, or operating valves, on occurrence of unwanted conditions
    • F04D15/029—Stopping of pumps, or operating valves, on occurrence of unwanted conditions for pumps operating in parallel
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
    • F04D—NON-POSITIVE-DISPLACEMENT PUMPS
    • F04D13/00—Pumping installations or systems
    • F04D13/12—Combinations of two or more pumps
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
    • F04D—NON-POSITIVE-DISPLACEMENT PUMPS
    • F04D15/00—Control, e.g. regulation, of pumps, pumping installations or systems
    • F04D15/0066—Control, e.g. regulation, of pumps, pumping installations or systems by changing the speed, e.g. of the driving engine
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
    • F04D—NON-POSITIVE-DISPLACEMENT PUMPS
    • F04D15/00—Control, e.g. regulation, of pumps, pumping installations or systems
    • F04D15/0088—Testing machines
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
    • F04D—NON-POSITIVE-DISPLACEMENT PUMPS
    • F04D25/00—Pumping installations or systems
    • F04D25/16—Combinations of two or more pumps ; Producing two or more separate gas flows
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
    • F04D—NON-POSITIVE-DISPLACEMENT PUMPS
    • F04D29/00—Details, component parts, or accessories
    • F04D29/66—Combating cavitation, whirls, noise, vibration or the like; Balancing
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/0985—Hyperparameter optimisation; Meta-learning; Learning-to-learn
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05D—INDEXING SCHEME FOR ASPECTS RELATING TO NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, GAS-TURBINES OR JET-PROPULSION PLANTS
    • F05D2260/00—Function
    • F05D2260/96—Preventing, counteracting or reducing vibration or noise
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05D—INDEXING SCHEME FOR ASPECTS RELATING TO NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, GAS-TURBINES OR JET-PROPULSION PLANTS
    • F05D2270/00—Control
    • F05D2270/01—Purpose of the control system
    • F05D2270/20—Purpose of the control system to optimize the performance of a machine
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05D—INDEXING SCHEME FOR ASPECTS RELATING TO NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, GAS-TURBINES OR JET-PROPULSION PLANTS
    • F05D2270/00—Control
    • F05D2270/30—Control parameters, e.g. input parameters
    • F05D2270/301—Pressure
    • F05D2270/3011—Inlet pressure
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05D—INDEXING SCHEME FOR ASPECTS RELATING TO NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, GAS-TURBINES OR JET-PROPULSION PLANTS
    • F05D2270/00—Control
    • F05D2270/30—Control parameters, e.g. input parameters
    • F05D2270/301—Pressure
    • F05D2270/3013—Outlet pressure
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05D—INDEXING SCHEME FOR ASPECTS RELATING TO NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, GAS-TURBINES OR JET-PROPULSION PLANTS
    • F05D2270/00—Control
    • F05D2270/30—Control parameters, e.g. input parameters
    • F05D2270/306—Mass flow
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05D—INDEXING SCHEME FOR ASPECTS RELATING TO NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, GAS-TURBINES OR JET-PROPULSION PLANTS
    • F05D2270/00—Control
    • F05D2270/30—Control parameters, e.g. input parameters
    • F05D2270/334—Vibration measurements
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05D—INDEXING SCHEME FOR ASPECTS RELATING TO NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, GAS-TURBINES OR JET-PROPULSION PLANTS
    • F05D2270/00—Control
    • F05D2270/80—Devices generating input signals, e.g. transducers, sensors, cameras or strain gauges
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/08—Fluids
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/09—Supervised learning

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Automation & Control Theory (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Control Of Positive-Displacement Pumps (AREA)
  • Control Of Non-Positive-Displacement Pumps (AREA)

Abstract

An intelligent parallel pumping system and an optimal regulating method. The system mainly comprises a pumping system, a data acquiring unit, a data processing unit, a target optimizing unit and an optimization algorithm solution unit. The method includes data acquiring, data processing, establishing optimization target and optimization model. According to the invention, the BP neural network is trained through the historical operation data of the pumping system, including flow rate, lift, rotating speed, valve opening and pump vibration signal under various working conditions, and the obtained neural network model is taken as an optimization objective function; the optimization model is solved by particle swarm optimization algorithm, and the optimal regulation scheme with minimum vibration of pumping system is obtained under specific demand conditions.

Description

Intelligent Parallel Pumping System and Optimal Regulating Method Thereof
TECHNICAL FIELD
The invention relates to the field of optimal regulation of pumping systems; in particular to an intelligent parallel pumping system and an optimal regulating method thereof.
BACKGROUND
As a kind of general rotating machinery, water pumping equipment has been widely used in all walks of life, such as national defense construction, petrochemical industry, electric power sectors and civil and commercial water use. With the rapid improvement of modern industrial" pumps are developed to be integrated and large-scale. As the mechanism of the pump is becoming increasingly complex, once the pump breaks down, the fault will not only lead to equipment breakdown, but also even cause a devastating blow to the whole production system. The breakdown is caused by many reasons. For example, when the pump runs for a lc_iliff time under vibrating conditions, all parts and components of the pump are likely to break down, which will eventually lead to faults, resulting in damage to machine pails, so the pump should be halted for check and even replacement. In severe cases; explosion and other hazards may be triggered. It can be seen that the failure of the pump not only causes huge economic losses, but also may lead to serious safety accidents and endanger the lives of workers.
On the pump flow and head performance curve, except the design working condition area, all the other areas are non-design working condition areas. The actual working point of the pump is determined by the intersection of the flow head characteristic curve of the pump and the resistance characteristic curve of the pipeline. Therefore, at a given rotation speed, the pump is at the best working point only at a certain flow rate, and at this time the efficiency of the pump reaches the maximum and the vibration of the pump is generally the smallest. When the pump runs in the non-design working condition area, the flow in the pump is complicated, which is no longer the ideal flow assumed by the design working condition, and may be accompanied by noise, vibration and other phenomena. In this case, the centrifugal pump runs unsteadily or even breaks down. Therefore, in the practical operation of centrifugal pump, it is necessary to ensure that the working point of centrifugal system is close to the design working point and reduce the vibration of the pump during operation, so as to improve the operational reliability of centrifugal pump and prolong the service life of pump and other parts.
SUMMARY
The objective of the present inventioti is to provide an intelligent parallel pumping system with a low vibration and reliable operation adjustment strategy and an optimization method, so as to realize that the pumping system can give an optimal regulating scheme when the working condition changes, and control the pump unit to perform optimal regulation, so that the pumping system can minimize vibration under the working condition when meeting the demand.
To achieve the above objective, the present invention provides the following scheme An intelligent parallel pumping system comprises a pumping system, a data acquiring unit, a data processing unit, a target optimizing unit and an optimization algorithm solution unit; the pumping system is a pipelinem fbrmed by water pump and auxiliary equipment in parallel; the data acquiring unit is used for collecting signals collected by various sensors in parallel pumping system; the data processing unit is used for processing the signals collected by the data acquiring unit; the target optimizing unit is used for dividing the processed data to provide an optimization target and an optimization model for the pumping system optimization method based on reducing the vibration of the water pump in the running state; and the optimization algorithm solution unit is used for solving the optimization model to obtain an optimized control scheme.
Preferably, the pumping system comprises: a water pump used to pressurize water to meet the user's requirements; a pipeline system used to configure and connect various components; various sensors used to collect various data; an electric valve used to adjust water flow; a check valve used to prevent water from flowingback; bypass pipeline used to transfer excess water to the return pipeline and adjust the water flow.
Preferably, the various sensors comprise: a flow meter used to collect the single pump flow on each branch pipe of he parallel pump group and the total flow of the pump station on the main pipe; a pressure sensor used to collect pressures at the inlet and outlet of each single pump and the inlet and outlet pressures on the main pipeline, and obtain the head of each single pump and the total head of the pumping station; vibration sensor used to collect vibration signals of monitoring points on the pump.
Preferably, the signals of all kinds of sensors are collected by NI data acquiring Preferably, the data collected by the data acquiring unit Maher comprises the frequency converter outputs the current frequency signal of each single pump, and the electric valve outputs the opening signal of each valve.
Preferably, the data processing unit includes noise reduction processing, time-frequency domain analysis and vibration feature extraction for vibration_ signals.
The optimal regulating method of an intelligent parallel pumping system comprises the following steps: data acquiring: collecting vibration signals of monitoring points on the pumping system, total flow of pumping stations on the parallel pump group, inlet and outlet pressures of each single pump, inlet and outlet pressures on the main pipeline, and current frequency signals of each pump and opening signals of each valve; S2, data processing: carrying out noise reduction processing on the collected vibration signals of the monitoring points, carrying out time-frequency domain analysis on the data after noise reduction, and finally extracting vibration characteristic quantities based on the data after time-frequency domain anal S3, establishing an optimization target and an optimization model: solving he optimization model through an optimization algorithm to obtain an optimal value. Preferably, the process of establishing the optimization target includes: S3.1, dividing the historical operation data set of the pump station, wherein the historical operation data set of the pump station comprises the flow rate, the lift, the pump revolution, the valve opening and the characteristic quantity of the vibration signal of the monitoring point under each working condition during the operation of the historical pump station; dividing the data set into training sample and prediction sample; S3.2, training the data set through a BP neural network, wherein the BP neural network performs fitting training on the divided data set, and takes the flow rate, the lift, pump revolution and valve opening as the input of the BP neural network while the vibration characteristic quantity as the output of the BP neural network; S3.3, optimizing the relevant hyperparameters of the BP neural network through an intelligent optimization algorithm, and taking the number of hidden layers, the number of units of each hidden layer, the activation function and the learning step as the input of the optimization, and taking the IR± value of the decision coefficient fitted by the BP neural network as the output; and S3.4, continuously optimizing the relevant hyperparameters through an optimization algorithm until a certain fitting accuracy is achieved; and outputting a neural network model trained under the setting of the hyperparameters as an optimization target.
Preferably, the steps of establishing the optimization model include: establishing the optimization target of the pumping system and setting the boundary conditions for solution; the optimization objective of establishing the pumping system is to establish an optimization objective formula of the pumping system according to the principle of m vibration: min F in which, . is whether the current water pump is turned on, is the vibration characteristic quantity corresponding to the water pump, and the sum of the vibration characteristic quantities of all the water pumps is the total vibration characteristic quantity under the current pumping system, N is the total number of pumps in the pumping system, and min.17 is the pumping system optimization goal of the intelligent parallel pumping system with low vibration and reliable operation regulation strategy.
The boundary conditions kw solution eludes: constraint on the number of pumps started: the number of pumps put into operation shall not exceed the total number of pumps in the pumping system; speed ratio constraint: the minimum speed ratio of the pump is not-smaller han 0.5 and the maximum speed ratio of the pump is not bigger than 1; total flow constraint: the total flow provided by the pumping system is not less than the flow required by users; total lift constraint: the minimum lift provided by the pumping system is not smaller than the required lift of users.: total vibration constraint: the total vibration of the pumping system is not bigger than the specified maximum vibration.
Preferably. the PSO algorithm is used to solve the optimIzation mock Inch specifically includes: step 1, determining parameters and search space: after determining optimized parameters, delimiting the search space of each parameter, and taking flow rate, lift, pump revolution and valve opening as optimized parameters; step 2, initializing particle swarm: a group of solutions randomly generated in solution space for initial calculation; step 3, calculating the fitness of each particle, which is the vibration value predicted by the system obtained by the optimization target of the pumping system; step 4, updating the optimal particles and their speed and position: updating individual optimal and global optimal particles according to fitness, updating the speed and position of particles, and providing a new solution fix the next calculation; and step 5, judging whether the algorithm termination conditions are met: judging Whether the maximum number of iterations is reached or the global optimal position meets the minimum limit; otherwise, continuing, iterative optimization until the judgment conditions are met to output the optimal value_ The invention ha.s the following beneficial effects, According to the invention, the BP neural network is trained through the historical operation data of the pumping system including flow rate, lift, rotating speed, valve opening and pump vibration signal under various working conditions, and the obtained neural network model is taken as an optimization objective function; the optimization model is solved by particle swarm optimization algorithm, and the optimal regulation scheme with minimum vibration of pumping system is obtained under specific demand conditions.
BRIEF DESCRIPTION OF THE FIGURES
In order to explain the embodiments of the present invention or the technical scheme in the prior art more clearly, the following will briefly introduce the drawings used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained according to these drawings without paying creative labour.
FIG. 1 is the overall block diagram of the intelligent parallel pumping system of the present invention; FIG 2 is a block diagram of the data acquiring system of the intelligent parallel pumping system of the present invention; FIG. 3 is a flow chart of vibration signal processing of the intelligent parallel pumping system of the present invention; HG. 4 is a mechanism block diagram ofestablishing: an objective function of the intelligent parallel pumping system of the present invention, FIG. 5 is a block diagram of solving mechanism of PSO optimization algorithm for intelligent parallel pumping system of the present invention.
DESCRIPTION OF THE [INVENTION
the following will clearly and completely describe the technical scheme in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the field without creative labour belong to the scope of protection of the present invention.
In order to make the above objectives, features and advantages of the present invention more obvious and easier to understand; the present invention will be further explained in detail with reference to the drawings and specific embodiments.
FIG. 1 is the overall block diagram of the intelligent parallel pumping system, ecifically includes: a pumping system; a data acquiring unit, a data processing unit, a target optimizing unit and an optimization algorithm solution unit; the pumping system includes pump unit, pipeline system, various sensors, electrically controlled valves and other auxiliary equipment; the data acquiring unit is responsible fix acquiring the signal data needed ter the optimization of the parallel pumping system; the data processing unit is responsible for processing the signals collected by the data acquiring unit, including vibration signal, flow rate, pressure, rotating speed, valve opening, , the optimization unit provides an optimization target and an optimization model for the optimization method of the parallel pumping system based on reducing the vibration of the pump in the running state; the algorithm solving unit solves the optimization model by heuristic optimization algorithm, and thus obtains the optimal control scheme.
The pumping system comprises a water pump, a pipeline system; various sensors, electrically controlled valves and other safety auxiliary equipment. The water pump is
S
used to pressurize water to meet the user's requirements. The pipeline system is used to configure and connect various components, and thus integrates the components; sensors are used to collect various data, including flow meters for monitoring water flow, pressure sensors for monitoring water inlet and outlet pressure, and vibration sensors for collecting vibration of monitoring points. The electric valve adjusts the water flow by adjusting the opening of the valve; check valves are used to prevent water from flowing back, and bypass pipeline is used to transfer excess water back to pipeline and adjust water flow With reference to FIG. 2, the data acquiring unit of the intelligent parallel pumping system comprises various sensors and Ni data acquiring card. All kinds of sensors are hardware equipment to collect data for setting up the optimization method of parallel pumping system to reduce the vibration of water pump in running state, mainly including vibration sensors, electromagnetic flow meters, pressure sensors, frequency converters, etc. These instruments transmit and convert data through NE data acquiring card. The vibration sensor collects vibration signals of monitor points; the electromagnetic flow meter collects the flow of each single pump on each loop and the total flow of the pump station on the total loop; the pressure sensor collects the inlet and outlet pressures of pumps in each circuit and the inlet and outlet pressures in the total circuit, wherein the difference between the outlet pressure and the inlet pressure is the head of each circuit, and provides the head of each single pump and the total head of the pumping station; The frequency converter is the frequency converter of each single pump, which transmits the working frequency of each single pump, and the electric valve transmits the opening signal of each valve. The collected signals provide a data set for the optimization goal of the parallel pumping system optimization method for reducing the vibration of the pump in operation.
With reference to FIG. 3, a flow chart of vibration signal processing of intelligent parallel pumping system mainly includes noise reduction processing, time-frequency domain analysis and vibration feature extraction. Firstly, the collected vibration signals of monitoring points are de-noised; and then the de-noised data are analysed in time and equency domain. Finally, the vibration features are extracted from the data analysed in time arid frequency domain. By processing the vibration signal through the above steps, the disordered vibration signal can be characterized as the vibration characteristic quantity of the pump under a specific working condition in a specific time period.
The optimal regulating method of an intelligent parallel pumping system, which comprises the following steps: St, data acquiring: including vibration signals of monitoring points on pumps; single pump flow on each branch pipe of the parallel pump group and total flow of pumping stations on the main pipeline, inlet and outlet pressures of each single pump and inlet and outlet pressures on the main pipeline, current frequency signals of each pump and signals of valve openings; S2, data processing: firstly, carrying out noise reduction processing on the collected vibration signals of the monitoring points, then carrying out time-frequency domain analysis on the noise-reduced data, and finally, extracting vibration characteristic quantities through the data after time-frequency domain analysis; S3, establishing an optimization target and an optimization model: solving the optimization model through an optimization algorithm to obtain an optimal value.
With reference to FIG. 4, a mechanism block diagram of establishing the objective function of the intelligent parallel pumping system mainly includes the fbllowing steps: dividing the historical operation data set of the pump station, then training the data set through BP neural network; and optimizing the relevant h Terparameters of the neural network through optimization algorithm until the -fitting precision is reached, and thus outputting the fitting model as the optimization objective function. The historical operation date set of the pump station include flow rate, lift, pump revolution, valve opening and vibration signal characteristic quantity of monitoring points under each working condition when the historical pump station operates; according to the BP neural network, fitting training is carried out on the divided data sets; and flow rate; lift., pump revolution and valve opening are taken as neural network inputs while vibration characteristic quantities are taken as neural network outputs; through the optimization algorithm, the relevant hyperparameters of neural network are optimized. Users can take the number of hidden layers, the number of units in each hidden layer, the activation function and the learning step as the input, and take the R2 value of neural network fitting as the output, until the fitting reaches certain accuracy,and finally output the fitting model as the optimization objective time:from The process of establishing optimization objectives mainly includes the following steps: dividing a historical operation data set of the pump station, wherein the historical operation data set of the pump station includes flow rate, lift, pump rotation number, valve opening degree, vibration signal characteristic quantity of monitoring points and the like at each operating point during the operation of the historical pump station; dividing; the data set into training samples and prediction samples according; to a certain proportion, which is usually 7:3 or 8:2.
S3.2, training the data set through a BP neural network, wherein the BP neural network performs fitting training on the divided data set, and takes the flow rate, the lift, pump revolution and valve opening as the input of the BP neural network while the vibration characteristic quantity as the output ot7 the RP neural network; S3.3, optimizing the algorithm, and optimizing the neural network related hyperparameters: during the training of the neural network, the hyperparameters have a great influence on the accuracy of the model, so the intelligent optimization algorithm can be used to optimize the neural network related hyperparameters, and the user can take the number of hidden layers, the number of units in each hidden layer, the activation function, the learning step as the input of the optimization, '11 take the R' value of the decision coefficient of neural network fitting as the output; S3.4, when the fitting accuracy is achieved, outputting the fitting model as an optimization objective function, continuously optimizing the hyperparameters through an optimization algorithm until a certain fitting accuracy is achieved, and outputting the neural network model trained under the setting of the hyperparameters as an optimization objective.
The process of establishing an optimization model mainly includes: establish n op1imizaton target of pumping system and setting boundary conditions for solution.
The pumping system optimization objective is to establish a pumping system optimization objective formula according to the principle of minimum vibration; min F= in which; je(x) is the fitting model of the BP neural network, x is the parameters of the input neural network, namely, four variables: flow rate, the lift, pump revolution and valve opening. ,f (x) is the predicted value of neural network, namely, the predicted value of the corresponding vibration signal characteristic quantity under these four parameter variables; Al is the current state of water pump opening, 0 corresponds to closing and 1 corresponds to opening; N is the total number of pumps in the pumping system. Therefore, AI/ is whether the current pump is on or not, and./(x) is the corresponding vibration characteri tic quantity of the pump.
The sum of the vibration characteristic quantities of all pumps is the total vibration characteristic quantity of the current pumping system, and min 1/ is the pumping system optimization goal of the intelligent parallel pumping system with low vibration and reliable operation adjustment strategy.
The set boundary conditions for solution: (I) constraint on the number of pumps started the number of pumps put into operation should not exceed the total number of pumps in the pumping system; 0 < Al< N in which is the total number of pumps in.g system and Ni is the number of pumps put into operation; (2) speed ratio constraint: generally, the pump speed ratio, is limited by support heat dissipation, efficiency, etc.; the minimum speed ratio of the pump is usually not smaller than 0.5; and the maximum speed ratio of the pump is usually not bigger than 0.5_,ks".1 total flow constraint: the actual flow of the parallel pumping system is the sum of the flow of all the pumps in operation, and the total flow provided by the pumping system should not be lower than the flow required by the user; = Lo in which -s the flow rate of each pump in operation, 0 flow rate of the parallel pumping system, and the flow rate required by users; (4) total head constraint: The total head of the parallel pumping system provides the difference between the pump head and the system loss, and the minimum head provided by the pumping system should not be lower than the user's demand head; 11 < H in which H is the total head provided by the pump, usis the head loss of the pumping system is the total head provided by the pumping system, and is the head required by users; and (5) total vibration constraint: the total vibration of the pumping system should not be higher than the specified maximum vibration; F <
-
in which is the sum of the vibrations of the running pumps and rrar is the sum of the maximum vibration on strain t values of the running pumps.
The algorithm solution is to solve the pumping system optimization model, and constitute the optimization algorithm solution flow of intelligent parallel pumping system with low vibration and reliable operation regulation strategy.
With reference to FIG. 5, the process of solving the optimization algorithm by PS() algorithm mainly includes the following steps: Step I, determining parameters and search space, and delimiting the search space of each parameter after determining the optimized parameters, wherein the flow rate, the lift, pump revolution and valve opening are taken as the optimized parameters; step 2; initializing particle swarm, which is a group of solutions randomly generated in solution space for initial calculation: step 3, calculating the fitness of each particle, wherein the -fitness is the value of an objective function, that is, the vibration value predicted by the system obtained by the optimization target of the pumping system; step 4, updating the optimal particles and their speed and position, updating individual optimal and global optimal particles according to fitness, and updating the speed and position of particles to provide a new solution for the next calculation; and step 5, judging whether the algorithm termination condition is met, and then judging whether the maximum iteration number is reached or the global optimal position meets the minimum limit, if the condition is not met, continuing iterative optimization until the judgment condition is met, and outputting the optimal value, In this optimization, the input is to find the optimal regulating scheme of flow rate, the lift, pump revolution and valve opening under a certain working condition, and then take it as X after parameterization. The evaluation objective function is the pumping system optimization objective function, that is, the vibration characteristic quantity of the pumping system under this working condition predicted by BP neural network. Finally; the optimal regulating, scheme is obtained when the pumping system is adjusted to the minimum vibration index of the pumping system under a certain working condition.
According to the invention, the BP neural network is trained through the historical operation data of the pumping system, including flow rate, lift, rotating speed, valve opening, pump vibration signal and the like under various working conditions, and the obtained neural network model is taken as an optimization objective function; The optimization model is solved by particle swarm optimization algorithm, and the optimal regulation scheme with minimum vibration of pumping system is obtained under specific demand conditions.
The above-mentioned embodiments are only part descriptions of the preferred mode of the present invention, but do not limit the scope of the present invention. Without departing from the design spirit of the present invention, all kinds of modifications and improvements made by those of ordinary skill in the art to the technical scheme of the present invention shall fall within the protection scope defined by the claims of the present invention.

Claims (9)

  1. THE CLAIMS DEFINING THE INVENTION ARE AS FOLLOWS1. An intelligent parallel pumping system, wherein comprising a pumping system, a data acquiring unit, a data processing unit, a target optimizing unit and an optimization a lgori thin solution unit; the pumping system is a pipeline system formed by a water pump and auxiliary equipment in parallel; the data acquiring unit is used for collecting signals collected by various sensors in the parallel pumping system; the data processing unit is used for processing the signals collected by the data acquiring unit; the target optimizing unit is used for dividing the processed data to provide an optimization target and an optimization model for the pumping system optimization method based on reducing the vibration of the water pump in the running state; and the optimization algorithm solution unit is used for solving the optimization model to obtain an optimized control scheme.
  2. 2. The intelligent parallel pumping system according to claim I, wherein the pumping system comprises: a water pump used to pressurize water to meet the user's requir a pipeline system used to configure and connect various components; various sensors used to collect various data; an electric valve used to adjust water flow; a check valve used to prevent water from flowing back; and a bypass pipeline used to transfer excess water to the return pipeline and adjust the water flow.
  3. 3. The intelligent parallel pumping system according to claim 2, wherein all kinds of sensors include: a flow meter used to collect the single pump flow on each branch pipe of the parallel pump group and the total flow of the pump station on the main pipe; a pressure sensor used to collect pressures at the inlet and outlet of each single pump and the inlet and outlet pressures on the main pipeline, and obtain the head of each single pump and the total head of the pumping station; and a vibration sensor used to collect vibration signals of monitoring points on the pump.
  4. 4. The intelligent parallel pumping system according to claim 3, wherein an Ni data acquiring card acquires data on signals of various sensors.
  5. 5. The intelligent parallel pumping system according to claim I wherein he data collected by the data acquiring unit further comprises: the current frequency signal of each single pump outputted by the frequency converter, and opening signals of each valve outputted by the electric valve.
  6. 6. The intelligent parallel pumping system according to claim I., wherein the data processing unit includes noise reduction processing, time-frequency domain analysis and vibration -feature extraction for vibration signals.
  7. 7. An optimal regulating method -for an intelligent parallel pumping system, comprising the following steps: SI, data acquiring: collecting vibration signals of monitoring points on the pumping system, total flow-of pumping stations on the parallel pump group, inlet and outlet pressures of each single pump, inlet and outlet pressures on the main pipeline, and current frequency signals of each pump and opening signals of each valve; S2, data processing: carrying out noise reduction processing on the collected vibration signals of the monitoring points, carrying out time-frequency domain analysis on the data after noise reduction, and finally extracting vihratio characteristic quantities through the data after time-frequency domain analysis; and S3, establishing an optimization target and an optimization model: solving the optimization model through an optimization algorithm to obtain an optimal value.
  8. 8. The optimal regulating method for an intelligent parallel pumping system according to claim 7, wherein the process of establishing the optimization target includes: S3.1 dividing the historical operation data set of the pump station, wherein the historical operation data set o p station comprises the flow rate: the lift, the pump revolution, the valve opening and the characteristic quantity of the vibration signal of e monitoring point tinder each working condition during the operation of the hist° -;a1 pump station; dividing the data set into training sample and prediction sample; S3.2, training the data set through a BP neural network, wherein the HP neural network performs fitting; training on the divided data set, and takes the flow rate, the lift, pump revolution and valve opening as the input of the BP neural network while the vibration characteristic quantity as the output of the BP neural network; S3.3, optimizing the relevant hyperparameters of the BP neural network through an intelligent optimization algorithm, and taking the number of hidden layers, the number of units of each hidden layer, the activation function and the learning step as the input of the optimization, and taking the PRi value of the decision coefficient fitted by the BP neural network as the output; and S3.4, continuously optimizing the relevant hyperparameters through an optimization algorithm until a certain fitting accuracy is achieved: and outputting a neural network model trained under the setting of the hyperparameters as an optinhization target.
  9. 9. The optimal regulating method of an intelligent parallel pumping system according to claim wherein the steps of establishing the optimization model include: establishing the optimization target of the pumping system and setting the boundary conditions for solution, the optimization objective of establishing the pumping system is to establish, an optimization objective formula of the pumping system according to the principle of minimum vibration; min which, Al, is whether the current water pump is turned on, is ti V tion characteristic quantity corresponding to the T pump, and the sum of the vibration characteristic quantities of all the water pumps is the total vibration characteristic quantity under the current pumping system, N is die -total number of pumps in the pumping system, and min F is the pumping system optimization goal of the intelligent parallel pumping system with low vibration and reliable operation adjustment strategy; the boundary conditions for solution includes: constraint on the number of pumps started: the number of pumps put into operation shall not exceed the total number of pumps in the pumping system; speed ratio constraint: the minimum speed ratio of the pump is not smaller than 0_5 and the maximum speed ratio of the pump is not bigger than l; total flow constraint: the total flow provided by the pumping system is not less than the flow required by users; total lift constraint: the minimum lift provided by the pumping system is not lower than the required lift of users; total vibration constraint: the total vibration of the pumping system is not bigger than the specified maximum vibration.
    10, The optimal regulating method of an intelligent parallel pumping system according to claim 9, wherein the PSO algorithm is used to solve the optimization model, which specifically includes: step 1, determining parameters and search space: after determining optimized parameters, delimiting the search space of each parameter, and taking flow rate lift, pump revolution and valve opening as optimized parameters; step 2, initializing particle swarm: a group of solutions randomly generated in solution space for initial calculation; step 3, calculating the fitness of each particle, which is the vibration value predicted by the system obtained by the optimization target of the pumping system; step 4, updating the optimal particles and their speed and position: updating individual optimal and global optimal particles according to fitness, updating the speed and position of particles, and providing a new solution for the next calculation; and step 5, judging whether the algorithm tennination conditions are met: ing whether the maximum number of iterations is reached or the global optimal positon meets the Inimmumn limit; otherwise continuing iterative optimization until the judgment conditions are met to output the optimal value,
GB2116859.6A 2021-06-29 2021-11-23 Intelligent parallel pumping system and optimal regulating method thereof Active GB2608476B (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110723929.7A CN113236581B (en) 2021-06-29 2021-06-29 Intelligent parallel pump system and optimal adjustment method

Publications (3)

Publication Number Publication Date
GB202116859D0 GB202116859D0 (en) 2022-01-05
GB2608476A true GB2608476A (en) 2023-01-04
GB2608476B GB2608476B (en) 2023-07-19

Family

ID=77141041

Family Applications (1)

Application Number Title Priority Date Filing Date
GB2116859.6A Active GB2608476B (en) 2021-06-29 2021-11-23 Intelligent parallel pumping system and optimal regulating method thereof

Country Status (2)

Country Link
CN (1) CN113236581B (en)
GB (1) GB2608476B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116663451A (en) * 2023-06-05 2023-08-29 广东岭秀科技有限公司 Energy-saving efficiency optimization method, system and control device for water supply system
CN116892505A (en) * 2023-09-11 2023-10-17 华夏天信智能物联股份有限公司 An intelligent underground pumping station liquid supply control method and system
CN119021781A (en) * 2024-10-24 2024-11-26 浙江沃德尔科技集团股份有限公司 A water pump control method and system based on TCU
CN120146323A (en) * 2025-05-15 2025-06-13 武汉大水云科技有限公司 A water supply network optimization scheduling method and system based on multi-model coupling
IT202400003703A1 (en) * 2024-02-21 2025-08-21 Fluid O Tech Srl SYSTEM AND METHOD FOR MANAGING THE OPERATION OF A PUMP, PARTICULARLY A DISPLACEMENT PUMP
CN120634317A (en) * 2025-06-06 2025-09-12 中国水利水电科学研究院 A method for determining the optimal number of frequency converters in an open channel pumping station

Families Citing this family (45)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114738229B (en) * 2021-08-30 2022-12-16 江苏大学 A regulation system of multi-pump parallel system based on artificial intelligence
CN113685895B (en) * 2021-09-09 2022-06-21 西安建筑科技大学 Heat exchange station parallel water pump optimization control method and system under distributed architecture
CN114909707B (en) * 2022-04-24 2023-10-10 浙江英集动力科技有限公司 Heat supply secondary network regulation and control method based on intelligent balance device and reinforcement learning
CN114792071B (en) * 2022-05-18 2023-08-25 西安理工大学 Optimal scheduling method of drainage pumping station based on machine learning technology
CN115203627A (en) * 2022-05-19 2022-10-18 湖南山水节能科技股份有限公司 Optimal operation point determination method based on tail-removing method non-variable rotating speed machine group
CN115013862B (en) * 2022-06-01 2023-05-16 浙江英集动力科技有限公司 Autonomous optimal operation method of heating system based on jet pump and auxiliary circulating pump
CN115094977B (en) * 2022-08-09 2024-06-28 广西联环生态科技有限公司 Energy-saving self-adaptive pump station control method
CN115405915B (en) * 2022-08-23 2025-12-16 西安热工研究院有限公司 Condensate system and control method based on condensate system
CN115596653A (en) * 2022-09-21 2023-01-13 南通阳鸿石化储运有限公司（Cn） An application technology for intelligent management and control of oil pumps in chemical storage areas
CN115450895A (en) * 2022-10-08 2022-12-09 北京旭曜建筑科技有限公司 Remote control method and system of water pump and computer readable storage medium
CN115657739A (en) * 2022-10-31 2023-01-31 中国航空工业集团公司雷华电子技术研究所 Flow optimization distribution method of multi-branch flow distribution system
CN115729097B (en) * 2022-11-18 2025-09-30 中国科学院合肥物质科学研究院 An energy-saving control method for parallel water pumps in a SHMFF pumping system
CN115826409A (en) * 2022-11-29 2023-03-21 中国计量大学 An Online Update and Control Method of Pump Group Based on DAG and Hybrid Algorithm
CN115982983B (en) * 2022-12-21 2024-06-04 西南石油大学 Method for optimizing carbon emission of crude oil pipeline
CN115853759B (en) * 2022-12-23 2025-06-03 江苏大学 An energy-saving operation system for water pump unit equipment based on the Internet of Things
CN116538065A (en) * 2023-03-28 2023-08-04 中国电建集团贵阳勘测设计研究院有限公司 An intelligent control method and system for a photovoltaic water pump
CN116050955B (en) * 2023-03-31 2023-07-28 杭州百子尖科技股份有限公司 Carbon dioxide emission statistics method, device and equipment based on digital twin
CN116044772B (en) * 2023-04-03 2023-07-04 四川省机械研究设计院(集团)有限公司 Skid-mounted centrifugal pump pumping system and operation control method thereof
CN116428241A (en) * 2023-04-04 2023-07-14 中国船舶集团有限公司第七一九研究所 Hydraulic pipeline vibration control method, device and hydraulic pipeline system
CN116305700B (en) * 2023-05-18 2023-08-29 青岛研博数据信息技术有限公司 A Water Hammer Assessment and Elimination Model for Long-Distance Water Distribution Networks
CN116658433A (en) * 2023-05-22 2023-08-29 犇流泵业科技(嘉兴)股份有限公司 A particle-resistant magnetic pump intelligent detection method and system
CN116466591B (en) * 2023-06-13 2023-08-29 埃睿迪信息技术（北京）有限公司 Method and device for determining water supply strategy of water supply system
CN116699998B (en) * 2023-06-21 2024-02-13 广州和达水务科技股份有限公司 Unmanned on duty pressurization station control system based on AI algorithm
CN117085284B (en) * 2023-07-19 2024-04-05 国网辽宁省电力有限公司电力科学研究院 Pneumatic oil-discharging nitrogen-injecting fire-extinguishing parameter regulation and control method and system based on environment monitoring
CN117236159B (en) * 2023-08-08 2024-07-16 中国长江电力股份有限公司 Method for adjusting runout working condition of hydropower station unit based on radial basis function neural network model
CN119902430B (en) * 2023-10-27 2025-10-10 中国电建集团华东勘测设计研究院有限公司 Energy-saving type water supply intelligent regulation and control system for pumped storage power station technology
CN118088464A (en) * 2024-02-18 2024-05-28 江阴东为资源再生技术有限公司 Efficient and energy-saving intelligent water conveying control system
CN117927457B (en) * 2024-03-13 2025-04-15 中建安装集团有限公司 Vibration and noise reduction system and method for water supply pump group based on smart park computer platform
CN117968143B (en) * 2024-04-01 2024-06-04 陕西德联新能源有限公司 Energy-saving optimization method and system for heating system
CN118378494B (en) * 2024-06-25 2024-09-27 中国航空工业集团公司金城南京机电液压工程研究中心 Pipeline valve monitoring method and device based on automatic updating large model
CN118940606A (en) * 2024-07-11 2024-11-12 江苏大学 Centrifugal pump performance prediction method and system based on hyperparameter optimization and genetic algorithm
CN119229023A (en) * 2024-09-30 2024-12-31 天津大学 A calculation method for valve regulation strategy of ventilation system based on deep learning
CN119042141B (en) * 2024-10-30 2025-01-21 三峡智控科技有限公司 A centrifugal pump module and variable frequency operation adjustment method thereof
CN119957471A (en) * 2024-12-06 2025-05-09 江苏晟飞智能科技有限公司 An adaptive energy-saving optimization system for air compressor special electric cabinet
CN119273117B (en) * 2024-12-10 2025-04-11 国网浙江省电力有限公司永康市供电公司 Comprehensive energy system operation optimization method based on intelligent group optimization engine
CN119395982B (en) * 2025-01-06 2025-05-16 江西省天然气管道有限公司运营分公司 Intelligent separate transmission method for natural gas station based on Internet of things
CN119536189B (en) * 2025-01-22 2025-06-10 中国地质科学院勘探技术研究所 Method, device, equipment, medium and product for optimizing process parameters of double-pump system
CN120042773B (en) * 2025-03-12 2025-10-24 无锡威顺煤矿机械有限公司 A method and device for suppressing pressure fluctuations in an emulsion pump station
CN120470895B (en) * 2025-04-23 2026-03-17 中国长江电力股份有限公司 An optimization method for the shutdown behavior of hydropower units considering the maximum and minimum values of rotational speed rise and head fluctuation.
CN120181530B (en) * 2025-05-20 2025-08-01 浙江英集动力科技有限公司 Multi-station coordinated dispatching method and system for abnormal power outage of pumping stations in long-distance pipeline networks
CN120386399B (en) * 2025-06-30 2025-10-03 鸿基骏业环保科技有限公司 Intelligent pipe network pressure control method and system
CN120520799B (en) * 2025-07-03 2025-12-16 浙江澳滨泵业有限公司 Sewage pump monitoring system based on multichannel
CN120402342B (en) * 2025-07-07 2025-08-29 河北绿鸿科技有限公司 A dynamic optimization control method and system for a multi-modal pump group
CN121028623A (en) * 2025-07-09 2025-11-28 杭州浩水科技有限公司 A method and system for controlling large-scale pressure fluctuations in micro pump stations
CN121025876A (en) * 2025-10-17 2025-11-28 广东省特种设备检测研究院（广东省特种设备事故调查中心） Control Method and System for Helical Winding Heat Exchangers Based on Internet of Things

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7539549B1 (en) * 1999-09-28 2009-05-26 Rockwell Automation Technologies, Inc. Motorized system integrated control and diagnostics using vibration, pressure, temperature, speed, and/or current analysis
US20100031435A1 (en) * 2008-08-06 2010-02-11 Guy Lemire Bypass system to control liquid volume
WO2019121753A1 (en) * 2017-12-19 2019-06-27 KSB SE & Co. KGaA Multiple pump system and method for the operation thereof
US20210026334A1 (en) * 2019-07-22 2021-01-28 Rockwell Automation Technologies, Inc. Industrial control system with machine learning for compressors

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6018957A (en) * 1998-12-07 2000-02-01 Carrier Corporation Method and apparatus for controlling beats and minimizing pulsation effects in multiple compressor installations
CN101705935B (en) * 2009-11-09 2011-12-28 江苏大学 Water pump parallel machine set operation mechanism and control strategy simulation test device
CN106127298A (en) * 2016-06-16 2016-11-16 太原科技大学 A kind of Fault Diagnosis of Hydraulic Pump method based on self adaptation PSO BP neutral net
CN106836379B (en) * 2017-02-16 2019-11-05 江苏大学 It is a kind of can intelligent vibration damping pumping plant installation method
CN110175698B (en) * 2019-04-26 2021-08-03 浙江工业大学 A state prediction method of water pump equipment based on improved particle swarm optimization BP neural network
CN111325306A (en) * 2020-02-05 2020-06-23 河北工程大学 A Water Supply Pump Group Scheduling Method Based on ABC-PSO Hybrid Algorithm
CN112052890B (en) * 2020-08-28 2024-04-02 华北电力科学研究院有限责任公司 Method and device for predicting vibration of water supply pump

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7539549B1 (en) * 1999-09-28 2009-05-26 Rockwell Automation Technologies, Inc. Motorized system integrated control and diagnostics using vibration, pressure, temperature, speed, and/or current analysis
US20100031435A1 (en) * 2008-08-06 2010-02-11 Guy Lemire Bypass system to control liquid volume
WO2019121753A1 (en) * 2017-12-19 2019-06-27 KSB SE & Co. KGaA Multiple pump system and method for the operation thereof
US20210026334A1 (en) * 2019-07-22 2021-01-28 Rockwell Automation Technologies, Inc. Industrial control system with machine learning for compressors

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116663451A (en) * 2023-06-05 2023-08-29 广东岭秀科技有限公司 Energy-saving efficiency optimization method, system and control device for water supply system
CN116663451B (en) * 2023-06-05 2024-05-03 广东岭秀科技有限公司 Energy-saving efficiency optimization method, system and control device for water supply system
CN116892505A (en) * 2023-09-11 2023-10-17 华夏天信智能物联股份有限公司 An intelligent underground pumping station liquid supply control method and system
CN116892505B (en) * 2023-09-11 2023-12-05 华夏天信智能物联股份有限公司 Intelligent underground pump station liquid supply control method and system
IT202400003703A1 (en) * 2024-02-21 2025-08-21 Fluid O Tech Srl SYSTEM AND METHOD FOR MANAGING THE OPERATION OF A PUMP, PARTICULARLY A DISPLACEMENT PUMP
CN119021781A (en) * 2024-10-24 2024-11-26 浙江沃德尔科技集团股份有限公司 A water pump control method and system based on TCU
CN119021781B (en) * 2024-10-24 2025-02-14 浙江沃德尔科技集团股份有限公司 Water pump control method and system based on TCU
CN120146323A (en) * 2025-05-15 2025-06-13 武汉大水云科技有限公司 A water supply network optimization scheduling method and system based on multi-model coupling
CN120634317A (en) * 2025-06-06 2025-09-12 中国水利水电科学研究院 A method for determining the optimal number of frequency converters in an open channel pumping station

Also Published As

Publication number Publication date
CN113236581A (en) 2021-08-10
GB202116859D0 (en) 2022-01-05
CN113236581B (en) 2022-02-22
GB2608476B (en) 2023-07-19

Similar Documents

Publication Publication Date Title
GB2608476A (en) Intelligent parallel pumping system and optimal regulating method thereof
CN120212064B (en) Operation adjusting device and method for water pump station
CN120520770B (en) Water pump energy-saving control system based on intelligent data model
CN106127359A (en) A kind of variable frequency pump rate of discharge method for early warning based on local weighted linear regression model (LRM)
CN101871448B (en) New method and system for determining characteristic curve of water pump in pump station
CN119393329B (en) Method, device and medium for determining actual operating characteristics of a variable frequency unit
CN120212075A (en) Energy-saving optimization control method and system for variable frequency centrifugal fan
CN115656430A (en) Novel lubricating system capable of realizing oil parameter online monitoring and intelligent evaluation
CN119982724A (en) Throttling control method of hydraulic system based on hydraulically controlled check valve
CN116734174B (en) Control method and system for electric valve
CN202176498U (en) Surge-preventing generalized predictive control system of air compressor
CN117605660B (en) Dynamic energy-saving control method and system for air compressor
CN119717555A (en) Self-adaptive control system for oilfield equipment
CN102297120A (en) Air compressor surge-preventing generalized predictive control system and method
CN119004304A (en) Hydroelectric generating set state health assessment method for extracting characteristics by utilizing Relief algorithm
CN113551157B (en) Oil-gas data acquisition system and method based on sensor network
CN121345789B (en) Full-automatic vacuum negative pressure self-priming device
CN120576084B (en) Large-scale screw pump shaft seal self-maintenance method and system
CN119712576B (en) Parallel water pump performance monitoring method, device, computing equipment and system
CN120990860B (en) Water pump energy-saving optimization method and system for complex water pump deployment form
CN117034157B (en) Hydropower equipment fault identification method and system combining multimodal operation data
CN121637828A (en) A method and system for energy-saving control of refrigeration systems based on digital twins
CN119531981A (en) A method and system for rapid response of primary frequency modulation of compressed air energy storage system
Gong et al. Research on prediction method of sensorless measurement of centrifugal pump operational state based on hybrid model
CN121111775A (en) Compressor surge active prevention system based on digital twin model and its application method