CN116882079A - Water pump characteristic curve self-adaptive calibration and prediction method - Google Patents

Water pump characteristic curve self-adaptive calibration and prediction method Download PDF

Info

Publication number
CN116882079A
CN116882079A CN202310697387.XA CN202310697387A CN116882079A CN 116882079 A CN116882079 A CN 116882079A CN 202310697387 A CN202310697387 A CN 202310697387A CN 116882079 A CN116882079 A CN 116882079A
Authority
CN
China
Prior art keywords
water pump
data
characteristic
flow
curve
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.)
Pending
Application number
CN202310697387.XA
Other languages
Chinese (zh)
Inventor
王子轩
黄文君
胡斌
邵长军
刘钢
周志勤
崔芳远
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.)
Zhejiang Yuanchuang Intelligent Control Technology Co ltd
Zhejiang University ZJU
Original Assignee
Zhejiang Yuanchuang Intelligent Control Technology Co ltd
Zhejiang University ZJU
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 Zhejiang Yuanchuang Intelligent Control Technology Co ltd, Zhejiang University ZJU filed Critical Zhejiang Yuanchuang Intelligent Control Technology Co ltd
Priority to CN202310697387.XA priority Critical patent/CN116882079A/en
Publication of CN116882079A publication Critical patent/CN116882079A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/17—Mechanical parametric or variational design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/06—Power analysis or power optimisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/12—Timing analysis or timing optimisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Computational Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Control Of Positive-Displacement Pumps (AREA)

Abstract

The invention discloses a self-adaptive calibration and prediction method for a characteristic curve of a water pump, which comprises the following steps: collecting data of each characteristic of the water pump in real time through external equipment, uploading the collected data to a designated platform, and storing current and historical data; establishing an ARMA model based on classification improvement, and predicting each characteristic of the water pump; substituting the predicted value of each characteristic of the water pump in the step S2 and the acquired value of each characteristic of the water pump at the current moment into an operation rule formula of the water pump at the rated frequency, and correcting and predicting the characteristic curve of the water pump at the current moment; fitting in a least square manner based on the acquired pipeline parameters through a formula; and drawing a pipeline characteristic curve and a water pump characteristic curve, wherein the intersection point of the two curves is the actual working condition point for predicting the work of the water pump. The invention has the characteristics of effectively improving the accuracy and expanding the application range.

Description

Water pump characteristic curve self-adaptive calibration and prediction method
Technical Field
The invention relates to a water pump characteristic processing method, in particular to a water pump characteristic curve self-adaptive calibration and prediction method.
Background
The traditional water pump modeling mode is mainly based on mechanism modeling, and the change of characteristic curves of the same type of water pump in different working condition environments and along with the increase of service time is not considered in the model, so that the traditional model has larger errors. In addition, due to the specificity of different industrial scenes, the acquired data can be limited to a certain extent (equipment cannot be started or stopped at will in the special industrial scenes), and only partial data points with fixed frequency or specific frequency can be acquired. For example, in the prior art named as a modeling method and a modeling system of a mathematical model of a variable-frequency speed-regulating water pump, the modeling method and the modeling system are based on massive historical operation data of the water pump, the modeling method and the modeling system are grouped according to the same frequency segment, and flow-lift and flow-efficiency curves of the corresponding frequency segment are fitted.
The following disadvantages still exist:
1. the model family is only suitable for fitting the flow-lift and flow-efficiency curves of the water pump to the data in the same frequency band, and is limited when the collected data cannot meet the requirement of fewer data points in the same frequency band or in the same frequency band.
2. The fitting of the model based on the historical data to the characteristic curve of the water pump can solve the problem of characteristic curve deviation caused by long-term use of the water pump to a certain extent, but the water pump fails, and the water pump cannot be found out in time when the acquired data has larger deviation.
Therefore, the prior art has the problems of poor accuracy and narrow application range.
Disclosure of Invention
The invention aims to provide a self-adaptive calibration and prediction method for a characteristic curve of a water pump, aiming at the defects of the prior art. The invention has the characteristics of effectively improving the accuracy and expanding the application range.
The technical scheme of the invention is as follows: a self-adaptive calibration and prediction method for a characteristic curve of a water pump comprises the following steps:
s1, acquiring data of each characteristic of a water pump and a pipeline in real time through external equipment, uploading the acquired data to a designated platform, and storing current and historical data;
s2, establishing an ARMA model based on classification improvement, and predicting each characteristic of the water pump;
s3, substituting the predicted value of each characteristic of the water pump in the step S2 and the acquired value of each characteristic of the water pump at the current moment into an operation rule formula of the water pump at the rated frequency, wherein the operation rule formula comprises a flow-lift curve equation, a flow-power curve equation and an efficiency curve equation, correcting the characteristic curve of the water pump at the current moment, and obtaining a predicted flow-lift and flow-efficiency curve when the water pump operates in the next time unit;
s4, fitting to obtain a pipeline characteristic curve in a least square mode based on the acquired pipeline parameters, wherein a fitting formula is as followsWherein->The lift of the pipeline is represented by Q, the flow of the pipeline is represented by D, S, and parameters to be fitted are represented by S; and drawing a pipeline characteristic curve and a water pump characteristic curve, wherein the intersection point of the two curves is an actual working condition point for predicting the work of the water pump.
Further, in step S1, data of each characteristic of the water pump and the pipeline is collected once a day, and each piece of data corresponds to the flow and the lift of the water pump and the pipeline;
for each piece of data collected, the data is taken as a measured value of the piece of data by taking an average value multiple times.
Further, in step S2, the classification-based improved ARMA model is implemented by:
1) Classifying the data of each characteristic of the water pump acquired in the step S1 into data under the same frequency, namely fixed frequency data, and data under different frequencies, namely variable frequency data;
2) Classifying the fixed frequency data and the variable frequency data according to quarters respectively, extracting each characteristic data information in the same class, including the maximum value, the minimum value, the average value, the tail-biting average value and the median of each characteristic, selecting one of the data information of the characteristics to describe the characteristics of the class, and marking asRepresenting the median of the data collected by the jth feature point under the ith class;
3) The data information of each feature in each class is formed into a vector, the acquired data vector closest to the feature data information vector is found according to the Legendre optimal approximation criterion, and the date d in the corresponding class is recorded i,t ；
4) M features under the first N classes are taken from the classified data set, the m feature points of the current class, namely the (n+1) th class, are respectively predicted based on an ARMA model, and the specific formula is as follows:
wherein p is the order of the autoregressive term AR, α i (i=0, 1, k, p) autoregressive coefficients; q is the order of the moving average term MA, β j (j=1, 2, k, q) is the moving average coefficient, ζ t Is a white noise which is a white noise,defining the boundary of noise; e represents mathematical expectation, var represents variance, < +.>Representing any collected water pump data of the same type.
5) Substituting the acquired values of the characteristic variables into the data information of the predicted characteristics of the next class obtained in the steps, wherein the corresponding date is
6) Fitting a change curve of each feature based on the measured feature value of the last kt day in the Nth class and the predicted future feature data information vector, and using a function f i To express, predict with 15 days as the cycle, realize carrying on the updating and iteration of the characteristic curve of water pump once every 15 days in the next quarter; the specific formula is as follows:
solving the formula by using a least square mode to obtain a function f i Wherein the function f i And (3) representing the i-th characteristic fitting prediction function, and obtaining a predicted value at any moment in the next class based on the prediction function.
Further, in step S3, the flow-lift curve equation, the flow-power curve equation, and the efficiency curve equation are respectively as follows:
H＝aQ 2 +bQ+c
P＝jQ 2 +kQ+l
where H is the pump head, Q is the pump flow, η is the pump efficiency, P is the pump power, a, b, c, j, k, l are parameters for fitting the quadratic curve.
Further, the flow-lift curve equation and the flow-power curve equation under specific frequency can be obtained through the flow-lift curve equation and the flow-power curve equation of the data collected under the same frequency;
the data collected at different frequencies are fitted by combining the collected data with a mechanism model in a least squares processing mode, as follows:
H 0 ＝aQ 0 2 +bQ 0 i+ci 2
P 0 ＝jQ 0 2 i+kQ 0 i 2 +li 3
wherein H is 0 ,Q 0 ,P 0 For the running frequency f of the water pump 0 The lift, flow and power of the device are equal to the rated frequency, f is the proportionality coefficient of the operating frequency and the rated frequency.
The invention has the beneficial effects that:
compared with the prior art, in order to improve the accuracy of a mathematical model of the water pump, the invention adopts two aspects of modeling to respectively perform data fusion on the characteristic curve of the water pump under specific frequency: firstly, fitting a characteristic curve of a water pump under variable frequency speed regulation, collecting parameters of flow, lift and power of the water pump under different frequencies, converting the data into data under the same frequency through a mechanism model, and further providing a characteristic curve of the corresponding frequency; secondly, fitting a characteristic curve of the water pump at fixed frequency, and fitting the characteristic curve of the water pump at the same frequency by collecting the characteristic parameters of the water pump at the same frequency; and finally, fitting a pipeline characteristic curve, namely fitting the pipeline characteristic curve in the scene by measuring the pipeline lift of the pipeline under different flow rates. The invention integrates and automates data acquisition, data processing, data inspection and real-time updating of the characteristic curve of the water pump, and does not need research personnel to carry out extra work; the flow-lift and flow efficiency curves of the water pump in one or more time units in the future can be predicted by the collected data under the same frequency and different frequencies, and the method reduces the working complexity and simultaneously maintains the accuracy of the characteristic curve. Moreover, the application scene can be popularized and is not only suitable for a specific industrial scene.
According to the invention, by collecting data in real time, calibrating characteristic curves of the water pump and the pipeline based on the data collected in real time, adaptively updating a model, analyzing collected historical data, judging whether the data collected at the current moment is abnormal or not according to an ARMA model of an improved time sequence, further predicting future flow-lift and flow-efficiency curves, and detecting abnormality of the water pump and the like, which can be used as a judging condition; the method is suitable for different industrial environments, and can be used for fitting the characteristic curves of the water pump under the specified frequency to the data collected by fixed frequency and variable frequency at the same time. In conclusion, the method has the characteristics of effectively improving accuracy and expanding application range.
Drawings
Fig. 1 is a flowchart of a method for adaptively calibrating and predicting a characteristic curve of a water pump according to an embodiment of the present invention.
Detailed Description
The following describes the embodiments of the present invention in further detail with reference to the drawings.
The invention provides a self-adaptive calibration and prediction method for a characteristic curve of a water pump,
the invention discloses a water pump characteristic curve self-adaptive checking, calibrating and predicting method, which comprises four aspects of data acquisition, data processing and rationality analysis, water pump model calibration and water pump characteristic curve prediction, and is realized by the following steps, wherein a specific flow chart is shown in fig. 1:
1. the external equipment collects data in real time, data is collected once a day, each data corresponds to the flow, the lift and the like of the water pump/pipeline, the data collected by the external equipment in real time is uploaded to a designated platform, and current and historical data are stored.
For each acquired data point, an average is taken over multiple acquisitions as a measurement of the piece of data.
2. Classification-based improved ARMA model building. The traditional ARMA model can predict data of a plurality of days in the future based on data acquired every day, however, the change amplitude of data points acquired by a characteristic curve of the water pump in a short period is small, the data which need to be predicted on a longer time scale is not clear in the process of predicting the trend of the data, and more calculation resources are wasted. Therefore, the traditional model is improved, the information of the data is fully mined, and the overall accuracy of data prediction is improved. The improved model is realized by the following steps:
the data collected in 1 is classified into data under the same frequency (fixed frequency) and data under different frequencies (variable frequency).
Classifying the data of the two parts according to quarters, extracting information of each feature (flow, lift and the like) in the same class, including maximum value, minimum value, average value and tail-cutting average value of each feature (the average value after the maximum value and the minimum value are removed in the same class), selecting the median of the features to describe the features of the class, and recording asRepresents the median of the data collected by the jth feature point under the ith class.
The median for each feature in each class may form a vectorThe data collected for each day can be expressed as +.>Wherein->The (q) feature representing the (t) th day under the (i) th class is based on Legendre's best approximation criterion, the (1-1) is targeted, the acquired data vector closest to the data median vector is found, and the record is recordedDate d in the next corresponding category i,t 。
M features under the first N classes are taken from the classified data set, and the m feature points of the current class (the (n+1) th class) are respectively predicted based on an ARMA model. The specific formula is as follows:
wherein p is the order of the autoregressive term AR, which can be determined from the PACF diagram, α i (i=0, 1, k, p) autoregressive coefficients; q is the order of the moving average term MA, which can be determined from the ACF map, beta j (j=1, 2, k, q) is the moving average coefficient, ζ t Is white noise.
The measured values of the characteristic variables are used to obtain the median of the predicted characteristics of the next class, and the corresponding date is
Fitting a variation curve of each feature (using a function f) based on the measured eigenvalues of the last kt day (divided into k segments) in the nth class and the predicted future median vector i Expressed by the specification), the water pump characteristic curve is predicted by taking 15 days as a period, and the water pump characteristic curve is updated and iterated once every 15 days in the next quarter. The specific implementation process is described by a formula (1-4), and the formula (1-4) is solved in a least square mode to obtain a function f i
Wherein the function f i And (3) representing the i-th characteristic fitting prediction function, and obtaining a predicted value at any moment in the next class based on the prediction function.
3. Based on the predicted value of each characteristic in the step 2 and the measured value of each data at the current moment, the operation rule formula of the brought water pump under the rated frequency comprises a flow-lift curve equation, a flow-power curve equation and an efficiency curve equation, and the operation rule formula is as follows:
H＝aQ 2 +bQ+c (1-5)
P＝jQ 2 +kQ+l (1-6)
where H is the pump head, Q is the pump flow, η is the pump efficiency, P is the pump power, a, b, c, j, k, l are parameters for fitting the quadratic curve. Aiming at different industrial scenes and collected data, the data collected at the same frequency and different frequencies are processed respectively.
The flow-lift curve equation and the flow-power curve equation under specific frequency can be obtained by the data collected under the same frequency through the formulas (1-5) (1-6).
The data collected at different frequencies are fitted by combining the collected data with a mechanism model in a least squares processing mode, as follows:
H 0 ＝aQ 0 2 +bQ 0 i+ci 2 (1-9)
P 0 ＝jQ 0 2 i+kQ 0 i 2 +li 3 (1-10)
wherein H is 0 ,Q 0 ,P 0 For the running frequency f of the water pump 0 The lift, the flow and the power of the air conditioner,f is the rated frequency, i is the proportionality coefficient of the operating frequency and the rated frequency.
Assuming that data at n different frequencies are collected, the data is calculated by the least squares method from (1-5), (1-9) and (1-6), (1-10):
Ax＝T (1-11)
By＝W (1-12)
wherein:
by the method, not only can the characteristic curve of the water pump at the current moment be corrected, but also the predicted flow-lift and flow-efficiency curve of the water pump in the next time unit can be obtained.
4. Fitting by least squares based on the acquired pipeline parameters through formulas (1-14)
Wherein the method comprises the steps ofAnd Q is the flow of the pipeline, D and S are parameters to be fitted.
And drawing a pipeline characteristic curve and a water pump characteristic curve, wherein the intersection point of the pipeline characteristic curve and the water pump characteristic curve is the actual working condition point for predicting the work of the water pump.
The embodiment of the invention can realize the following functions: each component on the platform can interact with a system outside the platform independently, collect and transmit data in real time, and upload the data to the data processing platform;
based on the data collected in real time, completing a script for automatically fitting and correcting the characteristic curves of the water pump and the pipeline, calculating a real-time pipeline impedance coefficient, and updating and correcting an original mechanism model of the water pump in real time;
based on historical data, predicting the change condition of a characteristic curve of the water pump;
the method has applicability to different industrial environments, and the acquired data is subjected to block processing to obtain a more accurate characteristic curve of the water pump.
In order to meet the functions, an external system is required to collect and input data in real time, and the characteristic curve of the water pump is updated in real time, so that a developer of the platform is not required to carry out manual processing additionally, secondary development of the platform is avoided, and efficiency is improved.
The above-described embodiments are intended to illustrate the present invention, not to limit it, and any modifications and variations made thereto are within the spirit of the invention and the scope of the appended claims.

Claims (5)

1. The self-adaptive calibration and prediction method for the characteristic curve of the water pump is characterized by comprising the following steps of:
s1, acquiring data of each characteristic of a water pump and a pipeline in real time through external equipment, uploading the acquired data to a designated platform, and storing current and historical data;
s2, establishing an ARMA model based on classification improvement, and predicting each characteristic of the water pump;
s3, substituting the predicted value of each characteristic of the water pump in the step S2 and the acquired value of each characteristic of the water pump at the current moment into an operation rule formula of the water pump at the rated frequency, wherein the operation rule formula comprises a flow-lift curve equation, a flow-power curve equation and an efficiency curve equation, correcting the characteristic curve of the water pump at the current moment, and obtaining a predicted flow-lift and flow-efficiency curve when the water pump operates in the next time unit;
s4, fitting to obtain a pipeline characteristic curve in a least square mode based on the acquired pipeline parameters, wherein a fitting formula is as followsWherein->The lift of the pipeline is represented by Q, the flow of the pipeline is represented by D, S, and parameters to be fitted are represented by S; and drawing a pipeline characteristic curve and a water pump characteristic curve, wherein the intersection point of the two curves is an actual working condition point for predicting the work of the water pump.
2. The self-adaptive calibration and prediction method of a water pump characteristic curve according to claim 1, wherein in step S1, data of each characteristic of the water pump and the pipeline is collected once a day, and each data corresponds to flow and lift of the water pump and the pipeline;
for each piece of data collected, the data is taken as a measured value of the piece of data by taking an average value multiple times.
3. The method for adaptively calibrating and predicting a characteristic curve of a water pump according to claim 1, wherein in step S2, the classification-based improved ARMA model is implemented by:
1) Classifying the data of each characteristic of the water pump acquired in the step S1 into data under the same frequency, namely fixed frequency data, and data under different frequencies, namely variable frequency data;
2) Classifying the fixed frequency data and the variable frequency data according to quarters respectively, extracting each characteristic data information in the same class, including the maximum value, the minimum value, the average value, the tail-biting average value and the median of each characteristic, selecting one of the data information of the characteristics to describe the characteristics of the class, and marking asRepresenting the median of the data collected by the jth feature point under the ith class;
3) The data information of each feature in each class is formed into a vector, the acquired data vector closest to the feature data information vector is found according to the Legendre optimal approximation criterion, and the date d in the corresponding class is recorded i,t ；
4) M features under the first N classes are taken from the classified data set, the m feature points of the current class, namely the (n+1) th class, are respectively predicted based on an ARMA model, and the specific formula is as follows:
wherein p is the order of the autoregressive term AR, α i (i=0, 1, k, p) autoregressive coefficients; q is the order of the moving average term MA, β j (j=1, 2, k, q) is the moving average coefficient, ζ t Is a white noise which is a white noise,defining the boundary of noise; e represents mathematical expectation, var represents variance, < +.>Representing the water pump data of the same type which are randomly collected;
5) Substituting the acquired values of the characteristic variables into the data information of the predicted characteristics of the next class obtained in the steps, wherein the corresponding date is
6) Fitting a change curve of each feature based on the measured feature value of the last kt day in the Nth class and the predicted future feature data information vector, and using a function f i The method comprises the steps of selecting a prediction period, and updating and iterating a water pump characteristic curve once in each prediction period in the next quarter; the specific formula is as follows:
solving the formula by a least square method to obtainFunction f i Wherein the function f i And (3) representing the i-th characteristic fitting prediction function, and obtaining a predicted value at any moment in the next class based on the prediction function.
4. The method for adaptively calibrating and predicting a characteristic curve of a water pump according to claim 1, wherein in step S3, a flow-head curve equation, a flow-power curve equation and an efficiency curve equation are respectively as follows:
H＝aQ 2 +bQ+c
P＝jQ 2 +kQ+l
where H is the pump head, Q is the pump flow, η is the pump efficiency, P is the pump power, a, b, c, j, k, l are parameters for fitting the quadratic curve.
5. The method for adaptively calibrating and predicting a characteristic curve of a water pump according to claim 4, wherein the flow-lift curve equation and the flow-power curve equation under specific frequencies can be obtained from data collected under the same frequency through the flow-lift curve equation and the flow-power curve equation;
the data collected at different frequencies are fitted by combining the collected data with a mechanism model in a least squares processing mode, as follows:
H 0 ＝aQ 0 2 +bQ 0 i+ci 2
P 0 ＝jQ 0 2 i+kQ 0 i 2 +li 3
wherein H is 0 ,Q 0 ,P 0 For the running frequency f of the water pump 0 When (1)The lift, flow and power, f is the rated frequency, i is the proportionality coefficient of the operating frequency and the rated frequency.
CN202310697387.XA 2023-06-13 2023-06-13 Water pump characteristic curve self-adaptive calibration and prediction method Pending CN116882079A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310697387.XA CN116882079A (en) 2023-06-13 2023-06-13 Water pump characteristic curve self-adaptive calibration and prediction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310697387.XA CN116882079A (en) 2023-06-13 2023-06-13 Water pump characteristic curve self-adaptive calibration and prediction method

Publications (1)

Publication Number Publication Date
CN116882079A true CN116882079A (en) 2023-10-13

Family

ID=88255758

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310697387.XA Pending CN116882079A (en) 2023-06-13 2023-06-13 Water pump characteristic curve self-adaptive calibration and prediction method

Country Status (1)

Country Link
CN (1) CN116882079A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117540163A (en) * 2023-11-09 2024-02-09 南栖仙策(南京)高新技术有限公司 Pump performance curve generation method, model construction and training method and device
CN118095053A (en) * 2024-01-15 2024-05-28 上海碳索能源服务股份有限公司 Indirect prediction method, system, terminal and medium for flow of cooling water pump

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117540163A (en) * 2023-11-09 2024-02-09 南栖仙策(南京)高新技术有限公司 Pump performance curve generation method, model construction and training method and device
CN118095053A (en) * 2024-01-15 2024-05-28 上海碳索能源服务股份有限公司 Indirect prediction method, system, terminal and medium for flow of cooling water pump

Similar Documents

Publication Publication Date Title
US11888316B2 (en) Method and system of predicting electric system load based on wavelet noise reduction and EMD-ARIMA
CN116882079A (en) Water pump characteristic curve self-adaptive calibration and prediction method
JP5658881B2 (en) Method for predicting the amount of electricity produced by photovoltaic power generation equipment
CN106227906B (en) A kind of appraisal procedure of the intelligent manufacturing equipment reliability based on performance degradation analysis
CN111275579B (en) Heat supply system thermal delay time identification method based on Pearson correlation coefficient and moving average method
CN108090515B (en) Data fusion-based environment grade evaluation method
KR101793625B1 (en) Evaluation method and system of rainfall quantile considering climate change in nonstationary regional frequency analysis
CN111695730B (en) Vertical mill vibration prediction method and device based on ARIMA and RNN
CN111445105B (en) Power plant online performance diagnosis method and system based on target value analysis
CN109523077B (en) Wind power prediction method
CN117387172B (en) Terminal air conditioner energy saving method and system based on accurate recommended equipment control parameters
CN114936504A (en) Equipment residual life prediction method and system based on Bayesian multi-source data fusion
CN115908051A (en) Method for determining energy storage capacity of power system
CN114329347B (en) Method and device for predicting metering error of electric energy meter and storage medium
CN118051083A (en) Intelligent temperature control method and device for heating wire
CN111950752A (en) Photovoltaic power station generating capacity prediction method, device and system and storage medium thereof
CN118114118A (en) CNDT-based fault diagnosis method for typical weapon equipment
CN117196257A (en) Auxiliary settlement system for power distribution network engineering
CN110083804B (en) Wind power plant SCADA data missing intelligent repairing method based on condition distribution regression
CN108537322A (en) Neural network interlayer activation value quantization method and device
CN112365103B (en) Method, device, equipment and medium for predicting short-term load of building in operation stage
CN115022348B (en) Intelligent factory cloud-level architecture data storage method for high-end battery
CN111507432A (en) Intelligent weighing method and system for agricultural insurance claims, electronic equipment and storage medium
CN110990768A (en) Method for determining data types of various parameters of generator set performance based on mutual information values
CN115114983B (en) Method for acquiring and analyzing electric quantity data based on big data equipment and computer system

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