CN111428747B - Method and device for monitoring dust and dirt conditions of air cooling radiating fins - Google Patents
Method and device for monitoring dust and dirt conditions of air cooling radiating fins Download PDFInfo
- Publication number
- CN111428747B CN111428747B CN202010092200.XA CN202010092200A CN111428747B CN 111428747 B CN111428747 B CN 111428747B CN 202010092200 A CN202010092200 A CN 202010092200A CN 111428747 B CN111428747 B CN 111428747B
- Authority
- CN
- China
- Prior art keywords
- back pressure
- data
- working condition
- condition data
- theoretical
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F28—HEAT EXCHANGE IN GENERAL
- F28F—DETAILS OF HEAT-EXCHANGE AND HEAT-TRANSFER APPARATUS, OF GENERAL APPLICATION
- F28F3/00—Plate-like or laminated elements; Assemblies of plate-like or laminated elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Thermal Sciences (AREA)
- Mechanical Engineering (AREA)
- Probability & Statistics with Applications (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a method and a device for monitoring dust and dirt conditions of air cooling radiating fins, wherein the method comprises the following steps: acquiring historical working condition data of the air cooling fins and design data of the air cooling fins in a preset period after flushing; modeling and training the historical working condition data and the design data as training data of the neural network to generate a theoretical back pressure model; determining the current theoretical back pressure according to the current working condition data by utilizing the theoretical back pressure model; and monitoring the dust and dirt condition of the air cooling radiating fins according to the determined current theoretical back pressure and the back pressure deviation of the collected actual back pressure. According to the invention, back pressure model modeling is carried out based on working condition data under a clean condition after flushing, a theoretical back pressure model is generated, theoretical back pressure data under a current working condition is determined, the pollution degree of the direct air cooling radiating fins is determined according to the deviation of the determined theoretical back pressure data and the measured actual back pressure data, and relevant works such as air cooling flushing and the like are provided with guiding basis.
Description
Technical Field
The invention relates to an air cooling heat dissipation technology, in particular to a method and a device for monitoring dust and dirt conditions of an air cooling heat dissipation fin.
Background
With the gradual enhancement of national energy conservation and emission reduction and environmental protection policies, air cooling units are widely adopted to replace traditional wet cooling units for saving water and thermal power units, and at present, direct air cooling is a mode mainly adopted by thermal power units.
The direct air cooling radiating fins are large in area and compact in structure, dust, catkin and other substances are easy to deposit, the heat resistance of the direct air cooling radiating fins is increased, the overall heat exchange efficiency is influenced, the problems of unit backpressure increase, air cooling fan power consumption increase and the like are caused, and especially, the unit backpressure increase is a main factor for reducing the load carrying capacity of a unit assembly during high load in summer, and the stability of a power grid is directly influenced. Therefore, the direct air-cooled heat dissipation fins need to be washed periodically, and in the prior art, the direct air-cooled heat dissipation fins are washed periodically mainly according to experience. In the prior art, the direct air-cooling radiating fins are regularly washed according to experience, on one hand, the phenomena of untimely washing and out-of-place washing exist, so that the back pressure of a unit is higher and the power consumption rate of an air-cooling fan is higher, and on the other hand, the phenomena of excessive washing exist in the regular washing, so that a large amount of water sources are wasted.
Disclosure of Invention
In order to monitor the dust and dirt condition of a direct air cooling radiating fin, a flushing basis is provided, and the embodiment of the invention provides a method for monitoring the dust and dirt condition of the air cooling radiating fin, which comprises the following steps:
acquiring historical working condition data and back pressure data of the air cooling radiating fins in a preset period after flushing;
modeling and training the historical working condition data and the back pressure data as training data of a neural network to generate a theoretical back pressure model;
determining the current theoretical back pressure according to the current working condition data by utilizing the theoretical back pressure model;
and monitoring the dust and dirt condition of the air cooling radiating fins according to the determined current theoretical back pressure and the back pressure deviation of the collected actual back pressure.
In the embodiment of the invention, the working condition data comprises:
unit load, exhaust flow, fan frequency, ambient temperature, ambient wind speed, ambient wind direction, ambient humidity, and air-cooled condensation water temperature.
In the embodiment of the present invention, modeling training is performed by using the historical working condition data and the back pressure data as training data of a neural network, and generating a theoretical back pressure model includes:
clustering the historical working condition data, and dividing the historical working condition data into different types of historical working condition data;
and taking the classified historical working condition data as input data and the corresponding back pressure data as output data, performing neural network modeling training, and generating theoretical back pressure models corresponding to various types of historical working condition data.
In the embodiment of the present invention, determining the current theoretical back pressure according to the current working condition data by using the theoretical back pressure model includes:
determining a theoretical back pressure model corresponding to the current working condition data according to the current working condition data and the clustered historical working condition data;
and determining the current theoretical back pressure according to the corresponding theoretical back pressure model and the current working condition data.
Meanwhile, the invention also provides a dust and dirt condition monitoring device of the air cooling radiating fin, which comprises:
the data acquisition module is used for acquiring historical working condition data and back pressure data of the air cooling radiating fins in a preset period after flushing;
the modeling module is used for modeling and training the historical working condition data and the back pressure data as training data of the neural network to generate a theoretical back pressure model;
the theoretical back pressure determining module is used for determining the current theoretical back pressure according to the current working condition data by utilizing the theoretical back pressure model;
and the monitoring module is used for monitoring the dust and dirt condition of the air cooling radiating fins according to the determined current theoretical back pressure and the back pressure deviation of the collected actual back pressure.
In an embodiment of the present invention, the modeling module includes:
the clustering unit is used for carrying out clustering processing on the historical working condition data and dividing the historical working condition data into different types of historical working condition data;
the training unit is used for taking the classified historical working condition data as input data and the corresponding back pressure data as output data, performing neural network modeling training, and generating theoretical back pressure models corresponding to various types of historical working condition data.
In an embodiment of the present invention, the theoretical back pressure determining module includes:
determining a theoretical back pressure model corresponding to the current working condition data according to the current working condition data and the clustered historical working condition data;
and determining the current theoretical back pressure according to the corresponding theoretical back pressure model and the current working condition data.
The invention also provides a computer device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the method.
Meanwhile, the invention also provides a computer readable storage medium which stores a computer program for executing the method.
The invention provides a method and a device for monitoring dust and dirt conditions of air cooling radiating fins, which are used for modeling a back pressure model based on working condition data of the air cooling radiating fins in a clean condition within a preset period after flushing, generating a theoretical back pressure model, determining the theoretical back pressure data under the current working condition by using the generated theoretical back pressure model, judging and determining the dirt degree of the direct air cooling radiating fins according to the deviation of the determined theoretical back pressure data and the measured actual back pressure data, namely guiding related personnel to perform related works such as air cooling flushing by using the back pressure deviation.
The foregoing and other objects, features and advantages of the invention will be apparent from the following more particular description of preferred embodiments, as illustrated in the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for monitoring dust and dirt conditions of an air cooling radiating fin;
FIG. 2 is a flow chart of an embodiment of the present invention;
FIG. 3 is a block diagram of an embodiment of the present invention;
FIG. 4 is a block diagram of an air cooling fin dust condition monitoring device provided by the invention;
fig. 5 is a schematic diagram of an electronic device according to an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the method for monitoring dust and dirt conditions of an air cooling radiating fin provided by the invention comprises the following steps:
step S101, acquiring historical working condition data and back pressure data of an air cooling radiating fin in a preset period after flushing;
step S102, modeling training is carried out by taking the history working condition data and the back pressure data as training data of a neural network, and a theoretical back pressure model is generated;
step S103, determining the current theoretical back pressure according to the current working condition data by utilizing the theoretical back pressure model;
and step S104, monitoring the dust and dirt condition of the air cooling radiating fins according to the determined back pressure deviation of the current theoretical back pressure and the collected actual back pressure.
According to the air cooling radiating fin dust and dirt condition monitoring method, based on working condition data of the air cooling radiating fins in a cleaning condition within a preset period after flushing, a neural network algorithm is utilized to conduct back pressure model modeling training, a theoretical back pressure model is generated, the generated theoretical back pressure model is utilized to determine theoretical back pressure data under the current working condition, the pollution degree of the direct air cooling radiating fins is determined according to deviation of the determined theoretical back pressure data and the measured actual back pressure data, namely, the back pressure deviation is utilized as a reference index to guide relevant works such as air cooling flushing and the like.
In an embodiment of the present invention, modeling training is performed by using the historical operating condition data and the backpressure data as training data of the neural network, and generating the theoretical backpressure model includes:
clustering is carried out on the historical working condition data, and the historical working condition data are divided into different types of historical working condition data;
and taking the classified historical working condition data as input data and the corresponding back pressure data as output data, performing neural network modeling training, and generating theoretical back pressure models corresponding to various types of historical working condition data.
Further, determining the current theoretical backpressure according to the current operating condition data by utilizing the theoretical backpressure model comprises:
determining a theoretical back pressure model corresponding to the current working condition data according to the current working condition data and the clustered historical public data;
and determining the current theoretical back pressure according to the corresponding theoretical back pressure model and the current working condition data.
Through carrying out the classification of clustering to history operating mode data, confirm the theoretical back pressure model that different types of history data correspond, select the theoretical back pressure model that corresponds to different operating modes, the back pressure deviation that obtains is more scientific, can be more scientific to the washing of air-cooled radiator, can predict the dirty degree of air cooling better, effectively promotes the economic nature of unit back pressure and air cooling fan power consumption rate.
The technical scheme of the invention is further elaborated in the following in conjunction with specific embodiments.
The air-cooled condenser is composed of 8 rows of 7 rows of A-shaped roof-shaped aluminum steel finned tube rows. In 7 sub-condensers of each row, 3, 6 rows are auxiliary condensers, 1, 2, 4, 5, 7 rows are main condensers, the main condensers are forward flow, the auxiliary condensers are reverse flow (the flow direction of condensed water after condensation is the same as the flow direction of steam is forward flow, and the flow direction is reverse flow). Each condenser comprises 10 tube bundles, each tube bundle comprises 41 pipelines, namely, each condenser is composed of 410 aluminum steel tubes. An axial flow fan arranged below the roof of the air-cooled condenser forces air to flow through the radiating fins, so that the steam in the fins is cooled and condensed into condensed water.
The heat dissipation fins are exposed outdoors throughout the year, dust causes the fins to be dirty so as to influence the heat exchange of the heat dissipation fins, so each unit provides a set of high-pressure water cleaning system, and the cleaning system comprises a cleaning water pump, a control valve, a stainless steel pipeline, a movable cleaning head with a truss and a nozzle, a hot dip plating guide rail, a movable hose, a supporting hanger, a valve, a pressure gauge and the like. The high-pressure water cleaning system can clean the outer surfaces of the fins when the air-cooled condenser works normally, and is semi-automatic cleaning equipment, wherein the vertical movement adopts a motor driving mode, and the horizontal movement adopts a manual mode. The scheme plans to utilize the equipped air cooling flushing device to conduct targeted flushing under the guidance of the dust and dirt condition monitoring model of the radiating fins.
In this embodiment, a method for monitoring an overall cleaning condition of a direct air-cooling heat dissipation fin is provided, where the steps include the following steps:
and (3) collecting historical data in the step (1).
In the embodiment, required working condition data are acquired from an SIS (real-time monitoring strand management system) data source of a unit;
in this embodiment, working condition data is collected by setting measuring points, the data collection interval is 1min, and the collection includes: the machine unit load, the exhaust flow, the fan frequency, the ambient temperature, the ambient wind speed, the ambient wind direction, the ambient humidity, the air cooling condensation water temperature and other data.
And (3) preprocessing the data.
Due to sensor failure or signal interruption, there may be some outliers in the operational data; in addition, because of a certain delay of each item of data in the power plant, the situation that each item of data cannot be accurately corresponding may occur, in this embodiment, preprocessing is performed before data analysis is performed on collected historical data.
The preprocessing of the history data in this embodiment includes:
removing abnormal values; for some abnormal values possibly existing in the data, for example, the numerical value exceeds the upper limit and the lower limit of normal operation and the numerical value remains unchanged for a period of time, the data needs to be removed, and the reliability of the result is ensured.
Homogenizing the data; aiming at the situation that data can not be accurately corresponding, the problem can be effectively solved by carrying out time homogenization treatment on the data for a certain time, for example, 30min accumulation is carried out on each item of data.
And (3) selecting flushing historical data.
And (3) selecting flushing history data based on the data processed in the step (2).
In this embodiment, the accumulated data under the working condition within 7 days after the air cooling island is washed is used as the data under the clean condition of the air cooling heat exchange fins to calculate the optimal theoretical back pressure, and the target library is built by using the theoretical back pressure data, so that the target library becomes the target function of the direct air cooling heat exchange fin washing model.
And (4) establishing a theoretical back pressure model.
Obtaining data; in this embodiment, the model data related to building the backpressure model by using neural network training includes: design data and post-rinse history data (within one week of rinse). And acquiring design data and different working condition data of unit load, exhaust flow, fan frequency, ambient temperature, ambient wind speed, ambient wind direction, ambient humidity, air-cooled condensation water temperature and back pressure in a time period after flushing.
And with a new round of flushing, the newly acquired flushing data is added into training, namely, the established back pressure model is dynamically corrected.
Clustering data; for all data collected, in this embodiment, gaussian Mixture Model (GMM) modeling is used to classify into K classes. Modeling data is considered to satisfy a gaussian mixture probability distribution, i.e., the data is composed of a plurality of gaussian probability distributions. Can be written in the form of a linear superposition of gaussian distributions, namely:
in the embodiment of the invention, when solving the Gaussian mixture model, a binary random variable z is introduced, and the variable adopts a '1-of-K' expression form, wherein a certain specific element z k 1, the remaining elements are 0, i.e. z k E {0,1} and Σ k z k =1, z has K possible states depending on whether the element is 0 or not. Defining a joint probability density p (x, z) from an edge probability density p (z) and a conditional probability distribution p (x|z), the edge probability distribution of z being based on a mixing coefficient pi k Performing assignment:
p(z k ＝1)＝π k
wherein the mixing coefficient pi k E {0,1}, and
since the expression "1-of-K" is used, the probability distribution of the variable z can be expressed as:
accordingly, given the value of z, the conditional probability distribution of x is a gaussian distribution:
p(x|z k ＝1)＝π k N(x|μ k ,Σ k )
the edge probability distribution of x can thus be obtained by summing all possible z by means of a joint probability distribution:
given observed quantity { x 1 ,...,x N Based on the edge probability distribution p (x), for each data observation sample x n There is a corresponding latent variable z n Thus, assuming that the Gaussian mixture distribution is linearly superimposed by K simple Gaussian distributions, and the latent variable z n In which only one variable value is 1 and the others are 0, the sample x is observed n Can be automatically categorized as the kth gaussian.
In an embodiment of the present invention, the data classification is specifically: the power generation process is characterized by multiple modes along with the change of the conditions such as load, and the like, and the embodiment of the invention considers nine parameters of unit load, exhaust flow, fan frequency, ambient temperature, ambient wind speed, ambient wind direction, ambient humidity, air-cooled condensation water temperature and back pressure, so that the Gaussian mixture model is based on historical training data { x } 1 ,...,x 9 Features incorporating latent variables in combination with likelihood functionsThe number maximization theory realizes efficient modal division and completes modeling, the edge probability distribution p (x) characterizes probability values of observed quantity in a certain Gaussian component, the prior probability and Bayesian inference given by combining a Gaussian mixture model when classifying historical working condition data are calculated, namely the data are taken as input, probability of each class is calculated by using Bayesian theory, and the probability of which class is large is determined as which class of data.
Specifically, for real-time data, the probability of each class is calculated by using Bayesian theory by taking the data as input, and the probability of each class is determined to be the data of which class if the probability of each class is large, and then back pressure is calculated according to a theoretical model corresponding to the data of which class. This is the same for the classification calculation process for each condition as the data is classified.
The GMM classification is performed with historical operating mode data, and if the classification is 3 (the classification is determined according to the data condition and is not limited to this), the three classes are respectively obtained finally:
(1) probability pi k The method comprises the steps of carrying out a first treatment on the surface of the I.e. the condition data belongs to a proportion of this type, e.g. each class of data is 30%/30%/40% of the total training data, pi 1 ＝0.3，π 2 ＝0.3，π 3 ＝0.4；
(2) An average value; i.e. the parameters { x }, respectively 1 ,...,x 9 Mean value, x 1 Representing the load, …, x 9 Represents back pressure;
(3) a variance matrix;
for each operating mode data, i.e. a certain { x } 1 ,...,x 9 The probability of each class is calculated by Bayesian theory, for example, the probability of each class of the first class, the second class and the third class is 0.5, 0.2 and 0.3 respectively, wherein the probability of each class of the first class is 0.5, then the working condition data is classified into the first class, and the process is carried out when the working condition data is classified according to historical data or real-time data, but the historical data affects the overall characteristics of each class, and when the working condition data is called, only a proper model is selected for the real-time data, and the classified data types are not affected.
Under the condition of a given training sample, the mean and covariance of different Gaussian components and the mixing coefficient of each Gaussian distribution are estimated according to an EM algorithm, and the final probability distribution condition is obtained.
And (5) establishing a model.
Different data types are obtained through GMM modeling, and for data of different types, the set load, the exhaust flow, the fan frequency, the ambient temperature, the ambient wind speed, the ambient wind direction, the ambient humidity and the air cooling condensation water temperature are taken as inputs, the theoretical back pressure is taken as output, and the BP neural network is adopted for modeling the theoretical back pressure. Training 80% of the data, and verifying the rest 20% of the data, in this embodiment, the BP algorithm program flow is shown in fig. 2. Continuously correcting the number of hidden layers and the node number of each hidden layer in the model, and repeatedly training the related weight to control the error within 3 percent so as to meet the practical application of engineering.
And (5) monitoring the cleaning condition of the radiating fins.
After theoretical back pressure models of different types of data are obtained, classification of each history working condition is judged, theoretical back pressure is calculated by the theoretical back pressure models, real-time working conditions are calculated and integrated with the history data, reasonable working conditions (large data quantity) are divided, theoretical back pressure and actual back pressure deviation values at different moments are compared, and a schematic diagram is shown in figure 2.
The idea of GMM modeling is that all data are overlapped and synthesized by a plurality of normally distributed data, namely, historical working condition data are split into a plurality of normally distributed data, each type of split data is regarded as one type, different ideal back pressure models are trained for different types of historical working condition data and back pressure data, when the model is required to be called when the theoretical back pressure is calculated by the model is required to be called for real-time data, the real-time data are firstly judged, the data belong to the type of split data, and the model trained by the corresponding data type is called.
And monitoring the integral cleaning condition of the air cooling radiating fins by monitoring a history curve of the back pressure deviation value of the same working condition, guiding the relevant flushing period and predicting the back pressure value after flushing.
According to the air cooling radiating fin dust and dirt condition monitoring method provided by the embodiment of the invention, related design parameters and well-washed historical parameters are obtained, unit load, exhaust flow, fan frequency, environment temperature, environment wind speed, environment wind direction, environment humidity and air cooling condensation water temperature are taken as inputs, theoretical back pressure is taken as outputs, and an air cooling condenser thermodynamic (back pressure) characteristic model is established. And then a model is built to calculate the predicted back pressure and the actual back pressure to compare and obtain the deviation. And comparing the back pressure deviation values at different moments under similar working conditions, and monitoring the pollution degree of the real-time air cooling radiating fins through the relative values and the change trend of the back pressure deviation. FIG. 3 is a schematic diagram of determining backpressure bias provided in an embodiment of the present invention.
According to the air cooling radiating fin dust and dirt condition monitoring method provided by the embodiment of the invention, the dust and dirt condition of the air cooling radiating fins is detected by using the back pressure deviation, the air cooling radiating fins can be washed more scientifically, the dirt degree of air cooling can be predicted better, and the economy of the back pressure of the unit and the power consumption rate of the air cooling fan is effectively improved. The problems that flushing is not timely and excessive in flushing, and an optimal running mode cannot be realized are solved, and the problems that in the prior art, the flushing of the direct air cooling radiating fins has no relevant basis, flushing work can only be carried out according to daily experience, the dirt degree of the air cooling radiating fins cannot be judged due to the change of external conditions such as climate environment, unit load and the like, and the development work of the air cooling radiating fins cannot be guided.
Meanwhile, the invention also provides a dust and dirt condition monitoring device of the air cooling radiating fin, as shown in fig. 4, the device comprises:
the data acquisition module 401 is configured to acquire historical working condition data and back pressure data of the air cooling fin in a preset period after flushing;
the modeling module 402 is configured to perform modeling training by using the historical working condition data and the back pressure data as training data of the neural network, so as to generate a theoretical back pressure model;
the theoretical back pressure determining module 403 is configured to determine a current theoretical back pressure according to current working condition data by using the theoretical back pressure model;
and the monitoring module 404 is used for monitoring the dust and dirt condition of the air cooling radiating fins according to the determined back pressure deviation of the current theoretical back pressure and the collected actual back pressure.
By adopting the air cooling radiating fin dust condition monitoring method and device provided by the invention, the dust degree of the air cooling radiating fins can be judged and the back pressure of the washed unit can be predicted, so that the air cooling radiating fins can be prejudged and washed in advance, and the air cooling condenser is under the optimal operation condition.
In addition, the embodiment of the invention also provides an electronic device, which can be a desktop computer, a tablet computer, a mobile terminal and the like, and the embodiment is not limited to the desktop computer, the tablet computer, the mobile terminal and the like. In this embodiment, the electronic device may refer to the foregoing embodiments, and the contents thereof are incorporated herein, and the repetition is omitted.
Fig. 5 is a schematic block diagram of a system configuration of an electronic device 600 according to an embodiment of the present invention. As shown in fig. 5, the electronic device 600 may include a central processor 100 and a memory 140; memory 140 is coupled to central processor 100. Notably, the diagram is exemplary; other types of structures may also be used in addition to or in place of the structures to implement telecommunications functions or other functions.
In one embodiment, the air-cooled fin dust condition monitoring function may be integrated into the CPU 100. Wherein the central processor 100 may be configured to control as follows:
acquiring historical working condition data of the air cooling fins and design data of the air cooling fins in a preset period after flushing;
modeling and training the historical working condition data and the design data as training data of a neural network to generate a theoretical back pressure model;
determining the current theoretical back pressure according to the current working condition data by utilizing the theoretical back pressure model;
and monitoring the dust and dirt condition of the air cooling radiating fins according to the determined current theoretical back pressure and the back pressure deviation of the collected actual back pressure.
In another embodiment, the air-cooling fin dust and dirt condition monitoring device may be configured separately from the cpu 100, for example, the air-cooling fin dust and dirt condition monitoring device may be configured as a chip connected to the cpu 100, and the air-cooling fin dust and dirt condition monitoring function may be implemented by the control of the cpu.
As shown in fig. 5, the electronic device 600 may further include: a communication module 110, an input unit 120, an audio processing unit 130, a display 160, a power supply 170. It is noted that the electronic device 600 need not include all of the components shown in fig. 5; in addition, the electronic device 600 may further include components not shown in fig. 5, to which reference is made to the prior art.
As shown in fig. 5, the central processor 100, sometimes also referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, which central processor 100 receives inputs and controls the operation of the various components of the electronic device 600.
The memory 140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information about failure may be stored, and a program for executing the information may be stored. And the central processor 100 can execute the program stored in the memory 140 to realize information storage or processing, etc.
The input unit 120 provides an input to the central processor 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used for displaying display objects such as images and characters. The display may be, for example, but not limited to, an LCD display.
The memory 140 may be a solid state memory such as Read Only Memory (ROM), random Access Memory (RAM), SIM card, or the like. But also a memory which holds information even when powered down, can be selectively erased and provided with further data, an example of which is sometimes referred to as EPROM or the like. Memory 140 may also be some other type of device. Memory 140 includes a buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application/function storage 142, the application/function storage 142 for storing application programs and function programs or a flow for executing operations of the electronic device 600 by the central processor 100.
The memory 140 may also include a data store 143, the data store 143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by the electronic device. The driver storage 144 of the memory 140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, address book applications, etc.).
The communication module 110 is a transmitter/receiver 110 that transmits and receives signals via an antenna 111. A communication module (transmitter/receiver) 110 is coupled to the central processor 100 to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, etc., may be provided in the same electronic device. The communication module (transmitter/receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and to receive audio input from the microphone 132 to implement usual telecommunication functions. The audio processor 130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 130 is also coupled to the central processor 100 so that sound can be recorded locally through the microphone 132 and so that sound stored locally can be played through the speaker 131.
The embodiment of the invention also provides a computer-readable program, wherein when the program is executed in an electronic device, the program causes a computer to execute the air-cooling fin dust condition monitoring method as described in the above embodiment in the electronic device.
The embodiment of the invention also provides a storage medium storing a computer readable program, wherein the computer readable program enables a computer to execute the air cooling fin dust condition monitoring described in the above embodiment in an electronic device.
Preferred embodiments of the present invention are described above with reference to the accompanying drawings. The many features and advantages of the embodiments are apparent from the detailed specification, and thus, it is intended by the appended claims to cover all such features and advantages of the embodiments which fall within the true spirit and scope thereof. Further, since numerous modifications and changes will readily occur to those skilled in the art, it is not desired to limit the embodiments of the invention to the exact construction and operation illustrated and described, and accordingly, all suitable modifications and equivalents may be resorted to, falling within the scope thereof.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principles and embodiments of the present invention have been described in detail with reference to specific examples, which are provided to facilitate understanding of the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (8)
1. The method for monitoring the dust and dirt condition of the air cooling radiating fin is characterized by comprising the following steps of:
acquiring historical working condition data and back pressure data of the air cooling radiating fins in a preset period after flushing;
modeling and training the historical working condition data and the back pressure data as training data of a neural network to generate a theoretical back pressure model;
determining the current theoretical back pressure according to the current working condition data by utilizing the theoretical back pressure model;
monitoring dust and dirt conditions of the air cooling radiating fins according to the determined current theoretical back pressure and the back pressure deviation of the collected actual back pressure;
modeling training is carried out by taking the historical working condition data and the back pressure data as training data of a neural network, and generating a theoretical back pressure model comprises the following steps:
clustering the historical working condition data, and dividing the historical working condition data into different types of historical working condition data;
and taking the classified historical working condition data as input data and the corresponding back pressure data as output data, performing neural network modeling training, and generating theoretical back pressure models corresponding to various types of historical working condition data.
2. The method for monitoring dust and dirt conditions of air cooling fins according to claim 1, wherein the working condition data comprises:
unit load, exhaust flow, fan frequency, ambient temperature, ambient wind speed, ambient wind direction, ambient humidity and air-cooled condensation water temperature.
3. The method for monitoring dust and dirt conditions of air cooling fins according to claim 1, wherein determining the current theoretical back pressure according to the current working condition data by using the theoretical back pressure model comprises:
determining a theoretical back pressure model corresponding to the current working condition data according to the current working condition data and the clustered historical working condition data;
and determining the current theoretical back pressure according to the corresponding theoretical back pressure model and the current working condition data.
4. An air cooling fin dust and dirt situation monitoring device, which is characterized in that the device comprises:
the data acquisition module is used for acquiring historical working condition data and back pressure data of the air cooling radiating fins in a preset period after flushing;
the modeling module is used for modeling and training the historical working condition data and the back pressure data as training data of the neural network to generate a theoretical back pressure model;
the theoretical back pressure determining module is used for determining the current theoretical back pressure according to the current working condition data by utilizing the theoretical back pressure model;
the monitoring module is used for monitoring the dust and dirt condition of the air cooling radiating fins according to the determined current theoretical back pressure and the back pressure deviation of the collected actual back pressure;
the modeling module comprises:
the clustering unit is used for carrying out clustering processing on the historical working condition data and dividing the historical working condition data into different types of historical working condition data;
the training unit is used for taking the classified historical working condition data as input data and the corresponding back pressure data as output data, performing neural network modeling training, and generating theoretical back pressure models corresponding to various types of historical working condition data.
5. The air-cooled fin dust condition monitoring device of claim 4, wherein the operating condition data comprises:
unit load, exhaust flow, fan frequency, ambient temperature, ambient wind speed, ambient wind direction, ambient humidity and air-cooled condensation water temperature.
6. The air-cooled fin dust condition monitoring device of claim 4, wherein the theoretical back pressure determination module comprises:
determining a theoretical back pressure model corresponding to the current working condition data according to the current working condition data and the clustered historical working condition data;
and determining the current theoretical back pressure according to the corresponding theoretical back pressure model and the current working condition data.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 3 when executing the computer program.
8. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program for executing the method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010092200.XA CN111428747B (en) | 2020-02-14 | 2020-02-14 | Method and device for monitoring dust and dirt conditions of air cooling radiating fins |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010092200.XA CN111428747B (en) | 2020-02-14 | 2020-02-14 | Method and device for monitoring dust and dirt conditions of air cooling radiating fins |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111428747A CN111428747A (en) | 2020-07-17 |
| CN111428747B true CN111428747B (en) | 2023-10-13 |
Family
ID=71547073
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010092200.XA Active CN111428747B (en) | 2020-02-14 | 2020-02-14 | Method and device for monitoring dust and dirt conditions of air cooling radiating fins |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111428747B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112153865B (en) * | 2020-09-20 | 2023-01-17 | 郑州精铖能源技术有限公司 | Big data center cooling system and install quick-witted case cabinet of this system |
| CN112905947B (en) * | 2021-02-02 | 2023-09-19 | 浙江浙能技术研究院有限公司 | Real-time monitoring method for dirt degree of fin tube heat exchanger of indirect air cooling tower |
| CN113268921B (en) * | 2021-05-13 | 2022-12-09 | 西安交通大学 | Condenser cleaning coefficient estimation method and system, electronic device and readable storage medium |
| CN117521499A (en) * | 2023-11-07 | 2024-02-06 | 北京大唐高鸿数据网络技术有限公司 | Optimal backpressure determination method, device, equipment and readable storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202854057U (en) * | 2012-11-07 | 2013-04-03 | 中国电能成套设备有限公司 | Finned tube air channel pollution detection system of cold air island |
| CN104296593A (en) * | 2014-07-11 | 2015-01-21 | 大唐阳城发电有限责任公司 | Calculation method, judgment method and system for cleanliness of air cooling heat sink |
-
2020
- 2020-02-14 CN CN202010092200.XA patent/CN111428747B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202854057U (en) * | 2012-11-07 | 2013-04-03 | 中国电能成套设备有限公司 | Finned tube air channel pollution detection system of cold air island |
| CN104296593A (en) * | 2014-07-11 | 2015-01-21 | 大唐阳城发电有限责任公司 | Calculation method, judgment method and system for cleanliness of air cooling heat sink |
Non-Patent Citations (1)
| Title |
|---|
| 张贝等.计及集群效应的直接空冷机组经济背压研究.中国电机工程学报.2018,第38卷(第19期),摘要，论文第1节，图1. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111428747A (en) | 2020-07-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111428747B (en) | Method and device for monitoring dust and dirt conditions of air cooling radiating fins | |
| CN103853106B (en) | A kind of energy consumption Prediction Parameters optimization method of building energy supplied equipment | |
| CN106779129A (en) | A kind of Short-Term Load Forecasting Method for considering meteorologic factor | |
| CN111401686A (en) | Method and device for monitoring dust condition of air-cooled cooling fins | |
| CN109612029B (en) | Efficacy prediction method | |
| Yang et al. | Multi-dimensional scenario forecast for generation of multiple wind farms | |
| CN103699771B (en) | A kind of sight-clustering method of cooling load prediction | |
| CN109634942A (en) | A kind of energy data exception judgment method and device | |
| CN115115088A (en) | Dynamic monitoring and early warning method, system, terminal and medium for carbon emission of commercial buildings | |
| CN112241607A (en) | A simulation-based approach to water resources planning that takes into account climate change | |
| Huang et al. | Sizing heating, ventilating, and air-conditioning systems under uncertainty in both load-demand and capacity-supply side from a life-cycle aspect | |
| CN113077163A (en) | Coupling forecast two-stage water abandoning risk assessment method for cascade reservoir group | |
| CN118819872B (en) | Dynamic planning method for detection server resources of industrial video monitoring and early warning | |
| CN111210060B (en) | A method for predicting the temperature of a computer room during working days | |
| CN119090480A (en) | Smart building operation and maintenance method, platform, storage medium and electronic equipment | |
| CN117952806A (en) | Intelligent low-carbon management method and system for realizing carbon-to-peak carbon neutralization | |
| TW201215824A (en) | Dynamic modeling method, monitoring method for chilling system and device for monitoring chilling system | |
| CN112365103B (en) | Method, device, equipment and medium for predicting short-term load of building in operation stage | |
| CN117974169B (en) | Emission reduction technology layout method and device for key emission industry | |
| CN112102610A (en) | Traffic flow prediction method | |
| CN108418203B (en) | A Spinning Reserve Optimization Method Using Risk Gradual Aggregation Scenarios | |
| CN117913985B (en) | A regional energy consumption monitoring management and early warning system based on power grid platform | |
| CN117557010B (en) | Method, system, device and medium for optimizing the number of spare parts in a random degradation system | |
| CN109711554B (en) | Application elasticity management device based on infrastructure big data | |
| CN119151139A (en) | Distributed photovoltaic power station assembly cleaning decision-making method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |