CN113758313B - Heat exchanger with four-fluid temperature cooperative communication memory control function - Google Patents

Heat exchanger with four-fluid temperature cooperative communication memory control function Download PDF

Info

Publication number
CN113758313B
CN113758313B CN202110387096.1A CN202110387096A CN113758313B CN 113758313 B CN113758313 B CN 113758313B CN 202110387096 A CN202110387096 A CN 202110387096A CN 113758313 B CN113758313 B CN 113758313B
Authority
CN
China
Prior art keywords
tube
heat exchange
data
fluid
valve
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
Application number
CN202110387096.1A
Other languages
Chinese (zh)
Other versions
CN113758313A (en
Inventor
王逸隆
籍艳
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.)
Shenzhen Hongyue Information Technology Co ltd
Xi'an Shangzhihe Energy Conservation Technology Co.,Ltd.
Original Assignee
Qingdao University of Science and Technology
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 Qingdao University of Science and Technology filed Critical Qingdao University of Science and Technology
Publication of CN113758313A publication Critical patent/CN113758313A/en
Application granted granted Critical
Publication of CN113758313B publication Critical patent/CN113758313B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F28HEAT EXCHANGE IN GENERAL
    • F28DHEAT-EXCHANGE APPARATUS, NOT PROVIDED FOR IN ANOTHER SUBCLASS, IN WHICH THE HEAT-EXCHANGE MEDIA DO NOT COME INTO DIRECT CONTACT
    • F28D15/00Heat-exchange apparatus with the intermediate heat-transfer medium in closed tubes passing into or through the conduit walls ; Heat-exchange apparatus employing intermediate heat-transfer medium or bodies
    • F28D15/02Heat-exchange apparatus with the intermediate heat-transfer medium in closed tubes passing into or through the conduit walls ; Heat-exchange apparatus employing intermediate heat-transfer medium or bodies in which the medium condenses and evaporates, e.g. heat pipes
    • F28D15/0266Heat-exchange apparatus with the intermediate heat-transfer medium in closed tubes passing into or through the conduit walls ; Heat-exchange apparatus employing intermediate heat-transfer medium or bodies in which the medium condenses and evaporates, e.g. heat pipes with separate evaporating and condensing chambers connected by at least one conduit; Loop-type heat pipes; with multiple or common evaporating or condensing chambers
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F28HEAT EXCHANGE IN GENERAL
    • F28DHEAT-EXCHANGE APPARATUS, NOT PROVIDED FOR IN ANOTHER SUBCLASS, IN WHICH THE HEAT-EXCHANGE MEDIA DO NOT COME INTO DIRECT CONTACT
    • F28D15/00Heat-exchange apparatus with the intermediate heat-transfer medium in closed tubes passing into or through the conduit walls ; Heat-exchange apparatus employing intermediate heat-transfer medium or bodies
    • F28D15/02Heat-exchange apparatus with the intermediate heat-transfer medium in closed tubes passing into or through the conduit walls ; Heat-exchange apparatus employing intermediate heat-transfer medium or bodies in which the medium condenses and evaporates, e.g. heat pipes
    • F28D15/06Control arrangements therefor
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F28HEAT EXCHANGE IN GENERAL
    • F28GCLEANING OF INTERNAL OR EXTERNAL SURFACES OF HEAT-EXCHANGE OR HEAT-TRANSFER CONDUITS, e.g. WATER TUBES OR BOILERS
    • F28G7/00Cleaning by vibration or pressure waves
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02EREDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02E60/14Thermal energy storage
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P20/00Technologies relating to chemical industry
    • Y02P20/10Process efficiency

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Sustainable Development (AREA)
  • Physics & Mathematics (AREA)
  • Thermal Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Heat-Exchange Devices With Radiators And Conduit Assemblies (AREA)

Abstract

The invention provides a heat exchanger with four fluid temperature cooperative communication memory control, wherein the inlets of a first heat exchange tube, a second heat exchange tube and a third heat exchange tube are provided with a first valve, a second valve and a third valve respectively; the temperature data of the first temperature sensor, the second temperature sensor and the third temperature sensor are stored in a database in real time, a one-dimensional deep convolutional neural network is adopted to extract data characteristics, and pattern recognition is carried out, so that the opening and closing of the first valve, the second valve and the third valve are controlled, and whether the first fluid, the third fluid and the second fluid exchange heat or not is controlled. The invention can be based on a theoretical method of machine memory and pattern recognition, so that the detection and judgment results are more accurate.

Description

Heat exchanger with four-fluid temperature cooperative communication memory control function
Technical Field
The invention relates to a shell-and-tube heat exchanger, in particular to an intermittent vibration descaling shell-and-tube heat exchanger.
Background
The invention relates to a novel invention for descaling a heat exchanger, which is used for a shell-and-tube heat exchanger based on research and development of Qingdao university of science and technology (application number 2019101874848).
The shell-and-tube heat exchanger is widely applied to industries such as chemical industry, petroleum, refrigeration, nuclear energy, power and the like, and because of the worldwide energy crisis, in order to reduce energy consumption, the demand for the heat exchanger in industrial production is also increasing, and the quality requirement for the heat exchanger is also increasing. In recent decades, although compact heat exchangers (plate-type, plate-fin-type, pressure-welded plate-type heat exchangers, etc.), heat pipe-type heat exchangers, direct contact heat exchangers, etc. have been rapidly developed, shell-and-tube heat exchangers still occupy the dominant position of yield and usage due to high reliability and wide adaptability, and the usage of the shell-and-tube heat exchangers in the current industrial devices still accounts for about 70% of the usage of all heat exchangers according to relevant statistics.
After the shell-and-tube heat exchanger is scaled, the heat exchanger is cleaned by adopting the conventional modes of steam sweeping, back flushing and the like, and the production practice proves that the effect is not very good. The heat exchanger seal heads can be detached only by adopting a physical cleaning mode, but the heat exchanger seal heads are cleaned by adopting the mode, so that the operation is complex, the time consumption is long, the investment of manpower and material resources is large, and great difficulty is brought to continuous industrial production.
The enhanced heat exchange is realized by utilizing the vibration of the fluid-induced heat transfer element, which is a form of passive enhanced heat exchange, and the strict prevention of the fluid vibration induction in the heat exchanger can be changed into the effective utilization of the vibration, so that the convective heat transfer coefficient of the transmission element under the low flow velocity is greatly improved, the dirt on the surface of the heat transfer element is restrained by utilizing the vibration, the dirt thermal resistance is reduced, and the composite enhanced heat transfer is realized.
In application, it is found that continuous heat exchange can lead to the formation stability of internal fluid, namely that the fluid is not flowing or has little fluidity, or the flow is stable, so that the vibration performance of the heat exchange tube is greatly weakened, and the descaling and heat exchange efficiency of the heat exchange tube are affected. There is therefore a need for improvements in the heat exchangers described above.
The heat exchanger generally exchanges heat by two fluids, but has little research on four-fluid heat exchange, the application researches on four-fluid heat exchange, develops a novel induced vibration four-fluid shell-and-tube heat exchanger,
current shell and tube heat exchangers include dual headers, one header evaporating and one header condensing, forming vibratory descaling heat pipes. Thereby improving the heat exchange efficiency of the heat pipe and reducing scaling. However, the heat exchange uniformity of the heat pipe is not enough, only one side is condensed, but the heat exchange amount is small, so that improvement is needed, and a heat pipe system with a novel structure is developed. There is therefore a need for improvements in the heat exchangers described above.
In the previous application, a shell-and-tube heat exchanger for heat exchange of four fluids has been developed, but the shell-and-tube heat exchanger is controlled according to the period, so that the vibration heat exchange effect is poor and the degree of intellectualization is low. The present application thus provides a further improvement over the previous studies.
Disclosure of Invention
The invention provides a four-fluid shell-and-tube heat exchanger with a novel structure, aiming at the defects of the shell-and-tube heat exchanger in the prior art. The shell-and-tube heat exchanger can realize heat exchange of four fluids, can utilize temperature data in a real-time monitoring system of the heater to design a corresponding operation mode according to different operation working conditions of the heat exchanger based on a theoretical method of machine memory and mode identification, and trains a deep convolutional neural network by using a large amount of temperature data, so that heat exchange component descaling is carried out, and the heat utilization effect and the descaling effect are improved. The shell-and-tube heat exchanger can realize periodic frequent vibration of the heat exchange tube, and improves the heating efficiency, thereby realizing good descaling and heating effects. The heat exchanger structure is particularly suitable for a heat exchanger arranged in the horizontal direction.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the shell-and-tube heat exchanger comprises a shell, a heat exchange component, a shell side inlet connecting pipe and a shell side outlet connecting pipe; the heat exchange component is arranged in the shell and is fixedly connected to the front tube plate and the rear tube plate; the shell side inlet connecting pipe and the shell side outlet connecting pipe are arranged on the shell; the shell side fluid enters from the shell side inlet connecting pipe, exchanges heat through the heat exchange component and exits from the shell side outlet connecting pipe;
The heat exchange component comprises a central tube, a left tube, a right tube and a tube group, wherein the tube group comprises a left tube group and a right tube group, the left tube group is communicated with the left tube group and the central tube, the right tube group is communicated with the right tube group and the central tube, so that the central tube, the left tube, the right tube group and the tube group form a heat exchange fluid closed cycle, phase change fluid is filled in the left tube and/or the central tube and/or the right tube, each tube group comprises a plurality of circular tubes in a circular arc shape, the end parts of the adjacent circular tubes are communicated, the plurality of circular tubes form a serial structure, and the end parts of the circular tubes form a free end of the circular tube; the central tube comprises a first tube orifice and a second tube orifice, the first tube orifice is connected with the inlet of the left tube group, the second tube orifice is connected with the inlet of the right tube group, the outlet of the left tube group is connected with the left tube, and the outlet of the right tube group is connected with the right tube; the first pipe orifice and the second pipe orifice are arranged on the same side of the central pipe; the left tube group and the right tube group are mirror symmetry along the surface where the axle center of the central tube is positioned;
a left return pipe is arranged between the left side pipe and the central pipe, and a right return pipe is arranged between the right side pipe and the central pipe;
the heat exchanger further comprises a first heat exchange tube, a second heat exchange tube and a third heat exchange tube, wherein the first heat exchange tube passes through the left side tube, the second heat exchange tube passes through the central tube, and the third heat exchange tube passes through the right side tube; the first heat exchange tube, the second heat exchange tube and the third heat exchange tube respectively flow through the first fluid, the second fluid and the third fluid;
The shell side fluid is a cold source, and the first fluid, the second fluid and the third fluid are heat sources; the inlets of the first heat exchange tube, the second heat exchange tube and the third heat exchange tube are provided with a first valve, a second valve and a third valve respectively, and the first valve, the second valve and the third valve are in data connection with a controller;
the device comprises a left side pipe, a central pipe, a right side pipe, a first temperature sensor, a second temperature sensor and a third temperature sensor, wherein the first temperature sensor, the second temperature sensor and the third temperature sensor are respectively arranged in the left side pipe, the central pipe and the right side pipe and are used for detecting the temperatures in the left side pipe, the central pipe and the right side pipe, the first temperature sensor, the second temperature sensor and the third temperature sensor are in data connection with a controller, temperature data of the first temperature sensor, the second temperature sensor and the third temperature sensor are stored in a database in real time, a one-dimensional deep convolutional neural network is used for extracting data characteristics, pattern recognition is carried out, and accordingly opening and closing of a first valve, a second valve and a third valve are controlled, and whether heat exchange is carried out on first fluid, third fluid and second fluid is controlled.
The invention has the following advantages:
1. according to different operation conditions of the heat exchanger, the temperature data in the system is monitored in real time by the heat exchanger, a corresponding operation mode is designed, and a great amount of temperature data is used for training the deep convolution neural network, so that the heat exchange part is subjected to descaling, and the heat utilization effect and the descaling effect are improved. The shell-and-tube heat exchanger can realize periodic frequent vibration of the heat exchange tube, and improves the heating efficiency, thereby realizing good descaling and heating effects.
2. According to the invention, through controlling the opening and closing of the first valve, the second valve and the third valve, on one hand, continuous heat exchange is realized on the shell side flow, and meanwhile, the elastic heat exchange tube can vibrate periodically and frequently, so that good descaling and heat exchange effects are realized.
3. The invention designs that the flowing directions of the first fluid, the third fluid and the second fluid are opposite, and the flowing of the phase-change fluid is further promoted, so that the heat transfer is enhanced.
4. The invention designs a layout diagram of a heat exchange component with a novel structure in a shell, optimizes the optimal relation between parameters of a heat exchange tube and flow, specific heat and the like of fluid through a large number of experiments and numerical simulation, and creatively fuses the flow, specific heat, temperature and target temperature of the heat exchange fluid into the dimensional design of a heat exchanger relative to the previous design, so that the heat exchange efficiency can be further improved.
5. By reasonably changing the inner diameter and the spacing of the tube bundles of the heat exchange tubes along the flowing direction of the fluid in the shell, the heat exchange efficiency is improved.
Description of the drawings:
fig. 1 is a schematic view of a heat exchanger according to the present invention.
FIG. 2 is a schematic cut-away view of a heat exchange component of the present invention.
Fig. 3 is a top view of a heat exchange component.
Fig. 4 is a schematic view of a preferred construction of the heat exchanger.
Fig. 5 is a schematic view of another preferred construction of the heat exchanger.
Fig. 6 is a schematic view of a layout of heat exchange components disposed in a circular housing.
Fig. 7 is a schematic view of a preferred construction of the heat exchanger.
Fig. 8 is a schematic view of another preferred construction of the heat exchanger.
In the figure: 1. tube group, left tube group 11, right tube group 12, 21, left tube, 22, right tube, 3, free end, 4, free end, 5, free end, 6, free end, 7, annular tube, 8, center tube, 91-93, heat exchange tube, 10 first tube orifice, 13 second tube orifice, left return tube 14, right return tube 15, front tube sheet 16, support 17, support 18, rear tube sheet 19, shell 20, 21, shell side inlet header, 22, shell side outlet header, 23, heat exchange unit, 24 first valve, 25 second valve, 26 third valve, 27 inlet header, 28 outlet header
Detailed Description
A shell-and-tube heat exchanger, as shown in fig. 1, comprising a housing 20, heat exchange means 23, a shell side inlet connection 21 and a shell side outlet connection 22; the heat exchange component 23 is arranged in the shell 20 and is fixedly connected to the front tube plate 16 and the rear tube plate 19; the shell side inlet connecting pipe 21 and the shell side outlet connecting pipe 22 are arranged on the shell 20; fluid enters from the shell side inlet connecting pipe 21, exchanges heat through the heat exchange component, and exits from the shell side outlet connecting pipe 22.
Preferably, the heat exchange member of FIG. 2-1 extends in a horizontal direction. The heat exchangers are arranged in the horizontal direction.
Fig. 2 shows a top view of a heat exchange member 23, which, as shown in fig. 2, comprises a central tube 8, a left tube 21, a right tube 22 and a tube group 1, the tube group 1 comprising a left tube group 11 and a right tube group 12, the left tube group 11 being in communication with the left tube 21 and the central tube 8, the right tube group 12 being in communication with the right tube 22 and the central tube 8, such that the central tube 8, the left tube 21, the right tube 22 and the tube group 1 form a heating fluid closed cycle, the left tube 21 and/or the central tube 8 and/or the right tube 22 being filled with a phase change fluid, each tube group 1 comprising a plurality of annular tubes 7 in the shape of a circular arc, the ends of adjacent annular tubes 7 being in communication such that the plurality of annular tubes 7 form a series structure, and such that the ends of the annular tubes 7 form annular tube free ends 3-6; the central tube comprises a first tube orifice 10 and a second tube orifice 13, the first tube orifice 10 is connected with the inlet of the left tube group 11, the second tube orifice 13 is connected with the inlet of the right tube group 12, the outlet of the left tube group 11 is connected with the left tube 21, and the outlet of the right tube group 12 is connected with the right tube 22; the first nozzle 10 and the second nozzle 13 are arranged on the same side of the central tube 8.
Preferably, the left tube group and the right tube group are mirror-symmetrical along the plane where the axis of the center tube is located. As shown in FIG. 2-1
The ends of the two ends of the center tube 8, the left tube 21 and the right tube 22 are arranged in the openings of the front and rear tube plates 16, 19 for fixation. The first nozzle 10 and the second nozzle 13 are located on the upper side of the central tube 8.
The heat exchanger further comprises a first heat exchange tube 91, a second heat exchange tube 92 and a third heat exchange tube 93, wherein the first heat exchange tube 91 is arranged through the left side tube 21, the second heat exchange tube 92 is arranged through the central tube 8, and the third heat exchange tube 93 is arranged through the right side tube 22. The first heat exchange tube 91, the second heat exchange tube 92, and the third heat exchange tube 93 flow through the first fluid, the second fluid, and the third fluid, respectively. The heat exchange of the four fluids can be carried out among the first fluid, the second fluid, the third fluid and the shell side fluid. The four fluid heat sources can be 1-3, and the residual fluid is a cold source, or the cold source can be 1-3, and the residual fluid is a heat source.
As an example of the preferred heat exchange, for example, the heat exchange process is as follows:
the first fluid is a heat source, the second fluid, the third fluid and the shell side fluid are cold sources, the phase change fluid in the heat exchange component is subjected to phase change through heat exchange of the first fluid, so that the heat exchange shell side fluid is radiated outwards through the annular tube 7, meanwhile, vapor phase fluid enters the central tube and the right side tube to exchange heat with the second fluid and the third fluid, and condensed fluid after heat exchange returns to the right side tube through the return tube, so that four-fluid heat exchange is realized.
Preferably, the third fluid and the second fluid are heat sources, the first fluid and the shell side fluid are cold sources, the phase change fluid in the heat exchange component is subjected to phase change through heat exchange of the second fluid and the third fluid, so that the shell side fluid is subjected to heat exchange through the annular tube 7 in an outward radiating manner, meanwhile, the vapor phase fluid enters the left side tube to exchange heat with the first fluid, and the condensed fluid after heat exchange returns to the right tube box through the return tube, so that four-fluid heat exchange is realized.
Preferably, the shell-side fluid is a heat source, the first fluid, the second fluid and the third fluid are cold sources, and heat exchange is carried out through the shell-side fluid, so that the fluid in the heat exchange component absorbs heat and exchanges heat with the first fluid, the second fluid and the third fluid, and heat exchange of four fluids is realized.
Preferably, the first fluid and the third fluid are cold sources, the second fluid and the shell side fluid are heat sources, and heat exchange is realized through the second fluid and the shell side fluid, so that four-fluid heat exchange is realized.
Preferably, the second fluid is a cold source, the first fluid, the third fluid and the shell side fluid are heat sources, and the heat exchange is realized through the heat exchange of the first fluid, the third fluid and the shell side fluid, so that the heat exchange of four fluids is realized.
Preferably, the shell side fluid is a cold source, the first fluid, the second fluid and the third fluid are heat sources, and heat exchange is realized by the heat exchange between the first fluid, the second fluid and the third fluid and the shell side fluid.
Preferably, the first heat exchange tube, the second heat exchange tube and the third heat exchange tube have the same inner diameter.
Preferably, a left return pipe 14 is provided between the left side pipe 21 and the center pipe 8, and a right return pipe 14 is provided between the right side pipe 22 and the center pipe 8. Preferably, the return pipe is arranged at the end of the central pipe. The two ends of the central tube are preferred.
Preferably, the fluid is a phase change fluid, preferably a vapour-liquid phase change fluid.
The following focuses on the case where the shell-side fluid is a cold source and the first, second, and third fluids are heat sources.
The fluid is subjected to heat exchange evaporation in the central tube 8, flows along the annular tube bundle to the left and right headers 21 and 22, and after being heated, the fluid expands in volume to form steam, and the steam is far more in volume than water, so that the formed steam can quickly impact flow in the coil. Because the volume expansion and the steam flow can induce the free end of the annular tube to vibrate, the free end of the heat exchange tube transmits the vibration to surrounding heat exchange fluid in the vibration process, and the fluids can generate disturbance, so that the surrounding heat exchange fluid forms turbulence and damages a boundary layer, and the purpose of enhancing heat transfer is realized. The fluid flows back to the central tube through the return tube after the left and right side tubes condense and release heat. Conversely, the fluid can also exchange heat in the left and right side pipes, then enter the central pipe to be condensed and then return to the left and right side pipes for circulation through the return pipe.
According to the invention, the prior art is improved, the condensing (evaporating) header pipe and the pipe groups are respectively arranged into two pipes which are distributed left and right, so that the pipe groups distributed on the left side and the right side can perform vibration heat exchange and scale removal, thereby enlarging the heat exchange vibration area, enabling the vibration to be more uniform, enabling the heat exchange effect to be more uniform, increasing the heat exchange area and strengthening the heat exchange and scale removal effects.
The flow rate in this application refers to a flow rate per unit time, unless otherwise specified. The unit is m 3 /s。
Preferably, as shown in fig. 7 and 8, the first valve 24, the second valve 25 and the third valve 26 are provided at the inlets of the first heat exchange tube 91, the second heat exchange tube 92 and the third heat exchange tube 93, the first valve 24, the second valve 25 and the third valve 26 are in data connection with a controller, and the opening and closing and opening sizes of the first valve 24, the second valve 25 and the third valve 26 are controlled by the controller so as to control the flow rate of the heat exchange fluid entering the first heat exchange tube 91, the second heat exchange tube 92 and the third heat exchange tube 93.
Preferably, the position of the right tube group is a position in which the left tube group is rotated 180 degrees along the axis of the center tube. Fig. 2-2. The heat exchange member is preferably arranged in a vertical direction. Preferably, the heat exchange member extends in a vertical direction. The heat exchangers are arranged in the vertical direction. Preferably, the shell side fluid is a gas. The gas is preferably air, or carbon dioxide gas.
It has been found in research and practice that heat exchange from a sustained power-stable heat source results in stability of the fluid formation of the internal heat exchange components, i.e., no or little fluid flow, or stable flow, resulting in a significant reduction in the vibrational performance of the annular tube 7, thereby affecting the descaling of the left tube bank 11 and the right tube bank 12 and the efficiency of heat exchange. There is a need for improvements in the heat exchangers described above as follows.
In the previous application of the inventor, a periodic heat exchange mode is provided, and the vibration of the annular tube is continuously promoted by the periodic heat exchange mode, so that the heat exchange efficiency and the descaling effect are improved. However, by adjusting the vibration of the tube bundle by a fixed periodic variation, hysteresis may occur and the period may be too long or too short. Therefore, the invention improves the prior application and intelligently controls the vibration, so that the fluid in the interior can vibrate frequently, and the scale removal and heat exchange effects are very good.
Aiming at the defects in the prior research technology, the invention provides a novel intelligent vibration control heat exchanger. The heat exchanger can improve the heat exchange efficiency, thereby realizing good descaling and heat exchange effects.
1. Autonomous pressure-based adjustment of vibration
Preferably, the left pipe 21, the central pipe 8 and the right pipe 22 are respectively provided with a first pressure sensor, a second pressure sensor and a third pressure sensor, which are used for detecting the pressures in the left pipe, the central pipe and the right pipe, the first pressure sensor, the second pressure sensor and the third pressure sensor are in data connection with a controller, the pressure data of the first pressure sensor, the second pressure sensor and the third pressure sensor are stored in a database in real time, a one-dimensional deep convolutional neural network is adopted for extracting data characteristics, and pattern recognition is performed, so that the opening and the closing of the first valve 24, the second valve 25 and the third valve 26 are controlled, and whether the first fluid, the third fluid and the second fluid exchange heat or not is controlled.
The pressure-based autonomous tuning vibration pattern recognition includes the steps of:
1. data preparation: and rechecking and checking the pressure data in the database, correcting the missing data, invalid data and inconsistent data, and ensuring the correctness and logical consistency of the data.
2. Generating a data set: the prepared data is divided into training set/training set labels, and detection set/detection set labels.
3. Training a network: and inputting the training set data into a convolutional neural network, continuously carrying out convolution and pooling to obtain feature vectors, and sending the feature vectors into a fully connected network. And obtaining a network error by calculating the output of the network and the training set label, and continuously correcting the network weight, the bias, the convolution coefficient and the pooling coefficient by using an error back propagation algorithm to ensure that the error meets the set precision requirement, thereby completing the network training.
4. Network detection: inputting the detection set data into the trained network, and outputting the detection result label.
5. The heat exchanger operates: the label controls the opening and closing of the first valve 24, the second valve 25 and the third valve 26 according to the detection result to perform descaling.
The invention provides a novel intelligent control heat exchange device vibration descaling system, which is based on a theoretical method of machine learning and pattern recognition, and according to different operation conditions of a heat exchanger, pressure data with time correlation in a centralized heat exchanger real-time monitoring system are utilized to design corresponding heat exchanger working states (opening and closing states of a first valve 24, a second valve 25 and a third valve 26), and a large amount of pressure data are used for training a deep convolutional neural network, so that heat exchange descaling control of the heat exchanger is performed.
Preferably, the data preparation step specifically includes the following processes:
1) Processing of missing data: due to network transmission failures, missing values may occur in the database. For the missing data value, adopting an estimation method, and replacing the missing value by a sample mean value;
2) Processing invalid data: due to a failure of the sensor, invalid values, such as negative values or exceeding a theoretical maximum value, are present in the pressure data in the database, for which values they are deleted from the database;
3) Processing inconsistent data: by means of the integrity constraint mechanism of the database management system, inconsistent data is checked and then corrected with reference to corresponding data values in the database. Preferably, in the heat exchanger, the heating pipe pressure of the first valve 24, the second valve 25 and the third valve 26 is higher than the non-heating pipe pressure, if the heating pipe pressure in the database is lower than the non-heating pipe pressure, a user error prompt can be given by means of checking constraint mechanism in the integrity constraint of the database management system, and the user replaces the pressure data value of the inconsistent data with the estimated data or the corresponding critical pressure data value according to the error prompt.
Preferably, the step of generating the data set comprises the steps of:
1) Generating training set data and labels: and reading pressure data values of corresponding working conditions from a database according to different operation working conditions of the heat collecting device, and generating training set data and working condition labels under various working conditions. Preferably, in a specific application, the operating condition is divided into a label of 1, a first valve and a third valve are closed, a second valve is in an open state, a label of 2, the first valve and the third valve are open, and the second valve is in a closed state. The program automatically generates a working condition label according to different working conditions;
preferably, the data includes data that the evaporation of fluid within the internal heat exchange component has substantially reached saturation or stability under different conditions. The working condition comprises at least one of valve opening, heat exchange fluid temperature and the like.
2) Generating detection set data and labels: and reading pressure data values of corresponding working conditions from a database according to different operation working conditions of the heat exchanger, and generating detection set data and working condition labels under various working conditions. The working condition label is the same as the working condition label of the training set and is automatically generated by a program according to the operation working condition.
Preferably, it is determined whether the evaporation of the fluid inside the left tube box, the right tube box (the first valve is opened by the third valve) or the intermediate tube box (the second valve is opened) is saturated or stabilized (reaches or exceeds a certain pressure). For example, the left pipe box and the right pipe box are not saturated or stable, the label is 11, the saturation or stability is reached, the label is 12, the middle pipe box is not saturated or stable, the label is 21, the saturation or stability is reached, and the label is 22.
The specific steps of the network training are as follows:
1) Reading a group of training set data d, wherein the size of the training set data d is [ M multiplied by 1 multiplied by N ], M represents the size of a training batch, and 1 multiplied by N represents one-dimensional training data;
2) And performing a first convolution operation on the read training data to obtain a feature map t. Initializing a coefficient of a convolution kernel g, wherein the size of g is set as [ P multiplied by 1 multiplied by Q ], P represents the number of the convolution kernels, [1 multiplied by Q ] represents the size of the convolution kernels, the obtained convolution result is t multiplied by (d multiplied by g), and the size of a feature map is [ M multiplied by 1 multiplied by N multiplied by Q ];
3) And carrying out maximum pooling operation on the characteristic diagram t obtained by the convolution operation to obtain a characteristic diagram z. Initializing a pooling coefficient, setting the pooling step length as p, the pooling window size as k, and finally obtaining the characteristic map z with the size of [ Mx1× (N/p) xQ ], wherein the pooling process reduces the dimension of data;
4) Repeating the steps 2) -3), repeatedly carrying out convolution and pooling operation to obtain a feature vector x, and completing the feature extraction process of the convolution neural network;
5) Initializing a weight matrix w and a bias b of the fully-connected network, and sending the extracted feature vector x into the fully-connected network, and calculating with the weight matrix w and the bias b to obtain a network output y= Σ (w x x+b);
6) Subtracting the output y obtained by the network from the training set label l to obtain a network error e=y-l, deriving the network error, and sequentially correcting the weight w, the bias b, the pooling coefficient of each layer and the convolution coefficient of each layer of the fully-connected network by using the derivative back propagation;
7) Repeating the above process until the network error e meets the precision requirement, and completing the network training process to generate the convolutional neural network model.
When the first valve and the third valve are opened and the second valve is closed, the data are measured by the first pressure sensor and the third pressure sensor. Preferably, an average value of the first third pressure is used. When the first valve and the third valve are closed and the second valve is opened, the data is measured by the second pressure sensor.
The network detection steps specifically include the following steps:
1) Loading a trained convolutional neural network model, wherein the convolutional kernel coefficient, the pooling coefficient and the network weight w of the convolutional neural network are trained, and the bias b is trained;
2) And inputting the detection data set into the trained convolutional neural network, and outputting a detection result. The type of operation can be determined, for example, based on the output tag. For example, 1 represents that the first valve, the third valve are open, the second valve is closed, 2 represents that the first valve, the third valve are closed, the second valve is open, etc.
The invention provides a novel method for controlling heat exchange of the heat exchanger, which fully utilizes the online monitoring data of the heat exchanger, and has the advantages of high detection speed and low cost.
The invention organically integrates the data processing technology, the machine learning and the pattern recognition theory, and can improve the operation accuracy of the heat exchanger.
The working process of the specific convolutional neural network is as follows:
1) Inputting a group of training set data d with the size of [ M x 1 x N ], wherein M represents the size of a training batch, and 1 x N represents one-dimensional training data;
2) And performing a first convolution operation on the read training data to obtain a feature map t. Initializing a coefficient of a convolution kernel g, wherein the size of g is set as [ P multiplied by 1 multiplied by Q ], P represents the number of the convolution kernels, [1 multiplied by Q ] represents the size of the convolution kernels, the obtained convolution result is t multiplied by (d multiplied by g), and the size of a feature map is [ M multiplied by 1 multiplied by N multiplied by Q ];
3) And carrying out maximum pooling operation on the characteristic diagram t obtained by the convolution operation to obtain a characteristic diagram z. Initializing a pooling coefficient, setting the pooling step length as p, setting the pooling window size as k, and finally obtaining the characteristic map z with the size of [ Mx1× (N/p) xQ ], wherein the pooling process reduces the dimension of data;
4) Repeating the steps 2) -3), and repeatedly carrying out convolution and pooling operation to obtain a feature vector;
according to the method, based on a theoretical method of machine memory and mode identification, according to different operation conditions of the heat exchanger, the pressure data in the system is monitored in real time by the heat exchanger, a corresponding operation mode is designed, and a large amount of pressure data is used for training a deep convolutional neural network, so that heat exchange part descaling is performed, and the heat utilization effect and the descaling effect are improved. The shell-and-tube heat exchanger can realize periodic frequent vibration of the heat exchange tube, and improves the heating efficiency, thereby realizing good descaling and heating effects.
According to the invention, based on a theoretical method of machine memory and pattern recognition, the pressure detected by the pressure sensing element can basically saturate evaporation of fluid in the left side pipe, the right side pipe or the central pipe under the condition of meeting a certain pressure, and the volume of the internal fluid basically changes little. Therefore, new fluid is started to perform alternate heat exchange by detecting the pressure changes in the left side pipe, the right side pipe and the central pipe, and the heat exchange effect and the descaling effect are improved.
The invention can be based on a theoretical method of machine memory and pattern recognition, so that the detection and judgment results are more accurate.
2. Autonomously adjusting vibration based on temperature
Preferably, the left side pipe 21, the central pipe 8 and the right side pipe 22 are respectively provided with a first temperature sensor, a second temperature sensor and a third temperature sensor, which are used for detecting the temperatures in the left side pipe, the central pipe and the right side pipe, the first temperature sensor, the second temperature sensor and the third temperature sensor are in data connection with a controller, the temperature data of the first temperature sensor, the second temperature sensor and the third temperature sensor are stored in a database in real time, a one-dimensional deep convolutional neural network is adopted for extracting data characteristics, and pattern recognition is performed, so that the opening and the closing of the first valve 24, the second valve 25 and the third valve 26 are controlled, and whether the first fluid, the third fluid and the second fluid exchange heat or not are controlled.
The temperature-based autonomous tuning vibration pattern recognition includes the steps of:
1. data preparation: and (3) rechecking and checking the temperature data in the database, correcting the missing data, invalid data and inconsistent data, and ensuring the correctness and logical consistency of the data.
2. Generating a data set: the prepared data is divided into training set/training set labels, and detection set/detection set labels.
3. Training a network: and inputting the training set data into a convolutional neural network, continuously carrying out convolution and pooling to obtain feature vectors, and sending the feature vectors into a fully connected network. And obtaining a network error by calculating the output of the network and the training set label, and continuously correcting the network weight, the bias, the convolution coefficient and the pooling coefficient by using an error back propagation algorithm to ensure that the error meets the set precision requirement, thereby completing the network training.
4. Network detection: inputting the detection set data into the trained network, and outputting the detection result label.
5. The heat exchanger operates: the label controls the opening and closing of the first valve 24, the second valve 25 and the third valve 26 according to the detection result to perform descaling.
The invention provides a novel intelligent control heat exchange device vibration descaling system, which is based on a theoretical method of machine learning and pattern recognition, and according to different operation conditions of a heat exchanger, temperature data with time correlation in a centralized heat exchanger real-time monitoring system are utilized to design corresponding heat exchanger working states (opening and closing states of a first valve 24, a second valve 25 and a third valve 26), and a large amount of temperature data are used for training a deep convolutional neural network, so that heat exchange descaling control of the heat exchanger is performed.
Preferably, the data preparation step specifically includes the following processes:
1) Processing of missing data: due to network transmission failures, missing values may occur in the database. For the missing data value, adopting an estimation method, and replacing the missing value by a sample mean value;
2) Processing invalid data: due to a failure of the sensor, invalid values, such as negative values or exceeding a theoretical maximum value, are present in the temperature data in the database, for which values they are deleted from the database;
3) Processing inconsistent data: by means of the integrity constraint mechanism of the database management system, inconsistent data is checked and then corrected with reference to corresponding data values in the database. Preferably, in the heat exchanger, the heating tube temperatures of the first valve 24, the second valve 25 and the third valve 26 are higher than the non-heating tube temperatures, and if the heating tube temperatures in the database are lower than the non-heating tube temperatures, a user error prompt can be given by means of an inspection constraint mechanism in the integrity constraint of the database management system, and the user replaces the temperature data value of the inconsistent data with the estimated data or the corresponding critical temperature data value according to the error prompt.
Preferably, the step of generating the data set comprises the steps of:
1) Generating training set data and labels: and reading temperature data values of corresponding working conditions from a database according to different operation working conditions of the heat collecting device, and generating training set data and working condition labels under various working conditions. Preferably, in a specific application, the operating condition is divided into a label of 1, a first valve and a third valve are closed, a second valve is in an open state, a label of 2, the first valve and the third valve are open, and the second valve is in a closed state. The program automatically generates a working condition label according to different working conditions;
preferably, the data includes data that the evaporation of fluid within the internal heat exchange component has substantially reached saturation or stability under different conditions. The working condition comprises at least one of valve opening, heat exchange fluid temperature and the like.
2) Generating detection set data and labels: and reading temperature data values of corresponding working conditions from a database according to different operation working conditions of the heat exchanger, and generating detection set data and working condition labels under various working conditions. The working condition label is the same as the working condition label of the training set and is automatically generated by a program according to the operation working condition.
Preferably, it is determined whether the evaporation of the fluid inside the left tube box, the right tube box (the first valve is opened with the third valve opened) or the intermediate tube box (the second valve is opened) is saturated or stabilized (reaches or exceeds a certain temperature). For example, the left pipe box and the right pipe box are not saturated or stable, the label is 11, the saturation or stability is reached, the label is 12, the middle pipe box is not saturated or stable, the label is 21, the saturation or stability is reached, and the label is 22.
The specific steps of the network training are as follows:
1) Reading a group of training set data d, wherein the size of the training set data d is [ M multiplied by 1 multiplied by N ], M represents the size of a training batch, and 1 multiplied by N represents one-dimensional training data;
2) And performing a first convolution operation on the read training data to obtain a feature map t. Initializing a coefficient of a convolution kernel g, wherein the size of g is set as [ P multiplied by 1 multiplied by Q ], P represents the number of the convolution kernels, [1 multiplied by Q ] represents the size of the convolution kernels, the obtained convolution result is t multiplied by (d multiplied by g), and the size of a feature map is [ M multiplied by 1 multiplied by N multiplied by Q ];
3) And carrying out maximum pooling operation on the characteristic diagram t obtained by the convolution operation to obtain a characteristic diagram z. Initializing a pooling coefficient, setting the pooling step length as p, the pooling window size as k, and finally obtaining the characteristic map z with the size of [ Mx1× (N/p) xQ ], wherein the pooling process reduces the dimension of data;
4) Repeating the steps 2) -3), repeatedly carrying out convolution and pooling operation to obtain a feature vector x, and completing the feature extraction process of the convolution neural network;
5) Initializing a weight matrix w and a bias b of the fully-connected network, and sending the extracted feature vector x into the fully-connected network, and calculating with the weight matrix w and the bias b to obtain a network output y= Σ (w x x+b);
6) Subtracting the output y obtained by the network from the training set label l to obtain a network error e=y-l, deriving the network error, and sequentially correcting the weight w, the bias b, the pooling coefficient of each layer and the convolution coefficient of each layer of the fully-connected network by using the derivative back propagation;
7) Repeating the above process until the network error e meets the precision requirement, and completing the network training process to generate the convolutional neural network model.
When the first valve and the third valve are opened and the second valve is closed, the data are measured by the first temperature sensor and the third temperature sensor. Preferably, an average value of the first and third temperatures is used. When the first valve and the third valve are closed and the second valve is opened, the data measured by the second temperature sensor is adopted as the data.
The network detection steps specifically include the following steps:
1) Loading a trained convolutional neural network model, wherein the convolutional kernel coefficient, the pooling coefficient and the network weight w of the convolutional neural network are trained, and the bias b is trained;
2) And inputting the detection data set into the trained convolutional neural network, and outputting a detection result. The type of operation can be determined, for example, based on the output tag. For example, 1 represents that the first valve, the third valve are open, the second valve is closed, 2 represents that the first valve, the third valve are closed, the second valve is open, etc.
The invention provides a novel method for controlling heat exchange of the heat exchanger, which fully utilizes the online monitoring data of the heat exchanger, and has the advantages of high detection speed and low cost.
The invention organically integrates the data processing technology, the machine learning and the pattern recognition theory, and can improve the operation accuracy of the heat exchanger.
The working process of the specific convolutional neural network is as follows:
1) Inputting a group of training set data d with the size of [ M x 1 x N ], wherein M represents the size of a training batch, and 1 x N represents one-dimensional training data;
2) And performing a first convolution operation on the read training data to obtain a feature map t. Initializing a coefficient of a convolution kernel g, wherein the size of g is set as [ P multiplied by 1 multiplied by Q ], P represents the number of the convolution kernels, [1 multiplied by Q ] represents the size of the convolution kernels, the obtained convolution result is t multiplied by (d multiplied by g), and the size of a feature map is [ M multiplied by 1 multiplied by N multiplied by Q ];
3) And carrying out maximum pooling operation on the characteristic diagram t obtained by the convolution operation to obtain a characteristic diagram z. Initializing a pooling coefficient, setting the pooling step length as p, setting the pooling window size as k, and finally obtaining the characteristic map z with the size of [ Mx1× (N/p) xQ ], wherein the pooling process reduces the dimension of data;
4) Repeating the steps 2) -3), and repeatedly carrying out convolution and pooling operation to obtain a feature vector;
according to the method, based on a theoretical method of machine memory and mode identification, according to different operation conditions of the heat exchanger, the temperature data in the system is monitored in real time by the heat exchanger, a corresponding operation mode is designed, and a large amount of temperature data is used for training a deep convolutional neural network, so that heat exchange components are descaled, and the heat utilization effect and the descaling effect are improved. The shell-and-tube heat exchanger can realize periodic frequent vibration of the heat exchange tube, and improves the heating efficiency, thereby realizing good descaling and heating effects.
According to the invention, based on a theoretical method of machine memory and pattern recognition, the temperature detected by the temperature sensing element can basically reach saturation of evaporation of fluid in the left side pipe, the right side pipe or the central pipe under the condition of meeting a certain temperature, and the volume of the internal fluid is basically not changed greatly. Therefore, new fluid is started to perform alternate heat exchange by detecting temperature changes in the left side pipe, the right side pipe and the central pipe, and the heat exchange effect and the descaling effect are improved.
The invention can be based on a theoretical method of machine memory and pattern recognition, so that the detection and judgment results are more accurate.
3. Autonomous adjustment of vibration based on liquid level
Preferably, the left pipe 21, the central pipe 8 and the right pipe 22 are respectively provided with a first liquid level sensor, a second liquid level sensor and a third liquid level sensor, which are used for detecting the liquid levels in the left pipe, the central pipe and the right pipe, the first liquid level sensor, the second liquid level sensor and the third liquid level sensor are in data connection with a controller, liquid level data of the first liquid level sensor, the second liquid level sensor and the third liquid level sensor are stored in a database in real time, a one-dimensional deep convolutional neural network is adopted for extracting data characteristics, and pattern recognition is performed, so that the opening and the closing of the first valve 24, the second valve 25 and the third valve 26 are controlled, and whether the first fluid, the third fluid and the second fluid exchange heat or not are controlled.
The autonomous liquid level based adjustment vibration pattern recognition includes the steps of:
1. data preparation: rechecking and checking the liquid level data in the database, correcting the missing data, invalid data and inconsistent data, and ensuring the correctness and logical consistency of the data.
2. Generating a data set: the prepared data is divided into training set/training set labels, and detection set/detection set labels.
3. Training a network: and inputting the training set data into a convolutional neural network, continuously carrying out convolution and pooling to obtain feature vectors, and sending the feature vectors into a fully connected network. And obtaining a network error by calculating the output of the network and the training set label, and continuously correcting the network weight, the bias, the convolution coefficient and the pooling coefficient by using an error back propagation algorithm to ensure that the error meets the set precision requirement, thereby completing the network training.
4. Network detection: inputting the detection set data into the trained network, and outputting the detection result label.
5. The heat exchanger operates: the label controls the opening and closing of the first valve 24, the second valve 25 and the third valve 26 according to the detection result to perform descaling.
The invention provides a novel intelligent control heat exchange device vibration descaling system, which is based on a theoretical method of machine learning and pattern recognition, and according to different operation conditions of a heat exchanger, liquid level data with time correlation in a centralized heat exchanger real-time monitoring system is utilized to design corresponding heat exchanger working states (opening and closing states of a first valve 24, a second valve 25 and a third valve 26), and a large amount of liquid level data is used for training a deep convolutional neural network so as to control heat exchange descaling of the heat exchanger.
Preferably, the data preparation step specifically includes the following processes:
1) Processing of missing data: due to network transmission failures, missing values may occur in the database. For the missing data value, adopting an estimation method, and replacing the missing value by a sample mean value;
2) Processing invalid data: due to a malfunction of the sensor, invalid values, such as negative values or exceeding a theoretical maximum value, are present in the liquid level data in the database, for which values they are deleted from the database;
3) Processing inconsistent data: by means of the integrity constraint mechanism of the database management system, inconsistent data is checked and then corrected with reference to corresponding data values in the database. Preferably, in the heat exchanger, the heating tube liquid level of the first valve 24, the second valve 25 and the third valve 26 is smaller than the liquid level of the non-heating tube, if the heating tube liquid level in the database is larger than the liquid level of the non-heating tube, a user error prompt can be given by means of an inspection constraint mechanism in the integrity constraint of the database management system, and the user replaces the liquid level data value of the inconsistent data with the estimated data or the corresponding critical liquid level data value according to the error prompt.
Preferably, the step of generating the data set comprises the steps of:
1) Generating training set data and labels: according to different operation conditions of the heat collecting device, liquid level data values of corresponding conditions are read from a database, and training set data and condition labels in various conditions are generated. Preferably, in a specific application, the operating condition is divided into a label of 1, a first valve and a third valve are closed, a second valve is in an open state, a label of 2, the first valve and the third valve are open, and the second valve is in a closed state. The program automatically generates a working condition label according to different working conditions;
preferably, the data includes data that the evaporation of fluid within the internal heat exchange component has substantially reached saturation or stability under different conditions. The working condition comprises at least one of valve opening, heat exchange fluid temperature and the like.
2) Generating detection set data and labels: according to different operation conditions of the heat exchanger, reading liquid level data values of corresponding conditions from a database, and generating detection set data and condition labels under various conditions. The working condition label is the same as the working condition label of the training set and is automatically generated by a program according to the operation working condition.
Preferably, it is determined whether the evaporation of the fluid inside the left tube box, the right tube box (the first valve is opened with the third valve opened) or the intermediate tube box (the second valve is opened) is saturated or stabilized (reaches or falls below a certain liquid level). For example, the left pipe box and the right pipe box are not saturated or stable, the label is 11, the saturation or stability is reached, the label is 12, the middle pipe box is not saturated or stable, the label is 21, the saturation or stability is reached, and the label is 22.
The specific steps of the network training are as follows:
1) Reading a group of training set data d, wherein the size of the training set data d is [ M multiplied by 1 multiplied by N ], M represents the size of a training batch, and 1 multiplied by N represents one-dimensional training data;
2) And performing a first convolution operation on the read training data to obtain a feature map t. Initializing a coefficient of a convolution kernel g, wherein the size of g is set as [ P multiplied by 1 multiplied by Q ], P represents the number of the convolution kernels, [1 multiplied by Q ] represents the size of the convolution kernels, the obtained convolution result is t multiplied by (d multiplied by g), and the size of a feature map is [ M multiplied by 1 multiplied by N multiplied by Q ];
3) And carrying out maximum pooling operation on the characteristic diagram t obtained by the convolution operation to obtain a characteristic diagram z. Initializing a pooling coefficient, setting the pooling step length as p, the pooling window size as k, and finally obtaining the characteristic map z with the size of [ Mx1× (N/p) xQ ], wherein the pooling process reduces the dimension of data;
4) Repeating the steps 2) -3), repeatedly carrying out convolution and pooling operation to obtain a feature vector x, and completing the feature extraction process of the convolution neural network;
5) Initializing a weight matrix w and a bias b of the fully-connected network, and sending the extracted feature vector x into the fully-connected network, and calculating with the weight matrix w and the bias b to obtain a network output y= Σ (w x x+b);
6) Subtracting the output y obtained by the network from the training set label l to obtain a network error e=y-l, deriving the network error, and sequentially correcting the weight w, the bias b, the pooling coefficient of each layer and the convolution coefficient of each layer of the fully-connected network by using the derivative back propagation;
7) Repeating the above process until the network error e meets the precision requirement, and completing the network training process to generate the convolutional neural network model.
When the first valve and the third valve are opened and the second valve is closed, the data are measured by the first liquid level sensor and the third liquid level sensor. Preferably, an average value of the first third liquid level is used. When the first valve and the third valve are closed and the second valve is opened, the data is measured by the second liquid level sensor.
The network detection steps specifically include the following steps:
1) Loading a trained convolutional neural network model, wherein the convolutional kernel coefficient, the pooling coefficient and the network weight w of the convolutional neural network are trained, and the bias b is trained;
2) And inputting the detection data set into the trained convolutional neural network, and outputting a detection result. The type of operation can be determined, for example, based on the output tag. For example, 1 represents that the first valve, the third valve are open, the second valve is closed, 2 represents that the first valve, the third valve are closed, the second valve is open, etc.
The invention provides a novel method for controlling heat exchange of the heat exchanger, which fully utilizes the online monitoring data of the heat exchanger, and has the advantages of high detection speed and low cost.
The invention organically integrates the data processing technology, the machine learning and the pattern recognition theory, and can improve the operation accuracy of the heat exchanger.
The working process of the specific convolutional neural network is as follows:
1) Inputting a group of training set data d with the size of [ M x 1 x N ], wherein M represents the size of a training batch, and 1 x N represents one-dimensional training data;
2) And performing a first convolution operation on the read training data to obtain a feature map t. Initializing a coefficient of a convolution kernel g, wherein the size of g is set as [ P multiplied by 1 multiplied by Q ], P represents the number of the convolution kernels, [1 multiplied by Q ] represents the size of the convolution kernels, the obtained convolution result is t multiplied by (d multiplied by g), and the size of a feature map is [ M multiplied by 1 multiplied by N multiplied by Q ];
3) And carrying out maximum pooling operation on the characteristic diagram t obtained by the convolution operation to obtain a characteristic diagram z. Initializing a pooling coefficient, setting the pooling step length as p, setting the pooling window size as k, and finally obtaining the characteristic map z with the size of [ Mx1× (N/p) xQ ], wherein the pooling process reduces the dimension of data;
4) Repeating the steps 2) -3), and repeatedly carrying out convolution and pooling operation to obtain a feature vector;
the invention can design a corresponding operation mode by utilizing the liquid level data in the real-time monitoring system of the heater according to different operation conditions of the heat exchanger based on a theoretical method of machine memory and mode identification through the mode identification of the liquid level detected by the liquid level sensing element, and trains a deep convolution neural network by utilizing a large amount of liquid level data, thereby carrying out descaling on heat exchange components and improving the heat utilization effect and the descaling effect. The shell-and-tube heat exchanger can realize periodic frequent vibration of the heat exchange tube, and improves the heating efficiency, thereby realizing good descaling and heating effects.
According to the invention, based on a theoretical method of machine memory and pattern recognition, the liquid level detected by the liquid level sensing element can basically saturate evaporation of fluid in the left side pipe, the right side pipe or the central pipe under the condition of meeting a certain liquid level, and the volume of the internal fluid basically changes little. Therefore, new fluid is started to perform alternate heat exchange by detecting the liquid level changes in the left side pipe, the right side pipe and the central pipe, and the heat exchange effect and the descaling effect are improved.
The invention can be based on a theoretical method of machine memory and pattern recognition, so that the detection and judgment results are more accurate.
4. Autonomous speed-based adjustment of vibration
Preferably, a speed sensing element is arranged in the free end of the tube bundle and is used for detecting the flow velocity of fluid in the free end of the tube bundle, the speed sensing element is in data connection with a controller, speed data of the speed sensor is stored in a database in real time, a one-dimensional deep convolutional neural network is adopted to extract data characteristics, and pattern recognition is carried out, so that the opening and closing of the first valve 24, the second valve 25 and the third valve 26 are controlled, and whether the first fluid, the third fluid and the second fluid exchange heat or not is controlled.
The speed-based autonomous tuning vibration pattern recognition includes the steps of:
1. data preparation: and (3) rechecking and checking the speed data in the database, correcting the missing data, invalid data and inconsistent data, and ensuring the correctness and logical consistency of the data.
2. Generating a data set: the prepared data is divided into training set/training set labels, and detection set/detection set labels.
3. Training a network: and inputting the training set data into a convolutional neural network, continuously carrying out convolution and pooling to obtain feature vectors, and sending the feature vectors into a fully connected network. And obtaining a network error by calculating the output of the network and the training set label, and continuously correcting the network weight, the bias, the convolution coefficient and the pooling coefficient by using an error back propagation algorithm to ensure that the error meets the set precision requirement, thereby completing the network training.
4. Network detection: inputting the detection set data into the trained network, and outputting the detection result label.
5. The heat exchanger operates: the label controls the opening and closing of the first valve 24, the second valve 25 and the third valve 26 according to the detection result to perform descaling.
The invention provides a novel intelligent control heat exchange device vibration descaling system, which is based on a theoretical method of machine learning and pattern recognition, and according to different operation conditions of a heat exchanger, corresponding heat exchanger working states (opening and closing states of a first valve 24, a second valve 25 and a third valve 26) are designed by utilizing speed data with time correlation in a centralized heat exchanger real-time monitoring system, and a great amount of speed data are used for training a deep convolutional neural network so as to control heat exchange descaling of the heat exchanger.
Preferably, the data preparation step specifically includes the following processes:
1) Processing of missing data: due to network transmission failures, missing values may occur in the database. For the missing data value, adopting an estimation method, and replacing the missing value by a sample mean value;
2) Processing invalid data: due to a failure of the sensor, invalid values, such as negative values or exceeding a theoretical maximum value, are present in the speed data in the database, for which values they are deleted from the database;
3) Processing inconsistent data: by means of the integrity constraint mechanism of the database management system, inconsistent data is checked and then corrected with reference to corresponding data values in the database. Preferably, in the heat exchanger, the heating pipe speed of the first valve 24, the second valve 25 and the third valve 26 is higher than that of the non-heating pipe, if the heating pipe speed in the database is lower than that of the non-heating pipe, the checking constraint mechanism in the integrity constraint of the database management system can be used for giving a user error prompt, and the user replaces the speed data value of the inconsistent data with the estimated data or the corresponding critical speed data value according to the error prompt.
Preferably, the step of generating the data set comprises the steps of:
1) Generating training set data and labels: and reading the speed data value of the corresponding working condition from the database according to different operation working conditions of the heat collecting device, and generating training set data and working condition labels under various working condition states. Preferably, in a specific application, the operating condition is divided into a label of 1, a first valve and a third valve are closed, a second valve is in an open state, a label of 2, the first valve and the third valve are open, and the second valve is in a closed state. The program automatically generates a working condition label according to different working conditions;
preferably, the data includes data that the evaporation of fluid within the internal heat exchange component has substantially reached saturation or stability under different conditions. The working condition comprises at least one of valve opening, heat exchange fluid temperature and the like.
2) Generating detection set data and labels: and reading the speed data value of the corresponding working condition from the database according to different operation working conditions of the heat exchanger, and generating detection set data and working condition labels under various working condition states. The working condition label is the same as the working condition label of the training set and is automatically generated by a program according to the operation working condition.
Preferably, it is determined whether the evaporation of the fluid inside the left tube box, the right tube box (the first valve is opened by the third valve) or the intermediate tube box (the second valve is opened) is saturated or stabilized (reaches or exceeds a certain speed). For example, the left pipe box and the right pipe box are not saturated or stable, the label is 11, the saturation or stability is reached, the label is 12, the middle pipe box is not saturated or stable, the label is 21, the saturation or stability is reached, and the label is 22.
The specific steps of the network training are as follows:
1) Reading a group of training set data d, wherein the size of the training set data d is [ M multiplied by 1 multiplied by N ], M represents the size of a training batch, and 1 multiplied by N represents one-dimensional training data;
2) And performing a first convolution operation on the read training data to obtain a feature map t. Initializing a coefficient of a convolution kernel g, wherein the size of g is set as [ P multiplied by 1 multiplied by Q ], P represents the number of the convolution kernels, [1 multiplied by Q ] represents the size of the convolution kernels, the obtained convolution result is t multiplied by (d multiplied by g), and the size of a feature map is [ M multiplied by 1 multiplied by N multiplied by Q ];
3) And carrying out maximum pooling operation on the characteristic diagram t obtained by the convolution operation to obtain a characteristic diagram z. Initializing a pooling coefficient, setting the pooling step length as p, the pooling window size as k, and finally obtaining the characteristic map z with the size of [ Mx1× (N/p) xQ ], wherein the pooling process reduces the dimension of data;
4) Repeating the steps 2) -3), repeatedly carrying out convolution and pooling operation to obtain a feature vector x, and completing the feature extraction process of the convolution neural network;
5) Initializing a weight matrix w and a bias b of the fully-connected network, and sending the extracted feature vector x into the fully-connected network, and calculating with the weight matrix w and the bias b to obtain a network output y= Σ (w x x+b);
6) Subtracting the output y obtained by the network from the training set label l to obtain a network error e=y-l, deriving the network error, and sequentially correcting the weight w, the bias b, the pooling coefficient of each layer and the convolution coefficient of each layer of the fully-connected network by using the derivative back propagation;
7) Repeating the above process until the network error e meets the precision requirement, and completing the network training process to generate the convolutional neural network model.
When the first valve and the third valve are opened and the second valve is closed, data in one direction are adopted by the data. When the first valve and the third valve are closed and the second valve is opened, the data adopts the data in the opposite direction.
The network detection steps specifically include the following steps:
1) Loading a trained convolutional neural network model, wherein the convolutional kernel coefficient, the pooling coefficient and the network weight w of the convolutional neural network are trained, and the bias b is trained;
2) And inputting the detection data set into the trained convolutional neural network, and outputting a detection result. The type of operation can be determined, for example, based on the output tag. For example, 1 represents that the first valve, the third valve are open, the second valve is closed, 2 represents that the first valve, the third valve are closed, the second valve is open, etc.
The invention provides a novel method for controlling heat exchange of the heat exchanger, which fully utilizes the online monitoring data of the heat exchanger, and has the advantages of high detection speed and low cost.
The invention organically integrates the data processing technology, the machine learning and the pattern recognition theory, and can improve the operation accuracy of the heat exchanger.
The working process of the specific convolutional neural network is as follows:
1) Inputting a group of training set data d with the size of [ M x 1 x N ], wherein M represents the size of a training batch, and 1 x N represents one-dimensional training data;
2) And performing a first convolution operation on the read training data to obtain a feature map t. Initializing a coefficient of a convolution kernel g, wherein the size of g is set as [ P multiplied by 1 multiplied by Q ], P represents the number of the convolution kernels, [1 multiplied by Q ] represents the size of the convolution kernels, the obtained convolution result is t multiplied by (d multiplied by g), and the size of a feature map is [ M multiplied by 1 multiplied by N multiplied by Q ];
3) And carrying out maximum pooling operation on the characteristic diagram t obtained by the convolution operation to obtain a characteristic diagram z. Initializing a pooling coefficient, setting the pooling step length as p, setting the pooling window size as k, and finally obtaining the characteristic map z with the size of [ Mx1× (N/p) xQ ], wherein the pooling process reduces the dimension of data;
4) Repeating the steps 2) -3), and repeatedly carrying out convolution and pooling operation to obtain a feature vector;
according to the method, based on a theoretical method of machine memory and pattern recognition, according to different operation conditions of the heat exchanger, the speed data in the system is monitored in real time by using the heater, a corresponding operation mode is designed, and a large amount of speed data is used for training the deep convolution neural network, so that the heat exchange part is subjected to descaling, and the heat utilization effect and the descaling effect are improved. The shell-and-tube heat exchanger can realize periodic frequent vibration of the heat exchange tube, and improves the heating efficiency, thereby realizing good descaling and heating effects.
According to the invention, based on a theoretical method of machine memory and pattern recognition, the speed detected by the speed sensing element can basically saturate evaporation of fluid in the left side pipe, the right side pipe or the central pipe under the condition of meeting a certain speed, and the volume of the internal fluid basically changes little. Therefore, new fluid is started to perform alternate heat exchange by detecting the speed change in the left side pipe, the right side pipe and the central pipe, and the heat exchange effect and the descaling effect are improved.
The invention can be based on a theoretical method of machine memory and pattern recognition, so that the detection and judgment results are more accurate.
Preferably, the speed sensing element is disposed at the free end. Through setting up at the free end, can perceive the speed variation of free end to realize better control and regulation.
Preferably, the average temperatures of the first fluid, the second fluid, and the third fluid are the same, the average flow rate per unit time of the first fluid is equal to the average flow rate per unit time of the third fluid, and the average flow rate per unit time of the first fluid is 0.5 times the average flow rate per unit time of the second fluid. The average temperature is an average of the fluid inlet temperature and the fluid outlet temperature.
Preferably, the first fluid, the second fluid, and the third fluid are the same fluid.
As is preferred, the first, second and third fluids have a common inlet header 27 and outlet header 28, as shown in fig. 4. The fluid enters the inlet header first, then enters the first heat exchange tube and the second heat exchange tube through the inlet header for heat exchange, and then flows out through the outlet header.
As best shown in FIG. 5, the first, second, and third fluids have respective inlet and outlet headers 29-30 and 31-32, respectively. The fluid enters the respective inlet headers, then enters the first heat exchange tube, the second heat exchange tube and the third heat exchange tube through the inlet headers for heat exchange, and then flows out through the respective outlet headers.
Preferably, return pipes communicated with the central pipes are arranged at the bottoms of the right pipe box and the left pipe box, so that the condensed fluid in the first pipe box and the second pipe box can flow rapidly.
Preferably, the pipe diameter of the right pipe is equal to the pipe diameter of the left pipe. The pipe diameters of the right pipe and the left pipe are equal, so that the fluid can be ensured to be subjected to phase change and keep the same transmission speed with the left pipe box in the first box body.
Through the alternating heat transfer of three kinds of fluids, can realize the vibration of elasticity coil pipe frequency to realize fine scale removal and heat transfer effect, guarantee that heat transfer power is basically the same in the time.
Preferably, the annular tubes of the left tube group are distributed by taking the axis of the left tube as the center of a circle, and the annular tubes of the right tube group are distributed by taking the axis of the right tube as the center of a circle. Through setting up left and right sides pipe as the centre of a circle, the distribution of assurance annular pipe that can be better for vibration and heat transfer are even.
Preferably, the tube group is plural.
Preferably, the center tube 8, the left tube 21, and the right tube 22 are provided along the longitudinal direction.
Preferably, the left tube group 21 and the right tube group 22 are arranged in a staggered manner in the longitudinal direction as shown in fig. 3. Through staggered distribution, vibration heat exchange and descaling can be performed on different lengths, so that vibration is more uniform, and heat exchange and descaling effects are enhanced.
Preferably, the tube group 2 (for example, the same side (left side or right side)) is provided in plural along the longitudinal direction of the center tube 8, and the tube diameter of the tube group 2 (for example, the same side (left side or right side)) is increased along the direction of fluid flow in the shell side.
Preferably, the annular tube diameter of the tube set (e.g., on the same side (left or right)) is increasing in magnitude along the direction of fluid flow within the shell side.
Through the pipe diameter range increase of the heat exchange pipe, the shell side fluid outlet position can be guaranteed to fully exchange heat, a heat exchange effect similar to countercurrent is formed, the heat transfer effect is further enhanced, the overall vibration effect is uniform, the heat exchange effect is increased, and the heat exchange effect and the descaling effect are further improved. Experiments show that better heat exchange effect and descaling effect can be obtained by adopting the structural design.
Preferably, the same side (left or right) tube group is provided in plural along the length direction of the center tube 8, and the pitch of adjacent tube groups on the same side (left or right) becomes smaller along the direction of fluid flow in the shell side.
Preferably, the spacing between the tube sets on the same side (left or right) is increasing with decreasing amplitude along the direction of fluid flow within the shell side.
Through the increase of the interval amplitude of the heat exchange tubes, the shell side fluid outlet position can be guaranteed to exchange heat fully, a heat exchange effect similar to countercurrent is formed, the heat transfer effect is further enhanced, the overall vibration effect is uniform, the heat exchange effect is increased, and the heat exchange effect and the descaling effect are further improved. Experiments show that better heat exchange effect and descaling effect can be obtained by adopting the structural design.
In the experiments, it was found that the pipe diameters, distances, and pipe diameters of the left side pipe 21, the right side pipe 22, the center pipe 8, and the ring pipe may have an influence on heat exchange efficiency and uniformity. If the distance between the headers is too large, the heat exchange efficiency is too poor, the distance between the annular pipes is too small, the annular pipes are distributed too densely, the heat exchange efficiency is also affected, the sizes of the headers and the heat exchange pipes affect the volume of the contained liquid or steam, and vibration of the free ends is affected, so that heat exchange is affected. The pipe diameters, distances and pipe diameters of the left side pipe 21, the right side pipe 22, the center pipe 8 and the annular pipe have a certain relationship.
The invention relates to an optimal size relation which is summarized by numerical simulation and test data of a plurality of heat pipes with different sizes. From the maximum heat exchange amount in the heat exchange effect, nearly 200 forms are calculated. The dimensional relationships are as follows:
the distance between the center of the center tube 8 and the center of the left tube 21 is equal to the distance between the center of the center tube 8 and the center of the right tube 21, L, the distance between the center of the left tube 21 and the center of the right tube 21 is M, the radius of the pipe diameter of the left side pipe 21, the pipe diameter of the central pipe 8 and the radius of the right side pipe 22 are R, the radius of the axis of the innermost annular pipe in the annular pipes is R1, and the radius of the axis of the outermost annular pipe is R2, so that the following requirements are satisfied:
r1/r2=a.ln (R/M) +b; wherein a, b are parameters and Ln is a logarithmic function, wherein 0.5785 < a < 0.5805,1.6615 < b < 1.6625; preferably, a=0.579 and b= 1.6621.
Preferably, 35 < R < 61mm;114 < L < 190mm;69 < R1 < 121mm,119 < R2 < 201mm. M=2l.
Preferably, the number of annular tubes of the tube group is 3 to 5, preferably 3 or 4.
Preferably, 0.55 < R1/R2 < 0.62; R/L is more than 0.3 and less than 0.33.
Preferably, 0.583 < R1/R2 < 0.615; R/L is more than 0.315 and less than 0.332.
Preferably, the radius of the annular tube is preferably 10-40mm; preferably 15 to 35mm, and more preferably 20 to 30mm.
Preferably, the centers of the left side tube 21, the right side tube 22 and the center tube 8 are aligned.
Preferably, the arc between the ends of the free ends 3, 4 is 95-130 degrees, preferably 120 degrees, centered on the central axis of the left tube. The free ends 5, 6 and the free ends 3, 4 have the same radian. Through the design of the preferable included angle, the vibration of the free end is optimal, so that the heat exchange efficiency is optimal.
Preferably, the heat exchange component can be used as an immersed heat exchange component, and is immersed in a heat exchange fluid, for example, the heat exchange component can be used as an air radiator heat exchange component and also can be used as a water heater heat exchange component.
Preferably, the box body is a circular section, and a plurality of heat exchange components are arranged, wherein one of the heat exchange components is arranged at the center of the circular section (the center pipe is arranged at the center) and the other heat exchange components are distributed around the center of the circular section.
Preferably, the tube bundle of the tube group 1 is an elastic tube bundle.
By providing the tube bundle of the tube group 1 with an elastic tube bundle, the heat exchange coefficient can be further improved.
The number of the tube groups 1 is plural, and the plurality of tube groups 1 are in a parallel structure.
The heat exchanger shown in fig. 6 has a housing of circular cross section, and the plurality of heat exchange members are disposed in the circular housing. Preferably, three heat exchange components are arranged in the shell, the center of the central tube of each heat exchange component is positioned at the middle point of an inscribed regular triangle with a circular section, the connecting line of the centers of the central tubes forms the regular triangle, the upper part is a heat exchange component, the lower part is two heat exchange components, and the connecting lines formed by the centers of the left side tube, the right side tube and the central tube of each heat exchange component are of a parallel structure. Through such setting, can make the interior fluid of heat exchanger fully reach vibrations and heat transfer purpose, improve the heat transfer effect.
Through numerical simulation and experiments, the size of the heat exchange component and the diameter of the circular section have great influence on the heat exchange effect, the heat exchange component is oversized to cause the adjacent interval to be too small, the space formed in the middle is too large, the intermediate heat exchange effect is poor, the heat exchange is uneven, and the undersize of the heat exchange component can cause the adjacent interval to be too large to cause the overall heat exchange effect to be poor. Therefore, the invention obtains the optimal dimensional relationship through a large number of numerical simulation and experimental researches.
The distance between the centers of the left side pipe and the right side pipe is L1, the side length of the inscription regular triangle is L2, the radius of the axis of the innermost annular pipe in the annular pipe is R1, and the radius of the axis of the outermost annular pipe is R2, so that the following requirements are satisfied:
10*(L1/L2)=d*(10*R1/R2)-e*(10*R1/R2) 2 -f; where d, e, f are parameters,
44.102<d<44.110,3.715<e<3.782,127.385<f<127.395;
further preferably, d=44.107, e=3.718, f= 127.39;
of these, 720 < L2 < 1130mm is preferred. Preferably 0.58 < R1/R2 < 0.62.
More preferably 0.30 < L1/L2 < 0.4.
Preferably, the centers of the left side tube 21, the right side tube 22 and the center tube 8 are aligned.
Through the layout of the structural optimization of the three heat exchange components, the whole heat exchange effect can reach the optimal heat exchange effect.
Preferably, the pipe diameters of the left side pipe and the right side pipe are smaller than the pipe diameter of the middle pipe. Preferably, the pipe diameter of the middle pipe is 1.4-1.5 times of the pipe diameters of the left pipe and the right pipe. Through the pipe diameter setting of left side pipe, right side pipe and intermediate tube, can guarantee that the fluid carries out the phase transition and keeps the same or nearly transmission speed at left side pipe, right side pipe and intermediate tube to guarantee the homogeneity of heat transfer.
Preferably, the connection position of the coil pipe on the left side pipe box is lower than the connection position of the middle pipe box and the coil pipe. This ensures that steam can quickly pass upwardly into the middle tube box. Similarly, the connection position of the coil pipe on the right side pipe box is lower than the connection position of the middle pipe box and the coil pipe
While the invention has been described in terms of preferred embodiments, the invention is not so limited. Various changes and modifications may be made by one skilled in the art without departing from the spirit and scope of the invention, and the scope of the invention should be assessed accordingly to that of the appended claims.

Claims (3)

1. A shell-and-tube heat exchanger comprising a housing, heat exchange components, a shell side inlet connection and a shell side outlet connection; the heat exchange component is arranged in the shell and is fixedly connected to the front tube plate and the rear tube plate; the shell side inlet connecting pipe and the shell side outlet connecting pipe are arranged on the shell; the shell side fluid enters from the shell side inlet connecting pipe, exchanges heat through the heat exchange component and exits from the shell side outlet connecting pipe;
the heat exchange component comprises a central tube, a left tube, a right tube and a tube group, wherein the tube group comprises a left tube group and a right tube group, the left tube group is communicated with the left tube group and the central tube, the right tube group is communicated with the right tube group and the central tube, so that the central tube, the left tube, the right tube group and the tube group form a heat exchange fluid closed cycle, phase change fluid is filled in the left tube and/or the central tube and/or the right tube, each tube group comprises a plurality of circular tubes in a circular arc shape, the end parts of the adjacent circular tubes are communicated, the plurality of circular tubes form a serial structure, and the end parts of the circular tubes form a free end of the circular tube; the central tube comprises a first tube orifice and a second tube orifice, the first tube orifice is connected with the inlet of the left tube group, the second tube orifice is connected with the inlet of the right tube group, the outlet of the left tube group is connected with the left tube, and the outlet of the right tube group is connected with the right tube; the first pipe orifice and the second pipe orifice are arranged on the same side of the central pipe; the left tube group and the right tube group are mirror symmetry along the surface where the axle center of the central tube is positioned;
A left return pipe is arranged between the left side pipe and the central pipe, and a right return pipe is arranged between the right side pipe and the central pipe;
the heat exchanger further comprises a first heat exchange tube, a second heat exchange tube and a third heat exchange tube, wherein the first heat exchange tube passes through the left side tube, the second heat exchange tube passes through the central tube, and the third heat exchange tube passes through the right side tube; the first heat exchange tube, the second heat exchange tube and the third heat exchange tube respectively flow through the first fluid, the second fluid and the third fluid;
the shell side fluid is a cold source, and the first fluid, the second fluid and the third fluid are heat sources; the inlets of the first heat exchange tube, the second heat exchange tube and the third heat exchange tube are provided with a first valve, a second valve and a third valve respectively, and the first valve, the second valve and the third valve are in data connection with a controller;
the device comprises a left side pipe, a central pipe, a right side pipe, a first temperature sensor, a second temperature sensor and a third temperature sensor, wherein the first temperature sensor, the second temperature sensor and the third temperature sensor are respectively arranged in the left side pipe, the central pipe and the right side pipe and are used for detecting the temperatures in the left side pipe, the central pipe and the right side pipe, the first temperature sensor, the second temperature sensor and the third temperature sensor are in data connection with a controller, temperature data of the first temperature sensor, the second temperature sensor and the third temperature sensor are stored in a database in real time, a one-dimensional deep convolutional neural network is used for extracting data characteristics, pattern recognition is carried out, and accordingly opening and closing of a first valve, a second valve and a third valve are controlled, and whether heat exchange is carried out on first fluid, third fluid and second fluid is controlled.
2. The heat exchanger of claim 1, controlling the opening and closing of the first, second and third valves to control whether the first, third and second fluids exchange heat, comprising the steps of:
1) Data preparation: rechecking and checking temperature data in a database, correcting missing data, invalid data and inconsistent data, and ensuring the correctness and logical consistency of the data;
2) Generating a data set: dividing the prepared data into a training set/training set label and a detection set/detection set label;
3) Training a network: and inputting the training set data into a convolutional neural network, continuously carrying out convolution and pooling to obtain feature vectors, and sending the feature vectors into a fully connected network. Obtaining a network error by calculating the output of the network and a training set label, and continuously correcting the network weight, bias, convolution coefficient and pooling coefficient by using an error back propagation algorithm to ensure that the error meets the set precision requirement, and completing the network training;
4) Network detection: inputting the detection set data into a trained network, and outputting a detection result label;
5) The heat exchanger operates: and controlling the opening and closing of the first valve, the second valve and the third valve according to the detection result label so as to remove the scale.
3. The heat exchanger of claim 1, wherein the step of generating a data set comprises the steps of:
1) Generating training set data and labels: according to different operation conditions of the heat collecting device, reading temperature data values of corresponding conditions from a database, and generating training set data and condition labels under various conditions;
2) Generating detection set data and labels: reading temperature data values of corresponding working conditions from a database according to different operation working conditions of the heat exchanger, and generating detection set data and working condition labels under various working conditions; the working condition label is the same as the working condition label of the training set and is automatically generated by a program according to the operation working condition.
CN202110387096.1A 2020-06-06 2021-04-12 Heat exchanger with four-fluid temperature cooperative communication memory control function Active CN113758313B (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN2020105097456 2020-06-06
CN202010509745 2020-06-06

Publications (2)

Publication Number Publication Date
CN113758313A CN113758313A (en) 2021-12-07
CN113758313B true CN113758313B (en) 2023-05-23

Family

ID=78786857

Family Applications (6)

Application Number Title Priority Date Filing Date
CN202110387096.1A Active CN113758313B (en) 2020-06-06 2021-04-12 Heat exchanger with four-fluid temperature cooperative communication memory control function
CN202110386763.4A Active CN113758311B (en) 2020-06-06 2021-04-12 Liquid level vibration cooperative communication control heat exchanger
CN202110386764.9A Active CN113758312B (en) 2020-06-06 2021-04-12 Heat exchanger with four fluid flow rates in cooperation with communication memory control
CN202110569944.0A Active CN113758318B (en) 2020-06-06 2021-05-25 Heat exchanger for cooperatively controlling flow distribution
CN202110576527.9A Withdrawn CN113758319A (en) 2020-06-06 2021-05-25 Heat exchanger with four fluids cooperatively controlling interval change
CN202110576528.3A Withdrawn CN113758320A (en) 2020-06-06 2021-05-25 Heat exchanger with four fluids for cooperatively controlling pipe diameter change

Family Applications After (5)

Application Number Title Priority Date Filing Date
CN202110386763.4A Active CN113758311B (en) 2020-06-06 2021-04-12 Liquid level vibration cooperative communication control heat exchanger
CN202110386764.9A Active CN113758312B (en) 2020-06-06 2021-04-12 Heat exchanger with four fluid flow rates in cooperation with communication memory control
CN202110569944.0A Active CN113758318B (en) 2020-06-06 2021-05-25 Heat exchanger for cooperatively controlling flow distribution
CN202110576527.9A Withdrawn CN113758319A (en) 2020-06-06 2021-05-25 Heat exchanger with four fluids cooperatively controlling interval change
CN202110576528.3A Withdrawn CN113758320A (en) 2020-06-06 2021-05-25 Heat exchanger with four fluids for cooperatively controlling pipe diameter change

Country Status (1)

Country Link
CN (6) CN113758313B (en)

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2034754A6 (en) * 1968-03-06 1970-12-18 Mille Gaston
DE19907871A1 (en) * 1999-02-23 2000-08-24 Ehw Thale Email Gmbh Heat exchanger and process for its manufacture
CN101029801B (en) * 2007-04-02 2010-04-21 张伟 Anti-fouling countercurrent calandria heat exchanger
US8452459B2 (en) * 2009-08-31 2013-05-28 Fisher-Rosemount Systems, Inc. Heat exchange network heat recovery optimization in a process plant
WO2015147658A1 (en) * 2014-03-28 2015-10-01 FRESH-ART Sp.z o.o. Energy processing and storage system
US10495384B2 (en) * 2015-07-30 2019-12-03 General Electric Company Counter-flow heat exchanger with helical passages
CN106016708B (en) * 2016-07-25 2017-03-29 冯大成 One kind carries out temperature controlled electric heater using mobile phone A PP
CN106052128B (en) * 2016-08-06 2017-07-14 青岛科技大学 A kind of electric heater of intelligent valve control
CN106595358B (en) * 2016-08-20 2018-06-19 中北大学 A kind of immersion heat exchange tube assemblies of heating power variation
GB201720450D0 (en) * 2017-12-08 2018-01-24 Mixergy Ltd A hot water storage tank
CN110314708B (en) * 2018-03-30 2024-05-14 日本碍子株式会社 Heat exchanger
CN111238275A (en) * 2018-04-03 2020-06-05 青岛鑫众合贸易有限公司 Heat accumulator for controlling valve and electric heater according to gas temperature
CN109945528B (en) * 2018-08-03 2020-06-12 青岛佰腾科技有限公司 Solar energy system of intelligence communication control
CN109883248B (en) * 2019-03-11 2020-05-22 山东大学 Pulsating tube bundle heat exchange assembly and fused salt heat storage tank thereof
CN110793227B (en) * 2019-04-09 2021-03-02 山东大学 Refrigerating system for deep well mining
CN109990633B (en) * 2019-05-06 2020-04-17 山东大学 Multi-tube-bundle heat storage system for adjusting pulsating heat exchange quantity
CN111156841B (en) * 2019-12-13 2020-10-16 山东大学 Plate heat exchanger intelligently controlled according to outlet temperature

Also Published As

Publication number Publication date
CN113758313A (en) 2021-12-07
CN113758312B (en) 2023-02-03
CN113758311A (en) 2021-12-07
CN113758311B (en) 2023-05-05
CN113758318B (en) 2023-03-14
CN113758319A (en) 2021-12-07
CN113758312A (en) 2021-12-07
CN113758320A (en) 2021-12-07
CN113758318A (en) 2021-12-07

Similar Documents

Publication Publication Date Title
CN111412773A (en) Method for controlling three-valve heat exchanger through temperature difference
CN111288823A (en) Heat exchanger controlled by four fluid liquid level heat exchange
CN111256498A (en) Method for controlling opening and closing of three valves by temperature for four-fluid heat exchanger
CN113758313B (en) Heat exchanger with four-fluid temperature cooperative communication memory control function
CN113203309B (en) Method for gas heat exchanger with liquid level memory data
CN112179169B (en) Temperature control heat exchange method of three-fluid heat exchanger
CN113758310A (en) Heat exchanger controlled by four fluid pressure memories
CN113108632B (en) Three-heat-source shell-and-tube heat exchanger capable of switching heat sources according to temperature
CN113758309A (en) Method for controlling three-valve heat exchanger through flow rate memory
CN112179168B (en) Liquid level control heat exchange method of three-fluid heat exchanger
CN111780591A (en) Method for controlling three-valve heat exchanger through flow speed difference
CN111780592A (en) Heat exchanger with four fluid pressure difference memory regulation
CN111780590A (en) Heat exchanger with four fluid liquid level difference memory regulation
CN112985120B (en) Vertical shell-and-tube heat exchanger controlled by four fluid heat exchange
CN113465415A (en) Three-fluid heat exchanger
CN113503754A (en) Memory control heat exchanger
CN111256499A (en) Heat exchanger controlled by four-fluid pressure heat exchange
CN112985122B (en) Four-fluid shell-and-tube heat exchanger with three-valve controlled opening amplitude variation
CN112985123B (en) Shell-and-tube heat exchanger with four fluid heat exchange valves periodically opened and closed
CN112665426B (en) Shell-and-tube heat exchanger of many casees pressure difference control
CN112985121B (en) Horizontal shell type heat exchanger controlled by heat exchange of four fluids
CN112880439B (en) Heat exchanger that speed difference was adjusted is handled to communication cloud
CN112797823B (en) Gas heat exchanger for heating according to pressure
CN113720179B (en) Hotel flow control shell-and-tube heat exchanger
CN113624035A (en) Method for cloud processing of three-valve heat exchanger

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
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20240116

Address after: 710086 G1-631, 7th Floor, Xixian Talent Building, Century Avenue, Fengdong New City, Xixian New District, Xi'an City, Shaanxi Province

Patentee after: Xi'an Shangzhihe Energy Conservation Technology Co.,Ltd.

Address before: 518000 1104, Building A, Zhiyun Industrial Park, No. 13, Huaxing Road, Henglang Community, Longhua District, Shenzhen, Guangdong Province

Patentee before: Shenzhen Hongyue Information Technology Co.,Ltd.

Effective date of registration: 20240116

Address after: 518000 1104, Building A, Zhiyun Industrial Park, No. 13, Huaxing Road, Henglang Community, Longhua District, Shenzhen, Guangdong Province

Patentee after: Shenzhen Hongyue Information Technology Co.,Ltd.

Address before: 266000 Songling Road, Laoshan District, Qingdao, Shandong Province, No. 99

Patentee before: QINGDAO University OF SCIENCE AND TECHNOLOGY