MVR evaporation low temperature assisted concentration intelligent prediction system

Abstract

The present invention relates to an intelligent prediction system for MVR evaporation and low-temperature assisted concentration, and to the field of artificial intelligence intelligent monitoring technology. The intelligent prediction system includes: a reduction prediction device for predicting the water reduction percentage of the current salt water body after evaporation treatment is performed on the current salt water body based on the gas volume, gas pressure, and gas temperature of the low-temperature secondary steam selected for the current salt water body; and a traversal execution device for traversing various numerical combinations of the gas volume, gas pressure, and gas temperature of the low-temperature secondary steam to predict the water reduction percentage corresponding to each numerical combination. The present invention builds a targeted AI prediction model for evaporation and low-temperature assisted concentration effects for the current MVR hardware, completes the prediction of the evaporation effect of the currently selected evaporation gas parameters, and selects the evaporation gas parameters corresponding to the optimal evaporation effect of the current salt water body to be processed, thereby increasing the predictability and configurability of the MVR evaporation process and improving the intelligence level of MVR evaporation control.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence monitoring technology, and in particular to an MVR evaporation low-temperature assisted concentration intelligent prediction system. Background Art

[0002] Mechanical Vapor Recompression (MVR) evaporators are a highly efficient and energy-efficient technology compared to traditional multi-effect evaporation. MVR evaporators, referring to mechanical thermal compression evaporators, operate by raising the temperature of secondary steam generated by the evaporator through a mechanical thermal compressor (similar to a blower) and returning it to the evaporator as a heat source. Fresh steam is used only to compensate for heat losses and replenish the heat enthalpy of the feed and discharge, significantly reducing the evaporator's consumption of external fresh steam. Steam that would otherwise be discarded is now fully utilized, recovering latent heat and improving thermal efficiency. The economic efficiency of live steam is equivalent to 20-30 times that of multi-effect evaporation, reducing the need for external heating and cooling resources, lowering energy consumption, and minimizing pollution.

[0003] For example, Chinese invention patent application publication number CN103816689A proposes an MVR evaporator comprising a compressor, a motor connected to the compressor, a single-effect falling film concentrator I, and a single-effect falling film concentrator II. The two devices have identical structures, consisting of a liquid storage tank, a liquid infusion pipe, and an evaporator. The evaporator is provided with a circular disk perpendicular to the inner wall of the evaporator, and the bottom of the liquid storage tank is provided with a liquid outlet. The exhaust port of the single-effect falling film concentrator I is connected to the vent of the single-effect falling film concentrator II, the liquid outlet of the single-effect falling film concentrator II is connected to the suction port of the compressor, and the exhaust port of the compressor is connected to a three-way gas infusion pipe. This invention patent application has the following advantages: a simple structure, significant energy savings, high concentration efficiency, and simple operation.

[0004] For example, Chinese invention patent application publication number CN103550941A proposes a low-temperature evaporation and concentration device comprising a Carnot heating cycle device and an evaporation concentrator. The Carnot heating cycle device comprises a compressor, evaporator, expansion valve, and condenser connected in a circular pipeline. The heating-side inlet of the condenser is connected to a feed pipeline. The evaporation concentrator is provided with an air circulation channel comprising a liquid concentration zone and a condensate generation zone. A fan is located at the bottom of the air circulation channel, directing cold air from the condensate generation zone to the liquid concentration zone. The beneficial effects of this invention patent application include: desalination, dehydration, and / or recovery of high-concentration salt and highly contaminated wastewater at low temperature and normal pressure, producing clean condensate as a byproduct, and zero emissions.

[0005] It can be concluded from the technical solutions in the above-mentioned prior art that the MVR evaporation low-temperature assisted concentration treatment in the prior art is only limited to the improvement and optimization of the MVR mechanical structure and process parameters, and is unable to perform any predictive intelligent processing. For example, it is impossible to predict the concentration effect that can be achieved for the saline water body with various parameters to be currently processed under the existing MVR hardware conditions, and it is also impossible to select the configuration parameters of various evaporation gases that can achieve the best concentration effect for the saline water body to be currently processed. As a result, the operator cannot determine in advance whether the evaporation concentration effect of each time meets the standards and whether additional evaporation treatment is required. It is also impossible to directly use the various evaporation gas configuration parameters that have the best concentration effect for the saline water body to be processed this time, resulting in the inability to directly obtain the best concentration effect for each saline water body to be processed. Summary of the Invention

[0006] In order to address the technical defects in the prior art, the present invention provides an MVR evaporation low-temperature assisted concentration intelligent prediction system. By building a targeted evaporation low-temperature assisted concentration effect prediction model for the currently used MVR hardware, the concentration effect that can be achieved for the salt-containing water body with various parameters to be currently processed under the conditions of the MVR hardware is predicted. At the same time, by traversing various evaporation gas configuration parameter combinations, the various evaporation gas configuration parameters that can achieve the best concentration effect are selected for the salt-containing water body to be currently processed, thereby increasing the predictability and configurability of the MVR evaporation process and improving the intelligence level of MVR evaporation control.

[0007] The present invention provides an intelligent prediction system for MVR evaporation and low-temperature assisted concentration, the intelligent prediction system comprising:

[0008] An MVR evaporation device includes a concentrating tank, an MVR compressor, a first communicating pipe, and a second communicating pipe. An exhaust port connected to one end of the first communicating pipe is provided on the top of the concentrating tank for discharging low-temperature secondary steam in the concentrating tank. The other end of the first communicating pipe is connected to one end of the MVR compressor for sending the low-temperature secondary steam to the MVR compressor for mechanical compression to obtain high-temperature heating steam. The temperature of the high-temperature heating steam is greater than that of the low-temperature secondary steam. The other end of the MVR compressor is connected to one end of the second communicating pipe. The other end of the second communicating pipe is connected to an air inlet on the left side of the concentrating tank for sending the high-temperature heating steam into the concentrating tank through the second communicating pipe to evaporate the salt water in the concentrating tank.

[0009] a data collating device connected to the MVR evaporation device, and configured to perform multiple evaporation processes on the MVR evaporation device to obtain multiple sets of evaporation data corresponding to the multiple evaporation processes;

[0010] a first component for forming a convolutional neural network, wherein the input information of the convolutional neural network is the gas volume, gas pressure, and gas temperature of the low-temperature secondary steam used when the MVR evaporation device performs a single evaporation process, the salt concentration and water volume of the salt water body to be evaporated, and the concentration tank capacity, exhaust port diameter, and air inlet diameter of the MVR evaporation device; and the single output information of the convolutional neural network is the water volume reduction percentage of the salt water body after the MVR evaporation device completes the single evaporation process;

[0011] a second component, connected to the data organizing component and the first component, respectively, for performing a fixed number of learning operations on the convolutional neural network using the multiple sets of evaporation data corresponding to the multiple evaporation processes to obtain a convolutional neural network after the multiple learning operations and outputting the convolutional neural network as an AI analysis model;

[0012] A reduction prediction device is connected to the second component device and is used to input the salt concentration and water volume of the current salt water body that has not yet undergone evaporation treatment, the concentration tank capacity, exhaust port diameter and air inlet diameter of the MVR evaporation device, and the gas volume, gas pressure and gas temperature of the low-temperature secondary steam selected for the current salt water body into the AI ​​analytical model, so as to execute the AI ​​analytical model and predict the water reduction percentage of the salt water body after the evaporation treatment is completed on the current salt water body as the predicted water reduction percentage output.

[0013] It can be seen that the present invention has at least the following outstanding substantive features:

[0014] Substantive Feature A: A customized AI analytical model is established for the MVR evaporation device, including the concentration tank, MVR compressor, first connecting pipe, and second connecting pipe. This model is used to traverse various numerical combinations of gas volume, gas pressure, and gas temperature of the low-temperature secondary steam and intelligently analyze the various water reduction percentages after evaporation. The numerical combination corresponding to the highest water reduction percentage is used as the numerical combination with the best low-temperature assisted concentration effect to implement the actual low-temperature secondary steam parameter settings, thereby achieving the optimal low-temperature assisted concentration effect for the current saline water body.

[0015] Substantive Feature B: A custom AI analytical model is established for the MVR evaporation device, including the concentration tank, MVR compressor, first connecting pipe, and second connecting pipe. Based on the currently set low-temperature secondary steam gas volume, gas pressure, and gas temperature inputs, the model predicts the effect of performing cryogenic-assisted concentration on the current saline water, providing key data for subsequent decisions on whether to continue evaporation.

[0016] Substantive Feature C: The customization of the AI ​​analytical model established for the MVR evaporation device is that: the AI ​​analytical model is a convolutional neural network that has completed multiple learning operations. The above-mentioned multiple learning operations are performed through multiple sets of evaporation data corresponding to the multiple completed evaporation processes. The number of learning operations is positively correlated with the concentration tank capacity of the MVR evaporation device. At the same time, the various input contents of the model are the salt concentration of the saline water body, the water volume, the concentration tank capacity of the MVR evaporation device, the exhaust port diameter and the air inlet diameter, as well as the gas volume, gas pressure and gas temperature of the low-temperature secondary steam selected for the saline water body, thereby ensuring the stability and effectiveness of each subsequent intelligent analysis result. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The embodiments of the present invention will be described below with reference to the accompanying drawings, in which: Figure 1 This is a technical flow chart of the MVR evaporation low-temperature assisted concentration intelligent prediction system according to the present invention.

[0018] Figure 2 FIG. 1 is a structural block diagram of an intelligent prediction system for MVR evaporation and low-temperature assisted concentration according to a first embodiment of the present invention.

[0019] Figure 3 1 is a structural block diagram of a network training device of an MVR evaporation low-temperature assisted concentration intelligent prediction system according to a second embodiment of the present invention.

[0020] Figure 4 FIG. 4 is a structural block diagram of an intelligent prediction system for MVR evaporation and low-temperature assisted concentration according to a sixth embodiment of the present invention. DETAILED DESCRIPTION

[0021] The present invention will be described in detail below with reference to the accompanying drawings.

[0022] like Figure 1 As shown, a technical flow chart of the MVR evaporation low-temperature assisted concentration intelligent prediction system according to the present invention is given.

[0023] like Figure 1 As shown, the specific technical process of the MVR evaporation low-temperature assisted concentration intelligent prediction system shown in the present invention is as follows:

[0024] Technical Process 1: Perform a limited number of evaporation processes on the MVR evaporation device including the concentration tank, the MVR compressor, the first connecting pipe, and the second connecting pipe to obtain various sets of evaporation control parameters and evaporation concentration effect data corresponding to the various sets of evaporation control parameters;

[0025] Technical Process 2: Establishing a specifically designed AI analytical model for the custom-structured MVR evaporation device. The AI ​​analytical model is a convolutional neural network that has completed multiple learning operations. The multiple learning operations use evaporation control parameters and evaporation concentration effect data corresponding to a limited number of evaporation processes, thereby ensuring the reliability and stability of the prediction results of the established AI analytical model.

[0026] For example, the targeted design of the AI ​​analytical model is reflected in the positive correlation between the number of learning operations performed and the capacity of the concentration tank of the MVR evaporation device, and the multiple inputs of the selected convolutional neural network include the salt concentration of the saline water body, the volume of the water body, the concentration tank capacity of the MVR evaporation device, the exhaust port diameter and the air inlet diameter, and the gas volume, gas pressure and gas temperature of the low-temperature secondary steam selected for the saline water body;

[0027] Technical Process 3: Using the constructed AI analytical model, the selected evaporation control parameters are used to predict the evaporation concentration effect data for the salt water currently being evaporated, thereby providing key reference information for whether to conduct additional evaporation operations in the future;

[0028] Technical process four: Using the constructed AI analytical model, for the saline water body currently being evaporated, the specific values ​​of the evaporation control parameters are traversed to obtain the predicted evaporation and concentration effect data corresponding to each specific value. The specific values ​​corresponding to the predicted optimal evaporation and concentration effect data are directly put into use as the optimal evaporation control parameters for the saline water body currently being evaporated, thereby quickly obtaining the optimal control parameters and skipping the tedious and complicated operation process of multiple experiments to pursue the optimal control parameters.

[0029] The key points of the present invention are: different AI analytical models designed specifically for MVR evaporation devices with different structures, evaporation control parameters corresponding to a limited number of evaporation processes and evaporation concentration effect data as learning data for multiple learning operations, and an intelligent optimal evaporation control parameter exploration process using a numerical analysis mode to explore the evaporation control parameters corresponding to the optimal evaporation concentration effect by traversing the specific values ​​of the evaporation control parameters as input to the AI ​​analytical model.

[0030] The MVR evaporation low-temperature assisted concentration intelligent prediction system of the present invention will be specifically described below in the form of an implementation plan.

[0031] First embodiment

[0032] Figure 2 FIG. 1 is a structural block diagram of an intelligent prediction system for MVR evaporation and low-temperature assisted concentration according to a first embodiment of the present invention.

[0033] like Figure 2As shown, the MVR evaporation low-temperature assisted concentration intelligent prediction system includes the following components:

[0034] An MVR evaporation device includes a concentrating tank, an MVR compressor, a first communicating pipe, and a second communicating pipe. An exhaust port connected to one end of the first communicating pipe is provided on the top of the concentrating tank for discharging low-temperature secondary steam in the concentrating tank. The other end of the first communicating pipe is connected to one end of the MVR compressor for sending the low-temperature secondary steam to the MVR compressor for mechanical compression to obtain high-temperature heating steam. The temperature of the high-temperature heating steam is greater than that of the low-temperature secondary steam. The other end of the MVR compressor is connected to one end of the second communicating pipe. The other end of the second communicating pipe is connected to an air inlet on the left side of the concentrating tank for sending the high-temperature heating steam into the concentrating tank through the second communicating pipe to evaporate the salt water in the concentrating tank.

[0035] For example, the MVR compressor can process the received low-temperature secondary steam by raising its temperature by a fixed value, thereby increasing the heat capacity of the steam and realizing the secondary utilization of the steam that was originally exhaust gas.

[0036] a data collating device connected to the MVR evaporation device, and configured to perform multiple evaporation processes on the MVR evaporation device to obtain multiple sets of evaporation data corresponding to the multiple evaporation processes;

[0037] For example, the multiple evaporation processes performed on the MVR evaporation device here are not simulated multiple evaporation processes, but multiple real evaporation processes actually performed. The control data and result data involved in these multiple real evaporation processes are key information for subsequently establishing an AI analytical model to ensure the effectiveness of the AI ​​analytical model.

[0038] a first component for forming a convolutional neural network, wherein the input information of the convolutional neural network is the gas volume, gas pressure, and gas temperature of the low-temperature secondary steam used when the MVR evaporation device performs a single evaporation process, the salt concentration and water volume of the salt water body to be evaporated, and the concentration tank capacity, exhaust port diameter, and air inlet diameter of the MVR evaporation device; and the single output information of the convolutional neural network is the water volume reduction percentage of the salt water body after the MVR evaporation device completes the single evaporation process;

[0039] a second component, connected to the data organizing component and the first component, respectively, for performing a fixed number of learning operations on the convolutional neural network using the multiple sets of evaporation data corresponding to the multiple evaporation processes to obtain a convolutional neural network after the multiple learning operations and outputting the convolutional neural network as an AI analysis model;

[0040] For example, different numerical simulation modes can be used to respectively realize the simulation processing of building a convolutional neural network and building an AI analytical model;

[0041] a reduction prediction device connected to the second component device, for inputting the salt concentration and water volume of the current salt water body before evaporation treatment, the concentration tank capacity, exhaust port diameter and air inlet diameter of the MVR evaporation device, and the gas volume, gas pressure and gas temperature of the low-temperature secondary steam selected for the current salt water body into the AI ​​analytical model, so as to execute the AI ​​analytical model and predict the water reduction percentage of the salt water body after the evaporation treatment is completed on the current salt water body, and output it as the predicted water reduction percentage;

[0042] For example, the water reduction percentage obtained here represents the effect of MVR evaporation and low-temperature assisted concentration. The larger the value of the water reduction percentage obtained, the better the effect of MVR evaporation and low-temperature assisted concentration. On the contrary, the smaller the value of the water reduction percentage obtained, the worse the effect of MVR evaporation and low-temperature assisted concentration. Obviously, the value of the water reduction percentage obtained is between 0 and 100%. For example, the predicted value is 95%;

[0043] The percentage of water volume reduction of the saline water body after the MVR evaporation device performs the single evaporation treatment is a value obtained by subtracting the percentage of the volume of the concentrated material obtained after the evaporation treatment of the saline water body subjected to the evaporation treatment to the volume of the saline water body subjected to the evaporation treatment from 100%;

[0044] The method includes performing a fixed number of multiple learning operations on the convolutional neural network using multiple sets of evaporation data corresponding to the multiple evaporation processes to obtain a convolutional neural network after the multiple learning operations and using the convolutional neural network as an AI analytical model, wherein: the fixed number of values ​​is positively correlated with the concentration tank capacity of the MVR evaporation device;

[0045] For example, a numerical mapping formula may be used to express a numerical mapping relationship of a positive correlation between the fixed number of values ​​and the concentration tank capacity of the MVR evaporation device.

[0046] Second embodiment

[0047] Figure 3 FIG. 1 is a structural block diagram of an intelligent prediction system for MVR evaporation and low-temperature assisted concentration according to a second embodiment of the present invention.

[0048] like Figure 3 As shown, Figure 2 The system is different. Figure 3The MVR evaporation low temperature assisted concentration intelligent prediction system also includes:

[0049] a traversal execution device connected to the second component device, configured to use the salt concentration of the current salt water body that has not yet been subjected to evaporation treatment, the water body volume, the concentration tank capacity of the MVR evaporation device, the exhaust port diameter, and the air inlet diameter as input information of the AI ​​analytical model, and simultaneously traverse various numerical combinations of the gas volume, gas pressure, and gas temperature of the low-temperature secondary steam to use each numerical combination as input information of the AI ​​analytical model, so as to execute the AI ​​analytical model and predict the water body reduction percentage corresponding to each numerical combination;

[0050] Specifically, traversing various numerical combinations of the gas volume, gas pressure, and gas temperature of the low-temperature secondary steam includes: obtaining various values ​​of the gas volume of the low-temperature secondary steam, obtaining various values ​​of the gas pressure of the low-temperature secondary steam, and obtaining various values ​​of the gas temperature of the low-temperature secondary steam, and combining the above three different steam control parameters to achieve traversal of various numerical combinations of the gas volume, gas pressure, and gas temperature of the low-temperature secondary steam;

[0051] Obviously, since each of the three different steam control parameters can take on a vast number of values, and the number of numerical combinations is even greater, it is unrealistic to test the actual MVR evaporation and concentration effect of each numerical combination. However, numerical simulation based on the AI ​​analytical model can be used to traverse a vast number of numerical combinations, which can be completed and implemented using a high-performance computer system.

[0052] The optimization processing device is connected to the traversal execution device and is used to obtain various water reduction percentages corresponding to various numerical combinations, and output the numerical combination corresponding to the water reduction percentage with the highest value among the various water reduction percentages as the priority evaporation numerical combination.

[0053] Third embodiment

[0054] Compared to Figure 2 The system, according to the third embodiment of the present invention, the MVR evaporation low-temperature assisted concentration intelligent prediction system may further include the following components: an on-site display device connected to the reduction prediction device, for receiving and displaying the predicted water reduction percentage;

[0055] For example, the on-site display device may be a liquid crystal display screen integrated with a touch screen or an LED display array composed of a plurality of LED units.

[0056] Fourth embodiment

[0057] Compared to Figure 2The system, according to the fourth embodiment of the present invention, the MVR evaporation low-temperature assisted concentration intelligent prediction system may further include the following components:

[0058] a mobile communication interface connected to the reduction prediction device and configured to transmit the received predicted water reduction percentage to a portable device of a nearest operator via a mobile communication link;

[0059] For example, the mobile communication interface may be implemented using a frequency division duplex communication interface or a time division duplex communication interface.

[0060] Fifth embodiment

[0061] Compared to Figure 2 The system, according to the fifth embodiment of the present invention, the MVR evaporation low-temperature assisted concentration intelligent prediction system may further include the following components:

[0062] a configuration operation device, connected to the first component device, the second component device and the reduction prediction device, respectively, for performing on-site configuration of operating parameters of the first component device, the second component device and the reduction prediction device respectively using different serial configuration addresses;

[0063] For example, an IIC serial configuration interface may be integrated into the configuration operation device to respectively perform on-site configuration of the operating parameters of the first component device, the second component device, and the reduction prediction device using different serial configuration addresses.

[0064] Sixth embodiment

[0065] Figure 4 FIG. 4 is a structural block diagram of an intelligent prediction system for MVR evaporation and low-temperature assisted concentration according to a sixth embodiment of the present invention.

[0066] like Figure 4 As shown, Figure 2 The system is different. Figure 4 The MVR evaporation low temperature assisted concentration intelligent prediction system also includes:

[0067] An information storage device, connected to the second component, and used to store various model data of the AI ​​analysis model;

[0068] For example, the information storage device may be implemented by using a static memory device, a TF memory device, or a CF memory device.

[0069] Next, various embodiments of the present invention will be further described.

[0070] In any of the above embodiments, optionally, in the MVR evaporation low-temperature assisted concentration intelligent prediction system:

[0071] performing multiple evaporation processes on the MVR evaporation device to obtain multiple sets of evaporation data corresponding to the multiple evaporation processes, including: each set of evaporation data is the gas volume, gas pressure, gas temperature of the low-temperature secondary steam used when the MVR evaporation device performs a corresponding single evaporation process, the salt concentration and volume of the salty water body to be evaporated, and the percentage of water reduction of the salty water body after the MVR evaporation device completes the corresponding single evaporation process;

[0072] For example, each set of evaporation data includes the gas volume, gas pressure, gas temperature of the low-temperature secondary steam used when the MVR evaporation device performs a corresponding single evaporation process, the salt concentration of the salt water body subjected to the evaporation process, the water volume, and the water reduction percentage of the salt water body after the MVR evaporation device completes the corresponding single evaporation process, including: the gas volume, gas pressure, gas temperature of the low-temperature secondary steam used when the MVR evaporation device performs the corresponding single evaporation process, the salt concentration of the salt water body subjected to the evaporation process, the water volume, and the water reduction percentage of the salt water body after the MVR evaporation device completes the corresponding single evaporation process, all in a binary numerical representation mode;

[0073] Among them, using multiple sets of evaporation data corresponding to the multiple evaporation treatments to perform a fixed number of multiple learning operations on the convolutional neural network to obtain a convolutional neural network after completing the multiple learning operations and using it as an AI analysis model includes: using multiple sets of evaporation data corresponding to the multiple evaporation treatments to perform multiple learning operations on the convolutional neural network respectively.

[0074] And in any of the above embodiments, optionally, in the MVR evaporation low temperature assisted concentration intelligent prediction system:

[0075] A steam condensate outlet is provided on the right side of the concentration tank body, and a concentrated material outlet is provided at the bottom of the concentration tank body, for respectively discharging the steam condensate and the concentrated material obtained after the evaporation treatment of the salt water;

[0076] Wherein, a material inlet is further provided on the left side of the concentration tank body for inputting saline water, and the opening height of the material inlet on the concentration tank body is higher than the opening height of the air inlet on the concentration tank body;

[0077] For example, the salt water of the present invention is only one type of material that the MVR evaporation low-temperature assisted concentration intelligent prediction system is specifically applicable to. In fact, there are also various types of materials suitable for low-temperature concentration in industries such as milk, glucose, starch, monosodium glutamate, xylose, pharmaceuticals, chemicals, bioengineering, environmental protection engineering, waste liquid recovery, papermaking, and salt production that can use the MVR evaporation low-temperature assisted concentration intelligent prediction system of the present invention.

[0078] The top of the concentrating tank is provided with an exhaust port connected to one end of the first communicating pipe for discharging low-temperature secondary steam in the concentrating tank, and the other end of the first communicating pipe is connected to one end of the MVR compressor for sending the low-temperature secondary steam to the MVR compressor for performing mechanical compression processing to obtain high-temperature heating steam. The temperature of the low-temperature secondary steam is between 30 degrees Celsius and 80 degrees Celsius, and the temperature of the high-temperature heating steam is between 80 degrees Celsius and 100 degrees Celsius.

[0079] Among them, an exhaust port is provided on the top of the concentration tank body and is connected to one end of the first communicating pipe, so as to discharge the low-temperature secondary steam in the concentration tank body. The other end of the first communicating pipe is connected to one end of the MVR compressor, so as to send the low-temperature secondary steam to the MVR compressor to perform mechanical compression processing to obtain high-temperature heating steam, including: the MVR compressor is a mechanical thermal energy compression evaporator, which is used to perform temperature raising processing on the received low-temperature secondary steam.

[0080] Seventh embodiment

[0081] According to a seventh embodiment of the present invention, an intelligent prediction system for MVR evaporation low-temperature assisted concentration is used for an MVR evaporation device. The intelligent prediction system includes a memory and one or more processors. The memory stores a computer program. The computer program is configured to be executed by the one or more processors to complete the following steps:

[0082] performing multiple evaporation processes on the MVR evaporation device to obtain multiple sets of evaporation data corresponding to the multiple evaporation processes;

[0083] For example, the multiple evaporation processes performed on the MVR evaporation device here are not simulated multiple evaporation processes, but multiple real evaporation processes actually performed. The control data and result data involved in these multiple real evaporation processes are key information for subsequently establishing an AI analytical model to ensure the effectiveness of the AI ​​analytical model.

[0084] A convolutional neural network is formed, wherein the input information of the convolutional neural network is the gas volume, gas pressure, and gas temperature of the low-temperature secondary steam used when the MVR evaporation device performs a single evaporation process, the salt concentration and water volume of the salty water body to be evaporated, and the concentration tank capacity, exhaust port diameter, and air inlet diameter of the MVR evaporation device. The single output information of the convolutional neural network is the water volume reduction percentage of the salty water body after the MVR evaporation device completes the single evaporation process;

[0085] Performing a fixed number of multiple learning operations on the convolutional neural network using multiple sets of evaporation data corresponding to the multiple evaporation processes to obtain a convolutional neural network after completing the multiple learning operations and outputting the convolutional neural network as an AI analytical model;

[0086] For example, different numerical simulation modes can be used to respectively realize the simulation processing of building a convolutional neural network and building an AI analytical model;

[0087] Inputting the salinity concentration and water volume of the current saline water body, which has not yet been subjected to evaporation treatment, the concentration tank capacity, exhaust port diameter, and air inlet diameter of the MVR evaporation device, and the gas volume, gas pressure, and gas temperature of the low-temperature secondary steam selected for the current saline water body into the AI ​​analytical model to execute the AI ​​analytical model and predict the water reduction percentage of the saline water body after the evaporation treatment is performed on the current saline water body as an output as the predicted water reduction percentage;

[0088] The salinity concentration and volume of the current salt water body before evaporation treatment, the concentration tank capacity of the MVR evaporation device, the exhaust port diameter, and the air inlet diameter are used as input information of the AI ​​analytical model. Various numerical combinations of the gas volume, gas pressure, and gas temperature of the low-temperature secondary steam are traversed and each numerical combination is also used as input information of the AI ​​analytical model to execute the AI ​​analytical model and predict the water body reduction percentage corresponding to each numerical combination;

[0089] For example, the water reduction percentage obtained here represents the effect of MVR evaporation and low-temperature assisted concentration. The larger the value of the water reduction percentage obtained, the better the effect of MVR evaporation and low-temperature assisted concentration. On the contrary, the smaller the value of the water reduction percentage obtained, the worse the effect of MVR evaporation and low-temperature assisted concentration. Obviously, the value of the water reduction percentage obtained is between 0 and 100%. For example, the predicted value is 95%;

[0090] Obtain various water reduction percentages corresponding to various numerical combinations, and output the numerical combination corresponding to the water reduction percentage with the highest value among the various water reduction percentages as the priority evaporation numerical combination;

[0091] Wherein, the MVR evaporation device includes a concentration tank body, an MVR compressor, a first communicating pipe and a second communicating pipe, an exhaust port connected to one end of the first communicating pipe is provided on the top of the concentration tank body, for discharging low-temperature secondary steam in the concentration tank body, the other end of the first communicating pipe is connected to one end of the MVR compressor, for sending the low-temperature secondary steam to the MVR compressor to perform mechanical compression processing to obtain high-temperature heating steam, the temperature of the high-temperature heating steam is greater than the temperature of the low-temperature secondary steam, the other end of the MVR compressor is connected to one end of the second communicating pipe, the other end of the second communicating pipe is connected to the air inlet on the left side of the concentration tank body, for sending the high-temperature heating steam into the concentration tank body through the second communicating pipe to evaporate the salt water in the concentration tank body;

[0092] For example, the MVR compressor can process the received low-temperature secondary steam by raising its temperature by a fixed value, thereby increasing the heat capacity of the steam and realizing the secondary utilization of the steam that was originally exhaust gas.

[0093] The percentage of water volume reduction of the saline water body after the MVR evaporation device performs the single evaporation treatment is a value obtained by subtracting the percentage of the volume of the concentrated material obtained after the evaporation treatment of the saline water body subjected to the evaporation treatment to the volume of the saline water body subjected to the evaporation treatment from 100%;

[0094] The method includes performing a fixed number of multiple learning operations on the convolutional neural network using multiple sets of evaporation data corresponding to the multiple evaporation processes to obtain a convolutional neural network after the multiple learning operations and using the convolutional neural network as an AI analytical model, wherein: the fixed number of values ​​is positively correlated with the concentration tank capacity of the MVR evaporation device;

[0095] For example, a numerical mapping formula may be used to represent a numerical mapping relationship of a positive correlation between the fixed number of values ​​and the concentration tank capacity of the MVR evaporation device. Exemplarily, M processors are provided, where M is a natural number greater than or equal to 1.

[0096] In addition, in the MVR evaporation low-temperature assisted concentration intelligent prediction system shown in the present invention: multiple learning operations are performed on the convolutional neural network using multiple sets of evaporation data corresponding to the multiple evaporation processes, including: when performing each learning operation on the convolutional neural network, the concentration tank capacity, exhaust port diameter and air inlet diameter of the MVR evaporation device, and the gas volume, gas pressure, gas temperature, salt concentration and water volume of the low-temperature secondary steam used by the MVR evaporation device when performing the corresponding single evaporation process in the corresponding set of evaporation data are used as input information of the convolutional neural network item by item, and the percentage of water reduction of the saline water after the MVR evaporation device completes the corresponding single evaporation process in the corresponding set of evaporation data is used as the single output information of the convolutional neural network to complete the learning operation.

[0097] Wherein, when executing each learning operation of the convolutional neural network, the concentration tank capacity, exhaust port diameter and air inlet diameter of the MVR evaporation device, and the gas volume, gas pressure, gas temperature, salt concentration and water volume of the low-temperature secondary steam used by the MVR evaporation device when performing a corresponding single evaporation process in a corresponding set of evaporation data, the salt concentration and water volume of the salty water body subjected to the evaporation process are used as input information of the convolutional neural network item by item, and the water volume reduction percentage of the salty water body after the MVR evaporation device completes the corresponding single evaporation process in the corresponding set of evaporation data is used as single output information of the convolutional neural network. Completing this learning operation includes: performing simulation processing of each learning operation of the convolutional neural network in a numerical simulation mode.

[0098] The foregoing description of the exemplary embodiments of the present invention is provided for the purpose of illustration and description. It is not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations will be apparent to those skilled in the art. The exemplary embodiments have been chosen and described in order to best illustrate the principles of the invention and its practical application, thereby enabling others skilled in the art to understand the various embodiments and variations of the invention as they apply to the specific use contemplated. It is intended that the scope of the invention be defined by the appended claims and their equivalents.

Claims

1. An MVR evaporation low temperature assisted concentration intelligent prediction system, characterized in that: The intelligent prediction system includes: an MVR evaporation device, including a concentration tank, an MVR compressor, a first communicating pipe, and a second communicating pipe; an exhaust port is provided on the top of the concentration tank, communicating with one end of the first communicating pipe, for discharging low-temperature secondary steam in the concentration tank; the other end of the first communicating pipe is communicated with one end of the MVR compressor, for sending the low-temperature secondary steam to the MVR compressor for mechanical compression processing to obtain high-temperature heating steam, wherein the temperature of the high-temperature heating steam is greater than that of the low-temperature secondary steam; the other end of the MVR compressor is communicated with one end of the second communicating pipe, and the other end of the second communicating pipe is communicated with the air inlet on the left side of the concentration tank, for sending the high-temperature heating steam into the concentration tank through the second communicating pipe to evaporate the salt water in the concentration tank; a data collating device is connected to the MVR evaporation device, for performing multiple evaporation processes on the MVR evaporation device to obtain multiple sets of evaporation data corresponding to the multiple evaporation processes; a first assembly device is used to assemble a convolutional neural network, wherein the item-by-item input information of the convolutional neural network is the data used when the MVR evaporation device performs a single evaporation process The gas volume, gas pressure, gas temperature of the low-temperature secondary steam, the salt concentration of the salt water body to be evaporated, the water volume, and the concentration tank capacity, exhaust port diameter and air inlet diameter of the MVR evaporation device, the single output information of the convolutional neural network is the water volume reduction percentage of the salt water body after the MVR evaporation device completes the single evaporation treatment; the second component is respectively connected to the data sorting component and the first component, and is used to use the multiple sets of evaporation data corresponding to the multiple evaporation treatments to perform a fixed number of multiple learning operations on the convolutional neural network to obtain a complete A convolutional neural network is formed after multiple learning operations and is output as an AI analytical model; a reduction prediction device is connected to the second component device, and is used to input the salt concentration and water volume of the current salt water body that has not yet been subjected to evaporation treatment, the concentration tank capacity of the MVR evaporation device, the exhaust port diameter and the air inlet diameter, and the gas volume, gas pressure and gas temperature of the low-temperature secondary steam selected for the current salt water body into the AI ​​analytical model, so as to execute the AI ​​analytical model and predict the water reduction percentage of the salt water body after the evaporation treatment is completed on the current salt water body, and output it as the predicted water reduction percentage.

2. The MVR evaporation low-temperature assisted concentration intelligent prediction system according to claim 1, characterized in that: The percentage of water reduction of the salt water body after the MVR evaporation device performs the single evaporation treatment is a value obtained by subtracting the percentage of the volume of the salt water body subjected to evaporation treatment obtained after the evaporation treatment as a percentage of the water volume of the salt water body subjected to evaporation treatment from the volume of the concentrated material obtained after the evaporation treatment is completed from one hundred percent; wherein, a fixed number of multiple learning operations are performed on the convolutional neural network using multiple sets of evaporation data corresponding to the multiple evaporation treatments to obtain the convolutional neural network after the multiple learning operations and serving as an AI analytical model, including: the fixed number of values ​​is positively correlated with the concentration tank capacity of the MVR evaporation device.

3. The MVR evaporation low temperature assisted concentration intelligent prediction system according to claim 2, characterized in that: The intelligent prediction system also includes: a traversal execution device, connected to the second component device, used to use the salt concentration, water volume, concentration tank capacity, exhaust port diameter and air inlet diameter of the current salt water body that has not yet been subjected to evaporation treatment as input information of the AI ​​analytical model, and at the same time traverse various numerical combinations of the gas volume, gas pressure and gas temperature of the low-temperature secondary steam to use each numerical combination as input information of the AI ​​analytical model, so as to execute the AI ​​analytical model and predict the water body reduction percentage corresponding to each numerical combination; an optimization processing device, connected to the traversal execution device, used to obtain various water body reduction percentages corresponding to various numerical combinations, and output the numerical combination corresponding to the water body reduction percentage with the highest numerical value among the various water body reduction percentages as the priority evaporation numerical combination.

4. The MVR evaporation low temperature assisted concentration intelligent prediction system according to claim 2, characterized in that: The intelligent prediction system further includes: an on-site display device connected to the reduction prediction device, for receiving and displaying the predicted water body reduction percentage.

5. The MVR evaporation low temperature assisted concentration intelligent prediction system according to claim 2, characterized in that: The intelligent prediction system further comprises: a mobile communication interface connected to the reduction prediction device, and configured to send the received predicted water reduction percentage to a portable device of the nearest operator via a mobile communication link.

6. The MVR evaporation low temperature assisted concentration intelligent prediction system according to claim 2, characterized in that: The intelligent prediction system also includes: a configuration operation device, which is respectively connected to the first component device, the second component device and the reduction prediction device, and is used to use different serial configuration addresses to perform on-site configuration of the working parameters of the first component device, the second component device and the reduction prediction device respectively.

7. The MVR evaporation low temperature assisted concentration intelligent prediction system according to claim 2, characterized in that: The intelligent prediction system also includes: an information storage device connected to the second component device, which is used to store various model data of the AI ​​analysis model.

8. The MVR evaporation low-temperature assisted concentration intelligent prediction system according to any one of claims 2 to 7, characterized in that: Performing multiple evaporation processes on the MVR evaporation device to obtain multiple sets of evaporation data corresponding to the multiple evaporation processes, including: each set of evaporation data is the gas volume, gas pressure, gas temperature, salt concentration, water volume of the salty water body subjected to evaporation process, and the percentage of water reduction of the salty water body after the MVR evaporation device completes the corresponding single evaporation process of the low-temperature secondary steam used when the MVR evaporation device performs the corresponding single evaporation process; wherein, using the multiple sets of evaporation data corresponding to the multiple evaporation processes to perform a fixed number of multiple learning operations on the convolutional neural network to obtain the convolutional neural network after completing the multiple learning operations and using it as an AI analysis model includes: using the multiple sets of evaporation data corresponding to the multiple evaporation processes to perform multiple learning operations on the convolutional neural network.

9. The MVR evaporation low-temperature assisted concentration intelligent prediction system according to any one of claims 2 to 7, characterized in that: A steam condensate discharge outlet is provided on the right side of the concentrating tank body, and a concentrated material discharge outlet is provided at the bottom of the concentrating tank body, for respectively discharging the steam condensate and concentrated material obtained after the evaporation treatment of the salt-containing water. A material inlet is also provided on the left side of the concentrating tank body for inputting salt-containing water, and the opening height of the material inlet in the concentrating tank body is higher than the opening height of the air inlet in the concentrating tank body.

10. The MVR evaporation low temperature assisted concentration intelligent prediction system according to claim 9, characterized in that: An exhaust port connected to one end of the first communicating pipe is provided at the top of the concentrating tank body for discharging the low-temperature secondary steam in the concentrating tank body, and the other end of the first communicating pipe is connected to one end of the MVR compressor, and is used to send the low-temperature secondary steam to the MVR compressor to perform mechanical compression processing to obtain high-temperature heating steam, including: the temperature of the low-temperature secondary steam is between 30 degrees Celsius and 80 degrees Celsius, and the temperature of the high-temperature heating steam is between 80 degrees Celsius and 100 degrees Celsius; wherein, an exhaust port connected to one end of the first communicating pipe is provided at the top of the concentrating tank body for discharging the low-temperature secondary steam in the concentrating tank body, and the other end of the first communicating pipe is connected to one end of the MVR compressor, and is used to send the low-temperature secondary steam to the MVR compressor to perform mechanical compression processing to obtain high-temperature heating steam, including: the MVR compressor is a mechanical thermal energy compression evaporator, and is used to perform temperature raising processing on the received low-temperature secondary steam.

Images