Design method and system of flue gas waste heat recovery device

Abstract

The invention provides a design method and system of a flue gas waste heat recovery device. The design method comprises the steps of collecting field arrangement data of an electric power plant, constructing a heat supply equipment model of the electric power plant, and performing feature extraction on the heat supply equipment model by using a deep neural network, a plurality of waste heat generation positions of the electric power plant are obtained and marked in the heat supply equipment model, a waste heat distribution model is obtained, a preset virtual plate heat exchanger and a preset virtual absorption heat pump are added into the waste heat distribution model for heat collection experiment simulation, and a preferred heat collection scheme of the electric power plant is obtained. Corresponding plate heat exchangers and absorption heat pumps are added to the electric power plant according to the optimized heat collection scheme, meanwhile, corresponding heat collection monitoring equipment is added to the electric power plant, and a data transmission channel between each plate heat exchanger and the preset heat collection monitoring equipment and a data transmission channel between each absorption heat pump and the preset heat collection monitoring equipment are debugged; and generating the flue gas waste heat recovery device of the electric power plant.

Description

Technical Field

[0001] The present invention relates to the technical field of waste heat recovery, and particularly relates to a design method and system for a flue gas waste heat recovery device. Background Art

[0002] A power plant, also known as a power station, is a facility that converts different forms of energy (such as fossil fuels, nuclear energy, hydropower, wind energy, solar energy, etc.) into electrical energy. Power plants are one of the important infrastructure in modern society, and they provide essential energy for daily life and industrial activities.

[0003] With the progress of technology and the improvement of environmental protection requirements, power plants are developing towards a more efficient, clean, and sustainable direction. However, due to the special nature of the work of power plants, a large amount of heat is easily generated during the power generation process. In current engineering applications, a direct contact spray tower is generally used for cooling to improve the heat transfer efficiency. However, this method requires a large amount of water resources, which is not only not environmentally friendly but also causes certain damage to the equipment in the power plant. Moreover, the internal facilities of different power plants are different, and a waste heat recovery device cannot adapt to individual power plants.

[0004] Therefore, the present invention provides a design method and system for a flue gas waste heat recovery device. Summary of the Invention

[0005] A design method and system for a flue gas waste heat recovery device according to the present invention constructs a waste heat recovery device based on the actual data of a power plant, increases the utilization rate of flue gas waste heat, so as to enhance the heating capacity and reduce the operating energy consumption.

[0006] The present invention provides a design method for a flue gas waste heat recovery device, including:

[0007] Step 1: Collect the on-site layout data of the power plant and construct a heating equipment model of the power plant;

[0008] Step 2: Use a deep neural network to extract features from the heating equipment model to obtain several waste heat generation positions of the power plant and mark them in the heating equipment model to obtain a waste heat distribution model;

[0009] Step 3: Add a preset virtual plate heat exchanger and a preset virtual absorption heat pump to the waste heat distribution model for heat collection experiment simulation to obtain an optimal heat collection scheme for the power plant;

[0010] Step 4: Add corresponding plate heat exchangers and absorption heat pumps to the power plant according to the optimal heat collection scheme, and at the same time add corresponding heat collection supervision equipment to the power plant;

[0011] Step 5: Debug the data transmission channels between each of the plate heat exchangers and the absorption heat pump and the preset heat collection supervision device respectively to generate the flue gas waste heat recovery device of the power plant.

[0012] In an implementable manner,

[0013] The said step 1 includes:

[0014] Step 11: Obtain the on-site image of the power plant, perform image recognition on the on-site image, and determine a number of on-site devices included in the power plant;

[0015] Step 12: Search for the device attributes corresponding to each of the on-site devices in the big data respectively, and screen the heating devices according to the device attributes;

[0016] Step 13: Perform on-site collection on each of the heating devices respectively to obtain the device data corresponding to each of the heating devices, and input the device data to the corresponding device position in the on-site image to generate the heating device model of the power plant.

[0017] In an implementable manner,

[0018] The said step 2 includes:

[0019] Step 21: Obtain the model parameters included in the heating device model, establish the three-dimensional device image of the power plant, perform convolution processing on the three-dimensional device image by using the deep neural network, obtain the device features corresponding to each heating device according to the convolution processing result, and combine the device features based on the model positions of each heating device in the heating model to generate a number of multi-dimensional heating features of the power plant;

[0020] Step 22: Perform convolution processing on each of the multi-dimensional heating features by using the deep network respectively to obtain a number of local features corresponding to each of the multi-dimensional heating features, and superimpose the local features into the corresponding multi-dimensional heating features to obtain a number of heating function information of the power plant;

[0021] Step 23: Build the heating dynamic diagram of the power plant based on the heating function information, capture the heat flow characteristics of the power plant in the heating dynamic diagram, determine a number of waste heat generation positions of the power plant, and mark each of the waste heat generation positions in the heating device model respectively;

[0022] Step 24: Input the device features corresponding to each of the heating devices into the heating device model respectively for heating simulation, obtain the waste heat accumulation trend corresponding to each of the waste heat generation positions, and generate the waste heat distribution model of the power plant.

[0023] In an implementable manner,

[0024] Step 3 includes:

[0025] Step 31: Run the waste heat distribution model to obtain the corresponding waste heat accumulation amount at each waste heat generation position per unit time, determine the waste heat recovery threshold corresponding to each waste heat generation position, adjust the first device parameters of the preset virtual plate heat exchanger and the second device parameters of the preset virtual absorption heat pump based on the waste heat recovery threshold, and obtain the device to be selected corresponding to each waste heat generation position;

[0026] Step 32: Establish several device matching schemes based on the devices to be selected corresponding to each waste heat generation position. After adding the corresponding devices to the waste heat distribution model for each device matching scheme, conduct a heat collection experiment simulation to obtain the total heat collection amount corresponding to each device matching scheme;

[0027] Step 33: Screen the target device matching scheme with the highest total heat collection amount, obtain the heat collection efficiency and heat production efficiency corresponding to each waste heat generation position in the waste heat distribution model, and adjust the parameters of the target device with the heat collection efficiency less than the heat production efficiency to generate the preferred heat collection scheme for the power plant.

[0028] In an implementable manner,

[0029] It further includes:

[0030] When conducting the heat collection experiment simulation, collect the heat of each waste heat generation position respectively to obtain the heat collection efficiency and heat production efficiency corresponding to each waste heat generation position, generate an efficiency corresponding list for each device matching scheme and display it.

[0031] In an implementable manner,

[0032] Step 4 includes:

[0033] Step 41: Determine the heat collection device corresponding to each waste heat generation position according to the preferred heat collection scheme, generate a device installation guidance scheme and display it;

[0034] Step 42: After the heat collection devices are installed, connect each heat collection device to the preset heat collection supervision device respectively.

[0035] In an implementable manner,

[0036] Step 5 includes:

[0037] Step 51: Set a corresponding first data transmission channel for each of the plate heat exchangers according to the corresponding first data transmission method between each plate heat exchanger and the preset heat collection supervision device;

[0038] Step 52: Set a corresponding second data transmission channel for each of the absorption heat pumps according to the corresponding second data transmission method between each absorption heat pump and the preset heat collection supervision device;

[0039] Step 53: Control the preset heat collection supervision device to collect the first data corresponding to each plate heat exchanger and the second data corresponding to each absorption heat pump, and construct the flue gas waste heat recovery device of the power plant.

[0040] In an implementable manner,

[0041] It further includes:

[0042] Obtain the real-time recovery data of the flue gas waste heat recovery device and transmit it to a specified terminal for display.

[0043] The present invention provides a design system for a flue gas waste heat recovery device, including:

[0044] A model building module, configured to collect on-site layout data of a power plant and construct a heating equipment model of the power plant;

[0045] A feature processing module, configured to use a deep neural network to extract features from the heating equipment model, obtain several waste heat generation positions of the power plant and mark them in the heating equipment model to obtain a waste heat distribution model;

[0046] An experimental simulation module, configured to add a preset virtual plate heat exchanger and a preset virtual absorption heat pump to the waste heat distribution model for heat collection experimental simulation to obtain an optimal heat collection scheme for the power plant;

[0047] A heat collection setting module, configured to add corresponding plate heat exchangers and absorption heat pumps to the power plant according to the optimal heat collection scheme, and at the same time add a corresponding heat collection supervision device to the power plant;

[0048] A device composition module, configured to respectively debug the data transmission channels between each plate heat exchanger and the absorption heat pump and the preset heat collection supervision device to generate the flue gas waste heat recovery device of the power plant.

[0049] In an implementable manner,

[0050] The feature processing module includes:

[0051] A deep convolution unit is used to obtain the model parameters included in the heating equipment model, establish a three-dimensional equipment image of the power plant, perform convolution processing on the three-dimensional equipment image using the deep neural network, obtain the equipment features corresponding to each heating equipment according to the convolution processing results, and combine the equipment features based on the model positions of each heating equipment in the heating model to generate several multi-dimensional heating features of the power plant;

[0052] A repeated convolution unit is used to perform convolution processing on each multi-dimensional heating feature respectively using the deep network, obtain several local features corresponding to each multi-dimensional heating feature, and superimpose the local features into the corresponding multi-dimensional heating features to obtain several heating function information of the power plant;

[0053] A waste heat positioning unit is used to build a heating dynamic map of the power plant based on the heating function information, capture the heat flow characteristics of the power plant in the heating dynamic map, determine several waste heat generation positions of the power plant, and mark each waste heat generation position in the heating equipment model respectively;

[0054] A heating simulation unit is used to input the equipment features corresponding to each heating equipment into the heating equipment model for heating simulation respectively, obtain the waste heat accumulation trend corresponding to each waste heat generation position, and generate a waste heat distribution model of the power plant.

[0055] The achievable beneficial effects of the above technical solution are as follows: In order to improve the heat collection efficiency of the power plant, first construct a heating equipment model of the power plant according to the on-site layout data of the power plant, then use a deep neural network to extract features from the heating equipment model, determine several waste heat generation positions of the power plant, thus construct a waste heat distribution model of the power plant, and then input virtual devices into the waste heat distribution model for heat collection experiment simulation, obtain an optimized heat collection scheme for the power plant, and thus conduct on-site layout of the power plant, construct a complete flue gas waste heat recovery device. In this way, not only can the waste heat generated by power plant equipment be quickly collected, but also the working conditions of each device can be monitored, reducing damage to the devices.

[0056] Other features and advantages of the present invention will be described in the following specification, and, in part, will become apparent from the specification or be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the written specification and the drawings.

[0057] The technical solution of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0058] The accompanying drawings are used to provide a further understanding of the present invention and form a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the accompanying drawings:

[0059] Figure 1 It is a schematic working flow diagram of a design method for a flue gas waste heat recovery device in an embodiment of the present invention;

[0060] Figure 2 It is a schematic composition diagram of a design system for a flue gas waste heat recovery device in an embodiment of the present invention. Detailed implementation manners

[0061] The following is an illustration of the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used for illustrating and explaining the present invention and are not used for limiting the present invention.

[0062] Embodiment 1

[0063] This embodiment provides a design method for a flue gas waste heat recovery device, as Figure 1 shown, including:

[0064] Step 1: Collect on-site layout data of the power plant and construct a heating equipment model of the power plant;

[0065] Step 2: Use a deep neural network to extract features from the heating equipment model to obtain several waste heat generation positions of the power plant and mark them in the heating equipment model to obtain a waste heat distribution model;

[0066] Step 3: Add a preset virtual plate heat exchanger and a preset virtual absorption heat pump to the waste heat distribution model for heat collection experiment simulation to obtain an optimal heat collection scheme for the power plant;

[0067] Step 4: Add corresponding plate heat exchangers and absorption heat pumps to the power plant according to the optimal heat collection scheme, and at the same time add corresponding heat collection supervision equipment to the power plant;

[0068] Step 5: Debug the data transmission channels between each plate heat exchanger and the absorption heat pump and the preset heat collection supervision equipment respectively to generate a flue gas waste heat recovery device for the power plant.

[0069] In this example, the on-site layout data represents the layout of various equipment inside the power plant;

[0070] In this example, the heating equipment model represents the result of presenting the structure of the heating equipment in the power plant using model technology;

[0071] In this example, the waste heat distribution model represents the result of presenting the waste heat of the heating equipment in the power plant using model technology;

[0072] In this example, the virtual plate heat exchanger represents a virtual structure established in the model space to represent the function of the plate heat exchanger, and the preset virtual absorption heat pump represents a virtual structure established in the model space to represent the function of the absorption heat pump;

[0073] In this example, the heat collection experiment simulation represents the process of using the waste heat distribution model to simulate the heat collection effects of the plate heat exchanger and the absorption heat pump;

[0074] In this example, the heat collection supervision device represents a device used to supervise the working processes of the plate heat exchanger and the absorption heat pump.

[0075] The working principle and beneficial effects of the above technical solution: In order to improve the heat collection efficiency of the power plant, first construct the heat supply equipment model of the power plant according to the on-site layout data of the power plant, then use the deep neural network to extract the features of the heat supply equipment model, determine several waste heat generation positions of the power plant, thereby constructing the waste heat distribution model of the power plant, and then input the virtual devices into the waste heat distribution model for heat collection experiment simulation, obtain the optimal heat collection scheme of the power plant, and thus conduct on-site layout of the power plant, construct a complete flue gas waste heat recovery device. In this way, not only can the waste heat generated by the power plant equipment be quickly collected, but also the working conditions of each device can be supervised, reducing the damage to the devices.

[0076] Embodiment 2

[0077] Based on Embodiment 1, for the design method of the flue gas waste heat recovery device, Step 1 includes:

[0078] Step 11: Obtain the on-site image of the power plant, perform image recognition on the on-site image, and determine several on-site devices included in the power plant;

[0079] Step 12: Search for the device attributes corresponding to each on-site device in the big data respectively, and screen the heat supply equipment according to the device attributes;

[0080] Step 13: Conduct on-site collection on each heat supply equipment respectively, obtain the device data corresponding to each heat supply equipment, and input the device data to the corresponding device position in the on-site image to generate the heat supply equipment model of the power plant.

[0081] In this example, the device attribute represents the attribute of the work that an on-site device can perform.

[0082] Working principle and beneficial effects of the above technical solution: By identifying the on-site images of the power plant to determine the on-site equipment included in the power plant, then analyzing the equipment attributes of each on-site equipment, and further determining the heating equipment in the power plant. Finally, the equipment data of the heating equipment is collected on-site to construct a heating equipment model of the power plant. In this way, the influence of non-heating equipment in the power plant can be eliminated, a complete heating equipment model is constructed, and the effectiveness of the design result of this time is guaranteed.

[0083] Embodiment 3

[0084] Based on Embodiment 1, for the design method of a flue gas waste heat recovery device, Step 2 includes:

[0085] Step 21: Obtain the model parameters included in the heating equipment model, establish a three-dimensional equipment image of the power plant, perform convolutional processing on the three-dimensional equipment image using the deep neural network, obtain the equipment features corresponding to each heating equipment according to the convolutional processing result, and combine the equipment features based on the model positions of each heating equipment in the heating model to generate several multi-dimensional heating features of the power plant;

[0086] Step 22: Use the deep network to perform convolutional processing on each multi-dimensional heating feature respectively, obtain several local features corresponding to each multi-dimensional heating feature, and superimpose the local features into the corresponding multi-dimensional heating features to obtain several heating function information of the power plant;

[0087] Step 23: Build a heating dynamic diagram of the power plant based on the heating function information, capture the heat flow characteristics of the power plant in the heating dynamic diagram, determine several waste heat generation positions of the power plant, and mark each waste heat generation position in the heating equipment model respectively;

[0088] Step 24: Input the equipment features corresponding to each heating equipment into the heating equipment model for heating simulation respectively, obtain the waste heat accumulation trend corresponding to each waste heat generation position, and generate a waste heat distribution model of the power plant.

[0089] In this example, the equipment feature represents the feature presented by a heating equipment during operation;

[0090] In this example, the multi-dimensional heating feature represents the feature presented when multiple heating equipment work simultaneously after combining the equipment features of multiple heating equipment;

[0091] In this example, the local feature represents the result of dividing the multi-dimensional heating feature into several parts and performing detailed processing on each part;

[0092] In this example, the heat supply function information represents several functions presented by the power plant during the heat supply process;

[0093] In this example, the heat flow characteristics represent the characteristics presented when the heat generated by the power plant flows on-site;

[0094] In this example, the heat supply dynamic diagram represents the heat supply process of the power plant in the form of an animation;

[0095] In this example, the waste heat accumulation trend represents the trend of heat accumulation generated at a waste heat generation location without external interference.

[0096] The working principle and beneficial effects of the above technical solution: First, a three-dimensional equipment image of the power plant is established according to the model parameters of the heat supply equipment model, and then it is subjected to convolutional processing using a neural network to obtain the equipment characteristics of each heat supply equipment. Further, the equipment characteristics are combined to obtain several multi-dimensional heat supply characteristics of the power plant. Then, the local characteristics of each multi-dimensional heat supply characteristic are analyzed through convolutional processing, and the heat supply function information of the power plant is generated by means of feature superposition. A heat supply dynamic diagram of the power plant is built, and the heat flow characteristics of the power plant are captured in this dynamic diagram. The waste heat generation location where heat accumulation occurs is determined according to the direction and speed of heat flow. Finally, the heat supply equipment model is used to perform heat supply simulation on it, and the waste heat accumulation trend corresponding to each waste heat generation location is determined, and a waste heat distribution model of the power plant is generated. In this way, each heat supply equipment in the power plant can be analyzed, and the functions of multiple heat supply equipment can also be analyzed simultaneously to generate an effective waste heat distribution model, improving the accuracy of subsequent device setting.

[0097] Example 4

[0098] Based on Example 1, for the design method of the flue gas waste heat recovery device, Step 3 includes:

[0099] Step 31: Run the waste heat distribution model to obtain the waste heat accumulation amount corresponding to each waste heat generation location per unit time, determine the waste heat recovery threshold corresponding to each waste heat generation location, and adjust the first device parameter of the preset virtual plate heat exchanger and the second device parameter of the preset virtual absorption heat pump based on the waste heat recovery threshold to obtain the device to be selected corresponding to each waste heat generation location;

[0100] Step 32: Establish several device matching schemes based on the device to be selected corresponding to each waste heat generation location. After adding the corresponding devices to the waste heat distribution model based on each device matching scheme, perform a heat collection experiment simulation to obtain the total heat collection amount corresponding to each device matching scheme;

[0101] Step 33: Screen the target device matching scheme with the highest total heat, obtain the heat collection efficiency and heat production efficiency corresponding to each waste heat generation position in the waste heat distribution model, adjust the parameters of the target device with the heat collection efficiency less than the heat production efficiency, and generate the preferred heat collection scheme for the power plant.

[0102] In this example, the unit time is 45 minutes;

[0103] In this example, the waste heat recovery threshold represents the minimum recovery speed when the device recovers heat;

[0104] In this example, the devices to be selected are: the plate heat exchanger with adjusted parameters and the absorption heat pump with adjusted parameters;

[0105] In this example, when the heat collection efficiency is not less than the heat production efficiency, it indicates that the heat in the power plant is in a piled-up state.

[0106] The working principle and beneficial effects of the above technical solution: By running the waste heat distribution model to determine the waste heat accumulation amount at each waste heat generation position within 45 minutes, thereby generating the waste heat recovery threshold to adjust the parameters of the preset virtual plate heat exchanger and the preset virtual absorption heat pump, and further constructing the device matching scheme through combination. After adding the corresponding devices to the waste heat distribution model, conduct the heat collection experiment simulation. The simulation method can improve the efficiency of device selection, reduce the input of manpower and material resources, reduce the expenditure of the power plant, and then select the target device matching scheme according to the total heat collection of each device matching scheme, and then fine-tune the target device matching scheme according to the actual situation of each waste heat generation position to generate the preferred heat collection scheme for the power plant. Relevant personnel can carry out the heat collection layout of the power plant under the guidance of this scheme, improve the work efficiency of relevant personnel, and reduce the probability of power plant shutdown.

[0107] Example 5

[0108] Based on Example 4, the design method of the flue gas waste heat recovery device further includes:

[0109] When conducting the heat collection experiment simulation, collect the heat at each waste heat generation position respectively, obtain the heat collection efficiency and heat production efficiency corresponding to each waste heat generation position, generate an efficiency corresponding list for each device matching scheme and display it.

[0110] The working principle and beneficial effects of the above technical solution: Display the heat collection efficiency and heat production efficiency corresponding to each waste heat generation position during the experiment to relevant personnel, which can help relevant personnel initially judge the perfection of the power plant equipment function and improve the work quality of the power plant.

[0111] Example 6

[0112] Based on Embodiment 1, for the design method of the flue gas waste heat recovery device, Step 4 includes:

[0113] Step 41: Determine the heat collection device corresponding to each waste heat generation position according to the preferred heat collection scheme, generate a device installation guidance scheme and display it;

[0114] Step 42: After the installation of the heat collection device is completed, connect each heat collection device to a preset heat collection supervision device respectively.

[0115] In this example, the heat collection device includes: a plate heat exchanger and an absorption heat pump.

[0116] The working principle and beneficial effects of the above technical solution: Under the guidance of the preferred heat collection scheme, install the corresponding heat collection device for each waste heat generation position, and connect them all to the heat collection supervision device for work supervision, thus constructing a complete flue gas waste heat recovery device.

[0117] Embodiment 7

[0118] Based on Embodiment 1, for the design method of the flue gas waste heat recovery device, Step 5 includes:

[0119] Step 51: Set a corresponding first data transmission channel for each plate heat exchanger according to the corresponding first data transmission method between each plate heat exchanger and the preset heat collection supervision device;

[0120] Step 52: Set a corresponding second data transmission channel for each absorption heat pump according to the corresponding second data transmission method between each absorption heat pump and the preset heat collection supervision device;

[0121] Step 53: Control the preset heat collection supervision device to collect the first data corresponding to each plate heat exchanger and the second data corresponding to each absorption heat pump, and construct the flue gas waste heat recovery device of the power plant.

[0122] The working principle and beneficial effects of the above technical solution: Connect the plate heat exchanger and the absorption heat pump to the preset heat collection supervision device and conduct debugging to ensure the functional integrity of each device, thus constructing a flue gas waste heat recovery device suitable for this power plant.

[0123] Embodiment 8

[0124] Based on Embodiment 1, the design method of the flue gas waste heat recovery device further includes:

[0125] Obtain the real-time recovery data of the flue gas waste heat recovery device and transmit it to a specified terminal for display.

[0126] The working principle and beneficial effects of the above technical solution: Relevant personnel can understand the working conditions of the flue gas waste heat recovery device at any time through a designated terminal.

[0127] Example 9

[0128] This example provides a design system for a flue gas waste heat recovery device, as Figure 2 shown, including:

[0129] A model building module, which is used to collect on-site layout data of a power plant and construct a heating equipment model of the power plant;

[0130] A feature processing module, which is used to extract features from the heating equipment model by using a deep neural network, obtain several waste heat generation positions of the power plant and mark them in the heating equipment model to obtain a waste heat distribution model;

[0131] An experimental simulation module, which is used to add a preset virtual plate heat exchanger and a preset virtual absorption heat pump to the waste heat distribution model for heat collection experimental simulation to obtain an optimal heat collection scheme for the power plant;

[0132] A heat collection setting module, which is used to add corresponding plate heat exchangers and absorption heat pumps to the power plant according to the optimal heat collection scheme, and at the same time add corresponding heat collection supervision equipment to the power plant;

[0133] A device composition module, which is used to debug the data transmission channels between each of the plate heat exchangers and the absorption heat pumps and the preset heat collection supervision equipment respectively to generate a flue gas waste heat recovery device for the power plant.

[0134] In this example, the on-site layout data represents the layout of various equipment inside the power plant;

[0135] In this example, the heating equipment model represents the result of using model technology to present the structure of the heating equipment in the power plant;

[0136] In this example, the waste heat distribution model represents the result of using model technology to present the waste heat of the heating equipment in the power plant;

[0137] In this example, the virtual plate heat exchanger represents a virtual structure established in the model space to represent the function of the plate heat exchanger, and the preset virtual absorption heat pump represents a virtual structure established in the model space to represent the function of the absorption heat pump;

[0138] In this example, the heat collection experimental simulation represents the process of using the waste heat distribution model to simulate the heat collection effects of the plate heat exchanger and the absorption heat pump;

[0139] In this example, the heat collection supervision device refers to a device used to supervise the working processes of the plate heat exchanger and the absorption heat pump.

[0140] The working principle and beneficial effects of the above technical solution: In order to improve the heat collection efficiency of the power plant, first, a heat supply equipment model of the power plant is constructed based on the on-site layout data of the power plant, and then a deep neural network is used to extract features from the heat supply equipment model to determine several waste heat generation positions of the power plant, thereby constructing a waste heat distribution model of the power plant. Then, virtual devices are input into the waste heat distribution model for heat collection experiment simulation to obtain an optimal heat collection scheme for the power plant, and thus the on-site layout of the power plant is carried out to construct a complete flue gas waste heat recovery device. In this way, not only can the waste heat generated by the power plant equipment be quickly collected, but also the working conditions of each device can be supervised, reducing damage to the devices.

[0141] Example 10

[0142] Based on Example 9, in the design system of the flue gas waste heat recovery device, the feature processing module includes:

[0143] A deep convolution unit, which is used to obtain the model parameters included in the heat supply equipment model, establish a three-dimensional equipment image of the power plant, perform convolution processing on the three-dimensional equipment image using the deep neural network, obtain the equipment features corresponding to each heat supply equipment according to the convolution processing results, and combine the equipment features based on the model positions of each heat supply equipment in the heat supply model to generate several multi-dimensional heat supply features of the power plant;

[0144] A repeated convolution unit, which is used to perform convolution processing on each multi-dimensional heat supply feature using the deep network respectively to obtain several local features corresponding to each multi-dimensional heat supply feature, and superimpose the local features into the corresponding multi-dimensional heat supply features to obtain several heat supply function information of the power plant;

[0145] A waste heat positioning unit, which is used to build a heat supply dynamic diagram of the power plant based on the heat supply function information, capture the heat flow characteristics of the power plant in the heat supply dynamic diagram, determine several waste heat generation positions of the power plant, and mark each waste heat generation position in the heat supply equipment model respectively;

[0146] A heat supply simulation unit, which is used to input the equipment features corresponding to each heat supply equipment into the heat supply equipment model for heat supply simulation respectively to obtain the waste heat accumulation trend corresponding to each waste heat generation position, and generate a waste heat distribution model of the power plant.

[0147] In this example, the equipment feature represents the feature presented by a heat supply equipment during operation;

[0148] In this example, the multi-dimensional heating feature represents the feature presented when multiple heating devices work simultaneously after combining the device features of multiple heating devices;

[0149] In this example, the local feature represents the result of dividing the multi-dimensional heating feature into several parts and performing detailed processing on each part;

[0150] In this example, the heating function information represents several functions presented by the power plant during the heating process;

[0151] In this example, the heat flow feature represents the feature presented when the heat generated by the power plant flows on-site;

[0152] In this example, the heating dynamic diagram represents the heating process of the power plant presented in the form of an animation;

[0153] In this example, the waste heat accumulation trend represents the trend of heat accumulation generated at a waste heat generation location without external interference.

[0154] The working principle and beneficial effects of the above technical solution: First, a three-dimensional device image of the power plant is established according to the model parameters of the heating device model, and then it is subjected to convolutional processing using a neural network to obtain the device features of each heating device. Further, the device features are combined to obtain several multi-dimensional heating features of the power plant. Then, the local features of each multi-dimensional heating feature are analyzed through convolutional processing, and the heating function information of the power plant is generated by feature superposition. A heating dynamic diagram of the power plant is built, and the heat flow feature of the power plant is captured in this dynamic diagram. The waste heat generation location where heat accumulation occurs is determined according to the direction and speed of heat flow. Finally, the heating device model is used to perform heating simulation on it, and the waste heat accumulation trend corresponding to each waste heat generation location is determined, generating a waste heat distribution model of the power plant. In this way, each heating device in the power plant can be analyzed, and the functions of multiple heating devices can also be analyzed simultaneously, generating an effective waste heat distribution model, improving the accuracy of subsequent device setting.

[0155] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A design method for a flue gas waste heat recovery device, characterized in that: include: Step 1: Collecting on-site layout data of the power plant and constructing a heating equipment model of the power plant; Step 2: Using a deep neural network to extract features from the heating equipment model, obtain several waste heat generation locations of the power plant and mark them in the heating equipment model to obtain a waste heat distribution model; Step 3: adding a preset virtual plate heat exchanger and a preset virtual absorption heat pump to the waste heat distribution model to perform a heat collection experiment simulation to obtain an optimal heat collection scheme for the power plant; Step 4: adding corresponding plate heat exchangers and absorption heat pumps to the power plant according to the preferred heat collection scheme, and adding corresponding heat collection monitoring equipment to the power plant; Step 5: Debug the data transmission channels between each of the plate heat exchangers and the absorption heat pump and the preset heat collection monitoring device to generate the flue gas waste heat recovery device of the power plant.

2. The design method of a flue gas waste heat recovery device according to claim 1, characterized in that: The step 1 comprises: Step 11: acquiring a field image of the power plant, performing image recognition on the field image, and determining a number of field devices included in the power plant; Step 12: Searching for device attributes corresponding to each of the field devices in the big data, and selecting heating devices according to the device attributes; Step 13: Conduct on-site data collection for each of the heating equipment to obtain equipment data corresponding to each of the heating equipment, input the equipment data into the corresponding equipment position in the on-site image, and generate a heating equipment model of the power plant.

3. The design method of a flue gas waste heat recovery device according to claim 1, characterized in that: The step 2 comprises: Step 21: Obtain model parameters contained in the heating equipment model, establish a three-dimensional equipment image of the power plant, perform convolution processing on the three-dimensional equipment image using the deep neural network, obtain equipment features corresponding to each heating equipment according to the convolution processing result, combine the equipment features based on the model position of each heating equipment in the heating model, and generate a plurality of multi-dimensional heating features of the power plant; Step 22: using the deep network to perform convolution processing on each of the multidimensional heating features, respectively, to obtain a number of local features corresponding to each of the multidimensional heating features, and superimposing the local features onto the corresponding multidimensional heating features to obtain a number of heating function information of the power plant; Step 23: constructing a heating dynamic diagram of the power plant based on the heating function information, capturing the heat flow characteristics of the power plant in the heating dynamic diagram, determining a plurality of waste heat generation locations of the power plant, and marking each of the waste heat generation locations in the heating equipment model; Step 24: Input the equipment characteristics corresponding to each of the heating equipment into the heating equipment model to perform heating simulation, obtain the waste heat accumulation trend corresponding to each of the waste heat generation positions, and generate a waste heat distribution model of the power plant.

4. The design method of a flue gas waste heat recovery device according to claim 1, characterized in that: The step 3 comprises: Step 31: running the waste heat distribution model to obtain the waste heat accumulation amount corresponding to each waste heat generation position per unit time, determining the waste heat recovery threshold corresponding to each waste heat generation position, adjusting the first device parameter of the preset virtual plate heat exchanger and the second device parameter of the preset virtual absorption heat pump based on the waste heat recovery threshold, and obtaining the device to be selected corresponding to each waste heat generation position; Step 32: establishing a plurality of device matching schemes based on the selected devices corresponding to each of the waste heat generation positions, adding corresponding devices to the waste heat distribution model based on each of the device matching schemes, and performing a heat collection experiment simulation to obtain a total heat collection amount corresponding to each of the device matching schemes; Step 33: Filter the target device matching scheme with the highest total heat collection, obtain the heat collection efficiency and heat production efficiency corresponding to each waste heat generation position in the waste heat distribution model, adjust the parameters of the target device whose heat collection efficiency is less than the heat production efficiency, and generate the optimal heat collection scheme for the power plant.

5. The design method of a flue gas waste heat recovery device according to claim 4, characterized in that: Also includes: When performing the heat collection experiment simulation, heat is collected at each waste heat generation position to obtain the heat collection efficiency and heat production efficiency corresponding to each waste heat generation position, and a corresponding efficiency list corresponding to each device matching solution is generated and displayed.

6. The design method of a flue gas waste heat recovery device according to claim 1, characterized in that: The step 4 comprises: Step 41: determining the heat collection device corresponding to each of the waste heat generation positions according to the preferred heat collection scheme, generating and displaying a device installation guidance scheme; Step 42: After the installation of the heat collecting devices is completed, each heat collecting device is connected to a preset heat collecting monitoring device.

7. The design method of a flue gas waste heat recovery device according to claim 1, characterized in that: The step 5 comprises: Step 51: setting a corresponding first data transmission channel for each of the plate heat exchangers according to the corresponding first data transmission mode between each of the plate heat exchangers and the preset heat collection monitoring device; Step 52: setting a corresponding second data transmission channel for each of the absorption heat pumps according to the corresponding second data transmission mode between each of the absorption heat pumps and the preset heat collection monitoring device; Step 53: Control the preset heat collection monitoring device to collect the first data corresponding to each of the plate heat exchangers and the second data corresponding to each of the absorption heat pumps to construct the flue gas waste heat recovery device of the power plant.

8. The design method of a flue gas waste heat recovery device according to claim 7, characterized in that: Also includes: The real-time recovery data of the flue gas waste heat recovery device is obtained and transmitted to a designated terminal for display.

9. A design system for a flue gas waste heat recovery device, characterized in that: include: A model building module, used to collect on-site layout data of the power plant and build a heating equipment model of the power plant; A feature processing module, used to extract features from the heating equipment model using a deep neural network, obtain a number of waste heat generation locations of the power plant and mark them in the heating equipment model, and obtain a waste heat distribution model; An experimental simulation module, used for adding a preset virtual plate heat exchanger and a preset virtual absorption heat pump to the waste heat distribution model to perform a heat collection experimental simulation, so as to obtain an optimal heat collection scheme for the power plant; A heat collection setting module, used for adding corresponding plate heat exchangers and absorption heat pumps to the power plant according to the preferred heat collection scheme, and adding corresponding heat collection supervision equipment to the power plant; The device composition module is used to debug the data transmission channel between each of the plate heat exchangers and the absorption heat pump and the preset heat collection supervision equipment, so as to generate the flue gas waste heat recovery device of the power plant.

10. A design system for a flue gas waste heat recovery device according to claim 9, characterized in that: The feature processing module comprises: a deep convolution unit, used to obtain model parameters contained in the heating equipment model, establish a three-dimensional equipment image of the power plant, perform convolution processing on the three-dimensional equipment image using the deep neural network, obtain equipment features corresponding to each heating equipment according to the convolution processing result, combine the equipment features based on the model position of each heating equipment in the heating model, and generate a plurality of multi-dimensional heating features of the power plant; A repeated convolution unit is used to use the deep network to perform convolution processing on each of the multi-dimensional heating features respectively, to obtain a number of local features corresponding to each of the multi-dimensional heating features, and to superimpose the local features onto the corresponding multi-dimensional heating features to obtain a number of heating function information of the power plant; a waste heat positioning unit, configured to construct a heat supply dynamic diagram of the power plant based on the heat supply function information, capture heat flow characteristics of the power plant in the heat supply dynamic diagram, determine a plurality of waste heat generation locations of the power plant, and mark each of the waste heat generation locations in the heat supply equipment model; The heating simulation unit is used to input the equipment characteristics corresponding to each of the heating equipment into the heating equipment model to perform heating simulation, obtain the waste heat accumulation trend corresponding to each of the waste heat generation positions, and generate a waste heat distribution model of the power plant.

Images