Air compressor waste heat recovery heating area prediction system

Abstract

The invention provides an air compressor waste heat recovery heating area prediction system, and relates to the technical field of industrial waste heat recovery and building energy consumption analysis. The air compressor waste heat utilization efficiency and the heating area are accurately modeled in combination with building heat load parameters and pipeline heat loss evaluation data of all the heating areas, and the system can recognize the qualified state of all the heating areas in real time in combination with the predicted effective heating area. For the areas with insufficient heating, the system automatically generates a waste heat allocation optimization strategy, redundant heat of the qualified areas is distributed to the insufficient areas according to the proportion, and therefore heat energy resource heating balance among the multiple areas is achieved; a pipeline loss collection module is arranged to collect parameters such as the length and the outer diameter of a pipeline between a heat source and each monitoring area and the thermal conductivity of a heat preservation layer, so that a prediction result is more suitable for field reality.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial waste heat recovery and building energy consumption analysis, and in particular to an air compressor waste heat recovery heating area prediction system. Background Art

[0002] Air compressors are widely used in industrial settings, generating significant amounts of heat during operation. Failure to recycle this heat not only wastes energy but can also lead to abnormally high workshop temperatures and increased energy consumption. To improve energy efficiency, a growing number of companies are exploring ways to recycle waste heat from air compressors and use it for winter heating within factories or workshops, implementing a green manufacturing strategy that reduces energy consumption and costs.

[0003] However, in actual engineering applications, air compressor waste heat recovery systems present numerous challenges. Traditional waste heat recovery designs often rely on empirical methods or linear heat load assessments to predict the heating area. These methods ignore the combined effects of key factors such as compressor operating status, building thermal parameters, and pipeline heat losses. This results in significant discrepancies between heating area predictions and actual demand.

[0004] Especially when transporting waste heat from air compressors to different areas (such as workshops, offices, and warehouses), heat requirements vary significantly due to differences in building structure, building envelope insulation performance, heating type, and thermal resistance. Furthermore, significant heat loss occurs in the pipeline during heat transfer, influenced by factors such as pipeline length, insulation thermal conductivity, and pipe diameter. The actual heat reaching each area often differs from the theoretical output value.

[0005] This series of uncertainties leads to redundant heating in some areas, resulting in energy waste; while in other areas, insufficient heating affects normal production and office comfort, and may even require additional electric heating to compensate, increasing costs. The above information disclosed in the background section is only for the purpose of enhancing understanding of the background of this disclosure. Therefore, it may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide an air compressor waste heat recovery heating area prediction system to solve the problems raised in the above background technology.

[0007] To achieve the above objectives, the present invention provides the following technical solutions: a system for predicting the area of ​​heating by recovering waste heat from an air compressor, comprising:

[0008] The operation data acquisition module is used to collect the air compressor electrical input power per unit time during the operation of the air compressor in real time , water flow , air compressor outlet water temperature and the inlet water temperature , construct the air compressor operating condition data group;

[0009] Building environment parameter collection module, used to collect the building area of ​​the i-th heating area , heat capacity , total thermal resistance , thermal insulation grade coefficient , Heating type coefficient , the difference between indoor temperature and outside temperature Summarize and form a building heat load parameter group;

[0010] Pipeline loss collection module, used to collect the length of the pipeline between the i-th detection area and the heat source output , pipe outer diameter D and pipe insulation layer thermal conductivity coefficient , forming a heat loss assessment data group;

[0011] The performance prediction analysis module is used to construct and train a waste heat utilization-heating area correlation prediction model based on the air compressor operating condition data group, heat loss assessment data group, building heat load parameter group and heat loss assessment data group using a convolutional neural network to obtain: the heat load of the i-th heating area , the air compressor heat energy conversion coefficient η1 and the pipe heat loss coefficient of the i-th heating area , and based on the heat load of the i-th heating area , the air compressor heat energy conversion coefficient η1 and the pipe heat loss coefficient of the i-th heating area , comprehensive analysis and prediction to obtain: the effective heating area of ​​the i-th heating area ;

[0012] The strategy output module is used to preset the heating coverage threshold X and calculate the effective heating area of ​​the i-th heating zone. The result is compared with the heating coverage threshold X to identify whether the heating is qualified. If there is insufficient heating, a waste heat allocation optimization strategy is generated to allocate the redundant waste heat ratio of all qualified areas to the areas with insufficient heating to achieve heating balance.

[0013] Furthermore, the operation data acquisition module includes a three-dimensional model acquisition unit and an air compressor operation data acquisition unit;

[0014] The 3D model acquisition unit is used to collect the position data of the air compressor in the workshop in real time using GPS and LiDAR, and convert the coordinate information of the air compressor into 3D coordinate data to form an air compressor position data set;

[0015] It is also used to collect 3D elevation data of the workshop based on LiDAR, drone aerial photography or architectural design drawings, build a 3D model of the workshop, subdivide the interior of the workshop, identify the spatial layout and relative position of each area, collect the position data of the air compressor in the workshop in real time, convert the coordinate information of the air compressor into 3D coordinate data, and mark it in the 3D model of the workshop. Different functional areas are identified according to the 3D model of the workshop, divided into the i-th heating area, and marked in the 3D model of the workshop as: , to Indicates the heating zones 1 to 3 The status mark of each heating area at the sd time point; the heating areas include production workshops, office buildings and storage areas;

[0016] The air compressor operation data acquisition unit is used to collect the air compressor operation data using an electric energy meter, an electromagnetic flow meter and a thermal resistance temperature sensor, and establish an air compressor operation condition data group;

[0017] The air compressor operating condition data group includes: air compressor electrical energy input power per unit time , water flow , air compressor outlet water temperature and the inlet water temperature .

[0018] Furthermore, the building environment parameter acquisition module includes a building area unit and a thermal insulation grade coefficient analysis unit:

[0019] Building area unit, used to extract the length and width of the facade of the i-th heating area, and multiply them to obtain the building area of ​​the i-th heating area ;

[0020] The thermal insulation grade coefficient analysis unit is used to obtain thermal property data of different building materials and structures, query the database and combine it with the collected real-time data to calculate the thermal resistance and heat capacity of each area, including:

[0021] Collect the material density and volume of the i-th heating area and calculate the heat capacity of the i-th heating area :

[0022] ;

[0023] in, is the material density, c is the specific heat capacity in J / kg·K; V is the volume;

[0024] Based on the thermal conductivity of the i-th heating area, the total thermal resistance of the i-th heating area is calculated. , the specific steps include:

[0025] S11. The calculation of total thermal resistance depends on the different structural layers of the heating area, including the thermal resistance of walls, windows, roofs and floors. The thermal resistance of the components of the jth layer is calculated by counting several structural layers (j=1,2,…,m) of each heating area. Calculated by the following formula:

[0026] ;

[0027] in, is the thickness of the jth layer, represents the thermal conductivity of the jth layer;

[0028] S12. Calculate the total thermal resistance of the i-th heating area :

[0029] ; m is the number of all building material layers in the heating area;

[0030] S13, based on the total thermal resistance of the i-th heating area , calculate and obtain the insulation grade coefficient ;

[0031] .

[0032] Furthermore, the building environment parameter acquisition module further includes a heating type coefficient acquisition unit and a heating target temperature acquisition unit;

[0033] The heating type coefficient collection unit is used to collect the heating type of the i-th heating area. The heating types include hot gas heating and hot water heating. When the heating type is hot gas heating, the number value is 001. Hot water is used for heat conduction through floor heating pipes and radiators. The heating type coefficient is When the heating type is hot water heating, the number value is 002, and hot water is used to send hot air through the hot air blower and air conditioner. The heat is mainly transferred in the form of convection. The heating type coefficient is is 1.2;

[0034] Heating target temperature acquisition unit, used to use the temperature sensor to obtain the difference between the indoor temperature and the outside temperature of the i-th heating area ,

[0035] ;

[0036] in, is the indoor temperature of the i-th heating area, is the outside temperature;

[0037] The building area of ​​the i-th heating area , heat capacity , total thermal resistance , thermal insulation grade coefficient , Heating type coefficient , the difference between indoor temperature and outside temperature Summarize and establish a building heat load parameter group.

[0038] Further, the performance prediction analysis module includes a model building unit;

[0039] The model building unit is used to use the convolutional neural network to construct an initial model of the convolutional neural network, and train and test the initial model of the convolutional neural network with the air compressor operating condition data group, the heat loss assessment data group and the building heat load parameter group, and use the trained initial model of the convolutional neural network as the waste heat utilization-heating area correlation prediction model, and use the intermediate layer output of the equipment operation status model as the feature vector to identify feature information, and use the acquired feature information to train and test the waste heat utilization-heating area correlation prediction model, and use the trained waste heat utilization-heating area correlation prediction model as data operation prediction.

[0040] Furthermore, the model building unit includes a building heat load analysis unit, an air compressor heat energy conversion unit, and a loss analysis unit;

[0041] Building heat load analysis unit is used to extract the building area of ​​the i-th heating zone in the building heat load parameter group based on the building heat load parameter group. , heat capacity , total thermal resistance , thermal insulation grade coefficient , Heating type coefficient , the difference between indoor temperature and outside temperature , the heat load of the i-th heating area is calculated by the following formula :

[0042] .

[0043] Furthermore, the air compressor heat energy conversion unit is used to obtain the air compressor heat energy conversion coefficient η1 based on the air compressor operating condition data group and through the following formula:

[0044]

[0045]

[0046] in, Indicates the heat recovered by the air compressor per unit time. Indicates the electrical input power of the air compressor per unit time; represents the specific heat capacity of water, which is set to 4.18 kJ / (kg·K), represents the density of water, set to approximately 1000 kg / m³, Indicates water flow, and Respectively represent the temperature values ​​of the air compressor water outlet and water inlet;

[0047] The loss analysis unit is used to calculate the pipe heat loss coefficient of the i-th heating area based on the heat loss evaluation data group using the following formula :

[0048]

[0049] in, represents the thermal conductivity coefficient of the pipe insulation layer in the i-th heating area; represents the circumference of a circle and is set to 3.1416; D represents the outer diameter of the pipe. Indicates the length of the pipe from the heat source output to the i-th heating area, It is expressed as the heat transfer surface area of ​​the pipe in the i-th heating zone;

[0050] Indicates the temperature inside the pipe during the hot water transportation process. is the outside temperature, Indicates the transmission time;

[0051] When the pipe insulation layer is rock wool, the thermal conductivity coefficient of the pipe insulation layer is 0.035-0.045W / m²·K;

[0052] When the pipe insulation layer is glass wool, the thermal conductivity coefficient of the pipe insulation layer is 0.033-0.040W / m²·K;

[0053] When the pipe insulation layer is polyurethane foam, the thermal conductivity coefficient of the pipe insulation layer is 0.020-0.030W / m²·K;

[0054] When the pipe insulation layer is polyethylene foam, the thermal conductivity of the pipe insulation layer is 0.035-0.045W / m²·K;

[0055] When the pipe insulation layer is foam glass, the thermal conductivity coefficient of the pipe insulation layer is 0.038-0.050W / m²·K;

[0056] When the pipeline insulation layer is a vacuum insulation panel, the thermal conductivity coefficient of the pipeline insulation layer is 0.005-0.008W / m²·K.

[0057] Furthermore, the performance prediction analysis module further includes a prediction analysis unit, which is used to calculate the heat load of the i-th heating area based on the heat load of the i-th heating area. and the pipe heat loss coefficient of the i-th heating area , and the air compressor heat energy conversion coefficient η1, comprehensive analysis to obtain the prediction to obtain the effective heating area of ​​the i-th heating area , the specific steps are:

[0058] S21. The available waste heat generated by the air compressor should be equal to the sum of the heat loads required by all heated areas, and the operating power of the air compressor should be extracted. , the heat conversion coefficient η1 of the air compressor and the operating time t, calculate the recoverable waste heat of the air compressor during the operating time t:

[0059] ;

[0060] S22, Pipeline heat loss coefficient based on the i-th heating area , it is necessary to calculate the effective heat that can actually be used for heating and obtain the effective heat of the i-th heating area ;

[0061] ;

[0062] in, represents the proportion of waste heat allocated to the i-th heating area;

[0063] S23, based on the heat load of the i-th heating area and the area of ​​the i-th heating zone , calculate the heat load per unit area of ​​the i-th heating area :

[0064]

[0065] S24, effective heat of the i-th heating area obtained according to S22 and the heat load per unit area of ​​the i-th heating zone , predict and obtain the effective heating area of ​​the i-th heating area :

[0066] .

[0067] Furthermore, the strategy output module includes an evaluation unit and a strategy unit;

[0068] The evaluation unit is used to preset the heating coverage threshold X and calculate the effective heating area of ​​the i-th heating zone Compare with the heating coverage threshold X to identify whether the heating is qualified, including:

[0069] When the effective heating area of ​​the i-th heating zone < Heating coverage threshold X × 0.75; the area is judged to be severely insufficient in heating, marked as a first-order insufficient heating area, and the first warning instruction is issued;

[0070] When the heating coverage threshold X×0.75≤the effective heating area of ​​the i-th heating zone ≤ heating coverage threshold X, it is judged as a heating insufficient area and marked as a second-order heating insufficient area. The degree of the second-order heating insufficient area is lower than that of the first-order heating insufficient area, and a second warning instruction is issued;

[0071] When the effective heating area of ​​the i-th heating zone >Heating coverage threshold X, judged as a heating qualified area.

[0072] Furthermore, the strategy unit is configured to generate a waste heat allocation optimization strategy based on receiving the first warning instruction and the second warning instruction, including:

[0073] First, count the qualified areas and calculate the redundant heat ratio of the i-th qualified area ,for:

[0074]

[0075] in, The ratio of the area of ​​the heating zone that exceeds the heating coverage threshold X to the total area, that is, the ratio of the redundant heating area; and multiplied by the ratio of the excess heat allocated to the i-th heating zone, the ratio of the redundant heat that can be released by the heating zone is obtained;

[0076] Allocate 60-70% of the redundant heat ratio of all qualified areas to the first-level heating deficiency areas;

[0077] Allocate 20-30% of the redundant heat ratio of all qualified areas to the secondary heating deficiency areas;

[0078] If there are still first-order heating shortage areas and second-order heating shortage areas, the remaining gap area is calculated for each unqualified area, and the percentage of redundant waste heat ratio is redistributed to the remaining gap area.

[0079] Compared with the prior art, the present invention has the following beneficial effects:

[0080] Based on this system, the present invention constructs an operating condition data group including air compressor power input, water flow, inlet and outlet water temperature, etc., and combines the building heat load parameters and pipeline heat loss assessment data of each heating area to achieve accurate modeling of air compressor waste heat utilization efficiency and heating area, effectively avoiding the heating area deviation problem caused by empirical methods or single-factor estimation in traditional systems, and improving the scientificity and accuracy of heating planning.

[0081] By setting a heating coverage threshold X and combining it with the predicted effective heating area, the system can identify the qualified status of each heating zone in real time. For areas with insufficient heating, the system automatically generates an optimized surplus heat allocation strategy, proportionally allocating excess heat from qualified areas to insufficient areas. This achieves efficient dynamic regulation of thermal energy resources and balanced heating across multiple zones, improving overall energy efficiency.

[0082] This invention overcomes the traditional practice of neglecting losses in heat transmission paths by incorporating a pipeline loss acquisition module that collects parameters such as the length, outer diameter, and thermal conductivity of the insulation layer between the heat source and each monitoring area. This module accurately assesses heat loss during transmission, making the prediction model more relevant to field conditions and enhancing the practical value of the prediction results. The system utilizes artificial intelligence models such as convolutional neural networks to learn nonlinear correlations between historical data samples and construct a correlation prediction model between waste heat and heating area. This system possesses adaptive learning capabilities and can dynamically optimize prediction performance based on different buildings, operating conditions, and environmental conditions. It is suitable for a variety of industrial applications and possesses strong scalability and versatility.

[0083] Through refined management and allocation of waste heat from air compressors, the utilization rate of waste heat can be improved, energy waste and additional heat emissions caused by redundant heating can be avoided, and dependence on auxiliary heating equipment such as electric heating can be reduced, which helps companies reduce operating costs.

[0084] The present invention also comprehensively considers factors such as pipe length, outer diameter, insulation material, hot water delivery temperature, external ambient temperature and transmission time through the loss analysis unit, and constructs a heat loss model under various insulation materials. It can perform detailed calculations on the heat loss of insulation pipes of different materials during the heating process, thereby providing a quantitative reference for the optimization of heat transmission paths and the selection of insulation materials, which has significant engineering application value and economic significance. By calculating the heat load of the i-th heating area and the pipe heat loss coefficient of the i-th heating area , and the air compressor thermal energy conversion coefficient η1 constructed a "heat source-heat demand-heat loss" three-in-one modeling architecture, which helps to improve the thermal efficiency prediction accuracy and dynamic adaptability of the entire heating system, provide accurate modeling and decision-making support for the intelligent utilization of waste heat, and significantly improve energy-saving effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Figure 1 This is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0086] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0087] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0088] Example 1:

[0089] See also Figure 1 , the present invention provides a technical solution:

[0090] An air compressor waste heat recovery heating area prediction system, comprising:

[0091] The operation data acquisition module is used to collect the air compressor electrical input power per unit time during the operation of the air compressor in real time , water flow , air compressor outlet water temperature and the inlet water temperature , construct the air compressor operating condition data group;

[0092] Building environment parameter collection module, used to collect the building area of ​​the i-th heating area , heat capacity , total thermal resistance , thermal insulation grade coefficient , Heating type coefficient , the difference between indoor temperature and outside temperature Summarize and form a building heat load parameter group;

[0093] Pipeline loss collection module, used to collect the length of the pipeline between the i-th detection area and the heat source output , pipe outer diameter D and pipe insulation layer thermal conductivity coefficient , forming a heat loss assessment data group;

[0094] The performance prediction analysis module is used to construct and train a waste heat utilization-heating area correlation prediction model based on the air compressor operating condition data group, heat loss assessment data group, building heat load parameter group and heat loss assessment data group using a convolutional neural network to obtain: the heat load of the i-th heating area , the air compressor heat energy conversion coefficient η1 and the pipe heat loss coefficient of the i-th heating area , and based on the heat load of the i-th heating area , the air compressor heat energy conversion coefficient η1 and the pipe heat loss coefficient of the i-th heating area , comprehensive analysis and prediction to obtain: the effective heating area of ​​the i-th heating area ;

[0095] The strategy output module is used to preset the heating coverage threshold X and calculate the effective heating area of ​​the i-th heating zone. The result is compared with the heating coverage threshold X to identify whether the heating is qualified. If there is insufficient heating, a waste heat allocation optimization strategy is generated to allocate the redundant waste heat ratio of all qualified areas to the areas with insufficient heating to achieve heating balance.

[0096] In this embodiment, the system constructs an operating condition data group including air compressor power input, water flow, inlet and outlet water temperature, etc., and combines the building heat load parameters and pipeline heat loss assessment data of each heating area to achieve accurate modeling of air compressor waste heat utilization efficiency and heating area, effectively avoiding the heating area deviation problem caused by empirical methods or single-factor estimation in traditional systems, and improving the scientificity and accuracy of heating planning.

[0097] By setting a heating coverage threshold X and combining it with the predicted effective heating area, the system can identify the qualified status of each heating zone in real time. For areas with insufficient heating, the system automatically generates an optimized surplus heat allocation strategy, proportionally allocating excess heat from qualified areas to insufficient areas. This achieves efficient dynamic regulation of thermal energy resources and balanced heating across multiple zones, improving overall energy efficiency.

[0098] This invention overcomes the traditional practice of neglecting losses in heat transmission paths by incorporating a pipeline loss acquisition module that collects parameters such as the length, outer diameter, and thermal conductivity of the insulation layer between the heat source and each monitoring area. This module accurately assesses heat loss during transmission, making the prediction model more relevant to field conditions and enhancing the practical value of the prediction results. The system utilizes artificial intelligence models such as convolutional neural networks to learn nonlinear correlations between historical data samples and construct a correlation prediction model between waste heat and heating area. This system possesses adaptive learning capabilities and can dynamically optimize prediction performance based on different buildings, operating conditions, and environmental conditions. It is suitable for a variety of industrial applications and possesses strong scalability and versatility.

[0099] Through refined management and allocation of waste heat from air compressors, the utilization rate of waste heat can be improved, energy waste and additional heat emissions caused by redundant heating can be avoided, and dependence on auxiliary heating equipment such as electric heating can be reduced. This will help companies reduce operating costs and promote green and energy-saving transformation.

[0100] Example 2: This example is explained in Example 1. Please refer to Figure 1 ,Specifically, the operation data acquisition module includes a 3D model acquisition unit and an ,air compressor operation data acquisition unit;

[0101] The 3D model acquisition unit is used to collect the position data of the air compressor in the workshop in real time using GPS and LiDAR, and convert the coordinate information of the air compressor into 3D coordinate data to form an air compressor position data set;

[0102] It is also used to collect 3D elevation data of the workshop based on LiDAR, drone aerial photography or architectural design drawings, build a 3D model of the workshop, subdivide the interior of the workshop, identify the spatial layout and relative position of each area, collect the position data of the air compressor in the workshop in real time, convert the coordinate information of the air compressor into 3D coordinate data, and mark it in the 3D model of the workshop. Different functional areas are identified according to the 3D model of the workshop, divided into the i-th heating area, and marked in the 3D model of the workshop as: , to Indicates the heating zones 1 to 3 The status mark of each heating area at the sd time point; the heating areas include production workshops, office buildings and storage areas;

[0103] The air compressor operation data acquisition unit is used to collect the air compressor operation data using an electric energy meter, an electromagnetic flow meter and a thermal resistance temperature sensor, and establish an air compressor operation condition data group;

[0104] The air compressor operating condition data group includes: air compressor electrical energy input power per unit time , water flow , air compressor outlet water temperature and the inlet water temperature .

[0105] In this embodiment, GPS and LiDAR technology are used to collect real-time spatial location data of air compressors within the workshop and convert it into standardized three-dimensional coordinates, enabling precise marking of the compressor heat source within the three-dimensional workshop model. This effectively avoids the large positioning errors and inappropriate heat transfer path design issues of traditional two-dimensional drawings, providing a highly accurate spatial foundation for subsequent heat energy transfer and zoning. Reconstructing three-dimensional workshop elevation information using LiDAR, drone aerial photography, or architectural drawing data not only accurately reflects the spatial boundaries and distribution of different functional areas such as production workshops, offices, and storage areas, but also automatically divides the i-th heating zone based on architectural spatial details and dynamically labels the spatial status of each heating zone at different time points (sd), providing strong support for regional parameter matching in subsequent heating prediction models. Because different areas (such as high-bay factories, low-rise warehouses, and enclosed offices) vary significantly in their response to heat loads, traditional methods often fail to account for the impact of these spatial differences. The three-dimensional model acquisition unit can accurately identify regional morphology and positional relationships at the spatial level, providing spatial input parameters for predictive analysis, thereby enhancing the practical adaptability and accuracy of waste heat heating models. The air compressor operation data acquisition unit integrates an electric energy meter, an electromagnetic flow meter, and a thermistor temperature sensor to accurately collect key thermal output indicators such as electrical input power, water flow, outlet water temperature, and inlet water temperature per unit time, thereby constructing an air compressor operation condition data set that truly reflects thermal energy conversion efficiency and dynamic fluctuation characteristics, providing reliable heat source benchmark data for the prediction model.

[0106] Example 3: This example is explained in Example 1. Please refer to Figure 1 Specifically, the building environment parameter acquisition module includes a building area unit and a thermal insulation grade coefficient analysis unit:

[0107] Building area unit, used to extract the length and width of the facade of the i-th heating area, and multiply them to obtain the building area of ​​the i-th heating area ;

[0108] The thermal insulation grade coefficient analysis unit is used to obtain thermal property data of different building materials and structures, query the database and combine it with the collected real-time data to calculate the thermal resistance and heat capacity of each area. The heat capacity reflects the heat storage capacity of the area and can dynamically respond to changes in external temperature. Specifically, it includes:

[0109] Collect the material density and volume of the i-th heating area and calculate the heat capacity of the i-th heating area :

[0110] ;

[0111] in, is the material density, c is the specific heat capacity in J / kg·K; V is the volume;

[0112] Based on the thermal conductivity of the i-th heating area, the total thermal resistance of the i-th heating area is calculated. , the specific steps include:

[0113] S11. The calculation of total thermal resistance depends on the different structural layers of the heating area, including the thermal resistance of walls, windows, roofs and floors. The thermal resistance of the components of the jth layer is calculated by counting several structural layers (j=1,2,…,m) of each heating area. Calculated by the following formula:

[0114] ;

[0115] in, is the thickness of the jth layer, Represents the thermal conductivity of the jth layer; collects the thickness and thermal conductivity of walls, windows, roofs, and floors layer by layer, first calculating the thermal resistance of a single layer, and supports differentiated modeling of the thermal conductivity of heterogeneous structures (such as insulation layer + concrete + coating);

[0116] S12. Calculate the total thermal resistance of the i-th heating area :

[0117] ; m is the number of all building material layers in the heating area;

[0118] S121, total thermal resistance of the i-th heating zone It can also be calculated in the following way:

[0119] The calculation of the total thermal resistance depends on the different structural layers of the heating area, including the thermal resistance of the walls, windows, roofs and floors. Several structural layers (j=1,2,…,m) are counted for each heating area. When the wall is composed of multiple layers of different materials, assuming that each heating area includes the wall thermal resistance, roof thermal resistance, window thermal resistance and floor thermal resistance, then by calculating the thickness and thermal conductivity of the material, the wall thermal resistance of the i-th heating area is Calculated by the following formula:

[0120]

[0121] in, Indicates the number of layers of different materials in the wall, Indicates the The thickness of the wall layer, Indicates the Thermal conductivity of the wall layer, in W / m·°C. The thermal conductivity of different materials (e.g., masonry, concrete, insulation) varies greatly.

[0122] S122, window thermal resistance of the i-th heating zone Calculated by the following formula:

[0123]

[0124] in, Indicates the thickness of the glass, represents the thermal conductivity of glass, Indicates the thickness of the window frame, represents the thermal conductivity of the window frame;

[0125] S122, roof thermal resistance of the i-th heating zone Calculated by the following formula:

[0126]

[0127] in, Indicates the number of roof middle layers, Indicates the Thickness of the roof middle layer, Indicates the Thermal conductivity of the roof mid-layer;

[0128] S123, floor thermal resistance of the i-th heating area Calculated by the following formula:

[0129]

[0130] in, Indicates the number of floors in the middle, Indicates the The thickness of the middle layer of the floor, Indicates the Thermal conductivity of the middle layer of the floor;

[0131] S124. Calculate the total thermal resistance of the i-th heating area :

[0132] ;

[0133] The total thermal resistance is calculated by calculating the thermal resistance of walls, windows, roofs, and floors separately and then summing them up. For old buildings, the root cause of the problem can be determined to be "high heat loss from windows" or "fast heat transfer from floors." This provides practical recommendations for energy-saving renovations (such as prioritizing the replacement of low-thermal-resistance components).

[0134] S13, based on the total thermal resistance of the i-th heating area , calculate and obtain the insulation grade coefficient ;

[0135] .

[0136] Based on the total thermal resistance of the i-th heating area , calculate and obtain the insulation grade coefficient , which is converted into a standardized scoring index to adapt to the waste heat distribution strategy of different regions; a thermal insulation quality grading system can be established to achieve zoned heating regulation; and basic indicators can be provided for regional thermal energy evaluation and economic accounting.

[0137] The building environment parameter acquisition module also includes a heating type coefficient acquisition unit and a heating target temperature acquisition unit;

[0138] The heating type coefficient collection unit is used to collect the heating type of the i-th heating area. The heating types include hot gas heating and hot water heating. When the heating type is hot gas heating, the number value is 001. Hot water is used for heat conduction through floor heating pipes and radiators. The heating type coefficient is When the heating type is hot water heating, the number value is 002, and hot water is used to send hot air through the hot air blower and air conditioner. The heat is mainly transferred in the form of convection. The heating type coefficient is is 1.2; identify the heating method of the i-th area and assign a coefficient (1 for floor heating / radiator and 1.2 for hot air convection); compare the unit heat consumption differences under different heating methods to achieve accurate energy efficiency analysis;

[0139] Heating target temperature acquisition unit, used to use the temperature sensor to obtain the difference between the indoor temperature and the outside temperature of the i-th heating area ,

[0140] ;

[0141] in, is the indoor temperature of the i-th heating area, is the outside temperature;

[0142] The building area of ​​the i-th heating area , heat capacity , total thermal resistance , thermal insulation grade coefficient , Heating type coefficient , the difference between indoor temperature and outside temperature Summarize and establish building heat load parameter groups. This accurately reflects the actual heat load demand of each area (larger temperature differences indicate higher loads), avoids insufficient heating or excessive heating waste due to inconsistency in ambient temperature differences, and helps dynamically adjust waste heat distribution strategies to achieve real-time temperature control targets.

[0143] Example 4: This example is explained in Example 1. Please refer to Figure 1 ,Specifically, the performance prediction and analysis module includes a model building ,unit;

[0144] a model building unit, configured to use a convolutional neural network to construct an initial convolutional neural network model, and train and test the initial convolutional neural network model using an air compressor operating condition data group, a heat loss assessment data group, and a building heat load parameter group, and use the trained initial convolutional neural network model as a waste heat utilization-heating area correlation prediction model, and simultaneously use the intermediate layer output of the equipment operating status model as a feature vector to identify feature information, and train and test the waste heat utilization-heating area correlation prediction model using the acquired feature information, and use the trained waste heat utilization-heating area correlation prediction model as data for operation prediction;

[0145] The specific steps are to build a CNN initial model, take the air compressor operating condition data group, heat loss assessment data group and building heat load parameter group as input values ​​of the CNN initial model, and perform structured data feature extraction;

[0146] Retrain the mean square error of the initial CNN model to measure the mean square error and the deviation between the area and the actual area; supervised training is performed using the Adam size and RMSProp optimizer;

[0147] Extract the feature vectors from the middle layer of the equipment operation status model and use them as the feature representation of the air compressor operation, including the Flatten layer before the fully connected layer. This is then used as an additional channel for the CNN input or as a parallel input for the Dense layer in the waste heat utilization-heating area correlation prediction model. A two-branch network is constructed, with the equipment status peak and building heat load branches, and feature fusion is performed in the middle.

[0148] The air compressor operating condition data set, heat loss assessment data set, and building heat load parameter set were classified into an 80% training set, a 10% test set, and a 10% validation set. Training was iterated until the loss function value on the validation set decreased repeatedly, stabilized, or reached a preset threshold. The fusion input of multi-source heterogeneous data enabled the model to more accurately capture the relationship between the air compressor's waste heat heating capacity and the actual building needs. By extracting the intermediate layer features of the equipment operating status model, the model's ability to express the dynamics of air compressor operation was significantly enhanced.

[0149] Intermediate layer features (such as the Flatten layer output) retain the nonlinear variation characteristics of equipment operation at different stages, helping to accurately characterize waste heat release capacity. The dual-branch structure (equipment state peak + building heat load branch) can learn the high-dimensional features of the two subsystems separately and then fuse the features to effectively avoid information interference. The joint representation after branch fusion can more comprehensively reflect the nonlinear mapping relationship between waste heat utilization potential and actual heating load, improving prediction capabilities. The MSE loss function can quantify the error between the predicted area and the actual heating area, which is conducive to continuously optimizing model accuracy. The combination of the Adam and RMSProp optimizers takes into account the adaptability and convergence speed of learning rate adjustment, which can accelerate model training and reduce the risk of falling into local optimality.

[0150] The model building unit includes a building heat load analysis unit, an air compressor heat energy conversion unit, and a loss analysis unit;

[0151] Building heat load analysis unit is used to extract the building area of ​​the i-th heating zone in the building heat load parameter group based on the building heat load parameter group. , heat capacity , total thermal resistance , thermal insulation grade coefficient , Heating type coefficient , the difference between indoor temperature and outside temperature , the heat load of the i-th heating area is calculated by the following formula :

[0152] ;

[0153] Among them, the building area The larger the temperature difference, the greater the required heat load, so the building area is a basic parameter of the heat load; the greater the temperature difference, the more heat is required inside the building; for example, if the outside temperature is very low, then more heat needs to be provided to maintain the indoor temperature; the worse and smaller the insulation level, the greater the heat loss of the building, and more heat is needed to maintain the indoor temperature; the thermal efficiency of the heating type and the thermal resistance of the building together determine the amount of heat required for heating; efficient heating systems (such as floor heating) require less heat to reach the target temperature; the greater the thermal capacity of the building, means that it can store more heat, so less heat is required for heating.

[0154] The air compressor heat energy conversion unit is used to calculate the air compressor heat energy conversion coefficient η1 based on the air compressor operating condition data group and using the following formula:

[0155]

[0156]

[0157] in, Indicates the heat recovered by the air compressor per unit time. Indicates the electrical input power of the air compressor per unit time; represents the specific heat capacity of water, which is set to 4.18 kJ / (kg·K), represents the density of water, set to approximately 1000 kg / m³, Indicates water flow, and Respectively represent the temperature values ​​of the air compressor water outlet and water inlet;

[0158] The loss analysis unit is used to calculate the pipe heat loss coefficient of the i-th heating area based on the heat loss evaluation data group using the following formula :

[0159]

[0160] in, represents the thermal conductivity coefficient of the pipe insulation layer in the i-th heating area; represents the circumference of a circle and is set to 3.1416; D represents the outer diameter of the pipe. Indicates the length of the pipe from the heat source output to the i-th heating area, It is expressed as the heat transfer surface area of ​​the pipe in the i-th heating zone;

[0161] Indicates the temperature inside the pipe during the hot water transportation process. is the outside temperature, Indicates the transmission time;

[0162] When the pipe insulation layer is rock wool, the thermal conductivity coefficient of the pipe insulation layer is 0.035-0.045W / m²·K;

[0163] When the pipe insulation layer is glass wool, the thermal conductivity coefficient of the pipe insulation layer is 0.033-0.040W / m²·K;

[0164] When the pipe insulation layer is polyurethane foam, the thermal conductivity coefficient of the pipe insulation layer is 0.020-0.030W / m²·K;

[0165] When the pipe insulation layer is polyethylene foam, the thermal conductivity of the pipe insulation layer is 0.035-0.045W / m²·K;

[0166] When the pipe insulation layer is foam glass, the thermal conductivity coefficient of the pipe insulation layer is 0.038-0.050W / m²·K;

[0167] When the pipeline insulation layer is a vacuum insulation panel, the thermal conductivity coefficient of the pipeline insulation layer is 0.005-0.008W / m²·K.

[0168] In this embodiment, the building heat load analysis unit constructs the heat load of the i-th heating area by introducing multiple influencing parameters such as the building area of ​​the heating area, heat capacity, total thermal resistance, insulation grade coefficient, heating type coefficient, temperature difference, etc. , which can more accurately reflect the heat demand characteristics of different building structures and heating methods. In particular, the introduction of the heat capacity parameter allows the model to fully consider the regulatory effect of building thermal inertia on heating power, improving the physical rationality and application accuracy of the prediction.

[0169] The air compressor thermal energy conversion unit clarifies the efficiency of the air compressor in converting electrical energy into thermal energy by calculating the air compressor thermal energy conversion coefficient η1. Combined with physical parameters such as the air compressor inlet and outlet water temperature, water flow rate, specific heat capacity and density, it realizes a quantitative assessment of the air compressor's waste heat release capacity, thereby improving the scientific nature and pertinence of the waste heat heating system modeling.

[0170] The loss analysis unit comprehensively considers factors such as pipeline length, outer diameter, insulation layer material, hot water transmission temperature, external ambient temperature and transmission time, and constructs a heat loss model under various insulation materials. It can perform detailed calculations on the heat loss of insulated pipes of different materials during the heating process, thereby providing a quantitative reference for the optimization of heat transmission paths and the selection of insulation materials, and has significant engineering application value and economic significance.

[0171] By calculating the heat load of the i-th heating zone and the pipe heat loss coefficient of the i-th heating area , and the air compressor thermal energy conversion coefficient η1 constructed a "heat source-heat demand-heat loss" three-in-one modeling architecture, which helps to improve the thermal efficiency prediction accuracy and dynamic adaptability of the entire heating system, and provides accurate modeling and decision-making support for the intelligent utilization of waste heat. It has significant energy-saving effects, strong adaptability, and good practical promotion and application value.

[0172] Example 5: This example is explained in Example 4. Please refer to Figure 1 Specifically, the performance prediction analysis module further includes a prediction analysis unit, which is used to calculate the heat load of the i-th heating area based on the heat load of the i-th heating area. and the pipe heat loss coefficient of the i-th heating area , and the air compressor heat energy conversion coefficient η1, comprehensive analysis to obtain the prediction to obtain the effective heating area of ​​the i-th heating area , the specific steps are:

[0173] S21. The available waste heat generated by the air compressor should be equal to the sum of the heat loads required by all heated areas, and the operating power of the air compressor should be extracted. , the heat conversion coefficient η1 of the air compressor and the operating time t, calculate the waste heat that can be recovered by the air compressor during the operating time t:

[0174] ;

[0175] S22, Pipeline heat loss coefficient based on the i-th heating area , it is necessary to calculate the effective heat that can actually be used for heating and obtain the effective heat of the i-th heating area ;

[0176] ;

[0177] in, represents the proportion of waste heat allocated to the i-th heating zone;

[0178] S23, based on the heat load of the i-th heating area and the area of ​​the i-th heating zone , calculate the heat load per unit area of ​​the i-th heating area :

[0179]

[0180] S24, effective heat of the i-th heating area obtained according to S22 and the heat load per unit area of ​​the i-th heating zone , predict and obtain the effective heating area of ​​the i-th heating area :

[0181] .

[0182] In this embodiment, the prediction and analysis unit calculates the total amount of waste heat recoverable by the air compressor per unit time by incorporating the air compressor operating power, heat conversion coefficient η1, and operating time t. This allows for a quantitative assessment of waste heat resource availability, providing a clear data foundation for subsequent heat allocation and heating capacity analysis. By calculating the pipeline heat loss coefficient for each heating zone and factoring this loss into the regional heat distribution process, unusable heat energy during transmission is effectively eliminated, improving the accuracy of the prediction results to actual heating capacity and making the prediction model more reliable for engineering applications. By dividing the heat load by the regional area to calculate the heat load per unit area, a standardized mapping between heat demand and regional area is established, enabling the model to be more adaptable and portable to accommodate differences in building structures and demand across different heating zones. After obtaining the regional effective heat, the effective area available for heating is inferred from the heat load per unit area. This allows the system to clearly identify the "effective heating capacity ceiling" of each heating zone under current heat source conditions, providing intelligent support for subsequent resource allocation, energy efficiency assessment, and system expansion.

[0183] Example 6: This example is explained in Example 1. Please refer to Figure 1 ,Specifically, the strategy output module includes an evaluation unit and a ,strategy unit;

[0184] The evaluation unit is used to preset the heating coverage threshold X and calculate the effective heating area of ​​the i-th heating zone Compare with the heating coverage threshold X to identify whether the heating is qualified, including:

[0185] When the effective heating area of ​​the i-th heating zone < Heating coverage threshold X × 0.75; the area is judged to be severely insufficient in heating, marked as a first-order insufficient heating area, and the first warning instruction is issued;

[0186] When the heating coverage threshold X×0.75≤the effective heating area of ​​the i-th heating zone ≤ heating coverage threshold X, it is judged as a heating insufficient area and marked as a second-order heating insufficient area. The degree of the second-order heating insufficient area is lower than that of the first-order heating insufficient area, and a second warning instruction is issued;

[0187] When the effective heating area of ​​the i-th heating zone >Heating coverage threshold X, judged as a heating qualified area.

[0188] The strategy unit is configured to generate a waste heat allocation optimization strategy based on the first warning instruction and the second warning instruction, including:

[0189] First, we count the qualified areas, the set S of qualified areas that meet the conditions, namely For the i-th qualified area, the redundant waste heat ratio of the i-th qualified area is calculated by the following formula: ,for:

[0190]

[0191] in, The ratio of the area of ​​the heating zone that exceeds the heating coverage threshold X to the total area, that is, the ratio of the redundant heating area; and multiplied by the ratio of the excess heat allocated to the i-th heating zone, the ratio of the redundant heat that can be released by the heating zone is obtained;

[0192] Calculate the sum of redundant warmups for all eligible regions :

[0193]

[0194] The sum of the redundant waste heat of all qualified areas The following proportions are allocated to the heating-deficient areas, including:

[0195] The proportion allocated to the first-level heating shortage area is 60%-70%;

[0196] The proportion allocated to the second-order heating insufficient areas is 20%-30%;

[0197] Assume that the first-order insufficient heating area is S1, and the second-order insufficient heating area ratio is S2, that is:

[0198] ;

[0199] ;

[0200] If there are still first-order heating shortage areas and second-order heating shortage areas, the remaining gap area is calculated for each unqualified area, and the percentage of redundant waste heat ratio is redistributed to the remaining gap area;

[0201] If there is a remaining proportion of waste heat that is not distributed (i.e. 1-( + )>0), or if there are still unqualified areas after preliminary allocation, identify the first-order and second-order insufficient heating areas that still do not meet the threshold X, and record them as S1' and S2' respectively.

[0202] Calculate the remaining gap area for each insufficient area :

[0203] , ;in, Indicates the effective heating area of ​​the area after the initial allocation. Recalculate the proportion of surplus heat that remains redundant after the initial allocation in all qualified areas to form the total amount of secondary redundant surplus heat. If the secondary redundancy is insufficient, the following supplementary measures need to be initiated, including:

[0204] Set the weights for the secondary distribution, for example, the first-order insufficient area accounts for 80%-90%, and the second-order insufficient area accounts for 10%-20%; calculate the allocation ratio of each insufficient area and distribute it according to the size of the remaining gap area:

[0205] If the redundant waste heat in qualified areas cannot meet the needs of insufficient areas, the system should activate external heat sources or increase the overall waste heat supply to ensure that all areas meet heating standards. Specifically, additional air compressors should be added in parallel to the original system to linearly expand the total amount of waste heat recovery. The accumulated available waste heat per unit time can be increased by adjusting the air compressor operating shifts (for example, extending operation from daytime to nighttime). Heat storage tanks made of high-specific-heat materials can be used to pre-store some heat during peak air compressor operation for peak load shaving or emergency replenishment. The heat storage materials can be water, rock salt, or phase-change materials (such as paraffin or organic salts).

[0206] It should be noted that all calculation formulas in this application document utilize, including but not limited to, regression analysis within machine learning algorithms to deeply analyze the collected parameters and identify their natural trends and interrelationships. Professional software, such as Python's Scikit-learn library or the R language, is used to automatically generate mathematical models that match the data. Model performance is then objectively evaluated through methods such as cross-validation, combined with continuous feedback and optimization to ensure that the created formulas truly reflect the inherent laws of the data, thereby guaranteeing their validity and accuracy, and ensuring that the calculation process complies with the constraints of natural laws rather than being based on artificially set rules.

[0207] The technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0208] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0209] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0210] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An air compressor waste heat recovery heating area prediction system, characterized in that: include: The operation data acquisition module is used to collect the air compressor electrical energy input power per unit time during the operation of the air compressor in real time , water flow , air compressor outlet water temperature and the inlet water temperature , construct the air compressor operating condition data group; Building environment parameter collection module, used to collect the building area of ​​the i-th heating area , heat capacity , total thermal resistance , thermal insulation grade coefficient , Heating type coefficient , the difference between indoor temperature and outside temperature Summarize and form a building heat load parameter group; Pipeline loss collection module, used to collect the length of the pipeline between the i-th detection area and the heat source output , pipe outer diameter D and pipe insulation layer thermal conductivity coefficient , forming a heat loss assessment data group; The performance prediction analysis module is used to construct and train a waste heat utilization-heating area correlation prediction model based on the air compressor operating condition data group, heat loss assessment data group, building heat load parameter group and heat loss assessment data group using a convolutional neural network to obtain: the heat load of the i-th heating area , the air compressor heat energy conversion coefficient η1 and the pipe heat loss coefficient of the i-th heating area , and based on the heat load of the i-th heating area , the air compressor heat energy conversion coefficient η1 and the pipe heat loss coefficient of the i-th heating area , comprehensive analysis and prediction to obtain: the effective heating area of ​​the i-th heating area ; The strategy output module is used to preset the heating coverage threshold X and calculate the effective heating area of ​​the i-th heating zone. The heating coverage threshold X is compared to identify whether the heating is qualified. If there is insufficient heating, a waste heat allocation optimization strategy is generated to allocate the redundant waste heat ratio of all qualified areas to the areas with insufficient heating to achieve heating balance.

2. The air compressor waste heat recovery heating area prediction system according to claim 1 is characterized by: The operation data acquisition module includes a three-dimensional model acquisition unit and an air compressor operation data acquisition unit; The three-dimensional model acquisition unit is used to collect the position data of the air compressor in the workshop in real time using GPS and LiDAR, and convert the coordinate information of the air compressor into three-dimensional coordinate data to form an air compressor position data set; It is also used to collect 3D elevation data of the workshop based on LiDAR, drone aerial photography or architectural design drawings, build a 3D model of the workshop, subdivide the interior of the workshop, identify the spatial layout and relative position of each area, collect the position data of the air compressor in the workshop in real time, convert the coordinate information of the air compressor into 3D coordinate data, and mark it in the 3D model of the workshop. Different functional areas are identified according to the 3D model of the workshop, divided into the i-th heating area, and marked in the 3D model of the workshop as: , to Indicates the heating zones 1 to 3 The status mark of each heating area at the sd time point; the heating areas include production workshops, office buildings and storage areas; The air compressor operation data acquisition unit is used to collect the operation data of the air compressor using an electric energy meter, an electromagnetic flow meter and a thermal resistance temperature sensor, and establish an air compressor operation condition data group; The air compressor operating condition data group includes: air compressor power input per unit time , water flow , air compressor outlet water temperature and the inlet water temperature .

3. The air compressor waste heat recovery heating area prediction system according to claim 2 is characterized by: The building environment parameter acquisition module includes a building area unit and a thermal insulation grade coefficient analysis unit: The building area unit is used to extract the length and width of the facade of the i-th heating area, and multiply them to obtain the building area of ​​the i-th heating area. ; The thermal insulation grade coefficient analysis unit is used to obtain thermal property data of different building materials and structures, query the database and combine it with the collected real-time data to calculate the thermal resistance and heat capacity of each area, specifically including: Collect the material density and volume of the i-th heating area and calculate the heat capacity of the i-th heating area : ； in, is the material density, c is the specific heat capacity in J / kg·K; V is the volume; Based on the thermal conductivity of the i-th heating area, the total thermal resistance of the i-th heating area is calculated. , the specific steps include: S11. The calculation of total thermal resistance depends on the different structural layers of the heating area, including the thermal resistance of walls, windows, roofs and floors. The thermal resistance of the components of the jth layer is calculated by counting several structural layers (j=1,2,…,m) of each heating area. Calculated by the following formula: ； in, is the thickness of the jth layer, represents the thermal conductivity of the jth layer; S12. Calculate the total thermal resistance of the i-th heating area : ; m is the number of all building material layers in the heating area; S13, based on the total thermal resistance of the i-th heating area , calculate and obtain the insulation grade coefficient ; 。 4. The air compressor waste heat recovery heating area prediction system according to claim 3 is characterized by: The building environment parameter acquisition module also includes a heating type coefficient acquisition unit and a heating target temperature acquisition unit; The heating type coefficient collection unit is used to collect the heating type of the i-th heating area. The heating types include hot gas heating and hot water heating. When the heating type is hot gas heating, the number value is 001. Hot water is used for heat conduction through floor heating pipes and radiators. The heating type coefficient is When the heating type is hot water heating, the number value is 002, and hot water is used to send hot air through the hot air blower and air conditioner. The heat is mainly transferred in the form of convection. The heating type coefficient is is 1.2; The heating target temperature acquisition unit is used to use a temperature sensor to obtain the difference between the indoor temperature and the outside temperature of the i-th heating area. , ； in, is the indoor temperature of the i-th heating area, is the outside temperature; The building area of ​​the i-th heating area , heat capacity , total thermal resistance , thermal insulation grade coefficient , Heating type coefficient , the difference between indoor temperature and outside temperature Summarize and establish a building heat load parameter group.

5. The air compressor waste heat recovery heating area prediction system according to claim 4 is characterized in that: The performance prediction and analysis module includes a model building unit; The model building unit is used to use a convolutional neural network to construct an initial convolutional neural network model, and train and test the initial convolutional neural network model using an air compressor operating condition data group, a heat loss assessment data group, and a building heat load parameter group, and use the trained initial convolutional neural network model as a waste heat utilization-heating area correlation prediction model. At the same time, the intermediate layer output of the equipment operation status model is used as a feature vector to identify feature information, and the waste heat utilization-heating area correlation prediction model is trained and tested through the acquired feature information, and the trained waste heat utilization-heating area correlation prediction model is used as data operation prediction.

6. The air compressor waste heat recovery heating area prediction system according to claim 5, characterized in that: The model building unit includes a building heat load analysis unit, an air compressor heat energy conversion unit and a loss analysis unit; The building heat load analysis unit is used to extract the building area of ​​the i-th heating area in the building heat load parameter group based on the building heat load parameter group. , heat capacity , total thermal resistance , thermal insulation grade coefficient , Heating type coefficient The difference between indoor temperature and outside temperature , calculate the heat load of the i-th heating area : 。 7. The air compressor waste heat recovery heating area prediction system according to claim 6, characterized in that: The air compressor heat energy conversion unit is used to calculate the air compressor heat energy conversion coefficient η1 based on the air compressor operating condition data group and using the following formula: in, Indicates the heat recovered by the air compressor per unit time. Indicates the electrical input power of the air compressor per unit time; represents the specific heat capacity of water, which is set to 4.18 kJ / (kg·K), represents the density of water, set to approximately 1000 kg / m³, Indicates water flow, and Respectively represent the temperature values ​​of the air compressor water outlet and water inlet; The loss analysis unit is used to calculate the pipeline heat loss coefficient of the i-th heating area based on the heat loss evaluation data group using the following formula : in, represents the thermal conductivity coefficient of the pipe insulation layer in the i-th heating area; represents the circumference of a circle and is set to 3.1416; D represents the outer diameter of the pipe. Indicates the length of the pipe from the heat source output to the i-th heating area, It is expressed as the heat transfer surface area of ​​the pipe in the i-th heating zone; Indicates the temperature inside the pipe during the hot water transportation process. is the outside temperature, Indicates the transmission time; When the pipe insulation layer is rock wool, the thermal conductivity of the pipe insulation layer is 0.035-0.045W / m²·K; When the pipe insulation layer is glass wool, the thermal conductivity coefficient of the pipe insulation layer is 0.033-0.040W / m²·K; When the pipe insulation layer is polyurethane foam, the thermal conductivity coefficient of the pipe insulation layer is 0.020-0.030W / m²·K; When the pipe insulation layer is polyethylene foam, the thermal conductivity of the pipe insulation layer is 0.035-0.045W / m²·K; When the pipe insulation layer is foam glass, the thermal conductivity coefficient of the pipe insulation layer is 0.038-0.050W / m²·K; When the pipeline insulation layer is a vacuum insulation panel, the thermal conductivity coefficient of the pipeline insulation layer is 0.005-0.008W / m²·K.

8. The air compressor waste heat recovery heating area prediction system according to claim 7, characterized in that: The performance prediction and analysis module further includes a prediction and analysis unit, which is used to calculate the heat load of the i-th heating area based on the heat load of the i-th heating area. and the pipe heat loss coefficient of the i-th heating area , and the air compressor heat energy conversion coefficient η1, comprehensive analysis to obtain the prediction to obtain the effective heating area of ​​the i-th heating area , the specific steps are: S21. The available waste heat generated by the air compressor should be equal to the sum of the heat loads required by all heated areas, and the operating power of the air compressor should be extracted. , the heat conversion coefficient η1 of the air compressor and the operating time t, calculate the waste heat that can be recovered by the air compressor during the operating time t: ； S22, Pipeline heat loss coefficient based on the i-th heating area , it is necessary to calculate the effective heat that can actually be used for heating and obtain the effective heat of the i-th heating area ; ； in, represents the proportion of waste heat allocated to the i-th heating zone; S23, based on the heat load of the i-th heating area and the area of ​​the i-th heating zone , calculate the heat load per unit area of ​​the i-th heating area : S24, effective heat of the i-th heating area obtained according to S22 and the heat load per unit area of ​​the i-th heating zone , predict and obtain the effective heating area of ​​the i-th heating area : 。 9. The air compressor waste heat recovery heating area prediction system according to claim 8, characterized in that: The strategy output module includes an evaluation unit and a strategy unit; The evaluation unit is used to preset the heating coverage threshold X and calculate the effective heating area of ​​the i-th heating zone. Compare with the heating coverage threshold X to identify whether the heating is qualified, including: When the effective heating area of ​​the i-th heating zone < Heating coverage threshold X × 0.75; the area is judged to be severely insufficient in heating, marked as a first-order insufficient heating area, and the first warning instruction is issued; When the heating coverage threshold X×0.75≤the effective heating area of ​​the i-th heating zone ≤ heating coverage threshold X, it is judged as a heating insufficient area and marked as a second-order heating insufficient area. The degree of the second-order heating insufficient area is lower than that of the first-order heating insufficient area, and a second warning instruction is issued; When the effective heating area of ​​the i-th heating zone >Heating coverage threshold X, judged as a heating qualified area.

10. The air compressor waste heat recovery heating area prediction system according to claim 9, characterized in that: The strategy unit is configured to generate a waste heat allocation optimization strategy based on receiving the first warning instruction and the second warning instruction, including: First, count the qualified areas and calculate the redundant heat ratio of the i-th qualified area ,for: in, The ratio of the area of ​​the heating zone that exceeds the heating coverage threshold X to the total area, that is, the ratio of the redundant heating area; and multiplied by the ratio of the excess heat allocated to the i-th heating zone, the ratio of the redundant heat that can be released by the heating zone is obtained; Allocate 60-70% of the redundant heat ratio of all qualified areas to the first-level heating deficiency areas; Allocate 20-30% of the redundant heat ratio of all qualified areas to the secondary heating deficiency areas; If there are still first-order heating shortage areas and second-order heating shortage areas, the remaining gap area is calculated for each unqualified area, and the percentage of redundant waste heat ratio is redistributed to the remaining gap area.

Images