Industrial circulating cooling water waste heat multi-source coupling system based on data driving

Abstract

The invention relates to the technical field of industrial waste heat recovery optimization, in particular to an industrial circulating cooling water waste heat multi-source coupling system based on data driving, and the system comprises a waste heat collection unit, a data processing unit and an intelligent coupling regulation and control unit. After the data processing unit preprocesses data, high, medium and low temperature layers are divided according to temperature, a clustering algorithm is combined to subdivide a calorific value sub-layer, a dynamic characteristic file containing a parameter change curve, fluctuation amplitude and duration is established, the intelligent coupling regulation and control unit compares the file with pre-stored user heat demand characteristics, the matching degree is calculated preferentially according to the temperature contact ratio, and the matching degree is calculated preferentially. A single or multi-source cooperative coupling path is generated, target thermal parameters are synthesized through thermal capacity weighting in a multi-source mode, the supply and demand matching precision and the utilization efficiency of waste heat are improved, diversified energy consumption requirements of industrial scenes are met, and energy conservation and emission reduction are facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial waste heat recovery optimization, and in particular to a data-driven industrial circulating cooling water waste heat multi-source coupling system. Background Art

[0002] Industrial waste heat recovery optimization is an important technology. The large amount of waste heat contained in industrial circulating cooling water has become an important energy-saving resource. Through efficient recovery and cascade utilization, it is of key significance to reducing corporate energy consumption, improving energy utilization and reducing carbon emissions. This technology breaks through the limitations of the traditional single waste heat utilization model and provides intelligent solutions for matching waste heat supply and demand in multiple scenarios. The traditional waste heat distribution method that relies on manual experience can no longer meet the refined energy needs of complex industrial scenarios.

[0003] However, the existing industrial circulating cooling water waste heat utilization technology has the core problem of insufficient accuracy in matching waste heat supply and demand. Traditional solutions do not perform hierarchical division and dynamic characteristic analysis of waste heat according to parameters such as temperature and flow, and only use fixed paths to distribute waste heat. When the user's heat demand does not match the characteristics of a single waste heat source, it is easy to cause excess or insufficient heat supply. At the same time, there is a lack of a multi-source waste heat collaborative coupling mechanism, and it is impossible to compensate for the defects of a single heat source through weighted allocation of waste heat at different levels, resulting in waste heat resource waste and a decline in user energy consumption experience. The combination of these problems makes the waste heat utilization efficiency low, making it difficult to adapt to the diversified and dynamic energy consumption demands of industrial scenarios, and restricting the realization of energy conservation and emission reduction goals. In order to solve this technical problem, we provide a data-driven industrial circulating cooling water waste heat multi-source coupling system. Summary of the Invention

[0004] The purpose of the present invention is to provide a data-driven industrial circulating cooling water waste heat multi-source coupling system to solve the problems raised in the above background technology.

[0005] 1. Because traditional solutions lack waste heat classification and dynamic analysis and use fixed path allocation, resulting in a mismatch between supply and demand, this case uses a data processing unit to divide waste heat into levels and establish dynamic characteristic profiles. The intelligent coupling control unit generates matching coupling paths, which can improve the accuracy of waste heat supply and demand matching.

[0006] 2. Because traditional solutions lack a multi-source collaborative mechanism and cannot compensate for the shortcomings of a single heat source, resulting in resource waste, this case uses an intelligent coupling control unit to activate a multi-source collaborative mode, weighted synthesize target thermal parameters to generate a collaborative path, which can improve waste heat utilization and meet diverse needs.

[0007] To achieve the above objectives, a data-driven industrial circulating cooling water waste heat multi-source coupling system is provided, including: The waste heat collection unit transmits monitoring data to the data processing unit through the sensor components that monitor temperature, flow rate and pressure parameters; The data processing unit pre-processes the monitoring data, divides the pre-processed monitoring data into three levels, and establishes dynamic characteristic files of waste heat at each level. The dynamic characteristic files include parameter change curves, parameter fluctuation amplitudes, and durations. The intelligent coupling control unit has a built-in self-learning database and coupling path optimization module. The self-learning database pre-stores the heat demand characteristic parameters of waste heat users in different industrial scenarios, including the required temperature range, heat load stability and continuous heating duration; The coupling path optimization module compares the dynamic characteristic profile with the heat demand characteristic parameters and calculates the matching degree between the two. When calculating the matching degree, the temperature range overlap is prioritized, followed by the flow fluctuation adaptability and the duration compatibility. When the matching degree exceeds the preset threshold, a coupling path is generated for the corresponding level of waste heat and user demand. When the matching degree is lower than the preset threshold, the coupling path optimization module starts the multi-source collaborative coupling mode, that is, it selects two waste heat sources at different levels, calculates the adjustable heat capacity according to the real-time parameters of each waste heat source, and synthesizes the target thermal parameters according to the weighted heat capacity ratio, so that the matching degree between the target thermal parameters and the user demand characteristic parameters reaches above the preset threshold, and generates a collaborative coupling path including the output ratio of each waste heat source and the transmission path switching node.

[0008] Compared with the prior art, the present invention has the following beneficial effects: 1. The data processing unit divides waste heat into high, medium and low temperature layers based on temperature ranges, and uses a clustering algorithm to secondary cluster the flow and pressure parameters to form a heat value sublayer. It then extracts dynamic features through a time series neural network to establish a dynamic characteristic profile containing parameter change curves, fluctuation amplitudes and durations, thereby achieving a refined characterization of waste heat resources. The intelligent coupling control unit compares these profiles with the user heat demand characteristics pre-stored in the self-learning database, calculates the matching degree based on the priority of temperature overlap, flow adaptability and duration compatibility, and generates a targeted coupling path to avoid excess or insufficient heat supply caused by traditional fixed allocation, thereby significantly improving the accuracy of supply and demand matching.

[0009] 2. When the matching degree of a single waste heat source is insufficient, the system excludes the layers with excessive temperature deviation, selects the combination whose heat capacity meets the required redundancy and the high-temperature layer reaches the minimum guarantee value, calculates the adjustable heat capacity based on real-time parameters, and synthesizes the target thermal parameters by weighted proportion. The temperature is linearly fused and the flow is smoothed to make the fluctuation amplitude of the synthesized parameters lower than the single-source level. At the same time, a collaborative path including output ratio and path switching nodes is generated, and smooth transmission is achieved through intelligent regulating valve group and pressure buffer device, which not only makes up for the defects of a single heat source, but also fully taps the utilization value of waste heat at different levels and reduces resource waste.

[0010] 3. The digital twin platform simulates and verifies the coupling path, pre-adjusts the valve opening to ensure feasibility, and uses a pipeline attenuation compensation mechanism to correct for heat capacity losses in long-distance transmission, improving data accuracy. The self-learning database continuously accumulates demand characteristics and matching cases for different scenarios, supporting the system's dynamic optimization of matching logic and enhancing its adaptability to diverse and dynamic working conditions. In addition, multi-level response instructions in the collaborative path implement timed switching to avoid fluid shock, ensure transmission stability, and ultimately improve overall waste heat utilization efficiency, helping companies achieve their energy conservation and emission reduction goals. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is an overall block diagram of the present invention.

[0012] The meaning of each number in the figure is: 1. Waste heat collection unit; 2. Data processing unit; 3. Intelligent coupling control unit. DETAILED DESCRIPTION

[0013] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0014] The present invention provides a data-driven industrial circulating cooling water waste heat multi-source coupling system, please refer to Figure 1 Shown, including: The waste heat collection unit 1 transmits monitoring data to the data processing unit 2 through the sensor components that monitor temperature, flow rate and pressure parameters; The data processing unit 2 pre-processes the monitoring data, divides the pre-processed monitoring data into three levels, and establishes dynamic characteristic files of waste heat at each level. The dynamic characteristic files include parameter change curves, parameter fluctuation amplitudes, and durations. In the industrial circulating cooling water system, the waste heat collection unit 1 is the source of data acquisition. It collects monitoring data reflecting the waste heat characteristics in real time through sensor components deployed at key nodes of the circulating cooling water network. These data specifically include the cooling water temperature, real-time flow rate and pressure value in the pipeline at each monitoring point. These parameters are directly related to the energy level and transmission status of the waste heat, and are the basis for subsequent data processing and coupled control.

[0015] The collected monitoring data is first transmitted to the data processing unit 2 for preprocessing to ensure the integrity and consistency of the data and provide reliable input for subsequent hierarchical division. After the preprocessing is completed, the data processing unit 2 begins to divide the monitoring data into three levels. The specific method of dividing the preprocessed monitoring data into three levels is as follows: This process starts with the temperature dimension, because temperature is the core indicator for measuring the quality of waste heat energy. The waste heat source here comes from the circulating cooling water discharged by various equipment in the industrial production process. These cooling waters carry different degrees of heat after heat exchange with the equipment, forming a recyclable waste heat source. Based on the preset temperature range, the waste heat source is divided into high-temperature layer, medium-temperature layer and low-temperature layer. The high-temperature layer is 60-90℃ and is used in scenarios requiring high-temperature heat sources, such as heating and raw material preheating. The medium-temperature layer is 30-60℃ and is used for process insulation and hot water supply. The low-temperature layer is 20-30℃ and is used in low-grade heat use scenarios such as agricultural greenhouses and fish pond insulation. This division method clarifies its potential application direction based on the energy grade of waste heat, laying the foundation for subsequent precise matching of user needs. After completing the temperature level division, in order to further refine the waste heat differences within the same temperature level, the flow and pressure parameters of the same temperature level are secondary clustered through a clustering algorithm, using a dynamic density peak clustering algorithm. The specific process is as follows: The flow and pressure parameters of all monitoring data within the same temperature level are taken as two-dimensional feature vectors, and each data point can be expressed as (flow, pressure). The local density of each data point is calculated, that is, the number of data points within a certain distance around the point and the minimum distance between the data points with higher density. The cluster center is determined based on this. Points with high local density and far distance from other high-density points are selected as centers. Data points are classified according to their distance from each cluster center. The data points closest to a certain center are assigned to the cluster cluster, forming multiple subgroups with similar flow-pressure characteristics. For example, in the mesothermal layer (30-60°C), there is a cluster with stable flow (20-30m³ / h) and small pressure fluctuation (0.3-0.4MPa), and another cluster with large flow fluctuation (10-40m³ / h) and high pressure (0.5-0.6MPa). Secondary clustering can capture the differences in the transfer characteristics of residual heat within the same temperature level, making the hierarchical division more refined. Afterwards, different calorific value sublayers are divided according to the distance relationship between the data point, that is, each monitoring data sample containing flow and pressure parameters and the cluster center. Specifically, the Euclidean distance from each data point to the cluster center is calculated. The data points with a distance less than or equal to a preset threshold, which is the average distance from all data points in the cluster to the center, are divided into the core sublayer, representing the residual heat part with the most stable characteristics in the cluster. The data points with a distance greater than the threshold but less than 2 times the threshold are divided into the edge sublayer. Through this division, each temperature level is subdivided into multiple calorific value sublayers, and finally a residual heat level system consisting of "temperature level + calorific value sublayer" is formed. A dynamic label is marked for each sublayer, and the label contains the flow pressure fluctuation range and average calorific value key information of the sublayer, which is convenient for the subsequent intelligent coupling control unit 3 to quickly identify and match.

[0016] Methods for establishing dynamic characteristic profiles of waste heat at each level include: After completing the waste heat level division and marking dynamic labels, in order to fully grasp the changing laws of waste heat at each level, it is necessary to establish a dynamic characteristic file for it. This process achieves in-depth characterization of waste heat characteristics through time series analysis and pattern comparison, and uses time series neural network to extract features of adaptive windows for monitoring data. The adaptive window will automatically adjust its size according to the degree of data fluctuation. The extracted features include: the mean value of the parameter in the window (reflecting the average level within the period), peak and valley values ​​(reflecting the fluctuation amplitude of the parameter), trend slope (indicating the direction of parameter change), and fluctuation frequency (counting the number of parameter fluctuations per unit time). These features capture the dynamic change characteristics of waste heat parameters from different dimensions and provide structured data for subsequent analysis. After the feature extraction is completed, due to these Features can reflect the historical variation patterns of parameters, and the prediction model needs to infer future trends based on historical patterns. Therefore, the extracted features are input into the prediction model (this model is a submodule of the time series neural network and uses the LSTM structure to capture temporal dependencies). By learning information such as the trend slope and fluctuation frequency in the features, the fluctuation trend of the parameters within the next 30 minutes is estimated. This enables the model to predict the direction of change of the waste heat parameters in advance, providing a forward-looking basis for responding to fluctuations. The real-time fluctuation data is dynamically compared with the historical pattern, and abnormal operating conditions are marked. The real-time fluctuation data refers to the original parameter values ​​collected during the current monitoring period and the features calculated from them. The historical pattern is the typical parameter change pattern stored by waste heat level and sub-layer classification from the historical data accumulated by the system. The specific comparison process is as follows: The similarity between the characteristics of real-time fluctuation data and the corresponding historical pattern characteristics is calculated, and a similarity threshold is set. When the similarity is lower than the threshold, the source of the deviation is further analyzed. If the deviation exceeds the temperature range of the level, it is marked as an abnormal operating condition, and information such as the time of the abnormality and the parameter deviation value are recorded. At the same time, the probability characteristic envelope of the parameter change curve is generated. The innovation lies in combining the estimated trend of the prediction model with the historical fluctuation probability distribution. The specific process is as follows: Taking the real-time parameter change curve as a benchmark, and based on the fluctuation amplitude distribution of the waste heat parameters at this level in historical data, probability boundaries are drawn on both sides of the curve. The upper boundary is the predicted trend value plus the upper limit of the historical 95% confidence interval, and the lower boundary is the predicted trend value minus the lower limit of the historical 95% confidence interval, forming an envelope line that wraps the parameter change curve. The envelope line can intuitively reflect the possible fluctuation range of the parameter in the future, providing a visual basis for judging whether the parameter is within the normal fluctuation range, making subsequent supply and demand matching more targeted, and effectively improving the system's adaptability to dynamic changes in waste heat.

[0017] The intelligent coupling control unit 3 has a built-in self-learning database and a coupling path optimization module. The self-learning database pre-stores the heat demand characteristic parameters of waste heat users in different industrial scenarios, including the required temperature range, heat load stability, and continuous heating time. After establishing dynamic characteristic profiles for waste heat at each level, to accurately measure the degree of match between waste heat and user needs, it is necessary to calculate the matching degree from three dimensions: temperature, flow rate, and duration. The core evaluation indicators are temperature range overlap, flow rate fluctuation adaptability, and duration fit. First, consider temperature range overlap, which is defined as the overlap ratio between the user's required temperature range and the waste heat source temperature fluctuation range. The user's required temperature range is the temperature range required by the user in a certain industrial scenario pre-stored in the self-learning database. The waste heat source temperature fluctuation range comes from the temperature parameter change curve of the waste heat level in the dynamic characteristic profile, that is, the range formed by the maximum and minimum temperature values ​​over a period of time. The overlap ratio is calculated as follows: First, determine the overlap between the two ranges (in the above example, the overlap is 40-50°C). Then, divide the length of the overlap (10°C) by the length of the user's required temperature range (10°C) to obtain a 100% overlap. If the user's required range is 50-60°C, and the overlap with the waste heat source range (5-55°C) is 50-55°C (5°C), the overlap is 0%. This metric directly reflects the basic compatibility between waste heat temperature and user needs and is the primary consideration in matching calculations. Flow fluctuation adaptability is calculated using a dynamic morphology matching algorithm to measure the similarity between the waste heat source flow curve and the user's demand baseline. The waste heat source flow curve is extracted from the dynamic characteristic file and is a continuous curve drawn from flow monitoring data at a waste heat level per unit time (flow values ​​are recorded every 5 minutes and connected to form a 24-hour flow change curve). The user demand baseline is a flow reference curve generated based on the user's heat load stability requirements. (If a user requires a stable flow, the baseline is a horizontal line. If the user's demand fluctuates periodically over time, the baseline is the corresponding cyclical curve.) The specific calculation process is as follows: The two curves are aligned along the time axis, and the distance between them is calculated using a dynamic time warping algorithm (which introduces a time elastic matching mechanism to allow the curves to locally scale in the time dimension). A smaller distance indicates a higher similarity. For example, the waste heat source flow curve exhibits small fluctuations (±2 m³ / h) over a certain period, while the user demand baseline is a horizontal line (target flow rate 20 m³ / h). The algorithm aligns the fluctuation nodes with the baseline value, calculates the sum of squared deviations at each point, and takes the average to obtain a similarity score (out of 100; if the average deviation is 1 m³ / h, the score might be 90). This score is a quantitative result of the flow fluctuation adaptability and reflects whether the waste heat flow can adapt to the user's load fluctuations. The duration fit is the degree to which the waste heat source's sustainable heating duration covers the user's demand duration. The sustainable heating duration of the waste heat source is derived from the parameter duration records in the dynamic characteristic file. This refers to the continuous duration for which the waste heat level can stably output heat that meets the basic temperature and flow requirements. The user demand duration is the duration of continuous heat demand required by the user in the self-learning database. The coverage is calculated as: If the sustainable duration of the waste heat source (8 hours) is greater than or equal to the user demand duration (6 hours), the degree of fit is 100%. If the sustainable duration of the waste heat source is 4 hours and the user demand duration is 6 hours, the degree of fit is 4 / 6≈67%. This indicator ensures that the waste heat supply can meet the user's continuous energy needs and avoids the impact of heat supply interruptions on production. It provides a scientific basis for the intelligent coupling control unit 3 to generate an accurate coupling path, so that the waste heat supply and demand matching is more in line with the actual needs of industrial scenarios.

[0018] The coupling path optimization module compares the dynamic characteristic profile with the heat demand characteristic parameters and calculates the matching degree between the two. When calculating the matching degree, the temperature range overlap is prioritized, followed by the flow fluctuation adaptability and the duration compatibility. When the matching degree exceeds the preset threshold, a coupling path is generated for the corresponding level of waste heat and user demand. The matching degree is calculated as follows: After completing individual calculations for temperature range overlap, flow fluctuation adaptability, and duration compatibility, the coupled path optimization module constructs a multi-dimensional feature vector space to perform system quantitative analysis in order to comprehensively evaluate the overall matching level between waste heat and user needs. A multidimensional feature vector space is constructed, specifically using temperature range overlap, flow fluctuation adaptability, and duration fit as the three dimensions. The numerical range of each dimension is normalized to 0-1 (1 represents a perfect match). The corresponding parameters in the dynamic characteristic file and the user heat demand characteristic parameters are converted into feature vectors in this space. For example, the vector of a certain residual heat source is (0.8, 0.7, 0.9), representing 80% temperature overlap, 70% flow adaptability, and 90% duration fit, while the user demand vector is (1.0, 1.0, 1.0) (ideal state). The role of the multidimensional feature vector space is to transform the abstract matching index into a quantifiable spatial coordinate, so that the matching difference between different waste heat sources and user needs can be intuitively reflected through the vector distance, providing a geometric basis for the subsequent similarity calculation. The similarity algorithm is used to calculate the matching value and map it to the standard interval. Specifically, the cosine similarity algorithm is used to calculate the cosine value of the angle between the two feature vectors (the value range is -1 to 1). The closer the cosine value is to 1, the more consistent the directions of the two vectors are, and the higher the matching degree is. For example, the cosine similarity between the waste heat source vector and the user demand vector is (0.8×1.0 + 0.7×1.0+0.9×1.0)÷(√(0.8²+0.7²+0.9²)×√(1.0²+1.0²+1.0²))≈0.95, and then the cosine value is converted into a standard interval score of 0-100 through linear mapping (for example, 0.95 corresponds to 95 points). The mapping formula is "standard score = (cosine value + 1) ÷ 2×100", ensuring that the matching value can reflect the relative difference and is easy to understand intuitively. This process condenses the matching degree of multi-dimensional features into a single quantitative indicator, providing a basis for the rapid screening of qualified waste heat sources. When the matching values ​​of multiple groups of waste heat sources are all higher than the preset threshold, in order to further screen out the optimal solution, a multi-objective optimization screening mechanism is introduced for dual priority sorting, and an "efficiency-stability" dual-objective optimization model is constructed: The first sorting phase targets waste heat utilization efficiency (calculating the proportion of waste heat converted into effective work) and sorts waste heat sources from high to low efficiency. The second sorting phase targets system operational stability (based on a comprehensive assessment of flow fluctuation adaptability and historical fault frequency). Waste heat sources with similar efficiency are sorted from high to low stability. For example, if waste heat sources A and B both have a matching score of 90, and A has an efficiency of 85% and a stability score of 90, while B has an efficiency of 82% and a stability score of 95, then A takes precedence over B in the first sorting phase. If stability is prioritized, B can be moved up in the comprehensive sorting by weight adjustment. After the sorting is complete, a list of non-inferior solutions is output, eliminating solutions with obvious disadvantages (e.g., solutions with lower efficiency and stability than other solutions) and retaining all solutions that have advantages in at least one objective. Each solution is then labeled with its efficiency value, stability score, and applicable scenario (e.g., A is suitable for scenarios prioritizing efficiency, and B is suitable for scenarios prioritizing stability). This provides flexibility for subsequent coupling path selection, lays a scientific foundation for the intelligent coupling control unit 3 to generate the optimal coupling path, and effectively improves the accuracy and flexibility of waste heat supply and demand matching.

[0019] The logic for generating coupling paths is: After determining the matching degree between waste heat and user demand and screening out the optimal waste heat source, the intelligent coupling control unit 3 needs to generate a specific coupling path to achieve efficient transmission of waste heat from the source to the user. The industrial scene topology map is a digital presentation of the spatial distribution and connection relationship of waste heat supply points, transmission pipelines, user energy points and related equipment in the industrial plant. It marks the location of each waste heat source, the distribution of user demand points, the direction and specifications of the pipeline, the control range of the valve and other information. It is equivalent to a "digital map" of the entire industrial waste heat transmission system, providing a spatial basis for path planning. Based on this topology map, the intelligent coupling control unit 3 first selects the waste heat source with the highest matching level as the main supply source, and then determines the transmission path with the lowest energy consumption through the path search algorithm. The dynamic energy consumption weight is used here. algorithm: The algorithm uses the waste heat source as its starting point and the user's demand point as its endpoint. It decomposes the energy consumption of the transmission path into heat loss along the pipeline (related to pipeline length and insulation coefficient) and pump transmission energy consumption (related to flow rate and pipeline resistance). Each pipeline segment is assigned a dynamic weight (the weighted sum of heat loss and transmission energy consumption). During the search process, it not only prioritizes pipeline segments with low weights but also avoids high-resistance segments (such as sudden changes in pipe diameter) and high-loss segments (such as areas with damaged insulation) marked in the topology map. By continuously iteratively updating path nodes, it ultimately generates the transmission path with the lowest total energy consumption. For example, if there are two paths, A and B, from a high-temperature waste heat source to a user, path A is shorter but has poor pipe insulation (high heat loss), while path B is slightly longer but has good insulation and low pump energy consumption. The algorithm calculates the lower total energy consumption of path B and selects it as the optimal path. After determining the transmission path, the opening of the intelligent regulating valve group must be pre-adjusted to match the user's real-time heat demand. This is because the valve opening in the path directly affects the flow rate and pressure, which in turn affects the stability of the heating supply. The specific process is as follows: According to the user's required flow rate and the total resistance of the path, the target opening required for each valve is calculated. First, pre-adjust the initial opening to 50%, and then use the flow sensor installed behind the valve to feedback the current flow in real time. After comparing it with the target flow, fine-tune the opening and repeat the adjustment until the flow stabilizes within ±5% of the target value. This pre-adjustment process can ensure the stability of the parameters when the path is started and avoid thermal shock caused by sudden changes in flow. In order to further verify the feasibility of the path, a digital twin platform is used for simulation verification. The platform constructs a virtual model that is completely consistent with the physical system, including the heat conduction characteristics of the pipeline, the adjustment response of the valve, the dynamic changes of user needs, etc. During the simulation, the pre-adjusted valve opening and the thermal parameters of the main supply source are input The virtual model simulates the transmission process in the next hour and monitors whether there are problems such as overpressure, overheating loss, and unstable flow. If there are problems, the problem will be fed back to the intelligent coupling control unit 3 to re-optimize the path or adjust the valve opening until the simulation results show that all parameters are within the safe range. For example, the simulation finds that the flow fluctuation of the original path exceeds the user's tolerance range in the 30th minute. The platform will automatically suggest adjusting the opening curve of a certain valve. After the secondary simulation is verified to be qualified, the feasible coupling path is finally determined, so that the generated coupling path can accurately adapt to user needs and the actual conditions of the industrial scenario, providing reliable guarantee for the efficient transmission of waste heat, and laying the foundation for the subsequent launch of the single-source path for the multi-source collaborative coupling mode.

[0020] When the matching degree is lower than the preset threshold, the coupling path optimization module starts the multi-source collaborative coupling mode, that is, it selects two waste heat sources at different levels, calculates the adjustable heat capacity according to the real-time parameters of each waste heat source, and synthesizes the target thermal parameters according to the weighted heat capacity ratio, so that the matching degree between the target thermal parameters and the user demand characteristic parameters reaches above the preset threshold, and generates a collaborative coupling path including the output ratio of each waste heat source and the transmission path switching node.

[0021] The strategy for selecting two waste heat sources at different levels is: When the matching degree of a single waste heat source is lower than the preset threshold, the coupling path optimization module of the intelligent coupling control unit 3 will start the multi-source collaborative coupling mode. First, two waste heat sources of different levels need to be selected. This process follows the strategy of combining precise screening with system evaluation to exclude waste heat levels that exceed the preset deviation from the target temperature range. The target temperature range is the core temperature range required by the user. The preset deviation is usually set to ±10°C. If the temperature fluctuation range of a high-temperature level is 70-80°C and the deviation from the target range is 20°C, it will be excluded to ensure that the selected waste heat sources have basic adaptability to user needs in terms of temperature properties, laying the foundation for subsequent thermal parameter synthesis. In the remaining levels that meet the temperature deviation requirements, a heat capacity contribution evaluation matrix is ​​constructed. The specific process is as follows: The initial matrix is ​​formed with the waste heat source levels (such as the remaining sublayer of the high-temperature layer, the sublayer of the mesothermal layer, etc.) as rows and the heat capacity related indicators as columns (including instantaneous heat capacity, heat capacity decay rate during continuous heating, and heat loss rate during transmission). Then, a weight is assigned to each indicator (instantaneous heat capacity weight 0.5, decay rate weight 0.3, heat loss rate weight 0.2), and the weighted score of each level is calculated as its heat capacity contribution. For example, the instantaneous heat capacity of a sublayer of the high-temperature layer is high but decays quickly, and the instantaneous heat capacity of a sublayer of the mesothermal layer is slightly lower but decays slowly. The matrix will quantify the comprehensive contribution capabilities of the two. Its function is to convert the heat capacity characteristics of different levels into comparable quantitative data, avoiding the one-sidedness caused by relying on a single indicator to select waste heat sources. Based on the evaluation matrix, the waste heat source combination whose effective heat capacity meets the redundancy requirements of waste heat users and whose high-temperature layer proportion reaches the minimum guarantee value is screened. The effective heat capacity refers to the actual available heat after deducting the transmission loss. The demand redundancy is usually It is set to 10% (that is, the effective heat capacity must reach 110% of the user's required heat capacity to cope with fluctuations), and the minimum guarantee value of the high-temperature layer ratio is set to 30% (that is, the heat capacity provided by the high-temperature layer in the combination must be no less than 30% of the total effective heat capacity to ensure the temperature basis of the combined heat source). For example, the user's required heat capacity is 100kW, and a combination consists of a high-temperature layer (effective heat capacity 40kW) and a medium-temperature layer (effective heat capacity 70kW), with a total effective heat capacity of 110kW (satisfying 10% redundancy), and a high-temperature ratio of 36.4% (exceeding the 30% guarantee value). Then this combination meets the screening conditions. If the total effective heat capacity of another combination meets the standard but the high-temperature ratio is only 25%, it will be excluded. This allows the two selected levels of waste heat sources to complement each other's advantages in collaborative coupling, providing a reliable source guarantee for the subsequent weighted synthesis of target thermal parameters and the generation of efficient collaborative paths, and also enables the multi-source mode to truly make up for the shortcomings of a single heat source and improve the flexibility and stability of waste heat utilization.

[0022] The method for calculating the adjustable heat capacity is: After selecting two waste heat sources at different levels, in order to ensure the accuracy of heat capacity allocation during multi-source collaborative coupling, the adjustable heat capacity of each waste heat source needs to be calculated. This process relies on the dynamic update of real-time data and needs to take into account the heat loss during transmission. The instantaneous value of the heat capacity of each waste heat source is dynamically refreshed based on the real-time collected temperature and flow data. Specifically, the calculation formula of the instantaneous value of heat capacity is "heat capacity = flow × temperature × specific heat capacity × density" (where specific heat capacity and density are inherent physical parameters of circulating cooling water and are preset as constants). The waste heat collection unit 1 collects the real-time temperature (e.g., the current temperature of the high-temperature layer waste heat source is 75°C) and flow rate (e.g., 30m³ / h) of each waste heat source every 5 minutes. These data are substituted into the formula to calculate the current heat capacity (e.g., 30×75×4.2×1000≈9.45× ), and automatically overwrite the value of the previous cycle to achieve dynamic refresh. This process can reflect the instantaneous heating capacity of the waste heat source in real time and provide the latest basis for subsequent weighted synthesis. Since multi-source collaborative coupling may involve long-distance transmission, heat will be lost due to pipeline heat dissipation during transmission. Therefore, it is necessary to introduce a pipeline attenuation compensation mechanism to pre-correct the heat capacity loss. The specific process is as follows: First, determine the transmission pipeline length from each waste heat source to the user demand point according to the industrial scenario topology diagram (for example, the transmission distance of the waste heat source in the high-temperature layer is 500 meters). Then, call the pipeline attenuation coefficient table (the table presets the attenuation rate of different distances based on the pipeline material, insulation layer thickness and ambient temperature, such as 2% attenuation per 100 meters for ordinary steel pipes), calculate the total attenuation rate (500 meters corresponds to 10% attenuation), and multiply the instantaneous value of the heat capacity by (1-total attenuation rate) to obtain the corrected adjustable heat capacity (for example, 9.45× ×0.9≈8.505× ), the effect after correction is: The calculated adjustable thermal capacity is made closer to the actual amount of heat reaching the user end, avoiding insufficient heat supply due to failure to consider attenuation (for example, if not corrected, the heat that actually reaches the user end according to the original thermal capacity may be only 90% of the demand. After correction, the attenuation part can be supplemented in advance to ensure the balance between supply and demand). The calculation of the adjustable thermal capacity is more in line with the actual working conditions, providing accurate basic data for the subsequent weighted synthesis of target thermal parameters according to the proportion of thermal capacity, and allowing the multi-source collaborative coupling mode to more accurately meet user needs, effectively improving the efficiency of waste heat transmission and utilization.

[0023] The logic of weighted synthesis target thermal parameters is: After determining the adjustable heat capacity of each waste heat source, the process of weighted synthesis of target thermal parameters needs to take into account the synergistic characteristics of temperature and flow to achieve accurate matching with user needs. The heat capacity ratio of waste heat sources at different levels is calculated as the weighting coefficient, that is, the heat capacity ratio of a waste heat source = the adjustable heat capacity of the waste heat source ÷ the sum of the adjustable heat capacity of all waste heat sources participating in the collaboration (for example, the adjustable heat capacity of the waste heat source in the high-temperature layer is 8.5× , the mesothermal layer is 6.3× , the high-temperature layer accounts for 8.5÷(8.5+6.3)≈57%, and the mesothermal layer accounts for 43%). This proportion directly reflects the energy contribution weight of each residual heat source in the collaborative coupling. For the temperature parameter, linear weighted fusion is adopted. Specifically, the real-time temperature of each residual heat source is multiplied by the corresponding heat capacity proportion and then summed to obtain the synthetic temperature (for example, the real-time temperature of the high-temperature layer is 75℃ and the mesothermal layer is 50℃, then the synthetic temperature = 75×57%+50×43%≈64.7℃). This linear fusion method can ensure that the synthetic temperature is within the user's required temperature range, while retaining the temperature dominance of the high-proportion residual heat source, avoiding the excessive impact of temperature fluctuations of a single heat source on the overall system. For the flow parameter, smoothing fusion is adopted and a dynamic attenuation factor is introduced: First, the initial weighted flow rate is calculated based on the heat capacity ratio (for example, the high-temperature layer flow rate is 30 m³ / h and the mesothermal layer is 25 m³ / h, so the initial weighted flow rate = 30 × 57% + 25 × 43% ≈ 27.85 m³ / h). Then, the real-time flow fluctuations of each residual heat source are monitored. If the flow fluctuation amplitude of a heat source exceeds the preset threshold, an attenuation factor is assigned to it (the larger the fluctuation, the smaller the factor, ranging from 0.8 to 1.0), and the weighted flow rate is recalculated (for example, if the mesothermal layer flow fluctuation reaches 6 m³ / h, the attenuation factor is 0.8, then the corrected weighted flow rate = 30 × 57% + 25 × 43% × 0.8 ≈ 26.1 m³ / h). Finally, the corrected flow rate for five consecutive cycles is smoothed using a sliding average algorithm to obtain the final composite flow rate. This ensures that the stability of the output parameters meets user requirements and provides a reliable thermal parameter foundation for the subsequent generation of collaborative coupling paths.

[0024] The process of generating cooperative coupling paths is: After completing the weighted synthesis of the target thermal parameters, a specific collaborative coupling path needs to be generated to achieve efficient transmission and collaborative supply of multi-source waste heat. This process revolves around flow distribution, pressure buffering and timing control to ensure the stability and accuracy of multi-source coupling, and drives the flow distribution valve according to the heat capacity ratio of each waste heat source. Specifically, an intelligent flow distribution valve is installed at the confluence pipe connecting two different levels of waste heat sources. After the valve controller receives the heat capacity ratio data (such as the high-temperature layer accounts for 57% and the medium-temperature layer accounts for 43%), it converts it into the corresponding valve opening instruction. The valve opening corresponding to the high-temperature layer is set to 57%, and the valve opening corresponding to the medium-temperature layer is set to 43%. At the same time, the actual flow ratio is monitored in real time through the built-in flow sensor of the valve. If the deviation from the target ratio exceeds 3% (such as the actual ratio of the high-temperature layer drops to 53%), the valve opening is automatically fine-tuned (increase the high-temperature layer valve opening by 1%) until the flow distribution and heat capacity ratio are consistent. This operation ensures that each waste heat source participates in the collaborative supply according to the expected contribution, providing a flow basis for the stable output of the target thermal parameters. Since multi-source waste heat may cause fluid shock due to pressure differences at the transmission path switching node, that is, the confluence point of different heat source pipelines, a pressure buffer device needs to be deployed here. The device has a built-in elastic diaphragm and a pressure sensor. When the pressure fluctuation in the pipeline exceeds ±0.1MPa, the diaphragm automatically expands and contracts to adjust the volume to absorb the pressure shock. For example, when the pressure in the high-temperature layer suddenly rises, the diaphragm expands to accommodate part of the fluid, reducing the pressure at the confluence point, and at the same time feeding back the pressure data to the control system. If the fluctuation lasts for more than 5 seconds, the auxiliary pressure relief valve is triggered to fine-tune to further stabilize the pressure, avoid pipeline vibration or equipment damage due to shock, and ensure the safety of the transmission process. On this basis, a control sequence containing multi-level response instructions is generated to realize the timed switching and parameter adjustment of the coupling path, which is specifically divided into three response levels: The first-level instruction is the initial startup phase (the first five minutes). The flow distribution valve is controlled to slowly open at an initial opening of 30%. Simultaneously, the pressure buffer device enters a pre-charged state to ensure smooth fluid confluence. The second-level instruction is the stable operation phase. Based on the deviation between the real-time monitored target thermal parameters (temperature, flow) and user requirements, a fine-tuning instruction is generated every two minutes (for example, if the temperature is too high, the high-temperature layer flow ratio is reduced by 2%). The third-level instruction is the switching transition phase. When a waste heat source needs to be withdrawn or added, the pressure is first pre-adjusted through the buffer device. Then, the flow distribution is adjusted according to the "increase first, then decrease" principle (for example, gradually increasing the medium-temperature layer ratio to 60% and simultaneously reducing the high-temperature layer ratio to 40%). The entire process uses timestamps to mark the execution order of each instruction, forming a timed control sequence. This sequence is stored in the instruction library of the intelligent coupling control unit 3 and can be called sequentially by the execution system. This ensures that the synthesized target thermal parameters continuously meet user requirements, ultimately achieving multi-source coordinated and efficient utilization of industrial circulating cooling water waste heat.

[0025] In the present invention, the waste heat collection unit 1 obtains temperature, flow and pressure data through the sensor component. After the data processing unit 2 pre-processes the data, it divides the data into high, medium and low temperature layers according to the temperature, and subdivides the calorific value sublayer by combining the clustering algorithm to establish a dynamic characteristic file containing parameter change curve, fluctuation amplitude and duration. The intelligent coupling control unit 3 compares the file with the pre-stored user heat demand characteristics, and preferentially calculates the matching degree according to the temperature coincidence, generates a single or multi-source collaborative coupling path, and synthesizes the target thermal parameters through heat capacity weighting in the multi-source mode, thereby improving the waste heat supply and demand matching accuracy and utilization efficiency, adapting to the diversified energy demand of industrial scenarios, and helping to save energy and reduce emissions.

[0026] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely preferred examples of the present invention and are not intended to limit the present invention. Various changes and improvements may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and improvements fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A data-driven industrial circulating cooling water waste heat multi-source coupling system, characterized by: include: The waste heat collection unit (1) transmits monitoring data to the data processing unit (2) through a sensor component that monitors temperature, flow rate, and pressure parameters; The data processing unit (2) pre-processes the monitoring data, divides the pre-processed monitoring data into three levels, and establishes dynamic characteristic files of waste heat at each level, wherein the dynamic characteristic files include parameter change curves, parameter fluctuation amplitudes, and durations; The intelligent coupling control unit (3) has a built-in self-learning database and a coupling path optimization module. The self-learning database pre-stores the heat demand characteristic parameters of waste heat users in different industrial scenarios, including the required temperature range, heat load stability and continuous heat use time; The coupling path optimization module compares the dynamic characteristic profile with the heat demand characteristic parameters and calculates the matching degree between the two. When calculating the matching degree, the temperature range overlap is prioritized, followed by the flow fluctuation adaptability and the duration compatibility. When the matching degree exceeds the preset threshold, a coupling path is generated for the corresponding level of waste heat and user demand. When the matching degree is lower than the preset threshold, the coupling path optimization module starts the multi-source collaborative coupling mode, that is, it selects two waste heat sources at different levels, calculates the adjustable heat capacity according to the real-time parameters of each waste heat source, and synthesizes the target thermal parameters according to the weighted heat capacity ratio, so that the matching degree between the target thermal parameters and the user demand characteristic parameters reaches above the preset threshold, and generates a collaborative coupling path including the output ratio of each waste heat source and the transmission path switching node.

2. The data-driven industrial circulating cooling water waste heat multi-source coupling system according to claim 1 is characterized in that: The specific method of dividing the pre-processed monitoring data into three levels is: Based on the preset temperature range, the waste heat source is divided into high-temperature layer, medium-temperature layer and low-temperature layer. The flow and pressure parameters of the same temperature level are secondary clustered through the clustering algorithm. Different calorific value sub-layers are divided according to the distance relationship between the data point and the cluster center to form a waste heat level and mark it with dynamic labels.

3. The data-driven industrial circulating cooling water waste heat multi-source coupling system according to claim 1 is characterized in that: The method for establishing a dynamic characteristic profile of waste heat at each level includes: A time series neural network is used to extract features of the monitoring data in an adaptive window. The parameter fluctuation trend is estimated through a prediction model. The real-time fluctuation data is dynamically compared with the historical pattern and abnormal conditions are marked. At the same time, the probability characteristic envelope of the parameter change curve is generated.

4. The data-driven industrial circulating cooling water waste heat multi-source coupling system according to claim 1 is characterized in that: The matching degree calculation method is: The coupled path optimization module constructs a multidimensional feature vector space, uses a similarity algorithm to calculate the matching values ​​between the dynamic characteristic profile and the heat demand characteristic parameters, and maps them to the standard interval. When multiple groups of waste heat sources meet the threshold conditions, a multi-objective optimization screening mechanism is introduced to perform dual priority sorting and output a list of non-inferior solutions.

5. The data-driven industrial circulating cooling water waste heat multi-source coupling system according to claim 1 is characterized in that: The temperature range overlap is defined as the overlapping ratio of the user's required temperature range and the waste heat source temperature fluctuation range. The flow fluctuation adaptability is calculated by the dynamic morphology matching algorithm to determine the similarity between the waste heat source flow curve and the user's required baseline. The duration fit is the degree of coverage of the waste heat source's sustainable heating duration to the user's required duration.

6. The data-driven industrial circulating cooling water waste heat multi-source coupling system according to claim 1 is characterized in that: The logic for generating the coupling path between the corresponding level of waste heat and user needs is as follows: The intelligent coupling control unit (3) selects the waste heat source with the highest matching level as the main supply source based on the industrial scenario topology diagram, determines the transmission path with the lowest energy consumption through the path search algorithm, pre-adjusts the opening of the intelligent regulating valve group, and uses the digital twin platform to simulate and verify the feasibility of the path.

7. The data-driven industrial circulating cooling water waste heat multi-source coupling system according to claim 1 is characterized in that: The strategy for selecting two waste heat sources at different levels is: The coupling path optimization module excludes waste heat levels that exceed the preset deviation from the target temperature range, constructs a heat capacity contribution evaluation matrix in the remaining levels, and screens waste heat source combinations whose effective heat capacity meets the redundancy requirements of waste heat users and whose high-temperature level ratio reaches the minimum guaranteed value.

8. The data-driven industrial circulating cooling water waste heat multi-source coupling system according to claim 1 is characterized in that: The method for calculating the adjustable heat capacity is: The instantaneous value of the heat capacity of each waste heat source is dynamically refreshed based on the real-time collected temperature and flow data. At the same time, a pipeline attenuation compensation mechanism is introduced to pre-correct the heat capacity loss of long-distance transmission.

9. The data-driven industrial circulating cooling water waste heat multi-source coupling system according to claim 1 is characterized in that: The logic of the weighted synthesis target thermal parameters is: Taking the heat capacity proportion of waste heat sources at different levels as the weighting coefficient, linear weighted fusion is adopted for temperature parameters, and smoothing fusion is adopted for flow parameters, so that the fluctuation amplitude of the synthesized target thermal parameters is lower than the original fluctuation level of a single source.

10. The data-driven industrial circulating cooling water waste heat multi-source coupling system according to claim 1 is characterized in that: The process of generating a coordinated coupling path including the output ratio of each waste heat source and the transmission path switching node is as follows: The flow distribution valve is driven according to the heat capacity ratio, a pressure buffer device is deployed at the transmission path switching node to prevent fluid shock, and a control sequence containing multi-level response instructions is generated to achieve timed switching and parameter adjustment of the coupling path.

Images