Intelligent coal mine multi-source waste heat utilization system and method based on cross-seasonal heat storage

Abstract

The invention provides a coal mine multi-source waste heat intelligent utilization system and method based on cross-seasonal heat storage, and relates to the technical field of coal mine waste heat utilization, and the system comprises the steps that a heat prediction module monitors and obtains a plurality of historical redundant heat sequences of a plurality of coal mine waste heat sources, and carries out heat prediction in a preset time window; a heat supply demand prediction module reads the heat use characteristic sequence and the associated heat use characteristic sequence and performs heat supply demand prediction; a heat storage scheme optimization module performs heat storage scheme optimization and outputs an optimal heat storage proportion sequence by taking a heat supply quantity sequence meeting a predicted demand as a conditional constraint, taking the maximum capacity of heat storage equipment as an equipment constraint and taking the minimum heat loss as a target; and the heat storage management and control module executes heat storage management and control in a preset time window according to the optimal heat storage proportion sequence. The technical problem that in the prior art, waste heat cannot be effectively stored can be solved, the technical target of intelligent regulation and control system construction is achieved, and the technical effect of improving the waste heat utilization efficiency is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coal mine waste heat utilization, and particularly relates to a coal mine multi-source waste heat intelligent utilization system and method based on cross-seasonal heat storage. BACKGROUND

[0002] With the promotion of green and low-carbon policy and the deepening of coal mine energy efficiency management, how to efficiently recover and utilize the multi-source waste heat generated in the coal mine production process has become the focus of current energy utilization optimization. At present, the traditional waste heat utilization mode generally adopts a real-time heating mode, that is, the waste heat is immediately used for heating in the nearby area after being generated. Although this mode can realize waste heat utilization in the short term, it cannot cope with the problem of redundant heat accumulation caused by seasonal differences. At the same time, distributed green electricity (such as wind power and photovoltaic power) often faces the problem of abandoned electricity due to its intermittent nature. A large amount of green electricity that has not been consumed can be converted into waste heat through electrolysis of water or heat pump upgrading, but the existing technology lacks a mechanism for the collaborative storage and cross-seasonal allocation of coal mine waste heat and green electricity. In the winter or summer transition period when supply and demand are mismatched, a large amount of waste heat is discharged into the environment, not only causing energy waste, but also increasing the environmental burden of the coal mine.

[0003] In summary, the existing technology has the technical problem that due to the lack of cross-seasonal regulation ability and waste heat dynamic prediction mechanism, the waste heat cannot be effectively stored and allocated, further affecting the comprehensive utilization efficiency of coal mine waste heat resources and the stability of the heating system. SUMMARY

[0004] The purpose of the present application is to provide a coal mine multi-source waste heat intelligent utilization system and method based on cross-seasonal heat storage, to solve the technical problem in the prior art that due to the lack of cross-seasonal regulation ability and waste heat dynamic prediction mechanism, the waste heat cannot be effectively stored and allocated, further affecting the comprehensive utilization efficiency of coal mine waste heat resources and the stability of the heating system.

[0005] In view of the above problems, the present application provides a coal mine multi-source waste heat intelligent utilization system and method based on cross-seasonal heat storage.

[0006] In a first aspect, the application provides a coal mine multi-source waste heat intelligent utilization system based on cross-season heat storage, comprising: a heat prediction module, configured to monitor and obtain a plurality of historical redundant heat sequences of a plurality of coal mine waste heat sources, perform heat prediction in a preset time window, and obtain a predicted redundant heat sequence; a heat demand prediction module, configured to read a heat use feature sequence and an associated heat use feature sequence of a to-be-heated area in the preset time window, perform heat demand prediction, and output a predicted demand heat supply sequence; a heat storage scheme optimization module, configured to take the predicted demand heat supply sequence as a conditional constraint, take the maximum capacity of a heat storage device as a device constraint, and take the lowest heat loss as a target, perform heat storage scheme optimization, and output an optimal heat storage proportion sequence; and a heat storage management and control module, configured to perform heat storage management and control in the preset time window according to the optimal heat storage proportion sequence.

[0007] Preferably, the coal mine multi-source waste heat intelligent utilization system based on cross-season heat storage further comprises: a heat monitoring unit, configured to monitor and obtain redundant heat of the plurality of coal mine waste heat sources at K continuous time points in a historical time zone, and obtain a plurality of historical redundant heat sequences, wherein K is greater than or equal to 5; a node summation unit, configured to perform same node summation on the plurality of historical redundant heat sequences, and output a historical total redundant heat sequence; and a heat prediction unit, configured to perform heat prediction in a preset time window according to the historical total redundant heat sequence, and obtain a predicted redundant heat sequence.

[0008] Preferably, the coal mine multi-source waste heat intelligent utilization system based on cross-season heat storage further comprises: a sample obtaining channel, configured to collect a sample total redundant heat sequence set, and obtain a historical total redundant heat sequence of different sample total redundant heat sequences in a historical time window, set as a sample predicted redundant heat sequence, and obtain a sample predicted redundant heat sequence set; a training channel, configured to train a long short-term memory network by using the sample total redundant heat sequence set and the sample predicted redundant heat sequence set until convergence, and obtain a redundant heat predictor; and a prediction channel, configured to analyze the historical total redundant heat sequence according to the redundant heat predictor, and obtain a predicted redundant heat sequence.

[0009] Preferably, the coal mine multi-source waste heat intelligent utilization system based on cross-seasonal heat storage further comprises: a sample setting unit, configured to collect a sample heat use feature sequence set and a sample associated heat use feature sequence set, and obtain a historical heat supply sequence under different sample heat use feature sequences and sample associated heat use feature sequences, set as a sample demand heat supply sequence, to obtain a sample demand heat supply sequence set; a supervised training unit, configured to take the sample heat use feature sequence set and the sample associated heat use feature sequence set as input, take the sample demand heat supply sequence set as supervision, train a long short-term memory network to convergence, and obtain a heat demand predictor; and a demand prediction unit, configured to use the heat demand predictor to perform heat demand prediction according to the heat use feature sequence and the associated heat use feature sequence, and output a predicted demand heat supply sequence.

[0010] Preferably, the coal mine multi-source waste heat intelligent utilization system based on cross-seasonal heat storage further comprises: a first heat storage scheme obtaining unit, configured to randomly select a first heat storage ratio sequence in a preset heat storage ratio interval based on the preset time window, and set as a first heat storage scheme; a first heat storage heat quantity sequence obtaining unit, configured to analyze a first heat storage heat quantity sequence according to the predicted redundant heat quantity sequence and the first heat storage ratio sequence; a judgment unit, configured to judge whether the first heat storage heat quantity sequence meets the predicted demand heat supply sequence and the maximum capacity, if both are met, perform heat loss analysis on the first heat storage heat quantity sequence, and output a heat loss value; and an iterative analysis unit, configured to continue to perform iterative selection of heat storage schemes and iterative analysis of heat loss until a preset iteration number is reached, output a heat storage ratio sequence corresponding to a minimum heat loss value, and set as an optimal heat storage ratio sequence.

[0011] Preferably, the coal mine multi-source waste heat intelligent utilization system based on cross-seasonal heat storage further comprises: a heat loss analysis channel, configured to perform heat loss analysis based on attribute features of heat storage equipment, and output a heat loss ratio per unit time; and a compensation channel, configured to compensate the first heat storage heat quantity sequence according to the heat loss ratio.

[0012] Preferably, the coal mine multi-source waste heat intelligent utilization system based on cross-seasonal heat storage further comprises: a loss heat output channel, configured to perform heat loss analysis on a plurality of first heat storage heat quantities in the first heat storage heat quantity sequence based on a time interval of heat use for heat storage, according to the heat loss ratio, and output a plurality of loss heat quantities; and a summation channel, configured to sum the plurality of loss heat quantities to obtain a heat loss value.

[0013] In a second aspect, the application also provides a coal mine multi-source waste heat intelligent utilization method based on cross-seasonal heat storage, comprising: monitoring and obtaining a plurality of historical redundant heat sequences of a plurality of coal mine waste heat sources, performing heat prediction in a preset time window to obtain a predicted redundant heat sequence; reading a heat consumption feature sequence and an associated heat consumption feature sequence of a to-be-heated area in the preset time window, performing heat demand prediction, and outputting a predicted demand heat quantity sequence; taking the predicted demand heat quantity sequence as a conditional constraint, taking the maximum capacity of the heat storage equipment as an equipment constraint, and taking the minimum heat loss as a target, performing heat storage scheme optimization, and outputting an optimal heat storage proportion sequence; and performing heat storage management and control in the preset time window according to the optimal heat storage proportion sequence.

[0014] The technical solutions provided in the application have at least the following technical effects or advantages: by achieving the technical target of constructing an intelligent regulation and control system based on multi-source waste heat prediction and optimized heat storage, the technical effects of improving waste heat utilization efficiency, reducing energy loss, realizing stable heat supply, and enhancing the overall energy efficiency management level of the coal mine are achieved.

[0015] The above description is only a summary of the technical solutions of the application. In order to more clearly understand the technical means of the application, the specific embodiments of the application can be implemented in accordance with the content of the description, and in order to make the above and other purposes, characteristics and advantages of the application more obvious and easy to understand, the following specific embodiments of the application are described. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the application, nor is it intended to limit the scope of the application. Other features of the application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only exemplary, and other drawings can be obtained by those skilled in the art without creating any creative labor on the basis of the provided drawings.

[0017] Figure 1 FIG. 1 is a structural schematic diagram of a coal mine multi-source waste heat intelligent utilization system based on cross-seasonal heat storage according to the application; Figure 2 FIG. 2 is a flow schematic diagram of a coal mine multi-source waste heat intelligent utilization method based on cross-seasonal heat storage according to the application.

[0018] Legend of the drawings: heat prediction module 1, heat demand prediction module 2, heat storage scheme optimization module 3, and heat storage management and control module 4. DETAILED DESCRIPTION

[0019] The present application provides a coal mine multi-source waste heat intelligent utilization system based on cross-seasonal heat storage and a method thereof, which solves the technical problem in the prior art that due to the lack of cross-seasonal regulation capability and waste heat dynamic prediction mechanism, waste heat cannot be effectively stored and allocated, further affecting the comprehensive utilization efficiency of coal mine waste heat resources and the stability of the heating system. The technical goal of constructing an intelligent regulation and control system based on multi-source waste heat prediction and optimized heat storage is achieved, and the technical effects of improving waste heat utilization efficiency, reducing energy loss, achieving stable heating, and enhancing the overall energy efficiency management level of the coal mine are achieved.

[0020] Below, the technical solutions in the present application will be described clearly and completely with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application. In addition, it should be noted that, for the convenience of description, only parts related to the present application are shown in the drawings, not all.

[0021] Embodiment one, please refer to the accompanying drawings Figure 1 The present application provides a coal mine multi-source waste heat intelligent utilization system based on cross-seasonal heat storage, specifically comprising: A heat prediction module 1 is configured to monitor and obtain a plurality of historical redundant heat sequences of a plurality of coal mine waste heat sources, perform heat prediction within a preset time window, and obtain a predicted redundant heat sequence.

[0022] Specifically, a plurality of historical redundant heat sequences of a plurality of coal mine waste heat sources are monitored and obtained, data is collected in real time by a sensor or a data acquisition system, and the coal mine waste heat sources are a plurality of waste heat energy sources generated in the production process of the coal mine, such as waste gas, waste water, or equipment waste heat, and surplus green electricity heat energy generated by distributed photovoltaic, wind power and other renewable energy through electric heating conversion; the plurality of historical redundant heat sequences refer to a plurality of groups of redundant heat data at a plurality of time points continuously collected from a plurality of waste heat sources within a certain time range in the past, and green electricity capacity fluctuation data is recorded synchronously, the redundant heat represents the remaining heat energy that is not directly utilized, and the historical redundant heat sequence contains the time variation trend. Then, heat prediction within a preset time window is performed, the historical data collected and a green electricity consumption demand prediction model are used to predict the redundant heat variation and the optimal green electricity consumption path that may occur within a future time period (such as 7 days or 30 days in the future) through a mathematical model or a machine learning algorithm. Finally, a predicted redundant heat sequence is obtained, that is, a time sequence formed by estimating the redundant heat at each time point in the future and a corresponding green electricity heat storage optimization scheme.

[0023] The heat supply demand prediction module 2 is used to read the heat use feature sequence and the associated heat use feature sequence of the heat supply area in the preset time window, perform heat supply demand prediction, and output the predicted demand heat supply sequence.

[0024] Specifically, reading the heat supply area refers to obtaining relevant data in a specific area that needs heat supply. The heat supply area can be a production workshop or a living area in a coal mine. The heat use feature sequence refers to time series data reflecting the heat use situation of the area, such as temperature change, equipment heat use frequency or heat use intensity in a time period, and green electricity consumption priority index. The associated heat use feature sequence is an additional influence factor sequence associated with the heat use feature, such as weather change, personnel activity rule or heat use situation of adjacent areas, and also includes power grid load state and distributed green electricity real-time capacity data. These data are collected within the preset time window, i.e. in a certain fixed time range in the future (such as the next 7 days or 15 days). Then, the heat supply demand prediction is performed by analyzing and modeling the heat use feature sequence and the associated heat use feature sequence, especially considering the time period feature of green electricity consumption, predicting the actual heat supply demand of the area in the time window, estimating the required heat energy at each time point in the future, and synchronously generating the optimal green electricity consumption scheduling scheme. Finally, the predicted demand heat supply sequence is output, i.e. a set of time series data representing the estimated heat supply at each time point in the future, and the recommended green electricity consumption proportion in each period is output.

[0025] The heat storage scheme optimization module 3 is used to perform heat storage scheme optimization with the predicted demand heat supply sequence as the condition constraint, the maximum capacity of the heat storage equipment as the equipment constraint, and the minimum heat loss as the target, and output the optimal heat storage proportion sequence.

[0026] Specifically, the predicted demand heat supply sequence is used as a conditional constraint, and the heat storage scheme must ensure that it can meet the predicted demand at each future time point, i.e., the stored and released heat must be sufficient to cover the demand. The predicted demand heat supply sequence represents the heat demand changes at different time points in the future period, and gives priority to the heat recovery of distributed green electricity. Then, the maximum capacity of the heat storage device is used as a device constraint, meaning that the capacity of the heat storage device during the storage process is limited and cannot exceed the maximum storage capacity of the device, such as a heat storage tank that can store up to 5000 kilojoules of heat. At the same time, the minimum heat loss is used as the target, which seeks to minimize the heat loss during the storage process under the premise of meeting the demand and device capacity constraints, improves energy efficiency, and maximizes green electricity consumption. Finally, the heat storage scheme is optimized, and through calculation and optimization methods, the heat storage proportion arrangement that meets the above constraints and minimizes heat loss is found, while optimizing the balance between seasonal heat storage and real-time green electricity consumption. The optimal heat storage proportion sequence represents the proportion of stored heat at different time points, i.e., the most suitable heat storage plan is given, providing a scientific basis for heat storage scheduling, especially increasing the heat storage proportion during the green electricity surplus period. With the increase of predicted demand or the change of device capacity, the optimal heat storage proportion sequence will also be adjusted accordingly to achieve the best balance between heat supply and energy efficiency and the demand for peak shaving and valley filling of the power grid.

[0027] The heat storage control module 4 is used to perform heat storage control within the preset time window according to the optimal heat storage proportion sequence.

[0028] Specifically, the optimal heat storage proportion sequence is used to arrange heat storage operations according to the most suitable heat storage proportion at different time points, and dynamically respond to the real-time power fluctuation of distributed green electricity to ensure the best match between heat supply demand and device capacity constraints and maximize green electricity consumption efficiency. The heat storage control within the preset time window means that the start, stop and heat storage allocation of the heat storage device are planned and controlled according to the proportion sequence during the entire future set period, such as a week or a month in the future, especially during the green electricity surplus period, to ensure that the heat storage system operates according to the predetermined scheme and realizes the peak shaving and valley filling function of the power grid. Heat storage control involves device state adjustment, heat flow control and energy efficiency management, as well as intelligent scheduling of green electricity waste heat, with the goal of achieving dynamic optimization of the heat storage process and efficient use of renewable energy. As time goes on, the heat storage control system continuously adjusts the operation and green electricity consumption demand according to the proportion sequence, achieving a balance between heat storage and release and optimal adjustment of power grid load, ensuring stable heat supply and minimum heat loss, while increasing the proportion of green electricity consumption.

[0029] Further, the application further comprises: a heat monitoring unit, configured to monitor and acquire redundant heat of a plurality of coal mine waste heat sources at K continuous time points in a historical time zone, to obtain a plurality of historical redundant heat sequences, wherein K is greater than or equal to 5; a node summation unit, configured to perform same node summation on the plurality of historical redundant heat sequences, to output a historical total redundant heat sequence; and a heat prediction unit, configured to perform heat prediction in a preset time window according to the historical total redundant heat sequence, to obtain a predicted redundant heat sequence.

[0030] Specifically, in the daily operation of a coal mine, various types of waste heat resources are generated, such as exhaust heat of a pressure fan, heat of a water pump motor, heat dissipation of underground equipment, etc. The redundant heat of a plurality of coal mine waste heat sources at K continuous time points in a historical time zone is monitored and acquired, and a sensor or a monitoring system is used to record the recoverable heat generated by a plurality of different waste heat sources at each time point (for example, every 1 hour or every 1 day) in a certain historical time period (for example, the past 30 days), to form a plurality of heat data sequences varying with time. These data sequences are referred to as historical redundant heat sequences. K represents the number of time points, and is set to be greater than or equal to 5, to ensure that the length of the sequence is sufficient for effective time series analysis.

[0031] After obtaining the historical redundant heat sequences of the plurality of waste heat sources, the historical redundant heat sequences are integrated. At each corresponding time point, the redundant heat values of all waste heat sources at this time are added to obtain a unified total heat value. For example, at the 1st time point, the redundant heat of waste heat source A is 100 kilojoules, the redundant heat of waste heat source B is 150 kilojoules, and the redundant heat of waste heat source C is 200 kilojoules, and the total redundant heat at this time point is 450 kilojoules. Similarly, a historical total redundant heat sequence is formed, representing the total available waste heat of the entire coal mine at each time point.

[0032] Then, the historical total redundant heat sequence is used to predict the future heat output, that is, to perform heat prediction in a preset time window according to the historical total redundant heat sequence. A deep learning algorithm such as a long short-term memory network (LSTM) is used to model the past heat change trend, and then the redundant heat that can be generated at each time point in a future period of time (for example, the next 7 days or 30 days) is calculated, to obtain a predicted redundant heat sequence.

[0033] Further, the application also includes: a sample obtaining channel for collecting sample total redundant heat sequence sets and obtaining historical total redundant heat sequences of different sample total redundant heat sequences in a historical time window, which are set as sample predicted redundant heat sequences to obtain sample predicted redundant heat sequence sets; a training channel for training a long short-term memory network by using the sample total redundant heat sequence sets and the sample predicted redundant heat sequence sets until convergence to obtain a redundant heat predictor; and a prediction channel for using the redundant heat predictor to analyze the historical total redundant heat sequences to obtain a predicted redundant heat sequence.

[0034] Specifically, when establishing a coal mine redundant heat prediction model, a large amount of historical heat data is collected as samples. Collecting sample total redundant heat sequence sets means extracting complete total redundant heat sequences from multiple historical time periods, such as total redundant heat data every day or every hour in the past several months. The samples represent the redundant heat output of the coal mine system under different climates, work intensities or equipment states. Then, a part of the time interval is selected from each sample as a historical input, for example, the heat data of the first 10 days of each sample is extracted, which is called a sample historical total redundant heat sequence, and the subsequent time period data for comparing the prediction accuracy is called a sample predicted redundant heat sequence, which together constitute a sample predicted redundant heat sequence set for training the model.

[0035] After the sample construction is completed, the long short-term memory network model is trained by using these data. The model is a special recurrent neural network suitable for processing and predicting time series data. The model training is performed by using the sample total redundant heat sequence sets and the sample predicted redundant heat sequence sets, taking the historical redundant heat as the input and the future redundant heat as the supervision target, so that the model learns the mapping relationship between the two. The training is repeated until the model prediction error no longer significantly decreases, at which time it is considered that the model has mastered the main rules of the data. After the training is completed, the redundant heat predictor is obtained, that is, a tool that can predict future heat output according to new historical data.

[0036] Finally, the actual scene is predicted by using the trained redundant heat predictor. The predictor is used to analyze the historical total redundant heat sequences, input the current or latest time period of coal mine heat data, let the model predict the redundant heat change in the subsequent time period, and output a complete predicted redundant heat sequence.

[0037] Further, the application also includes: a sample setting unit, configured to collect sample heat feature sequence sets and sample association heat feature sequence sets, and obtain historical heat supply sequences under different sample heat feature sequences and sample association heat feature sequences, as sample demand heat supply sequences, to obtain a sample demand heat supply sequence set; a supervision training unit, configured to take the sample heat feature sequence sets and the sample association heat feature sequence sets as inputs, take the sample demand heat supply sequence set as supervision, train a long short-term memory network to convergence, and obtain a heat demand predictor; and a demand prediction unit, configured to use the heat demand predictor to perform heat demand prediction according to the heat feature sequence and the association heat feature sequence, and output a predicted demand heat supply sequence.

[0038] Specifically, when performing coal mine heat demand prediction, heat-related data is collected. The sample heat feature sequence set refers to a series of variables directly related to heat in the historical period of the region to be heated, such as indoor and outdoor temperature, humidity, heating equipment operation time or power, etc.; and the sample association heat feature sequence set refers to factors that indirectly affect heat but are highly related, such as holiday markers, personnel activity density, electricity price changes or other seasonal indicators, etc. For each sample feature set, the actual heat supply under the condition needs to be obtained to form a historical heat supply sequence, which is defined as a sample demand heat supply sequence. After multiple sampling, a complete sample demand heat supply sequence set can be constructed for subsequent model training.

[0039] Next, in order to construct a system capable of automatically predicting heat demand, two feature sequence sets are taken as inputs, and a heat supply sequence set is taken as an output target to train a long short-term memory network model. The model can effectively capture the nonlinear relationship between the change of input variables over time and heat supply through the identification and memory ability of time series data. Convergence during training means that after multiple rounds of optimization, the prediction error tends to be stable and no longer significantly decreases, indicating that the main rules in the historical data have been mastered. At this time, the trained model becomes a heat demand predictor, which can predict future heat demand according to new input features.

[0040] Finally, in actual use, the current heat feature sequence and association feature sequence are input into the predictor for prediction analysis. That is, when the temperature, humidity, holiday arrangement and other information in the next period of time are known, the model can predict the specific heat demand in the period, and the output is a predicted demand heat supply sequence.

[0041] Further, the application further comprises: a first heat storage scheme obtaining unit, configured to randomly select a first heat storage ratio sequence in a preset heat storage ratio interval based on the preset time window, and set the first heat storage ratio sequence as a first heat storage scheme; a first heat storage heat sequence obtaining unit, configured to analyze a first heat storage heat sequence according to the predicted redundant heat sequence and the first heat storage ratio sequence; a judging unit, configured to judge whether the first heat storage heat sequence meets the predicted demand heat supply sequence and the maximum capacity, and if both are met, perform heat loss analysis on the first heat storage heat sequence, and output a heat loss value; and an iterative analysis unit, configured to continue iterative selection of heat storage schemes and iterative analysis of heat loss until a preset iteration number is reached, and output a heat storage ratio sequence corresponding to a minimum heat loss value, and set the heat storage ratio sequence as an optimal heat storage ratio sequence.

[0042] Specifically, in the coal mine multi-source waste heat system, in order to reasonably arrange the cross-season heat storage, a heat storage strategy is formulated in a fixed predicted time period, i.e., a preset time window. A set of heat storage ratio sequences is randomly selected in a preset heat storage ratio interval, such as between 0 and 1, which represents how much proportion of the redundant heat is used for heat storage at different time points. For example, 60% of the redundant heat is selected for heat storage on a certain day, which is referred to as the first heat storage scheme, and is the initial attempt scheme of the entire optimization process.

[0043] Subsequently, the redundant heat sequence obtained by the prediction model is combined with the heat storage ratio to perform calculation, and a heat storage heat sequence is obtained. The heat storage heat sequence refers to the storable heat actually allocated from the redundant heat at each time point according to the current heat storage ratio. For example, if the predicted redundant heat is 500 kilojoules on the first day and the heat storage ratio is 0.6, the corresponding heat storage heat is 300 kilojoules. The entire sequence covers the heat storage heat allocation at all time points in the entire time window.

[0044] Then, the heat storage heat sequence is subjected to constraint judgment to check whether two key conditions are met: one is whether it can cover the heat supply demand, i.e., the predicted heat supply sequence; and the other is whether it exceeds the maximum capacity of the heat storage device. If both conditions are met, the current heat storage heat sequence will be further subjected to heat loss analysis, i.e., the heat actually lost due to heat loss in the storage process is evaluated, and a heat loss value is output, which reflects the energy efficiency performance of the current scheme in use.

[0045] To find the best heat storage strategy, the above process will be repeated, that is, a new heat storage ratio sequence is randomly generated in the heat storage ratio interval, and the feasibility and heat loss analysis are performed on each heat storage heat sequence. Each generation and calculation is an iteration. After several rounds of calculation until the preset number of iterations is reached, the heat loss value of the heat storage ratio sequence with the smallest heat loss value is selected from all effective schemes as the optimal heat storage ratio sequence for the final heat storage execution.

[0046] Further, the application further comprises: a heat loss analysis channel for performing heat loss analysis based on the attribute characteristics of the heat storage device, outputting the heat loss ratio per unit time; a compensation channel for compensating the first heat storage heat sequence according to the heat loss ratio.

[0047] Specifically, the attribute characteristics of the heat storage device refer to the physical and performance parameters of the heat storage system itself, such as the thermal conductivity performance of the material of the device, the heat insulation effect, the thermal stability of the heat storage medium, and the structural design of the device. The attributes directly affect the heat loss during the heat storage process. Based on the characteristics, the heat loss ratio per unit time during the heat storage process is calculated according to the specific parameters and working conditions of the device, and the ratio is expressed as a percentage, such as 1% heat loss per hour. The heat loss ratio is an important indicator of heat storage efficiency, which can help judge the heat energy retention during the heat storage process.

[0048] Then, the first heat storage heat sequence is compensated according to the calculated heat loss ratio. Compensation refers to adjusting the stored heat so that the actual heat energy reflected by the heat storage heat sequence can make up for the part reduced due to heat loss during storage. If the stored heat at a certain time point is 1000 kilojoules, and the heat loss ratio per unit time is 2%, then the heat storage heat at that time point should be increased to 1020 kilojoules after compensation to ensure that the actual utilization can still achieve the original planned heat supply. Through compensation, the actual effective value of the heat storage heat can be more accurately reflected, providing more reliable data support for subsequent heat supply scheduling.

[0049] Further, the application further comprises: a loss heat output channel for performing heat loss analysis on a plurality of first heat storage heats in the first heat storage heat sequence based on the time interval of heat storage and heat, according to the heat loss ratio, outputting a plurality of loss heats; a summation channel for summing the plurality of loss heats to obtain a heat loss value.

[0050] Specifically, the time interval of the heat storage heat refers to the length of time between the storage of heat in the heat storage system and the use thereof, and the time interval is usually in units of hours or days, reflecting the length of time during which heat loss can occur during storage. According to the calculated heat loss proportion, the heat storage heat corresponding to each heat storage time point in the first heat storage heat sequence is separately analyzed for heat loss. The first heat storage heat sequence refers to the actual heat stored at each time point according to the heat storage proportion and the predicted redundant heat, and the multiple first heat storage heats represent the heat values stored at different time nodes. By multiplying the heat loss proportion by the heat stored at each time point, the corresponding loss heat in the time period is calculated, thereby outputting multiple loss heat data, which respectively reflect the heat loss at each heat storage time point.

[0051] Then, the multiple loss heats calculated at all time points are summed to obtain a total heat loss value. The heat loss value is the total amount of heat energy loss caused by factors such as equipment heat conduction, radiation, convection, etc. during the heat storage process, and is used to measure the energy efficiency loss during the entire heat storage period.

[0052] In summary, the coal mine multi-source waste heat intelligent utilization system based on cross-season heat storage provided in the present application has the following technical effects: by achieving the technical target of constructing an intelligent regulation and control system based on multi-source waste heat prediction and optimized heat storage, the technical effects of improving waste heat utilization efficiency, reducing energy loss, achieving stable heat supply, and enhancing the overall energy efficiency management level of the coal mine are achieved.

[0053] In the second embodiment, based on the same inventive concept as the coal mine multi-source waste heat intelligent utilization system based on cross-season heat storage in the preceding embodiments, the present application also provides a coal mine multi-source waste heat intelligent utilization method based on cross-season heat storage, please refer to the accompanying Figure 2 , including: S1: monitoring and obtaining a plurality of historical redundant heat sequences of a plurality of coal mine waste heat sources, performing heat prediction within a preset time window to obtain a predicted redundant heat sequence; S2: reading a heat use feature sequence and an associated heat use feature sequence of a heat supply area within the preset time window, performing heat demand prediction, and outputting a predicted demand heat supply sequence; S3: taking the predicted demand heat supply sequence as a condition constraint, taking the maximum capacity of the heat storage equipment as an equipment constraint, and taking the minimum heat loss as a target, performing heat storage scheme optimization, and outputting an optimal heat storage proportion sequence; S4: performing heat storage management and control within the preset time window according to the optimal heat storage proportion sequence.

[0054] Further, the coal mine multi-source waste heat intelligent utilization method based on cross-seasonal heat storage further comprises: monitoring and obtaining redundant heat of a plurality of coal mine waste heat sources at K continuous time points in a historical time zone, to obtain a plurality of historical redundant heat sequences, wherein K is greater than or equal to 5; performing same node summation on the plurality of historical redundant heat sequences to output a historical total redundant heat sequence; and performing heat prediction in a preset time window according to the historical total redundant heat sequence to obtain a predicted redundant heat sequence.

[0055] Further, the coal mine multi-source waste heat intelligent utilization method based on cross-seasonal heat storage further comprises: collecting a sample total redundant heat sequence set and obtaining historical total redundant heat sequences of different sample total redundant heat sequences in a historical time window, which are set as sample predicted redundant heat sequences to obtain a sample predicted redundant heat sequence set; training a long short-term memory network using the sample total redundant heat sequence set and the sample predicted redundant heat sequence set until convergence to obtain a redundant heat predictor; and using the redundant heat predictor to analyze the predicted redundant heat sequence according to the historical total redundant heat sequence.

[0056] Further, the coal mine multi-source waste heat intelligent utilization method based on cross-seasonal heat storage further comprises: collecting a sample total redundant heat sequence set and obtaining historical total redundant heat sequences of different sample total redundant heat sequences in a historical time window, which are set as sample predicted redundant heat sequences to obtain a sample predicted redundant heat sequence set; training a long short-term memory network using the sample total redundant heat sequence set and the sample predicted redundant heat sequence set until convergence to obtain a redundant heat predictor; and using the redundant heat predictor to analyze the predicted redundant heat sequence according to the historical total redundant heat sequence.

[0057] Further, the coal mine multi-source waste heat intelligent utilization method based on cross-seasonal heat storage further comprises: randomly selecting a first heat storage ratio sequence in a preset heat storage ratio interval based on the preset time window, which is set as a first heat storage scheme; analyzing a first heat storage heat sequence from the predicted redundant heat sequence and the first heat storage ratio sequence; determining whether the first heat storage heat sequence meets the predicted demand heat sequence and the maximum capacity, if both meet, performing heat loss analysis on the first heat storage heat sequence to output a heat loss value; continuing to select and analyze the heat loss of the heat storage scheme iteratively until a preset iteration number is reached, outputting a heat storage ratio sequence corresponding to a minimum heat loss value, which is set as an optimal heat storage ratio sequence.

[0058] Further, the coal mine multi-source waste heat intelligent utilization method based on cross-seasonal heat storage further comprises: performing heat loss analysis based on the attribute characteristics of the heat storage device, and outputting a heat loss proportion per unit time; and compensating the first heat storage heat sequence according to the heat loss proportion.

[0059] Further, the coal mine multi-source waste heat intelligent utilization method based on cross-seasonal heat storage further comprises: performing heat loss analysis on the plurality of first heat storage heats in the first heat storage heat sequence according to the heat loss proportion based on the time interval of heat storage and heat utilization, and outputting a plurality of loss heats; and summing the plurality of loss heats to obtain a heat loss value.

[0060] The embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The coal mine multi-source waste heat intelligent utilization system based on cross-seasonal heat storage in the first embodiment and the specific examples are also applicable to the coal mine multi-source waste heat intelligent utilization method based on cross-seasonal heat storage in the present embodiment. Through the foregoing detailed description of the coal mine multi-source waste heat intelligent utilization system based on cross-seasonal heat storage, those skilled in the art can clearly understand the coal mine multi-source waste heat intelligent utilization method based on cross-seasonal heat storage in the present embodiment. Therefore, for the sake of brevity of the specification, the coal mine multi-source waste heat intelligent utilization method based on cross-seasonal heat storage in the present embodiment will not be described in detail.

[0061] The above description of disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0062] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application also intends to include these modifications and variations.

Claims

1. A coal mine multi-source waste heat intelligent utilization system based on cross-season heat storage, characterized in that, The coal mine multi-source waste heat intelligent utilization system based on cross-season heat storage comprises: A heat prediction module is configured to monitor and acquire a plurality of historical redundant heat sequences of a plurality of coal mine waste heat sources, perform heat prediction in a preset time window, and obtain a predicted redundant heat sequence. A heat demand prediction module is configured to read a heat use feature sequence and an associated heat use feature sequence of a heat supply area in the preset time window, perform heat demand prediction, and output a predicted demand heat supply sequence. A heat storage scheme optimization module is configured to take the predicted demand heat supply sequence as a conditional constraint, take a maximum capacity of a heat storage device as a device constraint, take a minimum heat loss as a target, perform heat storage scheme optimization, and output an optimal heat storage ratio sequence. A heat storage management module is configured to perform heat storage management in the preset time window according to the optimal heat storage ratio sequence.

2. The coal mine multi-source waste heat intelligent utilization system based on cross-season heat storage according to claim 1, characterized in that, The heat prediction module comprises: A heat monitoring unit is configured to monitor and acquire redundant heat at K consecutive time points in a historical time zone of a plurality of coal mine waste heat sources, and obtain a plurality of historical redundant heat sequences, wherein K is greater than or equal to 5. A node summation unit is configured to perform same node summation on the plurality of historical redundant heat sequences, and output a historical total redundant heat sequence. A heat prediction unit is configured to perform heat prediction in a preset time window according to the historical total redundant heat sequence, and obtain a predicted redundant heat sequence.

3. The coal mine multi-source waste heat intelligent utilization system based on cross-season heat storage according to claim 2, characterized in that, The heat prediction unit comprises: A sample obtaining channel is configured to collect a sample total redundant heat sequence set, and obtain a historical total redundant heat sequence of different sample total redundant heat sequences in a historical time window, which is set as a sample predicted redundant heat sequence, and obtain a sample predicted redundant heat sequence set. A training channel is configured to train a long short-term memory network by using the sample total redundant heat sequence set and the sample predicted redundant heat sequence set until convergence, and obtain a redundant heat predictor. A prediction channel is configured to analyze a predicted redundant heat sequence according to the historical total redundant heat sequence by using the redundant heat predictor.

4. The coal mine multi-source waste heat intelligent utilization system based on cross-season heat storage according to claim 1, characterized in that, The heat demand prediction module comprises: A sample setting unit is configured to collect a sample heat use feature sequence set and a sample associated heat use feature sequence set, and obtain a historical heat supply sequence under different sample heat use feature sequences and sample associated heat use feature sequences, which is set as a sample demand heat supply sequence, and obtain a sample demand heat supply sequence set. A supervised training unit is configured to take the sample heat use feature sequence set and the sample associated heat use feature sequence set as input, take the sample demand heat supply sequence set as supervision, train a long short-term memory network until convergence, and obtain a heat demand predictor. A demand prediction unit is configured to perform heat demand prediction according to the heat use feature sequence and the associated heat use feature sequence by using the heat demand predictor, and output a predicted demand heat supply sequence.

5. The coal mine multi-source waste heat intelligent utilization system based on cross-season heat storage according to claim 1, characterized in that, The heat storage scheme optimization module comprises: A first heat storage scheme obtaining unit is configured to randomly select a first heat storage ratio sequence in a preset heat storage ratio interval based on the preset time window, and set the first heat storage ratio sequence as a first heat storage scheme. A first heat storage heat sequence obtaining unit is configured to analyze a first heat storage heat sequence according to the predicted redundant heat sequence and the first heat storage ratio sequence. A judgment unit is configured to judge whether the first heat storage heat sequence meets the predicted demand heat supply sequence and the maximum capacity. If both meet, the first heat storage heat sequence is subjected to heat loss analysis, and a heat loss value is output. An iterative analysis unit is configured to continue iterative selection of the heat storage scheme and iterative analysis of heat loss until a preset iteration number is reached, output a heat storage proportion sequence corresponding to a minimum heat loss value, and set the heat storage proportion sequence as an optimal heat storage proportion sequence.

6. The coal mine multi-source waste heat intelligent utilization system based on cross-season heat storage according to claim 5, characterized in that, The first heat storage heat sequence obtaining unit comprises: A heat loss analysis channel is configured to perform heat loss analysis based on the attribute characteristics of the heat storage device, and output a heat loss proportion per unit time. A compensation channel is configured to compensate the first heat storage heat sequence according to the heat loss proportion.

7. The coal mine multi-source waste heat intelligent utilization system based on cross-season heat storage according to claim 6, characterized in that, The judgment unit comprises: A loss heat output channel is configured to perform heat loss analysis on a plurality of first heat storage heats in the first heat storage heat sequence according to the heat loss proportion based on the time interval of heat storage and heat use, and output a plurality of loss heats. A summation channel is configured to sum the plurality of loss heats to obtain a heat loss value.

8. A coal mine multi-source waste heat intelligent utilization method based on cross-season heat storage, characterized in that, The coal mine multi-source waste heat intelligent utilization system based on cross-season heat storage according to any one of claims 1 to 7 comprises: A plurality of historical redundant heat sequences of a plurality of coal mine waste heat sources are monitored and obtained, heat prediction in a preset time window is performed, and a predicted redundant heat sequence is obtained. A heat use characteristic sequence and an associated heat use characteristic sequence of a to-be-heated area in the preset time window are read, heat demand prediction is performed, and a predicted demand heat supply sequence is output. The optimal heat storage proportion sequence is used to perform heat storage management and control in the preset time window. ​

Images