Heat supply device of photoelectric heating all-in-one machine

Abstract

The invention provides a heat supply device of a photoelectric heating all-in-one machine, and belongs to the technical field of heat supply control. According to the device, the maximum power generation power of a photovoltaic panel is automatically tracked through the photovoltaic adaptation module, the photovoltaic power supply heating module is directly driven, the photovoltaic power supply heating module is always kept near the maximum power point, and the photovoltaic power generation heat transfer efficiency is improved; through feedback of the temperature transmitting module, the intelligent control module controls the photovoltaic adaptation module and the mains supply control module at the same time, photovoltaic direct drive and mains supply can be automatically matched to assist in automatic conversion of heating control for complementary heat supply, the intelligent control module has a temperature compensation control technology, and when the photovoltaic heat supply temperature is lower than the lower limit, the intelligent control module controls the intelligent control module to supply heat. Mains supply is automatically switched on for temperature compensation; meanwhile, the photovoltaic adaptation module and the photovoltaic power supply heating module are independent systems, the commercial power control module and the commercial power supply heating module are independent systems, and the two systems are independent of each other, have no interference to a power grid and are more stable and safer in operation. The intelligent heat supply mode switching method and device can improve the intelligence of heat supply mode switching.

Description

Technical Field

[0001] The present application relates to the field of heating control technology, and in particular to a heating device for a photovoltaic heating integrated machine. Background Art

[0002] Modern electric boiler heating system technology has made great progress in recent years and has been widely used in various industries. At present, the conventional electric boiler direct heating system has problems such as inconvenient operation and lack of intelligence and accuracy in heating mode switching. In order to meet the needs of the current boiler heating system, an accurately controlled photovoltaic heating integrated heating device is urgently needed. Summary of the invention

[0003] The embodiment of the present application provides a photovoltaic heating integrated heating device to solve the problem of lack of intelligence and accuracy in heating mode switching.

[0004] The embodiment of the present application provides a photovoltaic heating integrated heating device, comprising: Photovoltaic power supply heating module, mains power supply heating module, intelligent control module, mains power control module, photovoltaic adapter module and temperature transmitter module; The photovoltaic power supply heating module is used to convert solar energy into photovoltaic electric energy through the photovoltaic panel when the intelligent control module sends a start command to the photovoltaic power supply heating module, and then use the photovoltaic electric energy to drive heating; The mains-powered heating module is used to generate mains power energy through the mains when the intelligent control module sends a start command to the mains-powered heating module, and then use the mains power energy for auxiliary heating; Intelligent control module, used to control the mains control module and the photovoltaic adapter module simultaneously; A mains power control module, used to control the mains power supply heating module; Photovoltaic adapter module, used to control the photovoltaic power supply heating module; The temperature transmitter module is used to monitor the indoor temperature or water temperature and feed back to the intelligent control module.

[0005] In an exemplary embodiment of the present application, the photovoltaic adapter module is specifically used for: The power generation power of the photovoltaic panel is determined according to the light intensity, and the power of the photovoltaic power supply heating module is controlled to adapt to the power generation power of the photovoltaic panel.

[0006] In an exemplary embodiment of the present application, the photovoltaic adapter module is further used for: The maximum power generation of the photovoltaic panel is tracked, and the power of the photovoltaic power supply heating module is controlled to be equal to the maximum power generation of the photovoltaic panel.

[0007] In an exemplary embodiment of the present application, the intelligent control module is specifically used for: Determine the photovoltaic heating temperature based on the light intensity; Control the switching of the photovoltaic power supply heating module / mains power supply heating module based on the photovoltaic heating temperature.

[0008] In an exemplary embodiment of the present application, the intelligent control module is further specifically configured to: In response to the photovoltaic heating temperature being less than the first temperature threshold, start the mains power supply heating module to perform temperature compensation on the mains power supply heating module.

[0009] In an exemplary embodiment of the present application, the intelligent control module is further specifically configured to: Input the target operating parameters and target environmental parameters of the photovoltaic heating integrated machine into the target random forest algorithm to obtain the target application scenario; Determine the target heating mode corresponding to the target application scenario from multiple standard heating modes, and the control parameters corresponding to the multiple standard heating modes for the photovoltaic heating integrated machine are different; control the photovoltaic heating integrated machine based on the target heating mode.

[0010] In an exemplary embodiment of the present application, the target heating mode is any one of photovoltaic heating, mains power supply heating, and photovoltaic-mains power supply collaborative heating; The intelligent control module is further specifically configured to: In response to the target heating mode being photovoltaic heating, control the photovoltaic heating integrated machine to receive the first heat energy circulation instruction; In response to the target heating mode being mains power supply heating, control the photovoltaic heating integrated machine to receive the second heat energy circulation instruction; In response to the target heating mode being photovoltaic-mains power supply collaborative heating, control the photovoltaic heating integrated machine to receive the third heat energy circulation instruction; The first heat energy circulation instruction, the second heat energy circulation instruction, and the third heat energy circulation instruction are all used to control the photovoltaic heating integrated machine to perform heat energy circulation work.

[0011] In an exemplary embodiment of the present application, a heating device for a photovoltaic heating integrated machine further includes: A safety protection module, configured to output a safety protection instruction in response to the target analysis result being abnormal; the safety protection instruction is used to control the protection device of the photovoltaic heating integrated machine; The target analysis result is the result after analyzing the target operating parameters of the photovoltaic heating integrated machine, and the target analysis result includes normal and abnormal.

[0012] In an exemplary embodiment of the present application, a heating device for a photovoltaic heating integrated machine further includes: A heating circulation pump, configured to control the flow direction of the heat energy circulation; The heating circulation pump is respectively connected to the photovoltaic power supply heating module and the mains power supply heating module.

[0013] In an exemplary embodiment of the present application, a heating device for an integrated photovoltaic heating machine further includes: A heating module for heating the user end; The heating module is connected to a heating circulation pump.

[0014] The beneficial effects of a heating device for an integrated photovoltaic heating machine provided by an embodiment of the present application are as follows: In the present application, the intelligent control module simultaneously controls the photovoltaic adaptation module and the mains control module, and can automatically match the control of photovoltaic direct drive and mains auxiliary heating of the heating module for automatic conversion for complementary heating, making the operation more convenient; and using renewable energy photovoltaic for heating can well save a large amount of energy; in special cases, electric auxiliary heating can also be used for heating work. The present application can solve the problem of lack of intelligence and accuracy in the switching of heating modes. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0016] Figure 1 is a schematic structural diagram of a heating device for an integrated photovoltaic heating machine provided by an embodiment of the present application; Figure 2 is a schematic overall structural diagram of a heating device for an integrated photovoltaic heating machine provided by an embodiment of the present application; Figure 3 is a schematic structural diagram of another heating device for an integrated photovoltaic heating machine provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to enable those skilled in the art to better understand this solution, the following will clearly describe the technical solutions in the embodiments of this solution with reference to the drawings in the embodiments of this solution. Obviously, the described embodiments are some, but not all, of the embodiments of this solution. Based on the embodiments in this solution, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this solution.

[0018] The terms "including" and any other variations in the specification and claims of this solution and the above drawings mean "including but not limited to", and are intended to cover non-exclusive inclusion, not limited to the examples listed in the text. In addition, terms such as "first" and "second" are used to distinguish different objects, rather than to describe a specific order.

[0019] The implementation of this application is described in detail below with reference to the specific drawings: Figure 1 This is a schematic diagram of the structure of a photovoltaic heating integrated heating device provided in an embodiment of the present application. Figure 1 The photovoltaic heating integrated heating device comprises: Photovoltaic power supply heating module 2, mains power supply heating module 3, intelligent control module 9, mains power control module 8, photovoltaic adaptation module 10 and temperature transmission module 11; The photovoltaic power supply and heating module 2 is used to convert solar energy into photovoltaic electric energy through the photovoltaic panel when the intelligent control module 9 sends a start instruction to the photovoltaic power supply and heating module 2, and then use the photovoltaic electric energy to drive heating; The mains-powered heating module 3 is used to generate mains power energy through the mains power when the intelligent control module 9 sends a start command to the mains-powered heating module 3, and then use the mains power energy for auxiliary heating; Intelligent control module 9, used to simultaneously control the mains control module 8 and the photovoltaic adaptation module 10; A mains power control module 8, used to control the mains power supply heating module 3; Photovoltaic adapter module 10, used to control the photovoltaic power supply heating module 2; The temperature transmitter module 11 is used to monitor the indoor temperature or water temperature and feed back the temperature to the intelligent control module 9 .

[0020] In this embodiment, the component for electrically heating water can be a semiconductor heater or a resistor heater. After power is turned on, the electrical energy is converted into thermal energy through the thermal effect of the current to heat the water.

[0021] The intelligent control module 9 can control the photovoltaic adapter module 10 and the mains control module 8 at the same time. The photovoltaic adapter module 10 can control the photovoltaic power supply heating module 2, and the mains control module 8 can control the mains power supply heating module 3. When the intelligent control module 9 issues a start command, the photovoltaic panel absorbs solar energy and converts it into direct current, which is processed by the photovoltaic adapter module 10 to drive the photovoltaic power supply heating module 2 to achieve photovoltaic power supply heating; when the intelligent control module 9 issues a command, the mains control module 8 is connected to the mains and transmits the mains power energy to the mains power supply heating module 3 for auxiliary heating to achieve mains power supply heating.

[0022] The temperature transmitter module 11 is used to monitor the indoor temperature or water temperature and feed back to the intelligent control module 9 , and the intelligent control module 9 controls the mains control module 8 and the photovoltaic adapter module 10 .

[0023] For example, when there is sufficient sunlight during the day, the intelligent control module 9 detects that the photovoltaic power supply conditions are met, sends instructions to the photovoltaic adapter module 10, and the photovoltaic power supply and heating module 2 is started. The photovoltaic panel generates electricity and drives the photovoltaic power supply and heating module 2 after adaptation, giving priority to the use of clean energy. When the light becomes weak or at night, the photovoltaic power is insufficient, and the intelligent control module 9 sends a signal to the mains control module 8 to start the mains power supply and heating module 3. The mains power is used for supplementary heating to maintain a stable water temperature. The intelligent control module 9 monitors and switches the entire process in real time to ensure uninterrupted heating.

[0024] It can be concluded from the above that the present application controls the photovoltaic adapter module 10 and the mains control module 8 simultaneously through the intelligent control module 9, and can automatically match the photovoltaic direct drive and the mains auxiliary control of the heating module to automatically switch to provide complementary heating, which is more convenient to operate; and the use of renewable energy photovoltaics for heating can save a lot of energy; in special cases, electric auxiliary heating can also be used for heating. The present application can solve the problem of lack of intelligence and accuracy in the switching of heating modes.

[0025] Figure 2 is a schematic diagram of the overall structure of the photovoltaic heating integrated heating device provided in the embodiment of the present application; Figure 2 The photovoltaic heating integrated machine heating device includes: a photovoltaic power source 1, a photovoltaic power supply heating module 2, a city power supply heating module 3, a stop valve 4, a heating module 5, a heating circulation pump 6, a water supply tank 7, a city power control module 8, an intelligent control module 9, a photovoltaic adaptation module 10 and a temperature transmitter module 11.

[0026] The present application uses the photovoltaic adapter module 10 to automatically adapt the photovoltaic power supply heating module 2 to the power generation power of the photovoltaic panel within a certain range; the photovoltaic adapter module 10 automatically tracks the maximum power generation power of the photovoltaic panel, controls the output, and directly drives the photovoltaic power supply heating module 2 to keep it near the maximum power point at all times, thereby improving the photovoltaic power generation efficiency; the photovoltaic adapter module 10 and the mains control module 8 are simultaneously controlled by the intelligent control module 9, the photovoltaic adapter module 10 can automatically match the photovoltaic direct drive, and the mains assists in the automatic conversion of the heating control of the mains power supply heating module 3 for complementary heating (the intelligent control module 9 has temperature compensation control technology, and when the photovoltaic heating temperature is lower than the lower limit, the mains compensation temperature is automatically input), timing and temperature, unattended, and remote control; the photovoltaic adapter module 10, the photovoltaic panel, and the photovoltaic power supply heating module 2 are an independent system, and the mains and the mains power supply heating module 3 are an independent system. The two systems are independent of each other, have no interference with the power grid, and run more smoothly and safely; in heating, the intelligent control module 9 and the photovoltaic panel adapter module 10, and the mains control module 8 have many protection functions such as overload protection and short circuit protection to ensure the safe operation of the system.

[0027] In actual operation, this application can form three heating modes: The first type: heat supply by the thermal energy of photovoltaic panels. When there is sufficient sunlight and the power generation power of the photovoltaic panels is relatively high, it is controlled by the photovoltaic adaptation module 10: As Figure 2 shown, the heat supply circulation pump 6 is started, and the direction is 4 (water in the system) → direction 5 (heat supply module 5) → direction 1 (water heating of the photovoltaic power supply heating module 2) → direction 3 → heat supply circulation pump 6, completing one cycle of heat energy work; The second type: heat supply by municipal electric energy. When it is night or there is no sunlight, it is controlled by the municipal power control module 8: As Figure 2 shown, the heat supply circulation pump 6 is started, and the direction is 4 (water in the system) → direction 5 (heat supply module 5) → direction 2 (water heating of the municipal power supply heating module 3) → direction 3 → heat supply circulation pump 6, completing one cycle of heat energy work; The third type: heat supply by photovoltaic panels and municipal power simultaneously. When the sunlight is insufficient and the power generation power of the photovoltaic panels is relatively low, the intelligent control module 9 controls both the photovoltaic adaptation module 10 and the municipal power control module 8: As Figure 2 shown, the heat supply circulation pump 6 is started, and the direction is 4 (water in the system) → direction 5 (heat supply module 5) → direction 1 / direction 2 (simultaneous water heating of the photovoltaic power supply and the municipal power heating system) → direction 3 → heat supply circulation pump 6, completing one cycle of heat energy work.

[0028] In an embodiment of the present application, referring to Figure 3 , the photovoltaic adaptation module 10 is specifically used for: Determining the power generation power of the photovoltaic panels according to the light intensity, and controlling the power of the photovoltaic power supply heating module 2 to adapt to the power generation power of the photovoltaic panels.

[0029] In this embodiment, the photovoltaic adaptation module 10 may be internally provided with a light sensor to detect the external light intensity in real time. At the same time, the characteristic curve data of the photovoltaic panels is stored inside the module. According to the light intensity value and in combination with the characteristic curve, the current power generation power of the photovoltaic panels can be calculated. The photovoltaic adaptation module 10 adjusts the working power of the photovoltaic power supply heating module 2 according to the calculated power generation power of the photovoltaic panels. The photovoltaic adaptation module 10 can make the power consumed by the photovoltaic power supply heating module 2 match the power generation power of the photovoltaic panels by adjusting the input voltage and current of the photovoltaic power supply heating module 2 or controlling the working duration of the photovoltaic power supply heating module 2, etc., to avoid the situation of excessive or insufficient power generation.

[0030] From the above, it can be concluded that the present application can realize the reasonable utilization of photovoltaic electric energy, avoid the situation of excessive or insufficient power generation, and ensure the stable operation of the photoelectric heating integrated machine heating device.

[0031] In an embodiment of the present application, referring toFigure 3 , the photovoltaic adaptation module 10 is specifically further configured to: Track the maximum power generation of the photovoltaic panel and control the power of the photovoltaic power supply heating module 2 to be equal to the maximum power generation of the photovoltaic panel.

[0032] In this embodiment, the photovoltaic adaptation module 10 continuously monitors parameters such as the output voltage and current of the photovoltaic panel, and uses the maximum power point tracking algorithm, such as the perturbation observation method, the conductance increment method, etc., to analyze and calculate these parameters, continuously adjust the working point of the photovoltaic panel, so that it is always in the working state corresponding to the maximum power generation, thereby determining the current maximum power generation value. After the photovoltaic adaptation module 10 determines the maximum power generation of the photovoltaic panel, it adjusts the working power of the photovoltaic power supply heating module 2 according to this power value. The photovoltaic adaptation module 10 controls the power supply circuit of the photovoltaic power supply heating module 2, such as adjusting the duty cycle of the pulse width modulation signal, or changing the power supply voltage, current, etc., so that the power consumed by the photovoltaic power supply heating module 2 is equal to the maximum power generation of the photovoltaic panel, realizing the full utilization of electric energy.

[0033] It can be concluded from the above that this embodiment makes the power of the photovoltaic power supply heating module 2 gradually approach and equal the maximum power generation of the photovoltaic panel, ensuring that the electric energy generated by the photovoltaic panel can be fully consumed by the photovoltaic power supply heating module 2, and avoiding the reduction of efficiency caused by electric energy waste or power mismatch.

[0034] In an embodiment of the present application, referring to Figure 3 , the intelligent control module 9 is specifically configured to: Determine the photovoltaic heating temperature based on the light intensity; Control the switching of the photovoltaic power supply heating module 2 / the municipal power supply heating module 3 based on the photovoltaic heating temperature.

[0035] In this embodiment, the intelligent control module 9 obtains the external light intensity data in real time through a light sensor. According to the pre-set corresponding relationship between the light intensity and the photovoltaic heating temperature (which can be summarized from a large number of experiments and actual operation data), the photovoltaic heating temperature under the current light intensity is calculated.

[0036] The intelligent control module 9 monitors the actual heating temperature in real time and compares it with the calculated photovoltaic heating temperature. If the actual heating temperature is lower than the photovoltaic heating temperature and the power generation of the photovoltaic panel is sufficient, the intelligent control module 9 will start the photovoltaic power supply heating module 2 for direct heating; if the power generation of the photovoltaic panel is insufficient, the municipal power supply heating module 3 will be started for auxiliary heating. If the actual heating temperature is higher than the photovoltaic heating temperature, the intelligent control module 9 will reduce the power of the photovoltaic power supply heating module 2 or turn off the municipal power supply heating module 3 to avoid overheating.

[0037] As can be seen from the above, this embodiment ensures that the heating temperature is always close to or reaches the calculated photovoltaic heating temperature, achieving an efficient and energy-saving heating effect.

[0038] In an embodiment of the present application, referring to Figure 3 , the intelligent control module 9 is specifically further configured to: In response to the photovoltaic heating temperature being less than the first temperature threshold, start the mains power heating module 3 to perform temperature compensation on the mains power heating module 3.

[0039] In this embodiment, the intelligent control module 9 real-time detects the photovoltaic heating temperature data and compares it with the preset first temperature threshold. Once it is found that the photovoltaic heating temperature is lower than the first temperature threshold, it indicates that relying solely on the photovoltaic power supply heating module 2 cannot meet the heating demand. At this time, it is necessary to use the mains power to supplement the heat. The intelligent control module 9 issues a start signal, and the mains power heating module 3 is connected to the mains power and starts to convert electrical energy into heat energy and transfer it to the mains power heating module 3, causing the heating temperature to gradually rise. During the heating process, the intelligent control module 9 will continuously monitor the photovoltaic heating temperature. When the temperature reaches or exceeds the first temperature threshold, the working state of the mains power heating module 3 can be adjusted according to the specific situation, such as reducing the power or stopping working, to avoid overheating.

[0040] As can be seen from the above, this embodiment can quickly respond and start the mains power heating module 3 to perform temperature compensation on the mains power heating module 3, effectively ensuring the stability of the heating temperature, avoiding heating interruption or too low temperature caused by insufficient light, and improving the user experience.

[0041] In an embodiment of the present application, referring to Figure 3 , the intelligent control module 9 is specifically further configured to: Input the target operating parameters and target environmental parameters of the photovoltaic heating integrated machine into the target random forest algorithm to obtain the target application scenario; Determine the target heating mode corresponding to the target application scenario from multiple standard heating modes, and the control parameters corresponding to the multiple standard heating modes for the photovoltaic heating integrated machine are different; control the photovoltaic heating integrated machine based on the target heating mode.

[0042] In this embodiment, the target random forest algorithm is obtained by iteratively optimizing the parameters of the random forest algorithm. The random forest algorithm is an ensemble learning algorithm based on decision trees. By constructing multiple decision trees and then synthesizing the prediction results of these decision trees for the final decision. The random forest algorithm has multiple adjustable parameters, and these parameters will affect the structure of the tree and the generalization ability of the model. For example, "n_estimators" represents the number of decision trees in the forest, and the more the number, the better the stability of the model; "max_depth" is the maximum depth of the decision tree, which restricts the growth of the tree to avoid overfitting.

[0043] Iterative optimization is a process of continuously adjusting the parameter values of the random forest algorithm through multiple repeated processes. Each adjustment is based on the result of the previous time, gradually searching for a set of parameters that can optimize the algorithm performance to achieve better prediction effects. The target random forest algorithm is the random forest algorithm model that performs best in the current task after iterative optimization, and its parameters are adjusted and optimized.

[0044] Specifically, in this embodiment, different random forest models are constructed by adjusting parameters, and the training data is used to let the model learn the rules in the data, and then the validation data is used to evaluate the performance of the model on unknown data. According to the evaluation results, continuously explore better parameter combinations and gradually approach the optimal solution.

[0045] In this embodiment, the parameters of the random forest algorithm are iteratively optimized. When the iterative optimization meets the first condition or the second condition, the target parameters are obtained; the target random forest algorithm is determined based on the target parameters; The first condition is that within the first number of iterations, the differences of the fitness function obtained after y consecutive adjacent iterations are all less than the first threshold; The second condition is that the number of iterations is equal to the second number of iterations; where the second number of iterations is greater than the first number of iterations.

[0046] In this embodiment, the target parameters are those that can make the random forest algorithm perform best in the current task after iterative optimization and meet the first condition or the second condition.

[0047] The first condition means that within the first number of iterations, the differences of the fitness function obtained after y consecutive adjacent iterations are all less than the first threshold. The fitness function is used to measure the performance of the random forest algorithm under the current parameters. The difference less than the first threshold indicates that the improvement of the algorithm performance is very small and close to convergence. The first number of iterations is a preset number of iterations used to determine whether the algorithm converges within this range. The first threshold is a preset small value used to determine whether the difference of the fitness function in adjacent iterations is small enough, that is, whether the algorithm has converged. Considering that only the difference of the fitness function in one adjacent iteration is less than the first threshold does not mean that the algorithm has converged stably, so the differences of the fitness function in multiple adjacent iterations are set to be less than the first threshold to ensure that the algorithm has converged stably. Therefore, the differences of the fitness function obtained after y consecutive adjacent iterations are set to be less than the first threshold.

[0048] The second condition means that the number of iterations is equal to the second number of iterations. The second number of iterations is a preset maximum number of iterations. When this number is reached, the iteration stops regardless of whether the algorithm has converged.

[0049] Specifically, the steps of this embodiment are as follows: Step 1, Initialize parameters: Select a set of initial parameter values for the random forest algorithm.

[0050] Step 2, Calculate the fitness function: Use the current parameters to construct a random forest model, train it on the training dataset, and then calculate the value of the fitness function on the validation dataset.

[0051] Step 3, Iteratively optimize parameters: Adjust the parameters according to a certain strategy (such as grid search, random search, genetic algorithm, etc.) to obtain a new parameter combination.

[0052] Step 4, Calculate the fitness function again: Use the new parameter combination to construct a random forest model, repeat Step 2, and obtain a new value of the fitness function.

[0053] Step 5, Determine whether the first condition is satisfied: Calculate the difference in the fitness function between adjacent iterations. If within the first number of iterations, the differences between consecutive adjacent iterations are all less than the first threshold, it is considered that the algorithm has converged, stop the iteration, and the current parameters are the target parameters.

[0054] Step 6, Determine whether the second condition is satisfied: If the first condition is not satisfied, check whether the number of iterations has reached the second number of iterations. If it has reached, stop the iteration, and the current parameters are the target parameters; otherwise, return to Step 3 to continue the iteration.

[0055] As can be seen from the above, this embodiment can efficiently and accurately obtain the target random forest algorithm and improve the stability of the target random forest algorithm.

[0056] In this embodiment, the parameters of the random forest algorithm are iteratively optimized to obtain the target parameters, including: Determine the fitness function of the genetic algorithm based on the dimensions of individuals in the genetic algorithm. The dimensions of individuals in the genetic algorithm include the maximum depth, the minimum number of samples, and the number of features; Determine the target crossover probability of the genetic algorithm based on the running speed of the genetic algorithm; Determine the target mutation probability of the genetic algorithm based on the accuracy of the genetic algorithm; Iteratively optimize the parameters of the random forest algorithm based on the fitness function, the target crossover probability, and the target mutation probability to obtain the target parameters.

[0057] In this embodiment, the genetic algorithm is an optimization algorithm that simulates natural selection and genetic mechanisms. By simulating the biological evolution process, it continuously iterates to find the optimal solution. In this embodiment, the genetic algorithm is used to optimize the parameters of the random forest algorithm.

[0058] In a genetic algorithm, an individual represents a possible solution, corresponding to a set of parameter combinations of the random forest algorithm. For example, an individual can be a vector containing the specific values of three parameters: maximum depth, minimum number of samples, and number of features. Dimension: refers to the number of parameters an individual contains. Here, the dimension of the individual includes the maximum depth, minimum number of samples, and number of features, that is, the individual is a three-dimensional vector, and each dimension corresponds to a parameter of the random forest algorithm.

[0059] The fitness function is used to evaluate the quality of each individual (i.e., a set of parameter combinations of the random forest algorithm) in the genetic algorithm. The higher the fitness value, the better the performance of the random forest algorithm corresponding to the individual in the current task.

[0060] The calculation formula of the fitness function is:

[0061]

[0062]

[0063] where, is the fitness value, is the accuracy value, is the weight of the accuracy, is the total number of samples, is the number of samples predicted correctly, is the energy utilization rate value, is the weight of the energy utilization rate, is the energy efficiency value, is the photovoltaic power supply, is the mains power supply, is the energy consumption value per unit of heat supply, is the total heat supply, is the maximum depth, is the penalty weight of the maximum depth, is the minimum number of samples, is the penalty weight of the minimum number of samples, is the number of features, is the penalty weight of the number of features, , , , .

[0064] The accuracy value can measure the accuracy of the random forest algorithm in predicting application scenarios; considers the proportion of photovoltaic power supply and mains power supply as well as the energy consumption situation, reflects the proportion of photovoltaic power supply in the total power supply, It can reflect the energy consumption per unit heat supply; and It can be set according to experience. When focusing on accuracy or energy utilization rate, the corresponding weight can be increased; is the complexity penalty term. By quantifying the complexity of the model, the fitness function is more inclined to select a model with lower complexity; Both are used to control the influence degree of each complexity factor on the fitness.

[0065] Specifically, this embodiment comprehensively considers the performance (accuracy and energy utilization rate) and complexity (maximum depth, minimum sample number, number of features) of the random forest algorithm. Partially encourages the genetic algorithm to improve the prediction ability of samples and energy utilization efficiency; Partially prevents the random forest algorithm from being overly complex, prevents overfitting, balances the complexity and generalization ability of the random forest algorithm, helps to find a better solution in terms of prediction accuracy, energy utilization and algorithm complexity, etc., and makes the random forest algorithm more robust and efficient in practical applications.

[0066] The crossover probability represents the probability of determining whether two individuals perform crossover in the crossover operation of the genetic algorithm. The crossover operation is a way to generate new individuals, and new parameter combinations are generated by exchanging part of the genes (parameters) of two individuals. The target crossover probability is a suitable crossover probability value determined according to the running speed of the genetic algorithm, and is used to control the frequency of the crossover operation during the iteration process.

[0067] In this embodiment, determining the target crossover probability of the genetic algorithm based on the running speed of the genetic algorithm includes: Determining a reference value of the crossover probability of the genetic algorithm; In response to the running speed being greater than or equal to the first speed threshold, adjusting the reference value of the crossover probability according to the first step length until the deviation between the first crossover probability and the reference value of the crossover probability is greater than the first difference value to obtain the target crossover probability; Wherein, the first crossover probability is the crossover probability obtained after each adjustment.

[0068] In this embodiment, the running speed is the speed of iterative search during the execution of the genetic algorithm, and can be measured by the number of iterations completed per unit time. The first speed threshold is a preset speed standard for determining whether the running speed of the genetic algorithm is fast enough.

[0069] The reference value of the crossover probability can be the probability of the crossover operation occurring when the genetic algorithm starts. The crossover operation is an operation that exchanges part of the genes of two parent individuals to generate offspring individuals. The first step size is a fixed value that is increased or decreased each time when adjusting the crossover probability. The first crossover probability is the crossover probability obtained after adjusting the reference value of the crossover probability. The first difference is a preset deviation value used to determine whether the adjustment of the crossover probability meets the requirements. The target crossover probability is the finally determined crossover probability applicable to the current running speed of the genetic algorithm.

[0070] Exemplarily, first, an initial probability value is set for the crossover operation of the genetic algorithm in this embodiment, which can be determined according to experience. For example, the reference value of the crossover probability can be set to 0.7.

[0071] Then, if the running speed of the genetic algorithm reaches or exceeds a preset first speed threshold, it indicates that the algorithm converges relatively fast, and it is necessary to increase the crossover probability to increase the diversity of the population and avoid the algorithm converging to the local optimal solution prematurely. The reference value of the crossover probability is adjusted according to the first step size. For example, the first step size is 0.05 and the reference value of the crossover probability is 0.7. When the running speed meets the condition, the first crossover probability after the first adjustment becomes 0.75.

[0072] Finally, the above adjustment process is continuously repeated until the deviation between the first crossover probability and the reference value of the crossover probability is greater than a preset first difference. For example, the first difference is set to 0.2. When the reference value of the crossover probability is 0.7, after multiple adjustments, when the crossover probability reaches 0.95, the deviation from the reference value of the crossover probability is 0.25, which is greater than the first difference of 0.2. At this time, 0.95 is the target crossover probability.

[0073] In response to the running speed being less than the first speed threshold, the reference value of the crossover probability is adjusted according to the second step size to obtain the second crossover probability until the deviation between the second crossover probability and the reference value of the crossover probability is greater than the second difference, and the target crossover probability is obtained; wherein, the second step size is less than the first step size.

[0074] In this embodiment, the second crossover probability is the crossover probability obtained by adjusting the reference value of the crossover probability according to the second step length when the running speed of the genetic algorithm is less than the first speed threshold. The second difference is another preset deviation value used to determine whether the adjustment of the crossover probability meets the requirements when the running speed is less than the first speed threshold. The second step length is a fixed value by which the crossover probability is increased or decreased each time when the running speed is less than the first speed threshold, and is less than the first step length. When the running speed of the genetic algorithm is less than the first speed threshold, a lower crossover probability can reduce the generation of new gene combinations, making the algorithm focus more on searching near the current existing better solutions, which helps to accelerate the convergence speed. In this case, it is expected to adjust the crossover probability relatively smoothly to avoid affecting the stability of the algorithm due to too large an adjustment amplitude, so the second step length is set to be less than the first step length.

[0075] The mutation probability represents the probability of determining whether a certain gene (parameter) of an individual undergoes mutation in the mutation operation of the genetic algorithm. The mutation operation can introduce new genes (parameters) and increase the diversity of the population. The target mutation probability is a suitable mutation probability value determined according to the accuracy requirements of the genetic algorithm, and is used to control the frequency of the mutation operation during the iteration process.

[0076] In this embodiment, determining the target mutation probability of the genetic algorithm based on the accuracy of the genetic algorithm includes: Determining the reference value of the mutation probability of the genetic algorithm; In response to the accuracy being greater than or equal to the first accuracy threshold, increasing the reference value of the mutation probability according to the third step length to obtain the target mutation probability; In response to the accuracy being less than the first accuracy threshold, decreasing the reference value of the mutation probability according to the fourth step length to obtain the target mutation probability.

[0077] In this embodiment, the reference value of the mutation probability can be the mutation probability set when the genetic algorithm starts running, which is the probability value of performing the mutation operation on individuals in the initial stage of the algorithm and provides a basis for subsequent adjustments. The accuracy is used to measure the accuracy of the result obtained by the genetic algorithm when solving problems. The first accuracy threshold is a preset accuracy standard used to determine whether the current accuracy of the genetic algorithm reaches a certain level and serves as a basis for determining the adjustment direction of the mutation probability.

[0078] The third step length is a fixed value of the reference value for increasing the mutation probability when the precision is greater than or equal to the first precision threshold. Increasing the mutation probability can enable the algorithm to further explore the new solution space on the basis of a higher precision and avoid falling into local optima. The fourth step length is a fixed value of the reference value for decreasing the mutation probability when the precision is less than the first precision threshold. Decreasing the mutation probability can reduce the randomness of the algorithm, make the algorithm more focused on searching near the current better solutions, and help improve the convergence speed. Among them, both the third step length and the fourth step length are set according to experience.

[0079] As can be seen from the above, this embodiment improves the effect and efficiency of parameter optimization. The fitness function is determined according to the individual dimension in the genetic algorithm, and key parameters such as the maximum depth, minimum sample number, and feature number are taken into consideration, so that the fitness function can accurately reflect the advantages and disadvantages of the random forest algorithm parameters and provide a clear direction for subsequent optimization. Secondly, the target crossover probability and the target mutation probability are determined respectively according to the running speed and precision of the genetic algorithm. This dynamic adjustment method helps to improve the search precision of the algorithm while ensuring the optimization speed and avoid falling into local optima. Finally, the random forest algorithm is iteratively optimized based on the above determined parameters, and the target parameters can be obtained quickly and accurately.

[0080] The photoelectric heating integrated machine is a device that combines photovoltaic power supply heating and municipal power supply heating for heating. The target operating parameters are some quantifiable indicators collected during the operation of the photoelectric heating integrated machine, which can reflect the working state of the device itself. For example, the power generation power of the photovoltaic panel reflects the photovoltaic power generation ability; the working current of the heating element reflects the heating intensity.

[0081] The target environmental parameters are relevant indicators of the external environment where the device is located, and these factors will affect the operation and heating effect of the photoelectric heating integrated machine. For example, the outdoor temperature directly affects the indoor heat loss and the heating demand of the device; the light intensity has an important impact on the power generation efficiency of the photovoltaic panel.

[0082] The target application scenario is an application scenario predicted by the target random forest algorithm according to the target operating parameters and the target environmental parameters. In this embodiment, the subsequent heating mode can be determined through the target application scenario, and the photoelectric heating integrated machine is controlled to heat according to the heating mode.

[0083] Specifically, the steps of this embodiment are as follows: First of all, this embodiment uses various sensors to collect the target operating parameters and the target environmental parameters of the photoelectric heating integrated machine. For example, a power sensor is installed on the photovoltaic panel to obtain the power generation power, and a temperature sensor and a light sensor are installed outdoors to measure the outdoor temperature and light intensity respectively.

[0084] Secondly, the data collected in this embodiment is cleaned and transformed to ensure data quality and consistency. This can include handling missing values, outliers, normalizing or standardizing the data, etc. For example, if there are individual abnormally large values in the collected light intensity data, which may be caused by sensor failures, they need to be corrected or removed; at the same time, to facilitate algorithm processing, all parameter values are normalized to the interval [0, 1].

[0085] Then, the preprocessed data is passed as input to the target random forest algorithm. The target random forest algorithm consists of multiple decision trees, and each decision tree processes and judges the input data.

[0086] Finally, each decision tree in the target random forest algorithm analyzes the input data according to its own rules and then gives a prediction result. In this embodiment, by integrating the prediction results of all decision trees (for example, using the majority voting method), the final target application scenario is obtained.

[0087] In this embodiment, each standard heating mode corresponds to a standard application scenario; Determining the target heating mode corresponding to the target application scenario from multiple standard heating modes includes: Calculating the matching degree between the target application scenario and each standard application scenario to obtain multiple first matching degrees; Comparing the multiple first matching degrees to obtain the target matching degree; Taking the standard heating mode corresponding to the standard application scenario corresponding to the target matching degree as the target heating mode.

[0088] In this embodiment, the first matching degree is a numerical value used to measure the similarity between the target application scenario and each standard application scenario. The higher the matching degree, the closer the target application scenario is to the standard application scenario.

[0089] The target matching degree is the highest matching degree selected from multiple first matching degrees, representing the best matching degree between the target application scenario and a certain standard application scenario.

[0090] In this embodiment, by comparing the similarity between the target application scenario and the standard application scenario, the most suitable heating mode for the current situation is selected. The corresponding relationship between the standard application scenario and the standard heating mode is preset based on the analysis of heating demand and energy utilization efficiency under different environments and operating conditions. By calculating the matching degree, the similarity between the target application scenario and each standard application scenario can be quantified, so as to find the most matching standard application scenario and then determine the target heating mode.

[0091] The parameter vector of the target application scenario is , and the parameter vector of the standard application scenario is , specifically, it can be the power of the photovoltaic panel, the indoor temperature, the outdoor light intensity, etc. The weight vector is , that is, a weight is assigned to each parameter, .

[0092] The calculation formula for the matching degree is:

[0093] Among them, is the matching degree, is the weight of the th parameter, is the parameter of the th target application scenario, is the parameter of the th standard application scenario; is the attenuation coefficient of the th parameter, which is used to control the attenuation speed of the matching degree with the parameter difference and can be set according to experience.

[0094] It can be concluded from the above that this embodiment realizes the intelligent and precise selection of the heating mode, can quickly select the most suitable heating mode according to actual needs, effectively improves the heating efficiency, reduces energy waste, and provides a more comfortable and energy-saving heating experience for users.

[0095] In an embodiment of the present application, referring to Figure 3 , the target heating mode is any one of photovoltaic heating, mains power heating, and photovoltaic-mains power collaborative heating; The intelligent control module 9 is specifically further configured to: In response to the target heating mode being photovoltaic heating, control the photovoltaic heating integrated machine to receive the first heat energy circulation instruction; In response to the target heating mode being mains power heating, control the photovoltaic heating integrated machine to receive the second heat energy circulation instruction; In response to the target heating mode being photovoltaic-mains power collaborative heating, control the photovoltaic heating integrated machine to receive the third heat energy circulation instruction; The first heat energy circulation instruction, the second heat energy circulation instruction, and the third heat energy circulation instruction are all used to control the photovoltaic heating integrated machine to perform heat energy circulation work.

[0096] In this embodiment, the determined target heating mode is obtained, such as photovoltaic heating, mains power heating, or photovoltaic-mains power collaborative heating. Photovoltaic heating is a clean heating mode that fully utilizes the electric energy converted by the photovoltaic panel from solar energy to drive the equipment for heating, relying on solar power supply. Mains power heating is to use the electric energy provided by the urban power grid to drive the equipment for heating, with stable power supply, and is suitable for scenarios where photovoltaic power supply is insufficient. Photovoltaic-mains power collaborative heating combines photovoltaic and mains power to jointly supply power to drive the equipment for heating, balancing energy utilization and heating demand.

[0097] Specifically, for photovoltaic heating, a first thermal energy circulation instruction is sent to the photovoltaic heating integrated machine. This instruction activates the photovoltaic power supply circuit, starts the heating element to operate with photovoltaic electric energy, and adjusts the circulation pump to make hot water circulate for heating according to the set path. For mains heating, a second thermal energy circulation instruction is sent. The device switches to mains power supply, and the controller adjusts the power of the heating element to adapt to the mains voltage, maintaining stable thermal energy output and circulation. For photovoltaic-mains collaborative heating, a third thermal energy circulation instruction is sent. The instruction first detects the photovoltaic power supply power. If it meets part of the heating demand (such as 50%), the remaining power gap is supplemented by the mains; at the same time, the circulation system is controlled to dynamically adjust the water flow rate according to the total heating power to ensure uniform heat energy delivery.

[0098] It can be concluded from the above that in this embodiment, the photovoltaic heating integrated machine is respectively controlled to receive corresponding thermal energy circulation instructions for different heating modes, ensuring that it can work as required in different heating scenarios. This control method realizes the intelligent operation of the photovoltaic heating integrated machine, can flexibly adapt to various energy supply situations, gives full play to the advantages of different heating modes, and improves energy utilization efficiency.

[0099] In an embodiment of the present application, referring to Figure 3 , a heating device for a photovoltaic heating integrated machine further includes: A safety protection module 101, which is used to output a safety protection instruction when the target analysis result is abnormal; the safety protection instruction is used to control the protection device of the photovoltaic heating integrated machine; The target analysis result is the result after analyzing the target operating parameters of the photovoltaic heating integrated machine, and the target analysis result includes normal and abnormal.

[0100] In this embodiment, the target analysis result is the conclusion obtained after analyzing the target operating parameters. For example, it can be obtained by analyzing through a trained neural network model, and it is divided into two situations: "normal" and "abnormal". "Normal" means that the operating parameters of the device are within the preset reasonable range, and the device is in a stable and safe operating state; "abnormal" means that some operating parameters exceed the normal range, indicating that there are problems such as device failures, potential dangers, or low operating efficiency.

[0101] When the target analysis result is abnormal, this embodiment issues an instruction for controlling the protection device of the photovoltaic heating integrated machine, and its purpose is to take corresponding measures to avoid further damage to the device, ensure personnel safety, and prevent safety accidents.

[0102] The protection device is a device equipped in the photovoltaic heating integrated machine for ensuring the safe operation of the device, such as an overload protection switch, a temperature sensor and a thermostat, a pressure safety valve, a leakage protector, etc. These devices will perform corresponding actions after receiving the safety protection instruction to protect the safety of the device and personnel.

[0103] Based on the real-time monitoring and analysis of the device operation status, this embodiment determines whether the device is operating normally by setting parameter ranges. When an abnormality occurs, a pre-designed safety protection mechanism is used to issue a safety protection instruction in a timely manner to control the action of the protection device, so as to ensure the safety of the device and personnel.

[0104] As can be seen from the above, by analyzing the target operating parameters, this embodiment can accurately obtain the normal or abnormal target analysis result. When the result is abnormal, this embodiment quickly responds and outputs a safety protection instruction to control the start of the protection device of the photoelectric heating integrated machine in a timely manner. This embodiment realizes the real-time monitoring and rapid protection of the device operation status, effectively prevents problems such as equipment damage and safety accidents caused by abnormal operation, and improves the safety and reliability of the operation of the photoelectric heating integrated machine.

[0105] In an embodiment of the present application, with reference to Figure 3 , a heat supply device of a photoelectric heating integrated machine further includes: A heat supply circulation pump 6 for controlling the flow direction of the heat energy cycle; The heat supply circulation pump 6 is respectively connected to the photovoltaic power supply heating module 2 and the municipal power supply heating module 3.

[0106] In this embodiment, the intelligent control module 9 selects the photovoltaic power supply heating module 2 or the municipal power supply heating module 3 to start according to conditions such as light intensity and indoor temperature, and activates the heat supply circulation pump 6 at the same time. The heat supply circulation pump 6 operates at a constant or variable frequency speed, and pushes the hot water output by the photovoltaic power supply heating module 2 or the municipal power supply heating module 3 to terminals such as radiators and floor heating coils through the main pipeline. After releasing the heat, the low-temperature return water returns to the photovoltaic power supply heating module 2 or the municipal power supply heating module 3 through the return pipeline to be reheated. If the photovoltaic power supply is insufficient and switches to the municipal power supply for assistance, the heat supply circulation pump 6 can adjust the speed or change the flow direction to ensure efficient heat energy distribution.

[0107] As can be seen from the above, this embodiment can control the flow direction of the heat energy cycle and improve the heat supply efficiency and temperature uniformity.

[0108] In an embodiment of the present application, with reference to Figure 3 , a heat supply device of a photoelectric heating integrated machine further includes: A heat supply module 5 for supplying heat to the user end; The heat supply module 5 is connected to the heat supply circulation pump 6.

[0109] In this embodiment, the heat supply module 5 is used as the terminal execution unit of the heating device to release the heat energy carried by the circulating hot water into the user end space, and may include radiators, floor heating coils, fan coils, etc., and improve the indoor temperature through heat conduction, convection and radiation methods.

[0110] The client is a place that needs to obtain heat energy, such as a family room, an office, a commercial space, etc., and is the service object of the heating module 5.

[0111] The photovoltaic or mains heating module heats up the water, and the circulation pump starts to establish the water flow power. The hot water is quickly transported to the heating module 5 through the pipeline, and the flow rate of the heating circulation pump 6 determines the heat transfer speed. The heating module 5 releases the heat energy to the client through heat exchange (such as the convection between the radiator surface and the air), reducing the temperature difference between indoors and outdoors. The cooled return water is pumped back to the photovoltaic-powered heating module 2 or the mains-powered heating module 3 by the heating circulation pump 6 to repeat the heating process.

[0112] It can be concluded from the above that this embodiment can efficiently convert the heat energy of hot water into the heat energy of the indoor environment.

[0113] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A photovoltaic heating integrated heating device, characterized in that: include: Photovoltaic power supply heating module, mains power supply heating module, intelligent control module, mains power control module, photovoltaic adapter module and temperature transmitter module; The photovoltaic power supply and heating module is used to convert solar energy into photovoltaic electric energy through the photovoltaic panel when the intelligent control module sends a start instruction to the photovoltaic power supply and heating module, and then use the photovoltaic electric energy to drive heating; The mains-powered heating module is used to generate mains electric energy through the mains when the intelligent control module sends a start-up instruction to the mains-powered heating module, and then use the mains electric energy for auxiliary heating; The intelligent control module is used to simultaneously control the mains control module and the photovoltaic adapter module; The mains power control module is used to control the mains power supply heating module; The photovoltaic adapter module is used to control the photovoltaic power supply heating module; The temperature transmitter module is used to monitor the indoor temperature or water temperature and feed back to the intelligent control module.

2. A photovoltaic heating integrated heating device as claimed in claim 1, characterized in that: The photovoltaic adapter module is specifically used for: The power generation power of the photovoltaic panel is determined according to the light intensity, and the power of the photovoltaic power supply heating module is controlled to adapt to the power generation power of the photovoltaic panel.

3. The photovoltaic heating integrated heating device according to claim 1, characterized in that: Photovoltaic adapter modules are also used for: The maximum power generation power of the photovoltaic panel is tracked, and the power of the photovoltaic power supply heating module is controlled to be equal to the maximum power generation power of the photovoltaic panel.

4. The photovoltaic heating integrated heating device according to claim 2, characterized in that: The intelligent control module is specifically used for: Determining a photovoltaic heating temperature based on the light intensity; The photovoltaic-powered heating module / the mains-powered heating module are switched based on the photovoltaic heating temperature control.

5. The photovoltaic heating integrated heating device according to claim 4, characterized in that: The intelligent control module is further used for: In response to the photovoltaic heating temperature being less than a first temperature threshold, the mains-powered heating module is started to perform temperature compensation on the mains-powered heating module.

6. The photovoltaic heating integrated heating device according to claim 1, characterized in that: The intelligent control module is further used for: The target operating parameters and target environmental parameters of the photovoltaic heating integrated machine are input into the target random forest algorithm to obtain the target application scenario; Determining a target heating mode corresponding to the target application scenario from a plurality of standard heating modes, wherein the plurality of standard heating modes correspond to different control parameters of the photovoltaic heating integrated machine; The photovoltaic heating integrated machine is controlled based on the target heating mode.

7. The photovoltaic heating integrated heating device according to claim 6, characterized in that: The target heating mode is any one of photovoltaic heating, mains heating and photovoltaic-mains coordinated heating; The intelligent control module is further used for: In response to the target heating mode being photovoltaic heating, controlling the photovoltaic heating integrated machine to receive a first heat energy circulation instruction; In response to the target heating mode being mains electricity heating, controlling the photovoltaic heating integrated machine to receive a second heat energy circulation instruction; In response to the target heating mode being photovoltaic-commercial power coordinated heating, controlling the photovoltaic heating integrated machine to receive a third heat energy circulation instruction; The first heat energy cycle instruction, the second heat energy cycle instruction and the third heat energy cycle instruction are all used to control the photovoltaic heating integrated machine to perform heat energy cycle work.

8. The photovoltaic heating integrated heating device according to claim 1, characterized in that: Also includes: A safety protection module, for outputting a safety protection instruction in response to an abnormal target analysis result; the safety protection instruction is used to control a protection device of the photovoltaic heating integrated machine; The target analysis result is the result of analyzing the target operating parameters of the photovoltaic heating integrated machine, and the target analysis result includes normal and abnormal.

9. The photovoltaic heating integrated heating device according to claim 1, characterized in that: Also includes: Heating circulation pump, used to control the flow direction of heat energy circulation; The heating circulation pump is connected to the photovoltaic power supply heating module and the mains power supply heating module respectively.

10. The photovoltaic heating integrated heating device according to claim 9, characterized in that: Also includes: A heating module, used for providing heating to the user end; The heating module is connected to the heating circulation pump.

Images