Intelligent heat supply adjusting system based on water source heat pump unit

Abstract

The invention discloses an intelligent heat supply adjusting system based on a water source heat pump unit, and relates to the technical field of intelligent heat supply. Installing an electromagnetic flowmeter; obtaining a return air inlet temperature sequence, a heat pump water outlet temperature sequence and a solution monitoring flow speed sequence; multi-dimensional time sequence correlation analysis is conducted on the return air inlet temperature sequence, the heat pump water outlet temperature sequence and the solution monitoring flow speed sequence, and the window return air inlet temperature, the window heat pump water outlet temperature and the window solution monitoring flow speed are obtained; and the target heat supply temperature is obtained, heat supply adjustment parameter analysis is conducted by combining the window air return opening temperature, the window heat pump water outlet temperature and the window solution monitoring flow speed, a target heat supply adjustment parameter set is obtained, and heat supply adjustment is conducted on the target water source heat pump unit through the target heat supply adjustment parameter set. The technical problems that in the prior art, the heat supply adjusting precision of the water source heat pump unit is low, and the real-time adjusting capacity is poor are solved, and the technical effect of efficient heat supply operation is achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent heating technology, and in particular to an intelligent heating regulation system based on a water source heat pump unit. Background Art

[0002] As the requirements for comfort and energy efficiency in the construction, industry and life fields continue to increase, water source heat pump units, as a highly efficient heating system, have been widely used in the heating and cooling fields. However, with the continuous expansion and complexity of building scale, the traditional water source heat pump unit heating regulation method faces more and more challenges. The existing heating regulation system has problems such as low regulation accuracy, slow response speed and insufficient energy efficiency, which makes it difficult to meet the needs of modern buildings and industrial systems for efficient, accurate and stable heating. Summary of the invention

[0003] The present application provides an intelligent heating regulation system based on a water source heat pump unit, which is used to solve the technical problems of low heating regulation accuracy and poor real-time regulation capability of the water source heat pump unit in the prior art.

[0004] In view of the above problems, the present application provides an intelligent heating regulation system based on a water source heat pump unit.

[0005] The present application provides an intelligent heating regulation system based on a water source heat pump unit, the system comprising:

[0006] A sensor deployment module is used to install temperature sensors at the return air inlet and heat pump outlet of the target water source heat pump unit, respectively, to obtain the return air inlet temperature sensor and the heat pump outlet temperature sensor; a flow meter deployment module is used to install an electromagnetic flow meter in the ethylene glycol solution flow pipeline; a data acquisition module is used to traverse the return air inlet temperature sensor, the heat pump outlet temperature sensor and the electromagnetic flow meter in a preset monitoring window to perform synchronous monitoring data acquisition, to obtain the return air inlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence; a correlation analysis module is used to perform multi-dimensional time series correlation analysis on the return air inlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence, to obtain the window return air inlet temperature, the window heat pump outlet temperature and the window solution monitoring flow rate; a heat supply regulation module is used to obtain the target heating temperature, perform heat supply regulation parameter analysis in combination with the window return air inlet temperature, the window heat pump outlet temperature and the window solution monitoring flow rate, to obtain the target heat supply regulation parameter group, and use the target heat supply regulation parameter group to perform heat supply regulation on the target water source heat pump unit.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The present application installs temperature sensors at the return air inlet and heat pump outlet of the target water source heat pump unit, respectively, to obtain the return air inlet temperature sensor and the heat pump outlet temperature sensor; installs an electromagnetic flowmeter in the ethylene glycol solution flow pipe; traverses the return air inlet temperature sensor, the heat pump outlet temperature sensor and the electromagnetic flowmeter in a preset monitoring window to perform synchronous monitoring data acquisition to obtain the return air inlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence; performs multi-dimensional time series correlation analysis on the return air inlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence to obtain the window return air inlet temperature, the window heat pump outlet temperature and the window solution monitoring flow rate; obtains the target heating temperature, performs heating regulation parameter analysis in combination with the window return air inlet temperature, the window heat pump outlet temperature and the window solution monitoring flow rate, obtains the target heating regulation parameter group, and uses the target heating regulation parameter group to perform heating regulation on the target water source heat pump unit. The present invention solves the technical problems of low heat regulation accuracy and poor real-time regulation capability of water source heat pump units in the prior art. Temperature sensors are installed at the return air inlet and the water outlet of the heat pump of the target water source heat pump unit, and an electromagnetic flowmeter is installed in the flow pipe of the ethylene glycol solution. The return air inlet temperature, the water outlet temperature of the heat pump and the solution flow rate are synchronously monitored. Multi-dimensional time series correlation analysis is used to combine the monitoring data and the target heating temperature to perform heat regulation parameter analysis, generate a target heating regulation parameter group, and regulate the water source heat pump unit to achieve the technical effect of efficient heating operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic diagram of the structure of an intelligent heating regulation system based on a water source heat pump unit provided in an embodiment of the present application;

[0011] Figure 2 A flow chart of a heating regulation module in an intelligent heating regulation system based on a water source heat pump unit provided in an embodiment of the present application.

[0012] Explanation of the reference numerals: sensor arrangement module 11 , flow meter arrangement module 12 , data acquisition module 13 , correlation analysis module 14 , heating regulation module 15 . DETAILED DESCRIPTION

[0013] The present application provides an intelligent heating regulation system based on a water source heat pump unit, aiming to solve the technical problems of low heating regulation accuracy and poor real-time regulation capability of the water source heat pump unit in the prior art. By installing temperature sensors at the return air inlet and the heat pump outlet of the target water source heat pump unit, and installing an electromagnetic flowmeter in the ethylene glycol solution flow pipeline, the return air inlet temperature, the heat pump outlet temperature and the solution flow rate are synchronously monitored, and multi-dimensional time series correlation analysis is used to combine the monitoring data and the target heating temperature to perform heating regulation parameter analysis, generate a target heating regulation parameter group, and regulate the water source heat pump unit to achieve the technical effect of efficient heating operation.

[0014] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0015] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0016] Examples, such as Figure 1 As shown, the embodiment of the present application provides an intelligent heating regulation system based on a water source heat pump unit, the system comprising:

[0017] The sensor arrangement module 11 is used to install temperature sensors at the return air inlet and the heat pump outlet of the target water source heat pump unit, respectively, to obtain the return air inlet temperature sensor and the heat pump outlet temperature sensor.

[0018] In the embodiment of the present application, the sensor layout module 11 obtains the return air outlet temperature sensor and the heat pump outlet temperature sensor by installing temperature sensors at the preset positions of the return air outlet and the heat pump outlet of the target water source heat pump unit. Through this layout, the temperature data of the return air outlet and the heat pump outlet are obtained in real time, providing basic data support for subsequent heat pump operation monitoring, efficiency analysis and heating regulation. Among them, the return air outlet temperature sensor is used to measure the temperature of the heat pump return air outlet. The heat pump outlet temperature sensor is used to measure the temperature of the heat pump outlet.

[0019] The flow meter layout module 12 is used to install an electromagnetic flow meter in the ethylene glycol solution flow pipeline.

[0020] In the embodiment of the present application, the flow meter layout module 12 installs the electromagnetic flow meter at a preset position of the ethylene glycol solution flow pipeline.

[0021] The data acquisition module 13 is used to traverse the return air temperature sensor, the heat pump outlet temperature sensor and the electromagnetic flowmeter in a preset monitoring window to perform synchronous monitoring data acquisition to obtain the return air temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence.

[0022] In an embodiment of the present application, the data acquisition module 13 synchronously collects data from the return air outlet temperature sensor, the heat pump outlet temperature sensor and the electromagnetic flowmeter within a preset monitoring window. Specifically, a predetermined preset monitoring window is first obtained, which represents the time interval for data acquisition. During this time period, the return air outlet, the heat pump outlet and the solution flow rate are synchronously monitored to ensure the timeliness and consistency of the data. Within the time range of the monitoring window, the data acquisition module 13 simultaneously traverses the return air outlet temperature sensor, the heat pump outlet temperature sensor and the electromagnetic flowmeter to synchronously monitor data acquisition. The return air outlet temperature sensor is used to obtain the temperature data of the fluid at the return air outlet; the heat pump outlet temperature sensor is used to obtain the temperature data of the fluid at the heat pump outlet; the electromagnetic flowmeter is used to monitor the flow rate of the ethylene glycol solution. Through the synchronous acquisition process, the return air outlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence are obtained. The return air outlet temperature sequence records the sequence data of the return air outlet temperature changing with time; the heat pump outlet temperature sequence records the sequence data of the heat pump outlet temperature changing with time; the solution monitoring flow rate sequence records the sequence data of the ethylene glycol solution flow rate changing with time.

[0023] The correlation analysis module 14 is used to perform multi-dimensional time series correlation analysis on the return air temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence to obtain the window return air temperature, the window heat pump outlet temperature and the window solution monitoring flow rate.

[0024] In the embodiment of the present application, the correlation analysis module 14 obtains the window return air temperature, the window heat pump outlet temperature and the window solution monitoring flow rate by performing multi-dimensional time series correlation analysis on the return air temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence. Specifically, firstly, the first data, i.e., the first return air temperature, the first heat pump outlet temperature and the first solution monitoring flow rate, are extracted from each sequence, and these data are used as components to construct the first multi-dimensional vector; then the second data is extracted to construct the second multi-dimensional vector. Next, the first multi-dimensional vector and the second multi-dimensional vector are subjected to multi-dimensional time series correlation analysis to obtain the first time series correlation vector. Subsequently, the third data is extracted to construct the third multi-dimensional vector, and the first time series correlation vector is subjected to correlation analysis with the third multi-dimensional vector to obtain the second time series correlation vector. This process continues until the data at all time points are subjected to correlation analysis, and finally the N-1th time series correlation vector is obtained. Through the final time series correlation vector, the window return air temperature, the window heat pump outlet temperature and the window solution monitoring flow rate are obtained.

[0025] Furthermore, in the system provided in the embodiment of the application, the association analysis module 14 is also used for:

[0026] The first return air temperature, the first heat pump outlet temperature and the first solution monitoring flow rate that are in the first position in the return air temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence are extracted respectively, and the first return air temperature, the first heat pump outlet temperature and the first solution monitoring flow rate are used as components to construct a first multidimensional vector; the second return air temperature, the second heat pump outlet temperature and the second solution monitoring flow rate that are in the second position in the return air temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence are extracted respectively, and the second return air temperature, the second heat pump outlet temperature and the second solution monitoring flow rate are used as components to construct a second multidimensional vector; a multidimensional time series correlation analysis is performed on the first multidimensional vector and the second multidimensional vector to obtain a first time series correlation vector; and the first multidimensional vector is extracted respectively. Take the third return air outlet temperature, the third heat pump outlet temperature and the third solution monitoring flow rate in the third position in the return air outlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence, and use the third return air outlet temperature, the third heat pump outlet temperature and the third solution monitoring flow rate as components respectively to construct a third multidimensional vector; perform multidimensional time series correlation analysis on the first time series association vector and the third multidimensional vector to obtain a second time series association vector; and so on, until the N-1th time series association vector is obtained, and obtain the window return air outlet temperature, the window heat pump outlet temperature and the window solution monitoring flow rate according to the N-1th time series association vector, wherein N is the amount of data in each sequence in the return air outlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence, and N is an integer greater than or equal to 1.

[0027] In the embodiment of the present application, firstly, the data at the first position, i.e., the first return air temperature, the first heat pump outlet temperature, and the first solution monitoring flow rate, are extracted from the return air temperature sequence, the heat pump outlet temperature sequence, and the solution monitoring flow rate sequence, and these data are used as components to construct a first multidimensional vector. Then, the second return air temperature, the second heat pump outlet temperature, and the second solution monitoring flow rate at the second position are extracted in sequence, and a second multidimensional vector is also constructed.

[0028] Next, a multidimensional time series correlation analysis is performed on the first multidimensional vector and the second multidimensional vector. Specifically, the component mapping similarity is calculated for the first multidimensional vector and the second multidimensional vector to obtain a first component mapping similarity set. This step is performed by calculating the similarity of each component between the two vectors. The obtained first component mapping similarity set is then normalized to standardize the similarity values ​​of different components so that they have a unified dimension. Based on the normalized similarity set, a first multidimensional time series correlation matrix is ​​constructed, which reflects the correlation and change pattern between the first and second moments. Then, the constructed first multidimensional time series correlation matrix is ​​convolved with the second multidimensional vector. Through convolution, the correlation information of the first and second moments is combined with the vector of the third moment, thereby extracting deeper time series features and finally obtaining the first time series correlation vector.

[0029] Next, the third return air temperature, the third heat pump outlet temperature and the third solution monitoring flow rate located in the third position are extracted to construct the third multidimensional vector. Subsequently, a multidimensional time series correlation analysis is performed on the first time series correlation vector and the third multidimensional vector to obtain the second time series correlation vector. This process is the same as the previous analysis steps, and new time series correlation information is extracted through inner product mapping, normalization, time series correlation matrix construction and convolution operations. This process is analogous to the above, and the data of subsequent time points (such as the fourth position, the fifth position, etc.) are continued to be extracted, the corresponding multidimensional vector is constructed, and the correlation analysis is performed with the previous time series correlation vector to gradually obtain the N-1th time series correlation vector.

[0030] Finally, the window return air temperature, window heat pump outlet temperature and window solution monitoring flow rate are determined according to the N-1th time series association vector. That is, the window return air temperature, window heat pump outlet temperature and window solution monitoring flow rate are three data in the N-1th time series association vector. Among them, N is the data amount of each sequence in the return air temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence, and N is an integer greater than or equal to 1.

[0031] Furthermore, in the system provided in the embodiment of the application, the association analysis module 14 is also used for:

[0032] Calculate component mapping similarity of the first multidimensional vector and the second multidimensional vector to obtain a first component mapping similarity set; normalize the first component mapping similarity set, and construct a first multidimensional time series association matrix based on the processing result; perform a convolution operation on the first multidimensional time series association matrix and the second multidimensional vector to obtain the first time series association vector.

[0033] In the embodiment of the present application, the component mapping similarity calculation is first performed on the first multidimensional vector and the second multidimensional vector. Specifically, the first component mapping similarity set is obtained by calculating the reciprocal of the difference between the corresponding components in the first multidimensional vector and the second multidimensional vector. For each pair of components in the first multidimensional vector and the second multidimensional vector, the difference between them is calculated and the reciprocal is taken, and their similarity is quantified in this way. The reciprocal is used to emphasize that the difference is smaller when the similarity is higher, and vice versa. In this way, the first component mapping similarity set is obtained.

[0034] Next, the first component mapping similarity set is normalized, and the similarity value is mapped to a fixed range (e.g., [0, 1]) by using minimum-maximum normalization. Based on the normalized similarity set, a first multidimensional temporal association matrix is ​​constructed. This matrix organizes the similarity information of each pair of components into a matrix structure, and each item in the matrix represents the association between the first multidimensional vector and the second multidimensional vector at a certain moment.

[0035] Finally, a convolution operation is used to perform convolution calculation on the first multidimensional time series association matrix and the second multidimensional vector. Specifically, the first multidimensional time series association matrix and the second multidimensional vector are input into a pre-trained convolution model, and the first time series association vector is obtained through the processing of the convolution model. In order to train the convolution model, a set of sample multidimensional time series association matrices, a set of sample multidimensional vectors, and a corresponding set of sample time series association vectors are obtained from a historical database, and the convolutional neural network is used for training to obtain the convolution model.

[0036] The heating regulation module 15 is used to obtain the target heating temperature, analyze the heating regulation parameters in combination with the window return air temperature, the window heat pump outlet temperature and the window solution monitoring flow rate, obtain the target heating regulation parameter group, and use the target heating regulation parameter group to regulate the heating of the target water source heat pump unit.

[0037] In the embodiment of the present application, the heating regulation module 15 first obtains the predetermined target heating temperature, then pre-trains the heating regulation parameter identification network layer, and then uses the trained network to identify the target heating temperature, the window return air outlet temperature, the window heat pump outlet temperature and the window solution monitoring flow rate to obtain an initial heating regulation parameter group. Then, the initial parameter group is randomly adjusted multiple times according to the preset adjustment range to obtain a set of adjusted heating regulation parameter groups. Finally, this set is directional optimized to obtain the target heating regulation parameter group, and is applied to the target water source heat pump unit for heating regulation.

[0038] Further, such as Figure 2 As shown, in the system provided by the application embodiment, the heat supply adjustment module 15 is also used for:

[0039] Pre-training a heating regulation parameter identification network layer; using the heating regulation parameter identification network layer to identify the target heating temperature, window return air outlet temperature, window heat pump outlet temperature and window solution monitoring flow rate to obtain an initial heating regulation parameter group; performing multiple random adjustments on the initial heating regulation parameter group according to a preset adjustment range to obtain an adjusted heating regulation parameter group set; performing directional optimization on the adjusted heating regulation parameter group set to obtain the target heating regulation parameter group.

[0040] In the embodiment of the present application, the heating regulation parameter identification network layer is first pre-trained. Specifically, the sample target heating temperature set, the sample window return air outlet temperature set, the sample window heat pump outlet temperature set, the sample window solution monitoring flow rate set and the corresponding sample initial heating regulation parameter set are obtained from the historical database. The sample target heating temperature set, the sample window return air outlet temperature set, the sample window heat pump outlet temperature set and the sample window solution monitoring flow rate set are used as input samples, and the sample initial heating regulation parameter set is used as an output sample. The heating regulation parameter identification network layer is obtained by training using a support vector machine.

[0041] Next, the target heating temperature, window return air outlet temperature, window heat pump outlet temperature and window solution monitoring flow rate are input into the heating regulation parameter identification network layer for identification to obtain the initial heating regulation parameter group.

[0042] Then, the initial heating adjustment parameter group is randomly adjusted multiple times according to the preset adjustment range. Each adjustment is made according to the preset range to explore the possible adjustment space. Through this random adjustment method, a set of adjusted heating adjustment parameter groups is generated.

[0043] Next, directional optimization is performed. First, the set of heat adjustment parameter groups is traversed, and the adjustment feasibility coefficient of each adjusted parameter group is analyzed to obtain a set of adjustment feasibility coefficients, in which each adjustment scheme corresponds to a feasibility coefficient, indicating the effectiveness and superiority of the scheme. Then, the adjustment parameter group corresponding to the maximum value in the adjustment feasibility coefficient set is extracted and used as the direction adjustment heat adjustment parameter group. Based on the direction adjustment heat adjustment parameter group, the remaining adjustment parameter groups are directional adjusted, that is, the optimization direction of the direction adjustment heat adjustment parameter group is fine-tuned to generate a set of follow-up adjustment heat adjustment parameter groups. Subsequently, the adjustment feasibility coefficient of the follow-up adjustment heat adjustment parameter group set is analyzed to obtain a set of follow-up adjustment feasibility coefficients. If there is a value greater than or equal to the feasibility coefficient corresponding to the direction adjustment heat adjustment parameter group in the follow-up adjustment feasibility coefficient set, the parameter group corresponding to the maximum value in the follow-up adjustment feasibility coefficient set is used as a new direction adjustment heat adjustment parameter group. This new parameter group will continue to be optimized until the preset number of optimizations is met. Finally, when the preset number of optimizations is completed, the last updated direction adjustment heat adjustment parameter group is the target heat adjustment parameter group.

[0044] Furthermore, in the system provided in the embodiment of the application, the heat supply adjustment module 15 is also used for:

[0045] The initial heating regulation parameters in the initial heating regulation parameter group are randomly adjusted multiple times according to preset adjustment ranges to obtain an initial adjusted heating regulation parameter group set; the initial adjusted heating regulation parameter group set is discretely authenticated, and if the discrete authentication passes, the initial adjusted heating regulation parameter group set is used as the adjusted heating regulation parameter group set.

[0046] In the embodiment of the present application, the initial heating adjustment parameters in the initial heating adjustment parameter group are first randomly adjusted multiple times according to the preset adjustment range by the Monte Carlo method. Specifically, the Monte Carlo method is used to randomly select values ​​within the preset adjustment range of each adjustment parameter to explore various possibilities in the adjustment space. The parameter values ​​after each adjustment are recorded, and after multiple random adjustments (such as 3 times), the adjusted parameter group is used as the initial adjustment heating adjustment parameter group set.

[0047] Next, the initial adjustment heating adjustment parameter group set is subjected to discrete authentication. The Euclidean distance between each adjustment parameter group in the initial adjustment heating adjustment parameter group set is calculated by using the Euclidean distance, and the mean of these distances is calculated. The calculated mean is compared with the preset distance. If the calculated mean of the Euclidean distance is greater than the preset distance, the discrete authentication is considered to have passed, and the initial adjustment heating adjustment parameter group set is used as the adjustment heating adjustment parameter group set.

[0048] If it fails, random adjustment will continue until the discreteness certification of the initial adjustment heating regulation parameter group set is passed, and the initial adjustment heating regulation parameter group set will be used as the adjustment heating regulation parameter group set.

[0049] Furthermore, in the system provided in the embodiment of the application, the heat supply adjustment module 15 is also used for:

[0050] Traverse the set of adjustment heating parameter groups to perform adjustment feasibility coefficient analysis to obtain an adjustment feasibility coefficient set, wherein the adjustment heating parameter groups correspond to the adjustment feasibility coefficients one-to-one; extract the adjustment heating parameter group corresponding to the maximum value in the adjustment feasibility coefficient set, and use it as the direction adjustment heating parameter group; take the direction adjustment heating parameter group as the optimization direction, and perform directional adjustment on the remaining adjustment heating parameter groups in the adjustment heating parameter group set according to a preset adjustment range to obtain a follow-up adjustment heating parameter group set; traverse the follow-up adjustment heating parameter group set to perform adjustment feasibility coefficient analysis to obtain a follow-up adjustment feasibility coefficient set; determine whether there is a follow-up adjustment feasibility coefficient greater than or equal to the adjustment feasibility coefficient corresponding to the direction adjustment heating parameter group in the follow-up adjustment feasibility coefficient set, and if so, use the follow-up adjustment heating parameter group corresponding to the maximum value in the follow-up adjustment feasibility coefficient set as the new direction adjustment heating parameter group, and continue to perform directional optimization until the preset number of optimization times is met, and use the last updated direction adjustment heating parameter group as the target heating parameter group.

[0051] In an embodiment of the present application, the set of adjustment parameters for adjusting the heating supply is first traversed to perform adjustment feasibility coefficient analysis. For each adjustment parameter (such as compressor frequency, circulating water flow rate, etc.) in each adjustment parameter group for adjusting the heating supply, an adjustment feasibility coefficient analysis is performed based on historical data. Specifically, the number of times each parameter appears in the historical data is calculated, and the number is divided by the total number of times in the historical data to obtain the frequency of occurrence of the parameter. The higher the frequency, the more common the parameter value is in the historical data, that is, the parameter is more likely to be applicable to the current heating system. Then, the frequency of occurrence of all parameters in each adjustment scheme is averaged to obtain the adjustment feasibility coefficient of the scheme. Through this process, a set of adjustment feasibility coefficients is obtained, in which the adjustment parameters for adjusting the heating supply correspond one to one to the adjustment feasibility coefficients.

[0052] Next, the heating adjustment parameter group corresponding to the maximum value in the adjustment feasibility coefficient set is extracted and used as the direction adjustment heating adjustment parameter group.

[0053] Then, based on the direction adjustment heating adjustment parameter group, it is used as the optimization direction to make directional adjustments to the remaining parameter groups in the set of adjustment heating adjustment parameter groups. Directional adjustment means that on the basis of the direction adjustment heating adjustment parameter group, other schemes are fine-tuned according to the preset adjustment range. In this way, new adjustment schemes are generated, and these schemes constitute the set of follow-up adjustment heating adjustment parameter groups.

[0054] Then, the same method as above is used to traverse the set of follow-up adjustment heating adjustment parameter groups to perform adjustment feasibility coefficient analysis and obtain a set of follow-up adjustment feasibility coefficients.

[0055] Next, determine whether there is a value in the set of follow-up adjustment feasibility coefficients that is greater than or equal to the feasibility coefficient corresponding to the direction adjustment heating adjustment parameter group. If there is a better solution, that is, the feasibility coefficient of a follow-up adjustment heating adjustment parameter group is greater than or equal to the feasibility coefficient corresponding to the current direction adjustment heating adjustment parameter group, then the follow-up adjustment heating adjustment parameter group will be used as the new direction adjustment heating adjustment parameter group, and directional optimization will continue until the preset number of optimizations is met. After each optimization, the direction adjustment heating adjustment parameter group will be continuously updated to find the optimal solution. When the preset number of optimizations is reached, the direction adjustment heating adjustment parameter group finally selected is the target heating adjustment parameter group.

[0056] Furthermore, the system provided in the application embodiment is also used for:

[0057] If not, the direction-adjusted heating regulation parameter group is used as the target heating regulation parameter group.

[0058] In an embodiment of the present application, if no, that is, if no value greater than or equal to the feasibility coefficient corresponding to the direction adjustment heating adjustment parameter group is found in the follow-up adjustment feasibility coefficient set, that is, there is no better adjustment scheme, then the direction adjustment heating adjustment parameter group is directly used as the target heating adjustment parameter group.

[0059] Furthermore, the system provided in the application embodiment is also used for:

[0060] Obtain a preset feedback window; continuously monitor the heating temperature of the target water source heat pump unit in the preset feedback window, and obtain early warning information based on the continuous monitoring results.

[0061] In the embodiment of the present application, after the target water source heat pump unit is heat regulated by the target heat supply regulation parameter group, a preset feedback window is obtained, and the preset feedback window is a time window preset by a technical expert according to the demand. Among them, the preset feedback window is a time period for continuous monitoring of the heat supply of the target water source heat pump unit after the heat supply regulation.

[0062] Within the preset feedback window, the heating temperature of the target water source heat pump unit is continuously monitored. Specifically, the temperature data of the heating outlet is collected in real time through the temperature sensor (such as thermocouple or RTD sensor) installed in the heat pump unit. These data form a time series, recording the changes in the heating temperature over time, and are compared with the target heating temperature to ensure that the heating effect is consistent with the expected target. If the fluctuation of the heating temperature exceeds the preset threshold, an early warning message is generated to notify the operation and maintenance personnel to intervene.

[0063] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0064] The present application installs temperature sensors at the return air inlet and heat pump outlet of the target water source heat pump unit, respectively, to obtain the return air inlet temperature sensor and the heat pump outlet temperature sensor; installs an electromagnetic flowmeter in the ethylene glycol solution flow pipe; traverses the return air inlet temperature sensor, the heat pump outlet temperature sensor and the electromagnetic flowmeter in a preset monitoring window to perform synchronous monitoring data acquisition to obtain the return air inlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence; performs multi-dimensional time series correlation analysis on the return air inlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence to obtain the window return air inlet temperature, the window heat pump outlet temperature and the window solution monitoring flow rate; obtains the target heating temperature, performs heating regulation parameter analysis in combination with the window return air inlet temperature, the window heat pump outlet temperature and the window solution monitoring flow rate, obtains the target heating regulation parameter group, and uses the target heating regulation parameter group to perform heating regulation on the target water source heat pump unit. The present invention solves the technical problems of low heat regulation accuracy and poor real-time regulation capability of water source heat pump units in the prior art. Temperature sensors are installed at the return air inlet and the water outlet of the heat pump of the target water source heat pump unit, and an electromagnetic flowmeter is installed in the flow pipe of the ethylene glycol solution. The return air inlet temperature, the water outlet temperature of the heat pump and the solution flow rate are synchronously monitored. Multi-dimensional time series correlation analysis is used to combine the monitoring data and the target heating temperature to perform heat regulation parameter analysis, generate a target heating regulation parameter group, and regulate the water source heat pump unit to achieve the technical effect of efficient heating operation.

[0065] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0067] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the 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 intends to include these modifications and variations.

Claims

1. An intelligent heating regulation system based on a water source heat pump unit, characterized in that: The system comprises: A sensor deployment module is used to install temperature sensors at the return air inlet and the heat pump outlet of the target water source heat pump unit, respectively, to obtain the return air inlet temperature sensor and the heat pump outlet temperature sensor; A flow meter layout module is used to install an electromagnetic flow meter in a glycol solution flow pipeline; A data acquisition module is used to traverse the return air outlet temperature sensor, the heat pump outlet temperature sensor and the electromagnetic flowmeter in a preset monitoring window to perform synchronous monitoring data acquisition, and obtain the return air outlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence; The correlation analysis module is used to perform multi-dimensional time series correlation analysis on the return air outlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence to obtain the window return air outlet temperature, the window heat pump outlet temperature and the window solution monitoring flow rate; The heating regulation module is used to obtain the target heating temperature, analyze the heating regulation parameters in combination with the window return air temperature, the window heat pump outlet temperature and the window solution monitoring flow rate, obtain the target heating regulation parameter group, and use the target heating regulation parameter group to regulate the heating of the target water source heat pump unit.

2. The intelligent heating regulation system based on a water source heat pump unit according to claim 1, characterized in that: Association analysis module, used to: Respectively extracting the first return air outlet temperature, the first heat pump outlet temperature and the first solution monitoring flow rate in the first position in the return air outlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence, and taking the first return air outlet temperature, the first heat pump outlet temperature and the first solution monitoring flow rate as components, respectively, to construct a first multidimensional vector; Respectively extract the second return air outlet temperature, the second heat pump outlet temperature and the second solution monitoring flow rate located at the second position in the return air outlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence, and use the second return air outlet temperature, the second heat pump outlet temperature and the second solution monitoring flow rate as components to construct a second multidimensional vector; Performing multidimensional time series correlation analysis on the first multidimensional vector and the second multidimensional vector to obtain a first time series correlation vector; Respectively extracting the third return air outlet temperature, the third heat pump outlet temperature and the third solution monitoring flow rate located at the third position in the return air outlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence, and taking the third return air outlet temperature, the third heat pump outlet temperature and the third solution monitoring flow rate as components, respectively, to construct a third multidimensional vector; Performing multi-dimensional time series correlation analysis on the first time series correlation vector and the third multi-dimensional vector to obtain a second time series correlation vector; And so on, until the N-1th time series association vector is obtained, and the window return air outlet temperature, the window heat pump outlet temperature and the window solution monitoring flow rate are obtained according to the N-1th time series association vector, where N is the amount of data in each of the return air outlet temperature sequence, the heat pump outlet temperature sequence and the solution monitoring flow rate sequence, and N is an integer greater than or equal to 1.

3. The intelligent heating regulation system based on a water source heat pump unit according to claim 2, characterized in that: Association analysis module, used to: Performing component mapping calculation on the first multidimensional vector and the second multidimensional vector using an inner product mapping function to obtain a first component mapping similarity set; Normalizing the first component mapping similarity set, and constructing a first multi-dimensional time series association matrix based on the processing result; A convolution operation is performed on the first multi-dimensional time series association matrix and the second multi-dimensional vector to obtain the first time series association vector.

4. The intelligent heating regulation system based on a water source heat pump unit according to claim 1, characterized in that: Heating regulation module for: Pre-training heating regulation parameter recognition network layer; The target heating temperature, the window return air outlet temperature, the window heat pump outlet temperature and the window solution monitoring flow rate are identified by using the heating regulation parameter identification network layer to obtain an initial heating regulation parameter group; Performing multiple random adjustments on the initial heating adjustment parameter group according to a preset adjustment range to obtain an adjusted heating adjustment parameter group set; Directional optimization is performed on the set of adjusted heating regulation parameter groups to obtain the target heating regulation parameter group.

5. The intelligent heating regulation system based on a water source heat pump unit as claimed in claim 4, characterized in that: Heating regulation module for: Performing multiple random adjustments on the initial heating adjustment parameters in the initial heating adjustment parameter group according to a preset adjustment range to obtain an initial adjustment heating adjustment parameter group set; The initial adjustment heating regulation parameter group set is subjected to discrete authentication. If the discrete authentication is passed, the initial adjustment heating regulation parameter group set is used as the adjustment heating regulation parameter group set.

6. The intelligent heating regulation system based on a water source heat pump unit as claimed in claim 4, characterized in that: Heating regulation module for: Traversing the heating adjustment parameter group set to perform adjustment feasibility coefficient analysis to obtain an adjustment feasibility coefficient set, wherein the heating adjustment parameter group and the adjustment feasibility coefficient correspond one to one; Extracting the heating adjustment parameter group corresponding to the maximum value in the adjustment feasibility coefficient set, and using it as the direction adjustment heating adjustment parameter group; Taking the direction-adjusted heating adjustment parameter group as the optimization direction, the remaining adjusted heating adjustment parameter groups in the adjusted heating adjustment parameter group set are directional adjusted according to a preset adjustment range to obtain a follow-up adjusted heating adjustment parameter group set; Traversing the set of follow-up adjustment heating adjustment parameter groups to perform adjustment feasibility coefficient analysis to obtain a set of follow-up adjustment feasibility coefficients; Determine whether there is a following adjustment feasibility coefficient in the following adjustment feasibility coefficient set that is greater than or equal to the adjustment feasibility coefficient corresponding to the direction adjustment heating adjustment parameter group. If so, take the following adjustment heating adjustment parameter group corresponding to the maximum value in the following adjustment feasibility coefficient set as the new direction adjustment heating adjustment parameter group, and continue to perform directional optimization until the preset number of optimization times is met, and take the last updated direction adjustment heating adjustment parameter group as the target heating adjustment parameter group.

7. The intelligent heating regulation system based on a water source heat pump unit according to claim 6, characterized in that: If not, the direction-adjusted heating regulation parameter group is used as the target heating regulation parameter group.

8. The intelligent heating regulation system based on a water source heat pump unit according to claim 1, characterized in that: Also used for: Get the preset feedback window; The heating temperature of the target water source heat pump unit is continuously monitored in the preset feedback window, and early warning information is obtained based on the continuous monitoring results.

Images