Control method and system for central air-conditioning cooling water in medical buildings

Abstract

The present invention relates to a control method and system for cooling water of central air conditioners in medical buildings, and to the technical field of air conditioner control, including: collecting basic refrigeration parameters of the air-conditioning area of ​​the medical building; calling the target temperature, combining the basic refrigeration parameters, analyzing through the load prediction model of the air-conditioning area of ​​the medical building, and generating the required refrigeration capacity of the air-conditioning area; obtaining the outlet water temperature parameter and the outlet water flow parameter; performing frequency optimization on the outlet water temperature parameter and the outlet water flow parameter according to the required refrigeration capacity of the air-conditioning area, and generating the recommended outlet water temperature and the recommended outlet water flow; and controlling the cooling pump according to the recommended outlet water temperature and the recommended outlet water flow. The method solves the technical problem that the prior art cannot automatically adapt to different usage scenarios and environmental changes, resulting in a relatively serious hysteresis in cooling water control.

Description

Technical Field

[0001] The present invention relates to the field of air conditioning control, and in particular to a control method and system for cooling water of a central air conditioning in a medical building. Background Art

[0002] Central air conditioning is a centralized cooling and heating air conditioning system that connects multiple terminal devices through a host to deliver hot and cold media to each room, thereby achieving temperature control of the entire building. Compared with traditional split air conditioners, central air conditioners have the advantages of high comfort, space saving, long service life, high energy consumption ratio and strong energy saving.

[0003] Medical buildings have a special service target, many internal departments and complex functions, and the demand for central air-conditioning products is increasing. Medical buildings in different areas have different requirements for central air-conditioning. For example, for general areas such as outpatient clinics and general wards, they need to have sensitive temperature adjustment functions, independent control, antibacterial functions, etc.; while for special areas such as burn wards, ICUs, operating rooms, etc., there are higher requirements for temperature, humidity, airflow, etc., and independent air-conditioning systems are required with good isolation airflow functions.

[0004] From the perspective of the particularity of medical buildings, the design of central air-conditioning systems needs to consider special requirements such as air quality requirements, temperature and humidity control, pressure gradient design, ventilation requirements, equipment reliability, noise control, disinfection function, flexibility, and intelligent control. Traditional central air-conditioning cooling water control has shortcomings such as delayed response and lack of intelligent adaptability. It cannot automatically adapt to different usage scenarios and environmental changes, and requires more manual intervention and adjustment.

[0005] The existing technology is unable to automatically adapt to different usage scenarios and environmental changes, resulting in a technical problem of severe cooling water control lag. Summary of the invention

[0006] The present invention aims to solve the technical problem that the prior art cannot automatically adapt to different usage scenarios and environmental changes, resulting in serious cooling water control lag, and provides a control method and system for central air-conditioning cooling water in medical buildings.

[0007] In a first aspect, the present invention provides a method for controlling cooling water of a central air conditioner in a medical building, comprising: collecting basic refrigeration parameters of an air-conditioning area of ​​the medical building through a temperature sensor, wherein the basic refrigeration parameters include supply water temperature, return water temperature, supply water flow, return water flow, supply and return water temperature difference, and outdoor temperature;

[0008] Retrieving the target temperature, combining the water supply temperature, the return water temperature, the water supply flow rate, the return water flow rate, the supply and return water temperature difference and the outdoor temperature, and analyzing through the load prediction model of the air-conditioning area of ​​the medical building to generate the required cooling capacity of the air-conditioning area;

[0009] Obtaining cooling pump control parameters, wherein the cooling pump control parameters include outlet water temperature parameters and outlet water flow parameters;

[0010] According to the required cooling capacity of the air-conditioning area, the water outlet temperature parameter and the water outlet flow rate parameter are frequency-optimized to generate a recommended water outlet temperature and a recommended water outlet flow rate;

[0011] The cooling pump is controlled according to the recommended outlet water temperature and the recommended outlet water flow rate.

[0012] In a second aspect, the present invention provides a control system for central air-conditioning cooling water in a medical building, comprising:

[0013] A basic parameter acquisition module is used to collect the basic refrigeration parameters of the air-conditioning area of ​​the medical building through a temperature sensor, wherein the basic refrigeration parameters include supply water temperature, return water temperature, supply water flow, return water flow, supply and return water temperature difference and outdoor temperature;

[0014] A cooling demand analysis module is used to retrieve the target temperature, combine the supply water temperature, the return water temperature, the supply water flow, the return water flow, the supply and return water temperature difference and the outdoor temperature, analyze through the load prediction model of the air-conditioning area of ​​the medical building, and generate the required cooling capacity of the air-conditioning area;

[0015] A control parameter acquisition module, used to obtain cooling pump control parameters, wherein the cooling pump control parameters include outlet water temperature parameters and outlet water flow parameters;

[0016] An optimization and recommendation module, used to perform frequency optimization on the water outlet temperature parameter and the water outlet flow rate parameter according to the required cooling capacity of the air-conditioning area, and generate a recommended water outlet temperature and a recommended water outlet flow rate;

[0017] The parameter control and adjustment module is used to control the cooling pump according to the recommended outlet water temperature and the recommended outlet water flow rate.

[0018] In a third aspect, the present invention provides an electronic device, comprising: a memory for storing a computer software program; a processor for reading and executing the computer software program, thereby implementing the method for controlling cooling water of central air conditioning in a medical building as described in any one of the first aspects.

[0019] In a fourth aspect, the present invention provides a non-transitory computer-readable storage medium, wherein the storage medium stores a computer software program, and when the computer software program is executed by a processor, the method for controlling cooling water of central air conditioning in a medical building as described in any one of the first aspects is implemented.

[0020] The beneficial effects of the present invention are as follows: by analyzing the basic refrigeration parameters and the target temperature, the required refrigeration capacity is predicted, and the optimal cooling water control parameters are searched according to the required refrigeration capacity, and the cooling pump is controlled according to the cooling water control parameters, so as to achieve the technical effect of improving the cooling water control accuracy and control timeliness. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic diagram of a process for controlling cooling water of central air conditioners in medical buildings provided by the present invention;

[0022] Figure 2 A schematic diagram of the structure of the central air-conditioning cooling water management and control system for medical buildings provided by the present invention;

[0023] Figure 3 A functional block diagram of the electronic device provided by the present invention;

[0024] Figure 4 A functional block diagram of a computer-readable storage device provided by the present invention. DETAILED DESCRIPTION

[0025] 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, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0026] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0027] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0028] Example 1

[0029] like Figure 1 As shown, an embodiment of the present invention provides a method for controlling cooling water of central air conditioning in a medical building, including:

[0030] S10: Collecting basic refrigeration parameters of the air-conditioning area of ​​the medical building through a temperature sensor, wherein the basic refrigeration parameters include supply water temperature, return water temperature, supply water flow, return water flow, supply and return water temperature difference and outdoor temperature;

[0031] Specifically, the temperature sensor is arranged at the indoor unit, air supply outlet, return air outlet, air duct and other positions of the central air-conditioning in the medical building. The water supply temperature refers to the temperature of the water supplied to the user in the air-conditioning system. In summer, the water supply temperature is usually low, generally about 7°C, which is used to reduce the indoor temperature. The return water temperature refers to the temperature of the water returned from the user in the air-conditioning system. The return water temperature is usually higher than the supply water temperature because the water absorbs heat at the user. The water supply flow rate refers to the flow rate of water supplied to the user in the air-conditioning system. The size of the water supply flow rate depends on the load of the air-conditioning system and the needs of the user. The return water flow rate refers to the flow rate of water returned from the user in the air-conditioning system. The size of the return water flow rate is usually equal to the supply water flow rate, but in some special cases, such as when the user partially closes or adjusts the valve, the return water flow rate may be less than the supply water flow rate. The supply and return water temperature difference refers to the difference between the supply water temperature and the return water temperature. The size of the supply and return water temperature difference reflects the heat exchange efficiency and energy consumption level of the air-conditioning system. Generally speaking, the smaller the supply and return water temperature difference, the higher the heat exchange efficiency of the air-conditioning system and the lower the energy consumption. Basic refrigeration parameters are collected through temperature sensors, providing data support for the management and control of central air-conditioning cooling water.

[0032] S20: Retrieving the target temperature, combining the water supply temperature, the return water temperature, the water supply flow rate, the return water flow rate, the supply and return water temperature difference and the outdoor temperature, and analyzing through the load prediction model of the air-conditioning area of ​​the medical building to generate the required cooling capacity of the air-conditioning area;

[0033] Further, the target temperature is retrieved, combined with the water supply temperature, the return water temperature, the water supply flow rate, the return water flow rate, the supply and return water temperature difference and the outdoor temperature, and analyzed through the load prediction model of the air-conditioning area of ​​the medical building to generate the required cooling capacity of the air-conditioning area. Step S20 includes:

[0034] S21: Obtaining the topological characteristics of the central air-conditioning layout of the air-conditioning area of ​​the medical building;

[0035] S22: taking the central air-conditioning layout topology feature as a constraint, collecting a work log data set of the same topology, wherein the work log data set of the same topology includes a supply water temperature record data set, a return water temperature record data set, a supply water flow record data set, a return water flow record data set, a supply and return water temperature difference record data set, an outdoor temperature record data set, and a required cooling capacity record data set;

[0036] S23: Taking the required cooling capacity record data set as supervision, taking the supply water temperature record data set, the return water temperature record data set, the supply water flow record data set, the return water flow record data set, the supply and return water temperature difference record data set, and the outdoor temperature record data set as input, configuring a first front model, a second front model, and up to an Nth front model, wherein the model topological structures of the first front model, the second front model, and up to the Nth front model are different;

[0037] S24: configuring a global fusion model using the first pre-output data set of the pre-first model, the second pre-output data set of the pre-second model, and up to the Nth pre-output data set of the pre-Nth model as inputs and the required cooling capacity record data set as supervision;

[0038] S25: Merge the first preceding model, the second preceding model up to the Nth preceding model, and the global fusion model to generate the load forecasting model.

[0039] Specifically, the central air-conditioning layout topology features of the air-conditioning area of ​​the medical building are designed and constructed by comprehensively considering the functional requirements, spatial layout, energy efficiency and operation management of the medical building. It mainly includes cold and heat source systems, air handling systems, air supply systems, return air systems, and water systems. After calling the central air-conditioning layout topology features of the current medical building, in order to control the cooling water, a large amount of data information needs to be collected. Therefore, according to the central air-conditioning layout topology features, the work log data set of the central air-conditioning with the same topology structure is collected. The same topology work log data set includes a water supply temperature record data set, a return water temperature record data set, a water supply flow record data set, a return water flow record data set, a supply and return water temperature difference record data set, an outdoor temperature record data set, and a demand cooling capacity record data set.

[0040] The required cooling capacity record data set is used as the supervisory data, and the supply water temperature record data set, the return water temperature record data set, the supply water flow record data set, the return water flow record data set, the supply and return water temperature difference record data set, and the outdoor temperature record data set are used as the input data to configure the first front model, the second front model, and the Nth front model. The input data and the supervisory data are used as the training data of the model to train the first front model, the second front model, and the Nth front model, respectively, and the model topological structures of the first front model, the second front model, and the Nth front model are different.

[0041] During the training process, the output data set of the first front model is the first front output data set, the output data set of the second front model is the second front output data set, and so on, the output data set of the Nth front model is the Nth front output data set. The first front output data set, the second front output data set, and the Nth front output data set are used as input data, and the required cooling capacity record data set is used as a supervision data set to train the global fusion model.

[0042] The load forecasting model is based on the concept of integrated model, and is obtained by merging multiple basic models (the first preceding model, the second preceding model to the Nth preceding model), that is, the load forecasting model inputs the training data set into the first preceding model, the second preceding model to the Nth preceding model respectively, and uses the output information of the first preceding model, the second preceding model to the Nth preceding model as the input information of the global fusion model, and uses the output of the global fusion model as the output information of the load forecasting model.

[0043] The target temperature is the set temperature that each important air-conditioning area needs to reach, and the required cooling capacity of the air-conditioning area is the cooling capacity that the air-conditioning system needs to output in order to reduce the temperature in a specific space to the required level. The load forecasting model generates the required cooling capacity of the air-conditioning area based on the target temperature that needs to be achieved, the current supply water temperature, the return water temperature, the supply water flow, the return water flow, the supply and return water temperature difference and the outdoor temperature. It fully utilizes the advantages of different basic models to obtain better performance than a single model, emphasizes the diversity between basic models, captures information in the data from different angles, and avoids the homogenization of models.

[0044] S30: obtaining a cooling pump control parameter, wherein the cooling pump control parameter includes an outlet water temperature parameter and an outlet water flow parameter;

[0045] Specifically, the cooling pump is an important device in the central air conditioning system. Its main function is to pump cooling water to the cooling tower, where it exchanges heat with the air to reduce the water temperature. The cooled water is then sent back to the condenser of the central air conditioning unit to help the condenser take away the heat in the refrigerant, thereby cooling the refrigerant and ensuring the normal refrigeration cycle of the central air conditioning system. The cooling pump is usually driven by a motor and connected to the central air conditioning unit and cooling tower through pipes to form a circulation system. It plays a key role in maintaining the stable operation and good cooling effect of the central air conditioning system.

[0046] The control parameters of the cooling pump are obtained through sensors installed at the cooling pump or through data displayed by some cooling pumps with built-in monitoring functions. The cooling pump control parameters include outlet water temperature parameters and outlet water flow parameters. The outlet water temperature parameter refers to the temperature of the water when the cooling pump transports the water out. The outlet water flow parameter refers to the volume of water flowing out of the cooling pump outlet per unit time. The level of the outlet water temperature parameter will affect the cooling effect. For example, too high a temperature may mean reduced cooling efficiency or certain problems. The size of the outlet water flow parameter is also critical. It is related to the circulation speed of the water and the strength of the cooling capacity. Too small a flow may lead to insufficient cooling, while too large a flow may bring some other problems such as increased energy consumption.

[0047] S40: performing frequency optimization on the water outlet temperature parameter and the water outlet flow rate parameter according to the required cooling capacity of the air-conditioning area, and generating a recommended water outlet temperature and a recommended water outlet flow rate;

[0048] Further, according to the required cooling capacity of the air-conditioning area, the frequency optimization of the water outlet temperature parameter and the water outlet flow parameter is performed to generate a recommended water outlet temperature and a recommended water outlet flow, and step S40 includes:

[0049] S41: Performing local control retrieval based on the required cooling capacity of the air-conditioning area to obtain a control history particle set;

[0050] S42: performing aggregation analysis on the control history particle set to generate multiple clusters of history particles;

[0051] S43: performing frequency optimization according to the multiple clusters of historical particles to generate the recommended outlet water temperature and the recommended outlet water flow rate.

[0052] Further, frequency optimization is performed according to the multiple clusters of historical particles to generate the recommended outlet water temperature and the recommended outlet water flow rate. Step S43 includes:

[0053] S431: Obtain the number of particles in multiple clusters of the multiple clusters of historical particles;

[0054] S432: deleting clusters in which the number of particles in the plurality of clusters is less than or equal to the frequency threshold, and obtaining remaining cluster historical particles;

[0055] S433: sorting the remaining cluster historical particles with the lowest energy consumption to obtain the recommended outlet water temperature and the recommended outlet water flow rate.

[0056] Specifically, local data is retrieved according to the required cooling capacity of the air-conditioning area, and the corresponding historical data of the outlet water temperature parameter and the historical data of the outlet water flow parameter are obtained to form the control history particle set. According to the aggregate analysis of the data, particles can be categorized based on distance, a distance threshold is preset, and the distance analysis between particles is performed, and particles less than the distance threshold are grouped into one cluster to obtain the multi-cluster historical particles.

[0057] The cooling pump control parameters that can be obtained after the frequency optimization operation with the highest probability to meet the cooling capacity required in the air-conditioning area. The specific process is to extract the number of the multiple clusters of historical particles to obtain the number of particles in the multiple clusters. The frequency threshold is the minimum number of parameter occurrence frequencies set according to the actual control parameters. The remaining cluster historical particles are the cluster particle sets remaining after deleting the clusters whose number of particles in the clusters is less than or equal to the frequency threshold.

[0058] Energy consumption analysis is performed based on the outlet water temperature parameters and outlet water flow rate parameters corresponding to the historical particles of the remaining clusters, and the particles corresponding to the lowest energy consumption and the corresponding outlet water temperature parameters and outlet water flow rate parameters are found, which are the recommended outlet water temperature and the recommended outlet water flow rate.

[0059] S50: Controlling the cooling pump according to the recommended outlet water temperature and the recommended outlet water flow rate.

[0060] Specifically, controlling the outlet water temperature of the cooling pump affects the heat exchange efficiency of the entire refrigeration system, and thus affects the refrigeration effect of the central air conditioner. Controlling the outlet water flow rate will also affect the heat exchange effect of the system and the water circulation speed. Accurately controlling the outlet water temperature and outlet water flow rate of the cooling pump can affect the temperature change of the central air conditioner to a certain extent. Controlling the cooling pump according to the recommended outlet water temperature and the recommended outlet water flow rate can improve the control accuracy of the cooling water control of the central air conditioner, and can improve the timeliness of the control and reduce the problems caused by the lag in cooling water control.

[0061] Further, the merging of the first preceding model, the second preceding model, up to the Nth preceding model, and the global fusion model to generate the load forecasting model, step S25 includes:

[0062] S251: configure load prediction loss function;

[0063] S252: performing loss verification on the load forecasting model according to the load forecasting loss function, and generating a number of consecutive loss parameters;

[0064] S253: When the proportion of the consecutive loss parameters that are less than or equal to the loss parameter threshold is greater than or equal to a preset proportion, the load forecasting model is deemed to have converged;

[0065] S254: Otherwise, continue iterating.

[0066] Furthermore, the configuration load prediction loss function, step S251 includes:

[0067] S2511: The load prediction loss function is:

[0068]

[0069] in, For load prediction losses, Represents the output value of the previous i-th model in the j-th verification, represents the j-th verification supervision value, represents the output value of the load forecasting model verified for the jth time, that is, the output value of the global fusion model, and They represent the first adjustment weight and the second adjustment weight respectively, and M represents the number of verifications.

[0070] Specifically, in order to evaluate the training effect of the load forecasting model, the loss verification of the model is performed by configuring the loss function. The specific load forecasting loss function is:

[0071]

[0072] in, For load prediction losses, Represents the output value of the previous i-th model in the j-th verification, represents the j-th verification supervision value, represents the output value of the load forecasting model verified for the jth time, that is, the output value of the global fusion model, and They represent the first adjustment weight and the second adjustment weight respectively, and M represents the number of verifications.

[0073] That is to say, the load forecast loss value is the sum of the loss values ​​of M verification times, and each loss value is the sum of the squares of the difference between the output value of the previous i-th model and the j-th verification supervision value in N j-th verifications, divided by N times the first adjustment weight, plus the square of the difference between the output value of the global fusion model of the j-th verification and the j-th verification supervision value multiplied by the second adjustment weight. The first adjustment weight and the second adjustment weight are artificially set parameters.

[0074] According to the load prediction loss function, the output value and the supervision value of the load prediction model are verified for loss, and a number of consecutive loss parameters are generated. The loss parameter threshold and the ratio are preset. When the ratio of the consecutive loss parameters that are less than or equal to the loss parameter threshold is greater than or equal to the preset ratio, the load prediction model is considered to have converged, otherwise it continues to iterate. When the ratio is greater than or equal to the preset ratio, the training is stopped, and a load prediction model with a certain prediction accuracy is obtained, thereby laying a foundation for accurately predicting the cooling capacity required in the air-conditioning area.

[0075] Furthermore, the control history particle set is aggregated and analyzed to generate multiple clusters of history particles, and step S42 includes:

[0076] S421: constructing a first coordinate axis with the normalized value of the outlet water temperature, and constructing a second coordinate axis with the normalized value of the outlet water flow rate;

[0077] S422: constructing a first virtual coordinate system based on the first coordinate axis and the second coordinate axis;

[0078] S423: Obtaining a distribution coordinate set of the control history particle set in the first virtual coordinate system;

[0079] S424: performing aggregation analysis on the control history particle set according to the distribution distance threshold and in combination with the distribution coordinate set to generate the multiple clusters of history particles.

[0080] Specifically, the preferred process of the control history particle set aggregation analysis can be as follows: in order to perform inter-particle distance analysis, the particles need to be converted into points with coordinate information. The first coordinate axis is constructed with the normalized value of the outlet water temperature, and the second coordinate axis is constructed with the normalized value of the outlet water flow. List normalization is an operation that divides each value of the input data by its range, which means scaling all data to the range of [0, 1]. The virtual coordinate system consists of the first coordinate axis and the second coordinate axis. After the control history particle set is normalized, it is mapped into the virtual coordinate system to obtain a distribution coordinate set in the first virtual coordinate system. The distribution distance threshold is pre-set and used to analyze the degree of distance between particles. When the distance between each particle of the controlled history particle set is less than the distribution distance threshold, it is divided into a cluster, and after traversing all particles for distance judgment and cluster division, the multi-cluster history particles are obtained. The effect of obtaining the particle aggregation analysis result by mapping the historical particle set to the virtual coordinate system and judging the distribution distance is achieved.

[0081] Example 2

[0082] like Figure 2 As shown, based on the same inventive concept as the method for controlling cooling water of central air conditioner in medical building provided in Example 1, the embodiment of the present invention provides a control system for cooling water of central air conditioner in medical building, including:

[0083] The basic parameter acquisition module 1000 is used to acquire the basic refrigeration parameters of the air-conditioning area of ​​the medical building through a temperature sensor, wherein the basic refrigeration parameters include supply water temperature, return water temperature, supply water flow, return water flow, supply and return water temperature difference and outdoor temperature;

[0084] The cooling demand analysis module 2000 is used to retrieve the target temperature, combine the supply water temperature, the return water temperature, the supply water flow, the return water flow, the supply and return water temperature difference and the outdoor temperature, and analyze the load prediction model of the air-conditioning area of ​​the medical building to generate the required cooling capacity of the air-conditioning area;

[0085] A control parameter acquisition module 3000 is used to obtain cooling pump control parameters, wherein the cooling pump control parameters include outlet water temperature parameters and outlet water flow parameters;

[0086] The optimization and recommendation module 4000 is used to perform frequency optimization on the water outlet temperature parameter and the water outlet flow parameter according to the required cooling capacity of the air-conditioning area, and generate a recommended water outlet temperature and a recommended water outlet flow;

[0087] The parameter control and adjustment module 5000 is used to control the cooling pump according to the recommended outlet water temperature and the recommended outlet water flow rate.

[0088] Furthermore, the system also includes:

[0089] A topological feature calling module, used to obtain the topological features of the central air-conditioning layout of the air-conditioning area of ​​the medical building;

[0090] A work log collection module, used to collect the same topology work log data set based on the central air-conditioning layout topology characteristics as constraints, wherein the same topology work log data set includes a supply water temperature record data set, a return water temperature record data set, a supply water flow record data set, a return water flow record data set, a supply and return water temperature difference record data set, an outdoor temperature record data set, and a required cooling capacity record data set;

[0091] A front-end model configuration module is used to configure a front-end first model, a front-end second model, and up to a front-end N-th model, taking the required cooling capacity record data set as supervision, and taking the supply water temperature record data set, the return water temperature record data set, the supply water flow record data set, the return water flow record data set, the supply and return water temperature difference record data set, and the outdoor temperature record data set as input, wherein the model topological structures of the front-end first model, the front-end second model, and up to the front-end N-th model are different;

[0092] A global model configuration module, configured to configure a global fusion model using the first pre-output data set of the pre-first model, the second pre-output data set of the pre-second model, and up to the Nth pre-output data set of the pre-Nth model as inputs and the required cooling capacity record data set as supervision;

[0093] The model merging module is used to merge the first preceding model, the second preceding model up to the Nth preceding model, and the global fusion model to generate the load forecasting model.

[0094] Furthermore, the system also includes:

[0095] Loss function configuration module, used to configure load forecasting loss function;

[0096] A loss verification module, used to perform loss verification on the load forecasting model according to the load forecasting loss function, and generate a number of consecutive loss parameters;

[0097] A first loss judgment module, configured to regard the load forecasting model as converged when the proportion of the consecutive loss parameters that are less than or equal to the loss parameter threshold is greater than or equal to a preset proportion;

[0098] The second loss judgment module is used to continue iterating otherwise.

[0099] Furthermore, the system also includes:

[0100] Function preset module, used for the load forecasting loss function is:

[0101]

[0102] in, For load prediction losses, Represents the output value of the previous i-th model in the j-th verification, represents the j-th verification supervision value, represents the output value of the load forecasting model verified for the jth time, that is, the output value of the global fusion model, and They represent the first adjustment weight and the second adjustment weight respectively, and M represents the number of verifications.

[0103] Furthermore, the system also includes:

[0104] A control retrieval module, used for performing local control retrieval based on the required cooling capacity of the air-conditioning area to obtain a control history particle set;

[0105] An aggregation analysis module, used for performing aggregation analysis on the control history particle set to generate multiple clusters of history particles;

[0106] The particle optimization module is used to perform frequency optimization according to the multiple clusters of historical particles to generate the recommended outlet water temperature and the recommended outlet water flow rate.

[0107] Furthermore, the system also includes:

[0108] A coordinate axis construction module, used to construct a first coordinate axis with a normalized value of the outlet water temperature, and to construct a second coordinate axis with a normalized value of the outlet water flow rate;

[0109] A coordinate system construction module, used for constructing a first virtual coordinate system based on the first coordinate axis and the second coordinate axis;

[0110] A distribution coordinate set acquisition module, used to obtain a distribution coordinate set of the control history particle set in the first virtual coordinate system;

[0111] The particle set aggregation module is used to perform aggregation analysis on the control history particle set according to the distribution distance threshold and in combination with the distribution coordinate set to generate the multiple clusters of historical particles.

[0112] Furthermore, the system also includes:

[0113] A quantity analysis module, used for obtaining the number of particles in multiple clusters of the multiple clusters of historical particles;

[0114] A cluster deletion module is used to delete clusters whose number of particles in the plurality of clusters is less than or equal to a frequency threshold, and obtain remaining cluster historical particles;

[0115] The particle sorting module is used to sort the remaining cluster historical particles with the lowest energy consumption to obtain the recommended water outlet temperature and the recommended water outlet flow rate.

[0116] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, the following steps are implemented: collecting basic refrigeration parameters of the air-conditioning area of ​​the medical building through a temperature sensor, wherein the basic refrigeration parameters include supply water temperature, return water temperature, supply water flow, return water flow, supply and return water temperature difference, and outdoor temperature; retrieving the target temperature, combining the supply water temperature, the return water temperature, the supply water flow, the return water flow, the supply and return water temperature difference, and the outdoor temperature, analyzing through the load prediction model of the air-conditioning area of ​​the medical building, and generating the required cooling capacity of the air-conditioning area; obtaining cooling pump control parameters, wherein the cooling pump control parameters include outlet water temperature parameters and outlet water flow parameters; according to the required cooling capacity of the air-conditioning area, performing frequency optimization on the outlet water temperature parameters and the outlet water flow parameters to generate recommended outlet water temperature and recommended outlet water flow; and controlling the cooling pump according to the recommended outlet water temperature and the recommended outlet water flow.

[0117] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 600, on which a computer program 611 is stored. When the computer program 611 is executed by a processor, the following steps are implemented: collecting basic refrigeration parameters of the air-conditioning area of ​​the medical building through a temperature sensor, wherein the basic refrigeration parameters include supply water temperature, return water temperature, supply water flow, return water flow, supply and return water temperature difference and outdoor temperature; calling the target temperature, combining the supply water temperature, the return water temperature, the supply water flow, the return water flow, the supply and return water temperature difference and the outdoor temperature, analyzing through the load prediction model of the air-conditioning area of ​​the medical building, and generating the required cooling capacity of the air-conditioning area; obtaining cooling pump control parameters, wherein the cooling pump control parameters include outlet water temperature parameters and outlet water flow parameters; according to the required cooling capacity of the air-conditioning area, performing frequency optimization on the outlet water temperature parameters and the outlet water flow parameters to generate recommended outlet water temperature and recommended outlet water flow; and controlling the cooling pump according to the recommended outlet water temperature and the recommended outlet water flow.

[0118] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0119] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0120] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0123] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0124] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A method for controlling cooling water of central air conditioning in medical buildings, characterized in that: include: The basic refrigeration parameters of the air-conditioning area of ​​the medical building are collected by temperature sensors, wherein the basic refrigeration parameters include supply water temperature, return water temperature, supply water flow, return water flow, supply and return water temperature difference and outdoor temperature; Retrieving the target temperature, combining the water supply temperature, the return water temperature, the water supply flow rate, the return water flow rate, the supply and return water temperature difference and the outdoor temperature, and analyzing through the load prediction model of the air-conditioning area of ​​the medical building to generate the required cooling capacity of the air-conditioning area; Obtaining cooling pump control parameters, wherein the cooling pump control parameters include outlet water temperature parameters and outlet water flow parameters; According to the required cooling capacity of the air-conditioning area, the water outlet temperature parameter and the water outlet flow rate parameter are frequency-optimized to generate a recommended water outlet temperature and a recommended water outlet flow rate; Controlling the cooling pump according to the recommended water outlet temperature and the recommended water outlet flow rate; The target temperature is retrieved, and combined with the supply water temperature, the return water temperature, the supply water flow rate, the return water flow rate, the supply and return water temperature difference and the outdoor temperature, and analyzed through the load prediction model of the air-conditioning area of ​​the medical building to generate the required cooling capacity of the air-conditioning area, including: Obtaining the topological characteristics of the central air-conditioning layout of the air-conditioning area of ​​the medical building; Taking the central air-conditioning layout topology feature as a constraint, collecting the same topology work log data set, wherein the same topology work log data set includes a supply water temperature record data set, a return water temperature record data set, a supply water flow record data set, a return water flow record data set, a supply and return water temperature difference record data set, an outdoor temperature record data set and a required cooling capacity record data set; Taking the required cooling capacity record data set as supervision, taking the supply water temperature record data set, the return water temperature record data set, the supply water flow record data set, the return water flow record data set, the supply and return water temperature difference record data set, and the outdoor temperature record data set as input, configuring a first front model, a second front model, and up to an Nth front model, wherein the model topological structures of the first front model, the second front model, and up to the Nth front model are different; The global fusion model is configured by taking the first pre-output data set of the pre-first model, the second pre-output data set of the pre-second model, and the Nth pre-output data set of the pre-Nth model as inputs and taking the required cooling capacity record data set as supervision; Merging the first preceding model, the second preceding model, up to the Nth preceding model, and the global fusion model to generate the load forecasting model; According to the required cooling capacity of the air-conditioning area, the water outlet temperature parameter and the water outlet flow rate parameter are frequency-optimized to generate a recommended water outlet temperature and a recommended water outlet flow rate, including: Performing local control retrieval based on the required cooling capacity of the air-conditioning area to obtain a control history particle set; Performing aggregation analysis on the control history particle set to generate multiple clusters of history particles; Performing frequency optimization according to the multiple clusters of historical particles to generate the recommended outlet water temperature and the recommended outlet water flow rate; Aggregate analysis is performed on the control history particle set to generate multiple clusters of history particles, including: The first coordinate axis is constructed by the normalized value of the outlet water temperature, and the second coordinate axis is constructed by the normalized value of the outlet water flow rate; Constructing a first virtual coordinate system based on the first coordinate axis and the second coordinate axis; Obtaining a distribution coordinate set of the control history particle set in the first virtual coordinate system; According to the distribution distance threshold, the control history particle set is aggregated and analyzed in combination with the distribution coordinate set to generate the multiple clusters of history particles; Performing frequency optimization according to the multiple clusters of historical particles to generate the recommended outlet water temperature and the recommended outlet water flow rate includes: Obtaining the number of particles in multiple clusters of the multiple clusters of historical particles; Deleting clusters whose number of particles in the plurality of clusters is less than or equal to the frequency threshold, to obtain remaining cluster historical particles; The remaining cluster historical particles are sorted with particles having the lowest energy consumption to obtain the recommended water outlet temperature and the recommended water outlet flow rate.

2. The method according to claim 1, characterized in that The first preceding model, the second preceding model, up to the Nth preceding model, and the global fusion model are combined to generate the load forecasting model, including: Configure load forecasting loss function; Performing loss verification on the load forecasting model according to the load forecasting loss function to generate a number of consecutive loss parameters; When the proportion of the consecutive loss parameters that are less than or equal to the loss parameter threshold is greater than or equal to a preset proportion, the load forecasting model is deemed to have converged; Otherwise, continue iterating.

3. The method according to claim 2, characterized in that Configure the load forecast loss function, including: The load forecasting loss function is: in, For load prediction losses, Represents the output value of the previous i-th model in the j-th verification, Represents the j-th verification supervision value, represents the output value of the load forecasting model verified for the jth time, that is, the output value of the global fusion model, and They represent the first adjustment weight and the second adjustment weight respectively, and M represents the number of verifications.

4. The control system of central air-conditioning cooling water in medical buildings is characterized by: include: A basic parameter acquisition module is used to collect the basic refrigeration parameters of the air-conditioning area of ​​the medical building through a temperature sensor, wherein the basic refrigeration parameters include supply water temperature, return water temperature, supply water flow, return water flow, supply and return water temperature difference and outdoor temperature; A cooling demand analysis module is used to retrieve the target temperature, combine the supply water temperature, the return water temperature, the supply water flow, the return water flow, the supply and return water temperature difference and the outdoor temperature, analyze through the load prediction model of the air-conditioning area of ​​the medical building, and generate the required cooling capacity of the air-conditioning area; A control parameter acquisition module, used to obtain cooling pump control parameters, wherein the cooling pump control parameters include outlet water temperature parameters and outlet water flow parameters; An optimization and recommendation module, used to perform frequency optimization on the water outlet temperature parameter and the water outlet flow rate parameter according to the required cooling capacity of the air-conditioning area, and generate a recommended water outlet temperature and a recommended water outlet flow rate; A parameter control and adjustment module, used for controlling the cooling pump according to the recommended outlet water temperature and the recommended outlet water flow rate; The target temperature is retrieved, and combined with the supply water temperature, the return water temperature, the supply water flow rate, the return water flow rate, the supply and return water temperature difference and the outdoor temperature, and analyzed through the load prediction model of the air-conditioning area of ​​the medical building to generate the required cooling capacity of the air-conditioning area, including: Obtaining the topological characteristics of the central air-conditioning layout of the air-conditioning area of ​​the medical building; Taking the central air-conditioning layout topology feature as a constraint, collecting the same topology work log data set, wherein the same topology work log data set includes a supply water temperature record data set, a return water temperature record data set, a supply water flow record data set, a return water flow record data set, a supply and return water temperature difference record data set, an outdoor temperature record data set and a required cooling capacity record data set; Taking the required cooling capacity record data set as supervision, taking the supply water temperature record data set, the return water temperature record data set, the supply water flow record data set, the return water flow record data set, the supply and return water temperature difference record data set, and the outdoor temperature record data set as input, configuring a first front model, a second front model, and up to an Nth front model, wherein the model topological structures of the first front model, the second front model, and up to the Nth front model are different; The global fusion model is configured by taking the first pre-output data set of the pre-first model, the second pre-output data set of the pre-second model, and the Nth pre-output data set of the pre-Nth model as inputs and taking the required cooling capacity record data set as supervision; Merging the first preceding model, the second preceding model, up to the Nth preceding model, and the global fusion model to generate the load forecasting model; According to the required cooling capacity of the air-conditioning area, the water outlet temperature parameter and the water outlet flow rate parameter are frequency-optimized to generate a recommended water outlet temperature and a recommended water outlet flow rate, including: Performing local control retrieval based on the required cooling capacity of the air-conditioning area to obtain a control history particle set; Performing aggregation analysis on the control history particle set to generate multiple clusters of history particles; Performing frequency optimization according to the multiple clusters of historical particles to generate the recommended outlet water temperature and the recommended outlet water flow rate; Aggregate analysis is performed on the control history particle set to generate multiple clusters of history particles, including: The first coordinate axis is constructed by the normalized value of the outlet water temperature, and the second coordinate axis is constructed by the normalized value of the outlet water flow rate; Constructing a first virtual coordinate system based on the first coordinate axis and the second coordinate axis; Obtaining a distribution coordinate set of the control history particle set in the first virtual coordinate system; According to the distribution distance threshold, the control history particle set is aggregated and analyzed in combination with the distribution coordinate set to generate the multiple clusters of history particles; Performing frequency optimization according to the multiple clusters of historical particles to generate the recommended outlet water temperature and the recommended outlet water flow rate includes: Obtaining the number of particles in multiple clusters of the multiple clusters of historical particles; Deleting clusters whose number of particles in the plurality of clusters is less than or equal to the frequency threshold, to obtain remaining cluster historical particles; The remaining cluster historical particles are sorted with particles having the lowest energy consumption to obtain the recommended water outlet temperature and the recommended water outlet flow rate.

5. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the method for controlling cooling water of central air conditioning in a medical building as described in any one of claims 1-3.

6. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the method for controlling the central air-conditioning cooling water of a medical building as described in any one of claims 1 to 3 is implemented.

Images