Self-adaptive adjusting method and system for refrigeration cycle of equipment

Abstract

The invention discloses a self-adaptive adjusting method and system for equipment refrigeration cycle, and relates to the technical field of intelligent control. The method comprises the following steps: pre-configuring N temperature control edge nodes in N temperature control areas; receiving and analyzing N pieces of region multi-dimensional environment data of the N temperature control regions to obtain N real-time cold load requirements; carrying out refrigeration load distribution on the M refrigeration devices through cold load fitness optimization to obtain M real-time refrigeration loads; after flow distribution adjustment is carried out, refrigeration cycle self-adaptive adjustment is carried out on the M refrigeration devices; and a refrigeration cycle adjusting window is preset, and the refrigeration cooperative control cloud receives N update cold load requirements returned by the N temperature control edge nodes with the refrigeration cycle adjusting window as a constraint to perform refrigeration cycle intermittent adjustment of the M refrigeration devices. The technical problems that in the prior art, refrigeration equipment is unreasonable in load distribution, high in energy consumption and low in response speed are solved, and the technical effects of improving the efficiency of a refrigeration system and reducing energy consumption are achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a self-adaptive regulation method and system for a refrigeration cycle of an equipment. Background Art

[0002] As a key facility for maintaining indoor environmental comfort and normal equipment operation, the importance of the refrigeration system is becoming increasingly prominent. Traditional refrigeration equipment mostly relies on fixed load distribution modes and lacks adaptive adjustment mechanisms for different environmental conditions and needs. Especially in large and complex refrigeration systems, the load distribution between equipment is often not reasonable, resulting in low system efficiency, serious energy waste and slow response speed. This situation not only increases operating costs, but also affects the stability and flexibility of the refrigeration system. Therefore, how to achieve intelligent allocation of refrigeration equipment loads, improve energy utilization efficiency, and respond to environmental changes in real time has become a technical problem that needs to be solved in the current refrigeration field. Summary of the invention

[0003] The present application provides a method and system for adaptively adjusting the refrigeration cycle of an equipment, which solves the technical problems of unreasonable load distribution, high energy consumption and slow response speed of refrigeration equipment in the prior art.

[0004] In view of the above problems, the present application provides a method and system for adaptively adjusting the refrigeration cycle of an equipment.

[0005] In a first aspect of the present application, a method for adaptively adjusting a refrigeration cycle of an equipment is provided, the method comprising: N temperature control edge nodes are preconfigured in N temperature control areas, wherein M refrigeration equipment covers the N temperature control areas through M integrated pipeline networks; the N temperature control edge nodes receive and analyze N regional multi-dimensional environmental data of the N temperature control areas to obtain N real-time cooling load demands; after the refrigeration collaborative control cloud receives the N real-time cooling load demands returned by the N temperature control edge nodes, the refrigeration load is distributed to the M refrigeration equipment through cooling load fitness optimization to obtain M real-time refrigeration loads, wherein the M real-time refrigeration loads are identified by M service area composition information; after the flow distribution of the M integrated pipeline networks is adjusted according to the M service area composition information, the M real-time refrigeration loads are used to perform refrigeration cycle adaptive adjustment on the M refrigeration equipment; a refrigeration cycle adjustment window is preset, and the refrigeration collaborative control cloud receives the N updated cooling load demands returned by the N temperature control edge nodes with the refrigeration cycle adjustment window as a constraint to perform refrigeration cycle intermittent adjustment of the M refrigeration equipment.

[0006] A second aspect of the present application provides an adaptive regulation system for a refrigeration cycle of an equipment, the system comprising: Configuration module: pre-configure N temperature control edge nodes in N temperature control areas, wherein M refrigeration equipment covers the N temperature control areas through M integrated pipeline networks; data processing module: the N temperature control edge nodes receive and analyze the N regional multi-dimensional environmental data of the N temperature control areas to obtain N real-time cooling load requirements; load distribution module: after the refrigeration collaborative control cloud receives the N real-time cooling load requirements returned by the N temperature control edge nodes, the M refrigeration equipment is distributed through cooling load fitness optimization to obtain M real-time cooling loads, wherein the M real-time cooling loads are identified by M service area composition information; flow regulation module: after the flow distribution of the M integrated pipeline networks is adjusted according to the M service area composition information, the M real-time cooling loads are used to perform refrigeration cycle adaptive adjustment on the M refrigeration equipment; intermittent adjustment module: a refrigeration cycle adjustment window is preset, and the refrigeration collaborative control cloud receives the N updated cooling load requirements returned by the N temperature control edge nodes with the refrigeration cycle adjustment window as a constraint to perform refrigeration cycle intermittent adjustment of the M refrigeration equipment.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, N temperature control edge nodes are preconfigured in N temperature control areas, where M refrigeration equipment covers the N temperature control areas through M integrated pipeline networks. Then, the N temperature control edge nodes receive and analyze the N regional multi-dimensional environmental data of the N temperature control areas to obtain N real-time cooling load requirements. Next, after the refrigeration collaborative control cloud receives the N real-time cooling load requirements transmitted back by the N temperature control edge nodes, the cooling load is distributed to the M refrigeration equipment through cooling load fitness optimization to obtain M real-time cooling loads, where the M real-time cooling loads are identified by M service area composition information. Then, after the flow distribution of the M integrated pipeline networks is adjusted according to the M service area composition information, the M real-time cooling loads are used to perform refrigeration cycle adaptive adjustment on the M refrigeration equipment. Finally, a refrigeration cycle adjustment window is preset, and the refrigeration collaborative control cloud receives the N updated cooling load requirements transmitted back by the N temperature control edge nodes with the refrigeration cycle adjustment window as a constraint to perform intermittent adjustment of the refrigeration cycle of the M refrigeration equipment. The invention solves the technical problems of unreasonable load distribution, high energy consumption and slow response speed of refrigeration equipment in the prior art, and achieves the technical effect of improving the efficiency of the refrigeration system and reducing energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] 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.

[0009] Figure 1 A schematic flow chart of a method for adaptively adjusting a refrigeration cycle of an equipment provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of an adaptive regulation system for a refrigeration cycle of an equipment provided in an embodiment of the present application.

[0010] Explanation of the reference numerals: configuration module 11 , data processing module 12 , load distribution module 13 , flow regulation module 14 , intermittent regulation module 15 . DETAILED DESCRIPTION

[0011] The present application solves the technical problems of unreasonable load distribution, high energy consumption and slow response speed of refrigeration equipment in the prior art by providing a method and system for adaptively adjusting the refrigeration cycle of the equipment.

[0012] 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.

[0013] It should be noted that the terms "including" and "having" 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 are inherent to these processes, methods, products or devices.

[0014] Embodiment 1, as Figure 1 As shown, the present application provides a method for adaptively adjusting a refrigeration cycle of an equipment, wherein the method comprises: N temperature-controlled edge nodes are preconfigured in N temperature-controlled areas, wherein M refrigeration devices cover the N temperature-controlled areas through M integrated pipeline networks.

[0015] There are N different temperature control areas in the system, and each area needs to maintain a specific temperature to meet the cooling needs of different environments or spaces. These areas may be different rooms, floors, or different parts of a building. Among them, the N temperature control areas are covered by M refrigeration equipment through M integrated pipe networks. The refrigeration equipment (such as central air conditioners, etc.) transports refrigerants through the integrated pipe network to adjust the temperature to ensure that the temperature control requirements of each area are met.

[0016] A temperature control edge node is configured in each temperature control area, with a total of N temperature control edge nodes. Each temperature control edge node is responsible for receiving and analyzing the environmental data in the area, including temperature, humidity, etc., and calculating the real-time cooling load demand of the area based on these data.

[0017] Furthermore, N temperature control edge nodes are preconfigured in N temperature control areas, and the method includes: Interactively obtain a first real-time target temperature of the first temperature control area; with the first real-time target temperature as a constraint, perform local data calls to obtain multiple sample cooling load demands and multiple sample area environmental data, wherein the sample area environmental data includes sample temperature, sample humidity, sample personnel activity, sample personnel density, sample equipment heat load and sample area air flow; generate a first cooling load prediction function by performing multivariate regression analysis on the multiple sample cooling load demands and multiple sample area environmental data; pre-configure a first temperature control edge node in the first temperature control area, wherein the first temperature control edge node includes a cooling load prediction unit, an environmental data acquisition unit and a load anomaly analysis unit; load the first cooling load prediction function into the cooling load prediction unit to complete the local update of the first temperature control edge node; and so on, pre-configure the N temperature control edge nodes in the N temperature control areas, and perform local updates of the N temperature control edge nodes according to the N real-time target temperatures of the N temperature control areas.

[0018] Specifically, the first real-time target temperature of the first temperature control area is obtained by interacting with the control system of the refrigeration equipment, and the first real-time target temperature represents the target temperature currently required for the first temperature control area; next, the first real-time target temperature is used as a constraint condition for cooling load prediction, and historical data close to or related to the target temperature is called in the local database to obtain multiple sample cooling load demands and multiple sample area environmental data, wherein the sample area environmental data includes sample temperature, sample humidity, sample personnel activity, sample personnel density, sample equipment heat load and sample area air flow, etc., reflecting the dynamic environmental changes in the area.

[0019] Using the statistical multivariate regression analysis method, the collected multiple sample cooling load demands and multiple sample regional environmental data are deeply analyzed, and multiple environmental data are used as independent variables and multiple cooling load demands as dependent variables. The relationship between cooling load and environmental data is obtained through mathematical modeling, and then the first cooling load prediction function is obtained. The first cooling load prediction function is used to predict the cooling load demand required under different environmental conditions. Specifically, regression analysis determines the degree of influence of each environmental factor on the cooling load demand by calculating the regression coefficient. For example, changes in temperature and humidity will have different effects on the cooling load, and changes in personnel activities and equipment heat load may also directly lead to fluctuations in the cooling load; through these environmental data, regression analysis can generate a function model that can accurately predict the amount of cooling load required under different environmental conditions.

[0020] Next, three key units are preconfigured in the temperature control edge node of the first temperature control area: a cooling load prediction unit, an environmental data acquisition unit, and a load anomaly analysis unit. The cooling load prediction unit loads and applies the generated first cooling load prediction function, calculates the cooling load demand of the area in real time according to the latest environmental data, and adjusts the cooling load; the environmental data acquisition unit is responsible for continuously collecting environmental change data in the area; and the load anomaly analysis unit is used to monitor load demand fluctuations in real time, analyze whether there is an abnormal load, and adjust the prediction function and load regulation strategy as needed. The generated first cooling load prediction function is loaded into the cooling load prediction unit to complete the local update of the first temperature control edge node. At this point, the first temperature control edge node can dynamically adjust the cooling load demand according to the latest environmental data and cooling load prediction function to optimize the cooling load.

[0021] After completing the update of the first temperature control area, the system will configure the corresponding temperature control edge nodes in the other N-1 temperature control areas, and follow the same process to obtain the real-time target temperature of each area, collect multi-dimensional environmental data, perform regression analysis, and update the load prediction function of each area. In this way, the entire system realizes adaptive adjustment based on edge computing, and can automatically optimize the load distribution of refrigeration equipment according to the real-time environmental changes and cooling load requirements of each area, improve system operation efficiency and reduce energy consumption.

[0022] The N temperature control edge nodes receive and analyze the N regional multi-dimensional environmental data of the N temperature control areas to obtain N real-time cooling load demands.

[0023] The main function of the N temperature control edge nodes is to receive and analyze environmental data from their respective temperature control areas to calculate the real-time cooling load demand of the area. The temperature control edge nodes in each temperature control area obtain multi-dimensional environmental data by connecting to sensors and monitoring equipment in the area. The multi-dimensional environmental data includes but is not limited to factors such as temperature, humidity, personnel activity, personnel density, equipment heat load, air flow, etc., which directly affect the cooling load demand of the area. Each temperature control edge node will calculate the real-time cooling load demand of the current area by collecting and processing these environmental data in real time, combined with the preset cooling load prediction function. These demands reflect the cooling capacity required in the area, that is, the cooling capacity that needs to be provided by the refrigeration equipment.

[0024] Furthermore, the N temperature control edge nodes receive and analyze the N regional multi-dimensional environmental data of the N temperature control areas to obtain N real-time cooling load requirements, and the method includes: In the first temperature-controlled edge node, the environmental data acquisition unit receives in real time the first-region multi-dimensional environmental data transmitted back by the first environmental sensor array, wherein the data acquisition time span of the first-region multi-dimensional environmental data satisfies the refrigeration cycle adjustment window; the cold load prediction unit receives and performs cold load prediction based on the first-region multi-dimensional environmental data to obtain a first predicted cold load sequence; after constructing a first cold load demand curve according to the first predicted cold load sequence, a sliding average method is used to perform short-term prediction on the first cold load demand curve to output a first real-time cold load demand, wherein the effective time of the first real-time cold load demand is 1 / K of the refrigeration cycle adjustment window; and so on, the N temperature-controlled edge nodes receive and analyze the N-region multi-dimensional environmental data to obtain the N real-time cold load demands.

[0025] Taking the first temperature control edge node as an example, first, the environmental data acquisition unit receives the multi-dimensional environmental data of the first area transmitted back from the first environmental sensor array in real time. The time span covered by these data acquisition must meet the requirements of the refrigeration cycle adjustment window, that is, the data acquisition needs to ensure that it can reflect the environmental changes in the temperature control area and provide sufficient real-time data for the subsequent cold load prediction. Then, after receiving these environmental data, the cold load prediction unit will perform cold load prediction based on the multi-dimensional environmental data of the first area; by using the previously established cold load prediction model, the system can predict the cold load demand of the area according to the real-time environmental data and generate a first predicted cold load sequence. The first predicted cold load sequence contains the expected cold load demand changes in the future (usually corresponding to the refrigeration cycle adjustment window), for example, based on the data of the last few minutes, the load demand in the next 1 minute is predicted. Then, using the first predicted cold load sequence, the system constructs a first cold load demand curve, which can depict the cold load change trend of the area in the predicted time period. In order to achieve short-term cold load demand prediction, the system uses the sliding average method to smooth this cold load demand curve, reduce the noise and fluctuation in the data, and obtain more accurate prediction results. Based on the prediction results generated by the sliding average method, the system finally outputs the first real-time cooling load demand, the effective duration of which is 1 / K of the refrigeration cycle adjustment window, where K is the coefficient of the refrigeration cycle adjustment window, which represents the proportional relationship between the time span of the predicted cooling load demand and the refrigeration cycle adjustment window. Through this process, the first temperature control edge node can perform real-time cooling load adjustment based on the environmental data and the results of the cooling load prediction. Similarly, the other N temperature control edge nodes will also receive and analyze the multi-dimensional environmental data of their respective temperature control areas in the same way, and generate and output the corresponding real-time cooling load demand. In this way, through the real-time data and prediction results of each temperature control area, the system can achieve precise control of the cooling load, ensuring that the entire system can flexibly respond to environmental changes and cooling load demands in each area.

[0026] After the refrigeration collaborative control cloud receives the N real-time cooling load demands returned by the N temperature control edge nodes, the cooling load is distributed to the M refrigeration equipment through cooling load fitness optimization to obtain M real-time cooling loads, wherein the M real-time cooling loads are identified by information formed by M service areas.

[0027] After receiving N real-time cooling load demands from N temperature-controlled edge nodes, the cooling collaborative control cloud uses the cooling load fitness optimization algorithm to distribute the cooling load to the M cooling devices to ensure that each cooling device reasonably distributes the load according to the cooling load demand of each temperature-controlled area, thereby improving the overall efficiency of the system.

[0028] Specifically, the refrigeration collaborative control cloud will first summarize and analyze the N real-time cooling load demands transmitted back to ensure that the cooling load demand of each temperature-controlled area is accurately reflected. Then, the cloud calculates the real-time cooling load that each refrigeration device should bear based on the real-time cooling load demand of each area and the current status of the refrigeration equipment through the cooling load fitness optimization algorithm. The cooling load fitness optimization algorithm takes into account factors such as the load capacity, working status, and energy efficiency performance of each refrigeration equipment to achieve balanced load distribution and maximize energy efficiency. After obtaining M real-time cooling loads, the refrigeration collaborative control cloud associates these loads with M service area composition information (referring to the service area composition of the refrigeration equipment). Each real-time cooling load corresponds to a service area identifier, indicating which area the cooling load serves.

[0029] Furthermore, after the refrigeration collaborative control cloud receives the N real-time cooling load demands transmitted back by the N temperature control edge nodes, the cooling load is distributed to the M refrigeration equipment through cooling load adaptability optimization to obtain M real-time cooling loads, and the method includes: Taking the M refrigeration load limits of the M refrigeration equipment; taking the M refrigeration load limits as load constraints, allocating the N real-time cooling load demands, and obtaining M groups of real-time cooling load demands; dividing the N temperature control areas into M first initial area compositions according to the source mapping of the N real-time cooling load demands and the N temperature control edge nodes; calling the M first cooling loss information of the M first initial area compositions from the cooling loss table; using the M groups of real-time cooling load demands and the M first cooling loss information to evaluate the cooling load fitness, and outputting the first cooling load fitness; performing regional exchange and updating on the M first initial area compositions according to the first cooling load fitness, and performing cooling load fitness evaluation according to the update result, and outputting the second cooling load fitness; and so on, performing regional composition exchange and updating and cooling load fitness evaluation according to the cooling load fitness, until obtaining the M service area composition information that meets the cooling load adaptation condition; grouping and adding the N real-time cooling load demands according to the M service area composition information, and obtaining the M real-time cooling loads.

[0030] Specifically, based on the refrigeration load limit of M refrigeration equipment, that is, the maximum load capacity of each refrigeration equipment, as the constraint condition for load distribution, on this basis, N real-time cooling load demands are distributed according to the load capacity to obtain M groups of real-time cooling load demands, ensuring that the cooling load allocated to each refrigeration equipment does not exceed its load limit; next, based on the source mapping of N real-time cooling load demands and N temperature control edge nodes, the N temperature control areas are divided into M first initial area compositions, each of which contains the cooling load demands of one or more temperature control areas, ensuring that the cooling load demands of these areas can be processed by the corresponding refrigeration equipment; the M first cooling loss information related to the M first initial area compositions is called from the cooling loss table, and this part of information is used to evaluate each area. The energy loss of the domain in the process of transmitting cold air, wherein the first cold loss information includes the cold loss caused by factors such as pipeline transmission and equipment efficiency, and the cold loss table is composed of the cold loss rates of M integrated pipelines of M refrigeration equipment in N regions; the M groups of real-time cold load demand are combined with the M first cold loss information to evaluate the cold load fitness and output the first refrigeration load fitness, which reflects the matching degree between the current cold load demand and the refrigeration equipment. The higher the value, the more reasonable the load distribution; according to the first refrigeration load fitness, the M first initial regional compositions are exchanged and updated, that is, the load distribution is optimized by adjusting the refrigeration equipment allocation in each region; after the update, the cold load fitness is evaluated again and the second refrigeration load fitness is output. By analogy, the regional composition exchange and update and the cold load fitness evaluation are continuously performed according to the refrigeration load fitness until the composition information of M service regions that meet the refrigeration load adaptation conditions is obtained. Finally, based on the information grouping of M service areas and the N real-time cooling load demands, M real-time cooling loads are obtained, that is, the final load distribution of each refrigeration equipment, ensuring that the refrigeration equipment can work efficiently according to actual needs and optimizing the energy efficiency and response speed of the system.

[0031] Further, the M groups of real-time cooling load demands and the M first cooling loss information are used to evaluate cooling load fitness and output a first cooling load fitness, the method comprising: The M groups of real-time cooling load demands are summed within the group to obtain M initial cooling loads; the M first cooling loss information are summed within the group to obtain M initial cooling losses; the M initial cooling losses are input into a cooling load compensation network, and M initial cooling load compensations are obtained through analysis; after mapping and summing the M initial cooling loads and the M initial cooling load compensations, normalization is performed according to M standard cooling power consumptions of the M refrigeration equipment to generate M normalized cooling loads; load distribution deviation of the M normalized cooling loads is evaluated, and the first cooling load fitness is output.

[0032] Specifically, M groups of real-time cooling load demands are summed up within the group to obtain M initial cooling loads, which reflect the load required to be borne by each cooling device, ensuring the initial distribution of the load; M first cooling loss information are summed up within the group to obtain M initial cooling losses, which reflect the energy loss in the cooling load transmission process, taking into account the influence of factors such as pipelines, equipment and air flow; the M initial cooling losses are input into the cooling load compensation network for analysis to obtain M initial cooling load compensations, where the cooling load compensation network is a prediction system based on machine learning or empirical models, which is used to calculate the additional cooling load required according to the cooling loss information. Cooling capacity; Map and add the M initial cooling loads and the M initial cooling load compensations to obtain the comprehensive cooling load demand; Normalize the summed results according to the standard cooling power consumption of the M cooling equipment to generate M normalized cooling loads to ensure that the load distribution of each device is adapted to its performance specifications to avoid overload or poor efficiency; Evaluate the load distribution deviation of these M normalized cooling loads. The load distribution deviation evaluation may involve calculating the uniformity of the load distribution, the degree of deviation from the standard power consumption, and other indicators to evaluate the rationality of the current load distribution plan; By evaluating the balance of the load distribution of each device, it is determined whether there is an uneven load. Through this evaluation, the first cooling load fitness is output, indicating the rationality of the current load distribution plan. The higher the fitness, the more reasonable the load distribution, and the higher the cooling efficiency and energy utilization of the system.

[0033] Further, the M first initial regions are updated by region exchange according to the first refrigeration load fitness, and the refrigeration load fitness is evaluated according to the update result to output the second refrigeration load fitness, the method comprising: The M first initial regional compositions are used as the starting point of regional allocation, and M first updated regional compositions are updated through regional exchange; the N real-time cooling load demands are allocated according to the M first updated regional compositions to obtain M first updated cooling load demands; the M second cooling loss information of the M first updated regional compositions is called from the cooling loss table; the first updated cooling load demand and the M second cooling loss information are used to evaluate the cooling load fitness, and the second cooling load fitness is output; if the second cooling load fitness is better than the first cooling load fitness, and the second cooling load fitness and the first cooling load fitness do not meet the cooling load adaptation condition, the first updated regional composition is used as the starting point of regional allocation, and M second updated regional compositions and M second updated cooling load demands are updated through regional exchange; the second updated cooling load demand and the M second cooling loss information are used to evaluate the cooling load fitness, and the third cooling load fitness is output; and so on, the starting point of regional allocation is determined by comparing the cooling load fitness, and the regional composition is updated and the cooling load fitness is evaluated based on the starting point of regional allocation, until the M service regional composition information that meets the cooling load adaptation condition is obtained.

[0034] Specifically, the M first initial area compositions are taken as the starting point of area allocation, and area exchange is performed through a certain strategy (such as random exchange, heuristic algorithm, etc.) to generate M first updated area compositions; according to the M first updated area compositions, the N real-time cooling load demands are reallocated to obtain M first updated cooling load demands; the M second cooling loss information corresponding to the M first updated area compositions are called from the cooling loss table; the first updated cooling load demand and the M second cooling loss information are used to evaluate the cooling load fitness, and the second cooling load fitness is output. Compare the second cooling load fitness with the first cooling load fitness. If the second cooling load fitness is better and neither meets the cooling load adaptation condition, then take the first updated area composition as a new starting point, and continue to update the M second updated area compositions and corresponding cooling load requirements through area exchange; use the second updated cooling load requirements and corresponding cooling loss information to perform a new fitness evaluation, output the third cooling load fitness, and by comparing with the previous round of fitness, decide whether to continue to update the area allocation, and so on, continuously iterate the update of the area composition and perform the fitness evaluation; the iterative process continues until M service area composition information that meets the cooling load adaptation condition is found. Through multiple rounds of area exchange updates and cooling load fitness evaluation, M service area composition information is finally obtained to ensure that the load distribution plan of the refrigeration equipment is optimal, and can be flexibly adjusted according to real-time needs to improve the energy efficiency and response speed of the system, and finally meet the cooling needs of all temperature control areas.

[0035] Further, calling the M first cold loss information formed by the M first initial regions from the cold loss table includes: Calling N groups of cold loss coefficients of the N temperature-controlled areas, wherein each group of cold loss coefficients includes M integrated pipeline cold loss rates of M refrigeration equipment; associatively storing the N temperature-controlled areas and the N groups of cold loss coefficients based on the knowledge graph, completing the construction of the cold loss table; calling the M groups of first integrated pipeline cold loss rates consisting of the M first initial areas from the cold loss table; mapping and weighting the M groups of real-time cold load demands and the M groups of first integrated pipeline cold loss rates to obtain M groups of cold loss load deviations; the M groups of cold loss load deviations constitute the M first cold loss information.

[0036] Specifically, N groups of cold loss coefficients of N temperature-controlled areas are called, and each group of cold loss coefficients contains M integrated pipeline cold loss rates of M refrigeration equipment. These cold loss rates reflect the energy loss of each refrigeration equipment when delivering cold air through pipelines. Then, based on the knowledge graph, N temperature-controlled areas and the corresponding N groups of cold loss coefficients are associated and stored, and these data are constructed into a cold loss table. In the knowledge graph, the association between the temperature-controlled areas and the cold loss coefficients is recorded to facilitate subsequent calls and updates. When the cold load fitness evaluation is required, the cold loss rates of the first integrated pipelines composed of the M first initial areas are called from the cold loss table. These cold loss rates are directly associated with each initial area and refrigeration equipment, indicating the loss during the cold air transmission process in these areas. Next, the real-time cold load demand of the M groups is mapped and weighted with the cold loss rate of the first integrated pipeline of the M groups, and the cold loss load deviation of each area is obtained by weighted calculation. These cold loss load deviations reflect the load adjustment requirements caused by the loss of cold air transmission. Finally, the M groups of cooling loss load deviations constitute the M first cooling loss information, which will be used in the subsequent cooling load fitness evaluation to evaluate the effect of the current load distribution scheme.

[0037] After the flow distribution of the M integrated pipeline networks is adjusted according to the composition information of the M service areas, the M real-time refrigeration loads are used to perform refrigeration cycle adaptive adjustment on the M refrigeration equipment.

[0038] Based on the composition information of the M service areas obtained through the optimization of cooling load adaptability, the system establishes a mapping relationship between the cooling load demand of each service area and the corresponding refrigeration equipment. At this time, the flow distribution of each integrated pipeline network is adjusted according to the cooling load demand of the area to ensure that the cooling air supply in each area meets the real-time cooling load demand.

[0039] The adjusted flow distribution will be used to guide the cold air circulation of the refrigeration equipment. Specifically, M real-time refrigeration loads, that is, the load amount allocated to each refrigeration equipment according to the real-time demand, will be used as input signals to adjust the operating status of each refrigeration equipment; based on these real-time refrigeration loads, the system will perform adaptive refrigeration cycle adjustment on the M refrigeration equipment. The refrigeration equipment will optimize its operating power according to the input cold load demand and flow adjustment parameters to ensure that the real-time cooling demand of each temperature control area is met.

[0040] A refrigeration cycle adjustment window is preset, and the refrigeration collaborative control cloud receives the N updated cooling load demands returned by the N temperature control edge nodes based on the refrigeration cycle adjustment window to perform intermittent adjustment of the refrigeration cycles of the M refrigeration equipment.

[0041] A refrigeration cycle adjustment window is preset, and the time length of the window is set according to the system operation requirements and the equipment response speed. The function of the refrigeration cycle adjustment window is to provide a time limit for the load adjustment of each refrigeration equipment to avoid excessive energy consumption and equipment wear caused by too frequent load adjustment. In this window, the system will receive N updated cold load demands sent back from N temperature control edge nodes. These demands reflect the changes in the cold load of each temperature control area at the current moment. Then, based on these N updated cold load demands sent back, the refrigeration collaborative control cloud performs intermittent refrigeration cycle adjustment on M refrigeration equipment through intelligent algorithms and control strategies. The adjustment may include adjusting the operating power of the refrigeration equipment, turning on or off some equipment, changing the flow and pressure of the refrigerant, etc. For example, when the load is low, the working intensity of the equipment is reduced accordingly, the intensity of the refrigeration cycle is weakened, and the equipment may enter a low-power operation state, thereby avoiding energy waste. In the low-load state, the workload of components such as the compressor, condenser, and expansion valve will be reduced accordingly, thereby achieving energy saving. When the load fluctuates, the refrigeration equipment needs to respond quickly and adjust the various parameters of the refrigeration cycle to ensure stable operation of the system and meet the temperature control requirements. For example, when the load suddenly increases, the system needs to quickly increase the refrigerant flow rate and enhance the working intensity of the compressor to improve the refrigeration capacity; when the load decreases, the system will automatically reduce the refrigerant flow rate and reduce the equipment power to prevent energy waste.

[0042] In summary, the embodiments of the present application have at least the following technical effects: First, an image sensor is configured in the printing quality inspection area, and the target printing product is sensed and collected to obtain a printing image. Then, the printing image is transmitted back, and the image is segmented and grayscale processed based on the boundary of the printing product to determine the grayscale printing image. Further, a standard printing template is obtained, and a pixel stack space is constructed to supervise the training of the printing registration module, wherein the printing registration module includes a first pixel registration unit and a second pixel registration unit, and the first acquisition registration is performed by pixel transition sampling, and the second acquisition registration is performed by pixel interval sampling. Then, the grayscale printing image is transmitted to the printing registration module, and the defective pixel features are determined by performing pixel transition sampling registration and pixel interval sampling registration. Finally, the defective pixel features are traversed, and defect type matching is performed based on the defect matcher, and the printing quality data is output. The technical problems of unreasonable load distribution, high energy consumption and slow response speed of refrigeration equipment in the prior art are solved, and the technical effect of improving the accuracy and efficiency of printing quality detection is achieved.

[0043] Embodiment 2, based on the same inventive concept as the method for adaptively adjusting a refrigeration cycle of a device in the above embodiment, Figure 2 As shown, the present application provides an adaptive regulation system for a refrigeration cycle of an equipment, wherein the system comprises: Configuration module 11: pre-configure N temperature control edge nodes in N temperature control areas, where M refrigeration equipment covers the N temperature control areas through M integrated pipeline networks; data processing module 12: the N temperature control edge nodes receive and analyze the N regional multi-dimensional environmental data of the N temperature control areas to obtain N real-time cooling load requirements; load distribution module 13: after the cooling collaborative control cloud receives the N real-time cooling load requirements returned by the N temperature control edge nodes, it distributes the cooling load of the M refrigeration equipment through cooling load fitness optimization to obtain M real-time cooling loads , wherein the M real-time refrigeration loads are identified by M service area composition information; a flow regulation module 14: after the flow distribution of the M integrated pipeline networks is adjusted according to the M service area composition information, the M real-time refrigeration loads are used to perform refrigeration cycle adaptive adjustment on the M refrigeration equipment; an intermittent adjustment module 15: a refrigeration cycle adjustment window is preset, and the refrigeration collaborative control cloud receives the N updated cooling load demands sent back by the N temperature control edge nodes with the refrigeration cycle adjustment window as a constraint to perform refrigeration cycle intermittent adjustment of the M refrigeration equipment.

[0044] Furthermore, the load distribution module 13 is used to perform the following method: Taking the M refrigeration load limits of the M refrigeration equipment; taking the M refrigeration load limits as load constraints, allocating the N real-time cooling load demands, and obtaining M groups of real-time cooling load demands; dividing the N temperature control areas into M first initial area compositions according to the source mapping of the N real-time cooling load demands and the N temperature control edge nodes; calling the M first cooling loss information of the M first initial area compositions from the cooling loss table; using the M groups of real-time cooling load demands and the M first cooling loss information to evaluate the cooling load fitness, and outputting the first cooling load fitness; performing regional exchange and updating on the M first initial area compositions according to the first cooling load fitness, and performing cooling load fitness evaluation according to the update result, and outputting the second cooling load fitness; and so on, performing regional composition exchange and updating and cooling load fitness evaluation according to the cooling load fitness, until obtaining the M service area composition information that meets the cooling load adaptation condition; grouping and adding the N real-time cooling load demands according to the M service area composition information, and obtaining the M real-time cooling loads.

[0045] Furthermore, the load distribution module 13 is used to perform the following method: The M groups of real-time cooling load demands are summed within the group to obtain M initial cooling loads; the M first cooling loss information are summed within the group to obtain M initial cooling losses; the M initial cooling losses are input into a cooling load compensation network, and M initial cooling load compensations are obtained through analysis; after mapping and summing the M initial cooling loads and the M initial cooling load compensations, normalization is performed according to M standard cooling power consumptions of the M refrigeration equipment to generate M normalized cooling loads; load distribution deviation of the M normalized cooling loads is evaluated, and the first cooling load fitness is output.

[0046] Furthermore, the load distribution module 13 is used to perform the following method: The M first initial regional compositions are used as the starting point of regional allocation, and M first updated regional compositions are updated through regional exchange; the N real-time cooling load demands are allocated according to the M first updated regional compositions to obtain M first updated cooling load demands; the M second cooling loss information of the M first updated regional compositions is called from the cooling loss table; the first updated cooling load demand and the M second cooling loss information are used to evaluate the cooling load fitness, and the second cooling load fitness is output; if the second cooling load fitness is better than the first cooling load fitness, and the second cooling load fitness and the first cooling load fitness do not meet the cooling load adaptation condition, the first updated regional composition is used as the starting point of regional allocation, and M second updated regional compositions and M second updated cooling load demands are updated through regional exchange; the second updated cooling load demand and the M second cooling loss information are used to evaluate the cooling load fitness, and the third cooling load fitness is output; and so on, the starting point of regional allocation is determined by comparing the cooling load fitness, and the regional composition is updated and the cooling load fitness is evaluated based on the starting point of regional allocation, until the M service regional composition information that meets the cooling load adaptation condition is obtained.

[0047] Furthermore, the load distribution module 13 is used to perform the following method: Calling N groups of cold loss coefficients of the N temperature-controlled areas, wherein each group of cold loss coefficients includes M integrated pipeline cold loss rates of M refrigeration equipment; associatively storing the N temperature-controlled areas and the N groups of cold loss coefficients based on the knowledge graph, completing the construction of the cold loss table; calling the M groups of first integrated pipeline cold loss rates consisting of the M first initial areas from the cold loss table; mapping and weighting the M groups of real-time cold load demands and the M groups of first integrated pipeline cold loss rates to obtain M groups of cold loss load deviations; the M groups of cold loss load deviations constitute the M first cold loss information.

[0048] Furthermore, the configuration module 11 is used to execute the following method: Interactively obtain a first real-time target temperature of the first temperature control area; with the first real-time target temperature as a constraint, perform local data calls to obtain multiple sample cooling load demands and multiple sample area environmental data, wherein the sample area environmental data includes sample temperature, sample humidity, sample personnel activity, sample personnel density, sample equipment heat load and sample area air flow; generate a first cooling load prediction function by performing multivariate regression analysis on the multiple sample cooling load demands and multiple sample area environmental data; pre-configure a first temperature control edge node in the first temperature control area, wherein the first temperature control edge node includes a cooling load prediction unit, an environmental data acquisition unit and a load anomaly analysis unit; load the first cooling load prediction function into the cooling load prediction unit to complete the local update of the first temperature control edge node; and so on, pre-configure the N temperature control edge nodes in the N temperature control areas, and perform local updates of the N temperature control edge nodes according to the N real-time target temperatures of the N temperature control areas.

[0049] Furthermore, the data processing module 12 is used to execute the following method: In the first temperature-controlled edge node, the environmental data acquisition unit receives in real time the first-region multi-dimensional environmental data transmitted back by the first environmental sensor array, wherein the data acquisition time span of the first-region multi-dimensional environmental data satisfies the refrigeration cycle adjustment window; the cold load prediction unit receives and performs cold load prediction based on the first-region multi-dimensional environmental data to obtain a first predicted cold load sequence; after constructing a first cold load demand curve according to the first predicted cold load sequence, a sliding average method is used to perform short-term prediction on the first cold load demand curve to output a first real-time cold load demand, wherein the effective time of the first real-time cold load demand is 1 / K of the refrigeration cycle adjustment window; and so on, the N temperature-controlled edge nodes receive and analyze the N-region multi-dimensional environmental data to obtain the N real-time cold load demands.

[0050] 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 or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0051] 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.

[0052] 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. A method for adaptively adjusting a refrigeration cycle of an equipment, characterized in that: The method comprises: Preconfiguring N temperature control edge nodes in N temperature control areas, wherein M refrigeration equipment covers the N temperature control areas through M integrated pipeline networks; The N temperature control edge nodes receive and analyze N regional multi-dimensional environmental data of the N temperature control areas to obtain N real-time cooling load demands; After receiving the N real-time cooling load demands transmitted back by the N temperature control edge nodes, the cooling collaborative control cloud allocates cooling loads to the M cooling devices through cooling load fitness optimization to obtain M real-time cooling loads, wherein the M real-time cooling loads are identified by M service area composition information; After adjusting the flow distribution of the M integrated pipeline networks according to the composition information of the M service areas, adaptively adjusting the refrigeration cycles of the M refrigeration equipment using the M real-time refrigeration loads; A refrigeration cycle adjustment window is preset, and the refrigeration collaborative control cloud receives the N updated cooling load demands returned by the N temperature control edge nodes based on the refrigeration cycle adjustment window to perform intermittent adjustment of the refrigeration cycles of the M refrigeration equipment.

2. The method for adaptively adjusting a refrigeration cycle of an equipment according to claim 1, characterized in that: After the refrigeration collaborative control cloud receives the N real-time cooling load demands transmitted back by the N temperature control edge nodes, the cooling load is distributed to the M refrigeration equipment through cooling load fitness optimization to obtain M real-time cooling loads. The method includes: Based on the M refrigeration load limits of the M refrigeration equipments; Taking the M refrigeration load limits as load constraints, allocating the N real-time cooling load demands, and obtaining M groups of real-time cooling load demands; According to the source mapping of the N real-time cooling load demands and the N temperature control edge nodes, the N temperature control areas are divided into M first initial areas; Retrieving M first cold loss information consisting of the M first initial areas from the cold loss table; Using the M groups of real-time cooling load demands and the M first cooling loss information to evaluate cooling load adaptability, and outputting a first cooling load adaptability; Performing regional exchange update on the M first initial regional configurations according to the first refrigeration load fitness, and evaluating the refrigeration load fitness according to the update result, and outputting a second refrigeration load fitness; By analogy, the regional composition exchange and update and the cooling load fitness evaluation are performed according to the cooling load fitness until the composition information of the M service areas that meet the cooling load fitness condition is obtained; The M real-time cooling loads are obtained by grouping and adding the N real-time cooling load demands according to the M service area composition information.

3. The method for adaptively adjusting a refrigeration cycle of an equipment according to claim 2, characterized in that: The M groups of real-time cooling load demands and the M first cooling loss information are used to evaluate cooling load fitness and output a first cooling load fitness. The method includes: Adding the real-time cooling load demands of the M groups within the group to obtain M initial cooling loads; Adding the M pieces of first cooling loss information within a group to obtain M initial cooling losses; Inputting the M initial cooling losses into the cooling load compensation network, and analyzing to obtain M initial cooling load compensations; After mapping and adding the M initial cooling loads and the M initial cooling load compensations, normalization processing is performed according to the M standard cooling power consumptions of the M cooling devices to generate M normalized cooling loads; A load distribution deviation evaluation is performed on the M normalized refrigeration loads, and the first refrigeration load fitness is output.

4. The method for adaptively adjusting a refrigeration cycle of an equipment according to claim 2, characterized in that: The M first initial regions are updated by region exchange according to the first refrigeration load fitness, and a refrigeration load fitness evaluation is performed according to the update result to output a second refrigeration load fitness. The method includes: Taking the M first initial area compositions as the area allocation starting points, and updating M first updated area compositions by area exchange; Allocating the N real-time cooling load demands according to the M first update regions to obtain M first updated cooling load demands; Retrieving M second cold loss information consisting of the M first update areas from the cold loss table; Using the first updated cooling load demand and the M second cooling loss information to evaluate cooling load fitness, and outputting a second cooling load fitness; If the second refrigeration load fitness is better than the first refrigeration load fitness, and both the second refrigeration load fitness and the first refrigeration load fitness do not meet the refrigeration load adaptation condition, the first updated area composition is used as the area allocation starting point, and M second updated area compositions and M second updated cooling load requirements are updated through area exchange; Using the second updated cooling load demand and the M second cooling loss information to evaluate cooling load fitness, and outputting a third cooling load fitness; By analogy, the area allocation starting point is determined by comparing the cooling load adaptability, and the area composition is updated and the cooling load adaptability is evaluated based on the area allocation starting point until the composition information of the M service areas that meet the cooling load adaptability condition is obtained.

5. The method for adaptively adjusting a refrigeration cycle of an equipment as claimed in claim 2, characterized in that: Retrieving M first cold loss information formed by the M first initial regions from the cold loss table, the method comprising: Calling N groups of cooling loss coefficients of the N temperature control areas, wherein each group of cooling loss coefficients includes cooling loss rates of M integrated pipelines of M refrigeration equipment; The N temperature control areas and the N groups of cooling loss coefficients are stored in association with each other based on the knowledge graph to complete the construction of the cooling loss table; Retrieving the cold loss rates of the M groups of first integrated pipelines formed by the M first initial areas from the cold loss table; Mapping the weighted real-time cooling load demand of the M group and the cooling loss rate of the first integrated pipeline of the M group to obtain the cooling loss load deviation of the M group; The M groups of cooling loss load deviations constitute the M first cooling loss information.

6. The method for adaptively adjusting a refrigeration cycle of an equipment according to claim 1, characterized in that: Pre-configuring N temperature control edge nodes in N temperature control areas, the method comprising: interactively obtaining a first real-time target temperature of a first temperature control area; Taking the first real-time target temperature as a constraint, local data is called to obtain multiple sample cooling load requirements and multiple sample area environmental data, wherein the sample area environmental data includes sample temperature, sample humidity, sample personnel activity, sample personnel density, sample equipment heat load and sample area air flow; Generate a first cooling load prediction function by performing a multivariate regression analysis on the plurality of sample cooling load demands and a plurality of sample regional environmental data; Preconfiguring a first temperature control edge node in the first temperature control area, wherein the first temperature control edge node includes a cooling load prediction unit, an environmental data collection unit, and a load anomaly analysis unit; Loading the first cooling load prediction function into the cooling load prediction unit to complete the local update of the first temperature control edge node; By analogy, the N temperature control edge nodes are preconfigured in the N temperature control areas, and the N temperature control edge nodes are locally updated according to the N real-time target temperatures of the N temperature control areas.

7. A method for adaptively adjusting a refrigeration cycle of an equipment as claimed in claim 6, characterized in that: The N temperature control edge nodes receive and analyze the N regional multi-dimensional environmental data of the N temperature control areas to obtain N real-time cooling load requirements, and the method includes: In the first temperature control edge node, the environmental data acquisition unit receives in real time the first regional multi-dimensional environmental data transmitted back by the first environmental sensor array, wherein the data acquisition time span of the first regional multi-dimensional environmental data meets the refrigeration cycle adjustment window; The cooling load prediction unit receives and performs cooling load prediction based on the first regional multi-dimensional environmental data to obtain a first predicted cooling load sequence; After constructing a first cooling load demand curve according to the first predicted cooling load sequence, a sliding average method is used to perform short-term prediction on the first cooling load demand curve, and a first real-time cooling load demand is output, wherein the effective duration of the first real-time cooling load demand is 1 / K of the refrigeration cycle adjustment window; By analogy, the N temperature control edge nodes receive and analyze the multi-dimensional environmental data of the N regions to obtain the N real-time cooling load demands.

8. An adaptive regulation system for a refrigeration cycle of an equipment, characterized in that: A method for implementing an adaptive regulation method of a refrigeration cycle of an equipment according to any one of claims 1 to 7, the system comprising: Configuration module: pre-configure N temperature control edge nodes in N temperature control areas, wherein M refrigeration equipment covers the N temperature control areas through M integrated pipeline networks; Data processing module: the N temperature control edge nodes receive and analyze the N regional multi-dimensional environmental data of the N temperature control areas to obtain N real-time cooling load requirements; Load distribution module: After receiving the N real-time cooling load demands transmitted back by the N temperature control edge nodes, the cooling collaborative control cloud distributes the cooling loads to the M cooling devices through cooling load fitness optimization to obtain M real-time cooling loads, wherein the M real-time cooling loads are identified by M service area composition information; A flow regulation module: after adjusting the flow distribution of the M integrated pipeline networks according to the composition information of the M service areas, adaptively adjusting the refrigeration cycles of the M refrigeration equipment using the M real-time refrigeration loads; Intermittent adjustment module: a refrigeration cycle adjustment window is preset, and the refrigeration collaborative control cloud receives the N updated cooling load demands returned by the N temperature control edge nodes based on the refrigeration cycle adjustment window to perform intermittent adjustment of the refrigeration cycle of the M refrigeration equipment.

Images