Intelligent archival repository environment control method and system

Abstract

The invention relates to an intelligent archival repository environment control method and system, and relates to the field of intelligent environment control, and the method comprises the steps: monitoring and obtaining Q temperature sequences and Q humidity sequences of Q temperature and humidity cooperative management regions, and predicting and obtaining Q temperature prediction sequences and Q humidity prediction sequences in a predetermined time zone; taking the minimum temperature deviation, the minimum humidity deviation and the minimum equipment energy consumption as a comprehensive optimization target, performing control parameter optimization analysis on the N air conditioning equipment in the storehouse environment simulation space, and outputting an optimal equipment control scheme; and carrying out storehouse environment regulation and control in the preset time zone. According to the invention, the technical problem that the control accuracy and stability of the temperature and humidity in the warehouse are insufficient because the cooperative work of a plurality of air conditioning devices in the warehouse cannot be accurately coordinated by the existing method can be solved; efficient cooperative work of the multiple air conditioning devices can be achieved, the accuracy and stability of temperature and humidity control are remarkably improved, and file damage caused by environment fluctuation is effectively prevented.

Description

Technical Field

[0001] The present invention relates to the field of intelligent environmental control, and in particular to a method and system for controlling an intelligent archive warehouse environment. Background Art

[0002] With the increasing demand for archive management and preservation, especially in the context of digitalization and informatization, environmental control of archive warehouses is particularly important. As a carrier of historical information and important data, the quality of archive preservation is directly related to the effectiveness, integrity and sustainable use of archives. Therefore, how to effectively control the environmental conditions in the warehouse, especially the precise control of temperature and humidity, has become an important topic in the field of archive management.

[0003] Traditional environmental control systems are usually based on the independent operation of a single or multiple air-conditioning devices, lacking comprehensive coordination and optimization of the operating status of each device. This leads to uneven temperature and humidity control in different areas. Some areas may be too humid or too dry, or the temperature may be too high or too low, thus affecting the safety and preservation quality of the archives in the warehouse. Summary of the invention

[0004] The present invention aims to solve the technical problem that the existing archive warehouse environment control method cannot accurately coordinate the collaborative work of multiple air-conditioning equipment in the warehouse, resulting in insufficient accuracy and stability of temperature and humidity control in the warehouse, and provides a smart archive warehouse environment control method and system to solve the problem.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a method for controlling the environment of a smart archive warehouse, comprising: clustering N coverage areas of N air-conditioning devices in a target archive warehouse with temperature and humidity as variables to determine Q temperature and humidity collaborative management areas; monitoring and obtaining Q temperature sequences and Q humidity sequences of the Q temperature and humidity collaborative management areas at K consecutive time points, and predicting and obtaining Q temperature prediction sequences and Q humidity prediction sequences within a predetermined time zone based on the Q temperature sequences and Q humidity sequences; based on the Q temperature prediction sequences and Q humidity prediction sequences, with minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal, performing control parameter optimization analysis on the N air-conditioning devices in a warehouse environment simulation space, and outputting an optimal equipment control scheme; according to the optimal equipment control scheme, controlling the N air-conditioning devices to perform warehouse environment regulation within the predetermined time zone; wherein , taking temperature and humidity as variables, clustering the N coverage areas of N air-conditioning equipment in the target archive warehouse, and determining Q temperature and humidity collaborative management areas, including: according to the environmental monitoring log of the target archive warehouse, collecting P temperature monitoring data and P humidity monitoring data of the N coverage areas at a predetermined time interval to obtain N temperature data sets and N humidity data sets, wherein the predetermined time interval is 10 days and P is 36; clustering the N coverage areas based on the N temperature data sets to determine a number of temperature collaborative areas; clustering the N coverage areas based on the N humidity data sets to determine a number of humidity collaborative areas; performing intersection operation extraction on the several temperature collaborative areas and the several humidity collaborative areas to obtain the Q temperature and humidity collaborative management areas, wherein the temperature and humidity of each temperature and humidity collaborative management area at the same time point are the same by default.

[0006] Optionally, the method for controlling the environment of a smart archive warehouse also includes: randomly selecting a first temperature data set of a first coverage area from the N temperature data sets, wherein the first temperature data set includes a first temperature sequence, and the first temperature sequence is obtained after arranging P first temperature data; selecting a first temperature at a first time point in the first temperature sequence, and taking the first temperature as a benchmark, respectively calculating the temperature difference values ​​of other temperature data sets in the N temperature data sets at the first time point, eliminating coverage areas with temperature difference values ​​greater than a predetermined temperature difference threshold, and obtaining a first remaining coverage area; continuing to select a second temperature at a second time point in the first temperature sequence, screening the first remaining coverage area, and obtaining a second remaining coverage area; iteratively performing area screening until a predetermined number of selections is met, outputting the current remaining coverage area, and constructing a first temperature collaborative area in combination with the first coverage area, wherein the predetermined number of selections is one half of P; continuing to cluster the areas of the N coverage areas except the first temperature collaborative area until all areas are clustered, and outputting the several temperature collaborative areas.

[0007] Optionally, the method for controlling the environment of a smart archive warehouse further includes: configuring a predetermined time zone, wherein the predetermined time zone includes M continuous time points, M is less than K; randomly selecting a first temperature and humidity collaborative management area from the Q temperature and humidity collaborative management areas, and collecting a sample temperature sequence set and a sample humidity sequence set based on the environmental monitoring log of the target archive warehouse, with the K continuous time points of the first temperature and humidity collaborative management area as constraints, and collecting temperature data of subsequent M continuous time points of different sample temperature sequences to obtain a sample temperature prediction sequence, collecting humidity data of subsequent M continuous time points of different sample humidity sequences to obtain a sample humidity prediction sequence, and constructing A sample temperature prediction sequence set and a sample humidity prediction sequence set; training a BP neural network with the sample temperature sequence set and the sample temperature prediction sequence set until convergence, and constructing a first temperature prediction branch; training a BP neural network with the sample humidity sequence set and the sample humidity prediction sequence set until convergence, and constructing a first humidity prediction branch; sequentially analyzing and constructing Q temperature prediction branches and Q humidity prediction branches, and inputting the Q temperature sequences into the Q temperature prediction branches for mapping matching and prediction, and outputting the Q temperature prediction sequences, and inputting the Q humidity sequences into the Q humidity prediction branches for mapping matching and prediction, and outputting the Q humidity prediction sequences.

[0008] Optionally, the smart archive warehouse environment control method also includes: constructing a warehouse environment simulation space based on the layout information of the target archive warehouse, N air-conditioning equipment and Q temperature and humidity collaborative management areas, and training the warehouse environment simulation space to convergence based on sample data collected from the environmental monitoring log, wherein the warehouse environment simulation space is used to simulate the operation of the air-conditioning equipment, and output the predicted temperature, predicted humidity and equipment energy consumption of the Q temperature and humidity collaborative management areas; obtaining N operating parameter thresholds of the N air-conditioning equipment, and randomly selecting operating parameters based on the N operating parameter thresholds for combination to obtain several initial equipment control schemes; utilizing the warehouse environment simulation space, with minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal, performing control parameter optimization analysis according to the several initial equipment control schemes, and outputting the optimal equipment control scheme.

[0009] Optionally, the smart archive warehouse environment control method also includes: constructing a scheme fitness evaluation function with minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal; utilizing the warehouse environment simulation space to perform equipment simulation operation according to the several initial equipment control schemes to obtain several simulation results at M consecutive time points, wherein each simulation result includes Q temperature simulation sequences, Q humidity simulation sequences and N equipment energy consumption; based on the scheme fitness evaluation function, obtaining several scheme fitnesses based on the evaluation of the several simulation results; taking the N operating parameter thresholds as constraints, performing control parameter optimization analysis according to the several scheme fitnesses, and outputting the optimal equipment control scheme.

[0010] Optionally, the smart archive warehouse environment control method further includes: the expression of the scheme fitness evaluation function is: ;in, is the solution fitness, is the temperature difference weight, is the wet difference weight, is the energy consumption weight, Q is the number of temperature and humidity collaborative management areas, M is the number of consecutive time points, is the temperature prediction data of the mth time point in the qth region, is the temperature simulation data of the mth time point in the qth region, is the humidity forecast data of the mth time point in the qth area, is the humidity simulation data of the mth time point in the qth region, is the total energy consumption of the equipment in the qth area, which is obtained by summing the energy consumption of N devices.

[0011] Optionally, the method for controlling the environment of a smart archive warehouse further includes: based on the fitness of the several solutions, arranging the several initial equipment control solutions in descending order according to the fitness of the solutions, constructing an initial solution sequence, and setting the first 5% of the solutions in the initial solution sequence as optimal solutions, and setting the last 95% of the solutions as inferior solutions, to obtain E optimal solutions and F inferior solutions; clustering the F inferior solutions with the E optimal solutions as the center, obtaining E solution sets, and in each solution set, taking the optimal solution as the direction, updating the inferior solutions in the solution set according to a predetermined optimal step length, E updated solution sets are obtained, wherein if the updated inferior solution exceeds the N operating parameter thresholds, any initial equipment control scheme is randomly selected to replace the inferior solution; the E updated solution sets are identified, and if within the same updated solution set, there is a situation where the fitness of the inferior solution is greater than the fitness of the superior solution, the superior solution is replaced by the inferior solution; the iterative optimization is continued until a predetermined number of convergences is reached, E current solution sets are output, and the current solution set with the largest sum of fitness is set as the optimal solution set, and the superior solution in the optimal solution set is set as the optimal equipment control scheme.

[0012] In the second aspect, the present invention provides a smart archive warehouse environment control system, including: a coverage area clustering module, which is used to cluster N coverage areas of N air-conditioning equipment in a target archive warehouse with temperature and humidity as variables, and determine Q temperature and humidity collaborative management areas; a temperature and humidity prediction module, which is used to monitor and obtain Q temperature sequences and Q humidity sequences of the Q temperature and humidity collaborative management areas at K consecutive time points, and predict and obtain Q temperature prediction sequences and Q humidity prediction sequences within a predetermined time zone based on the Q temperature sequences and Q humidity sequences; a control parameter optimization module, which is used to optimize and analyze the control parameters of the N air-conditioning equipment in a warehouse environment simulation space according to the Q temperature prediction sequences and Q humidity prediction sequences, and output an optimal equipment control scheme with minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal; a warehouse environment control module, which is used to control the N air-conditioning equipment to perform warehouse environment control within the predetermined time zone according to the optimal equipment control scheme.

[0013] The beneficial effects of the present invention are as follows: by clustering N coverage areas of N air-conditioning devices in a target archive warehouse with temperature and humidity as variables, Q temperature and humidity collaborative management areas are determined; then, Q temperature sequences and Q humidity sequences of the Q temperature and humidity collaborative management areas at K consecutive time points are monitored and obtained, and Q temperature prediction sequences and Q humidity prediction sequences in a predetermined time zone are predicted based on the Q temperature sequences and Q humidity sequences; then, based on the Q temperature prediction sequences and Q humidity prediction sequences, the control parameters of the N air-conditioning devices are optimized and analyzed in the warehouse environment simulation space with minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal, and the optimal equipment control scheme is output; finally, according to the optimal equipment control scheme, the N air-conditioning devices are controlled to perform warehouse environment regulation in the predetermined time zone; that is, through the intelligent control system, efficient collaborative work of multiple air-conditioning devices can be achieved, the accuracy and stability of temperature and humidity control in the warehouse can be significantly improved, the temperature and humidity of each area in the warehouse can be ensured to be maintained within the optimal range, and archive damage caused by environmental fluctuations can be effectively prevented, while energy consumption can be optimized and management efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A schematic diagram of a flow chart of a smart archive warehouse environment control method provided by the present invention; Figure 2 A schematic diagram of the structure of a smart archive warehouse environment control system provided by the present invention.

[0015] In the accompanying drawings, the components represented by the reference numerals are described as follows: Covering area clustering module 11, temperature and humidity prediction module 12, control parameter optimization module 13, warehouse environment control module 14. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0017] In the description of the present invention, 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 the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0018] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention 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 obscuring the description of the present invention with unnecessary details. 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 invention.

[0019] Embodiment 1, as Figure 1 As shown, the embodiment of the present invention provides a method for controlling the environment of a smart archive warehouse, which specifically includes the following steps: S100: Taking temperature and humidity as variables, cluster the N coverage areas of N air-conditioning equipment in the target archive warehouse to determine Q temperature and humidity collaborative management areas.

[0020] Furthermore, step S100 of the present invention further includes: S110: According to the environmental monitoring log of the target archive warehouse, P temperature monitoring data and P humidity monitoring data of the N covered areas are collected at a predetermined time interval to obtain N temperature data sets and N humidity data sets, wherein the predetermined time interval is 10 days and P is 36.

[0021] Specifically, in the target archive warehouse, multiple temperature and humidity sensors are arranged to cover N different areas. These areas can be divided based on different spatial layouts or environmental conditions, such as storage areas, office areas, corridor areas, etc.; each sensor regularly records the temperature and humidity data of the area where it is located, and stores these data in the form of logs in a database or cloud platform to ensure efficient management and subsequent analysis of the data; among them, the target archive warehouse includes N air-conditioning equipment, the model of each air-conditioning equipment is not exactly the same, and each air-conditioning equipment has a coverage area, that is, the performance and scope of application of each air-conditioning equipment are different. Due to the different models of each equipment, its cooling or heating capacity, energy efficiency and other parameters may be different. Therefore, when working together, it is necessary to accurately adjust the operation strategy of each equipment to ensure that the temperature and humidity in all areas of the warehouse are kept within the optimal range.

[0022] Configure the scheduled time interval and data collection volume P. The scheduled time interval is 10 days, that is, batch data collection is performed every 10 days to ensure comprehensive monitoring of environmental changes at different time points. The purpose of this time interval setting is to ensure that the environmental fluctuation characteristics within a long time scale can be captured; P is 36, that is, P monitoring data are continuously acquired. Then, according to the scheduled time interval and data collection volume P, the environmental monitoring log of the target archive warehouse is retrieved, that is, for each coverage area (a total of N areas), P temperature monitoring data and P humidity monitoring data are collected within the scheduled time interval. Then, for each coverage area, the 36 collected temperature data and 36 humidity data are combined into a data set, forming N temperature data sets and N humidity data sets respectively. These data sets will serve as the basis for subsequent analysis and optimization control, supporting the time series prediction and optimization scheduling of temperature and humidity.

[0023] S120: Clustering the N coverage areas based on the N temperature data sets to determine a plurality of temperature coordination areas.

[0024] Furthermore, step S120 of the present invention further includes: S121: randomly selecting a first temperature data set of a first coverage area from the N temperature data sets, wherein the first temperature data set includes a first temperature sequence, and the first temperature sequence is obtained after arranging P first temperature data; S122: selecting a first temperature at a first time point from the first temperature sequence, and taking the first temperature as a benchmark, respectively calculating the temperature difference values ​​of other temperature data sets in the N temperature data sets at the first time point, eliminating coverage areas with temperature difference values ​​greater than a predetermined temperature difference threshold, and obtaining a first remaining coverage area; S123: continuing to select a second temperature at a second time point from the first temperature sequence, screening the first remaining coverage area, and obtaining a second remaining coverage area; S124: iteratively screening areas until a predetermined number of selections is met, outputting the current remaining coverage area, and constructing a first temperature collaborative area in combination with the first coverage area, wherein the predetermined number of selections is half of P; S125: continuing to cluster the areas of the N coverage areas except the first temperature collaborative area until all areas are clustered, and outputting the several temperature collaborative areas.

[0025] Specifically, by clustering the temperature data in the coverage areas of multiple air-conditioning equipment, multiple temperature collaborative management areas are identified and constructed. The temperature changes in these areas at the same time point have high similarity and can be centrally regulated and optimized. First, the first temperature data set of the first coverage area is randomly selected from the N temperature data sets, wherein the first temperature data set includes a first temperature sequence, which is composed of P first temperature data arranged in chronological order. Then, the first temperature at the first time point is selected from the first temperature sequence, and the temperature difference values ​​of other temperature data sets in the N temperature data sets at the first time point are calculated based on the first temperature, and N-1 temperature difference values ​​are obtained, and the coverage areas with temperature difference values ​​greater than a predetermined temperature difference threshold (which can be set according to the actual scene, such as 0.1 degrees Celsius) are eliminated, wherein the area with too large a temperature difference value indicates that the temperature fluctuation of the area is different from that of the first area, and therefore does not belong to the same temperature collaborative area, and the first remaining coverage area is obtained.

[0026] Then, continue to select the second temperature at the second time point in the first temperature sequence, and use the second temperature as a reference to calculate the second temperature difference of the first remaining coverage area at the second time point, and eliminate the coverage area with a temperature difference value greater than the predetermined temperature difference threshold, to obtain the second remaining coverage area, and through continuous screening, select the temperature data at different time points each time to calculate the temperature difference value, and further narrow the area that meets the temperature collaborative management requirements. Continue to perform the screening step, iteratively screen the temperature data until the predetermined number of selections is met, which is one-half of P. During each screening, continue to calculate the temperature difference value based on the selected temperature data, and gradually exclude areas with large temperature fluctuations, and finally obtain areas that meet the temperature coordination requirements; finally output the current remaining coverage area, and combine it with the first coverage area to construct a first temperature coordination area. The temperature fluctuations of all coverage areas in this area are relatively consistent, and can be managed through a unified control strategy.

[0027] For the remaining N coverage areas that are not included in the first temperature coordination area, cluster analysis will continue until all areas are assigned to corresponding temperature coordination areas. The clustering process will automatically divide similar areas into the same group based on the similarity of temperature data in each area, and finally output multiple temperature coordination areas. These coordination areas will be optimized for temperature control as a whole in the subsequent intelligent control process, thereby ensuring that the regulation of air-conditioning equipment is more accurate and efficient under the same environmental conditions.

[0028] Through iterative screening and clustering, multiple areas can be efficiently divided into several areas with similar temperature fluctuations, providing precise management areas for subsequent environmental control. The regional temperature fluctuations in each temperature coordination area are similar, which can ensure that the adjustment strategy of the air-conditioning equipment is more consistent and efficient. By centrally managing the coordination areas, energy waste and system burden can be effectively reduced. By accurately dividing the temperature coordination areas, the problem of excessively high or low temperatures can be avoided, the stability of temperature control in the warehouse can be improved, and the safe storage of archives can be ensured.

[0029] S130: Clustering the N coverage areas based on the N humidity data sets to determine a number of humidity coordination areas; S140: Performing intersection operations on the several temperature coordination areas and the several humidity coordination areas to obtain the Q temperature and humidity coordination management areas, wherein the temperature and humidity of each temperature and humidity coordination management area at the same time point are the same by default.

[0030] Specifically, the same method of clustering the N coverage areas to determine several temperature coordination areas is used to cluster the N coverage areas based on the N humidity data sets to determine several humidity coordination areas. By clustering the N humidity data sets, the coverage area in the warehouse can be divided into several areas with similar humidity fluctuations, where the regional humidity requirements in the humidity coordination area are similar, and centralized control can be achieved to avoid adjusting each device separately. By intelligently scheduling the humidity coordination area, resource waste can be effectively reduced, and accurate adjustment of humidity in each area can be ensured, optimizing equipment energy consumption, thereby facilitating subsequent accurate adjustment of the working parameters of the humidity control equipment and ensuring the stability of humidity in the warehouse.

[0031] Finally, the intersection operation is performed on the several temperature coordination areas and the several humidity coordination areas, that is, the similarities of the two dimensions of temperature and humidity are integrated to obtain an area that satisfies the temperature and humidity conditions at the same time. Each temperature and humidity coordinated management area obtained after the intersection operation can meet the dual control requirements of temperature and humidity in the warehouse at the same time. The temperature and humidity changes in each area are highly consistent, which is convenient for the precise coordinated regulation of air-conditioning equipment and dehumidification equipment, and Q temperature and humidity coordinated management areas are obtained. Among them, the temperature and humidity inside each temperature and humidity coordinated management area are stable and consistent, and the air-conditioning and dehumidification equipment can be efficiently mobilized for precise coordination, avoiding temperature and humidity fluctuations caused by asynchronous adjustment between areas, thereby improving the overall performance of the system.

[0032] S200: Monitor and obtain Q temperature sequences and Q humidity sequences of the Q temperature and humidity collaborative management areas at K consecutive time points, and predict and obtain Q temperature prediction sequences and Q humidity prediction sequences within a predetermined time zone based on the Q temperature sequences and Q humidity sequences.

[0033] Furthermore, step S200 of the present invention further includes: S210: Configure a predetermined time zone, wherein the predetermined time zone includes M continuous time points, M is less than K; S220: Randomly select a first temperature and humidity collaborative management area from the Q temperature and humidity collaborative management areas, and based on the environmental monitoring log of the target archive warehouse, collect the K continuous time points of the first temperature and humidity collaborative management area as constraints, collect the sample temperature sequence set and the sample humidity sequence set, and collect the temperature data of the subsequent M continuous time points of different sample temperature sequences to obtain the sample temperature prediction sequence, collect the humidity data of the subsequent M continuous time points of different sample humidity sequences to obtain the sample humidity prediction sequence, and construct the sample temperature prediction sequence set and the sample humidity sequence set. Humidity prediction sequence set; S230: train the BP neural network with the sample temperature sequence set and the sample temperature prediction sequence set until convergence, and construct a first temperature prediction branch. Train the BP neural network with the sample humidity sequence set and the sample humidity prediction sequence set until convergence, and construct a first humidity prediction branch; S240: analyze and construct Q temperature prediction branches and Q humidity prediction branches in sequence, and input the Q temperature sequences into the Q temperature prediction branches for mapping matching and prediction, and output the Q temperature prediction sequences. Input the Q humidity sequences into the Q humidity prediction branches for mapping matching and prediction, and output the Q humidity prediction sequences.

[0034] Specifically, first, the environmental data of the target area is collected in real time through sensors, the environmental changes of each temperature and humidity collaborative management area are continuously tracked within K consecutive time points, the temperature data and humidity data of the Q temperature and humidity collaborative management areas at K consecutive time points are monitored and acquired, and Q temperature sequences and Q humidity sequences are constructed respectively. The temperature sequence and humidity sequence of each temperature and humidity collaborative management area contain temperature and humidity data at K consecutive time points, which will provide a basis for temperature and humidity prediction.

[0035] Next, a predetermined time zone is configured, wherein the predetermined time zone includes M continuous time points, where M is less than K; then, a first temperature and humidity collaborative management area is randomly selected from the Q temperature and humidity collaborative management areas, and the first temperature and humidity collaborative management area and K continuous time points are used as constraints to retrieve the environmental monitoring log of the target archive warehouse, collect a sample temperature sequence set and a sample humidity sequence set, and then collect temperature data of subsequent M continuous time points of different sample temperature sequences to obtain a sample temperature prediction sequence, collect humidity data of subsequent M continuous time points of different sample humidity sequences to obtain a sample humidity prediction sequence, and construct a sample temperature prediction sequence set and a sample humidity prediction sequence set.

[0036] A first temperature prediction branch and a first humidity prediction branch are further constructed based on the BP neural network. The first temperature prediction branch and the first humidity prediction branch are BP neural network models that can be iteratively optimized in machine learning. Then, the first temperature prediction branch is trained with the sample temperature sequence set and the sample temperature prediction sequence set until convergence, and the first humidity prediction branch is trained with the sample humidity sequence set and the sample humidity prediction sequence set until convergence, so as to obtain the trained first temperature prediction branch and the first humidity prediction branch. The prediction branch training method is as follows: first, input data is passed into the network, and the output temperature prediction value is calculated through a multi-layer network structure (including an input layer, a hidden layer and an output layer); then, the error between the network output value and the actual value (target prediction value) is calculated using a loss function. The commonly used loss function is the mean square error (MSE), that is, the mean of the sum of the squares of the difference between the predicted value and the true value; then, the network weights and biases are adjusted according to the error through the back propagation algorithm to gradually reduce the error. This process is optimized by the gradient descent method, the network parameters are iteratively updated, and the weights and biases are continuously adjusted until the prediction error of the network reaches a set threshold.

[0037] The same method is used to sequentially construct Q temperature prediction branches and Q humidity prediction branches, and then the Q temperature sequences are input into the Q temperature prediction branches for mapping matching (matching the temperature prediction branches in the same area) and prediction, and the Q temperature prediction sequences are output; the Q humidity sequences are input into the Q humidity prediction branches for mapping matching (matching the humidity prediction branches in the same area) and prediction, and the Q humidity prediction sequences are output. By constructing multiple temperature and humidity prediction branches, the temperature and humidity data of multiple areas can be processed simultaneously, and their future states can be predicted. Each branch can be iteratively optimized through the BP neural network, and can accurately predict future temperature and humidity changes based on historical data, thereby improving the accuracy of environmental control.

[0038] S300: Based on the Q temperature prediction sequences and the Q humidity prediction sequences, with minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal, control parameter optimization analysis is performed on the N air-conditioning equipment in the warehouse environment simulation space, and the optimal equipment control solution is output.

[0039] Furthermore, step S300 of the present invention further includes: S310: Based on the layout information of the target archive warehouse, N air-conditioning equipment and Q temperature and humidity collaborative management areas, a warehouse environment simulation space is constructed by simulation, and sample data collected based on the environmental monitoring log is trained to convergence, wherein the warehouse environment simulation space is used to simulate the operation of the air-conditioning equipment, and output the predicted temperature, predicted humidity and equipment energy consumption of the Q temperature and humidity collaborative management areas; S320: Obtain N operating parameter thresholds of the N air-conditioning equipment, and randomly select operating parameters based on the N operating parameter thresholds for combination to obtain several initial equipment control schemes.

[0040] Specifically, first, based on the layout information of the target archive warehouse, N air-conditioning equipment (modeled according to the equipment model, working principle and functional characteristics to simulate its operating status) and Q temperature and humidity collaborative management areas, a warehouse environment simulation space is constructed. The warehouse environment simulation space is used to simulate the temperature and humidity distribution and equipment energy consumption in the warehouse according to the air-conditioning operation parameters. Then, based on the environmental monitoring log, sample data (temperature and humidity data, air-conditioning equipment operation data and energy consumption information) are collected to train the warehouse environment simulation space to convergence. For example, a machine learning algorithm is used to optimize the simulation space by inputting sample data to ensure that the simulation space can truly simulate the warehouse environment. The training process continues until the predicted temperature, humidity and equipment energy consumption data output by the simulation space have the smallest error and the simulation reaches convergence. After the simulation space training is completed, the predicted temperature, predicted humidity and predicted equipment energy consumption of Q temperature and humidity collaborative management areas can be output in real time. These outputs will be used for subsequent equipment control optimization to provide support for precise control of the warehouse environment.

[0041] Then, N operating parameter thresholds of the N air-conditioning devices are obtained, where the operating parameters include temperature, humidity, wind speed, power, etc., and then operating parameters are randomly selected within the N operating parameter thresholds for combination to obtain several initial equipment control schemes, each of which includes N initial operating parameters of the N air-conditioning devices.

[0042] S330: Utilizing the warehouse environment simulation space, minimizing temperature deviation, humidity deviation and equipment energy consumption as a comprehensive optimization goal, performing control parameter optimization analysis according to the several initial equipment control schemes, and outputting an optimal equipment control scheme.

[0043] Further, step S330 of the present invention further includes: S331: Taking minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal, construct a solution fitness evaluation function.

[0044] Further, step S331 of the present invention further includes: S3311: The expression of the fitness evaluation function of the scheme is: ;in, is the solution fitness, is the temperature difference weight, is the wet difference weight, is the energy consumption weight, Q is the number of temperature and humidity collaborative management areas, M is the number of consecutive time points, is the temperature prediction data of the mth time point in the qth region, is the temperature simulation data of the mth time point in the qth region, is the humidity forecast data of the mth time point in the qth area, is the humidity simulation data of the mth time point in the qth region, is the total energy consumption of the equipment in the qth area, which is obtained by summing the energy consumption of N devices.

[0045] Specifically, is the temperature difference weight, is the wet difference weight, is the energy consumption weight, where the sum of the temperature difference weight, humidity difference weight and energy consumption weight is 1, the temperature difference weight represents the degree of influence of the temperature difference data on the overall solution effect, the humidity difference weight represents the degree of influence of the humidity difference data on the overall solution effect, and the energy consumption weight represents the degree of influence of the equipment energy consumption on the overall solution effect. The greater the influence of the indicator, the greater the corresponding weight. The specific values ​​of the temperature difference weight, humidity difference weight and energy consumption weight can be set according to the empirical method or industry standard, or dynamically adjusted according to current needs. For example, in scenarios such as energy saving and green buildings, energy saving is the most important goal, then the energy consumption weight is the largest, and the temperature difference weight and humidity difference weight are relatively low. The energy consumption weight can be set to 0.5, the temperature difference weight to 0.25, and the humidity difference weight to 0.25 to ensure that the optimization target focuses more on energy efficiency. This flexible weight adjustment method can be adjusted according to different optimization goals and usage scenarios, adapting to different control needs, so as to achieve the best solution effect.

[0046] Taking minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal, the fitness evaluation function of the scheme is constructed, that is, the smaller the overall temperature deviation, the smaller the overall humidity deviation, and the smaller the overall equipment energy consumption, the greater the fitness of the scheme, and the better the scheme is characterized. By minimizing the temperature deviation and humidity deviation, it is ensured that the equipment accurately controls the temperature and humidity in the warehouse environment, so that the temperature and humidity in the archive warehouse are always maintained within an appropriate range, thereby extending the preservation life of the archives; by minimizing the energy consumption of the equipment, it is possible to reduce the energy consumption of the equipment while ensuring the accuracy of temperature and humidity, optimize energy utilization efficiency, and reduce operating costs; the fitness evaluation function provides a clear optimization goal for the intelligent control system, and can automatically adjust the working parameters of the equipment through the optimization algorithm, thereby achieving a balance between environmental control and energy efficiency optimization.

[0047] S332: Using the warehouse environment simulation space, perform equipment simulation operation according to the several initial equipment control schemes to obtain several simulation results at M consecutive time points, wherein each simulation result includes Q temperature simulation sequences, Q humidity simulation sequences and N equipment energy consumption. S333: Based on the scheme fitness evaluation function, obtain several scheme fitnesses based on the several simulation results.

[0048] Specifically, the warehouse environment simulation space is used to perform equipment simulation operation according to the several initial equipment control schemes, and several simulation results of M continuous time points are obtained, wherein each simulation result includes Q temperature simulation sequences (simulated temperature data within M continuous time points), Q humidity simulation sequences (simulated humidity data within M continuous time points) and N equipment energy consumptions; then, the scheme fitness evaluation function is used to evaluate the scheme fitness according to the Q temperature simulation sequences, Q humidity simulation sequences and N equipment energy consumptions in each simulation result, and several scheme fitnesses are obtained.

[0049] S334: Taking the N operating parameter thresholds as constraints, perform control parameter optimization analysis according to the fitness of the several schemes, and output the optimal equipment control scheme.

[0050] Further, step S334 of the present invention further includes: S3341: Based on the fitness of the several solutions, the several initial equipment control solutions are arranged from large to small according to the fitness of the solutions, an initial solution sequence is constructed, and the first 5% of the solutions in the initial solution sequence are set as optimal solutions, and the last 95% of the solutions are set as inferior solutions, and E optimal solutions and F inferior solutions are obtained; S3342: With the E optimal solutions as the center, the F inferior solutions are clustered to obtain E solution sets, and in each solution set, with the optimal solution as the direction, the inferior solutions in the solution set are updated according to the predetermined optimal search step length to obtain E updated solution sets, wherein, If the updated inferior solution exceeds the N operating parameter thresholds, any initial equipment control scheme is randomly selected to replace the inferior solution; S3343: Identify the E updated solution sets, and if in the same updated solution set, the fitness of the inferior solution is greater than the fitness of the superior solution, replace the superior solution with the inferior solution; S3344: Continue to iterate and optimize until the predetermined number of convergence times is reached, output E current solution sets, and set the current solution set with the largest sum of fitness as the optimal solution set, and set the superior solution in the optimal solution set as the optimal equipment control scheme.

[0051] Specifically, first, based on the fitness of the several solutions, the several initial equipment control solutions are arranged from large to small according to the fitness of the solutions, and an initial solution sequence is constructed. The first 5% of the solutions in the initial solution sequence are set as optimal solutions, and the last 95% of the solutions are set as inferior solutions, and E optimal solutions and F inferior solutions are obtained. The purpose of this process is to distinguish the better solutions (optimal solutions) from the worse solutions (inferior solutions) so as to further improve the inferior solutions and use the optimal solutions to guide the optimization. Then, with the E optimal solutions as the center, the F inferior solutions are clustered to obtain E solution sets, in which the number of inferior solutions in each solution set is the same; further, in each solution set, with the optimal solution as the direction, the inferior solutions in the solution set are updated according to the predetermined optimal step length to obtain E updated solution sets. If the updated inferior solution exceeds the predetermined N operating parameter thresholds, an initial equipment control solution is randomly selected to replace the inferior solution to ensure that all solution sets meet the constraints of the system operation. The goal of this process is to improve the inferior solution through the guidance of the optimal solution and avoid excessive deviation caused by some inferior solutions through the replacement mechanism.

[0052] Next, E update solution sets are identified. In each update solution set, if it is found that the fitness of a certain inferior solution is higher than the optimal solution in the current solution set, the superior solution is replaced by the inferior solution, thereby improving the overall fitness of the solution set and ensuring that the optimal solution in the solution set is always in the optimal state; the iterative optimization is continued until a predetermined number of convergence times (such as 500 times) is reached, and E current solution sets are output, and the current solution set with the largest sum of fitness is set as the optimal solution set, and the optimal solution in the optimal solution set is set as the optimal equipment control scheme.

[0053] By guiding the updating of inferior solutions with superior solutions, inferior solutions gradually approach the optimal solution, effectively improving the overall fitness of the solution; through clustering and step-size update mechanisms, unnecessary calculations can be reduced while ensuring optimization accuracy, thereby improving optimization efficiency; by performing constraint checking and replacement on the updated solutions, it can be ensured that no solutions that do not meet the operating parameters will appear during the optimization process, thus avoiding infeasible control solutions; through multiple rounds of optimization in this process, the optimal solution can be gradually approached, providing an accurate and energy-saving equipment control solution, thereby ensuring the long-term stable operation of the archive warehouse.

[0054] S400: According to the optimal equipment control scheme, the N air-conditioning devices are controlled to perform warehouse environment control within the predetermined time zone.

[0055] Specifically, finally, according to the optimal equipment control scheme, the N air-conditioning devices are controlled to regulate the warehouse environment within the predetermined time zone. Through the implementation of the optimal control scheme, the temperature and humidity in the warehouse can be kept stable within the predetermined time zone, ensuring that the archive storage environment reaches the optimal state.

[0056] The embodiment of the present invention provides a method for controlling the environment of a smart archive warehouse, which has at least the following technical effects: By taking temperature and humidity as variables, the N coverage areas of N air-conditioning devices in the target archive warehouse are clustered to determine Q temperature and humidity collaborative management areas; then, Q temperature sequences and Q humidity sequences of the Q temperature and humidity collaborative management areas at K consecutive time points are monitored and obtained, and Q temperature prediction sequences and Q humidity prediction sequences in a predetermined time zone are predicted based on the Q temperature sequences and Q humidity sequences; then, based on the Q temperature prediction sequences and Q humidity prediction sequences, the control parameters of the N air-conditioning devices are optimized and analyzed in the warehouse environment simulation space with minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal, and the optimal equipment control scheme is output; finally, according to the optimal equipment control scheme, the N air-conditioning devices are controlled to perform warehouse environment regulation in the predetermined time zone; that is, through the intelligent control system, efficient collaborative work of multiple air-conditioning devices can be achieved, the accuracy and stability of temperature and humidity control in the warehouse can be significantly improved, the temperature and humidity of each area in the warehouse can be ensured to be maintained within the optimal range, and archive damage caused by environmental fluctuations can be effectively prevented. At the same time, energy consumption can be optimized and management efficiency can be improved.

[0057] Embodiment 2, as Figure 2 As shown, based on the same inventive concept as the method for controlling the environment of a smart archive warehouse provided in Example 1, an embodiment of the present invention further provides an environment control system for a smart archive warehouse, including: a coverage area clustering module 11, which is used to cluster the N coverage areas of N air-conditioning devices in the target archive warehouse with temperature and humidity as variables, and determine Q temperature and humidity collaborative management areas; a temperature and humidity prediction module 12, which is used to monitor and obtain Q temperature sequences and Q humidity sequences of the Q temperature and humidity collaborative management areas at K consecutive time points, and predict and obtain Q temperature prediction sequences and Q humidity prediction sequences in a predetermined time zone based on the Q temperature sequences and Q humidity sequences; a control parameter optimization module 13, which is used to optimize and analyze the control parameters of the N air-conditioning devices in the warehouse environment simulation space according to the Q temperature prediction sequences and Q humidity prediction sequences, and output an optimal equipment control scheme with minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal; a warehouse environment control module 14, which is used to control the N air-conditioning devices to perform warehouse environment control in the predetermined time zone according to the optimal equipment control scheme.

[0058] Furthermore, the intelligent archive warehouse environment control system is also used to: collect P temperature monitoring data and P humidity monitoring data of the N coverage areas according to the environmental monitoring log of the target archive warehouse at a predetermined time interval to obtain N temperature data sets and N humidity data sets, wherein the predetermined time interval is 10 days and P is 36; cluster the N coverage areas based on the N temperature data sets to determine a number of temperature coordination areas; cluster the N coverage areas based on the N humidity data sets to determine a number of humidity coordination areas; perform intersection operation extraction on the several temperature coordination areas and the several humidity coordination areas to obtain the Q temperature and humidity coordinated management areas, wherein the temperature and humidity of each temperature and humidity coordinated management area at the same time point are the same by default.

[0059] Furthermore, the intelligent archive warehouse environment control system is also used to: randomly select a first temperature data set of a first coverage area from the N temperature data sets, wherein the first temperature data set includes a first temperature sequence, and the first temperature sequence is obtained after arranging P first temperature data; select the first temperature at the first time point in the first temperature sequence, and use the first temperature as a benchmark to calculate the temperature difference values ​​of other temperature data sets in the N temperature data sets at the first time point, and eliminate the coverage areas with temperature difference values ​​greater than a predetermined temperature difference threshold to obtain a first remaining coverage area; continue to select the second temperature at the second time point in the first temperature sequence, screen the first remaining coverage area, and obtain a second remaining coverage area; iteratively perform area screening until a predetermined number of selections is met, output the current remaining coverage area, and construct a first temperature collaborative area in combination with the first coverage area, wherein the predetermined number of selections is half of P; continue to cluster the areas of the N coverage areas except the first temperature collaborative area until all areas are clustered, and output the several temperature collaborative areas.

[0060] Furthermore, the intelligent archive warehouse environment control system is also used to: configure a predetermined time zone, wherein the predetermined time zone includes M continuous time points, M is less than K; randomly select a first temperature and humidity collaborative management area from the Q temperature and humidity collaborative management areas, and collect sample temperature sequence sets and sample humidity sequence sets according to the environmental monitoring log of the target archive warehouse, with the K continuous time points of the first temperature and humidity collaborative management area as constraints, and collect temperature data of subsequent M continuous time points of different sample temperature sequences to obtain a sample temperature prediction sequence, collect humidity data of subsequent M continuous time points of different sample humidity sequences to obtain a sample humidity prediction sequence, and construct A sample temperature prediction sequence set and a sample humidity prediction sequence set; training a BP neural network with the sample temperature sequence set and the sample temperature prediction sequence set until convergence, and constructing a first temperature prediction branch; training a BP neural network with the sample humidity sequence set and the sample humidity prediction sequence set until convergence, and constructing a first humidity prediction branch; sequentially analyzing and constructing Q temperature prediction branches and Q humidity prediction branches, and inputting the Q temperature sequences into the Q temperature prediction branches for mapping matching and prediction, and outputting the Q temperature prediction sequences, and inputting the Q humidity sequences into the Q humidity prediction branches for mapping matching and prediction, and outputting the Q humidity prediction sequences.

[0061] Furthermore, the intelligent archive warehouse environment control system is also used to: construct a warehouse environment simulation space based on the layout information of the target archive warehouse, N air-conditioning equipment and Q temperature and humidity collaborative management areas, and train the warehouse environment simulation space to convergence based on sample data collected from the environmental monitoring log, wherein the warehouse environment simulation space is used to simulate the operation of air-conditioning equipment, and output the predicted temperature, predicted humidity and equipment energy consumption of Q temperature and humidity collaborative management areas; obtain N operating parameter thresholds of the N air-conditioning equipment, and randomly select operating parameters based on the N operating parameter thresholds for combination to obtain several initial equipment control schemes; utilize the warehouse environment simulation space, with minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal, perform control parameter optimization analysis according to the several initial equipment control schemes, and output the optimal equipment control scheme.

[0062] Furthermore, the smart archive warehouse environment control system is also used to: construct a scheme fitness evaluation function with minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal; utilize the warehouse environment simulation space to perform equipment simulation operation according to the several initial equipment control schemes to obtain several simulation results at M consecutive time points, wherein each simulation result includes Q temperature simulation sequences, Q humidity simulation sequences and N equipment energy consumption; based on the scheme fitness evaluation function, obtain several scheme fitnesses based on the evaluation of the several simulation results; use the N operating parameter thresholds as constraints, perform control parameter optimization analysis according to the several scheme fitnesses, and output the optimal equipment control scheme.

[0063] Furthermore, the intelligent archive warehouse environment control system is also used for: the expression of the scheme fitness evaluation function is: ;in, is the solution fitness, is the temperature difference weight, is the wet difference weight, is the energy consumption weight, Q is the number of temperature and humidity collaborative management areas, M is the number of consecutive time points, is the temperature prediction data of the mth time point in the qth region, is the temperature simulation data of the mth time point in the qth region, is the humidity forecast data of the mth time point in the qth area, is the humidity simulation data of the mth time point in the qth region, is the total energy consumption of the equipment in the qth area, which is obtained by summing the energy consumption of N devices.

[0064] Furthermore, the intelligent archive warehouse environment control system is also used for: based on the fitness of the several solutions, arranging the several initial equipment control solutions in descending order according to the fitness of the solutions, constructing an initial solution sequence, and setting the first 5% of the solutions in the initial solution sequence as optimal solutions, and setting the last 95% of the solutions as inferior solutions, to obtain E optimal solutions and F inferior solutions; clustering the F inferior solutions with the E optimal solutions as the center, obtaining E solution sets, and in each solution set, taking the optimal solution as the direction, updating the inferior solutions in the solution set according to a predetermined optimal step length, E updated solution sets are obtained, wherein if the updated inferior solution exceeds the N operating parameter thresholds, any initial equipment control scheme is randomly selected to replace the inferior solution; the E updated solution sets are identified, and if within the same updated solution set, there is a situation where the fitness of the inferior solution is greater than the fitness of the superior solution, the superior solution is replaced by the inferior solution; the iterative optimization is continued until a predetermined number of convergences is reached, E current solution sets are output, and the current solution set with the largest sum of fitness is set as the optimal solution set, and the superior solution in the optimal solution set is set as the optimal equipment control scheme.

[0065] 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.

[0066] 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 the environment of a smart archive warehouse, characterized in that: Methods include: Taking temperature and humidity as variables, cluster the N coverage areas of N air-conditioning equipment in the target archive warehouse and determine Q temperature and humidity collaborative management areas; Monitor and obtain Q temperature sequences and Q humidity sequences of the Q temperature and humidity collaborative management areas at K consecutive time points, and predict and obtain Q temperature prediction sequences and Q humidity prediction sequences within a predetermined time zone based on the Q temperature sequences and Q humidity sequences; According to the Q temperature prediction sequences and the Q humidity prediction sequences, with minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal, the control parameters of the N air-conditioning equipment are optimized and analyzed in the warehouse environment simulation space, and the optimal equipment control plan is output; According to the optimal equipment control scheme, control the N air-conditioning equipment to perform warehouse environment control within the predetermined time zone; Among them, taking temperature and humidity as variables, clustering the N coverage areas of N air-conditioning equipment in the target archive warehouse, and determining Q temperature and humidity collaborative management areas, including: According to the environmental monitoring log of the target archive warehouse, P temperature monitoring data and P humidity monitoring data of the N coverage areas are collected at a predetermined time interval to obtain N temperature data sets and N humidity data sets, wherein the predetermined time interval is 10 days and P is 36; Clustering the N coverage areas based on the N temperature data sets to determine a plurality of temperature coordination areas; Clustering the N coverage areas based on the N humidity data sets to determine a number of humidity coordination areas; An intersection operation is performed on the plurality of temperature coordination areas and the plurality of humidity coordination areas to extract the Q temperature and humidity coordination management areas, wherein the temperature and humidity of each temperature and humidity coordination management area at the same time point are the same by default.

2. A method for controlling the environment of a smart archive warehouse according to claim 1, characterized in that: Clustering the N coverage areas based on the N temperature data sets to determine a plurality of temperature coordination areas includes: Randomly selecting a first temperature data set of a first coverage area from the N temperature data sets, wherein the first temperature data set includes a first temperature sequence, and the first temperature sequence is obtained by arranging the P first temperature data sets; Selecting a first temperature at a first time point in the first temperature sequence, and taking the first temperature as a reference, respectively calculating temperature difference values ​​of other temperature data sets in the N temperature data sets at the first time point, and eliminating coverage areas whose temperature difference values ​​are greater than a predetermined temperature difference threshold, to obtain a first remaining coverage area; Continue to select a second temperature at a second time point in the first temperature sequence, screen the first remaining coverage area, and obtain a second remaining coverage area; Iteratively perform area screening until a predetermined number of selections is met, output the current remaining coverage area, and construct a first temperature coordination area in combination with the first coverage area, wherein the predetermined number of selections is one half of P; Continue to cluster the regions except the first temperature coordination region among the N coverage regions until all regions are clustered, and output the plurality of temperature coordination regions.

3. A method for controlling the environment of a smart archive warehouse according to claim 1, characterized in that: Predicting and acquiring Q temperature prediction sequences and Q humidity prediction sequences within a predetermined time zone according to the Q temperature sequences and the Q humidity sequences includes: Configuring a predetermined time zone, wherein the predetermined time zone includes M consecutive time points, where M is less than K; A first temperature and humidity collaborative management area is randomly selected from the Q temperature and humidity collaborative management areas, and according to the environmental monitoring log of the target archive warehouse, a sample temperature sequence set and a sample humidity sequence set are collected with K consecutive time points of the first temperature and humidity collaborative management area as constraints, and temperature data of subsequent M consecutive time points of different sample temperature sequences are collected to obtain a sample temperature prediction sequence, and humidity data of subsequent M consecutive time points of different sample humidity sequences are collected to obtain a sample humidity prediction sequence, and a sample temperature prediction sequence set and a sample humidity prediction sequence set are constructed; Training the BP neural network with the sample temperature sequence set and the sample temperature prediction sequence set until convergence, and constructing a first temperature prediction branch; training the BP neural network with the sample humidity sequence set and the sample humidity prediction sequence set until convergence, and constructing a first humidity prediction branch; Analyze and construct Q temperature prediction branches and Q humidity prediction branches in sequence, input the Q temperature sequences into the Q temperature prediction branches for mapping matching and prediction, output the Q temperature prediction sequences, input the Q humidity sequences into the Q humidity prediction branches for mapping matching and prediction, and output the Q humidity prediction sequences.

4. A method for controlling the environment of a smart archive warehouse according to claim 3, characterized in that: According to the Q temperature prediction sequences and Q humidity prediction sequences, with minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal, the control parameters of the N air-conditioning equipment are optimized and analyzed in the warehouse environment simulation space, and the optimal equipment control scheme is output, including: Based on the layout information of the target archive warehouse, N air-conditioning equipment and Q temperature and humidity collaborative management areas, a warehouse environment simulation space is constructed, and sample data collected based on the environmental monitoring log is trained to convergence, wherein the warehouse environment simulation space is used to simulate the operation of the air-conditioning equipment and output the predicted temperature, predicted humidity and equipment energy consumption of the Q temperature and humidity collaborative management areas; Obtaining N operating parameter thresholds of the N air-conditioning devices, and randomly selecting operating parameters based on the N operating parameter thresholds to combine, to obtain a plurality of initial device control schemes; By utilizing the warehouse environment simulation space, minimizing temperature deviation, humidity deviation and equipment energy consumption is taken as a comprehensive optimization goal, and control parameter optimization analysis is performed according to the several initial equipment control schemes to output the optimal equipment control scheme.

5. A method for controlling the environment of a smart archive warehouse according to claim 4, characterized in that: By using the warehouse environment simulation space, minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal, the control parameter optimization analysis is performed according to the several initial equipment control schemes, and the optimal equipment control scheme is output, including: Taking minimizing temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal, a scheme fitness evaluation function is constructed; Using the warehouse environment simulation space, performing equipment simulation operation according to the several initial equipment control schemes, and obtaining several simulation results at M consecutive time points, wherein each simulation result includes Q temperature simulation sequences, Q humidity simulation sequences and N equipment energy consumption; Based on the scheme fitness evaluation function, the fitness of several schemes is obtained by evaluating the several simulation results; Taking the N operating parameter thresholds as constraints, control parameter optimization analysis is performed according to the fitness of the several schemes, and the optimal equipment control scheme is output.

6. A method for controlling the environment of a smart archive warehouse according to claim 5, characterized in that: The expression of the fitness evaluation function of the scheme is: ； in, is the solution fitness, is the temperature difference weight, is the wet difference weight, is the energy consumption weight, Q is the number of temperature and humidity collaborative management areas, M is the number of consecutive time points, is the temperature prediction data of the mth time point in the qth region, is the temperature simulation data of the mth time point in the qth region, is the humidity forecast data of the mth time point in the qth area, is the humidity simulation data of the mth time point in the qth region, is the total energy consumption of the equipment in the qth area, which is obtained by summing the energy consumption of N devices.

7. A method for controlling the environment of a smart archive warehouse according to claim 5, characterized in that: Taking the N operating parameter thresholds as constraints, performing control parameter optimization analysis according to the fitness of the several schemes, and outputting the optimal equipment control scheme, including: Based on the fitness of the several solutions, the several initial equipment control solutions are arranged from large to small according to the fitness of the solutions, an initial solution sequence is constructed, and the first 5% of the solutions in the initial solution sequence are set as optimal solutions, and the last 95% of the solutions are set as inferior solutions, so as to obtain E optimal solutions and F inferior solutions; Taking E optimal solutions as the center, clustering F inferior solutions, obtaining E solution sets, and in each solution set, taking the optimal solution as the direction, updating the inferior solutions in the solution set according to the predetermined optimal step length, obtaining E updated solution sets, wherein if the updated inferior solution exceeds the N operating parameter thresholds, randomly selecting any initial equipment control scheme to replace the inferior solution; Identify the E update solution sets, and if there is a situation in the same update solution set where the fitness of the inferior solution is greater than the fitness of the superior solution, then replace the superior solution with the inferior solution; Continue to iterate and optimize until a predetermined number of convergences is reached, output E current solution sets, and set the current solution set with the largest sum of fitness as the optimal solution set, and set the optimal solution in the optimal solution set as the optimal device control solution.

8. A smart archive warehouse environment control system, characterized in that: The steps for implementing the method for controlling the environment of a smart archive warehouse as described in any one of claims 1 to 7 include: The coverage area clustering module is used to cluster the N coverage areas of N air-conditioning equipment in the target archive warehouse with temperature and humidity as variables, and determine Q temperature and humidity collaborative management areas; A temperature and humidity prediction module, used to monitor and obtain Q temperature sequences and Q humidity sequences of the Q temperature and humidity collaborative management areas at K consecutive time points, and predict and obtain Q temperature prediction sequences and Q humidity prediction sequences in a predetermined time zone based on the Q temperature sequences and Q humidity sequences; A control parameter optimization module is used to optimize the control parameters of the N air-conditioning equipment in the warehouse environment simulation space according to the Q temperature prediction sequences and the Q humidity prediction sequences, with minimizing the temperature deviation, humidity deviation and equipment energy consumption as the comprehensive optimization goal, and output the optimal equipment control solution; The warehouse environment control module is used to control the N air-conditioning devices to perform warehouse environment control within the predetermined time zone according to the optimal equipment control plan.

Images