Remote intelligent control method and system for constant temperature equipment

Abstract

The present invention relates to the field of temperature control technology, and discloses a remote intelligent control method and system for constant temperature equipment. The method comprises: obtaining initial temperature data and initial humidity data of a target device, performing multidimensional anomaly analysis on the initial temperature data and initial humidity data to obtain temperature anomaly data and humidity anomaly data; performing humidity time series analysis on the humidity anomaly data to obtain humidity supplementation data; obtaining device operation data of the target device, performing status monitoring on the device operation data to obtain device status data; generating an environmental change factor of the target device based on the temperature anomaly data and humidity supplementation data, and performing compensation calibration on the initial temperature data based on the environmental change factor and the device status data to obtain temperature calibration data; and performing temperature control on the target device based on the temperature calibration data to obtain target temperature data. The present invention improves the temperature control efficiency and temperature control accuracy of constant temperature equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control, and in particular to a remote intelligent control method and system for constant temperature equipment. Background Art

[0002] Constant temperature equipment is widely used in industrial production, agricultural greenhouses, cold chain logistics, smart homes, and other fields. Its core function is to ensure stable system operation through precise temperature control. With the rapid development of the Internet of Things, cloud computing, big data, and artificial intelligence (AI) technologies, traditional constant temperature equipment has gradually exposed problems such as low control accuracy, slow response speed, and lack of remote monitoring and intelligent management capabilities.

[0003] Most existing traditional constant temperature equipment uses PID temperature control algorithm for temperature control. This algorithm is difficult to adapt to dynamic changes in complex environments, especially in scenarios with large temperature fluctuations or many interference factors. The control accuracy and response speed are difficult to meet high-precision requirements.

[0004] At the same time, traditional constant temperature equipment usually relies on local control and mostly operates at fixed power. It is unable to dynamically adjust the equipment status energy consumption according to changes in ambient temperature, nor can it achieve remote real-time monitoring, fault warning and other capabilities, resulting in low operation and maintenance efficiency and equipment energy waste.

[0005] Therefore, how to improve the temperature control efficiency and temperature control accuracy of constant temperature equipment has become an urgent problem to be solved. Summary of the Invention

[0006] The present invention provides a remote intelligent control method for a constant temperature device, the main purpose of which is to solve the problems of low temperature control efficiency and insufficient temperature control precision.

[0007] In a first aspect, to achieve the above-mentioned objectives, the present invention provides a remote intelligent control method for a constant temperature device, comprising:

[0008] Acquiring initial temperature data and initial humidity data of a target device, performing multi-dimensional anomaly analysis on the initial temperature data and the initial humidity data, and obtaining temperature anomaly data and humidity anomaly data;

[0009] Performing humidity time series analysis on the humidity anomaly data to obtain humidity supplement data;

[0010] Acquiring device operation data of the target device, performing status monitoring on the device operation data, and obtaining device status data;

[0011] generating an environmental change factor of the target device according to the temperature anomaly data and the humidity supplementation data, and performing compensation calibration on the initial temperature data according to the environmental change factor and the device status data to obtain temperature calibration data;

[0012] The target device is temperature-controlled according to the temperature calibration data to obtain target temperature data.

[0013] In a second aspect, the present invention further provides a remote intelligent control system for a constant temperature device, the system comprising:

[0014] a data anomaly analysis module, configured to obtain initial temperature data and initial humidity data of a target device, and perform multi-dimensional anomaly analysis on the initial temperature data and the initial humidity data to obtain temperature anomaly data and humidity anomaly data;

[0015] A humidity time series analysis module is used to perform humidity time series analysis on the humidity anomaly data to obtain humidity supplement data;

[0016] A device status monitoring module is used to obtain device operation data of the target device, perform status monitoring on the device operation data, and obtain device status data;

[0017] a temperature compensation and calibration module, configured to generate an environmental change factor of the target device based on the temperature anomaly data and the humidity supplementation data, and to perform compensation and calibration on the initial temperature data based on the environmental change factor and the device status data to obtain temperature calibration data;

[0018] The device temperature control module is used to perform temperature control on the target device according to the temperature calibration data to obtain target temperature data.

[0019] The present invention can comprehensively capture the dynamic correlation between temperature and humidity through time alignment, feature extraction, and joint temperature and humidity feature matrix construction, avoiding the limitations of single-dimensional analysis and improving the efficiency of temperature control and data accuracy. It can also identify and supplement abnormal data through time series analysis, making humidity data more complete and more accurately reflecting actual humidity changes, reducing analysis deviations caused by missing or abnormal data, and enhancing data accuracy. By automatically collecting equipment operation data through a computer, equipment status information can be obtained in real time and continuously, avoiding delays and errors in manual monitoring and ensuring the timeliness and accuracy of monitoring. The environmental change factor makes the temperature calibration process more comprehensive and accurate, can dynamically reflect the real-time changes in the environment in which the equipment is located, and greatly improves the accuracy and reliability of the temperature calibration data. The compensation calibration is performed in combination with the equipment status data, fully considering the impact of the equipment's own operating status on the temperature, avoiding the calibration deviation that may be caused by relying solely on environmental data, achieving accurate compensation calibration of the initial temperature data, and improving the reliability and practicality of the temperature data. By calculating the difference between the temperature calibration data and the initial temperature data, the temperature deviation can be accurately grasped, realizing the automation and intelligence of the control process, reducing manual intervention, and improving efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. 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 paying any creative labor.

[0021] Figure 1 A flow chart of a remote intelligent control method for a thermostat device provided by one embodiment of the present invention;

[0022] Figure 2 A schematic diagram of a process for performing multi-dimensional anomaly analysis on the initial temperature data and the initial humidity data provided by an embodiment of the present invention;

[0023] Figure 3 A schematic diagram of a process for performing humidity time series analysis on the humidity anomaly data provided by an embodiment of the present invention;

[0024] Figure 4 A schematic diagram of a process for generating an environmental change factor of the target device based on the temperature anomaly data and the humidity supplementation data provided in one embodiment of the present invention;

[0025] Figure 5 A schematic diagram of a module of a remote intelligent control system for a constant temperature device provided by one embodiment of the present invention;

[0026] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, and to fully understand and implement how the present disclosure applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. The embodiments of the present disclosure and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] An embodiment of the present application provides a remote intelligent control method for a thermostat device, which can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0030] Reference Figure 1 FIG. 1 is a flow chart of a remote intelligent control method for a thermostat device according to an embodiment of the present invention. In this embodiment, the remote intelligent control method for a thermostat device includes:

[0031] S1. Acquire initial temperature data and initial humidity data of a target device, perform multi-dimensional anomaly analysis on the initial temperature data and the initial humidity data, and obtain temperature anomaly data and humidity anomaly data.

[0032] In an embodiment of the present invention, the initial temperature data refers to the ambient temperature value recorded by the target device at a specific time point, such as when the device is turned on, measured for the first time, or when a certain event is triggered, reflecting the thermodynamic state of the environment in which the target device is located in the initial state; the initial humidity data refers to the ambient humidity value recorded by the target device at the same time point, and humidity represents the water vapor content in the air, that is, the percentage of the actual water vapor content in the air to the saturated water vapor content at the same temperature.

[0033] In an embodiment of the present invention, the initial temperature data and the initial humidity data can be obtained through a temperature and humidity sensor (such as DHT11, DHT22, SHT30, etc.) or an Internet of Things device with an integrated temperature and humidity sensor (such as a smart home sensor, industrial environment monitoring equipment), etc. The sensor is connected to a data acquisition device such as a single-chip microcomputer through a bus protocol, and the API provided by the sensor is called or the register value is directly read to obtain the initial temperature data and the initial humidity data.

[0034] The present invention ensures that the sensor or instrument is calibrated, avoids data inaccuracy due to hardware errors, ensures data acquisition reliability, and stores initial temperature data and initial humidity data in a timely manner to avoid data loss due to device restart or power outage.

[0035] like Figure 2 As shown, in the embodiment of the present invention, the multi-dimensional anomaly analysis is performed on the initial temperature data and the initial humidity data to obtain temperature anomaly data and humidity anomaly data, including:

[0036] Performing time alignment processing on the initial temperature data and the initial humidity data to generate corresponding temperature time series and humidity time series;

[0037] Calculating temperature characteristic data and humidity characteristic data corresponding to the temperature time series and the humidity time series, and constructing a joint temperature and humidity characteristic matrix of the temperature characteristic data and the humidity characteristic data;

[0038] Performing a temperature-humidity correlation analysis on the combined temperature-humidity feature matrix to obtain a temperature-humidity correlation score;

[0039] An abnormal comparison is performed on the initial temperature data and the initial humidity data according to the temperature-humidity correlation score and a preset temperature-humidity correlation threshold to obtain temperature abnormality data and humidity abnormality data.

[0040] In an embodiment of the present invention, the initial temperature data and the initial humidity data are timestamp aligned to ensure that each temperature value and humidity value corresponds to the same time point. If the timestamps do not completely match, the missing data is supplemented by linear interpolation, spline interpolation, etc., thereby generating a time-aligned temperature and humidity time series to ensure that the temperature data and humidity data are aligned in the time dimension.

[0041] Specifically, the timestamp list of the initial temperature data and the initial humidity data is extracted, the timestamp list is traversed to sort the timestamps of the initial temperature data, and for each initial humidity data point, the temperature timestamp of its nearest neighbor is found, and the maximum allowable offset threshold is set. If its timestamp is not in the temperature data, the two previous and next temperature points are found and interpolated according to the time ratio to obtain the time-aligned temperature time series and humidity time series.

[0042] In detail, the temperature characteristic data includes temperature mean, temperature variance, temperature maximum and minimum values, temperature change rate, etc., and the humidity characteristic data includes humidity mean, humidity variance, humidity maximum and minimum values, humidity change rate, etc. A characteristic matrix is ​​initialized, and the temperature characteristic data and the humidity characteristic data are used to fill the characteristic matrix, thereby combining to generate a joint temperature and humidity characteristic matrix.

[0043] In the embodiment of the present invention, performing temperature and humidity correlation analysis on the joint temperature and humidity feature matrix to obtain a temperature and humidity correlation score includes:

[0044] Calculating a first correlation metric value between the temperature feature data and the humidity feature data in the joint temperature and humidity feature matrix;

[0045] Calculating a second correlation metric value between the temperature characteristic data and the humidity characteristic vector data;

[0046] A temperature and humidity correlation score is generated based on the fusion of the first correlation metric and the second correlation metric.

[0047] Specifically, the first correlation metric value between the temperature characteristic data and the humidity characteristic data is calculated using the following formula: in, represents the initial temperature data, Represents the initial humidity data, The total number of series representing the temperature time series and humidity time series, Indicates a point in time, Indicates the Temperature characteristic data at each time point, represents the mean temperature, Indicates the Humidity characteristic data at each time point, represents the mean humidity, Represents the first association metric value.

[0048] Specifically, the second correlation metric value between the temperature characteristic data and the humidity characteristic data is calculated using the following formula: in, represents the initial temperature data, Represents the initial humidity data, Represents temperature characteristic data, Represents humidity characteristic data, represents the joint probability distribution of temperature feature data and humidity feature data, represents the marginal probability distribution of temperature characteristic data, Represents the marginal probability distribution of humidity feature data, represents mutual information.

[0049] Specifically, the temperature and humidity correlation score is calculated using the following formula: in, represents the temperature-humidity correlation score, represents the covariance weight coefficient, represents the mutual information weight coefficient, represents the covariance, represents mutual information, represents the maximum mutual information.

[0050] In detail, abnormal temperature or humidity data is identified based on the temperature and humidity correlation score. If the temperature and humidity correlation score is greater than or equal to the preset temperature and humidity correlation threshold, the temperature and humidity relationship is determined to be abnormal, so as to further check whether the temperature or humidity data deviates from the normal range, and mark the temperature data or humidity data at the abnormal time point as abnormal, thereby obtaining abnormal temperature data and abnormal humidity data.

[0051] In an embodiment of the present invention, through time alignment, feature extraction (such as mean, variance, and rate of change) and joint temperature and humidity feature matrix construction, the dynamic correlation between temperature and humidity can be fully captured, avoiding the limitations of single-dimensional analysis, and improving the efficiency of temperature control and data accuracy.

[0052] S2. Performing humidity time series analysis on the humidity anomaly data to obtain humidity supplement data.

[0053] In the embodiment of the present invention, the humidity time series analysis refers to the analysis process of humidity anomaly data changing over time, and the humidity anomaly data is subjected to timestamp extraction, sequence resampling and other processing to obtain humidity completion data.

[0054] like Figure 3As shown, in the embodiment of the present invention, performing humidity time series analysis on the humidity abnormality data to obtain humidity supplement data includes:

[0055] Extracting a humidity timestamp sequence of the humidity anomaly data;

[0056] Resampling the humidity timestamp sequence according to a preset time granularity to obtain multiple target humidity sequences;

[0057] Calculating a humidity Euclidean distance matrix for each target humidity data item between the target humidity sequences, and generating a humidity adjacency matrix based on the humidity Euclidean distance matrix;

[0058] Calculating a humidity completion value of the target humidity data according to the humidity adjacency matrix;

[0059] The target humidity data is humidity-complemented according to the humidity complement value to generate humidity-complemented data.

[0060] In the embodiment of the present invention, the timestamps corresponding to the screened abnormal humidity data are extracted to form a humidity timestamp sequence. The timestamp records the specific time when the data point was collected. The abnormal humidity data and its timestamp can be retrieved from the database or file system to ensure the integrity and accuracy of the data.

[0061] In detail, the extracted humidity timestamp sequence is mapped to the defined target time granularity, and a fixed time interval such as 1 minute or 5 minutes is selected as the time granularity. For each target time point, check whether there is corresponding humidity data. If not, it is marked as a missing value. If multiple humidity data points fall within the same time granularity, aggregation processing such as taking the average may be required. Each sequence corresponds to a time granularity and contains the humidity values ​​within the time granularity. The resampling can unify the time dimension, facilitate subsequent matrix calculations, and reduce noise interference caused by irregular sampling.

[0062] Specifically, the humidity Euclidean distance is calculated using the following formula: in, represents the humidity Euclidean distance, Indicates the number of target humidity sequences, Indicates a point in time, Indicates the Target humidity data, Indicates the Target humidity data.

[0063] In detail, a Euclidean distance matrix is ​​constructed based on multiple humidity Euclidean distances, where the rows and columns of the matrix correspond to different target humidity sequences and time points, respectively. The Euclidean distance matrix is ​​converted into a humidity adjacency matrix to represent the correlation strength between time points. By setting a distance threshold, the target humidity data whose humidity Euclidean distance is less than the distance threshold are used to generate a humidity adjacency matrix.

[0064] Specifically, for each target time point of target humidity data, its adjacent nodes, i.e., humidity data points, are identified, and the weighted average of the humidity data is calculated as the completion value based on the humidity values ​​of the adjacent nodes and the weights in the adjacency matrix. The graph structure constructed using the adjacency matrix is ​​used to complete the humidity value using a graph smoothing algorithm such as Laplace smoothing. The target humidity data is completed based on the humidity completion value, and the completed humidity data is verified to ensure the rationality and accuracy of the completion value. The completed humidity data is organized into a new data set or data sequence, i.e., humidity completion data.

[0065] In an embodiment of the present invention, humidity anomaly data points and their corresponding timestamps are extracted from the original data, which can clarify the time distribution of the anomaly data and facilitate the identification of the time period when the anomaly occurs. At the same time, the Euclidean distance matrix is ​​calculated to quantify the spatiotemporal correlation of the humidity series. By identifying and completing the anomaly data through time series analysis, the humidity data is made more complete, providing a more reliable basis for subsequent data analysis. The completed data can more accurately reflect the actual humidity changes, reduce the analysis deviation caused by missing or anomaly data, and enhance data accuracy.

[0066] S3. Obtain device operation data of the target device, perform status monitoring on the device operation data, and obtain device status data.

[0067] In an embodiment of the present invention, the device operation data refers to a data set generated by the target device during operation that reflects information such as the device's working status, performance indicators, operating parameters, etc., and may include but is not limited to physical quantities such as temperature, pressure, vibration, speed, current, voltage, as well as management information such as the device's operating time, fault records, and maintenance history.

[0068] In an embodiment of the present invention, based on the type, purpose, and monitoring or management requirements of the target device, it is clear which operating data needs to be obtained. For example, for a constant temperature device, its current, voltage, speed, temperature and other data need to be obtained; sensors such as temperature sensors, pressure sensors, vibration sensors, etc. can be used to directly measure the physical quantities of the target device and convert them into electrical signals or digital signals for collection, or data can be indirectly obtained through the device's control system, monitoring system, etc.

[0069] In the embodiment of the present invention, the state monitoring of the device operation data to obtain the device state data includes:

[0070] Performing spatiotemporal alignment on the device operation data to obtain aligned operation data;

[0071] Performing physical feature extraction on the alignment operation data to obtain a physical state feature set, and performing data analysis on the alignment operation data to obtain a logical state feature set;

[0072] Performing weighted feature fusion on the physical state feature set and the logical state feature set to obtain a fused state vector;

[0073] The fused state vector is subjected to state classification to obtain device state data.

[0074] In an embodiment of the present invention, data collected at different time points are aligned based on the timestamp of the device operation data, ensuring the consistency of the data in the time dimension. For data involving multiple sensors or devices, the data is mapped to a unified spatial coordinate system based on the location information of the devices or sensors; using timestamp synchronization technology, data from different sources or that are not synchronized are adjusted to the same time base, specifically by translation, rotation or scaling to ensure the spatial consistency of the data.

[0075] Specifically, from the aligned operating data, features closely related to the physical state of the equipment, such as temperature, pressure, vibration amplitude, etc., are selected. The selected features are further processed to extract key information that can reflect the physical state of the equipment, such as statistical features such as maximum value, minimum value, average value, and variance. For time series data, signal processing techniques such as filtering and denoising are used to extract clearer physical features, and the physical state of the equipment is quantified by calculating statistical quantities (such as mean, variance, extreme value, etc.).

[0076] Specifically, the equipment operation data is analyzed at the logical level to identify logical information such as the equipment's working mode and operation state transitions. A state machine model is used to describe the equipment's operation logic, identify different operation states and their transition conditions, and use pattern recognition technology to identify specific patterns or behaviors in the equipment operation data to construct logical state characteristics such as operation cycle, number of faults, state duration, etc.

[0077] The present invention assigns different weights to physical state characteristics and logical state characteristics according to the degree of influence on the device state, fuses the physical state characteristics and logical state characteristics according to the assigned weights, and generates a vector that comprehensively reflects the device state. Specifically, a weighted average method can be used to reflect the importance of different characteristics in the fusion result, thereby improving the comprehensiveness and accuracy of the state description.

[0078] The present invention can use machine learning algorithms (such as support vector machines, random forests, neural networks, etc.) to train classifiers to achieve automatic identification of equipment status, such as normal operation, fault warning, and shutdown maintenance.

[0079] In an embodiment of the present invention, spatiotemporal alignment of device operation data can eliminate timestamp deviations of different sensors or data sources, ensure data consistency in the time dimension, and improve the accuracy of status monitoring; extract physical quantities such as temperature, vibration frequency, current, etc. during device operation to directly reflect the actual physical state of the device, extract logical features from the data, reflect the operating logic or behavior pattern of the device, and improve the comprehensiveness of the status description; at the same time, the sensitivity of the fusion features to noise and anomalies is reduced, the robustness of status monitoring is improved, the delays and errors of manual monitoring are avoided, the timeliness and accuracy of monitoring are ensured, and the accuracy of data acquisition is improved.

[0080] S4. Generate an environmental change factor of the target device according to the temperature anomaly data and the humidity supplement data, and perform compensation calibration on the initial temperature data according to the environmental change factor and the device status data to obtain temperature calibration data.

[0081] In an embodiment of the present invention, the temperature anomaly data reflects the deviation between the actual temperature and the expected or normal temperature, and the humidity completion data completes the complete information of the ambient humidity. The environmental change factor generated based on these two aspects of data can comprehensively and accurately quantify the dynamic impact of the environment on the device temperature; the environmental change factor is combined with the device status data to compensate and calibrate the initial temperature data. The device status data contains key information such as the device operating mode and load conditions. Combined with the environmental change factor, the degree of interference caused by environmental factors on temperature measurement can be more accurately evaluated. Through a specific compensation algorithm, the initial temperature data is corrected to eliminate the errors caused by environmental factors, and finally the temperature calibration data is obtained.

[0082] like Figure 4 As shown, in the embodiment of the present invention, generating the environment change factor of the target device according to the temperature anomaly data and the humidity supplement data includes:

[0083] Constructing a temperature and humidity coupling function of the target device according to the temperature anomaly data and the humidity supplementation data;

[0084] Obtaining a time attenuation factor of the temperature and humidity coupling function, and generating a temperature and humidity data sequence corresponding to the target device according to the time attenuation factor;

[0085] Obtaining the spatial position coordinates of the target device, and constructing a three-dimensional thermal distribution matrix corresponding to the spatial position coordinates according to the temperature and humidity data sequence;

[0086] Performing exponential calculation on the three-dimensional thermal distribution matrix to obtain a gradient norm and an entropy value change rate;

[0087] Generate an environmental mutation index according to the gradient norm and the entropy value change rate;

[0088] The environmental mutation index is normalized to obtain an environmental change factor.

[0089] In an embodiment of the present invention, temperature anomaly data and humidity supplementation data are regarded as two related variables, and coupling analysis methods such as covariance analysis and mutual information analysis are used to obtain the correlation between them. Based on the results of data fusion, a mathematical function is constructed to describe the interaction between temperature and humidity.

[0090] In detail, the changing trend of the temperature and humidity coupling function over time is analyzed, and its attenuation characteristics are identified to obtain the time attenuation factor. The original temperature and humidity data are weighted or adjusted according to the time attenuation factor to generate a new temperature and humidity data sequence to reflect the influence of time attenuation; the spatial position coordinates of the target device are used as the reference point, and the surrounding space is divided into multiple grid points using grid division technology (such as uniform grid, adaptive grid, etc.), and the temperature and humidity data sequence is mapped to the grid points to form an initial three-dimensional grid space representation.

[0091] In an embodiment of the present invention, constructing a three-dimensional thermal distribution matrix corresponding to the spatial position coordinates based on the temperature and humidity data sequence includes:

[0092] Determine the spatial position coordinates as a coordinate base point, perform spatial mapping on the temperature and humidity data sequence and the coordinate base point, and obtain an initial three-dimensional grid space;

[0093] Calculating a thermal influence value at each grid point in the initial three-dimensional grid space;

[0094] A three-dimensional thermal distribution matrix corresponding to the spatial position coordinates is generated according to the thermal influence value.

[0095] In an embodiment of the present invention, the spatial coordinates of the target device are clearly defined, which is usually a three-dimensional coordinate point (such as x, y, z), representing the specific position of the target device in space. The collected temperature and humidity data sequence is associated and mapped with the coordinate base point, and the discrete temperature and humidity data points are expanded to the entire three-dimensional space, thereby forming an initial three-dimensional grid space. The grid space is composed of multiple grid points, each of which represents a small area in the space for subsequent thermal analysis.

[0096] In detail, based on the numerical values ​​in the temperature and humidity data series and combined with physical principles such as heat conduction and convection, the thermal contribution at each grid point is calculated. For example, areas with higher temperatures will have a greater thermal impact, and humidity changes may also indirectly change the thermal distribution by affecting the efficiency of heat conduction. By comprehensively considering these factors, a thermal impact value is assigned to each grid point, which reflects the importance or intensity of the point in the overall thermal distribution.

[0097] The present invention generates a three-dimensional thermal distribution matrix corresponding to the spatial position coordinates based on the thermal influence value. This matrix is ​​a three-dimensional array, and its rows, columns, and depth correspond to the horizontal, vertical, and vertical coordinate axes in the space, respectively. The value of each matrix element is the thermal influence value of the corresponding grid point. The three-dimensional thermal distribution matrix can intuitively display the thermal distribution of the target equipment in the space, providing strong data support for subsequent thermal analysis, equipment optimization, or fault warning.

[0098] In the embodiment of the present invention, performing exponential calculation on the three-dimensional thermal distribution matrix to obtain the gradient norm and the entropy value change rate includes:

[0099] Performing spatial transformation on the three-dimensional thermal distribution matrix to obtain a transformed distribution matrix;

[0100] Calculating the gradient of the transformation distribution matrix in each direction of the three-dimensional space;

[0101] Calculating a gradient norm of the three-dimensional thermal distribution matrix according to the gradient, and determining a dimensional change of the transformation distribution matrix according to the gradient;

[0102] The entropy change rate of the three-dimensional thermal distribution matrix is ​​calculated according to the dimensional change.

[0103] Specifically, the gradient norm of the three-dimensional thermal distribution matrix is ​​calculated using the following formula: in, represents the gradient norm, represents the gradient, The horizontal coordinate represents the spatial position coordinate. The vertical coordinate represents the spatial position coordinate. The vertical coordinate representing the spatial position coordinate.

[0104] In an embodiment of the present invention, the original three-dimensional thermal distribution matrix is ​​normalized to eliminate dimensional differences and bring the data into the same scale. The principal component analysis technique is used to identify the main change patterns in the data. The data covariance matrix is ​​calculated and its eigenvectors and eigenvalues ​​are solved to transform the data into a new coordinate space, where the new coordinate axes are composed of eigenvectors and are sorted by eigenvalue size. Based on the size of the eigenvalue, the first few main eigenvectors are selected to form a transformation matrix, and the original data is projected into this low-dimensional space to obtain a transformed distribution matrix, thereby reducing data redundancy and highlighting key features.

[0105] In detail, the central difference method is applied to calculate the gradient in three orthogonal directions. For each grid point, the difference in thermal value between it and the adjacent grid points is calculated. The calculated differential values ​​are combined into gradient vectors, which correspond to the rate of change in the three directions, forming a gradient field in three-dimensional space, which intuitively shows the changing trend of thermal distribution.

[0106] Specifically, for each grid point, its gradient vectors in three directions are synthesized and its modulus (i.e., gradient norm) is calculated. This can be obtained by squaring the gradient values ​​in the three directions, adding them, and then taking the square root. The gradient norm comprehensively reflects the intensity of the change in the thermal distribution of the point. By analyzing the distribution of gradient vectors in different directions, the dominant direction of change is identified. For example, if the gradient in the horizontal axis direction is generally larger, it means that the change in the thermal distribution in this direction is more significant, thereby affecting the dimensional characteristics of the matrix.

[0107] The present invention calculates the entropy value of the transformation distribution matrix based on the entropy definition in information theory, counts the probability of occurrence of each thermal value, and calculates the entropy value according to the entropy formula. The larger the entropy value, the more chaotic the data distribution. By comparing the entropy values ​​at different time points or under different conditions, the rate of change of the entropy value is calculated. If the entropy value increases, it indicates that the thermal distribution has become more dispersed or chaotic. Conversely, it indicates that the distribution has become more ordered or concentrated.

[0108] In an embodiment of the present invention, the compensating and calibrating the initial temperature data according to the environmental change factor and the device status data to obtain temperature calibration data includes:

[0109] Performing status coding on the device status data to obtain a device status coding value;

[0110] Calculating a basic compensation coefficient and a compensation mode identifier of the initial temperature data according to the device state code value and the environmental change factor using a preset compensation rule matrix;

[0111] Determining a corresponding time-varying compensation function according to the compensation mode identifier;

[0112] Performing compensation calculation on the initial temperature data according to the basic compensation coefficient and the time-varying compensation function to obtain a temperature compensation value;

[0113] The initial temperature data is temperature-calibrated according to the temperature compensation value to obtain temperature-calibrated data.

[0114] In an embodiment of the present invention, the device status data includes various status types, such as operating mode (normal, standby, fault, etc.), load conditions (light load, full load, overload, etc.) and other related status parameters, and a unique coding value is assigned to each status type.

[0115] For example, digital coding (such as 0 for standby, 1 for normal, 2 for fault, etc.) or binary coding can be used to facilitate subsequent calculation and processing.

[0116] In detail, according to the current actual state of the device, it is mapped to the corresponding coding value to generate the device state coding value, and a compensation rule matrix is ​​pre-constructed. The matrix is ​​a lookup table that stores the basic compensation coefficients and compensation mode identifiers corresponding to different combinations of device state coding values ​​and environmental change factors. The construction of the matrix is ​​based on experimental data or empirical knowledge, reflecting the influence of environmental factors on temperature under various states; according to the current device state coding value and environmental change factor, a search is performed in the compensation rule matrix to find the closest or completely matching entry, thereby obtaining the corresponding basic compensation coefficient and compensation mode identifier.

[0117] The compensation mode identifier described in the present invention indicates the type of compensation strategy that should be currently adopted, such as linear compensation, nonlinear compensation or dynamic compensation; according to the compensation mode identifier, a corresponding function is selected from a preset time-varying compensation function library, and the time-varying compensation function is a function based on time changes, which is used to simulate the impact of environmental factors on temperature that changes over time.

[0118] In detail, the basic compensation coefficient is applied to the initial temperature data to make a preliminary compensation adjustment, which can be achieved through simple multiplication or addition operations, depending on the definition of the compensation rule matrix. The temperature data after preliminary compensation is further adjusted using a time-varying compensation function. The time-varying compensation function may consider time factors, such as the rate or trend of environmental changes, to dynamically correct the temperature data; the calculated temperature compensation value is directly added to the initial temperature data, or combined according to a certain preset rule to obtain a calibrated temperature value, and the calibrated temperature data is output as the final temperature calibration data, which reflects the actual temperature situation of the target device under the current state and environmental conditions.

[0119] In this embodiment of the present invention, the environmental change factor makes the temperature calibration process more comprehensive and accurate. It can dynamically reflect real-time changes in the device's environment, including abnormal temperature fluctuations and humidity effects, greatly improving the accuracy and reliability of temperature calibration data. Compensation calibration, combined with device status data, fully considers the impact of the device's own operating status on temperature, avoiding calibration bias that may result from relying solely on environmental data. This enables precise compensation calibration of initial temperature data, improving the reliability and practicality of temperature data.

[0120] S5. Perform temperature control on the target device according to the temperature calibration data to obtain target temperature data.

[0121] In the embodiment of the present invention, the deviation value is obtained by calculating the difference between the temperature calibration data and the initial temperature data, and then the control parameters are determined and instructions are generated, and finally the temperature of the target device is controlled to obtain the target temperature data.

[0122] In an embodiment of the present invention, the step of controlling the temperature of the target device according to the temperature calibration data to obtain target temperature data includes:

[0123] Performing a difference calculation on the temperature calibration data and the initial temperature data to obtain a temperature deviation value;

[0124] Determining a control parameter according to the temperature deviation value, and generating a temperature control instruction for the target device according to the control parameter;

[0125] The target device is temperature-controlled according to the temperature control instruction to obtain target temperature data.

[0126] In an embodiment of the present invention, it is first ensured that the temperature calibration data and the initial temperature data are aligned in terms of timestamp and spatial position for accurate comparison. For each corresponding data point, the difference between the temperature calibration data and the initial temperature data is calculated, that is, the temperature deviation value, which reflects the difference between the calibrated temperature and the original temperature.

[0127] In detail, perform statistical analysis on the calculated temperature deviation values, such as calculating the average, maximum, and minimum values, to fully understand the overall situation and fluctuation range of the temperature deviation. Analyze the statistical results of the temperature deviation values ​​to identify the main sources and trends of the deviation. For example, determine whether the deviation is a continuous positive deviation or a negative deviation, and whether the size of the deviation is within an acceptable range.

[0128] Based on the results of deviation analysis, the present invention determines appropriate control parameters, including the amplitude of temperature adjustment, the speed of adjustment, and the direction of adjustment (heating or cooling). According to the determined control parameters, specific temperature control instructions are generated, which can be simple switching instructions or complex control signals, used to guide the device to perform corresponding temperature adjustment operations; the generated temperature control instructions are sent to the control system of the target device, and the control system is responsible for executing these instructions. The execution process may involve specific operations such as adjusting the power of the heating element and changing the flow of the cooling system.

[0129] In detail, the present invention can also monitor the temperature changes of the equipment in real time during the regulation process to ensure that the regulation operation is carried out as expected, and record the temperature data changes during the regulation process, including the temperature values ​​before and after regulation, the execution status of the regulation instructions, etc. After the regulation is completed, verify whether the target temperature data achieves the expected effect. If it does not meet the expectations, it is necessary to re-perform deviation analysis and regulation parameter adjustment, thereby achieving precise regulation of the target device temperature and ensuring that the equipment operates at the optimal temperature state.

[0130] In an embodiment of the present invention, by calculating the difference between the temperature calibration data and the initial temperature data, the temperature deviation can be accurately grasped, providing a reliable basis for subsequent regulation. The regulation parameters are determined and instructions are generated based on the deviation, thereby realizing the automation and intelligence of the regulation process, reducing manual intervention, and improving efficiency and accuracy. The temperature of the target device is regulated according to the instructions, which can respond quickly and make the device temperature reach the ideal state, thereby ensuring stable operation of the equipment and reducing maintenance costs.

[0131] It should be understood that the order of execution of the steps in the above embodiments does not necessarily mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0132] like Figure 5 , which is a functional module diagram of a remote intelligent control system for a constant temperature device provided by one embodiment of the present invention.

[0133] In the embodiment of the present disclosure, a remote intelligent control system for a thermostat is provided, which corresponds to the remote intelligent control method for a thermostat in the above embodiment. Figure 5 As shown, the remote intelligent control system 100 of the constant temperature device includes a data anomaly analysis module 101, a humidity time series analysis module 102, a device status monitoring module 103, a temperature compensation calibration module 104 and a device temperature control module 105. The functional modules are described in detail as follows:

[0134] The data anomaly analysis module 101 is used to obtain initial temperature data and initial humidity data of the target device, perform multi-dimensional anomaly analysis on the initial temperature data and the initial humidity data, and obtain temperature anomaly data and humidity anomaly data;

[0135] A humidity time series analysis module 102 is configured to perform a humidity time series analysis on the humidity anomaly data to obtain humidity supplement data;

[0136] The device status monitoring module 103 is used to obtain the device operation data of the target device, perform status monitoring on the device operation data, and obtain device status data;

[0137] a temperature compensation and calibration module 104 for generating an environmental change factor of the target device based on the temperature anomaly data and the humidity supplementation data, and performing compensation and calibration on the initial temperature data based on the environmental change factor and the device status data to obtain temperature calibration data;

[0138] The device temperature control module 105 is configured to perform temperature control on the target device according to the temperature calibration data to obtain target temperature data.

[0139] In one embodiment, when performing multi-dimensional anomaly analysis on the initial temperature data and the initial humidity data to obtain temperature anomaly data and humidity anomaly data, the data anomaly analysis module 101 is configured to:

[0140] Performing time alignment processing on the initial temperature data and the initial humidity data to generate corresponding temperature time series and humidity time series;

[0141] Calculating temperature characteristic data and humidity characteristic data corresponding to the temperature time series and the humidity time series, and constructing a joint temperature and humidity characteristic matrix of the temperature characteristic data and the humidity characteristic data;

[0142] Performing a temperature-humidity correlation analysis on the combined temperature-humidity feature matrix to obtain a temperature-humidity correlation score;

[0143] An abnormal comparison is performed on the initial temperature data and the initial humidity data according to the temperature-humidity correlation score and a preset temperature-humidity correlation threshold to obtain temperature abnormality data and humidity abnormality data.

[0144] In one embodiment, when performing temperature-humidity correlation analysis on the joint temperature-humidity feature matrix to obtain a temperature-humidity correlation score, the data anomaly analysis module 101 is configured to:

[0145] Calculating a first correlation metric value between the temperature feature data and the humidity feature data in the joint temperature and humidity feature matrix;

[0146] Calculating a second correlation metric value between the temperature characteristic data and the humidity characteristic vector data;

[0147] A temperature and humidity correlation score is generated based on the fusion of the first correlation metric and the second correlation metric.

[0148] In one embodiment, when the humidity time series analysis module 102 performs humidity time series analysis on the humidity abnormality data to obtain humidity supplement data, it is configured to:

[0149] Extracting a humidity timestamp sequence of the humidity anomaly data;

[0150] Resampling the humidity timestamp sequence according to a preset time granularity to obtain multiple target humidity sequences;

[0151] Calculating a humidity Euclidean distance matrix for each target humidity data item between the target humidity sequences, and generating a humidity adjacency matrix based on the humidity Euclidean distance matrix;

[0152] Calculating a humidity completion value of the target humidity data according to the humidity adjacency matrix;

[0153] The target humidity data is humidity-complemented according to the humidity complement value to generate humidity-complemented data.

[0154] In one embodiment, when the device status monitoring module 103 performs status monitoring on the device operation data and obtains the device status data, it is configured to:

[0155] Performing spatiotemporal alignment on the device operation data to obtain aligned operation data;

[0156] Performing physical feature extraction on the alignment operation data to obtain a physical state feature set, and performing data analysis on the alignment operation data to obtain a logical state feature set;

[0157] Performing weighted feature fusion on the physical state feature set and the logical state feature set to obtain a fused state vector;

[0158] The fused state vector is subjected to state classification to obtain device state data.

[0159] In one embodiment, when generating the environment change factor of the target device according to the temperature anomaly data and the humidity supplemented data, the temperature compensation calibration module 104 is configured to:

[0160] Constructing a temperature and humidity coupling function of the target device according to the temperature anomaly data and the humidity supplementation data;

[0161] Obtaining a time attenuation factor of the temperature and humidity coupling function, and generating a temperature and humidity data sequence corresponding to the target device according to the time attenuation factor;

[0162] Obtaining the spatial position coordinates of the target device, and constructing a three-dimensional thermal distribution matrix corresponding to the spatial position coordinates according to the temperature and humidity data sequence;

[0163] Performing exponential calculation on the three-dimensional thermal distribution matrix to obtain a gradient norm and an entropy value change rate;

[0164] Generate an environmental mutation index according to the gradient norm and the entropy value change rate;

[0165] The environmental mutation index is normalized to obtain an environmental change factor.

[0166] In one embodiment, when constructing the three-dimensional thermal distribution matrix corresponding to the spatial position coordinates according to the temperature and humidity data sequence, the temperature compensation calibration module 104 is configured to:

[0167] Determine the spatial position coordinates as a coordinate base point, perform spatial mapping on the temperature and humidity data sequence and the coordinate base point, and obtain an initial three-dimensional grid space;

[0168] Calculating a thermal influence value at each grid point in the initial three-dimensional grid space;

[0169] A three-dimensional thermal distribution matrix corresponding to the spatial position coordinates is generated according to the thermal influence value.

[0170] In one embodiment, when performing exponential calculation on the three-dimensional thermal distribution matrix to obtain the gradient norm and the entropy value change rate, the temperature compensation calibration module 104 is configured to:

[0171] Performing spatial transformation on the three-dimensional thermal distribution matrix to obtain a transformed distribution matrix;

[0172] Calculating the gradient of the transformation distribution matrix in each direction of the three-dimensional space;

[0173] Calculating a gradient norm of the three-dimensional thermal distribution matrix according to the gradient, and determining a dimensional change of the transformation distribution matrix according to the gradient;

[0174] The entropy change rate of the three-dimensional thermal distribution matrix is ​​calculated according to the dimensional change.

[0175] In one embodiment, when the temperature compensation calibration module 104 performs compensation calibration on the initial temperature data according to the environmental change factor and the device status data to obtain temperature calibration data, it is configured to:

[0176] Performing status coding on the device status data to obtain a device status coding value;

[0177] Calculating a basic compensation coefficient and a compensation mode identifier of the initial temperature data according to the device state code value and the environmental change factor using a preset compensation rule matrix;

[0178] Determining a corresponding time-varying compensation function according to the compensation mode identifier;

[0179] Performing compensation calculation on the initial temperature data according to the basic compensation coefficient and the time-varying compensation function to obtain a temperature compensation value;

[0180] The initial temperature data is temperature-calibrated according to the temperature compensation value to obtain temperature-calibrated data.

[0181] In one embodiment, when the device temperature control module 105 performs temperature control on the target device according to the temperature calibration data to obtain target temperature data, it is configured to:

[0182] Performing a difference calculation on the temperature calibration data and the initial temperature data to obtain a temperature deviation value;

[0183] Determining a control parameter according to the temperature deviation value, and generating a temperature control instruction for the target device according to the control parameter;

[0184] The target device is temperature-controlled according to the temperature control instruction to obtain target temperature data.

[0185] In the present invention, the specific definition of a remote intelligent control system for a thermostat device can be found in the definition of a remote intelligent control method for a thermostat device described above and will not be repeated here. Each module in the aforementioned remote intelligent control system for a thermostat device can be implemented in whole or in part through software, hardware, or a combination thereof. Each of these modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in the computer device in software form, so that the processor can call and execute the corresponding operations of each of these modules.

[0186] In the embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is only a logical function division, and other division methods may be used in actual implementation.

[0187] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0188] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. Any reference to a figure in a claim should not be construed as limiting the claim to which it relates.

[0189] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0190] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0191] Those skilled in the art will clearly understand that for the sake of convenience and brevity in description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0192] In the embodiments provided in the present disclosure, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the systems, methods, and computer program products according to the various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a portion of code, and the above-mentioned module, program segment, or a portion of code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or actions, or can be implemented using a combination of dedicated hardware and computer instructions.

[0193] It should be noted that, in this disclosure, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element limited by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0194] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A remote intelligent control method for a constant temperature device, characterized in that: The method comprises: Acquiring initial temperature data and initial humidity data of a target device, performing multi-dimensional anomaly analysis on the initial temperature data and the initial humidity data, and obtaining temperature anomaly data and humidity anomaly data; Performing humidity time series analysis on the humidity anomaly data to obtain humidity supplement data; wherein, performing humidity time series analysis on the humidity anomaly data to obtain humidity supplement data includes: extracting a humidity timestamp sequence of the humidity anomaly data; resampling the humidity timestamp sequence according to a preset time granularity to obtain multiple target humidity sequences; calculating a humidity Euclidean distance matrix of each target humidity data between the target humidity sequences, and generating a humidity adjacency matrix according to the humidity Euclidean distance matrix; calculating a humidity supplement value of the target humidity data according to the humidity adjacency matrix; performing humidity supplement on the target humidity data according to the humidity supplement value to generate humidity supplement data; Acquiring device operation data of the target device, performing status monitoring on the device operation data, and obtaining device status data; generating an environmental change factor of the target device according to the temperature anomaly data and the humidity supplement data, wherein the generating the environmental change factor of the target device according to the temperature anomaly data and the humidity supplement data includes: constructing a temperature and humidity coupling function of the target device according to the temperature anomaly data and the humidity supplement data; obtaining a time attenuation factor of the temperature and humidity coupling function, and generating a temperature and humidity data sequence corresponding to the target device according to the time attenuation factor; obtaining the spatial position coordinates of the target device, and constructing a three-dimensional thermal distribution matrix corresponding to the spatial position coordinates according to the temperature and humidity data sequence; performing exponential calculation on the three-dimensional thermal distribution matrix to obtain a gradient norm and an entropy value change rate; generating an environmental mutation index according to the gradient norm and the entropy value change rate; normalizing the environmental mutation index to obtain an environmental change factor; and compensating and calibrating the initial temperature data according to the environmental change factor and the device status data to obtain temperature calibration data; The target device is temperature-controlled according to the temperature calibration data to obtain target temperature data.

2. A remote intelligent control method for a constant temperature device according to claim 1, characterized in that: The performing multi-dimensional anomaly analysis on the initial temperature data and the initial humidity data to obtain temperature anomaly data and humidity anomaly data includes: Performing time alignment processing on the initial temperature data and the initial humidity data to generate corresponding temperature time series and humidity time series; Calculating temperature characteristic data and humidity characteristic data corresponding to the temperature time series and the humidity time series, and constructing a joint temperature and humidity characteristic matrix of the temperature characteristic data and the humidity characteristic data; Performing a temperature-humidity correlation analysis on the combined temperature-humidity feature matrix to obtain a temperature-humidity correlation score; An abnormal comparison is performed on the initial temperature data and the initial humidity data according to the temperature-humidity correlation score and a preset temperature-humidity correlation threshold to obtain temperature abnormality data and humidity abnormality data.

3. A remote intelligent control method for a constant temperature device according to claim 1, characterized in that: The exponential calculation of the three-dimensional thermal distribution matrix to obtain the gradient norm and the entropy value change rate includes: Performing spatial transformation on the three-dimensional thermal distribution matrix to obtain a transformed distribution matrix; Calculating the gradient of the transformation distribution matrix in each direction of the three-dimensional space; Calculating a gradient norm of the three-dimensional thermal distribution matrix according to the gradient, and determining a dimensional change of the transformation distribution matrix according to the gradient; The entropy change rate of the three-dimensional thermal distribution matrix is ​​calculated according to the dimensional change.

4. A remote intelligent control method for a constant temperature device according to claim 1, characterized in that: The constructing of a three-dimensional thermal distribution matrix corresponding to the spatial position coordinates according to the temperature and humidity data sequence includes: Determine the spatial position coordinates as a coordinate base point, perform spatial mapping on the temperature and humidity data sequence and the coordinate base point, and obtain an initial three-dimensional grid space; Calculating a thermal influence value at each grid point in the initial three-dimensional grid space; A three-dimensional thermal distribution matrix corresponding to the spatial position coordinates is generated according to the thermal influence value.

5. The remote intelligent control method for a constant temperature device according to claim 1, characterized in that: Compensating and calibrating the initial temperature data according to the environmental change factor and the device status data to obtain temperature calibration data includes: Performing status coding on the device status data to obtain a device status coding value; Calculating a basic compensation coefficient and a compensation mode identifier of the initial temperature data according to the device state code value and the environmental change factor using a preset compensation rule matrix; Determining a corresponding time-varying compensation function according to the compensation mode identifier; Performing compensation calculation on the initial temperature data according to the basic compensation coefficient and the time-varying compensation function to obtain a temperature compensation value; The initial temperature data is temperature-calibrated according to the temperature compensation value to obtain temperature-calibrated data.

6. A remote intelligent control method for a constant temperature device according to claim 1, characterized in that: The step of controlling the temperature of the target device according to the temperature calibration data to obtain target temperature data includes: Performing a difference calculation on the temperature calibration data and the initial temperature data to obtain a temperature deviation value; Determining a control parameter according to the temperature deviation value, and generating a temperature control instruction for the target device according to the control parameter; The target device is temperature-controlled according to the temperature control instruction to obtain target temperature data.

7. A remote intelligent control method for a constant temperature device according to claim 1, characterized in that: The state monitoring of the equipment operation data to obtain equipment state data includes: Performing spatiotemporal alignment on the device operation data to obtain aligned operation data; Performing physical feature extraction on the alignment operation data to obtain a physical state feature set, and performing data analysis on the alignment operation data to obtain a logical state feature set; Performing weighted feature fusion on the physical state feature set and the logical state feature set to obtain a fused state vector; The fused state vector is subjected to state classification to obtain device state data.

8. A remote intelligent control system for constant temperature equipment, characterized in that: The system comprises: a data anomaly analysis module, configured to obtain initial temperature data and initial humidity data of a target device, and perform multi-dimensional anomaly analysis on the initial temperature data and the initial humidity data to obtain temperature anomaly data and humidity anomaly data; A humidity time series analysis module is configured to perform a humidity time series analysis on the humidity anomaly data to obtain humidity supplementary data; wherein, performing a humidity time series analysis on the humidity anomaly data to obtain humidity supplementary data comprises: extracting a humidity timestamp sequence of the humidity anomaly data; resampling the humidity timestamp sequence according to a preset time granularity to obtain a plurality of target humidity sequences; calculating a humidity Euclidean distance matrix of each target humidity data between the target humidity sequences, and generating a humidity adjacency matrix based on the humidity Euclidean distance matrix; calculating a humidity supplementary value of the target humidity data based on the humidity adjacency matrix; and supplementing the target humidity data based on the humidity supplementary value to generate humidity supplementary data; A device status monitoring module is used to obtain device operation data of the target device, perform status monitoring on the device operation data, and obtain device status data; a temperature compensation and calibration module, configured to generate an environmental change factor of the target device based on the temperature anomaly data and the humidity supplementary data, wherein the generating of the environmental change factor of the target device based on the temperature anomaly data and the humidity supplementary data comprises: constructing a temperature and humidity coupling function of the target device based on the temperature anomaly data and the humidity supplementary data; obtaining a time attenuation factor of the temperature and humidity coupling function, and generating a temperature and humidity data sequence corresponding to the target device based on the time attenuation factor; obtaining the spatial position coordinates of the target device, and constructing a three-dimensional thermal distribution matrix corresponding to the spatial position coordinates based on the temperature and humidity data sequence; performing exponential calculation on the three-dimensional thermal distribution matrix to obtain a gradient norm and an entropy value change rate; generating an environmental mutation index based on the gradient norm and the entropy value change rate; normalizing the environmental mutation index to obtain an environmental change factor; and performing compensation and calibration on the initial temperature data based on the environmental change factor and the device status data to obtain temperature calibration data; The device temperature control module is used to perform temperature control on the target device according to the temperature calibration data to obtain target temperature data.

Images