Intelligent building equipment control method and system

Abstract

The invention discloses an intelligent building equipment control method and system, and relates to the technical field of intelligent building equipment control, and the method comprises the steps: fusing the multi-mode association topology of two groups of data through employing a Kruskal algorithm, constructing a minimum spanning tree, setting the reciprocal of an edge weight as a pheromone value, and selecting an optimal control path through employing a maximum flow algorithm-ant colony algorithm. The method comprises the following steps: converting phase space data by using a Takens embedding method, randomly selecting a pair of adjacent phase space data from a time sequence as initial points, analyzing the state of building equipment by using a Lyapunov index, constructing a hidden Markov model, and dynamically correcting a transition probability matrix and a transmission probability matrix by using the Lyapunov index to obtain the predicted state of the building equipment. The optimal control path is selected by constructing the minimum spanning tree and combining the maximum flow algorithm-ant colony algorithm, the resource utilization rate and the control precision are improved, and the comprehensiveness and adaptability of equipment control are enhanced based on the combination of the hidden Markov model and the Lyapunov index.

Description

Technical Field

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

[0002] With the continuous advancement of smart city construction, building automation technology plays an important role in improving the energy efficiency, comfort and safety of buildings. Building automation systems usually include the control and management of air conditioners, elevators, lighting and other equipment. The efficient operation of these equipment can greatly improve the energy efficiency and user experience of buildings. In these systems, smart sensors are widely used to monitor environmental changes and building equipment status in real time, providing data support for optimizing control strategies. With the development of Internet of Things (IoT) technology, the interconnection of building equipment has become the basis for realizing intelligent control. By collecting environmental data and equipment data through sensors, combined with advanced computing algorithms, building equipment can be intelligently scheduled and optimized to ensure the maximum comfort and energy efficiency of buildings.

[0003] Existing building equipment control systems still face many challenges in practical applications. Although smart sensors can provide multi-dimensional data, the existing system's modeling of complex relationships between devices is relatively simple, making it difficult to achieve optimal control path selection between devices. Existing building management systems often rely on traditional rules and experience when predicting the status of building equipment, and are slow to respond to environmental changes, unable to meet increasingly complex equipment management needs. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a smart building equipment control method and system to solve the problem that although smart sensors can provide multi-dimensional data, the existing system has a relatively simple modeling of the relationship between complex devices, and it is difficult to achieve the optimal control path selection between devices. The existing building management system often relies on traditional rules and experience when predicting the status of building equipment, and responds slowly to environmental changes, and cannot meet the increasingly complex equipment management needs.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for controlling smart building equipment, comprising:

[0008] Use smart sensors to collect environmental and building equipment data, pre-process the two sets of collected data, define building equipment as network nodes, define connections between building equipment as edges, use the Kruskal algorithm to fuse the multimodal association topology of the two sets of data, construct a minimum spanning tree, set the inverse of the edge weight as the pheromone value, and use the maximum flow algorithm-ant colony algorithm to select the optimal control path;

[0009] The phase space data is transformed using the Takens embedding method. A pair of adjacent phase space data is randomly selected from the time series as the initial point. The Lyapunov exponent is used to analyze the state of the building equipment, and a hidden Markov model is constructed. The Lyapunov exponent is used to dynamically modify the transition probability matrix and the emission probability matrix to obtain the predicted state of the building equipment.

[0010] The linear weighted method is used to construct a comprehensive objective function, which is solved using the particle swarm optimization algorithm to obtain the optimal individual, which is converted into a scheduling instruction using the dynamic scheduling algorithm and executed, and the PID control algorithm is used for monitoring and adjustment;

[0011] Two sets of data generated by storage collection and analysis.

[0012] As a preferred solution of the intelligent building equipment control method of the present invention, wherein: the intelligent sensor is used to collect environmental and building equipment data, the building equipment is defined as a network node, the connection between the building equipment is defined as an edge, the Kruskal algorithm is used to fuse the multimodal association topology of the two sets of data, a minimum spanning tree is constructed, the inverse of the edge weight is set as the pheromone value, and the maximum flow algorithm-ant colony algorithm is used to select the optimal control path, including:

[0013] The smart sensors include light, temperature and humidity, vibration, bandwidth monitoring and delay monitoring sensors;

[0014] The environment and building equipment data, including light intensity, temperature and humidity, vibration, bandwidth, and connection delay data;

[0015] Use IoT protocols to connect sensors to central control systems;

[0016] The building equipment includes air conditioners, elevators, lighting and smart sensors;

[0017] Define building equipment as network nodes, define connections between building equipment as edges, use hierarchical analysis method to calculate weighted coefficients of bandwidth and connection delay data respectively, use weighted sum method to combine bandwidth and connection delay data, calculate connection weights between building equipment, and define them as edge weights;

[0018] Sort the edge weights in ascending order, select the edge with the smallest edge weight as the first connection, then select the next edge with the smallest edge weight as the second connection, and use the union-find algorithm to gradually select the edges connecting the building equipment from the sorted edge weights until all the building equipment are connected into a connected graph, and then stop selecting to generate a minimum spanning tree;

[0019] The inverse of the edge weight is set as the pheromone value, the ant colony algorithm is used to calculate the path selection probability, the edge weight is set as the path quality, the heuristic information is used to select the path, the empirical rule is used to set the pheromone evaporation coefficient, and the pheromone increment formula is used to calculate the pheromone increment;

[0020] When the ant selects a path, it uses the local pheromone update formula to update the pheromone concentration of the path;

[0021] After each ant completes path selection and pheromone update, it proceeds to the next selection until all ants complete path selection and stop updating;

[0022] After all ants have completed path selection, the weighted sum method is used to calculate the optimal path quality, the pheromone increment formula is used to calculate the optimal pheromone increment, and the global pheromone update formula is used to update the pheromone concentration of the optimal path;

[0023] According to the pheromone concentration and quality of the optimal path, the ant colony algorithm is used to select the optimal control path.

[0024] As a preferred solution of the intelligent building equipment control method of the present invention, the preprocessing of the two sets of collected data includes:

[0025] The two sets of collected data were aligned in time using the timestamp alignment method, outliers were identified and deleted using the quartile method, missing values ​​were filled using the mean imputation method, and the two sets of filled data were normalized.

[0026] As a preferred solution of the intelligent building equipment control method of the present invention, the phase space data is converted using the Takens embedding method, a pair of adjacent phase space data is randomly selected from the time series as the initial point, the Lyapunov index is used to analyze the state of the building equipment, a hidden Markov model is constructed, and the Lyapunov index is used to dynamically correct the transition probability matrix and the emission probability matrix to obtain the predicted state of the building equipment, including:

[0027] Collect historical environmental data and preprocess them to generate training sets;

[0028] Constructing a hidden Markov model and training the hidden Markov model using a training set, including discretizing the preprocessed historical environmental data into hidden states using a threshold discretization, wherein the hidden states include normal, faulty, and degraded;

[0029] Count the number of transitions from one hidden state to another of the preprocessed historical environment data, use maximum likelihood to calculate the transition probability between each pair of states, fill the transition probability into the transition probability matrix and normalize it to obtain the initial transition probability matrix;

[0030] Count the number of times the preprocessed historical environment data appears in the hidden state, use maximum likelihood to calculate the emission probability of each hidden state, fill the emission probability into the emission probability matrix and normalize it to obtain the initial emission probability matrix;

[0031] Sort the preprocessed environmental data in chronological order to generate a time series;

[0032] Use mutual information and FNN methods to set delay time and embedding dimension, and use Takens embedding method to transform time series into phase space data;

[0033] Randomly select a pair of adjacent phase space data from the time series as the initial points;

[0034] Use the Euclidean distance formula to calculate the Euclidean distance between the initial points;

[0035] The second time series is generated by using the small perturbation method for the initial point, and the Euclidean distance formula is used to calculate the Euclidean distance between the time series and the second time series;

[0036] Calculate the Lyapunov exponent at time t using the tangent vector method;

[0037] If the Lyapunov index at time t is greater than 0, it means that the building equipment is unstable. The control factors of the initial transfer probability matrix and the initial emission probability matrix are set using the cross-validation method, and the adjustment range of the transfer probability and the emission probability are calculated using the dynamic adjustment method.

[0038] Use the proportional adjustment method to dynamically correct the transfer probability in the initial transfer probability matrix, dynamically correct the emission probability in the initial emission probability matrix, and obtain the dynamically corrected transfer probability matrix and emission probability matrix;

[0039] The maximum a posteriori estimation is used to optimize the dynamically corrected transfer probability matrix and emission probability matrix to obtain the final transfer probability matrix and emission probability matrix;

[0040] If the Lyapunov index at time t is less than or equal to 0, it means that the building equipment is normal, and the initial transfer probability matrix and initial emission probability matrix are used;

[0041] The maximum probability that a building device is in a hidden state at time t using the Viterbi algorithm;

[0042] The real-time environmental data is input into the trained hidden Markov model to obtain the predicted status of the building equipment.

[0043] As a preferred solution of the intelligent building equipment control method of the present invention, the linear weighted method is used to construct a comprehensive objective function, and a particle swarm optimization algorithm is used to solve the problem to obtain the optimal individual, including:

[0044] Normalize the predicted status of building equipment;

[0045] Calculate the mean of the pre-processed temperature and humidity data respectively and set them as the ideal temperature and humidity data;

[0046] The comfort objective function is set using the temperature and humidity deviation method;

[0047] Use mean absolute error to set the loss function;

[0048] The data-driven method is used to calculate the weight coefficients of the comfort objective function and the loss function respectively, and the linear weighted method is used to construct the comprehensive objective function;

[0049] The initial population is randomly generated, and the individuals represent the combination of prediction error and comfort requirement;

[0050] Bring the individual into the comprehensive objective function for evaluation and calculate the individual's fitness value;

[0051] Use the tournament selection method to randomly select individuals for comparison, and select individuals with higher fitness as parents to participate in the crossover operation;

[0052] Use single-point crossover to exchange genes of parent individuals to produce new offspring individuals.

[0053] After crossover, individuals are randomly selected to mutate using single-point mutation to generate new individuals;

[0054] The maximum number of iterations is set using the stopping criterion. When the maximum number of iterations is reached, the iteration is stopped and the optimal individual is output, including the optimized prediction error and comfort requirement.

[0055] As a preferred solution of the intelligent building equipment control method of the present invention, the method of converting the dynamic scheduling algorithm into a scheduling instruction and executing it, and using the PID control algorithm for monitoring and adjustment, includes:

[0056] Use dynamic scheduling algorithms to convert optimal individuals into scheduling instructions, which are transmitted to building equipment through API interfaces. Building equipment receives the scheduling instructions and executes them.

[0057] Collect feedback data and calculate the difference between the feedback data and the optimal individual;

[0058] Use statistical methods to set the judgment threshold, compare the difference with the judgment threshold, and use the PID control algorithm to adjust the difference that is greater than or equal to the judgment threshold. Stop adjustment when the difference is less than the judgment threshold and continue to monitor the feedback data.

[0059] As a preferred solution of the intelligent building equipment control method of the present invention, the two sets of data generated by the storage, collection and analysis include:

[0060] The two sets of collected data and the optimal individual generated by the analysis are stored in the central database, and security access measures are set up. The central database will back up the stored data in the cloud and regularly perform integrity checks on the stored data and backup data. After the test is completed, the integrity test record is generated and stored synchronously in the central database.

[0061] In a second aspect, the present invention provides a smart building equipment control system, comprising:

[0062] The collection topology optimization module is used to collect environmental and building equipment data using intelligent sensors, pre-process the two sets of collected data, define building equipment as network nodes, define the connections between building equipment as edges, use the Kruskal algorithm to fuse the multimodal association topology of the two sets of data, construct a minimum spanning tree, set the inverse of the edge weight as the pheromone value, and use the maximum flow algorithm-ant colony algorithm to select the optimal control path;

[0063] The state prediction module is used to transform phase space data using the Takens embedding method, randomly select a pair of adjacent phase space data from the time series as the initial point, use the Lyapunov exponent to analyze the state of building equipment, build a hidden Markov model, and use the Lyapunov exponent to dynamically correct the transition probability matrix and the emission probability matrix to obtain the predicted state of the building equipment;

[0064] The scheduling monitoring module is used to construct a comprehensive objective function using a linear weighted method, solve it using a particle swarm optimization algorithm to obtain the optimal individual, convert it into a scheduling instruction using a dynamic scheduling algorithm and execute it, and use a PID control algorithm for monitoring and adjustment;

[0065] The storage module is used to store two sets of data generated by collection and analysis.

[0066] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the smart building equipment control method as described in the first aspect of the present invention is implemented.

[0067] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the smart building equipment control method as described in the first aspect of the present invention is implemented.

[0068] The beneficial effects of the present invention are as follows: the present invention collects environmental and building equipment data by using intelligent sensors, pre-processes the two sets of collected data, defines building equipment as network nodes, defines connections between building equipment as edges, uses the Kruskal algorithm to fuse the multimodal association topology of the two sets of data, constructs a minimum spanning tree, sets the inverse of the edge weight as the pheromone value, and uses the maximum flow algorithm-ant colony algorithm to select the optimal control path; uses the Takens embedding method to convert phase space data, randomly selects a pair of adjacent phase space data from the time series as the initial point, uses the Lyapunov index to analyze the state of building equipment, constructs a hidden Markov model, and uses the Lyapunov index to dynamically correct the transition probability matrix and the emission probability matrix to obtain the predicted state of the building equipment; uses the linear weighted method to construct a comprehensive objective function, uses the particle swarm optimization algorithm to solve it, obtains the optimal individual, uses the dynamic scheduling algorithm to convert it into a scheduling instruction and execute it, and uses the PID control algorithm to monitor and adjust it; improves the response speed, resource utilization and control accuracy, avoids the impact of equipment failure on building operation, and enhances the comprehensiveness and adaptability of equipment control. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0070] Figure 1 This is a flow chart of the smart building equipment control method in Example 1.

[0071] Figure 2 This is a structural diagram of the smart building equipment control system in Example 1. DETAILED DESCRIPTION

[0072] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0073] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0074] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0075] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a method for controlling smart building equipment, comprising the following steps:

[0076] S1. Use smart sensors to collect environmental and building equipment data, pre-process the two sets of collected data, define building equipment as network nodes, define connections between building equipment as edges, use the Kruskal algorithm to fuse the multimodal association topology of the two sets of data, construct a minimum spanning tree, set the inverse of the edge weight as the pheromone value, and use the maximum flow algorithm-ant colony algorithm to select the optimal control path;

[0077] Specifically, intelligent sensors are used to collect environmental and building equipment data, building equipment is defined as network nodes, and connections between building equipment are defined as edges. The Kruskal algorithm is used to fuse the multimodal association topology of the two sets of data, and a minimum spanning tree is constructed. The inverse of the edge weight is set as the pheromone value, and the maximum flow algorithm-ant colony algorithm is used to select the optimal control path, including:

[0078] The smart sensors include light, temperature and humidity, vibration, bandwidth monitoring and delay monitoring sensors;

[0079] The environment and building equipment data, including light intensity, temperature and humidity, vibration, bandwidth, and connection delay data;

[0080] Use IoT protocols to connect sensors to central control systems;

[0081] The building equipment includes air conditioners, elevators, lighting and smart sensors;

[0082] Define building equipment as network nodes, define connections between building equipment as edges, use hierarchical analysis method to calculate weighted coefficients of bandwidth and connection delay data respectively, use weighted sum method to combine bandwidth and connection delay data, calculate connection weights between building equipment, and define them as edge weights;

[0083] Sort the edge weights in ascending order, select the edge with the smallest edge weight as the first connection, then select the next edge with the smallest edge weight as the second connection, and use the union-find algorithm to gradually select the edges connecting the building equipment from the sorted edge weights until all the building equipment are connected into a connected graph, and then stop selecting to generate a minimum spanning tree;

[0084] The inverse of the edge weight is set as the pheromone value, the ant colony algorithm is used to calculate the path selection probability, the edge weight is set as the path quality, the heuristic information is used to select the path, the empirical rule is used to set the pheromone evaporation coefficient, and the pheromone increment formula is used to calculate the pheromone increment;

[0085] After the ant selects a path, it uses the local pheromone update formula to update the pheromone concentration of the path. The formula is:

[0086] ,

[0087] in is the pheromone concentration on the ijth path at time t+1, is the pheromone evaporation coefficient, is the pheromone concentration on the ijth path at time t, is the pheromone increment on the ijth path;

[0088] After each ant completes path selection and pheromone update, it proceeds to the next selection until all ants complete path selection and stop updating;

[0089] After all ants have completed path selection, the weighted sum method is used to calculate the optimal path quality, the pheromone increment formula is used to calculate the optimal pheromone increment, and the global pheromone update formula is used to update the pheromone concentration of the optimal path. The formula is:

[0090] ,

[0091] in is the pheromone concentration on the ijth path at time t+1, is the pheromone evaporation coefficient, is the pheromone concentration on the ijth path at time t, is the optimal pheromone increment on the ijth path;

[0092] According to the pheromone concentration and quality of the optimal path, the ant colony algorithm is used to select the optimal control path.

[0093] By optimizing the control path and reducing invalid device connections, resources can be effectively saved, energy consumption can be reduced, and control paths and device scheduling can be dynamically adjusted to ensure that the system responds promptly to environmental changes and device status changes. By combining the minimum spanning tree and ant colony algorithm, building equipment can be ensured to work together efficiently and avoid system bottlenecks. By combining intelligent sensors and optimization algorithms, building equipment control can be made more intelligent and automated, reducing manual intervention and improving the system's adaptive ability.

[0094] By collecting real-time environmental parameters in the building (such as temperature, humidity, vibration, etc.) and equipment status data (such as bandwidth and connection delay), the system can dynamically monitor and control building equipment. This helps to detect equipment anomalies or environmental changes in a timely manner, so as to make timely adjustments, avoid waste of resources, and improve the energy efficiency and comfort of buildings. The Kruskal algorithm optimizes the connection structure between building equipment by generating a minimum spanning tree, ensuring that data transmission between devices is not interfered by redundant paths, thereby improving the efficiency of the system. The generated minimum spanning tree can reduce bandwidth occupancy and delay in the network, improve the smoothness of collaboration between devices, and is the basis for optimized control. Combined with the maximum flow algorithm and the ant colony algorithm, the system can not only evaluate and select the best control path, but also dynamically adapt to changes in different network states. The maximum flow algorithm The method ensures that the flow of information is not blocked, while the ant colony algorithm optimizes path selection based on real-time data, so that control instructions can be transmitted efficiently. The system can coordinate and schedule between devices more accurately, improving the response speed and accuracy of building control. The hierarchical analysis method calculates the weighted coefficients of bandwidth and connection delay, ensuring that the importance of each factor in path selection is reasonably considered, and also improving the comprehensive effect of network optimization, thereby ensuring efficient and stable communication between devices. Pheromone evaporation ensures that the system gradually eliminates inefficient paths, while incremental updates enhance the pheromone concentration of high-quality paths, enabling the system to find the optimal control path in a complex environment. The effective operation of this mechanism can improve the accuracy and efficiency of building equipment control, especially in complex systems with a large number of devices, and can ensure the accurate execution of real-time control decisions.

[0095] Furthermore, the two sets of collected data are preprocessed, including:

[0096] The two sets of collected data were aligned in time using the timestamp alignment method, outliers were identified and deleted using the quartile method, missing values ​​were filled using the mean imputation method, and the two sets of filled data were normalized.

[0097] Timestamp alignment can effectively eliminate errors caused by time differences, ensure that data is compared in the same time window, improve the temporal consistency of data, and avoid misleading analysis results caused by time differences. Especially when dealing with time-related analysis tasks, it can provide a more reliable and consistent data basis. Deleting abnormal data improves the stability and accuracy of the data and ensures the reliability of subsequent analysis results, especially in applications that require high-precision calculations. It can avoid erroneous judgments or misleading conclusions caused by outliers. Mean filling can prevent large errors caused by missing data. Through normalization, each feature of the data can be compared on a uniform scale, thereby avoiding the impact of excessively large or small values ​​of certain feature factors on the analysis results.

[0098] S2. Use the Takens embedding method to transform the phase space data, randomly select a pair of adjacent phase space data from the time series as the initial point, use the Lyapunov index to analyze the state of the building equipment, build a hidden Markov model, and use the Lyapunov index to dynamically correct the transition probability matrix and the emission probability matrix to obtain the predicted state of the building equipment;

[0099] Specifically, the Takens embedding method is used to transform the phase space data, a pair of adjacent phase space data is randomly selected from the time series as the initial point, the Lyapunov exponent is used to analyze the state of the building equipment, a hidden Markov model is constructed, and the Lyapunov exponent is used to dynamically correct the transition probability matrix and the emission probability matrix to obtain the predicted state of the building equipment, including:

[0100] Collect historical environmental data and preprocess them to generate training sets;

[0101] Constructing a hidden Markov model and training the hidden Markov model using a training set, including discretizing the preprocessed historical environmental data into hidden states using a threshold discretization, wherein the hidden states include normal, faulty, and degraded;

[0102] Count the number of transitions from one hidden state to another of the preprocessed historical environment data, use maximum likelihood to calculate the transition probability between each pair of states, fill the transition probability into the transition probability matrix and normalize it to obtain the initial transition probability matrix;

[0103] Count the number of times the preprocessed historical environment data appears in the hidden state, use maximum likelihood to calculate the emission probability of each hidden state, fill the emission probability into the emission probability matrix and normalize it to obtain the initial emission probability matrix;

[0104] Sort the preprocessed environmental data in chronological order to generate a time series;

[0105] Use mutual information and FNN methods to set delay time and embedding dimension, and use Takens embedding method to transform time series into phase space data;

[0106] Randomly select a pair of adjacent phase space data from the time series as the initial points;

[0107] Use the Euclidean distance formula to calculate the Euclidean distance between the initial points;

[0108] The second time series is generated by using the small perturbation method for the initial point, and the Euclidean distance formula is used to calculate the Euclidean distance between the time series and the second time series;

[0109] The Lyapunov exponent at time t is calculated using the tangent vector method. The formula is:

[0110] ,

[0111] in is the Lyapunov exponent at time t, is the Euclidean distance between the initial points, is the Euclidean distance between the time series at time t and the second trajectory;

[0112] If the Lyapunov index at time t is greater than 0, it means that the building equipment is unstable. The cross-validation method is used to set the control factors of the initial transfer probability matrix and the initial emission probability matrix respectively, and the dynamic adjustment method is used to calculate the adjustment range of the transfer probability and the emission probability respectively. The formula is:

[0113] ,

[0114] ,

[0115] in is the adjustment amplitude of the transition probability, is the adjustment amplitude of the emission probability, From hidden state To hidden state The transition probability represents the element in the initial transition probability matrix, the normalized transition probability, In hidden state The number of emission probabilities of the preprocessed historical environment data x, the elements in the original emission probability matrix, and the normalized emission probability;

[0116] Use the proportional adjustment method to dynamically correct the transition probability in the initial transition probability matrix and the emission probability in the initial emission probability matrix. The formula is:

[0117] ,

[0118] ,

[0119] Obtaining the dynamically corrected transfer probability matrix and emission probability matrix;

[0120] The maximum a posteriori estimation is used to optimize the dynamically corrected transfer probability matrix and emission probability matrix to obtain the final transfer probability matrix and emission probability matrix;

[0121] If the Lyapunov index at time t is less than or equal to 0, it means that the building equipment is normal, and the initial transfer probability matrix and initial emission probability matrix are used;

[0122] The maximum probability that a building device is in a hidden state at time t using the Viterbi algorithm;

[0123] The real-time environmental data is input into the trained hidden Markov model to obtain the predicted status of the building equipment.

[0124] By real-time monitoring of the Lyapunov exponent and using the hidden Markov model for status prediction, the system can issue early warnings before equipment failure or degradation occurs, greatly improving the stability and reliability of equipment operation, achieving dynamic tracking and optimal scheduling of multiple equipment states, reducing unplanned equipment downtime, and improving the energy efficiency management level of buildings. By introducing the Takens embedding method and Lyapunov exponent analysis, the operating status of equipment can be more accurately predicted, the intelligence level of building equipment management can be improved, and the transfer probability and emission probability matrices can be dynamically adjusted so that the system can maintain high prediction accuracy and control efficiency in a constantly changing environment and equipment state.

[0125] By converting time series data into phase space data, the Takens embedding method can reveal the potential dynamic behavior of the system, fully capture the nonlinear characteristics of building equipment, and extract more status information from complex equipment operation data. By calculating the Lyapunov exponent of the equipment in real time, the system can determine whether the equipment is in a stable operating state, improve the stability monitoring capability of building equipment, reduce the occurrence rate of equipment failures, and improve the reliability of equipment. By using historical environmental data for model training, the system can effectively learn the transition law of equipment status and its corresponding probability distribution, and then predict the future status of equipment. By modeling hidden states and their transition laws, more accurate equipment status prediction can be achieved, which is beneficial to buildings. The management system provides intelligent decision support. When the Lyapunov exponent indicates that the equipment status is unstable, the system adjusts the transfer probability matrix and the emission probability matrix through cross-validation and dynamic adjustment methods. The dynamic adjustment mechanism enables the model to adapt to changes in equipment status, improving the model's response speed and accuracy to changes in equipment status. The Viterbi algorithm can accurately predict the state changes of building equipment by solving the most likely hidden state sequence under a given observation sequence, so that equipment status prediction is not limited to static analysis, but can also take into account the impact of historical state transfers, realize dynamic prediction of future equipment status, improve the intelligence level of the building equipment management system, and promptly identify equipment failure or degradation to avoid equipment damage or energy efficiency degradation.

[0126] S3, use the linear weighted method to construct a comprehensive objective function, use the particle swarm optimization algorithm to solve it, get the optimal individual, use the dynamic scheduling algorithm to convert it into a scheduling instruction and execute it, and use the PID control algorithm to monitor and adjust it;

[0127] Specifically, the linear weighted method is used to construct a comprehensive objective function, and the particle swarm optimization algorithm is used to solve it to obtain the optimal individual, including:

[0128] Normalize the predicted status of building equipment;

[0129] Calculate the mean of the pre-processed temperature and humidity data respectively and set them as the ideal temperature and humidity data;

[0130] The temperature and humidity deviation method is used to set the comfort objective function. The formula is:

[0131] ,

[0132] in is the comfort objective function, N is the number of temperature and humidity sensors, and are the lth temperature and humidity data, and They are ideal temperature and humidity data respectively;

[0133] The loss function is set using the mean absolute error, and the formula is:

[0134] ,

[0135] in is the loss function, n is the number of building equipment, and are the predicted state and actual state of the z-th building equipment respectively;

[0136] The data-driven method is used to calculate the weight coefficients of the comfort objective function and the loss function respectively, and the linear weighted method is used to construct the comprehensive objective function;

[0137] The initial population is randomly generated, and the individuals represent the combination of prediction error and comfort requirement;

[0138] Bring the individual into the comprehensive objective function for evaluation and calculate the individual's fitness value;

[0139] Use the tournament selection method to randomly select individuals for comparison, and select individuals with higher fitness as parents to participate in the crossover operation;

[0140] Use single-point crossover to exchange genes of parent individuals to produce new offspring individuals.

[0141] After crossover, individuals are randomly selected to mutate using single-point mutation to generate new individuals;

[0142] The maximum number of iterations is set using the stopping criterion. When the maximum number of iterations is reached, the iteration is stopped and the optimal individual is output, including the optimized prediction error and comfort requirement.

[0143] By minimizing prediction errors and optimizing comfort targets, the system can achieve more accurate equipment scheduling, improve building comfort and energy efficiency. The combination of data-driven methods and particle swarm optimization algorithms makes the optimization process more intelligent and automated, improving the adaptive ability of the building equipment management system. The global search capability of particle swarm optimization ensures the optimal balance between energy efficiency and comfort, and improves the overall benefits of the building management system.

[0144] In building equipment optimization, normalization processing helps to eliminate the scale differences between different data, so that the optimization algorithm can better handle multiple factors such as temperature, humidity, and equipment status, thereby improving the stability of the algorithm and the solution effect. By calculating the mean of temperature and humidity and setting the ideal value, the system can clearly define the comfort target in the building. By minimizing the loss function, the scheduling and control of the equipment are more accurate, thereby reducing the misoperation and energy consumption of the equipment and improving the system efficiency. The weights are dynamically adjusted using the data-driven method to ensure that the system finds the best balance between comfort and energy efficiency, thereby improving the reliability and adaptability of the optimization effect. In building equipment control optimization, particle swarm optimization can efficiently search for the optimal control solution, handle complex multi-objective optimization problems, and find the global optimal solution in a shorter time, which helps to improve the scheduling efficiency of equipment and reduce the waste of computing resources. The tournament selection method can quickly screen out individuals with higher fitness, while crossover and mutation operations can increase the diversity of the solution space and avoid falling into the local optimal solution. The optimal individual finally output represents the optimized balance between the prediction error and comfort requirements of building equipment, providing accurate scheduling decisions for building equipment control and optimizing energy efficiency and comfort.

[0145] Furthermore, a dynamic scheduling algorithm is used to convert the scheduling instructions and execute them, and a PID control algorithm is used for monitoring and adjustment, including:

[0146] Use dynamic scheduling algorithms to convert optimal individuals into scheduling instructions, which are transmitted to building equipment through API interfaces. Building equipment receives the scheduling instructions and executes them.

[0147] Collect feedback data and calculate the difference between the feedback data and the optimal individual;

[0148] Use statistical methods to set the judgment threshold, compare the difference with the judgment threshold, and use the PID control algorithm to adjust the difference that is greater than or equal to the judgment threshold. Stop adjustment when the difference is less than the judgment threshold and continue to monitor the feedback data.

[0149] The combination of dynamic scheduling and PID control enables building equipment to respond to environmental changes and load changes in real time, ensuring that the equipment is always in the optimal state. The equipment operation is adjusted by the difference between feedback data and target state to maximize energy efficiency while improving user comfort experience. The combination of PID control algorithm and dynamic scheduling algorithm enables the system to be flexibly adjusted under different environments and operating conditions, avoiding manual intervention and over-adjustment, and improving the system's adaptability. Through the use of API interfaces, the scheduling and control of building equipment has become more intelligent and automated, improving the efficiency and sustainability of building management.

[0150] The dynamic scheduling algorithm automatically calculates and generates the optimal scheduling plan based on real-time data and equipment status, improves the flexibility and response speed of building equipment scheduling, and can adapt to changes in demand under different time periods and different load conditions. The API interface not only simplifies the data transmission process between systems, but also ensures real-time updating of information, greatly improving the automation and intelligence level of the system. By collecting feedback data in real time and comparing it with the optimal individual, the system can timely understand the operating effect of the equipment, evaluate whether further adjustment is needed, accurately detect deviations in equipment operation, and promptly discover situations where equipment performance does not meet standards or environmental conditions are not ideal, providing data support for subsequent adjustments. Through statistical analysis, the system can avoid excessive or invalid adjustments and ensure the accuracy and stability of the PID control process. PID control uses the coordination of three-part control strategies (proportional, integral and differential) to enable the equipment to quickly and smoothly adjust to the ideal state. Through real-time monitoring and adjustment, the system can respond to various external environmental changes or internal equipment status changes, making building equipment management more intelligent and automated.

[0151] S4, stores the two sets of data generated by collection and analysis;

[0152] Specifically, two sets of data generated by storage, collection and analysis include:

[0153] The two sets of collected data and the optimal individual generated by the analysis are stored in the central database, and security access measures are set up. The central database will back up the stored data in the cloud and regularly perform integrity checks on the stored data and backup data. After the test is completed, the integrity test record is generated and stored synchronously in the central database.

[0154] Centralized management makes data processing and analysis more efficient and can better support subsequent data query, processing and mining. The introduction of secure access control measures helps prevent data leakage, tampering or unauthorized access, thereby improving data confidentiality and protecting user privacy. The beneficial effects of cloud backup include: improving data recoverability and ensuring that data is not lost in unexpected circumstances; at the same time, cloud backup also allows data to be shared and accessed between different locations, enhancing the flexibility and accessibility of the system, enhancing the transparency of the system, and making it easier for managers and auditors to check and confirm the integrity and security of data, ensuring the controllability and compliance of the data processing process.

[0155] This embodiment also provides a smart building equipment control system, including:

[0156] The collection topology optimization module is used to collect environmental and building equipment data using intelligent sensors, pre-process the two sets of collected data, define building equipment as network nodes, define the connections between building equipment as edges, use the Kruskal algorithm to fuse the multimodal association topology of the two sets of data, construct a minimum spanning tree, set the inverse of the edge weight as the pheromone value, and use the maximum flow algorithm-ant colony algorithm to select the optimal control path;

[0157] The state prediction module is used to transform phase space data using the Takens embedding method, randomly select a pair of adjacent phase space data from the time series as the initial point, use the Lyapunov exponent to analyze the state of building equipment, build a hidden Markov model, and use the Lyapunov exponent to dynamically correct the transition probability matrix and the emission probability matrix to obtain the predicted state of the building equipment;

[0158] The scheduling monitoring module is used to construct a comprehensive objective function using a linear weighted method, solve it using a particle swarm optimization algorithm to obtain the optimal individual, convert it into a scheduling instruction using a dynamic scheduling algorithm and execute it, and use a PID control algorithm for monitoring and adjustment;

[0159] The storage module is used to store two sets of data generated by collection and analysis.

[0160] This embodiment also provides a computer device suitable for the case of a smart building equipment control method, comprising: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the smart building equipment control method proposed in the above embodiment.

[0161] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0162] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for controlling smart building equipment proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0163] In summary, the present invention collects environmental and building equipment data by using intelligent sensors, pre-processes the two sets of collected data, defines building equipment as network nodes, defines the connections between building equipment as edges, uses the Kruskal algorithm to fuse the multimodal association topology of the two sets of data, constructs a minimum spanning tree, sets the inverse of the edge weight as the pheromone value, and uses the maximum flow algorithm-ant colony algorithm to select the optimal control path; uses the Takens embedding method to convert phase space data, randomly selects a pair of adjacent phase space data from the time series as the initial point, uses the Lyapunov exponent to analyze the state of building equipment, constructs a hidden Markov model, and uses the Lyapunov exponent to dynamically correct the transition probability matrix and the emission probability matrix to obtain the predicted state of the building equipment; uses the linear weighted method to construct a comprehensive objective function, uses the particle swarm optimization algorithm to solve it, obtains the optimal individual, uses the dynamic scheduling algorithm to convert it into a scheduling instruction and execute it, and uses the PID control algorithm to monitor and adjust it; improves the response speed, resource utilization and control accuracy, avoids the impact of equipment failure on building operation, and enhances the comprehensiveness and adaptability of equipment control.

[0164] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for controlling smart building equipment, characterized in that: include, Use smart sensors to collect environmental and building equipment data, pre-process the two sets of collected data, define building equipment as network nodes, define connections between building equipment as edges, use the Kruskal algorithm to fuse the multimodal association topology of the two sets of data, construct a minimum spanning tree, set the inverse of the edge weight as the pheromone value, and use the maximum flow algorithm-ant colony algorithm to select the optimal control path; The phase space data is transformed using the Takens embedding method. A pair of adjacent phase space data is randomly selected from the time series as the initial point. The Lyapunov exponent is used to analyze the state of the building equipment, and a hidden Markov model is constructed. The Lyapunov exponent is used to dynamically modify the transition probability matrix and the emission probability matrix to obtain the predicted state of the building equipment. The linear weighted method is used to construct a comprehensive objective function, which is solved using the particle swarm optimization algorithm to obtain the optimal individual, which is converted into a scheduling instruction using the dynamic scheduling algorithm and executed, and the PID control algorithm is used for monitoring and adjustment; Two sets of data generated by storage collection and analysis.

2. The smart building equipment control method according to claim 1, characterized in that: The method uses intelligent sensors to collect environmental and building equipment data, defines building equipment as network nodes, defines connections between building equipment as edges, uses the Kruskal algorithm to fuse the multimodal association topology of the two sets of data, constructs a minimum spanning tree, sets the inverse of the edge weight as the pheromone value, and uses the maximum flow algorithm-ant colony algorithm to select the optimal control path, including: The smart sensors include light, temperature and humidity, vibration, bandwidth monitoring and delay monitoring sensors; The environment and building equipment data, including light intensity, temperature and humidity, vibration, bandwidth, and connection delay data; Use IoT protocols to connect sensors to central control systems; The building equipment includes air conditioners, elevators, lighting and smart sensors; The weight coefficients of bandwidth and connection delay data are calculated respectively using the hierarchical analysis method, and the bandwidth and connection delay data are combined using the weighted sum method to calculate the connection weights between building equipment, which are defined as edge weights. Sort the edge weights in ascending order, select the edge with the smallest edge weight as the first connection, then select the next edge with the smallest edge weight as the second connection, and use the union-find algorithm to gradually select the edges connecting the building equipment from the sorted edge weights until all the building equipment are connected into a connected graph, and then stop selecting to generate a minimum spanning tree; The ant colony algorithm is used to calculate the path selection probability, the edge weight is set as the path quality, the heuristic information is used to select the path, the pheromone evaporation coefficient is set using the empirical rule, and the pheromone increment formula is used to calculate the pheromone increment; When the ant selects a path, it uses the local pheromone update formula to update the pheromone concentration of the path; After each ant completes path selection and pheromone update, it proceeds to the next selection until all ants complete path selection and stop updating; After all ants have completed path selection, the weighted sum method is used to calculate the optimal path quality, the pheromone increment formula is used to calculate the optimal pheromone increment, and the global pheromone update formula is used to update the pheromone concentration of the optimal path; According to the pheromone concentration and quality of the optimal path, the ant colony algorithm is used to select the optimal control path.

3. The smart building equipment control method according to claim 2, characterized in that: The phase space data is transformed using the Takens embedding method, a pair of adjacent phase space data is randomly selected from the time series as the initial point, the Lyapunov index is used to analyze the state of the building equipment, a hidden Markov model is constructed, and the Lyapunov index is used to dynamically correct the transition probability matrix and the emission probability matrix to obtain the predicted state of the building equipment, including: Collect historical environmental data and preprocess them to generate training sets; Constructing a hidden Markov model and training the hidden Markov model using a training set, including discretizing the preprocessed historical environmental data into hidden states using a threshold discretization, wherein the hidden states include normal, faulty, and degraded; Count the number of transitions from one hidden state to another of the preprocessed historical environment data, use maximum likelihood to calculate the transition probability between each pair of states, fill the transition probability into the transition probability matrix and normalize it to obtain the initial transition probability matrix; Count the number of times the preprocessed historical environment data appears in the hidden state, use maximum likelihood to calculate the emission probability of each hidden state, fill the emission probability into the emission probability matrix and normalize it to obtain the initial emission probability matrix; Sort the preprocessed environmental data in chronological order to generate a time series; Use mutual information and FNN methods to set delay time and embedding dimension, and use Takens embedding method to transform time series into phase space data; Use the Euclidean distance formula to calculate the Euclidean distance between the initial points; The second time series is generated by using the small perturbation method for the initial point, and the Euclidean distance formula is used to calculate the Euclidean distance between the time series and the second time series; Calculate the Lyapunov exponent at time t using the tangent vector method; If the Lyapunov index at time t is greater than 0, it means that the building equipment is unstable. The control factors of the initial transfer probability matrix and the initial emission probability matrix are set using the cross-validation method, and the adjustment range of the transfer probability and the emission probability are calculated using the dynamic adjustment method. Use the proportional adjustment method to dynamically correct the transfer probability in the initial transfer probability matrix, dynamically correct the emission probability in the initial emission probability matrix, and obtain the dynamically corrected transfer probability matrix and emission probability matrix; The maximum a posteriori estimation is used to optimize the dynamically corrected transfer probability matrix and emission probability matrix to obtain the final transfer probability matrix and emission probability matrix; If the Lyapunov index at time t is less than or equal to 0, it means that the building equipment is normal, and the initial transfer probability matrix and initial emission probability matrix are used; The maximum probability that a building device is in a hidden state at time t using the Viterbi algorithm; The real-time environmental data is input into the trained hidden Markov model to obtain the predicted status of the building equipment.

4. The intelligent building equipment control method according to claim 3, characterized in that: The linear weighted method is used to construct a comprehensive objective function, and the particle swarm optimization algorithm is used to solve it to obtain the optimal individual, including: Normalize the predicted status of building equipment; Calculate the mean of the pre-processed temperature and humidity data respectively and set them as the ideal temperature and humidity data; The comfort objective function is set using the temperature and humidity deviation method; Use mean absolute error to set the loss function; The data-driven method is used to calculate the weight coefficients of the comfort objective function and the loss function respectively, and the linear weighted method is used to construct the comprehensive objective function; The initial population is randomly generated, and the individuals represent the combination of prediction error and comfort requirement; Bring the individual into the comprehensive objective function for evaluation and calculate the individual's fitness value; Use the tournament selection method to randomly select individuals for comparison, and select individuals with higher fitness as parents to participate in the crossover operation; Use single-point crossover to exchange genes of parent individuals to produce new offspring individuals. After crossover, individuals are randomly selected to mutate using single-point mutation to generate new individuals; The maximum number of iterations is set using the stopping criterion. When the maximum number of iterations is reached, the iteration is stopped and the optimal individual is output, including the optimized prediction error and comfort requirement.

5. The intelligent building equipment control method according to claim 4, characterized in that: The dynamic scheduling algorithm is used to convert the scheduling instructions and execute them, and the PID control algorithm is used to monitor and adjust, including: Use dynamic scheduling algorithms to convert optimal individuals into scheduling instructions, which are transmitted to building equipment through API interfaces. Building equipment receives the scheduling instructions and executes them. Collect feedback data and calculate the difference between the feedback data and the optimal individual; Use statistical methods to set the judgment threshold, compare the difference with the judgment threshold, and use the PID control algorithm to adjust the difference that is greater than or equal to the judgment threshold. Stop adjustment when the difference is less than the judgment threshold and continue to monitor the feedback data.

6. The intelligent building equipment control method according to claim 5, characterized in that: The preprocessing of the two sets of collected data includes: The two sets of collected data were aligned in time using the timestamp alignment method, outliers were identified and deleted using the quartile method, missing values ​​were filled using the mean imputation method, and the two sets of filled data were normalized.

7. The intelligent building equipment control method according to claim 6, characterized in that: The two sets of data generated by the storage collection and analysis include: The two sets of collected data and the optimal individual generated by the analysis are stored in the central database, and security access measures are set up. The central database will back up the stored data in the cloud and regularly perform integrity checks on the stored data and backup data. After the test is completed, the integrity test record is generated and stored synchronously in the central database.

8. A smart building equipment control system, based on the smart building equipment control method according to any one of claims 1 to 7, characterized in that: include, The collection topology optimization module is used to collect environmental and building equipment data using intelligent sensors, pre-process the two sets of collected data, define building equipment as network nodes, define the connections between building equipment as edges, use the Kruskal algorithm to fuse the multimodal association topology of the two sets of data, construct a minimum spanning tree, set the inverse of the edge weight as the pheromone value, and use the maximum flow algorithm-ant colony algorithm to select the optimal control path; The state prediction module is used to transform phase space data using the Takens embedding method, randomly select a pair of adjacent phase space data from the time series as the initial point, use the Lyapunov exponent to analyze the state of building equipment, build a hidden Markov model, and use the Lyapunov exponent to dynamically correct the transition probability matrix and the emission probability matrix to obtain the predicted state of the building equipment; The scheduling monitoring module is used to construct a comprehensive objective function using a linear weighted method, solve it using a particle swarm optimization algorithm to obtain the optimal individual, convert it into a scheduling instruction using a dynamic scheduling algorithm and execute it, and use a PID control algorithm for monitoring and adjustment; The storage module is used to store two sets of data generated by collection and analysis.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the smart building equipment control method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the smart building equipment control method described in any one of claims 1 to 7 are implemented.

Images