Elevator energy efficiency improvement control system

Abstract

The invention belongs to the technical field of elevator energy efficiency improvement control, and discloses an elevator energy efficiency improvement control system. The system comprises an elevator load prediction module, an operation scheme optimization generation module, a stepped voltage regulation module, an emergency scene sensing module and an emergency scene self-adaptive balance module, an elevator load prediction model is established based on historical feature vectors, a load prediction value is obtained according to the feature vectors, the load prediction value is analyzed, and an elevator load prediction result is obtained. The method comprises the steps of obtaining a start-stop optimization report, dynamically adjusting a voltage value required by a motor according to a load prediction value, obtaining a voltage adjustment report, collecting emergency scene related data based on a sensor network, processing the emergency scene related data, obtaining an emergency scene report, and obtaining an emergency operation report. The method has the remarkable advantages that the energy efficiency improvement effect on the use rule level is good, the invalid energy consumption saving effect on the energy supply level is large, and the safety energy efficiency balance capacity is high.

Description

Technical Field

[0001] The present invention relates to the technical field of elevator energy efficiency improvement control technology, and more particularly, to an elevator energy efficiency improvement control system. Background Art

[0002] An elevator is a permanent transport device that serves specific floors within a building, with its car running on at least two rigid tracks perpendicular to the horizontal plane or inclined at an angle of less than 15° to the vertical. At the end of the 20th century, elevators began using permanent magnet synchronous traction machines. These significantly reduced the size of the machine room and offered advantages such as low energy consumption, high efficiency, and rapid lifting speeds. This significantly boosted the development of super-high-rise real estate. By the end of 2024, there were 11.5324 million elevators in China. As of March 9, 2025, over 130,000 elevators had been installed through urban renewal initiatives nationwide.

[0003] The patent application publication number CN222023847U discloses an elevator control system and an elevator system, which are connected to an energy storage unit through a DC bus and are used to drive or brake the traction machine. The elevator control unit is connected to the energy storage unit and the drive unit respectively. When the traction machine is in the power generation state, the elevator control unit controls the energy storage unit to store the electric energy generated by the traction machine through the DC bus. By configuring the energy storage unit and controlling the energy storage unit through the elevator control unit, the energy storage unit stores the electric energy generated by the traction machine, which can improve the energy saving performance of the elevator.

[0004] However, although the above-mentioned elevator control system and elevator system achieve the effect of energy recovery and energy storage to a certain extent by controlling the energy storage unit to store the electric energy generated by the traction motor through the DC bus through the elevator control unit, and using the energy storage unit to store the electric energy generated by the traction motor, during the use of the elevator, due to the convenient attributes of the elevator, the elevator is a high-frequency used tool, so it is easy for the elevator to be empty and run ineffectively, which greatly causes the waste of elevator energy consumption. In addition, in emergency scenarios, due to its convenience, the elevator is likely to become the first choice of escape for frightened people, but often due to the vulnerability of the elevator in emergency scenarios, the people riding the elevator suffer greater harm.

[0005] In view of this, the present invention proposes an elevator energy efficiency improvement control system to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned objectives, the present invention provides the following technical solutions, including:

[0007] Elevator passenger flow data collection module, used to collect elevator passenger flow data sets, including floor call data, time period regularity data and average passenger data;

[0008] Real-time operation data collection module, used to collect real-time operation data sets, including real-time load data and pre-wait data;

[0009] The data conversion and extraction module is used to preprocess the elevator passenger flow dataset and the real-time operation dataset, and perform feature extraction to obtain feature vectors;

[0010] Furthermore, the steps of preprocessing the elevator passenger flow dataset and the real-time operation dataset and performing feature extraction include:

[0011] Q1: Complete data cleaning of all sub-data items in the basic data set by removing outliers, and normalize all sub-data items in the basic data set to the range of [0, 1] according to the normalization formula;

[0012] Q2: Calculate floor call data S a PS with historical average floor call data a The ratio of the frequency characteristic data A is obtained. a ;

[0013] Q3: Calculate the deviation feature based on real-time load data. The specific calculation formula for the deviation feature is:

[0014]

[0015] Get deviation characteristic data A b , where S d For real-time load data, μS d is the mean of historical real-time load data, σS d is the standard deviation of historical real-time load data;

[0016] Q4: Pre-wait data S e Multiply by the historical average number of passengers to obtain traffic characteristic data A c ;

[0017] Q5: Pack the frequency feature data, deviation feature data, and flow feature data to obtain a feature vector;

[0018] The elevator load prediction module is used to establish an elevator load prediction model based on historical feature vectors and obtain the load prediction value based on the feature vectors;

[0019] Furthermore, the steps of establishing an elevator load prediction model based on the historical feature vectors and obtaining a load prediction value based on the feature vectors include:

[0020] Step 1: Obtain a set of historical feature vectors stored in the database, compare them with the current time based on the timestamp, and group the comparison results into corresponding groups from small to large. The labeled results are L1, L2, L3, ..., Ln, and the labeled results are used as the sample set;

[0021] Step 2: Divide the sample set into a 70% training set, a 15% test set, and a 15% validation set, and establish the first elevator load prediction model based on the sample set;

[0022] Step 3: Calculate the historical eigenvectors through multiple heterogeneous sub-models. The specific formula for the calculation is:

[0023]

[0024] Get the first load prediction value respectively Second load prediction value and the third weight-bearing prediction value Among them, ν is the Sigmoid activation function, ω g is the gate weight vector, GELU is the Gaussian error linear unit, ω a is the attention weight matrix, F (t) is the eigenvector at time point t, b a Attention bias vector, is the feature modulation weight vector ω m The transpose T, tanh is the hyperbolic tangent function, D is the number of radial basis functions, α d , β d and γ d is the parameter of the dth basis function, φ is the radial basis function, Median is the median function, Γ is the historical feature library, and k is the number of nearest neighbors;

[0025] Step 4: Based on the first load prediction value, the second load prediction value, and the third load prediction value in step 3, the fusion output is performed. The specific calculation formula for the fusion is:

[0026]

[0027] Get the fourth load prediction value Among them, λ a ,λ b and λ c is the model confidence weight factor, ε is a constant term;

[0028] Step 5: Based on the fourth load prediction value in step 4, calculate the absolute value of the fourth load prediction value and the historical actual load value, and multiply it by 100% to obtain the prediction deviation rate;

[0029] When the prediction deviation rate is less than 2%, the elevator load prediction model is output;

[0030] When the prediction deviation rate is greater than or equal to 2%, return to step 3 to retrain the first elevator load prediction model;

[0031] Step 6: Input the feature vector into the elevator load prediction model and output the load prediction value;

[0032] Step 7: Output the load prediction value to the operation plan optimization generation module and the step voltage regulation module;

[0033] Operation plan optimization generation module is used to analyze the load prediction value and obtain the start-stop optimization report;

[0034] Furthermore, the methods for analyzing the weight-bearing prediction value include:

[0035] Based on the weight threshold interval (W1, W2);

[0036] When the predicted load value is less than W1, a low load report is generated; when the predicted load value is greater than or equal to W1 and less than W2, a medium load report is generated; when the predicted load value is greater than or equal to W2, a high load report is generated;

[0037] The low load report includes a description of the low elevator load forecast for a future time period, asking staff to monitor the elevator operation status, and generating a set of instructions representing a reduction in the number of invalid floor stops;

[0038] The medium load report includes instructions for predicting the elevator load in the future time period. The staff is requested to monitor the elevator status data during the period and generate a set of instructions for adjusting the elevator counterweight and dynamically allocating the landing floors.

[0039] The high load report includes a statement that the elevator load is predicted to be high in the future time period, and asks the staff to pay close attention to the safety status of the elevator operation, and generates a set of instructions representing increasing direct operation and reducing the number of starts and stops;

[0040] Pack low load report, medium load report and high load report to obtain start-stop optimization report;

[0041] The step-by-step voltage regulation module is used to dynamically adjust the motor voltage value according to the load prediction value and obtain a voltage regulation report;

[0042] Furthermore, the method of dynamically adjusting the voltage value required by the motor according to the load prediction value includes:

[0043] Based on the elevator load threshold interval (E1, E2);

[0044] When the load prediction value is less than E1, calculate and obtain the low load regulation voltage data When the load prediction value is greater than or equal to E1 and less than E2, calculate and obtain the medium load regulation voltage data When the load prediction value is greater than or equal to E2, calculate and obtain the low load regulation voltage data

[0045] The specific formula group for calculation is:

[0046]

[0047] in, is the minimum voltage value, A f is the rated voltage value, is the maximum voltage value, A e is the predicted value of weight bearing;

[0048] Packing low-load regulation voltage data, medium-load regulation voltage data, and high-load regulation voltage data to obtain a voltage regulation report;

[0049] Emergency scene perception module, which is used to collect emergency scene related data based on the sensor network, and process the emergency scene related data to obtain emergency scene reports;

[0050] Furthermore, the method of collecting emergency scene related data based on the sensor network and processing the emergency scene related data includes:

[0051] Through smart meters, the voltage values ​​of power supply lines in a specified area are collected to obtain environmental power supply data;

[0052] The photoelectric smoke sensor collects the particle concentration value in the specified area to obtain the environmental smoke data;

[0053] The MEMS accelerometer is used to collect the three-axis acceleration values ​​in the specified elevator shaft to obtain the environmental vibration data;

[0054] When the ambient power supply data is less than 100 for five seconds, a power outage status report is generated;

[0055] When the ambient smoke data is greater than 500, a fire status report is generated;

[0056] When the ambient vibration data is greater than 0.5 for three seconds, an earthquake status report is generated;

[0057] Package power outage status reports, fire status reports, and earthquake status reports to obtain emergency scenario reports;

[0058] Emergency scenario adaptive balancing module, used to adjust the elevator operation mode based on the emergency scenario report and obtain the emergency operation report in combination with the minimum number of operations;

[0059] Furthermore, the elevator operation mode is adjusted based on the emergency scenario report and combined with the minimum number of operations, including:

[0060] Identify the contents of emergency operations reports;

[0061] When the emergency scenario report is a fire status report or an earthquake status report, an operation stop report and a set of instructions representing enabling minimum energy consumption operation are generated;

[0062] When the emergency scenario report is a power outage status report, a minimum operation report and a set of instructions representing enabling minimum energy consumption operation are generated;

[0063] The operation stop report includes stating that the current environment is not suitable for using the elevator and generating a set of instructions representing disabling the elevator;

[0064] The minimum operation report includes information indicating the low performance of the elevator in the current environment, data on the minimum number of operations, and a set of instructions for enabling minimum energy consumption operation;

[0065] The minimum number of operations is obtained by dividing the remaining power of the backup power supply by the maximum energy consumption of a single operation;

[0066] Pack the operation stop report and minimum operation report to obtain the emergency operation report;

[0067] Data management and communication module, used to integrate system data and store it in the database, and process start-stop optimization reports, voltage regulation reports and emergency operation reports;

[0068] Furthermore, the methods for processing the start-stop optimization report, the voltage regulation report, and the emergency operation report include:

[0069] Identify the instruction content in the start-stop optimization report and send the instruction to the operation rule controller;

[0070] Identify the instruction content in the voltage regulation report and send the instruction to the motor power controller;

[0071] Identify the instruction content in the emergency operation report and send the instruction to the intelligent controller;

[0072] Collect the elevator passenger flow dataset, real-time operation dataset, feature vector, load prediction value, start-stop optimization report, voltage regulation report, and emergency operation report to obtain the system dataset;

[0073] Furthermore, S1: collecting an elevator passenger flow data set, the elevator passenger flow data set includes floor call data, time period regularity data and average passenger data;

[0074] S2: Collect real-time operation data sets, which include real-time load data and pre-wait data;

[0075] S3: Preprocess the elevator passenger flow dataset and the real-time operation dataset, and perform feature extraction to obtain feature vectors;

[0076] S4: Establish an elevator load prediction model based on the historical feature vectors, and obtain the load prediction value based on the feature vectors;

[0077] S5: Analyze the load prediction value and obtain a start-stop optimization report;

[0078] S6: Dynamically adjust the voltage value required by the motor according to the load prediction value and obtain a voltage regulation report;

[0079] S7: Collect emergency scenario-related data based on the sensor network, process the emergency scenario-related data, and obtain an emergency scenario report;

[0080] S8: Adjust the elevator operation mode based on the emergency scenario report and obtain an emergency operation report in combination with the minimum number of operations;

[0081] S9: Integrate system data and store it in the database, and process the start-stop optimization report, voltage regulation report and emergency operation report.

[0082] The technical effects and advantages of the elevator energy efficiency improvement control system of the present invention are as follows:

[0083] The present invention collects elevator passenger flow data sets, which include floor call data, time period regularity data and average passenger data, collects real-time operation data sets, which include real-time load data and pre-waiting data, pre-processes the elevator passenger flow data sets and the real-time operation data sets, and performs feature extraction to obtain feature vectors, establishes an elevator load prediction model based on historical feature vectors, obtains load prediction values ​​based on the feature vectors, analyzes the load prediction values ​​to obtain a start-stop optimization report, dynamically adjusts the voltage value required by the motor based on the load prediction value to obtain a voltage regulation report, collects emergency scenario related data based on a sensor network, processes the emergency scenario related data to obtain an emergency scenario report, adjusts the elevator operation mode based on the emergency scenario report, and obtains an emergency operation report in combination with the minimum number of operations, integrates system data and stores them in a database, and processes the start-stop optimization report, voltage regulation report and emergency operation report, so that the system can The invention can accurately predict the required load of the elevator in the next time period under the dynamic changes of weight and the number of people waiting in advance, which provides an important data basis for the subsequent data analysis and mining of the system. In addition, the invention also analyzes the weight prediction value, so that the system can generate corresponding energy-saving measures according to the elevator weight situation in the future time period, thereby effectively reducing the invalid energy loss during the use of the elevator, thereby further reducing the user's elevator use cost. At the same time, by dynamically adjusting the voltage value required for the operation of the elevator based on the weight prediction value, compared with the traditional fixed voltage input, the system can further reduce the invalid energy loss during the use of the elevator at the energy input level. Moreover, by identifying the type of emergency scene and performing targeted classification processing, the system can effectively balance the conflict between safety and energy efficiency. In general, the invention has the significant advantages of good energy efficiency improvement effect at the usage rule level, large invalid energy saving effect at the energy supply level, and strong safety and energy efficiency balancing ability. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Figure 1 This is a schematic diagram of an elevator energy efficiency improvement control system according to the present invention;

[0085] Figure 2 Schematic diagram of a control method for improving elevator energy efficiency according to the present invention. DETAILED DESCRIPTION

[0086] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0087] The terms used in the embodiments of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms "a," "an," "the," and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two.

[0088] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0089] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0090] In fact, the server-side device deployed by the elevator energy efficiency improvement control system may be composed of one or more devices. The above-mentioned elevator energy efficiency improvement control system can be implemented as: a business instance, a virtual machine, and a hardware device. For example, the elevator energy efficiency improvement control system can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, the elevator energy efficiency improvement control system can be understood as a software deployed on a cloud node, which is used to provide the elevator energy efficiency improvement control system to each user terminal. Alternatively, the elevator energy efficiency improvement control system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. The virtual machine is installed with application software for managing each user terminal. Alternatively, the elevator energy efficiency improvement control system can also be implemented as a server-side composed of many hardware devices of the same or different types, with one or more hardware devices being set up to provide the elevator energy efficiency improvement control system to each user terminal.

[0091] In terms of implementation, the elevator energy efficiency improvement control system and the user end are mutually compatible. Specifically, if the elevator energy efficiency improvement control system is an application installed on a cloud service platform, the user end is the client that establishes a communication connection with the application. Alternatively, if the elevator energy efficiency improvement control system is implemented as a website, the user end is implemented as a webpage. Alternatively, if the elevator energy efficiency improvement control system is implemented as a cloud service platform, the user end is implemented as a mini-program within an instant messaging application.

[0092] like Figure 1 FIG. 1 is a system architecture diagram of an elevator energy efficiency improvement control system provided by an embodiment of the present invention.

[0093] The elevator energy efficiency improvement control system of the present invention can be set in a cloud server. In terms of implementation, it can be used as one or more service devices, or as an application installed on the cloud (such as a mobile service operator's server, server cluster, etc.), or it can be developed as a website. According to the functions implemented, the elevator energy efficiency improvement control system may include an elevator passenger flow data acquisition module, a real-time operation data acquisition module, a data conversion and extraction module, an elevator load prediction module, an operation plan optimization generation module, a step-by-step voltage regulation module, an emergency scenario perception module, an emergency scenario adaptive balancing module, and a data management and communication module. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0094] In an embodiment of the present invention, in the elevator energy efficiency improvement control system, each of the above modules can be implemented independently and called with other modules. The call here can be understood as a module that can connect to multiple modules of another type and provide corresponding services to the multiple modules connected to it. For example, the sharing evaluation module can call the same information acquisition module to obtain the information collected by the information acquisition module. Based on the above characteristics, in the elevator energy efficiency improvement control system provided by the embodiment of the present invention, the scope of application of the elevator energy efficiency improvement control system architecture can be adjusted by adding modules and directly calling them without modifying the program code, thereby realizing cluster-type horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the elevator energy efficiency improvement control system. In actual applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in cloud servers.

[0095] Example 1

[0096] See also Figure 1 As shown, the elevator energy efficiency improvement control system described in this embodiment includes:

[0097] The elevator passenger flow data collection module is used to collect elevator passenger flow data sets, which include floor call data, time period regularity data and average passenger data;

[0098] It should be explained that the elevator control motherboard is used to collect the number of floor button triggers per hour of the specified elevator to obtain floor call data; the gate counter is used to collect the number of people entering and exiting the specified elevator per hour, and average statistics are performed. Peak hours and off-peak hours are divided according to the average number of people entering and exiting per hour to obtain time period regularity data, where, for example, the peak hour is 8:00-10:00; the car weight sensor and AI camera are used to collect the number of passengers and passenger weight in a single call of the specified elevator, and the average weight of each passenger is taken to obtain average passenger data;

[0099] The real-time operation data acquisition module is used to collect real-time operation data sets, which include real-time load data and pre-wait data;

[0100] It should be explained that the real-time pressure value of the specified elevator is collected through the car piezoelectric sensor to obtain the real-time load data; the number of heat sources in the waiting area is collected through the infrared thermal imager to obtain the pre-waiting data;

[0101] The data conversion and extraction module is used to preprocess the elevator passenger flow data set and the real-time operation data set, and perform feature extraction to obtain feature vectors;

[0102] Furthermore, the steps of preprocessing the elevator passenger flow dataset and the real-time operation dataset and performing feature extraction include:

[0103] Q1: Complete data cleaning of all sub-data items in the basic data set by removing outliers, and normalize all sub-data items in the basic data set to the range of [0, 1] according to the normalization formula;

[0104] It should be explained that removing outliers means, for example, that the real-time weight data is negative; the basic data set includes the elevator passenger flow data set and the real-time operation data set; the specific expression formula of the normalization formula is: where X new is the normalized value, X is any sub-data item of the basic data, X max is the historical maximum value of any sub-data item, X min is the historical minimum value of any sub-data item; normalization is used to eliminate the dimensions of all sub-data items in the basic data set;

[0105] Q2: Calculate floor call data S a PS with historical average floor call data a The ratio of the frequency characteristic data A is obtained. a ;

[0106] Q3: Calculate the deviation feature based on real-time load data. The specific calculation formula for the deviation feature is:

[0107]

[0108] Get deviation characteristic data A b , where S d For real-time load data, μS d is the mean of historical real-time load data, σS d is the standard deviation of historical real-time load data;

[0109] Q4: Pre-wait data S eMultiply the historical average passenger number to get the traffic feature data A c ;

[0110] Q5: Pack the frequency feature data, bias feature data and traffic feature data to get the feature vector;

[0111] It needs to be explained that the use of sub-data items in the basic data involved in steps Q2 to Q4 and all subsequent modules is the data value after data cleaning and data normalization;

[0112] The elevator load prediction module is configured to establish an elevator load prediction model based on historical feature vectors and obtain a load prediction value according to the feature vectors;

[0113] Further, the step of establishing an elevator load prediction model based on historical feature vectors and obtaining a load prediction value according to the feature vectors includes:

[0114] Step one: Obtain a set of historical feature vectors stored in the database, and compare the time stamp with the current time, and sort the comparison results from small to large, and mark the corresponding groups as L1, L2, L3,..., Ln, and the marking result is used as a sample set;

[0115] Step two: divide the sample set into 70% training set, 15% test set and 15% validation set, and establish a first elevator load prediction model according to the sample set;

[0116] Step three: calculate the historical feature vectors by multiple heterogeneous sub-models, and the specific formula group is:

[0117]

[0118] respectively obtaining a first load prediction value a second load prediction value and a third load prediction value Wherein, ν is a Sigmoid activation function, ω g is a gate weight vector, GELU is a Gaussian error linear unit, ω a is an attention weight matrix, F (t) is the feature vector of time point t, b a is the attention bias vector, is the transpose T of the feature modulation weight vector ω m , tanh is the hyperbolic tangent function, D is the number of radial basis functions, α d , β d and γ d are the parameters of the dth basis function, φ is the radial basis function, Median is the median function, Γ is the historical feature library, and k is the number of nearest neighbors.

[0119] It should be explained that the Sigmoid activation function is used to constrain the output values ​​in the brackets to be within the range of (0, 1); the hyperbolic tangent function constrains the output norm values ​​in the brackets to be within the range of [-1, 1]; the radial basis function is used to extract local features; and the median function is used to take the median of the values ​​in the brackets as the output value.

[0120] Step 4: Based on the first load prediction value, the second load prediction value, and the third load prediction value in step 3, the fusion output is performed. The specific calculation formula for the fusion is:

[0121]

[0122] Get the fourth load prediction value Among them, λ a ,λ b and λ c is the model confidence weight factor, ε is a constant term;

[0123] Step 5: Based on the fourth load prediction value in step 4, calculate the absolute value of the fourth load prediction value and the historical actual load value, and multiply it by 100% to obtain the prediction deviation rate;

[0124] When the prediction deviation rate is less than 2%, the elevator load prediction model is output;

[0125] When the prediction deviation rate is greater than or equal to 2%, return to step 3 to retrain the first elevator load prediction model;

[0126] Step 6: Input the feature vector into the elevator load prediction model and output the load prediction value;

[0127] Step 7: Output the load prediction value to the operation plan optimization generation module and the step voltage regulation module;

[0128] The operation plan optimization generation module is used to analyze the load prediction value and obtain a start-stop optimization report;

[0129] Further, methods for analyzing the weight-bearing prediction value include:

[0130] Based on the weight threshold interval (W1, W2);

[0131] It should be explained that the weight threshold interval is manually determined and input into the system;

[0132] When the predicted load value is less than W1, a low load report is generated; when the predicted load value is greater than or equal to W1 and less than W2, a medium load report is generated; when the predicted load value is greater than or equal to W2, a high load report is generated;

[0133] The low load report includes a description of the low elevator load forecast for a future time period, asking staff to monitor the elevator operation status, and generating a set of instructions representing a reduction in the number of invalid floor stops;

[0134] The medium load report includes instructions for predicting the elevator load in the future time period. The staff is requested to monitor the elevator status data during the period and generate a set of instructions for adjusting the elevator counterweight and dynamically allocating the landing floors.

[0135] The high load report includes a statement that the elevator load is predicted to be high in the future time period, and asks the staff to pay close attention to the safety status of the elevator operation, and generates a set of instructions representing increasing direct operation and reducing the number of starts and stops;

[0136] Pack low load report, medium load report and high load report to obtain start-stop optimization report;

[0137] The step-by-step voltage regulation module is used to dynamically adjust the voltage value required by the motor according to the load prediction value to obtain a voltage regulation report;

[0138] Furthermore, the method of dynamically adjusting the motor voltage value according to the load prediction value includes:

[0139] Based on the elevator load threshold interval (E1, E2);

[0140] It should be explained that the elevator load threshold range is manually determined and input into the system;

[0141] When the load prediction value is less than E1, calculate and obtain the low load regulation voltage data A e (1) When the load prediction value is greater than or equal to E1 and less than E2, calculate and obtain the medium load regulation voltage data A e (2) When the load prediction value is greater than or equal to E2, calculate and obtain the low load regulation voltage data A e (3) ;

[0142] The specific formula group for calculation is:

[0143]

[0144] in, is the minimum voltage value, A f is the rated voltage value, is the maximum voltage value, A e is the predicted value of weight bearing;

[0145] Packing low-load regulation voltage data, medium-load regulation voltage data, and high-load regulation voltage data to obtain a voltage regulation report;

[0146] The emergency scene perception module is used to collect emergency scene related data based on the sensor network, and process the emergency scene related data to obtain an emergency scene report;

[0147] Furthermore, the method of collecting emergency scene related data based on the sensor network and processing the emergency scene related data includes:

[0148] Through smart meters, the voltage values ​​of power supply lines in a specified area are collected to obtain environmental power supply data;

[0149] The photoelectric smoke sensor collects the particle concentration value in the specified area to obtain the environmental smoke data;

[0150] The MEMS accelerometer is used to collect the three-axis acceleration values ​​in the specified elevator shaft to obtain the environmental vibration data;

[0151] When the ambient power supply data is less than 100 for five seconds, a power outage status report is generated;

[0152] When the ambient smoke data is greater than 500, a fire status report is generated;

[0153] When the ambient vibration data is greater than 0.5 for three seconds, an earthquake status report is generated;

[0154] Package power outage status reports, fire status reports, and earthquake status reports to obtain emergency scenario reports;

[0155] The emergency scenario adaptive balancing module is used to adjust the elevator operation mode based on the emergency scenario report and obtain an emergency operation report in combination with the minimum operation number;

[0156] Furthermore, the elevator operation mode is adjusted based on the emergency scenario report and combined with the minimum number of operations, including:

[0157] Identify the contents of emergency operations reports;

[0158] When the emergency scenario report is a fire status report or an earthquake status report, an operation stop report and a set of instructions representing enabling minimum energy consumption operation are generated;

[0159] When the emergency scenario report is a power outage status report, a minimum operation report and a set of instructions representing enabling minimum energy consumption operation are generated;

[0160] The operation stop report includes stating that the current environment is not suitable for using the elevator and generating a set of instructions representing disabling the elevator;

[0161] The minimum operation report includes information indicating the low performance of the elevator in the current environment, data on the minimum number of operations, and a set of instructions for enabling minimum energy consumption operation;

[0162] The minimum number of operations is obtained by dividing the remaining power of the backup power supply by the maximum energy consumption of a single operation;

[0163] Pack the operation stop report and minimum operation report to obtain the emergency operation report;

[0164] The data management and communication module is used to integrate system data and store it in a database, and process start-stop optimization reports, voltage regulation reports, and emergency operation reports;

[0165] Furthermore, the methods for processing the start-stop optimization report, voltage regulation report and emergency operation report include:

[0166] Identify the instruction content in the start-stop optimization report and send the instruction to the operation rule controller;

[0167] Identify the instruction content in the voltage regulation report and send the instruction to the motor power controller;

[0168] Identify the instruction content in the emergency operation report and send the instruction to the intelligent controller;

[0169] Collect the elevator passenger flow dataset, real-time operation dataset, feature vector, load prediction value, start-stop optimization report, voltage regulation report, and emergency operation report to obtain the system dataset;

[0170] This embodiment has the beneficial effects of collecting elevator passenger flow data sets, which include floor call data, time period regularity data and average passenger data, collecting real-time operation data sets, which include real-time load data and pre-waiting data, pre-processing the elevator passenger flow data sets and real-time operation data sets, and performing feature extraction to obtain feature vectors, establishing an elevator load prediction model based on historical feature vectors, and obtaining load prediction values ​​based on the feature vectors, analyzing the load prediction values ​​to obtain a start-stop optimization report, dynamically adjusting the voltage value required by the motor based on the load prediction value to obtain a voltage regulation report, collecting emergency scenario related data based on the sensor network, processing the emergency scenario related data to obtain an emergency scenario report, adjusting the elevator operation mode based on the emergency scenario report, and obtaining an emergency operation report in combination with the minimum number of operations, integrating system data and storing them in a database, and processing the start-stop optimization report, voltage regulation report and emergency operation report, so that the system can The system accurately predicts the required load of the elevator in the next time period under the dynamic changes of real-time load and the number of people waiting in advance, which provides an important data basis for the subsequent data analysis and mining of the system. In addition, the present invention also analyzes the load prediction value, so that the system can generate corresponding energy-saving measures according to the load situation of the elevator in the future time period, thereby effectively reducing the invalid energy loss during the use of the elevator, thereby further reducing the user's elevator usage cost. At the same time, by dynamically adjusting the voltage value required for the operation of the elevator based on the load prediction value, compared with the traditional fixed voltage input, the system can further reduce the invalid energy loss during the use of the elevator at the energy input level. Moreover, by identifying the type of emergency scene and performing targeted classification processing, the system can effectively balance the conflict between safety and energy efficiency. Overall, the present invention has the significant advantages of good energy efficiency improvement effect at the usage rule level, large invalid energy saving effect at the energy supply level, and strong safety and energy efficiency balancing ability.

[0171] Example 2

[0172] See also Figure 2 As shown, for parts not described in detail in this embodiment, please refer to the description of Embodiment 1. A method for improving energy efficiency of an elevator is provided, the method comprising: S1: collecting an elevator passenger flow data set, the elevator passenger flow data set including floor call data, time period regularity data, and average passenger data;

[0173] S2: Collect real-time operation data sets, which include real-time load data and pre-wait data;

[0174] S3: Preprocess the elevator passenger flow dataset and the real-time operation dataset, and perform feature extraction to obtain feature vectors;

[0175] S4: Establish an elevator load prediction model based on the historical feature vectors, and obtain the load prediction value based on the feature vectors;

[0176] S5: Analyze the load prediction value and obtain a start-stop optimization report;

[0177] S6: Dynamically adjust the voltage value required by the motor according to the load prediction value and obtain a voltage regulation report;

[0178] S7: Collect emergency scenario-related data based on the sensor network, process the emergency scenario-related data, and obtain an emergency scenario report;

[0179] S8: Adjust the elevator operation mode based on the emergency scenario report and obtain an emergency operation report in combination with the minimum number of operations;

[0180] S9: Integrate system data and store it in the database, and process the start-stop optimization report, voltage regulation report and emergency operation report.

[0181] Example 3

[0182] 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.

[0183] 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.

[0184] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0185] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. Terms such as "first" and "second" are used to indicate names and do not imply any particular order.

[0186] Finally, it should be noted that the above examples are merely intended to illustrate the technical solutions of the present application and not to limit the present application. Although the present application 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 application can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. An elevator energy efficiency improvement control system, characterized in that: The system includes: an elevator load prediction module, an operation plan optimization generation module, a step-by-step voltage regulation module, an emergency scenario perception module, and an emergency scenario adaptive balancing module, wherein: The elevator load prediction module is used to establish an elevator load prediction model based on historical feature vectors and obtain a load prediction value based on the feature vectors; The operation plan optimization generation module is used to analyze the load prediction value and obtain a start-stop optimization report; The step-by-step voltage regulation module is used to dynamically adjust the voltage value required by the motor according to the load prediction value to obtain a voltage regulation report; The emergency scene perception module is used to collect emergency scene related data based on the sensor network, and process the emergency scene related data to obtain an emergency scene report; The emergency scenario adaptive balancing module is used to adjust the elevator operation mode based on the emergency scenario report and obtain an emergency operation report in combination with the minimum operation number.

2. The elevator energy efficiency improvement control system according to claim 1, characterized in that: The system also includes: an elevator passenger flow data acquisition module, a real-time operation data acquisition module, a data conversion and extraction module, and a data management and communication module, wherein: The elevator passenger flow data collection module is used to collect elevator passenger flow data sets, which include floor call data, time period regularity data and average passenger data; The real-time operation data acquisition module is used to collect real-time operation data sets, which include real-time load data and pre-wait data; The data conversion and extraction module is used to preprocess the elevator passenger flow data set and the real-time operation data set, and perform feature extraction to obtain feature vectors; The data management and communication module is used to integrate system data and store it in a database, and to process start-stop optimization reports, voltage regulation reports and emergency operation reports.

3. The elevator energy efficiency improvement control system according to claim 2, characterized in that: The steps for preprocessing the elevator passenger flow dataset and the real-time operation dataset and extracting features include: Q1: Complete data cleaning of all sub-data items in the basic data set by removing outliers, and normalize all sub-data items in the basic data set to the range of [0, 1] according to the normalization formula; Q2: Calculate floor call data S a PS with historical average floor call data a The ratio of the frequency characteristic data A is obtained. a ; Q3: Calculate the deviation feature based on real-time load data. The specific calculation formula for the deviation feature is: Get deviation characteristic data A b , where S d For real-time load data, μS d is the mean of historical real-time load data, σS d is the standard deviation of historical real-time load data; Q4: Pre-wait data S e Multiply by the historical average number of passengers to obtain traffic characteristic data A c ; Q5: Package the frequency feature data, deviation feature data, and flow feature data to obtain a feature vector.

4. The elevator energy efficiency improvement control system according to claim 1, characterized in that: The steps of establishing an elevator load prediction model based on historical eigenvectors and obtaining a load prediction value based on the eigenvectors include: Step 1: Obtain a set of historical feature vectors stored in the database, compare them with the current time based on the timestamp, and group the comparison results into corresponding groups from small to large. The labeled results are L1, L2, L3, ..., Ln, and the labeled results are used as the sample set; Step 2: Divide the sample set into a 70% training set, a 15% test set, and a 15% validation set, and establish the first elevator load prediction model based on the sample set; Step 3: Calculate the historical eigenvectors through multiple heterogeneous sub-models. The specific formula for the calculation is: Get the first load prediction value respectively Second load prediction value and the third weight-bearing prediction value Among them, ν is the Sigmoid activation function, ω g is the gate weight vector, GELU is the Gaussian error linear unit, ω a is the attention weight matrix, F (t) is the eigenvector at time point t, b a Attention bias vector, is the feature modulation weight vector ω m The transpose T, tanh is the hyperbolic tangent function, D is the number of radial basis functions, α d , β d and γ d is the parameter of the dth basis function, φ is the radial basis function, Median is the median function, Γ is the historical feature library, and k is the number of nearest neighbors; Step 4: Based on the first load prediction value, the second load prediction value, and the third load prediction value in step 3, the fusion output is performed. The specific calculation formula for the fusion is: Get the fourth load prediction value Among them, λ a ,λ b and λ c is the model confidence weight factor, ε is a constant term; Step 5: Based on the fourth load prediction value in step 4, calculate the absolute value of the fourth load prediction value and the historical actual load value, and multiply it by 100% to obtain the prediction deviation rate; When the prediction deviation rate is less than 2%, the elevator load prediction model is output; When the prediction deviation rate is greater than or equal to 2%, return to step 3 to retrain the first elevator load prediction model; Step 6: Input the feature vector into the elevator load prediction model and output the load prediction value; Step 7: Output the load prediction value to the operation plan optimization generation module and the step voltage regulation module.

5. The elevator energy efficiency improvement control system according to claim 1, characterized in that: Methods for analyzing weight-bearing predictions include: Based on the weight threshold interval (W1, W2); When the predicted load value is less than W1, a low load report is generated; when the predicted load value is greater than or equal to W1 and less than W2, a medium load report is generated; when the predicted load value is greater than or equal to W2, a high load report is generated; The low load report includes a description of the low elevator load forecast for a future time period, asking staff to monitor the elevator operation status, and generating a set of instructions representing a reduction in the number of invalid floor stops; The medium load report includes instructions for predicting the elevator load in the future time period. The staff is requested to monitor the elevator status data during the period and generate a set of instructions representing the adjustment of the elevator counterweight and the dynamic allocation of the landing floors. The high load report includes a statement that the elevator load is predicted to be high in the future time period, and asks the staff to pay close attention to the safe operation status of the elevator, and generates a set of instructions representing increasing direct operation and reducing the number of starts and stops; The low load report, medium load report and high load report are packaged to obtain the start-stop optimization report.

6. The elevator energy efficiency improvement control system according to claim 1, characterized in that: Methods for dynamically adjusting the motor voltage value based on the load prediction value include: Based on the elevator load threshold interval (E1, E2); When the load prediction value is less than E1, calculate and obtain the low load regulation voltage data A e (1) When the load prediction value is greater than or equal to E1 and less than E2, calculate and obtain the medium load regulation voltage data A e (2) When the load prediction value is greater than or equal to E2, calculate and obtain the low load regulation voltage data The specific formula group for calculation is: in, is the minimum voltage value, A f is the rated voltage value, is the maximum voltage value, A e is the predicted value of weight bearing; The low load regulation voltage data, the medium load regulation voltage data and the high load regulation voltage data are packaged to obtain a voltage regulation report.

7. The elevator energy efficiency improvement control system according to claim 1, characterized in that: Methods for collecting emergency scenario-related data based on sensor networks and processing the emergency scenario-related data include: Through smart meters, the voltage values ​​of power supply lines in a specified area are collected to obtain environmental power supply data; The photoelectric smoke sensor collects the particle concentration value in the specified area to obtain the environmental smoke data; The MEMS accelerometer is used to collect the three-axis acceleration values ​​in the specified elevator shaft to obtain the environmental vibration data; When the ambient power supply data is less than 100 for five seconds, a power outage status report is generated; When the ambient smoke data is greater than 500, a fire status report is generated; When the ambient vibration data is greater than 0.5 for three seconds, an earthquake status report is generated; Package power outage status reports, fire status reports, and earthquake status reports to obtain emergency scenario reports.

8. The elevator energy efficiency improvement control system according to claim 1, characterized in that: Methods for adjusting elevator operation modes based on emergency scenario reports and combining them with the minimum number of operations include: Identify the contents of emergency operations reports; When the emergency scenario report is a fire status report or an earthquake status report, an operation stop report and a set of instructions representing enabling minimum energy consumption operation are generated; When the emergency scenario report is a power outage status report, a minimum operation report and a set of instructions representing enabling minimum energy consumption operation are generated; The operation stop report includes stating that the current environment is not suitable for using the elevator and generating a set of instructions representing disabling the elevator; The minimum operation report includes information indicating the low performance of the elevator in the current environment, data on the minimum number of operations, and a set of instructions for enabling minimum energy consumption operation; The minimum number of operations is obtained by dividing the remaining power of the backup power supply by the maximum energy consumption of a single operation; Package the operation stop report and minimum operation report to obtain the emergency operation report.

9. The elevator energy efficiency improvement control system according to claim 2, characterized in that: The methods for processing the start-stop optimization report, voltage regulation report and emergency operation report include: Identify the instruction content in the start-stop optimization report and send the instruction to the operation rule controller; Identify the instruction content in the voltage regulation report and send the instruction to the motor power controller; Identify the instruction content in the emergency operation report and send the instruction to the intelligent controller; The system dataset is obtained by integrating the elevator passenger flow dataset, real-time operation dataset, feature vector, load prediction value, start-stop optimization report, voltage regulation report and emergency operation report.

10. A method for improving energy efficiency of an elevator, implemented according to an elevator energy efficiency improvement control system according to any one of claims 1 to 9, characterized in that: The following steps are included: S1: Collect elevator passenger flow data sets, which include floor call data, time period regularity data, and average passenger data; S2: Collect real-time operation data sets, which include real-time load data and pre-wait data; S3: Preprocess the elevator passenger flow dataset and the real-time operation dataset, and perform feature extraction to obtain feature vectors; S4: Establish an elevator load prediction model based on the historical feature vectors, and obtain the load prediction value based on the feature vectors; S5: Analyze the load prediction value and obtain a start-stop optimization report; S6: Dynamically adjust the voltage value required by the motor according to the load prediction value and obtain a voltage regulation report; S7: Collect emergency scenario-related data based on the sensor network, process the emergency scenario-related data, and obtain an emergency scenario report; S8: Adjust the elevator operation mode based on the emergency scenario report and obtain an emergency operation report in combination with the minimum number of operations; S9: Integrate system data and store it in the database, and process the start-stop optimization report, voltage regulation report and emergency operation report.

Images