An elevator management system based on elevator operation electrical data

By building an elevator operation energy consumption analysis model in the elevator management system, real-time monitoring and prediction of elevator energy consumption, the problem of insufficient timeliness of elevator operation management in the existing technology is solved, and real-time monitoring and risk warning of elevator energy consumption is achieved. Reduces the risk of elevator operation.

CN118850901BActive Publication Date: 2024-11-26HUNAN ELECTRICAL COLLEGE OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411331794.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-24
Publication Date
2024-11-26
Estimated Expiration
2044-09-24

AI Technical Summary

Technical Problem

The existing elevator management system lacks the ability to monitor the elevator operation data in real time and is unable to continuously and dynamically monitor the power supply status, resulting in abnormal elevator operation failures in time, increasing the risk of elevator operation.

Method used

Design an elevator management system based on elevator operation data, and use linear regression or The recurrent neural network builds an elevator operation energy consumption analysis model, predicts energy consumption in real time and compares it with actual energy consumption, generates early warning information and abnormal indexes, finds energy consumption waste nodes, and reduces the risk of elevator operation.

Benefits of technology

Real-time prediction and continuous monitoring of elevator energy consumption are achieved, potential risks are discovered in advance, elevator operation risks are reduced, serious accidents such as electrical fires caused by power failures, and the safety and reliability of elevator operation are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118850901B_ABST
    Figure CN118850901B_ABST
Patent Text Reader

Abstract

The present invention discloses an elevator management system based on elevator operation electrical data, and specifically relates to the technical field of elevator operation data analysis. The product of the elevator's standby time and the preset standby energy consumption per unit time is used to represent the theoretical value of the elevator's standby energy consumption. An elevator operation energy consumption analysis model is built based on linear regression or recurrent neural network. Operation data is input into the elevator operation energy consumption analysis model, and the theoretical value of the elevator operation energy consumption is output. The difference between the theoretical value of the elevator energy consumption and the actual energy consumption value is monitored in real time, and measures are taken to solve the problem of insufficient timeliness of elevator operation management in the prior art. The elevator operation data is divided into several time periods based on the operation scenario, and an operation risk coefficient is generated based on the elevator energy consumption abnormality index, the audio abnormality index and the operation reliability index. The elevator monitoring resources are allocated based on the operation risk coefficient to solve the problem of waste of monitoring resources caused by fixed frequency maintenance.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of elevator operation data analysis, and more specifically, to an elevator management system based on elevator operation electrical data. Background Art

[0002] As an indispensable means of vertical transportation in modern buildings, the safe and efficient operation of elevators is of great significance to ensuring personnel safety and improving building efficiency.

[0003] At present, with the advancement of science and technology and the development of intelligent technology, elevator management systems have made certain progress. The existing elevator management systems can collect some basic data during the operation of the elevator through sensors and other equipment, such as operating time, floor information, etc.; traditional elevator management systems often focus on post-management, that is, inspection and maintenance are carried out only after the elevator fails or abnormalities.

[0004] Elevators rely on electricity to operate. Abnormal energy consumption may mean that there is a problem with the power control system. Abnormal elevator energy consumption often reflects that the mechanical parts of the elevator may be worn, aged or faulty. Power failures will not only cause the elevator to suddenly stop running or fail to start normally, but may also cause serious accidents such as electrical fires. These problems may cause the elevator to run unsteadily, with increased noise and vibration, thereby increasing the risk of elevator operation and possibly causing physical harm or psychological fear to passengers.

[0005] However, in actual use, it still has many shortcomings. For example, most existing systems lack the ability to monitor the electrical data of the elevator operation in real time, cannot continuously and dynamically monitor the power supply status of the elevator, and cannot monitor the elevator operation in real time, resulting in the elevator operation abnormality cannot be discovered in time, and the elevator operation risk cannot be effectively reduced. Summary of the invention

[0006] In order to overcome the above defects of the prior art, the present invention provides an elevator management system based on elevator operation electrical data to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: an elevator management system based on elevator operation electrical data, comprising:

[0008] The elevator energy consumption data acquisition module is used to collect the operation data of the elevator, and the operation data includes: actual energy consumption value, elevator load, elevator operation time, elevator operation speed and elevator operation audio; by installing energy consumption monitoring equipment in the elevator system, the actual energy consumption value E is recorded. actu Time series data of

[0009] The area division module divides the elevator operation scenarios into standby, no-load operation, and loaded operation based on the elevator load and operation speed; divides the elevator operation data into several time periods based on the operation scenarios, and marks the elevator operation scenarios;

[0010] The standby energy consumption analysis submodule is used to output the theoretical value of the elevator standby energy consumption; the product of the elevator's standby time and the preset standby energy consumption per unit time represents the theoretical value of the elevator standby energy consumption E aeo ;

[0011] An operation energy consumption analysis submodule is used to output a theoretical value of elevator operation energy consumption; the method for obtaining the theoretical value of elevator operation energy consumption is: building an elevator operation energy consumption analysis model based on linear regression or recurrent neural network, inputting operation data into the elevator operation energy consumption analysis model, outputting the theoretical value of elevator operation energy consumption, and using the average value of the error between the theoretical value of elevator operation energy consumption and the actual energy consumption value as the loss function for training until the loss function meets the preset requirements;

[0012] The elevator energy consumption abnormality management module takes measures based on the difference between the elevator energy consumption theoretical value and the actual energy consumption value. The elevator energy consumption theoretical value includes the elevator standby energy consumption theoretical value and the elevator operation energy consumption theoretical value.

[0013] If the theoretical value of the elevator energy consumption is greater than the actual value, it indicates that there is an abnormality in the data collection and analysis, and a first-level warning message is generated; based on the first-level warning message, the data collection and analysis process of the elevator involved is self-checked;

[0014] If the theoretical value of the elevator energy consumption is not greater than the actual energy consumption value, the elevator energy consumption abnormality index YE is calculated based on the difference between the theoretical value and the actual energy consumption value; if the elevator energy consumption abnormality index exceeds the threshold, it indicates that the elevator operation resistance increases, and a secondary warning information is generated. The secondary warning information includes the time when the abnormality occurred, the elevator involved, and the difference between the elevator energy consumption abnormality index YE and the threshold; based on the secondary warning information, check the mechanical components and electrical systems involved in the elevator to find energy waste nodes; construct an elevator power network topology diagram, set energy consumption nodes based on energy consumption equipment, and find energy waste nodes through monitoring and analysis of energy consumption nodes.

[0015] Preferably, the method for obtaining the theoretical value of the elevator standby energy consumption is:

[0016] In the scenario where the elevator is qualified for maintenance, a measurement cycle is set, and the energy consumption data of the elevator is continuously recorded during the measurement cycle and sorted by time; the total standby energy consumption value is divided by the total standby time to obtain the average standby energy consumption per unit time, which is recorded as the preset standby energy consumption per unit time; the product of the elevator standby time and the preset standby energy consumption per unit time is used to represent the theoretical value of the elevator standby energy consumption E aeo .

[0017] Preferably, an elevator operation energy consumption analysis model is built based on a recurrent neural network, and gradient descent is used to update parameters to minimize the loss function, and the training is performed until the loss function meets the preset requirements to obtain a trained elevator operation energy consumption analysis model; and the weight coefficient of each operation characteristic parameter is obtained based on forward and backward propagation, including the following steps:

[0018] Step S11, data preprocessing: converting the elevator operation data into a sequence form;

[0019] Step S12, the recurrent neural network includes an input layer, a hidden layer and an output layer; the input layer is used to receive serialized elevator operation data; the hidden layer uses RNN units to capture the time dependency in the data; the output layer is used to output the theoretical value of elevator operation energy consumption;

[0020] Step S13, taking the average value of the error between the theoretical value and the actual value of the energy consumption of the elevator operation as the loss function;

[0021] Step S14, initialize the weights and biases of the recurrent neural network, process the input sequence through the recurrent neural network in the forward propagation, output the predicted value, that is, the theoretical value of the elevator operation energy consumption, and calculate the loss; in the reverse propagation, calculate the gradient through the time backpropagation algorithm, and update the weights and biases of the recurrent neural network, repeat the forward propagation and reverse propagation steps until the loss function value meets the preset requirements.

[0022] Preferably, an elevator operation energy consumption analysis model is built based on linear regression, the load, operation time and energy conversion efficiency of each time period are input into the elevator operation energy consumption analysis model, and the theoretical value of the elevator operation energy consumption of each time period is output; the elevator operation energy consumption analysis model of the elevator satisfies the following formula,

[0023]

[0024] Among them, E theo Represents the theoretical value of elevator operation energy consumption, W L Represents the work done by the elevator in joules. The theoretical work done by the elevator is calculated based on the load, work duration, and operating altitude. η t Indicates the total energy conversion efficiency, which is expressed by the product of the motor energy conversion efficiency and the transmission efficiency; It represents the influence factor of elevator friction resistance on energy consumption, represents the influence factor of wind resistance on energy consumption, represents an empirical constant.

[0025] Preferably, in the elevator energy consumption abnormality management module, if the theoretical energy consumption value of the elevator is greater than the actual energy consumption value, it indicates that there is an abnormality in the data collection and analysis, and a first-level warning information is generated; the first-level warning information at least includes the time when the abnormality occurred, the elevator involved, and the difference between the theoretical energy consumption value and the actual energy consumption value of the elevator; based on the first-level warning information, the data collection and analysis process of the elevator involved is self-checked.

[0026] Preferably, in the elevator energy consumption abnormality management module, the operation data of the elevator is divided into n time periods, and i is used to represent the sequential number of the time period;

[0027] The theoretical energy consumption value of the elevator in the i-th time period is recorded as Eti, and the actual energy consumption value in the i-th time period is recorded as Eai; the elevator energy consumption abnormality index YE is calculated based on the difference between the theoretical energy consumption value and the actual energy consumption value;

[0028] The abnormal energy consumption index of the elevator exceeds the threshold, indicating that the elevator running resistance increases, and a secondary warning information is generated. The secondary warning information includes the time when the abnormality occurs, the elevator involved, and the difference between the abnormal energy consumption index YE and the threshold;

[0029] Based on the secondary warning information, check the mechanical components and electrical systems involved in the elevator to find energy waste nodes.

[0030] Preferably, an elevator power network topology diagram is constructed, energy consumption nodes are set based on energy consumption equipment, energy waste nodes are found out through monitoring and analysis of energy consumption nodes, and optimization measures are formulated to reduce standby energy consumption.

[0031] Preferably, the elevator management system further includes:

[0032] The no-load audio data analysis module obtains the no-load audio anomaly index YA by analyzing the audio signal in the no-load scenario;

[0033] The load operation speed analysis module obtains the load operation reliability index YK by analyzing the speed information under the load scenario;

[0034] When the elevator energy consumption abnormality index, audio abnormality index or operation reliability index do not meet the corresponding requirements, the elevator operation is suspended; when the elevator energy consumption abnormality index, audio abnormality index and operation reliability index all meet the corresponding requirements, the operation risk coefficient is generated;

[0035] Operation risk assessment module: Based on the elevator energy consumption abnormality index, audio abnormality index and operation reliability index, the elevator operation risk coefficient is obtained, and auxiliary elevator management decision-making is performed based on the operation risk coefficient.

[0036] Preferably, the no-load audio anomaly index YA is obtained in the following manner:

[0037] An audio signal is obtained by screening the running data, and an audio signal is collected in an unloaded scenario, and is divided into R audio segments, and t is used to represent the sequential number of the audio segment;

[0038] Perform fast Fourier transform on the audio signal in the audio segment to obtain the corresponding spectrum; extract audio features from the spectrum, including at least specific frequency band energy, spectrum centroid, and spectrum broadening, and record the frequency band energy, spectrum centroid, and spectrum broadening obtained by actual measurement as Ea, Ca, and Wa, respectively;

[0039] Based on the extracted audio features, the audio anomaly index is calculated; the frequency band energy, spectrum centroid, and spectrum width preset by the elevator are recorded as Eb, Cb, and Wb respectively; through the formula , where w1, w2 and w3 are the weight coefficients of each feature.

[0040] Preferably, the load operation reliability index is obtained in the following manner:

[0041] Sample evenly in the load scenario, record the sampling points where the actual acceleration exceeds the maximum acceleration as abnormal, and calculate the frequency of abnormal acceleration;

[0042] The sampling points where the actual running speed exceeds the maximum running speed are recorded as abnormal, and the frequency of abnormal running speed is calculated;

[0043] The speed fluctuation curve should be smooth, calculate the running speed smoothness index, obtain the acceleration of each sampling point, and use the inverse of the standard deviation of the acceleration to express the running speed smoothness index;

[0044] Combined analysis of abnormal running speed frequency, abnormal acceleration frequency, running speed smoothing index, through the formula The load operation reliability index YK is calculated; wherein α and β are weight coefficients used to adjust the influence of abnormal operation speed frequency and abnormal acceleration frequency on YK. The specific values ​​of these two coefficients need to be determined according to the actual situation.

[0045] Technical effects and advantages of the present invention:

[0046] (1) The elevator management system based on elevator operation electrical data provided by the present invention divides the elevator operation data into several time periods based on the operation scenario and marks the elevator operation scenario; the product of the elevator standby time and the preset standby energy consumption per unit time represents the theoretical value of the elevator standby energy consumption E. aeo; Build an elevator operation energy consumption analysis model based on linear regression or recurrent neural network, input operation data into the elevator operation energy consumption analysis model, output the theoretical value of elevator operation energy consumption, and use the average error between the theoretical value and the actual value as the loss function to train until the loss function meets the preset requirements; based on the difference between the theoretical value and the actual value of the elevator energy consumption, take measures to solve the problem of insufficient timeliness of elevator operation management in the existing technology; predict the elevator energy consumption in real time and compare it with the actual energy consumption continuously to discover potential risks in advance.

[0047] (2) The elevator management system based on elevator operation electrical data provided by the present invention has a fixed-term maintenance for existing elevators, or a temporary maintenance when the elevator cannot operate, which leads to a poor user experience; by analyzing the audio signal in the no-load scenario, the no-load audio anomaly index YA is obtained; by analyzing the speed information in the load scenario, the load operation reliability index YK is obtained; when the elevator energy consumption anomaly index, audio anomaly index or operation reliability index does not meet the corresponding requirements, the elevator operation is suspended; when the elevator energy consumption anomaly index, audio anomaly index and operation reliability index all meet the corresponding requirements, an operation risk coefficient is generated; elevator monitoring resources are allocated based on the operation risk coefficient to solve the problem of waste of monitoring resources caused by fixed-frequency maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a structural block diagram of the elevator management system based on energy consumption analysis of the present invention.

[0049] Figure 2 This is a structural block diagram of the elevator management system based on operation risk assessment of the present invention. DETAILED DESCRIPTION

[0050] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0051] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0052] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.

[0053] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0054] Example 1, see Figure 1 The present invention provides a structural block diagram of an elevator management system based on energy consumption analysis. Figure 1 An elevator management system based on elevator operation electrical data is shown, comprising:

[0055] The elevator energy consumption data acquisition module is used to collect the operation data of the elevator, which includes: actual energy consumption value, elevator load, elevator operation time, elevator operation speed and elevator operation audio; by installing energy consumption monitoring equipment in the elevator system, it can ensure that the energy consumption in the standby state can be accurately recorded, and the actual energy consumption value E can be recorded. actu Time series data of

[0056] The area division module divides the elevator operation scenarios into standby, no-load operation, and loaded operation based on the elevator load and operation speed; divides the elevator operation data into several time periods based on the operation scenarios, and marks the elevator operation scenarios;

[0057] The standby energy consumption analysis submodule is used to output the theoretical value of the elevator standby energy consumption; the product of the elevator's standby time and the preset standby energy consumption per unit time represents the theoretical value of the elevator standby energy consumption E aeo ;

[0058] An operation energy consumption analysis submodule is used to output a theoretical value of elevator operation energy consumption; the method for obtaining the theoretical value of elevator operation energy consumption is: building an elevator operation energy consumption analysis model based on linear regression or recurrent neural network, inputting operation data into the elevator operation energy consumption analysis model, outputting the theoretical value of elevator operation energy consumption, and using the average value of the error between the theoretical value of elevator operation energy consumption and the actual energy consumption value as the loss function for training until the loss function meets the preset requirements;

[0059] The elevator energy consumption abnormality management module takes measures based on the difference between the elevator energy consumption theoretical value and the actual energy consumption value. The elevator energy consumption theoretical value includes the elevator standby energy consumption theoretical value and the elevator operation energy consumption theoretical value.

[0060] It needs to be further explained in the embodiment of the present invention that the method for obtaining the theoretical value of the elevator standby energy consumption is:

[0061] In the scenario where the elevator is qualified for maintenance, the measurement cycle is set to one week, and a reasonable time period is selected, such as one week or one month, to capture the changes in standby energy consumption in different time periods; during the measurement period, the energy consumption data of the elevator is continuously recorded, including information on whether it is in standby state; the energy consumption data in the non-standby state is eliminated, the energy consumption data in the standby scenario is obtained, and sorted by time; the total standby energy consumption value is divided by the total standby time to obtain the average standby energy consumption per unit time, which is recorded as the preset standby energy consumption per unit time; the product of the elevator's standby time and the preset standby energy consumption per unit time is used to represent the theoretical value of the elevator's standby energy consumption E aeo .

[0062] It is necessary to further explain in the embodiment of the present invention that an elevator operation energy consumption analysis model is built based on a recurrent neural network, and parameters are updated using gradient descent or other optimization algorithms (such as Adam) to minimize the loss function, and the training is performed until the loss function meets the preset requirements to obtain a trained elevator operation energy consumption analysis model; and the weight coefficient of each operation characteristic parameter is obtained based on forward and backward propagation, including the following steps:

[0063] Step S11, data preprocessing: converting the elevator operation data (such as load, operation time, operation distance, etc.) into a sequence form;

[0064] Step S12, the recurrent neural network includes an input layer, a hidden layer and an output layer; the input layer is used to receive serialized elevator operation data; the hidden layer uses RNN units (such as LSTM or GRU) to capture the time dependency in the data; the output layer is used to output the theoretical value of elevator operation energy consumption;

[0065] Step S13, taking the average value of the error between the theoretical value and the actual value of the energy consumption of the elevator operation as the loss function;

[0066] Step S14, initialize the weights and biases of the recurrent neural network, process the input sequence through the recurrent neural network in the forward propagation, output the predicted value, that is, the theoretical value of the elevator operation energy consumption, and calculate the loss; in the reverse propagation, calculate the gradient through the time backpropagation algorithm, and update the weights and biases of the recurrent neural network, repeat the forward propagation and reverse propagation steps until the loss function value meets the preset requirements.

[0067] Explanation: In a recurrent neural network, the weight coefficients are distributed in the internal parameters of each RNN unit, including the weights and biases of the forget gate, input gate, output gate, and the weight of the unit state. The weights are automatically adjusted through the training process without the need to manually list specific formulas.

[0068] In a possible embodiment, the load, running time, and energy conversion efficiency of each time period are input into an elevator operation energy consumption analysis model, and a theoretical value of the elevator operation energy consumption of each time period is output; the elevator operation energy consumption analysis model of the elevator satisfies the following formula,

[0069]

[0070] Among them, E theo Represents the theoretical value of elevator operation energy consumption, W L Represents the work done by the elevator in joules. The theoretical work done by the elevator is calculated based on the load, work duration, and operating altitude. η t Indicates the total energy conversion efficiency, which is expressed by the product of the motor energy conversion efficiency and the transmission efficiency; It represents the influence factor of elevator friction resistance on energy consumption, represents the influence factor of wind resistance on energy consumption, represents an empirical constant.

[0071] It is necessary to further explain in the embodiment of the present invention that the theoretical value of the energy consumption of the elevator is not greater than the actual energy consumption value. If the theoretical value of the energy consumption of the elevator is greater than the actual energy consumption value, it indicates that there is an abnormality in the data collection and analysis, and a first-level warning information is generated; based on the first-level warning information, the data collection and analysis process of the elevator involved is self-checked; the first-level warning information at least includes the time when the abnormality occurs, the elevator involved, and the difference between the theoretical value of the energy consumption of the elevator and the actual energy consumption value;

[0072] The self-test process includes:

[0073] Check the data source: First, confirm whether the data collection equipment (such as sensors, meters, etc.) is working properly and whether the data is complete and correct;

[0074] Data transmission check: Check whether there is packet loss, delay or error during data transmission to ensure the integrity and accuracy of data during transmission;

[0075] Data processing logic: Review the logic of data processing and analysis to confirm whether there are programming errors, algorithm defects or improper configuration issues;

[0076] Data comparison: Compare current data with historical data to check for abnormal fluctuations or inconsistencies and identify potential sources of problems;

[0077] Based on the self-test results, targeted processing is performed on the problems found; for example, replacing faulty equipment, fixing data transmission problems, and adjusting data processing algorithms.

[0078] It is necessary to further explain in the embodiment of the present invention that, in the elevator energy consumption abnormality management module, the operation data of the elevator is divided into n time periods, i is used to represent the sequential number of the time periods; the theoretical energy consumption value of the elevator in the i-th time period is recorded as Eti, and the actual energy consumption value of the i-th time period is recorded as Eai;

[0079] The embodiment of the present invention does not make any specific limitation on the calculation formula of the elevator energy consumption abnormality index YE. It is sufficient to obtain the elevator energy consumption abnormality index based on the energy consumption difference. For example, by formula The elevator energy consumption abnormality index YE is calculated, where Zt represents the total operation time of the elevator and Dt represents the standby time of the elevator;

[0080] Alternatively, considering the different weights of standby energy consumption and running energy consumption, Zt_i represents the elevator running time in the i-th time period, and Dt_i represents the elevator standby time in the i-th time period. The abnormal index of elevator energy consumption is calculated, where f1 is used to adjust the weight of standby energy consumption in the overall energy consumption assessment; standby energy consumption refers to the electric energy consumed by the elevator in a non-operating state (such as waiting for passengers, doors remaining open, etc.). By adjusting the f1 coefficient, the impact of standby energy consumption on the overall energy consumption can be considered more flexibly; f2 is the normalization factor. Due to differences in the models, specifications, operating environments and other factors of different elevators, their energy consumption levels will also be different; in order to be able to compare and evaluate different elevators, their energy consumption data need to be converted to the same standard or scale, which is the purpose of normalization processing; the normalization factor can be adjusted according to actual conditions to ensure the accuracy and fairness of energy consumption assessment;

[0081] The abnormal energy consumption index of the elevator exceeds the threshold, indicating that the running resistance of the elevator increases, and a secondary warning information is generated. The secondary warning information includes the time when the abnormality occurred, the elevator involved, and the difference between the abnormal energy consumption index YE and the threshold. Based on the secondary warning information, the mechanical components and electrical systems involved in the elevator are checked to find energy waste nodes.

[0082] In a possible embodiment, an elevator power network topology is constructed, energy consumption nodes are set based on energy consumption equipment, energy consumption nodes are monitored and analyzed, energy waste nodes are found, and optimization measures are formulated to reduce standby energy consumption, including:

[0083] Based on the power supply network of the elevator system, a detailed power network topology diagram is constructed, which includes various energy-consuming devices (such as motors, controllers, lighting, etc.) as energy-consuming nodes;

[0084] Energy consumption node monitoring and analysis: Use smart sensors and data analysis technology to monitor the energy consumption of each energy consumption node in real time, and identify energy-wasting nodes by comparing historical average levels or preset values;

[0085] Find and optimize energy-wasting nodes: Conduct detailed inspection and analysis on energy-wasting nodes to determine the causes of high energy consumption (such as equipment aging, improper configuration, low operating efficiency, etc.). Based on the analysis results, formulate corresponding optimization measures, such as replacing high-efficiency equipment, adjusting equipment configuration, optimizing operation strategies, etc., to reduce standby energy consumption and operating energy consumption.

[0086] In summary, elevators rely on electricity to operate. Abnormal energy consumption may mean that there is a problem with the power control system. Abnormal elevator energy consumption often reflects that the mechanical parts of the elevator may be worn, aged or faulty. Power failures will not only cause the elevator to suddenly stop running or fail to start normally, but may also cause serious accidents such as electrical fires. These problems may cause the elevator to run unsteadily, increase noise and vibration, and thus increase the risk of elevator operation, which may cause physical harm or psychological fear to passengers. Taking measures based on the difference between the theoretical value and the actual energy consumption value of the elevator operation will help reduce the risk of elevator operation caused by elevator energy consumption.

[0087] Example 2, see Figure 2 The structural block diagram of an elevator management system based on operation risk assessment is shown in FIG. 1 . The difference between this embodiment of the present invention and embodiment 1 is that the elevator management system further includes:

[0088] The no-load audio data analysis module obtains the no-load audio anomaly index YA by analyzing the audio signal in the no-load scenario;

[0089] The load operation speed analysis module obtains the load operation reliability index YK by analyzing the speed information under the load scenario;

[0090] When the elevator energy consumption abnormality index, audio abnormality index or operation reliability index does not meet the corresponding requirements, the elevator operation is suspended; that is, when the elevator energy consumption abnormality index and audio abnormality index YA exceed the corresponding threshold; or the operation reliability index YK is lower than the corresponding threshold, the elevator operation is immediately suspended and an alarm is issued to notify maintenance personnel to conduct inspection and repair; the thresholds of each index can be automatically adjusted according to historical data and real-time operation status to improve the accuracy and sensitivity of the assessment;

[0091] When the elevator energy consumption abnormality index, audio abnormality index and operation reliability index all meet the corresponding requirements, the operation risk coefficient is generated;

[0092] Operation risk assessment module: Based on the elevator energy consumption abnormality index, audio abnormality index and operation reliability index, the operation risk coefficient of the elevator is obtained, and elevator management auxiliary decision-making is performed based on the operation risk coefficient; different management auxiliary decision-making suggestions are provided according to the level of the operation risk coefficient; for example, for low-risk elevators, regular inspections are recommended; for medium-risk elevators, enhanced monitoring and preparation of necessary maintenance spare parts are recommended; for high-risk elevators, it is strongly recommended to immediately shut down the elevator for inspection and repair of potential faults.

[0093] In a possible embodiment, weight coefficients are set for the elevator energy consumption abnormality index, the audio abnormality index, and the operation reliability index, and the elevator operation risk coefficient is obtained by weighted sum calculation;

[0094] Taking measures based on the elevator operation risk coefficient, allocating monitoring resources or allocating the proportion of standby time; the monitoring resources include the frequency of elevator maintenance and the frequency of elevator operation data collection;

[0095] The elevator maintenance module is used to inspect the effectiveness of the elevator electrical circuit, drive components, elevator shaft, and safety devices to find out the cause of the elevator failure;

[0096] The fault map building module establishes a knowledge map of elevator fault causes and operating characteristic parameters.

[0097] The embodiment of the present invention does not specifically limit the value of the operation risk factor YF. For example,

[0098] Obtain the elevator energy consumption abnormality index, audio abnormality index and operation reliability index to set weight coefficients, which are recorded as wa, wb and wc respectively;

[0099] Get the thresholds of the elevator energy consumption abnormality index, audio abnormality index and operation reliability index, which are recorded as Tha, Thb and Thc respectively; The operation risk factor YF is calculated.

[0100] It needs to be further explained in the embodiment of the present invention that the method for obtaining the no-load audio anomaly index YA is:

[0101] An audio signal is obtained by screening the running data, and an audio signal is collected in an unloaded scenario, and is divided into R audio segments, and t is used to represent the sequential number of the audio segment;

[0102] Perform fast Fourier transform on the audio signal in the audio segment to obtain the corresponding spectrum; extract audio features from the spectrum, including at least specific frequency band energy, spectrum centroid, and spectrum broadening, and record the frequency band energy, spectrum centroid, and spectrum broadening obtained by actual measurement as Ea, Ca, and Wa, respectively;

[0103] Based on the extracted audio features, the audio anomaly index is calculated; in the further design, the frequency band energy, spectrum centroid, and spectrum broadening preset by the elevator are recorded as Eb, Cb, and Wb respectively; through the formula , where w1, w2 and w3 are the weight coefficients of each feature.

[0104] It needs to be further explained in the embodiment of the present invention that the load operation reliability index is obtained in the following manner:

[0105] Sample evenly in the load scenario, record the sampling points where the actual acceleration exceeds the maximum acceleration as abnormal, and calculate the frequency of abnormal acceleration;

[0106] The sampling points where the actual running speed exceeds the maximum running speed are recorded as abnormal, and the frequency of abnormal running speed is calculated;

[0107] The speed fluctuation curve should be smooth, calculate the running speed smoothness index, obtain the acceleration of each sampling point, and use the inverse of the standard deviation of the acceleration to express the running speed smoothness index;

[0108] Combined analysis of abnormal running speed frequency, abnormal acceleration frequency, running speed smoothing index, through the formula The load operation reliability index YK is calculated; where α and β are weight coefficients, which are used to adjust the influence of abnormal operation speed frequency and abnormal acceleration frequency on YK. The specific values ​​of these two coefficients need to be determined according to the actual situation, such as through expert scoring, historical data analysis or experimental testing.

[0109] The load operation reliability index YK reflects the stability and reliability of the elevator during operation, and is closely related to the user's experience satisfaction; abnormal operating speed frequency Fv: indicates the number of times the elevator operating speed is abnormal within a period of time; abnormal acceleration frequency Fa: indicates the number of times the elevator acceleration is abnormal within the same period of time; operating speed smoothness index Sv: an indicator to measure the fluctuation of the operating speed. Generally, the larger the value, the smoother the speed, that is, the better the stability.

[0110] Summary: It is very necessary to quantitatively evaluate the operation risk of elevators based on abnormal elevator energy consumption; this helps to promptly discover and eliminate potential safety hazards, improve the efficiency and effectiveness of elevator management, and provide passengers with a safer and more comfortable elevator riding environment; the embodiments of the present invention can provide a basis for scientific decision-making for relevant management departments by quantitatively evaluating the operation risks under abnormal elevator energy consumption conditions; it helps to formulate reasonable maintenance plans, renovation plans, and emergency plans, etc., to improve management efficiency: quantitative evaluation helps to identify key problems and weak links in elevator operation, so as to take targeted measures to improve them, significantly improve the efficiency and effectiveness of elevator management, and reduce elevator operation risks; the ultimate goal is to ensure the safety of passengers when using elevators; by quantitatively evaluating the operation risks under abnormal elevator energy consumption conditions, potential safety hazards can be discovered and eliminated in a timely manner, providing passengers with a safer and more comfortable elevator riding environment.

[0111] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An elevator management system based on elevator operation electrical data, characterized in that: include: The elevator energy consumption data acquisition module is used to collect the operation data of the elevator, and the operation data includes: actual energy consumption value, elevator load, elevator operation time, elevator operation speed and elevator operation audio; by installing energy consumption monitoring equipment in the elevator system, the actual energy consumption value E is recorded. actu Time series data of The area division module divides the elevator operation scenarios into standby, no-load operation, and loaded operation based on the elevator load and operation speed; divides the elevator operation data into several time periods based on the operation scenarios, and marks the elevator operation scenarios; The standby energy consumption analysis submodule is used to output the theoretical value of the elevator standby energy consumption; the product of the elevator's standby time and the preset standby energy consumption per unit time represents the theoretical value of the elevator standby energy consumption E aeo ; An operation energy consumption analysis submodule is used to output a theoretical value of elevator operation energy consumption; the method for obtaining the theoretical value of elevator operation energy consumption is: building an elevator operation energy consumption analysis model based on linear regression or recurrent neural network, inputting operation data into the elevator operation energy consumption analysis model, outputting the theoretical value of elevator operation energy consumption, and using the average value of the error between the theoretical value of elevator operation energy consumption and the actual energy consumption value as the loss function for training until the loss function meets the preset requirements; The elevator energy consumption abnormality management module takes measures based on the difference between the elevator energy consumption theoretical value and the actual energy consumption value. The elevator energy consumption theoretical value includes the elevator standby energy consumption theoretical value and the elevator operation energy consumption theoretical value. If the theoretical value of the elevator energy consumption is greater than the actual value, it indicates that there is an abnormality in the data collection and analysis, and a first-level warning message is generated; based on the first-level warning message, the data collection and analysis process of the elevator involved is self-checked; If the theoretical value of the elevator energy consumption is not greater than the actual energy consumption value, the elevator energy consumption abnormality index YE is calculated based on the difference between the theoretical value and the actual energy consumption value; if the elevator energy consumption abnormality index exceeds the threshold, it indicates that the elevator operation resistance increases, and a secondary warning information is generated. The secondary warning information includes the time when the abnormality occurred, the elevator involved, and the difference between the elevator energy consumption abnormality index YE and the threshold; based on the secondary warning information, check the mechanical components and electrical systems involved in the elevator to find energy waste nodes; construct an elevator power network topology diagram, set energy consumption nodes based on energy consumption equipment, and find energy waste nodes through monitoring and analysis of energy consumption nodes.

2. An elevator management system based on elevator operation electrical data according to claim 1, characterized in that: The method for obtaining the theoretical value of the elevator standby energy consumption is as follows: In the scenario where the elevator is qualified for maintenance, a measurement cycle is set to continuously record the energy consumption data of the elevator during the measurement cycle and sort it by time; the total standby energy consumption value is divided by the total standby time to obtain the average standby energy consumption per unit time, which is recorded as the preset standby energy consumption per unit time; The theoretical value of the elevator standby energy consumption E is expressed by multiplying the elevator standby time by the preset standby energy consumption per unit time. aeo .

3. The elevator management system based on elevator operation electrical data according to claim 1, characterized in that: An elevator operation energy consumption analysis model is built based on a recurrent neural network, and the parameters are updated using gradient descent. The training is performed until the loss function meets the preset requirements to obtain a trained elevator operation energy consumption analysis model. The weight coefficient of each operation characteristic parameter is obtained based on forward and backward propagation, including the following steps: Step S11, data preprocessing: converting the elevator operation data into a sequence form; Step S12, the recurrent neural network includes an input layer, a hidden layer and an output layer; the input layer is used to receive serialized elevator operation data; the hidden layer uses RNN units to capture the time dependency in the data; the output layer is used to output the theoretical value of elevator operation energy consumption; Step S13, taking the average value of the error between the theoretical value and the actual value of the energy consumption of the elevator operation as the loss function; Step S14, initialize the weights and biases of the recurrent neural network, process the input sequence through the recurrent neural network in the forward propagation, output the predicted value, that is, the theoretical value of the elevator operation energy consumption, and calculate the loss; in the reverse propagation, calculate the gradient through the time backpropagation algorithm, and update the weights and biases of the recurrent neural network, repeat the forward propagation and reverse propagation steps until the loss function value meets the preset requirements.

4. The elevator management system based on elevator operation electrical data according to claim 1, characterized in that: An elevator operation energy consumption analysis model is built based on linear regression, and the load, operation time, and energy conversion efficiency of each time period are input into the elevator operation energy consumption analysis model, and the theoretical value of the elevator operation energy consumption of each time period is output; the elevator operation energy consumption analysis model of the elevator satisfies the following formula, Among them, E theo Represents the theoretical value of elevator operation energy consumption, W L Represents the work done by the elevator in joules. The theoretical work done by the elevator is calculated based on the load, work duration, and operating altitude. η t Indicates the total energy conversion efficiency, which is expressed by the product of the motor energy conversion efficiency and the transmission efficiency; It represents the influence factor of elevator friction resistance on energy consumption, represents the influence factor of wind resistance on energy consumption, represents an empirical constant.

5. The elevator management system based on elevator operation electrical data according to claim 1, characterized in that: In the elevator energy consumption abnormality management module, if the theoretical value of the elevator energy consumption is greater than the actual energy consumption value, it indicates that there is an abnormality in data collection and analysis, and a first-level warning information is generated; the first-level warning information at least includes the time when the abnormality occurred, the elevator involved, and the difference between the theoretical value of the elevator energy consumption and the actual energy consumption value; Based on the first-level warning information, the elevators involved are self-checked during data collection and analysis.

6. The elevator management system based on elevator operation electrical data according to claim 1, characterized in that: In the elevator energy consumption abnormality management module, the elevator operation data is divided into n time periods, and i is used to represent the sequential number of the time period; The theoretical energy consumption value of the elevator in the i-th time period is recorded as Eti, and the actual energy consumption value in the i-th time period is recorded as Eai; The elevator energy consumption abnormality index YE is calculated based on the difference between the theoretical value and the actual energy consumption value of the elevator; The abnormal energy consumption index of the elevator exceeds the threshold, indicating that the elevator running resistance increases, and a secondary warning information is generated. The secondary warning information includes the time when the abnormality occurs, the elevator involved, and the difference between the abnormal energy consumption index YE and the threshold; Based on the secondary warning information, check the mechanical components and electrical systems involved in the elevator to find energy waste nodes.

7. An elevator management system based on elevator operation electrical data according to claim 6, characterized in that: Construct the elevator power network topology diagram, set energy consumption nodes based on energy-consuming equipment, identify energy-wasting nodes through monitoring and analysis of energy consumption nodes, and formulate optimization measures to reduce standby energy consumption.

8. An elevator management system based on elevator operation electrical data according to claim 6, characterized in that: The elevator management system further comprises: The no-load audio data analysis module obtains the no-load audio anomaly index YA by analyzing the audio signal in the no-load scenario; The load operation speed analysis module obtains the load operation reliability index YK by analyzing the speed information under the load scenario; When the elevator energy consumption abnormality index, audio abnormality index or operation reliability index do not meet the corresponding requirements, the elevator operation is suspended; when the elevator energy consumption abnormality index, audio abnormality index and operation reliability index all meet the corresponding requirements, the operation risk coefficient is generated; Operation risk assessment module: Based on the elevator energy consumption abnormality index, audio abnormality index and operation reliability index, the elevator operation risk coefficient is obtained, and auxiliary elevator management decision-making is performed based on the operation risk coefficient.

9. An elevator management system based on elevator operation electrical data according to claim 8, characterized in that: The method for obtaining the no-load audio anomaly index YA is as follows: An audio signal is obtained by screening the running data, and an audio signal is collected in an unloaded scenario, and is divided into R audio segments, and t is used to represent the sequential number of the audio segment; Perform fast Fourier transform on the audio signal in the audio segment to obtain the corresponding spectrum; extract audio features from the spectrum, and measure the actual frequency band energy, spectrum centroid, and spectrum broadening, which are recorded as Ea, Ca, and Wa respectively; Based on the extracted audio features, the audio anomaly index is calculated; the frequency band energy, spectrum centroid, and spectrum width preset by the elevator are recorded as Eb, Cb, and Wb respectively; through the formula , where w1, w2 and w3 are the weight coefficients of each feature.

10. An elevator management system based on elevator operation electrical data according to claim 8, characterized in that: The load operation reliability index is obtained as follows: Sample evenly under the load scenario, record the sampling points where the actual acceleration exceeds the maximum acceleration as abnormal, and calculate the abnormal acceleration frequency Fa; The sampling points where the actual running speed exceeds the maximum running speed are recorded as abnormal, and the abnormal running speed frequency Fv is calculated; Calculate the running speed smoothness index, obtain the acceleration of each sampling point, and use the inverse of the standard deviation of the acceleration to represent the running speed smoothness index Sv; Combined analysis of abnormal running speed frequency, abnormal acceleration frequency, running speed smoothing index, through the formula The load operation reliability index YK is calculated; wherein α and β are weight coefficients, which are used to adjust the influence of abnormal operation speed frequency and abnormal acceleration frequency on YK and are determined according to the actual situation.