An elevator operation state prediction model updating method, device and prediction system

Abstract

The application provides an elevator operation state prediction model updating method and device and a prediction system. The updating method comprises the following steps: obtaining a target operation parameter group of a target elevator in a preset first monitoring time length; performing data alignment on the parameters in the target operation parameter group to obtain a monitoring data set of the target elevator; predicting a current data update quantization index according to the monitoring data set; determining whether the current data update quantization index belongs to a preset first threshold range; if not, no updating is performed; if yes, performing a parameter aggregation operation on the elevator operation state prediction model parameters according to the corresponding elevator operation state prediction model parameters of the target elevator to obtain a first result, feeding back the first result to the target elevator, and updating the corresponding elevator operation state prediction model. Thus, the necessity of each updating operation is quantitatively evaluated, the elevator operation state model is accurately updated, and the efficiency of the elevator operation state prediction model updating is improved.

Description

Technical Field

[0001] This invention relates to the field of elevator operation status prediction technology, and in particular to a method, apparatus and prediction system for updating an elevator operation status prediction model. Background Technology

[0002] Patent application CN117611135A discloses a visualized equipment operation and maintenance management method and system. Specifically, it discloses: using a neural network game theory model to collect multi-source heterogeneous data from equipment and the environment, and using federated learning technology for data processing while protecting data privacy; using the RELATION NET algorithm based on graph neural networks to establish a dynamic digital twin of the entire lifecycle of equipment operation, achieving near real-time mapping of multi-dimensional equipment states; training a strategy model for equipment anomaly detection and fault prediction based on the PPO algorithm of reinforcement learning, and using a resilient analysis engine to monitor model performance and security; and using a model logic expert network based on reinforcement transfer learning to achieve online adaptation and upgrades of the model. This application, through the collection and deep cross-domain analysis of multi-source heterogeneous data from the power system, achieves near real-time, high-fidelity mapping of equipment states, providing a foundation for equipment health assessment and condition prediction.

[0003] Understandably, the aforementioned technical solutions can be used for elevator equipment in smart industrial parks or smart residential communities to achieve health assessments and condition predictions. This helps improve the stability of daily elevator operation and reduces labor costs for elevator maintenance. However, as the equipment continues to operate, the prediction results of the elevator operation status prediction system become less accurate in predicting the elevator's condition, leading to a decrease in the system's reliability.

[0004] Therefore, there is an urgent need for an update method for the elevator operation status prediction model to solve the above problems, and thus obtain a reliable elevator operation status prediction system. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method, device and prediction system for updating an elevator operation status prediction model, which can improve the reliability of the elevator operation status prediction system by efficiently executing the update operation of the prediction model.

[0006] To this end, the present invention provides a method for updating an elevator operation status prediction model, comprising:

[0007] S101. Obtain the target elevator's target operating parameter set during the preset first monitoring period;

[0008] S102. Align the parameters in the target operating parameter group to obtain the monitoring dataset of the target elevator; the monitoring dataset includes the target operating parameters of the target elevator during a preset first monitoring period and the label information corresponding to the target operating parameters that represents the predicted operating status of the target elevator;

[0009] S103. Predict the current data update quantification index based on the monitoring dataset;

[0010] S104. Determine whether the current data update quantization index is within the preset first threshold range. If not, do not update; if yes, proceed to step S105.

[0011] S105. Then, based on the elevator operation state prediction model parameters corresponding to the target elevator, perform parameter aggregation operation on the elevator operation state prediction model parameters to obtain the first result.

[0012] S106. Feed the first result back to the target elevator and update the corresponding elevator operation status prediction model.

[0013] The elevator operation status prediction model update method disclosed in this invention predicts the current data update quantification index based on the monitoring dataset, and then determines whether to perform the elevator operation status prediction model update operation based on whether the current data update quantification index falls within the first threshold range. This method is beneficial for quantifying the necessity of performing the update operation, accurately updating the elevator operation status model, improving the efficiency of the elevator operation status prediction model update, and thus enhancing the efficiency of the elevator operation status prediction system.

[0014] Furthermore, the label information of the predicted operating state of the target elevator includes one of the following: a first label information indicating that the elevator state prediction model predicts that the target elevator is in a first calibrated operating state; a second label information indicating that the elevator state prediction model predicts that the target elevator is in a second calibrated operating state; and a third label information indicating that the elevator state prediction model predicts that the target elevator is in an uncalibrated operating state. The uncalibrated operating state means that the elevator state prediction model predicts that the target elevator is in an operating state other than the first calibrated operating state and the second calibrated operating state.

[0015] Furthermore, the quantitative index for predicting current data updates based on the monitoring dataset specifically includes:

[0016] Calculate the evaluation index based on the target operating parameters;

[0017] The evaluation index C is calculated using the following formula:

[0018]

[0019] Where k is the total number of target operating parameters, C i Let C be the evaluation index component of the i-th target operating parameter; where C i The calculation formula is as follows:

[0020]

[0021] M represents the sample number of the i-th target operating parameter within the preset monitoring duration, K represents the total number of samples of the i-th target operating parameter within the preset monitoring duration, and N... M N represents the parameter value corresponding to the Mth sample of the i-th target operating parameter within the preset monitoring duration. max For N M The maximum value, N min For N M The minimum value, For N M The mean;

[0022] The feature index is calculated based on the evaluation index and the number of samples for each type of label information;

[0023] The formula for calculating the characteristic index l is as follows:

[0024]

[0025] Where C is the evaluation index, M1 represents the number of samples of the target elevator whose label information is the first label information during the preset monitoring period, M2 represents the number of samples of the target elevator whose label information is the second label information during the preset monitoring period, and M3 represents the number of samples of the target elevator whose label information is the third label information during the preset monitoring period.

[0026] Calculate the current updated quantification index based on the aforementioned characteristic index;

[0027] The formula for calculating the data update quantification index is as follows:

[0028]

[0029] Where l represents the feature index corresponding to the current data update quantization index, and e is the natural logarithm.

[0030] Furthermore, the target operating parameter set includes:

[0031] The target elevator's control box temperature, load capacity, wire rope cross-sectional area, elevator door opening and closing speed, car operating noise, and power supply voltage are one or more of the following:

[0032] Furthermore, the method for updating the elevator operation status prediction model also includes an update monitoring step, which specifically includes:

[0033] S201. Obtain the number of times the target elevator performs the update operation of the elevator operation status prediction model within the preset second monitoring time period;

[0034] S202. Determine whether the ratio between the number of executions and the preset second monitoring duration falls within the preset second threshold range. If yes, proceed to step S203a; otherwise, proceed to step S203b.

[0035] S203a. Output data indicating an abnormal situation when the target elevator performs the update operation of the elevator operation status prediction model;

[0036] S203b: Output data indicating that the target elevator performed the elevator operation status prediction model update operation without any anomalies.

[0037] On the other hand, the present invention also provides an update device for an elevator operation status prediction model, comprising:

[0038] The parameter acquisition module is used to acquire the target elevator's target operating parameter set during the preset first monitoring period;

[0039] Data preprocessing module: used to align the parameters in the target operating parameter group to obtain the monitoring dataset of the target elevator; the monitoring dataset includes the target operating parameters of the target elevator during a preset first monitoring period and the label information corresponding to the target operating parameters representing the predicted operating status of the target elevator;

[0040] Data Update Quantitative Index Calculation Module: Used to predict the current data update quantitative index based on the monitored dataset;

[0041] The first determination module is used to determine whether the current data update quantization index falls within the preset first threshold range. If not, no update is performed; if so, the federated aggregation module is executed.

[0042] Federated aggregation module: used to perform parameter aggregation operation on the elevator operation state prediction model parameters corresponding to the target elevator to obtain a first result;

[0043] Model update module: Feeds back the first result to the target elevator and updates the corresponding elevator operation status prediction model; otherwise, no update is performed.

[0044] Furthermore, the data update quantification index calculation module includes:

[0045] Evaluation index calculation submodule: used to calculate the evaluation index based on the target operating parameters;

[0046] The evaluation index C is calculated using the following formula:

[0047]

[0048] Where k is the total number of target operating parameters, C i Let C be the evaluation index component of the i-th target operating parameter; where C i The calculation formula is as follows:

[0049]

[0050] M represents the sample number of the i-th target operating parameter within the preset monitoring duration, K represents the total number of samples of the i-th target operating parameter within the preset monitoring duration, and N... M N represents the parameter value corresponding to the Mth sample of the i-th target operating parameter within the preset monitoring duration. max For N M The maximum value, N min For N M The minimum value, For N M The mean;

[0051] Feature index calculation submodule: used to calculate the feature index based on the evaluation index and the number of samples for each type of label information;

[0052] The formula for calculating the characteristic index l is as follows:

[0053]

[0054] Where C is the evaluation index, M1 represents the number of samples of the target elevator whose label information is the first label information during the preset monitoring period, M2 represents the number of samples of the target elevator whose label information is the second label information during the preset monitoring period, and M3 represents the number of samples of the target elevator whose label information is the third label information during the preset monitoring period.

[0055] Update Quantitative Index Calculation Submodule: Used to calculate the current updated quantitative index based on the feature index;

[0056] The formula for calculating the data update quantification index is as follows:

[0057]

[0058] Where l represents the feature index corresponding to the current data update quantization index, and e is the natural logarithm.

[0059] Furthermore, it also includes updating the monitoring unit, which includes:

[0060] The execution count module is used to obtain the number of times the target elevator performs the update operation of the elevator operation status prediction model within a preset second monitoring period;

[0061] The second determination module is used to determine whether the ratio between the number of executions and the preset second monitoring duration falls within the preset second threshold range. If so, the step update abnormal output module is started; otherwise, the update normal output module is started.

[0062] The update exception output module is used to output data indicating that an abnormal situation occurred when the target elevator performed the update operation of the elevator operation status prediction model;

[0063] The update normal output module is used to output data indicating that the target elevator has performed an update operation on the elevator operation status prediction model without any abnormalities.

[0064] On the other hand, the present invention also provides an elevator operation status prediction system, characterized in that it includes:

[0065] Multiple elevators and elevator operation status prediction models corresponding to the multiple elevators, servers, and updating devices as described in any of the above;

[0066] The multiple elevators are connected to the server, and the updating device is also connected to the server.

[0067] In summary, this invention first predicts the current data update quantification index based on the monitoring dataset, and then determines whether to execute the elevator operation status prediction model update operation based on whether the current data update quantification index falls within the first threshold range. This facilitates a quantitative assessment of the necessity of executing the update operation, accurately updates the elevator operation status model, and improves the efficiency of the elevator operation status prediction model update, thereby enhancing the efficiency of the elevator operation status prediction system. Furthermore, by monitoring the frequency of the system's update operations, the operating status of the target elevator is monitored. While ensuring accurate detection, this further improves the system's response capability to abnormal situations, ensuring the accuracy and timeliness of the elevator operation status prediction system's detection of elevator operation status.

[0068] To better understand and implement this invention, the following detailed description is provided in conjunction with the accompanying drawings. Attached Figure Description

[0069] Figure 1 This is a flowchart of an exemplary elevator operation status prediction model update method provided by the present invention;

[0070] Figure 2 To execute Figure 1 A structural block diagram of the updating device for the updating method shown;

[0071] Figure 3 This is a flowchart of the update monitoring steps of an exemplary update method provided by the present invention;

[0072] Figure 4 To execute Figure 3 The diagram shows the structure of the update monitoring unit in the update monitoring steps. Detailed Implementation

[0073] This invention is based on an elevator operation status prediction system. This system utilizes federated learning technology to divide the elevators in smart industrial parks within a region into groups corresponding to each smart industrial park. For example, elevators in smart industrial park A are grouped into elevator group AZ, elevators in smart industrial park B are grouped into another group BZ, and elevators in smart industrial park C are grouped into yet another group CZ. A server can be set up in this region to communicate with elevator groups AZ, BZ, and CZ. Elevator groups AZ, BZ, and CZ can upload parameters of the elevator operation status prediction model to this server. The server then aggregates these parameters and distributes the updated prediction model parameters back to elevator groups AZ, BZ, and CZ. After receiving the updated prediction model parameters, elevator groups AZ, BZ, and CZ can update the parameters of the prediction model for a specific elevator as needed, thereby improving the accuracy of the elevator operation status prediction. Optionally, the method for updating the elevator operation status prediction model disclosed in this invention can be set within the aforementioned server. Alternatively, it can be a prediction system located outside the server, capable of communicating with the server and with the elevator group. Optionally, the elevator group can be a network composed of several elevators. Based on this network, the elevator group can conduct local area network communication internally, or it can achieve data interaction with external systems through communication connections.

[0074] At this point, the elevator operation status prediction system can predict the operating status of elevator equipment in smart industrial parks or smart communities. For example, when the prediction indicates that the elevator will enter an abnormal operating state, relevant maintenance personnel can inspect the elevator early and troubleshoot if necessary, which is beneficial to ensuring the safety of elevator users and improving the efficiency of daily operations in smart industrial parks or smart communities. Furthermore, the elevator operation status prediction system can interact with the elevator network of the smart industrial park or smart community to predict the operating status of each elevator within that network.

[0075] However, the aforementioned elevator operation status prediction system lacks the ability to update the elevator operation status prediction model. As elevator components age or operational misalignments occur, the original prediction model can no longer accurately predict the operation status of the target elevator, resulting in inaccurate assessments by the prediction system and affecting elevator maintenance and user safety.

[0076] Based on this, the present invention provides a method and apparatus for updating an elevator operation status prediction model, so as to update the elevator prediction model in the system periodically to ensure the accuracy of the elevator operation status prediction system. The present invention will be explained and illustrated through the following embodiments.

[0077] Example 1:

[0078] Please see Figure 1 and Figure 2 The updating device includes: a parameter acquisition module 101, a data preprocessing module 102, a data update quantization index calculation module 103, a first judgment module 104, a federated aggregation module 105, and a model updating module 106. The updating device is used to execute the updating method for the elevator operating state prediction model. The specific execution flow of each module of the elevator operating state prediction model updating device is as follows:

[0079] The parameter acquisition module 101 is used to execute step S101 and acquire the target operating parameter group of the target elevator during the preset first monitoring time.

[0080] Optionally, the target operating parameter set includes at least one of the following parameters: control box temperature of the target elevator, load capacity, wire rope cross-sectional area, elevator door opening and closing speed, car operating noise, and power supply voltage.

[0081] The target operating parameters can be any parameters related to the elevator status. This invention uses the main influencing items as monitoring parameters, but other monitoring items can also be added.

[0082] The data preprocessing module 102 is used to perform step S102, aligning the parameters in the target operating parameter group to obtain a monitoring dataset of the target elevator. The monitoring dataset includes the target operating parameters of the target elevator during a preset first monitoring period, and corresponding label information representing the predicted operating state of the target elevator. This label information is the predicted operating state of the target elevator obtained after processing by the elevator operating state prediction model using a sample of the target operating parameters as input.

[0083] An elevator operation status prediction model requires one or more elevator operation parameters to evaluate the elevator's operation status. By inputting the required data into the elevator operation status prediction model, the prediction results can be obtained. For example, in one sample of target elevator operating parameters, the control box temperature is T1, the load capacity is H1, the cross-sectional area of ​​the wire rope is S1, the door opening speed is D1, the car noise is Y1, and the power supply voltage is V1. After processing the above data, the elevator operating status prediction model predicts that the target elevator is operating normally. In another sample of target elevator operating parameters, the control box temperature is T2, the load capacity is H2, the cross-sectional area of ​​the wire rope is S2, the door opening speed is D2, the car noise is Y2, and the power supply voltage is V2. After processing the above data, the elevator operating status prediction model predicts that the target elevator is operating abnormally. In yet another sample of target elevator operating parameters, the control box temperature is T3, the load capacity is H3, the cross-sectional area of ​​the wire rope is S3, the door opening speed is D3, the car noise is Y3, and the power supply voltage is V3. After processing the above data, the elevator operating status prediction model predicts that the target elevator is in an uncalibrated operating state.

[0084] There are three possible predicted operating states for elevators: 1. Normal operation, 2. Abnormal operation, and 3. Unknown state.

[0085] The data update quantification index calculation module 103 is used to perform step S103 and predict the current data update quantification index based on the monitoring dataset.

[0086] The data update quantitative index calculation module 103 includes: evaluation index calculation submodule 103.1, feature index calculation submodule 103.2, and update quantitative index calculation submodule 103.3.

[0087] Among them, the evaluation index calculation submodule 103.1 is used to execute step S103.1: calculate the evaluation index based on the target operating parameters;

[0088] The calculation formula for the evaluation index is as follows:

[0089]

[0090] Where k is the total number of target operating parameters, C i Let C be the evaluation index component of the i-th target operating parameter; where C i The calculation formula is as follows:

[0091]

[0092] M represents the sample number of the i-th target operating parameter within the preset monitoring duration, K represents the total number of samples of the i-th target operating parameter within the preset monitoring duration, and N... M N represents the parameter value corresponding to the Mth sample of the i-th target operating parameter within the preset monitoring duration. max For N M The maximum value, N min For N M The minimum value, For N M The mean.

[0093] The feature index calculation submodule 103.2 is used to execute step S103.2: calculate the feature index based on the evaluation index and the number of samples for each type of label information;

[0094] The update quantization index calculation submodule 103.3 is used to execute step S103.3: calculate the current update quantization index based on the characteristic index;

[0095] The specific calculation formula for the data update quantification index is as follows:

[0096] The control module controls the data processing module to determine the current data update quantization index based on the data difference between the monitoring dataset and the preset first training dataset, using the following algorithm:

[0097]

[0098] Where l represents the feature index corresponding to the current data update quantization index, and e is the natural logarithm.

[0099] In one specific embodiment of this application, the formula for calculating the characteristic index l is as follows:

[0100]

[0101] C represents the evaluation index regarding the impact of target operating parameters on the characteristic index; M1 represents the number of samples where the label information of the target elevator corresponds to the first label information within the preset monitoring period; M2 represents the number of samples where the label information of the target elevator corresponds to the second label information within the preset monitoring period; and M3 represents the number of samples where the label information of the target elevator corresponds to the second label information within the preset monitoring period.

[0102] C = C t +C h +C s +C d +C y +C v

[0103] C t C represents the first sub-item of the evaluation index, indicating the impact of the control box temperature of the target elevator on the evaluation index. h C represents the second sub-item of the evaluation index, which indicates the impact of the target elevator's load capacity on the evaluation index. s The third sub-item of the evaluation index, C, represents the impact of the cross-sectional area of ​​the target elevator's wire rope on the evaluation index. d The fourth sub-item of the evaluation index, C, represents the impact of the elevator door opening and closing speed on the evaluation index. y The fifth sub-item of the evaluation index, C, represents the impact of the target elevator's car operating noise on the evaluation index. v The sixth sub-item of the evaluation index indicates the impact of the target elevator's power supply voltage on the overall evaluation index.

[0104]

[0105] t1 represents the sample number of the target elevator's control box temperature within the preset monitoring period, t2 represents the total number of samples of the target elevator's control box temperature within the preset monitoring period, and T t1 This represents the control box temperature value corresponding to the t1th sample of the target elevator's control box temperature within the preset monitoring period, where T is the control box temperature value. max for The maximum value, T min for The minimum value, For T t1 The mean,

[0106]

[0107] h1 represents the sample number of the target elevator's load capacity within the preset monitoring period, and h2 represents the total number of samples of the target elevator's load capacity within the preset monitoring period. H represents the load weight corresponding to the h1th sample of the target elevator's load weight within the preset monitoring period. max for The maximum value of H min for The minimum value, for The mean,

[0108]

[0109] s1 represents the sample number of the cross-sectional area of ​​the target elevator's wire rope during the preset monitoring period, s2 represents the total number of samples of the cross-sectional area of ​​the target elevator's wire rope during the preset monitoring period, and S s1S represents the cross-sectional area of ​​the steel wire rope corresponding to the s1th sample within the preset monitoring period. max for The maximum value, S min for The minimum value, for The mean,

[0110]

[0111] d1 represents the sample number of the target elevator's door opening and closing speed within the preset monitoring period, and d2 represents the total number of samples of the target elevator's door opening and closing speed within the preset monitoring period. This represents the elevator door opening and closing speed corresponding to the d1th sample of the target elevator's elevator door opening and closing speed within a preset monitoring period, where D is the elevator door opening and closing speed. max for The maximum value, D min for The minimum value, for The mean,

[0112]

[0113] y1 represents the sample number of the target elevator's car operating noise within the preset monitoring period, and y2 represents the total number of samples of the target elevator's car operating noise within the preset monitoring period. y1 Y represents the volume of the y1th sample of the target elevator's car operating noise during the preset monitoring period. max For Y y1 The maximum value of Y min For Y y1 The minimum value, For Y y1 The mean,

[0114]

[0115] v1 represents the sample number of the target elevator's power supply voltage during the preset monitoring period, and v2 represents the total number of samples of the target elevator's power supply voltage during the preset monitoring period. V represents the volume corresponding to the v1th sample of the target elevator's power supply voltage during the preset monitoring period. max for The maximum value, V min for The minimum value, for The mean.

[0116] The first determination module 104 is used to execute step S104, determining whether the current data update quantization index is within the preset first threshold range. If not, no update is performed; if so, step S105 is executed.

[0117] The federated aggregation module 105 is used to execute step S105, which involves performing parameter aggregation operation based on the elevator operation state prediction model parameters corresponding to the target elevator to obtain the first result.

[0118] Parameter aggregation is a component of the federated algorithm. It aggregates multiple local model parameters to generate a global model, and finally assigns the updated model parameters to the corresponding devices or systems. This completes the model parameter update process.

[0119] The model update module is used to perform step S106: feed the first result back to the target elevator and update its elevator operation status prediction model.

[0120] The elevator operation status prediction model update method disclosed in this invention predicts the current data update quantification index based on the monitoring dataset, and then determines whether to perform the elevator operation status prediction model update operation based on whether the current data update quantification index falls within the first threshold range. This method is beneficial for quantifying the necessity of performing the update operation, accurately updating the elevator operation status model, improving the efficiency of the elevator operation status prediction model update, and thus enhancing the efficiency of the elevator operation status prediction system.

[0121] Example 2:

[0122] Considering that the frequency of the system's update operation also reflects the operating status of the target elevator, in this embodiment, the frequency (or cycle) of the target elevator's update operation is used to screen for any abnormalities in the update operation. When an abnormality occurs in the update frequency or cycle, relevant personnel or related systems can respond in a timely manner, which is beneficial to the efficiency of the elevator operating status prediction system. Therefore, the update device of the present invention also includes an update monitoring unit, and the update method of the elevator operating status prediction model of the present invention also includes an update monitoring step. The update monitoring unit includes: an execution count module 201, a second judgment module 202, an update abnormality output module 203.a, and an update abnormality normal module 203.b.

[0123] The execution count module 201 executes step S201: obtain the number of times the target elevator performs the update operation of the elevator operation status prediction model within the preset second monitoring time period;

[0124] The second determination module 202 executes step S202, determining whether the ratio between the number of executions and the preset second monitoring duration falls within the preset second threshold range. If yes, it executes step S203a; otherwise, it executes step S203b.

[0125] Update the abnormal output module 203.a. Execute step S203a and output data indicating that the target elevator has encountered an abnormal situation when performing the update operation of the elevator operation status prediction model.

[0126] The update module 203.b executes step S203b and outputs data indicating that the target elevator has performed the update operation of the elevator operation status prediction model without any abnormalities.

[0127] In addition, it should be noted that the frequency (or cycle) at which the above-mentioned update operation of the target elevator is not triggered can also be used to screen for abnormalities in the update operation. If the ratio between the number of times the operation is not executed and the duration of the third monitoring exceeds the preset third threshold range, the output will show that the update operation of the target elevator executing the elevator operation status prediction model is normal; otherwise, the output will show that there is an abnormality.

[0128] In summary, this invention first predicts the current data update quantification index based on the monitoring dataset, and then determines whether to execute the elevator operation status prediction model update operation based on whether the current data update quantification index falls within the first threshold range. This facilitates a quantitative assessment of the necessity of executing the update operation, accurately updates the elevator operation status model, and improves the efficiency of the elevator operation status prediction model update, thereby enhancing the efficiency of the elevator operation status prediction system. Furthermore, by monitoring the frequency of the system's update operations, the operating status of the target elevator is monitored. While ensuring accurate detection, this further improves the system's response capability to abnormal situations, ensuring the accuracy and timeliness of elevator operation status detection.

[0129] Finally, it should be noted that the elevator operation status prediction model update method disclosed in the embodiments of the present invention is only a preferred embodiment of the present invention and is only used to illustrate the technical solution of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for updating an elevator operation status prediction model, characterized in that: S101. Obtain the target elevator's target operating parameter set during the preset first monitoring period; S102. Align the parameters in the target operating parameter group to obtain the monitoring dataset of the target elevator; The monitoring dataset includes the target operating parameters of the target elevator during a preset first monitoring period and the label information corresponding to the target operating parameters that represents the predicted operating status of the target elevator; S103. Predict the current data update quantification index based on the monitoring dataset; S104. Determine whether the current data update quantization index is within the preset first threshold range. If not, do not update; if yes, proceed to step S105. S105. Then, based on the elevator operation state prediction model parameters corresponding to the target elevator, perform parameter aggregation operation on the elevator operation state prediction model parameters to obtain the first result. S106. Feed the first result back to the target elevator and update the corresponding elevator operation status prediction model.

2. The method for updating the elevator operation status prediction model according to claim 1, characterized in that, The label information of the predicted operating state of the target elevator includes one of the following: a first label information indicating that the elevator state prediction model predicts that the target elevator is in a first calibrated operating state; a second label information indicating that the elevator state prediction model predicts that the target elevator is in a second calibrated operating state; and a third label information indicating that the elevator state prediction model predicts that the target elevator is in an uncalibrated operating state. The uncalibrated operating state means that the elevator state prediction model predicts that the target elevator is in an operating state other than the first calibrated operating state and the second calibrated operating state.

3. The method for updating the elevator operation status prediction model according to claim 2, characterized in that, The quantitative index for predicting current data updates based on the monitoring dataset specifically includes: Calculate the evaluation index based on the target operating parameters; The evaluation index C is calculated using the following formula: Where k is the total number of target operating parameters, C i Let C be the evaluation index component of the i-th target operating parameter; where C i The calculation formula is as follows: M represents the sample number of the i-th target operating parameter within the preset monitoring duration, K represents the total number of samples of the i-th target operating parameter within the preset monitoring duration, and N... M N represents the parameter value corresponding to the Mth sample of the i-th target operating parameter within the preset monitoring duration. max For N M The maximum value, N min For N M The minimum value, For N M The mean; The feature index is calculated based on the evaluation index and the number of samples for each type of label information; The formula for calculating the characteristic index l is as follows: Where C is the evaluation index, M1 represents the number of samples of the target elevator whose label information is the first label information during the preset monitoring period, M2 represents the number of samples of the target elevator whose label information is the second label information during the preset monitoring period, and M3 represents the number of samples of the target elevator whose label information is the third label information during the preset monitoring period. Calculate the current updated quantification index based on the aforementioned characteristic index; The formula for calculating the data update quantification index is as follows: Where l represents the feature index corresponding to the current data update quantization index, and e is the natural logarithm.

4. The method for updating the elevator operation status prediction model according to claim 3, characterized in that, The target operating parameter set includes: The target elevator's control box temperature, load capacity, wire rope cross-sectional area, elevator door opening and closing speed, car operating noise, and power supply voltage are one or more of the following:

5. The method for updating the elevator operation status prediction model according to any one of claims 1-4, characterized in that, It also includes updating the monitoring steps, which specifically include: S201. Obtain the number of times the target elevator performs the update operation of the elevator operation status prediction model within the preset second monitoring time period; S202. Determine whether the ratio between the number of executions and the preset second monitoring duration falls within the preset second threshold range. If yes, proceed to step S203a; otherwise, proceed to step S203b. S203a. Output data indicating an abnormal situation when the target elevator performs the update operation of the elevator operation status prediction model; S203b: Output data indicating that the target elevator performed the elevator operation status prediction model update operation without any anomalies.

6. An update device for an elevator operation status prediction model, characterized in that... include: An update unit, the update unit comprising: The parameter acquisition module is used to acquire the target elevator's target operating parameter set during the preset first monitoring period; Data preprocessing module: used to align the parameters in the target operating parameter group to obtain the monitoring dataset of the target elevator; the monitoring dataset includes the target operating parameters of the target elevator during a preset first monitoring period and the label information corresponding to the target operating parameters representing the predicted operating status of the target elevator; Data Update Quantitative Index Calculation Module: Used to predict the current data update quantitative index based on the monitored dataset; The first determination module is used to determine whether the current data update quantization index falls within the preset first threshold range. If not, no update is performed; if so, the federated aggregation module is executed. Federated aggregation module: used to perform parameter aggregation operation on the elevator operation state prediction model parameters corresponding to the target elevator to obtain a first result; Model update module: Feeds back the first result to the target elevator and updates the corresponding elevator operation status prediction model; otherwise, no update is performed.

7. The updating device for an elevator operation status prediction model according to claim 6, characterized in that, The data update quantification index calculation module includes: Evaluation index calculation submodule: used to calculate the evaluation index based on the target operating parameters; The evaluation index C is calculated using the following formula: Where k is the total number of target operating parameters, C i Let C be the evaluation index component of the i-th target operating parameter; where C i The calculation formula is as follows: M represents the sample number of the i-th target operating parameter within the preset monitoring duration, K represents the total number of samples of the i-th target operating parameter within the preset monitoring duration, and N... M N represents the parameter value corresponding to the Mth sample of the i-th target operating parameter within the preset monitoring duration. max For N M The maximum value, N min For N M The minimum value, For N M The mean; Feature index calculation submodule: used to calculate the feature index based on the evaluation index and the number of samples for each type of label information; The formula for calculating the characteristic index l is as follows: Where C is the evaluation index, M1 represents the number of samples of the target elevator whose label information is the first label information during the preset monitoring period, M2 represents the number of samples of the target elevator whose label information is the second label information during the preset monitoring period, and M3 represents the number of samples of the target elevator whose label information is the third label information during the preset monitoring period. Update Quantitative Index Calculation Submodule: Used to calculate the current updated quantitative index based on the feature index; The formula for calculating the data update quantification index is as follows: Where l represents the feature index corresponding to the current data update quantization index, and e is the natural logarithm.

8. The updating device for an elevator operation status prediction model according to claim 7, characterized in that, It also includes an updated monitoring unit, which includes: The execution count module is used to obtain the number of times the target elevator performs the update operation of the elevator operation status prediction model within a preset second monitoring period; The second determination module is used to determine whether the ratio between the number of executions and the preset second monitoring duration falls within the preset second threshold range. If so, the step update abnormal output module is started; otherwise, the update normal output module is started. The update exception output module is used to output data indicating that an abnormal situation occurred when the target elevator performed the update operation of the elevator operation status prediction model; The update normal output module is used to output data indicating that the target elevator has performed an update operation on the elevator operation status prediction model without any abnormalities.

9. An elevator operation status prediction system, characterized in that, include: Multiple elevators and elevator operation status prediction models, servers, and updating devices as described in any one of claims 6-8; The multiple elevators are connected to the server, and the updating device is also connected to the server.

Images