Elevator operation risk prediction method, device, equipment and medium

Abstract

The invention provides an elevator operation risk prediction method and device, equipment and a medium, and belongs to the technical field of elevator safety. The collected elevator operation data are transmitted to a cloud server; the elevator operation data are preprocessed; preset elevator parameter features are extracted from the preprocessed elevator operation data; calculating a mean value, a standard deviation, a maximum value and a minimum value of the elevator parameter characteristics to obtain an elevator parameter characteristic distribution condition; displaying the elevator parameter feature distribution condition by using a scatter diagram and a histogram; establishing an association relationship between the elevator parameter characteristics exceeding the elevator risk assessment threshold range and the risk early warning data set, quantifying a linear relationship between each elevator parameter characteristic and the risk early warning data set, and judging the relevancy between the elevator parameter characteristics and the risk early warning data set; and the elevator operation risk state is judged based on the relevancy. The elevator fault rate is reduced by predicting the elevator operation risk, and stable operation of the elevator is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of elevator safety, and in particular relates to an elevator operation risk prediction method, device, equipment and medium. Background Art

[0002] At present, elevators are increasingly used as vertical transportation tools in buildings. However, elevators face a variety of risk factors during operation, such as equipment aging, improper maintenance, human operating errors, etc., which may lead to elevator failures or even accidents. Therefore, it is particularly important to accurately predict and promptly warn of elevator operation risks.

[0003] Existing elevator monitoring systems can collect elevator operation data through sensors and issue alarms when abnormal situations occur. However, most of these focus on real-time monitoring and emergency response after failures, and their ability to predict risks is relatively limited. In addition, elevator monitoring systems often have limitations in data collection and cannot fully obtain various data during elevator operation. At the same time, there is a lack of effective pre-processing methods in data processing, resulting in low data quality, which in turn affects the accuracy of risk prediction. Summary of the invention

[0004] The present invention provides a method for predicting elevator operation risks, which predicts potential failures and risks of the elevator by analyzing the elevator's operation data, maintenance records, fault history and other information, so as to take early warning and maintenance measures to ensure the safe operation of the elevator.

[0005] Methods include: Obtain elevator operation data and construct an elevator operation data set based on a preset prediction period; Transmit the collected elevator operation data to the cloud server; Preprocess the elevator operation data, including filling processing, outlier processing, denoising processing and normalization processing; Extracting preset elevator parameter features from the preprocessed elevator operation data; Calculate the mean, standard deviation, maximum value, and minimum value of the elevator parameter characteristics to obtain the distribution of the elevator parameter characteristics; Use scatter plots and histograms to display the distribution of elevator parameter characteristics; Establish an association relationship between the elevator parameter characteristics that exceed the elevator risk assessment threshold range and the risk warning data set, quantify the linear relationship between each elevator parameter characteristic and the risk warning data set, and determine the correlation between the elevator parameter characteristics and the risk warning data set; The elevator operation risk status is determined based on the correlation.

[0006] It should be further explained that, in the method, a risk assessment joint table between elevator parameter characteristics and risk assessment models is also constructed to show the frequency distribution between different categories of elevator parameter characteristics and risk occurrence.

[0007] It should be further explained that the chi-square test module is used to determine the correlation between the chi-square value of the elevator parameter characteristics and the risk warning data set: According to the chi-square value and degrees of freedom, look up the chi-square distribution table to obtain the corresponding association value; If the correlation value is less than the preset correlation value, there is no correlation between the elevator parameter characteristics exceeding the elevator risk assessment threshold range and the risk occurrence.

[0008] It should be further explained that the step of using a scatter plot and a histogram to display the distribution of elevator parameter characteristics also includes: Determine any two elevator parameter characteristics to be displayed on the scatter plot; Configure the scatter plot coordinate axis, take each elevator parameter feature as a data point, and plot it on the coordinate axis to form a scatter plot; According to the value range and distribution characteristics of the elevator parameter characteristics, the group interval is selected to group the elevator parameter characteristics; the frequency of the elevator parameter characteristic points in each group is counted; and a histogram is drawn with the group interval as the base length and the frequency as the height.

[0009] It should be further explained that the step of establishing an association between the elevator parameter characteristics exceeding the elevator risk assessment threshold range and the risk warning data set, quantifying the linear relationship between each elevator parameter characteristic and the risk warning data set, and determining the correlation between the elevator parameter characteristics and the risk warning data set also includes: Building the association relationship also includes: setting the threshold of elevator risk assessment based on historical data and expert knowledge, screening out the elevator parameter characteristics that exceed the threshold range; associating the elevator parameter characteristics with the risk warning data set, and marking the corresponding risk warning information; The method of quantifying the linear relationship includes: based on a univariate linear regression model, using the elevator parameter features exceeding the threshold range and the corresponding risk warning data set to fit the linear model, and obtaining the linear relationship between each elevator parameter feature and the risk warning data set from the fitted model; The method of determining the correlation includes: calculating the correlation coefficient based on the Pearson correlation coefficient, and determining the correlation between the elevator parameter characteristics and the risk warning data set according to the value of the correlation coefficient.

[0010] It should be further explained that the filling methods of the preprocessing method include: mean filling, median filling and mode filling; The outlier processing method is to define the elevator operation data that exceeds the mean ±3 times the standard deviation as an outlier; The formula is: Outlier = {x|x<μ−3σ or x>μ+3σ}, where μ is the mean and σ is the standard deviation.

[0011] It should be further explained that, in the method, denoising is performed based on convolution operation; Elevator operation data based on convolution operation It is expressed as:

[0012] Among them, the discrete signal , h[k] is the filter coefficient, n is the index of the output signal, and k is the index of the filter coefficient; The formula for normalization is as follows: Xnorm=a+ (X−Xmin)*(ba) / (Xmax−Xmin) Where: X is the original elevator operation data, Xmin and Xmax are the minimum and maximum values ​​in the elevator operation data set, Xnorm is the normalized data, and a and b are the minimum and maximum values ​​of the normalized data range.

[0013] The present application also provides an elevator operation risk prediction system, the system comprising: A data acquisition module, used to acquire elevator operation data and construct an elevator operation data set based on a preset prediction period; Data communication module, used to transmit the collected elevator operation data to the cloud server; The cloud server is used to preprocess the elevator operation data, and the preprocessing methods include: filling processing, outlier processing, denoising processing and normalization processing; extracting preset elevator parameter features from the preprocessed elevator operation data; calculating the mean, standard deviation, maximum value and minimum value of the elevator parameter features to obtain the distribution of the elevator parameter features; using scatter plots and histograms to display the distribution of the elevator parameter features; establishing an association relationship between the elevator parameter features that exceed the elevator risk assessment threshold range and the risk warning data set, quantifying the linear relationship between each elevator parameter feature and the risk warning data set, and judging the correlation between the elevator parameter features and the risk warning data set; judging the elevator operation risk status based on the correlation.

[0014] According to another embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the elevator operation risk prediction method when executing the program.

[0015] According to another embodiment of the present application, a storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the elevator operation risk prediction method are implemented.

[0016] It can be seen from the above technical solutions that the present invention has the following advantages: The elevator operation risk prediction method provided by the present invention obtains elevator operation data in real time to ensure the timeliness and accuracy of risk prediction. By constructing a data set with a preset prediction period, it can adapt to the elevator operation risk prediction needs in different scenarios. In the data preprocessing step, a variety of processing methods are adopted to deal with elevator operation data from different sources and of different quality. This makes the present invention more adaptable and robust in practical applications. The present invention makes the risk prediction results more intuitive by accurately extracting elevator parameter features and combining them with visualization means for display. It is convenient for relevant personnel to make quick and accurate decisions. By constructing the correlation between elevator parameter features and risk warning data sets, the intelligence of risk warning is realized. It can issue warnings in time when potential risks occur in elevators.

[0017] The present invention also establishes an association relationship between the elevator parameter characteristics that exceed the elevator risk assessment threshold range and the risk warning data set, which can timely detect abnormal conditions in elevator operation. By quantifying the linear relationship between each elevator parameter characteristic and the risk warning data set, the operating risk status of the elevator can be quickly determined, providing the possibility for timely response measures. This timely risk warning mechanism helps to reduce the occurrence of elevator accidents and ensure the safety of passengers. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0019] Figure 1 This is a flow chart of the elevator operation risk prediction method; Figure 2 This is a schematic diagram of the elevator operation risk prediction system; Figure 3 Schematic diagram of an electronic device. DETAILED DESCRIPTION

[0020] The method provided by the present invention predicts elevator operation risks by integrating data acquisition, cloud transmission, preprocessing, feature extraction, feature analysis, risk warning association and risk status, thereby achieving comprehensive prediction and evaluation of elevator operation risks.

[0021] The present invention obtains elevator operation data, constructs an elevator operation data set based on a preset prediction period, and transmits the data to a cloud server in real time. After the cloud server receives the data, it adopts a variety of preprocessing methods such as filling processing, outlier processing, denoising processing, and normalization processing to ensure the accuracy and consistency of the data and improve the reliability of subsequent analysis. The preset elevator parameter features are extracted from the preprocessed data, and the mean, standard deviation, maximum value, and minimum value of these features are calculated to obtain the distribution of the elevator parameter features. Through the visual display of scatter plots and histograms, the feature distribution is clear at a glance, which is convenient for further risk analysis.

[0022] The present invention establishes an association relationship between the elevator parameter characteristics that exceed the elevator risk assessment threshold range and the risk warning data set, quantifies the linear relationship between each elevator parameter characteristic and the risk warning data set, and determines their correlation. Based on the analysis results of the correlation, the present invention can accurately determine the operating risk status of the elevator for timely maintenance and processing.

[0023] The specific steps of the elevator operation risk prediction method will be described in detail below. For the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are proposed to facilitate a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details.

[0024] The phrases such as "one embodiment" or "some embodiments" described in the present application mean that the specific features, structures or characteristics described in the embodiment are included in one or more embodiments of the present application. Therefore, the phrases such as "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments" etc. that appear in different places in the present application do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways.

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] See also Figure 1 The figure is a flow chart of a method for predicting elevator operation risks in a specific embodiment, the method comprising: S101: Acquire elevator operation data and construct an elevator operation data set based on a preset prediction period.

[0027] In some embodiments, by installing speed sensors, acceleration sensors, weight sensors, door sensors, smart cameras and other devices in the elevator, the physical state data, video data and environmental data of the elevator are collected in real time, which may specifically include: the speed, acceleration, load, door switch status, fault code, etc. of the elevator.

[0028] S102: Transmit the collected elevator operation data to the cloud server.

[0029] This embodiment uses power line carrier technology to transmit the collected elevator operation data to the cloud server based on high speed and long distance. Optionally, in order to deal with the signal attenuation and interference problems that may be encountered by power line carrier technology and avoid data transmission interruption, a Wifi transmission method is also used.

[0030] S103: Preprocessing the elevator operation data, wherein the preprocessing method includes: filling processing, outlier processing, denoising processing and normalization processing.

[0031] S104: extracting preset elevator parameter features from the preprocessed elevator operation data.

[0032] In this embodiment, according to the characteristics of the elevator operation data, the elevator parameter characteristics related to the elevator operation risk prediction are selected. The elevator parameter characteristics include the elevator's operating speed, operating time, load, temperature, vibration frequency, etc.

[0033] To extract features from preprocessed data, you can use a sliding window algorithm to extract statistical features such as the average, maximum, and minimum values ​​over a period of time; or use signal processing techniques such as Fourier transform to extract frequency domain features. The extracted features are processed to improve their prediction accuracy.

[0034] S105: Calculate the mean, standard deviation, maximum value, and minimum value of the elevator parameter characteristics to obtain the distribution of the elevator parameter characteristics.

[0035] In this embodiment, the maximum value and the minimum value can be found based on the elevator operation data set. The standard deviation of the elevator parameter feature can be calculated to measure the degree of dispersion of the elevator parameter feature.

[0036] S106: Use a scatter plot and a histogram to display the distribution of elevator parameter characteristics.

[0037] In this embodiment, the calculated elevator parameter characteristics are combined with the mean, standard deviation, maximum value, minimum value, etc. to form the data format required for the chart.

[0038] According to the characteristics of the data and the purpose of analysis, scatter plots and histograms are selected as display tools. Scatter plots are used to show the correlation between features, while histograms are used to show the distribution of features. Based on the results displayed in the charts, the distribution of elevator parameter features is explained and analyzed.

[0039] In some specific embodiments, the step of displaying the distribution of elevator parameter characteristics using a scatter plot and a histogram also includes: Determine any two elevator parameter features to be displayed on the scatter plot; configure the scatter plot coordinate axis, and use each elevator parameter feature as a data point and plot it on the coordinate axis to form a scatter plot.

[0040] According to the value range and distribution characteristics of the elevator parameter characteristics, the group interval is selected to group the elevator parameter characteristics; the frequency of the elevator parameter characteristic points in each group is counted; and a histogram is drawn with the group interval as the base length and the frequency as the height.

[0041] S107: Establishing an association relationship between the elevator parameter characteristics that exceed the elevator risk assessment threshold range and the risk warning data set, quantifying the linear relationship between each elevator parameter characteristic and the risk warning data set, and determining the correlation between the elevator parameter characteristics and the risk warning data set.

[0042] It should be noted that the threshold range of risk assessment is set according to elevator safety standards and historical data. Parameter features that exceed the threshold range are screened out from the preprocessed elevator operation data. These screened features are associated with the risk warning data set by establishing a feature matrix and a label matrix.

[0043] In this embodiment, a statistical method such as linear regression can be used to quantify the linear relationship between each elevator parameter feature and the risk warning data set. According to the quantification result, the correlation between the elevator parameter feature and the risk warning data set is determined. Optionally, this can be achieved by observing the significance of the regression coefficient, the size of the determination coefficient, etc.

[0044] The risk level can be set based on the correlation to determine the risk status of elevator operation. Different risk levels can be set according to elevator safety standards and historical data. The current risk status of the elevator is evaluated based on the correlation between the elevator parameter characteristics and the risk warning data set. If the correlation is high and the characteristic value exceeds the safety range, it is judged as a high-risk state.

[0045] Based on the assessment results, risk warnings are issued in a timely manner to remind relevant personnel to take necessary measures to reduce risks.

[0046] S108: Determine the elevator operation risk status based on the correlation.

[0047] It can be seen that the elevator operation risk prediction method can timely discover potential safety hazards by real-time monitoring and predicting the operation risks of elevators, and take measures to prevent and deal with them, thereby improving the safety of elevators. By improving the safety and reliability of elevators, the waiting time and failure rate of passengers can be reduced, thereby improving the travel experience of passengers.

[0048] In some embodiments, a risk assessment joint table between elevator parameter characteristics and risk assessment models is also constructed to display the frequency distribution between different categories of elevator parameter characteristics and risk occurrence situations.

[0049] The chi-square test module is used to determine the association between the chi-square value of the elevator parameter characteristics and the risk warning data set: according to the chi-square value and degree of freedom, the chi-square distribution table is searched to obtain the corresponding association value; if the association value is less than the preset association value, there is no association between the elevator parameter characteristics that exceed the elevator risk assessment threshold range and the occurrence of risks.

[0050] In some specific embodiments, a risk assessment contingency table between elevator parameter features and risk assessment models is constructed, and the elevator parameter features are selected based on the elevator operation data. Specifically, parameter features that may be related to the occurrence of risks can be selected based on the professional knowledge and experience of elevator operation. Using the contingency table method, the elevator parameter features are combined with the risk occurrence situation to display the frequency distribution between different categories of elevator parameter features and risk occurrence. For example, a two-dimensional table can be constructed, in which a row represents a certain operating time of the elevator, a column represents the risk occurrence situation, and the values ​​in the table represent the frequency of risk occurrence under the parameter feature. The risk assessment contingency table is displayed through bar charts and heat maps, which facilitates intuitive understanding of the relationship between different parameter features and risk occurrence. Based on the analysis of frequency distribution, it is identified which parameter features have a strong correlation with risk occurrence.

[0051] For this embodiment, the chi-square test module is used to determine the correlation between the elevator parameter characteristics and the risk warning data set. The chi2_contingency function in the scipy.stats library can be used to perform the chi-square test. According to the data in the risk assessment contingency table, the chi-square value is calculated. The chi-square value is used to measure the degree of difference between the actual observation value and the expected observation value. Use the chi2_contingency function to input the risk assessment contingency table to obtain the chi-square value, p value, degree of freedom, and expected frequency.

[0052] According to the calculated chi-square value and degree of freedom, the chi-square distribution table is searched to obtain the corresponding association value, which can also be the critical value or threshold of the elevator parameter characteristics. Compare the calculated chi-square value with the association value. If the chi-square value is greater than the association value, it indicates that there is a significant association between the elevator parameter characteristics and the occurrence of risks; if the chi-square value is less than or equal to the association value, it indicates that there is no significant association.

[0053] In some embodiments, a preset correlation value may be set to determine the significance level of the correlation relationship. If the correlation value is less than the preset correlation value, it is considered that there is a significant correlation between the elevator parameter feature and the risk occurrence; otherwise, it is considered that there is no significant correlation.

[0054] According to the results of the chi-square test, determine which elevator parameter characteristics are significantly associated with the occurrence of risks and which are not. For parameter characteristics with significant correlation, their impact degree and direction can be further analyzed to provide a basis for elevator risk assessment and early warning. For parameter characteristics with no correlation, consider removing them from the model or further exploring their relationship with other factors.

[0055] In some embodiments, the step of establishing an association relationship between the elevator parameter characteristics exceeding the elevator risk assessment threshold range and the risk warning data set, quantifying the linear relationship between each elevator parameter characteristic and the risk warning data set, and determining the correlation between the elevator parameter characteristics and the risk warning data set also includes: Building the association relationship also includes: setting the threshold of elevator risk assessment based on historical data and expert knowledge, screening out the elevator parameter characteristics that exceed the threshold range; associating the elevator parameter characteristics with the risk warning data set, and marking the corresponding risk warning information; The method of quantifying the linear relationship includes: based on a univariate linear regression model, using the elevator parameter features exceeding the threshold range and the corresponding risk warning data set to fit the linear model, and obtaining the linear relationship between each elevator parameter feature and the risk warning data set from the fitted model; The method of determining the correlation includes: calculating the correlation coefficient based on the Pearson correlation coefficient, and determining the correlation between the elevator parameter characteristics and the risk warning data set according to the value of the correlation coefficient.

[0056] The elevator operation risk prediction method of this embodiment transmits the acquired original elevator operation data to the cloud server for storage and processing. On the cloud server, the received elevator operation data is sorted into time series data sets on a daily, weekly or monthly basis. Each data set contains the readings of all sensors within a prediction period and the corresponding timestamp information.

[0057] Preprocess the constructed elevator operation dataset.

[0058] Among them, filling processing is used to solve the problem of missing values ​​that may exist in the data set. For missing data caused by sensor failure or other reasons, interpolation or prediction models based on historical data are used to fill in to ensure the integrity of the data set.

[0059] Outlier processing is aimed at values ​​that appear in the data set that are significantly deviated from the normal range. These outliers may be caused by sensor error readings or accidental events. By setting a reasonable threshold range, combining statistical methods and machine learning algorithms, these outliers can be identified and processed to avoid interference with subsequent analysis.

[0060] Denoising is to eliminate random noise in the data set. Kalman filtering is used to smooth the original data to reduce the impact of noise on feature extraction and model training.

[0061] Normalization is to scale the feature values ​​in the data set to the same magnitude range to eliminate the analytical bias caused by the dimension difference between different features. Through linear transformation or other normalization methods, ensure that each feature has the same weight during the model training process.

[0062] In some specific embodiments, the data may also be deduplicated, that is, checking whether there are duplicate records in the data set and deleting them from the data.

[0063] For missing values, you can use methods to fill missing values, such as using mean filling, median filling, or mode filling.

[0064] Mean filling can be used for continuous variables, using the mean to fill missing values. The calculation formula is: mean Where Xi is the measurement value and n is the total number of measurements.

[0065] This embodiment can also use the median to fill in missing values. The median is the value in the middle after the data set is sorted. If the total number of measured values ​​is an even number, the median is the average of the two middle values.

[0066] Optionally, you can fill missing values ​​with the mode, which is the value that occurs most often in a data set.

[0067] For outliers, you can use the method of deleting or replacing outliers. Any data point that exceeds the mean ± 3 times the standard deviation is considered an outlier. The formula is: Outlier = {x|x<μ−3σ or x>μ+3σ}, where μ is the mean and σ is the standard deviation.

[0068] For denoising technology, filter technology is applied to reduce the noise in sensor data. Filter denoising is based on the different characteristics of signal and noise in the frequency domain. Signals usually contain useful information, while noise is regarded as unwanted components. By designing a suitable filter, noise can be suppressed in the frequency domain while retaining the main characteristics of the signal. For a discrete signal x[n] and a filter coefficient h[k], the elevator operation data of the convolution operation It can be expressed as:

[0069] Where n is the index of the output signal and k is the index of the filter coefficient. During the convolution process, for each n, a value y[n] is calculated, and the filter coefficient h and the input signal x are weighted sums at different time points.

[0070] Normalization is to ensure that all data are on the same scale to facilitate subsequent analysis.

[0071] The formula is as follows: Xnorm=a+ (X−Xmin)*(ba) / (Xmax−Xmin) Where: X is the original data, Xmin and Xmax are the minimum and maximum values ​​in the data set, Xnorm is the normalized data, and a and b are the minimum and maximum values ​​of the normalized data range.

[0072] After the preprocessing is completed, the preset elevator parameter features are extracted from the processed elevator operation data. These features include but are not limited to average operating speed, maximum acceleration, total displacement distance, and load change rate. These features can fully reflect the operating status of the elevator within a prediction period.

[0073] This embodiment can calculate the mean, standard deviation, maximum value and minimum value of the elevator parameter characteristics to obtain the distribution of the elevator parameter characteristics.

[0074] In order to more intuitively display the distribution of elevator parameter features, the present invention uses scatter plots and histograms for visual display. Scatter plots are used to present the correlation between various elevator parameter features, helping to identify the existence of abnormal patterns or trends; while histograms are used to display the distribution of a single elevator parameter feature, making it easier to observe its value range and central tendency.

[0075] Through visual display, users can intuitively understand the operating status of the elevator within a forecast period, identify potential risk points in a timely manner, and take corresponding preventive measures.

[0076] On the basis of the above embodiments, in order to further improve the reliability of the elevator operation risk prediction method provided in the above embodiments, in an implementable embodiment, after completing the collection, preprocessing and feature extraction of the elevator operation data, this specific implementation method will elaborate on how to construct an elevator operation risk prediction model and apply the elevator operation risk prediction model for risk prediction.

[0077] Before building an elevator operation risk prediction model, you need to prepare historical elevator parameter features as a training set. The historical elevator parameter features include parameter features under various elevator operating conditions, as well as the corresponding normal elevator parameter features, abnormal elevator parameter features or risk levels. Then select a support vector machine or random forest to train an elevator operation risk prediction model.

[0078] Use the prepared training set to train the selected machine learning algorithm. During the training process, optimize the model performance by adjusting the model's learning rate, regularization coefficient, and using cross-validation techniques. Monitor the performance of the elevator operation risk prediction model on the training set and validation set to ensure that the model can fully learn the inherent laws of the data and avoid overfitting.

[0079] After training, an independent test set is used to evaluate the model. Evaluation indicators include but are not limited to accuracy, recall, F1 score, etc. By comparing the evaluation results of different models or the same model under different hyperparameter settings, the model with the best performance is selected as the final elevator operation risk prediction model.

[0080] The trained model is deployed to the cloud server to receive and process the operation data from the elevator in real time. The model predicts the operation risk status of the elevator based on the input data and displays the prediction results to the user in a visual form. For example, a scatter plot can be used to show the distribution of elevator parameter characteristics, a histogram can be used to show the statistical information of the risk level, and a dashboard or warning light can be used to intuitively display the real-time risk status of the elevator.

[0081] When the model predicts that there is an operating risk in the elevator, the system will automatically trigger the early warning mechanism. The early warning information can be promptly notified to relevant personnel through SMS, email or APP push. At the same time, the system can also assist relevant personnel to respond quickly based on preset response measures, thereby effectively reducing the probability of elevator accidents.

[0082] In this embodiment, as elevator operation data continues to accumulate, and elevator technology and operating environment continue to change, the previously trained model may gradually lose its effectiveness. New data can be collected regularly and the model can be retrained to ensure that the model's prediction performance is always maintained at the best state. At the same time, the model is continuously monitored and maintained to promptly discover and resolve potential problems.

[0083] Through the above specific implementation methods, an efficient and reliable elevator operation risk prediction model can be constructed and applied to the actual elevator operation and maintenance management. It can improve the safety performance of the elevator, reduce the occurrence of accidents, and provide strong data support and decision-making basis for the maintenance of the elevator.

[0084] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0085] The following is an embodiment of the elevator operation risk prediction system provided by the embodiments of the present disclosure. The system and the elevator operation risk prediction methods of the above-mentioned embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the elevator operation risk prediction system, please refer to the embodiments of the above-mentioned elevator operation risk prediction method.

[0086] like Figure 2 As shown, the system includes: a data acquisition module, which is used to acquire elevator operation data and construct an elevator operation data set based on a preset prediction period.

[0087] The data communication module is used to transmit the collected elevator operation data to the cloud server.

[0088] The cloud server is used to preprocess the elevator operation data, and the preprocessing methods include: filling processing, outlier processing, denoising processing and normalization processing; extracting preset elevator parameter features from the preprocessed elevator operation data; calculating the mean, standard deviation, maximum value and minimum value of the elevator parameter features to obtain the distribution of the elevator parameter features; using scatter plots and histograms to display the distribution of the elevator parameter features; establishing an association relationship between the elevator parameter features that exceed the elevator risk assessment threshold range and the risk warning data set, quantifying the linear relationship between each elevator parameter feature and the risk warning data set, and judging the correlation between the elevator parameter features and the risk warning data set; judging the elevator operation risk status based on the correlation.

[0089] The elevator operation risk prediction system provided by the present invention can detect the operating status of the elevator in real time, and predict the potential failures and risks of the elevator by analyzing the elevator's operating data, maintenance records, fault history and other information, so as to take early warning and maintenance measures to ensure the safe operation of the elevator.

[0090] like Figure 3 As shown, the present application also provides an electronic device, including a display module 103, a memory 102, a processor 101, and a computer program stored in the memory and executable on the processor 101, wherein the processor 101 implements the steps of a method for parsing and loading a GIM model of a power transmission project when executing the program.

[0091] Electronic devices may refer to data acquisition modules, data communication modules, and to cloud servers. Electronic devices include, but are not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or required herein.

[0092] In the embodiment of the present application, the processor 101 can be implemented by using at least one of an application-specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), a processor, a controller, a microcontroller, a microprocessor, and an electronic unit designed to perform the functions described herein. In some cases, such an implementation can be implemented in a controller. For software implementation, implementations such as processes or functions can be implemented with separate software modules that allow execution of at least one function or operation. The software code can be implemented by a software application (or program) written in any appropriate programming language, and the software code can be stored in a memory and executed by a controller.

[0093] The display module 103 is used to display information input by the user or information provided to the user. The display module 103 may include a display panel, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc.

[0094] The memory 102 may be used to store software programs and various data. The memory 102 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0095] The present application also provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the elevator operation risk prediction method are implemented.

[0096] The storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0097] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting elevator operation risks, characterized in that: Methods include: Obtain elevator operation data and construct an elevator operation data set based on a preset prediction period; Transmit the collected elevator operation data to the cloud server; Preprocess the elevator operation data, including filling processing, outlier processing, denoising processing and normalization processing; Extracting preset elevator parameter features from the preprocessed elevator operation data; Calculate the mean, standard deviation, maximum value, and minimum value of the elevator parameter characteristics to obtain the distribution of the elevator parameter characteristics; Use scatter plots and histograms to display the distribution of elevator parameter characteristics; Establish an association relationship between the elevator parameter characteristics that exceed the elevator risk assessment threshold range and the risk warning data set, quantify the linear relationship between each elevator parameter characteristic and the risk warning data set, and determine the correlation between the elevator parameter characteristics and the risk warning data set; The elevator operation risk status is determined based on the correlation.

2. The elevator operation risk prediction method according to claim 1, characterized in that: In the method, a risk assessment joint table between elevator parameter characteristics and risk assessment models is also constructed to show the frequency distribution between different categories of elevator parameter characteristics and risk occurrence.

3. The elevator operation risk prediction method according to claim 2, characterized in that: Use the chi-square test module to determine the correlation between the chi-square value of the elevator parameter characteristics and the risk warning data set: According to the chi-square value and degrees of freedom, look up the chi-square distribution table to obtain the corresponding association value; If the correlation value is less than the preset correlation value, there is no correlation between the elevator parameter characteristics exceeding the elevator risk assessment threshold range and the risk occurrence.

4. The elevator operation risk prediction method according to claim 1, characterized in that: The steps of using scatter plots and histograms to display the distribution of elevator parameter characteristics also include: Determine any two elevator parameter characteristics to be displayed on the scatter plot; Configure the scatter plot coordinate axis, take each elevator parameter feature as a data point, and plot it on the coordinate axis to form a scatter plot; According to the value range and distribution characteristics of the elevator parameter characteristics, the group interval is selected to group the elevator parameter characteristics; the frequency of the elevator parameter characteristic points in each group is counted; and a histogram is drawn with the group interval as the base length and the frequency as the height.

5. The elevator operation risk prediction method according to claim 1, characterized in that: The step of establishing a correlation between the elevator parameter characteristics that exceed the elevator risk assessment threshold range and the risk warning data set, quantifying the linear relationship between each elevator parameter characteristic and the risk warning data set, and determining the correlation between the elevator parameter characteristics and the risk warning data set also includes: Building the association relationship also includes: setting the threshold of elevator risk assessment based on historical data and expert knowledge, screening out the elevator parameter characteristics that exceed the threshold range; associating the elevator parameter characteristics with the risk warning data set, and marking the corresponding risk warning information; The method of quantifying the linear relationship includes: based on a univariate linear regression model, using the elevator parameter features exceeding the threshold range and the corresponding risk warning data set to fit the linear model, and obtaining the linear relationship between each elevator parameter feature and the risk warning data set from the fitted model; The method of determining the correlation includes: calculating the correlation coefficient based on the Pearson correlation coefficient, and determining the correlation between the elevator parameter characteristics and the risk warning data set according to the value of the correlation coefficient.

6. The elevator operation risk prediction method according to claim 1, characterized in that: The filling methods of the preprocessing method include: mean filling, median filling and mode filling; The outlier processing method is to define the elevator operation data that exceeds the mean ±3 times the standard deviation as an outlier; The formula is: Outlier = {x|x<μ−3σ or x>μ+3σ}, where μ is the mean and σ is the standard deviation.

7. The elevator operation risk prediction method according to claim 1, characterized in that: In the method, denoising is performed based on convolution operation; Elevator operation data based on convolution operation It is expressed as: Among them, the discrete signal , h[k] is the filter coefficient, n is the index of the output signal, and k is the index of the filter coefficient; The formula for normalization is as follows: Xnorm=a+ (X−Xmin)*(ba) / (Xmax−Xmin) Where: X is the original elevator operation data, Xmin and Xmax are the minimum and maximum values ​​in the elevator operation data set, Xnorm is the normalized data, and a and b are the minimum and maximum values ​​of the normalized data range.

8. An elevator operation risk prediction system, characterized in that: The system is used to implement the elevator operation risk prediction method according to any one of claims 1 to 7; The system includes: A data acquisition module, used to acquire elevator operation data and construct an elevator operation data set based on a preset prediction period; Data communication module, used to transmit the collected elevator operation data to the cloud server; The cloud server is used to preprocess the elevator operation data, and the preprocessing methods include: filling processing, outlier processing, denoising processing and normalization processing; extracting preset elevator parameter features from the preprocessed elevator operation data; calculating the mean, standard deviation, maximum value and minimum value of the elevator parameter features to obtain the distribution of the elevator parameter features; using scatter plots and histograms to display the distribution of the elevator parameter features; establishing an association relationship between the elevator parameter features that exceed the elevator risk assessment threshold range and the risk warning data set, quantifying the linear relationship between each elevator parameter feature and the risk warning data set, and judging the correlation between the elevator parameter features and the risk warning data set; judging the elevator operation risk status based on the correlation.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the elevator operation risk prediction method according to any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the elevator operation risk prediction method according to any one of claims 1 to 7 are implemented.

Images