An elevator safety risk adaptive analysis method and system

Abstract

The present invention relates to the technical field of elevator safety risk analysis, and particularly to an elevator safety risk adaptive analysis method and system. The method includes the following steps: performing misoperation code execution unit mapping on the elevator operation logic code according to the elevator historical operation log to obtain misoperation code execution units; performing abnormal speed change code logic parsing on the misoperation code execution units and backtracking the triggering conditions to obtain abnormal speed change triggering condition data; constructing a causal relationship network based on the abnormal speed change triggering condition data to obtain a potential risk causal relationship network; constructing an elevator safety risk adaptive analysis model based on the potential risk causal relationship network by using a random forest algorithm to obtain an elevator safety risk adaptive analysis model. The present invention makes the elevator safety risk analysis technology more perfect through optimizing the elevator safety risk analysis technology.

Description

Technical Field

[0001] The present invention relates to the technical field of elevator safety risk analysis, and in particular, to an elevator safety risk adaptive analysis method and system. Background Art

[0002] With the rapid development of information technology and big data analysis technology, artificial intelligence and machine learning technologies have gradually been introduced into the field of elevator safety management. These technologies provide new ideas and methods for elevator operation status monitoring, fault warning, and risk assessment. By deeply analyzing the historical operation logs of elevators, potential safety hazards can be discovered, which helps to achieve real-time monitoring and prediction of the system operation status. However, there is a problem in a traditional elevator safety risk adaptive analysis method that the error in analyzing the cause of abnormal speed change control of elevators is large, resulting in low accuracy of elevator safety risk analysis. Summary of the Invention

[0003] Based on this, it is necessary to provide an elevator safety risk adaptive analysis method and system to solve at least one of the above technical problems.

[0004] To achieve the above object, an elevator safety risk adaptive analysis method, the method includes the following steps:

[0005] Step S1: Obtain the elevator historical operation log and the elevator operation logic code; perform misoperation code execution unit mapping on the elevator operation logic code according to the elevator historical operation log to obtain the misoperation code execution unit;

[0006] Step S2: Perform abnormal speed change code logic parsing on the misoperation code execution unit to obtain abnormal speed change code logic data; perform trigger condition backtracking on the abnormal speed change code logic data to obtain abnormal speed change trigger condition data;

[0007] Step S3: Perform potential risk code segment linkage analysis based on the abnormal speed change trigger condition data to obtain potential risk code segment linkage data; construct a causal relationship network according to the potential risk code segment linkage data to obtain a potential risk causal relationship network;

[0008] Step S4: Construct an elevator safety risk adaptive analysis model based on the random forest algorithm for the potential risk causal relationship network to obtain an elevator safety risk adaptive analysis model; send the elevator safety risk adaptive analysis model to the elevator operation control center to perform elevator safety risk adaptive analysis.

[0009] Preferably, step S1 includes the following steps:

[0010] Step S11: Obtain the elevator historical operation log and the elevator operation logic code;

[0011] Step S12: Clean the elevator historical operation logs to obtain the cleaned elevator historical operation logs;

[0012] Step S13: Extract misoperation behaviors from the cleaned elevator historical operation logs to obtain elevator historical misoperation behaviors;

[0013] Step S14: Map the misoperation code execution units to the elevator operation logic code according to the elevator historical misoperation behaviors to obtain misoperation code execution units.

[0014] Preferably, step S2 includes the following steps:

[0015] Step S21: Identify abnormal speed change behaviors in the elevator historical misoperation behaviors to obtain elevator abnormal speed change behaviors;

[0016] Step S22: Analyze the speed change risk factors based on the elevator abnormal speed change behaviors and the cleaned elevator historical operation logs to obtain elevator speed change risk factors;

[0017] Step S23: Analyze the abnormal speed change code logic for the misoperation code execution units based on the elevator speed change risk factors to obtain abnormal speed change code logic data;

[0018] Step S24: Trace back the trigger conditions for the abnormal speed change code logic data to obtain abnormal speed change trigger condition data.

[0019] Preferably, step S22 includes the following steps:

[0020] Step S221: Extract the load and passenger density from the cleaned elevator historical operation logs to obtain elevator load data and elevator passenger density data;

[0021] Step S222: Analyze the speed change jerks and fluctuations of the elevator abnormal speed change behaviors to obtain elevator speed change jerk and fluctuation data;

[0022] Step S223: Estimate the dynamic changes of upward / downward inertial gravity for the elevator load data and elevator passenger density data based on the elevator speed change jerk and fluctuation data to obtain upward / downward inertial gravity change data;

[0023] Step S224: Obtain the wire traction material data of the elevator traction sheave;

[0024] Step S225: Quantify the indirect tension imbalance of the wire traction material data based on the upward / downward inertial gravity change data to obtain traction indirect tension imbalance data;

[0025] Step S226: Analyze the speed change risk factors for the elevator speed change jerk and fluctuation data based on the traction indirect tension imbalance data to obtain elevator speed change risk factors.

[0026] Preferably, step S23 includes the following steps:

[0027] Step S231: Locate the abnormal speed change code for the misoperation code execution unit based on the elevator speed change risk factor to obtain the abnormal speed change code;

[0028] Step S232: Perform syntax reverse engineering analysis on the abnormal speed change code to obtain the syntax analysis data of the abnormal speed change code;

[0029] Step S233: Analyze the setting of the abnormal speed change loop condition for the syntax analysis data of the abnormal speed change code to obtain the abnormal speed change loop setting condition;

[0030] Step S234: Perform variable parameter overflow control analysis on the syntax analysis data of the abnormal speed change code according to the abnormal speed change loop setting condition to obtain the variable parameter overflow control data;

[0031] Step S235: Perform function exception throwing analysis based on the abnormal speed change loop setting condition and the variable parameter overflow control data to obtain the function exception throwing data;

[0032] Step S236: Perform abnormal speed change code logic analysis on the abnormal speed change code based on the abnormal speed change loop setting condition, the variable parameter overflow control data, and the function exception throwing data to obtain the abnormal speed change code logic data.

[0033] Preferably, step S3 includes the following steps:

[0034] Step S31: Normalize the abnormal speed change trigger condition data to obtain the normalized abnormal speed change trigger condition data;

[0035] Step S32: Perform linkage analysis of potential risk code segments on the abnormal speed change code logic data based on the normalized abnormal speed change trigger condition data to obtain the potential risk code segment linkage data;

[0036] Step S33: Construct a causal relationship network for the abnormal speed change code logic data according to the potential risk code segment linkage data to obtain the potential risk causal relationship network.

[0037] Preferably, step S4 includes the following steps:

[0038] Step S41: Analyze the risk characteristics of the potential risk causal relationship network to obtain the potential risk causal characteristic relationship network;

[0039] Step S42: Assign weights to the risk causal relationships of the potential risk causal characteristic relationship network to obtain the potential risk relationship weight relationship network;

[0040] Step S43: Based on the random forest algorithm, construct an elevator safety risk adaptive analysis model for the potential risk relationship weight network, and obtain the elevator safety risk adaptive analysis model; send the elevator safety risk adaptive analysis model to the elevator operation control center to perform elevator safety risk adaptive analysis.

[0041] Preferably, the present invention also provides an elevator safety risk adaptive analysis system for performing the elevator safety risk adaptive analysis method as described above. The elevator safety risk adaptive analysis system includes:

[0042] A misoperation code mapping module, configured to obtain the elevator historical operation log and the elevator operation logic code; map the elevator operation logic code to the misoperation code execution unit according to the elevator historical operation log to obtain the misoperation code execution unit;

[0043] A trigger condition backtracking module, configured to perform abnormal speed change code logic parsing on the misoperation code execution unit to obtain abnormal speed change code logic data; perform trigger condition backtracking on the abnormal speed change code logic data to obtain abnormal speed change trigger condition data;

[0044] A causal relationship network construction module, configured to perform potential risk code segment linkage analysis based on the abnormal speed change trigger condition data to obtain potential risk code segment linkage data; construct a causal relationship network according to the potential risk code segment linkage data to obtain a potential risk causal relationship network;

[0045] An adaptive analysis model construction module, configured to construct an elevator safety risk adaptive analysis model for the potential risk causal relationship network based on the random forest algorithm to obtain the elevator safety risk adaptive analysis model; send the elevator safety risk adaptive analysis model to the elevator operation control center to perform elevator safety risk adaptive analysis.

[0046] The beneficial effects of the present invention are as follows. First, by obtaining the historical operation logs of the elevator, it is possible to deeply understand the operation status of the elevator during actual use, including records of normal operation and abnormal operation. At the same time, by comparing and analyzing these historical data with the operation logic code of the elevator, it is possible to identify the malfunctioning code execution units. Through this mapping relationship, we can reveal which operation logics lead to improper or malfunctioning operations of the elevator, and provide basic data for subsequent optimization and fault analysis, providing important evidence for the stability and safety of the elevator. After identifying the malfunctioning code, the next step is to analyze the logic of the abnormal speed change code. This process helps to analyze the abnormal speed change phenomenon during operation and further obtain the logic data of the abnormal speed change code. These data will be used to trace back the triggering conditions and understand under what circumstances the elevator experiences abnormal speed changes. By deeply exploring these triggering conditions, it is possible to better understand the logic behind the elevator's behavior and provide data support for subsequent risk prediction and improvement measures, thereby improving the safety and reliability of the elevator. After obtaining the data on the triggering conditions for abnormal speed changes, this step will conduct a linkage analysis of potential risk code segments around these data. By analyzing the relationships between various code segments, it is possible to identify potential risks within the system and their interrelationships. In addition, the construction of a causal relationship network can provide us with a more comprehensive perspective to observe how various code segments interact with each other and the potential safety hazards caused under specific conditions. Such analysis not only helps to understand the current safety status of the elevator, but also provides data basis for future risk prediction, helping relevant technical teams to take measures in advance to avoid risks. Finally, based on the constructed causal relationship network of potential risks, a random forest algorithm is used to build a model to achieve adaptive analysis of elevator safety risks. The application of this machine learning technology can provide a more intelligent solution for elevator safety management. By creating an adaptive analysis model for elevator safety risks, it is possible to monitor and evaluate the operation status of the elevator in real time, and timely feedback the analysis results to the elevator operation control center, enabling the operator to obtain risk warning information in a timely manner. Such implementation not only improves the efficiency of elevator safety monitoring, but also makes elevator management more systematic and intelligent, further protecting the lives of passengers. Therefore, the present invention is an optimized treatment of a traditional method for adaptive analysis of elevator safety risks, solving the problem of large errors in the cause analysis of elevator abnormal speed change control in the traditional method for adaptive analysis of elevator safety risks, resulting in low accuracy in elevator safety risk analysis, reducing the error in the cause analysis of elevator abnormal speed change control, and improving the accuracy of elevator safety risk analysis. Brief Description of the Drawings

[0047] Figure 1 It is a schematic diagram of the step flow of a method for adaptive analysis of elevator safety risks;

[0048] Figure 2 For Figure 1 the detailed implementation step flow diagram of step S2 in

[0049] Figure 3 For Figure 1 the detailed implementation step flow diagram of step S3 in Specific implementation manner

[0050] Please refer to Figures 1 to 3 , an elevator safety risk adaptive analysis method, the method includes the following steps:

[0051] Step S1: Obtain the elevator historical operation log and the elevator operation logic code; perform misoperation code execution unit mapping on the elevator operation logic code according to the elevator historical operation log to obtain the misoperation code execution unit;

[0052] Step S2: Perform abnormal speed change code logic parsing on the misoperation code execution unit to obtain abnormal speed change code logic data; perform trigger condition backtracking on the abnormal speed change code logic data to obtain abnormal speed change trigger condition data;

[0053] Step S3: Perform potential risk code segment linkage analysis based on the abnormal speed change trigger condition data to obtain potential risk code segment linkage data; construct a causal relationship network according to the potential risk code segment linkage data to obtain a potential risk causal relationship network;

[0054] Step S4: Construct an elevator safety risk adaptive analysis model based on the random forest algorithm for the potential risk causal relationship network to obtain an elevator safety risk adaptive analysis model; send the elevator safety risk adaptive analysis model to the elevator operation control center to perform elevator safety risk adaptive analysis.

[0055] In the embodiment of the present invention, referring to Figure 1 as described above, it is the step flow diagram of an elevator safety risk adaptive analysis method of the present invention. In this example, the elevator safety risk adaptive analysis method includes the following steps:

[0056] Step S1: Obtain the elevator historical operation log and the elevator operation logic code; perform misoperation code execution unit mapping on the elevator operation logic code according to the elevator historical operation log to obtain the misoperation code execution unit;

[0057] In the embodiments of the present invention, first, the historical operation logs of the elevator and the operation logic code of the elevator are obtained. The elevator historical operation logs are recorded by the elevator control system or relevant sensors and contain various operation data of the elevator in different time periods, including up and down floors, operation speed, load, passenger density, etc. After obtaining these historical operation logs, it is necessary to analyze the operation logic code of the elevator. The elevator operation logic code is generally the instruction code run by the elevator controller, and these instructions determine the specific operation mode of the elevator. The operation logic code of the elevator usually includes various state switches, floor control, speed control, fault handling, etc. Next, by analyzing the elevator historical operation logs, the misoperation behaviors recorded in the logs are mapped to the elevator operation logic code, and the misoperations in the elevator history are associated with the corresponding code execution units. The misoperation code execution unit usually refers to the control instruction segment or code unit triggered in a certain specific operation scenario. Specifically, first, the misoperation behaviors are extracted from the elevator historical operation logs to identify misoperations or abnormal operation behaviors, such as inaccurate floor stops of the elevator, abnormal acceleration and deceleration, etc. Then, based on these misoperation behaviors, they are corresponded to the elevator operation logic code and mapped to the corresponding code segments. The core of this process is to locate the code execution unit that causes the misoperation by comparing various abnormal behaviors in the elevator historical operation logs with the operation steps in the elevator program code.

[0058] Step S2: Analyze the abnormal speed change code logic of the misoperation code execution unit to obtain the abnormal speed change code logic data; trace back the trigger conditions of the abnormal speed change code logic data to obtain the abnormal speed change trigger condition data;

[0059] In the embodiments of the present invention, first, the abnormal speed change code logic of the malfunction code execution unit is parsed. Speed change abnormality refers to the abnormal phenomena that occur during the acceleration and deceleration processes of the elevator, such as sudden acceleration, uneven acceleration or deceleration, or sudden acceleration. These abnormal speed change behaviors are caused by hardware failures, software logic errors, or external interferences of the elevator. Therefore, at this stage, first, by analyzing the code segments related to speed change in the malfunction code execution unit, the logic code causing the abnormal speed change is found, such as functions and control instructions related to speed regulation, acceleration, and deceleration. After obtaining the code related to the abnormal speed change, the trigger condition of the abnormal speed change code logic is further traced back to find the specific conditions that trigger the abnormal speed change. For example, it will be found that certain inappropriate sensor input data, external load changes, and the current operating state of the elevator (such as high load state) and other factors cause the elevator to have an abnormal speed change. The core method of trigger condition tracing is to reverse calculate the specific time and conditions when the abnormal speed change occurs based on the cleaned log of the elevator's historical operation, and match the relevant parameters (such as the current load, speed, floor, etc. of the elevator) in the historical log with the relevant trigger conditions in the control code to obtain the trigger condition data of the abnormal speed change.

[0060] Step S3: Based on the abnormal speed change trigger condition data, perform a linkage analysis of the potential risk code segments to obtain the potential risk code segment linkage data; construct a causal relationship network according to the potential risk code segment linkage data to obtain the potential risk causal relationship network;

[0061] In the embodiments of the present invention, first, potential risk code segment linkage analysis is performed using abnormal speed change trigger condition data. The purpose of the linkage analysis is to identify which code segments or modules interact with each other under the trigger conditions of abnormal speed change during the operation of the elevator, thereby causing other potential risks to the elevator. During the implementation process, first, the trigger condition data of abnormal speed change is extracted from the elevator control system, including a series of relevant parameters such as the speed, load, and running time of the elevator. To perform effective linkage analysis on this data, a linkage analysis model based on graph theory is constructed, where each code segment or module is used as a node in the graph, and the mutual relationships and data transmission between the code segments are used as the edges in the graph. Then, based on the abnormal speed change trigger condition data, the linkage relationships between various modules are checked when a specific abnormal speed change occurs. By calculating the similarity or dependency relationships of different code segments, it is identified which code segments have a linkage effect, and then the potential risk code segment linkage data is obtained. Specifically, using data flow analysis technology, by examining the execution order of each code module during the abnormal speed change and the data interaction between them, a linkage analysis model is constructed. This process can calculate the data flow dependencies and function call graphs between code segments through algorithms, thereby analyzing the existing potential risk linkage paths. Finally, based on the results of the linkage analysis, a causal relationship network is constructed, which can accurately describe the causal impacts between various modules of the elevator, facilitating further assessment of the risk sources and their extended impacts.

[0062] Step S4: Based on the random forest algorithm, construct an elevator safety risk adaptive analysis model for the potential risk causal relationship network to obtain the elevator safety risk adaptive analysis model; send the elevator safety risk adaptive analysis model to the elevator operation control center to perform the elevator safety risk adaptive analysis.

[0063] In the embodiments of the present invention, based on the constructed causal relationship network of potential risks, a random forest algorithm is used to establish an adaptive analysis model for elevator safety risks. First, each node in the causal relationship network is regarded as a feature, representing various potential risks or abnormal events that occur during the operation of the elevator. The features of the nodes can include the operating state of the elevator, abnormal speed change, load information, external interference, etc. Subsequently, these features are combined with the data in the elevator historical operation log to construct a training data set. Each training sample contains the feature data at different time points and whether a safety risk event (such as a fault, accident, etc.) occurred at that time point. In order to train the random forest model, data preprocessing is required, including data standardization and missing value processing, to ensure the data quality. The random forest algorithm classifies and regresses by constructing multiple decision trees, and each decision tree is trained by randomly selecting a subset of the training data and a subset of the features. The training process calculates the error rate of each tree and synthesizes the final prediction result through a voting mechanism or an average value. For the elevator safety risk analysis problem, each tree will judge whether there is a potential safety risk according to different combinations of features. After the model training is completed, the trained random forest model is applied to the elevator operation control center to monitor the operation state of the elevator in real time. Specifically, the elevator operation control system will collect the operation data of the elevator (such as floor, speed, load, etc.) in real time and input it into the trained random forest model for prediction. The output of the model will be the safety risk assessment result of the elevator in the current state, and the control center will take corresponding adjustment measures according to this result, such as alarm notification, stopping the elevator operation, etc.

[0064] Step S1 includes the following steps:

[0065] Step S11: Obtain the elevator historical operation log and the elevator operation logic code;

[0066] Step S12: Clean the data of the elevator historical operation log to obtain the cleaned elevator historical operation log;

[0067] Step S13: Extract the misoperation behaviors from the cleaned elevator historical operation log to obtain the elevator historical misoperation behaviors;

[0068] Step S14: Map the misoperation code execution units to the elevator operation logic code according to the elevator historical misoperation behaviors to obtain the misoperation code execution units.

[0069] In the embodiments of the present invention, first, the historical operation log and operation logic code of the elevator are obtained from the elevator control system. The elevator historical operation log records all the operation data generated during the past operation of the elevator. These data usually include each start, stop, acceleration, deceleration, floor stop, load condition, door open / close state, fault alarm information, etc. of the elevator. The operation log is generally stored in the database of the elevator control system in a time series manner, and the format is usually CSV or database table format. The elevator operation logic code is the source code for writing the elevator control system program. These codes define the operation rules, scheduling algorithms, variable speed control strategies, fault detection and response strategies, etc. of the elevator. The elevator control system manages various behaviors of the elevator through these codes, such as determining how the elevator starts and how to stop at different floors. At this time, the way to obtain the elevator historical operation log is usually to extract the required historical data from the log table through database query statements, and the elevator operation logic code can extract the source code or compiled control instructions from the elevator programming and development environment. First, data cleaning is performed on the obtained elevator historical operation log. The goal of data cleaning is to remove the error data and irrelevant data in the original log, so that the log data can be more effectively used for subsequent analysis and processing. The cleaning process includes several steps: First, check the data integrity and identify and repair missing values or blank values. The methods for handling missing values include filling in the missing values or deleting the records containing missing values. Second, check the format and type of the data to ensure that the format of all data meets the expectations (for example, the timestamp field should be in the date and time format, and the speed field should be in the numerical type). Next, detect and process outliers. Identify the values that exceed the normal range through statistical methods (such as the box plot method or the 3σ principle), and correct or delete them according to the specific situation. In addition, check for duplicate records in the log. Especially when the elevator fails or restarts, duplicate data will be generated, and duplicate removal processing is required. After the above data cleaning, the obtained elevator historical operation cleaning log can be used for subsequent analysis and modeling. Extract misoperation behaviors from the elevator historical operation cleaning log. Misoperation behaviors refer to abnormal behaviors of the elevator during operation due to factors such as control logic errors, hardware failures, or external interferences. For example, the elevator accelerates or decelerates abnormally without clear instructions, or stops at the wrong floor. In order to extract these misoperation behaviors, first, the criteria for abnormal behaviors need to be defined. For example, when the elevator is accelerating, if the speed change exceeds a predetermined range, or the stop time at a specific floor is abnormal, it can be regarded as a misoperation behavior. Misoperation behavior extraction can be achieved by writing a rule engine to identify these abnormal situations in the log. The specific operation is to compare based on the data such as speed, floor, time, acceleration, etc. in the log using the set threshold rules (such as the speed fluctuation range, floor error threshold, etc.). When the data exceeds the threshold, record this behavior as a misoperation.In addition, machine learning algorithms, such as anomaly detection algorithms (e.g., Isolation Forest algorithm or clustering-based algorithms), are used to further extract potential misoperation behaviors. These misoperation behavior data can help identify potential problems in the elevator operation logic subsequently. Based on the elevator historical misoperation behaviors, a misoperation code execution unit mapping is performed on the elevator operation logic code. The purpose of the misoperation code execution unit mapping is to associate the identified misoperation behaviors with specific code modules in the elevator control system and find out the specific code segments that cause these misoperations. In this step, first, a static analysis of the elevator operation logic code is required to identify key modules that control elevator behaviors, such as the acceleration control module, parking control module, floor scheduling module, etc. Through static analysis, the functions and operating conditions of these modules can be extracted. Then, according to the elevator historical misoperation behaviors extracted in the previous steps, the triggering conditions of these behaviors in the elevator control logic are searched. For example, a certain misoperation behavior is related to the parameter settings of the elevator's acceleration control module or the floor stopping rules under a specific condition. To establish the mapping relationship, a one-by-one comparison of the elevator historical misoperation behaviors and the operation logic code is needed to determine which specific code execution units (such as function calls, conditional judgments, etc.) are directly associated with the misoperation behaviors. The mapping process can be completed by writing code mapping rules, analyzing the event logs and anomaly behavior triggering conditions of the elevator control system, and combining manual analysis with automated tools (such as static code analysis tools). Finally, the obtained misoperation code execution units refer to specific code segments or modules that are prone to cause misoperation behaviors when running in the elevator control system and become the focus of subsequent analysis and optimization.

[0070] Step S2 includes the following steps:

[0071] Step S21: Identify variable-speed abnormal behaviors from the elevator historical misoperation behaviors to obtain elevator variable-speed abnormal behaviors;

[0072] Step S22: Analyze the variable-speed risk factors based on the elevator variable-speed abnormal behaviors and the elevator historical operation cleaning logs to obtain elevator variable-speed risk factors;

[0073] Step S23: Perform abnormal variable-speed code logic analysis on the misoperation code execution unit based on the elevator variable-speed risk factors to obtain abnormal variable-speed code logic data;

[0074] Step S24: Trace back the triggering conditions for the abnormal variable-speed code logic data to obtain abnormal variable-speed triggering condition data.

[0075] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0076] Step S21: Identify abnormal speed change behaviors in the elevator's historical misoperation behaviors to obtain elevator abnormal speed change behaviors;

[0077] In the embodiments of the present invention, first, identify abnormal speed change behaviors in the elevator's historical misoperation behaviors. Abnormal speed change behaviors refer to the acceleration and deceleration phenomena that do not conform to the predetermined operation logic during the elevator's operation, such as the elevator accelerating too fast or decelerating too slowly. By analyzing the log of the elevator's historical misoperation behaviors, first identify the acceleration, speed, and position data during the elevator's operation. Combining with the elevator operation specifications, determine which acceleration or deceleration behaviors can be regarded as abnormal. For example, if the acceleration of the elevator at startup exceeds the designed maximum acceleration value, or the deceleration time is too long during the parking process, it can be marked as an abnormal speed change behavior. To achieve this identification, the technologies used include anomaly detection algorithms based on time series, specifically, clustering-based anomaly detection methods (such as the K-means clustering algorithm) or threshold-based methods. By monitoring the speed change and acceleration change data in the elevator operation log in real time, calculate the acceleration of the elevator in each cycle and compare it with the designed threshold. When the acceleration exceeds the set threshold, mark it as an abnormal speed change behavior, and record the time, acceleration, speed change, and other detailed information of this event for subsequent analysis.

[0078] Step S22: Analyze the speed change risk factors based on the elevator abnormal speed change behaviors and the elevator's historical operation cleaning log to obtain elevator speed change risk factors;

[0079] In the embodiments of the present invention, analyze the speed change risk factors based on the elevator abnormal speed change behaviors and the elevator's historical operation cleaning log to obtain elevator speed change risk factors. Speed change risk factors refer to the factors that affect the occurrence of elevator abnormal speed change behaviors, such as load, passenger density, floor difference, etc. First, based on the acceleration, deceleration, speed, and load data in the elevator's historical operation cleaning log, conduct a background analysis on each abnormal speed change behavior. By analyzing the performance of the elevator when operating between different loads and different floors, find out the factors that cause abnormal speed changes. For example, if the elevator has a high frequency of abnormal speed changes under high load, then the load is a key risk factor. Further, use statistical analysis methods (such as linear regression or correlation analysis) to calculate the correlation between each factor and the abnormal speed change behavior. The specific operation includes comparing each record of the abnormal speed change behavior in the elevator's historical operation cleaning log with the corresponding load, operation time, floor difference, and other data, and calculating the contribution degree of each factor to the abnormal speed change. These factors can be represented in a weighted manner, and the result obtained is the speed change risk factor. The analysis of the elevator speed change risk factor is helpful for subsequent risk assessment and control measure formulation.

[0080] Step S23: Based on the elevator speed change risk factors, perform abnormal speed change code logic analysis on the misoperation code execution unit to obtain abnormal speed change code logic data;

[0081] In the embodiment of the present invention, based on the elevator speed change risk factors, perform abnormal speed change code logic analysis on the misoperation code execution unit to obtain abnormal speed change code logic data. The purpose of the abnormal speed change code logic analysis is to find out the code units in the elevator control system that are related to the abnormal speed change behavior. Especially when the abnormal speed change behavior occurs, whether there are problems or defects in the elevator control logic. First, according to the analysis results of the speed change risk factors, select the risk factors with greater influence (such as load, speed change, etc.), and then map these factors to the corresponding control modules in the elevator operation logic. By analyzing the program logic in the elevator control system (for example, the elevator acceleration and deceleration control algorithm), find out the code segments related to the abnormal speed change behavior. The specific operation steps include: performing static code analysis on the elevator control code to identify functions or conditional statements related to variables such as speed, acceleration, and load. Then, according to the risk factor data, perform dynamic analysis on these code segments to check their execution in the actual operation of the elevator, and identify the logical defects or algorithmic inappropriateness that cause abnormal speed changes. For example, if the acceleration algorithm does not consider the change of the load factor, or the parameters of the deceleration algorithm are not adjusted under high load conditions, it will cause abnormal speed changes. Finally, through these analyses, obtain the abnormal speed change code logic data, including specific code modules, conditional judgments and other information.

[0082] Step S24: Perform trigger condition backtracking on the abnormal speed change code logic data to obtain abnormal speed change trigger condition data.

[0083] In the embodiments of the present invention, the trigger condition of the abnormal speed change code logic data is traced back to obtain the abnormal speed change trigger condition data. The purpose of trigger condition tracing is to find out the specific control conditions and triggering mechanisms that lead to abnormal speed change behavior. According to the abnormal speed change code logic data obtained in step S23, various control conditions during the elevator operation are traced back. For example, when the elevator starts, whether there is an incorrect acceleration instruction, or when the elevator decelerates, whether there is an inappropriate deceleration condition judgment. First, according to the acceleration or deceleration functions defined in the abnormal speed change code logic data, analyze the triggering timing and execution parameters of these functions under different conditions. By tracing back the relevant data (such as load, speed, acceleration, etc.) in the elevator historical operation cleaning log, judge in what specific situation the abnormal speed change behavior is triggered. For example, if the elevator starts under high load and the acceleration is too fast, it can be traced back to the judgment conditions in the acceleration function and it is found that there is a lack of dynamic adaptability to the load data. Further, the time series analysis method can be combined to trace back the acceleration and deceleration processes of the elevator, and analyze the specific reasons for triggering the abnormal speed change behavior at specific time nodes. Through these trace-back analyses, the abnormal speed change trigger condition data, including specific control parameters, triggering timing and other information, are obtained, providing a basis for subsequent optimization and adjustment.

[0084] Step S22 includes the following steps:

[0085] Step S221: Extract the load and passenger density from the elevator historical operation cleaning log to obtain the elevator load data and the elevator passenger density data;

[0086] Step S222: Conduct a speed change jerky fluctuation analysis on the abnormal elevator speed change behavior to obtain the elevator speed change jerky fluctuation data;

[0087] Step S223: Estimate the dynamic change of the ascending / descending inertial gravity based on the elevator speed change jerky fluctuation data for the elevator load data and the elevator passenger density data to obtain the ascending / descending inertial gravity change data;

[0088] Step S224: Obtain the steel wire traction material data of the elevator traction sheave;

[0089] Step S225: Quantify the indirect tension imbalance of the steel wire traction material data based on the ascending / descending inertial gravity change data to obtain the traction indirect tension imbalance data;

[0090] Step S226: Analyze the speed change risk factors of the elevator speed change jerky fluctuation data based on the traction indirect tension imbalance data to obtain the elevator speed change risk factors.

[0091] In the embodiment of the present invention, the load and population density of the elevator historical operation cleaning log are first extracted to obtain the elevator load data and the elevator population density data. The elevator historical operation cleaning log contains multiple important parameters during the elevator operation process, including information such as the operating speed, acceleration, number of floors, load, and population density in the elevator. First, by parsing the load-related fields in the elevator operation cleaning log, the load data of each elevator operation process is extracted. The load data can be obtained through the original signal provided by the elevator load sensor. Usually, the load sensor of the elevator will provide real-time data when the elevator is running, such as the load value at each start, the load value when reaching the target floor, etc. After filtering, denoising, etc., these data are processed to obtain an accurate load value. Then, the population density data is extracted from the log. The population density data is calculated based on the number of people in the elevator and the carrying capacity of the elevator. The change in population density is calculated by the ratio of the personnel counter in the elevator to the total load of the elevator. The specific operation includes extracting the data of the number of people getting on and off on each floor during each operation of the elevator, and calculating the population density in combination with the maximum load of the elevator. Finally, the load and population density data are sorted into a data set in chronological order for subsequent analysis. The speed change jerking fluctuation analysis is performed on the abnormal speed change behavior of the elevator to obtain the speed change jerking fluctuation data of the elevator. The speed change jerking fluctuation analysis aims to detect whether there is an abrupt speed change during the speed change process of the elevator, especially whether there is an unsteady or violent fluctuation during the acceleration or deceleration process. First, based on the speed and acceleration data in the historical operation cleaning log of the elevator, the original data is denoised using smoothing filtering technology (such as Savitzky-Golay filter) to remove short-term fluctuations caused by sensor noise or environmental interference. Next, the acceleration change rate of the elevator during acceleration and deceleration is calculated to identify the mutation point of speed or acceleration. The excessive change rate during acceleration or deceleration is the speed change jerking fluctuation. The stability during the acceleration process is judged by calculating the standard deviation of the elevator acceleration. When the standard deviation exceeds the set threshold, it can be determined as a speed change jerking fluctuation. Further, a fluctuation index (for example, defined as the ratio of the difference between the maximum acceleration and the minimum acceleration during the speed change process to the average acceleration) is used to quantify the speed change jerking fluctuation. The fluctuation data will be used as an indicator of speed change abnormality and input into the subsequent risk analysis. According to the elevator speed change and jerking fluctuation data, the elevator load data and the elevator population density data are used to estimate the dynamic changes of the rising / falling inertial gravity, and the rising / falling inertial gravity change data is obtained. The estimation of the dynamic changes of the rising / falling inertial gravity is based on the acceleration and speed changes of the elevator in the vertical direction, combined with the influence of load and population density, to analyze the inertial changes of the elevator during acceleration or deceleration. First, the elevator's acceleration sensor data is used to obtain the elevator's vertical acceleration, and the inertial force is calculated based on the elevator's mass (including changes in load and population density). The inertial force can be expressed by the following formula: ,in, is the inertial force, is the mass of the elevator (including data on load and passenger density), is the acceleration. On this basis, by combining the acceleration data of the elevator during the upward and downward processes, the inertial changes during the upward and downward processes are calculated. For example, during the upward movement of the elevator, the mass of the elevator is affected by gravity, so the change in inertial force depends on the magnitude and direction of the acceleration. During the downward movement, the inertial force is jointly affected by the load and the mass of the elevator itself. Therefore, the change in the inertial force of the elevator shows certain dynamic characteristics. By combining the change factors of the load and the passenger density with the acceleration and speed changes of the elevator, the change in the inertial force during the upward and downward processes can be estimated, and the upward / downward inertial gravity change data can be obtained. This data can provide a basis for subsequent traction force analysis. Obtain the wire traction material data of the elevator traction sheave. As an important part of the elevator power system, the quality and characteristics of the wire traction material of the traction sheave are crucial for the safe operation of the elevator. First, detailed data on the wire traction material used in the elevator need to be obtained, including the material of the wire (such as the strength and wear resistance of the wire), diameter, manufacturing process, traction capacity, etc. Extract relevant traction material information through the elevator maintenance records or the material specification sheets provided by the equipment. The tension-bearing capacity of the wire is crucial for the safe operation of the elevator. Therefore, obtaining this data helps analyze whether there is a problem of insufficient traction force in the elevator under different loads and speed changes. The traction material data can be obtained from the technical documents provided by the elevator manufacturer or the maintenance unit and distinguished in detail according to the elevator model. Indirect tension imbalance quantification is performed on the wire traction material data based on the upward / downward inertial gravity change data to obtain the traction indirect tension imbalance data. Traction indirect tension imbalance refers to the uneven distribution of tension in the traction system during the operation of the elevator due to the uneven inertial force caused by variable-speed jerks or the aging of the wire traction material. To quantify this imbalance, first, based on the upward / downward inertial gravity change data in step S223 and combined with the characteristics of the wire, calculate the tension distribution in the traction system during the operation of the elevator. By analyzing the acceleration and speed data at each moment during the operation of the elevator, estimate the traction force change between different floors and consider the tension limit of the wire. The specific calculation method is as follows: During the acceleration and deceleration of the elevator, calculate the traction force requirement at each moment and compare it with the maximum bearing tension of the elevator wire. If the traction force exceeds the maximum bearing capacity of the wire, tension imbalance occurs. Finally, obtain the traction indirect tension imbalance data as an important indicator of the safe operation of the elevator. Analyze the variable-speed risk factors of the elevator variable-speed jerk fluctuation data based on the traction indirect tension imbalance data to obtain the elevator variable-speed risk factors. The purpose of analyzing the variable-speed risk factors is to find out the root cause of the abnormal variable-speed behavior of the elevator and link it with the traction force imbalance. First, through the correlation analysis of the traction indirect tension imbalance data and the variable-speed jerk fluctuation data, identify the impact of the traction force imbalance on the jerk fluctuation during the acceleration and deceleration of the elevator.By tracing the acceleration and deceleration behaviors between different floors, it is found that traction imbalance causes abnormal speed changes of the elevator under certain specific conditions. After combining the traction imbalance with the speed change fluctuation data, risk factor analysis methods (such as principal component analysis or regression analysis) are used to obtain the speed change risk factors. These risk factors can help identify high-risk conditions for abnormal elevator speed changes and provide guidance for subsequent elevator safety control.

[0092] Step S225 includes the following steps:

[0093] Perform inertial gravity time series incremental difference processing on the ascending / descending inertial gravity change data to obtain inertial gravity time series incremental difference data;

[0094] Based on the inertial gravity time series incremental difference data, conduct instantaneous gravity tensile load assessment on the wire traction material data to obtain material instantaneous gravity tensile load data;

[0095] Based on the material instantaneous gravity tensile load data, perform discontinuous inertial gravity similarity interval restriction to obtain the gravity tensile discontinuous similarity interval;

[0096] According to the Simpson integration method and the gravity tensile discontinuous similarity interval, perform tensile load segmented constraint integration on the material instantaneous gravity tensile load data to obtain tensile load segmented integration data;

[0097] Based on the tensile load segmented integration data, conduct indirect tension imbalance quantification on the wire traction material data to obtain traction indirect tension imbalance data.

[0098] In the embodiment of the present invention, first, inertial gravity time series incremental difference processing is performed on the ascending / descending inertial gravity change data. The inertial gravity time series incremental difference processing eliminates the trend changes and low-frequency noise in the gravity change data by performing difference operations on consecutive moments of the gravity change data, thereby highlighting more subtle instantaneous changes. Specifically, for the inertial gravity data at each moment , perform incremental difference processing calculation to obtain difference data , where is the inertial gravity value at moment . In this way, the obtained incremental difference data can be used to capture the tiny and rapidly changing gravity changes during the elevator operation, which are crucial for the safety of the elevator system. Next, based on the inertial gravity time series incremental difference data, perform instantaneous gravity tensile load assessment on the wire traction material. In this step, calculate the tensile load capacity of the wire traction material under instantaneous changes according to the gravity changes experienced by the elevator during ascending or descending. The tensile load assessment formula is as follows: , where Denote the instantaneous tensile force (bearing capacity) of the wire traction material at time t, that is, the tensile force borne by the wire material at this moment. Denote the differential data of the inertial gravity increment at time t, which reflects the instantaneous change of gravity during the operation of the elevator. Denote the mass of the elevator, that is, the total weight of the elevator. Denote the cross-sectional area of the wire, usually in square millimeters or square meters. It determines the stress distribution of the wire when bearing tensile force. Reflects the gravity change. Through this evaluation, the bearing capacity of the wire traction material at each instantaneous moment during the operation of the elevator can be accurately predicted, avoiding safety problems caused by overloading and stretching. Then, based on the instantaneous gravity tensile bearing data of the material, the restriction of the discontinuous inertial gravity similarity interval is carried out to obtain the discontinuous gravity tensile similarity interval. In this step, by analyzing the instantaneous gravity tensile bearing data, the discontinuous inertial gravity change mode that occurs in the elevator during certain specific time periods is judged. These discontinuous changes are usually caused by factors such as elevator load changes, people getting on and off the elevator, or the opening and closing of elevator doors. By extracting these specific interval data, they can be regarded as potential abnormal fluctuation intervals. These intervals usually show mutations or violent fluctuations in the gravity change graph. Then, according to the Simpson integral method and the discontinuous gravity tensile similarity interval, the tensile bearing piecewise constraint integral of the material instantaneous gravity tensile bearing data is carried out. The Simpson integral method is a common numerical integration method, suitable for calculating the area under an irregular curve. In this step, the gravity tensile data is piecewise integrated by the Simpson integral method, and the specific calculation formula is as follows: , where Denote within the interval the integral of the function , usually used to calculate the cumulative value of a certain physical quantity (such as bearing capacity, force, etc.) within a certain interval. Denote the starting and ending points of the integration interval, that is, the upper and lower bounds of the interval. h represents the small interval length of each interval, and the calculation method is , where n is the number of small segments divided within this interval. Denote the function to be integrated, which is the instantaneous gravity tensile bearing data or other functions reflecting the behavior of the elevator here. Through this method, the cumulative tensile load of the wire traction material within each discontinuous gravity change interval can be obtained. This result is crucial for analyzing the performance of the elevator under specific loads.

[0099] Finally, based on the stretching load segmented integration data, the indirect tension imbalance of the wire traction material data is quantified to obtain the traction indirect tension imbalance data. This step combines the stretching load segmented integration results with the physical properties of the wire traction material (such as the elastic modulus and yield strength of the material) to quantify the tension imbalance in the traction system. The specific calculation method is to compare the stretching load in each integration interval with the theoretical load-bearing limit of the material, thereby obtaining the tension imbalance degree. The formula for the traction indirect tension imbalance data is expressed as: , where represents the tension imbalance degree in the elevator traction system, which quantifies the degree of tension imbalance of the wire traction material during the operation of the elevator. The larger this value, the more serious the imbalance in the traction system. represents the stretching load data in the i-th time period, reflecting the stretching force borne by the wire traction material during the operation of the elevator in each time period. represents the maximum load-bearing capacity of the wire traction material, that is, the maximum tensile force that the wire can withstand, usually the physical limit value of the material. represents the summation over all time periods i to calculate the total tension imbalance. Each Fi corresponds to the stretching load data in a specific time period. The existence of tension imbalance leads to abnormal fluctuations during the operation of the elevator system, which in turn affects the safety of the elevator. By quantifying this data, reliable input can be provided for subsequent risk analysis. The above steps finally obtain the traction indirect tension imbalance data, which are used to further analyze the abnormal speed change and safety risks that occur during the operation of the elevator system, and help to realize the adaptive analysis and prediction of elevator safety risks.

[0100] Step S23 includes the following steps:

[0101] Step S231: Based on the elevator speed change risk factor, locate the speed change risk abnormal code for the malfunction code execution unit to obtain the speed change risk abnormal code;

[0102] Step S232: Perform syntax reverse engineering parsing on the speed change risk abnormal code to obtain the speed change abnormal code syntax parsing data;

[0103] Step S233: Analyze the speed change abnormal loop condition setting for the speed change abnormal code syntax parsing data to obtain the speed change abnormal loop setting condition;

[0104] Step S234: According to the speed change abnormal loop setting condition, perform variable parameter overflow control parsing on the speed change abnormal code syntax parsing data to obtain the variable parameter overflow control data;

[0105] Step S235: Based on the speed change abnormal loop setting condition and the variable parameter overflow control data, perform function abnormal throw analysis to obtain the function abnormal throw data;

[0106] Step S236: Based on the variable speed abnormal loop setting conditions, variable parameter overflow control data, and function abnormal throw data, perform abnormal variable speed code logic analysis on the variable speed risk abnormal code to obtain abnormal variable speed code logic data.

[0107] In the embodiments of the present invention, first, the misoperation code execution unit is analyzed and located using the value of the elevator speed change risk factor. The elevator speed change risk factor is obtained from the real-time monitoring data of the inertial force, load state, and operation mode of the elevator during the speed change process. These data include the elevator's acceleration, speed change, and the load condition of the wire traction system. During the analysis process, the speed change risk factor is mapped to different parts of the elevator's operation logic code, especially the code lines related to speed change and acceleration / deceleration control logic. By matching the elevator operation state with the control logic, the logic unit causing the speed change abnormality is identified. The specific operation is to compare the historical speed change abnormal behaviors line by line with the corresponding function calls, judgment conditions, etc. in the elevator control logic code to accurately locate the speed change control module with potential risks, and finally obtain the speed change risk abnormal code. The location process uses a rule matching method based on data mining and cross-verifies in combination with the timing characteristics of the abnormal data to ensure the accurate identification of the abnormal code. Reverse engineering analysis is performed on the speed change risk abnormal code located in step S231. The specific implementation is to perform syntax analysis on the abnormal code through decompilation technology and reverse deduce its source code structure. The key to reverse engineering is to restore the corresponding high-level language code by parsing assembly code, machine code, or bytecode. First, a static analysis tool is used to extract the control flow graph and data flow graph of the target code, and analyze the execution path, function call relationship, and conditional judgment statements of the program. Then, a syntax parsing algorithm (such as recursive descent parsing, LL(1) grammar parsing, etc.) is used to restore the target code into an abstract syntax tree (AST), so as to extract the logical structure, loop body, conditional statements, function calls, and other components in the code. Finally, according to the restored syntax information, syntax parsing data of the speed change abnormal code is generated, including variables, constants, control statements, and their relationships, providing a basis for subsequent logical analysis. By further analyzing the syntax parsing data of the speed change abnormal code, the loop structure and its conditions involved in the speed change operation are identified. First, the loop structures (such as for, while, do-while, etc.) in the speed change abnormal code are extracted, and the start condition, loop body, and termination condition of each loop are analyzed. The loop body part affecting the speed change process is analyzed with emphasis, especially the logic controlling operations such as acceleration, deceleration, and stopping. During the analysis process, in combination with the actual speed change requirements of the elevator, the key variables in the loop condition are determined, such as whether the elevator's speed, position, acceleration, etc. are subject to unreasonable restrictions or trigger conditions. For example, if there are acceleration thresholds or deceleration rates that are not reasonably verified in the loop condition, these will cause the elevator to have speed change abnormalities under specific conditions. By using a static analysis tool to detect and simulate the performance of the loop condition under different input parameters, the setting conditions of the speed change abnormal loop are finally extracted. Analyze the variables of the speed change abnormal code, especially check the control mechanism for parameter overflow.First, identify the key variables in the abnormal speed change code that control acceleration, deceleration, position, and speed. These variables are affected by the boundary values of the input data. Through static data flow analysis, trace the passing process of these variables in the code and detect whether their values are affected by the limit values of external inputs or internal calculations, especially important parameters such as acceleration thresholds, braking torques, and wire traction forces. Subsequently, analyze the overflow protection measures (such as range checks, overflow detections, etc.) in the code to determine whether there are overflow vulnerabilities. For unhandled overflow problems, use symbolic execution methods to simulate the changes in variable values under different input conditions and detect whether there are abnormal behaviors caused by overflows, such as unlimited acceleration or deceleration. Finally, based on the detection results of the overflow control mechanism, obtain the overflow control data for variable parameters and identify the links in the code that cause overflows. Based on the abnormal speed change loop setting conditions and the overflow control data for variable parameters, further analyze the function exception throwing logic in the code. First, in the abnormal speed change code, locate all functions related to speed change operations, especially functions involving operations such as acceleration, deceleration, and stop. Analyze the error handling mechanisms of these functions, such as whether they throw exceptions or perform error handling when the input parameters are illegal or the calculations exceed the predetermined range. Combining the loop setting conditions and overflow control data analyzed in steps S233 and S234, check whether there are cases where exceptions thrown due to improper loop conditions or variable overflows are not captured in a timely manner. Use static code analysis tools to simulate input scenarios and detect whether the functions can throw corresponding errors or perform protective measures in abnormal situations. Finally, based on these exception throwing analyses, generate function exception throwing data, indicating under what circumstances the abnormal code will trigger uncontrollable speed change problems. Based on the results of the above-mentioned analyses, conduct an overall logical analysis of the abnormal speed change risk code. According to the abnormal speed change loop setting conditions, the overflow control data for variable parameters, and the function exception throwing data, systematically analyze the execution logic of the abnormal speed change risk code. Specifically, first, based on the condition judgments and overflow controls analyzed previously, re-examine each logical node in the code, analyze its performance under different input conditions, and identify potential risk points. Then, combined with the exception throwing analysis data, check whether there are scenarios where abnormal speed changes are caused because exceptions are not captured in a timely manner. Finally, by merging all relevant analysis results, obtain the complete logical data of the abnormal speed change code, including the logical associations of all speed change operations, control conditions, overflow controls, error throwing, etc., forming the complete analysis data of the elevator speed change risk, providing a basis for subsequent risk assessment and correction.

[0108] Step S3 includes the following steps:

[0109] Step S31: Normalize the abnormal speed change trigger condition data to obtain the normalized abnormal speed change trigger condition data;

[0110] Step S32: Perform a linkage analysis of potential risk code segments on the abnormal speed change code logic data based on the normalized data of the abnormal speed change trigger conditions to obtain potential risk code segment linkage data;

[0111] Step S33: Construct a causal relationship network for the abnormal speed change code logic data based on the potential risk code segment linkage data to obtain a potential risk causal relationship network.

[0112] As an example of the present invention, refer to Figure 3 As shown, in this example, the said Step S3 includes:

[0113] Step S31: Normalize the abnormal speed change trigger condition data to obtain normalized abnormal speed change trigger condition data;

[0114] In the embodiment of the present invention, first, the abnormal speed change trigger condition data is normalized to eliminate the differences between different data dimensions, make it on a unified scale, and facilitate subsequent analysis. The normalization process is carried out by converting the original data into the range of [0,1]. The common methods used in this process are min-max normalization or Z-score standardization. Specifically, for each piece of abnormal speed change trigger condition data, first calculate the minimum value and the maximum value of this data. Then, subtract the minimum value from each data point and divide it by the difference between the maximum value and the minimum value to obtain the normalized data. This normalization process ensures that all trigger condition data is processed in the same way and effectively avoids the analysis deviation caused by inconsistent data dimensions. The normalized data will be used for the subsequent risk linkage analysis and causal relationship network construction.

[0115] Step S32: Perform a linkage analysis of potential risk code segments on the abnormal speed change code logic data based on the normalized data of the abnormal speed change trigger conditions to obtain potential risk code segment linkage data;

[0116] In the embodiments of the present invention, by performing joint analysis on the normalized abnormal speed change trigger condition data and the abnormal speed change code logic data, potential risk code segments are identified. The specific operation is to first analyze the relationship between the abnormal speed change trigger condition data and the execution status of each code module in the control system to determine the mutual influence between the trigger condition and the code logic. Correlation analysis and multi-dimensional matching methods are adopted. By constructing a data association matrix, the abnormal speed change trigger conditions are compared one by one with different code modules. For each piece of trigger condition data, analyze the abnormal behaviors caused in different code segments, record the potential risk code segments, and perform weighted evaluation according to the level of data association. For example, if a certain speed change abnormal trigger condition is highly correlated with the speed change function and the acceleration adjustment module in the elevator control system, then this function or module is marked as a potential risk code segment. This process adopts an association rule analysis method similar to that in data mining, such as the Apriori algorithm. By calculating the support and confidence between data, the identification accuracy of potential risk code segments is further improved. The finally obtained joint data of potential risk code segments will provide a basis for the subsequent construction of the causal relationship network.

[0117] Step S33: Construct a causal relationship network for the abnormal speed change code logic data based on the joint data of potential risk code segments to obtain a potential risk causal relationship network.

[0118] In the embodiments of the present invention, based on the joint data of potential risk code segments obtained in step S32, a causal relationship network is further constructed. The construction of the causal relationship network adopts a directed graph model in graph theory, representing the mutual influence relationship between code segments as the relationship between nodes and edges. In the graph, each code segment represents a node, and the influence relationship between the trigger condition and the risk code segment is represented by a directed edge. By calculating the causal dependence relationship between code segments, a causal network containing potential risks is constructed. In order to accurately identify the causal relationship between code segments, first perform a detailed analysis on the potential risk code segments, and analyze their influence on other code segments in combination with their execution order, input and output variables, and state changes. By constructing a causal graph, the causal chain between the abnormal speed change trigger condition and its corresponding code segment can be visualized, and it can be clarified which code segments are the root causes of the abnormal speed change. For example, if the output state of an acceleration module directly affects the working mode of the speed change control module, then in the causal relationship network, there will be a directed edge connecting these two modules. During this process, causal inference algorithms (such as Granger causality test or Bayesian network inference) are used to determine the causal relationship between code segments. This causal relationship network not only reveals the interaction between potential risk code segments but also helps to locate the key code segments that cause abnormal speed changes. The finally obtained potential risk causal relationship network provides a clear basis for subsequent risk analysis and control.

[0119] Step S33 includes the following steps:

[0120] Step S331: Perform linkage multi-level nested analysis on the linkage data of potential risk code segments to obtain risk code linkage multi-level nested data;

[0121] Step S332: Construct a risk code logic diagram based on the risk code linkage multi-level nested data;

[0122] Step S333: Perform causal relationship reasoning on the abnormal variable speed code logic data based on the risk code logic diagram to obtain causal relationship logic reasoning data;

[0123] Step S334: Perform relationship clustering processing on the risk code linkage multi-level nested data based on the causal relationship logic reasoning data to obtain risk code causal relationship clustering data;

[0124] Step S335: Construct a causal relationship network based on the risk code causal relationship clustering data and the causal relationship logic reasoning data to obtain a potential risk causal relationship network.

[0125] In the embodiments of the present invention, first, multi-layer nested analysis is performed on the linked data of potential risk code segments to capture the complex linkage relationships between potential code segments. By constructing a multi-level linkage analysis framework, code modules at different levels are hierarchically analyzed according to their association degrees. The specific operation is to use the nested structure in graph theory to divide the code segments into multiple levels according to their impacts on the system. For example, for the relationship between high-level control logic and low-level hardware control, a multi-layer nested structure can be constructed, where each layer represents the state changes of different modules in the system and their impacts on other modules. In this process, the influence range and action chain of each potential risk code segment are first calculated, and then these code segments are arranged hierarchically according to the influence relationship. To ensure the accuracy of the linkage relationship, data flow analysis technology is also adopted, and the input, output, state changes of each code segment and its impact on other modules are used as the basis for the linkage relationship. The finally generated multi-layer nested data of risk code linkages can clearly show the linkage levels of each code segment and their complex relationships with each other, providing basic data for subsequent risk assessment. Based on the multi-layer nested data of risk code linkages obtained in step S331, a complete risk code logic diagram is constructed. The construction of the logic diagram uses a directed graph model, where each node represents a risk code segment, and each edge represents the potential linkage relationship between two code segments. First, according to the results of the multi-layer nested analysis, the level of each code segment is determined, and based on this, the hierarchical structure of the graph is designed. Then, according to the relationships between different levels, the edges in the graph are gradually filled to define the causal influence relationships between code segments. During the construction process, it is considered that there are not only direct causal relationships but also indirect influences between code modules. To more comprehensively reflect the logical relationships between various code segments in the system, the method of "hierarchical progression" is adopted, that is, on the basis of low-level modules, the influence of upper-level modules on them is gradually deduced. The finally generated risk code logic diagram can intuitively show the logical connections of each module in the elevator system, helping to identify potential risk points and critical paths. Based on the constructed risk code logic diagram, causal relationship reasoning is performed on the abnormal speed change code logic data. The core of the causal relationship reasoning is to deduce the causal chain between each code segment by analyzing the directed edges in the code logic diagram. The specific method is to use algorithms such as Bayesian network reasoning and DAG (directed acyclic graph) traversal to simulate the execution order and state changes of code segments, and identify the potential causes of abnormal speed changes. Whenever a potential abnormal speed change trigger condition appears in a certain code segment, the system will trace the relevant upstream and downstream code segments and gradually deduce the causal relationship chain that causes the speed change abnormality. This process first analyzes each node in the logic diagram, identifies its input, output and internal state changes, and uses conditional probability for reasoning to deduce the causal dependence relationship between events. Finally, the causal relationship logical reasoning data obtained through the reasoning process will provide an effective basis for subsequent clustering analysis and network construction.Based on the causal relationship logical reasoning data, perform clustering analysis on the risk code linkage multi-level nested data obtained in step S331 to obtain risk code causal relationship clustering data. The clustering process uses an unsupervised learning method based on similarity, such as K-means clustering or spectral clustering. First, by analyzing the causal reasoning data of each risk code segment, calculate the similarity between each code segment. This similarity is measured by comparing the state changes, input-output relationships, and causal influence chains between code segments. Then, divide the risk code segments into several clusters according to the similarity. The code segments in each cluster have strong correlations in terms of causal relationships and can jointly trigger a certain type of abnormal speed change. During the clustering process, the influence of the multi-level structure is also considered to ensure that code segments at the same level can be clustered into the same cluster, while cross-level linkage relationships are incorporated into the corresponding clustering calculations. Finally, the risk code causal relationship clustering data obtained through clustering analysis can help identify which code segment combinations trigger similar abnormal behaviors, thereby providing a basis for further risk early warning. Combine the risk code causal relationship clustering data obtained in step S334 and the causal relationship logical reasoning data obtained in step S333 to finally construct a potential risk causal relationship network. The construction process uses graph theory methods to visualize the code segments and their mutual relationships in different clusters using a weighted directed graph. In this network, each clustering result is used as a node, and the edges between nodes represent the causal relationships between code segments. The weights of the edges are obtained from the causal relationship reasoning results in step S333, reflecting the intensity and possibility of the mutual influence between code segments. The final causal relationship network clearly shows the potential risk paths in the elevator system and can intuitively identify the key code segments leading to abnormal speed changes and their associated risk factors. Through this causal relationship network, it is possible to provide accurate bases for risk early warning, fault diagnosis, and safety assessment during the operation of the elevator.

[0126] Step S4 includes the following steps:

[0127] Step S41: Conduct risk feature analysis on the potential risk causal relationship network to obtain a potential risk causal feature relationship network;

[0128] Step S42: Assign risk causal relationship weights to the potential risk causal feature relationship network to obtain a potential risk relationship weight relationship network;

[0129] Step S43: Based on the random forest algorithm, construct an elevator safety risk adaptive analysis model for the potential risk relationship weight relationship network to obtain an elevator safety risk adaptive analysis model; send the elevator safety risk adaptive analysis model to the elevator operation control center to perform elevator safety risk adaptive analysis.

[0130] In the embodiments of the present invention, first, an in-depth analysis is performed on the causal relationship network of potential risks, aiming to identify the key risk features in the system. The specific approach is to extract the risk features related to elevator safety by analyzing each node (i.e., each risk code segment) in the network and the causal relationships between them. These features include the execution frequency of the risk code segment, the degree of impact on the overall system performance, the propagation path of potential failures, and the interdependence relationship between each risk node. Through network structure analysis, the code modules that pose safety hazards and their interaction characteristics with other modules are identified. Using graph spectrum analysis technology, the centrality, importance, and influence of each code segment in the causal relationship network are calculated to find the key code segments that cause greater risks. At the same time, community detection algorithms (such as the Louvain algorithm or hierarchical clustering algorithm) are used to partition the causal relationship network to identify the collaborative risk features between different modules. The output of this process is a causal feature relationship network of potential risks, which includes the feature description of each risk node and the association strength between it and other nodes, serving as the basis for subsequent risk analysis and modeling. Based on the causal feature relationship network of potential risks obtained from the analysis in step S41, weight assignment is performed for each causal relationship to quantify the importance and influence degree of each risk factor in the entire causal network. First, a weighted graph model is used to represent each edge in the causal relationship network, and the weight of each edge represents the causal influence from one risk code segment to another. The weight calculation of the edge adopts a statistical-based weighting method, including but not limited to techniques such as maximum likelihood estimation and correlation coefficient calculation. The impact of each risk factor on the elevator system is quantified according to factors such as historical data, the complexity of the code segment, and the frequency of fault occurrence, so as to assign a numerical weight to each risk causal relationship. Specifically, if multiple code segments in a certain causal chain act together and generate a high risk, a larger numerical value will be assigned to the weight of this chain. The weight assignment not only considers the directness and strength of the causal relationship, but also includes time delay and fault propagation effects, ensuring that the dynamic changes of the causal relationship can be accurately reflected in actual operation. The final output is a weighted relationship network of potential risks that includes all causal relationships and their corresponding weights, providing a quantitative assessment of each risk factor in the elevator safety system. Using the random forest algorithm to model the weighted relationship network of potential risks obtained in step S42 to construct an adaptive analysis model for elevator safety risks. Random forest is an ensemble learning method widely used to handle problems with multiple input variables and complex decision boundaries. First, by taking each causal node and edge in the weighted relationship network of potential risks as input features, an input data set for constructing a decision tree is built. The training objective of each decision tree is to learn from the historical data of the elevator system to judge the impact of different risk features and causal relationships on elevator safety.Specifically, the weights of each node in the risk causal relationship network are used as feature inputs, combined with the operation data of the elevator (such as load, speed, acceleration, etc.) for training to predict the probability of the elevator having safety risks under different causal relationship combinations. Each tree is trained according to a randomly selected feature set, thus having strong generalization ability when dealing with complex multi-dimensional data. Finally, the prediction results of each decision tree are aggregated through a voting mechanism to obtain the final evaluation model of the elevator safety risk. This model can automatically evaluate the safety status of the elevator based on real-time data and make adaptive adjustments for different operating conditions. The constructed adaptive analysis model of the elevator safety risk will be transmitted to the elevator operation control center through the network. The control center can monitor and evaluate the safety status of the elevator in real time through the received model. The specific operation is to deploy the model to the central processing system of the control center. The system regularly receives the operation data of the elevator and uses these data as inputs to the constructed random forest model for analysis. In this way, the elevator control system can evaluate the potential risks during the elevator operation in real time and take corresponding safety measures according to the output results of the model. For example, when the model detects that a certain risk factor exceeds the set safety threshold, the control center can automatically trigger a safety alarm or start an emergency stop operation to avoid accidents. In addition, the elevator operation control center can continuously optimize the control strategy according to the adaptive characteristics of the model to ensure the safety of the elevator under different operating states.

[0131] The present invention also provides an adaptive analysis system for elevator safety risks, which is used to execute the adaptive analysis method for elevator safety risks as described above. The adaptive analysis system for elevator safety risks includes:

[0132] A misoperation code mapping module, which is used to obtain the elevator historical operation log and the elevator operation logic code; perform misoperation code execution unit mapping on the elevator operation logic code according to the elevator historical operation log to obtain the misoperation code execution unit;

[0133] A trigger condition backtracking module, which is used to perform abnormal speed change code logic parsing on the misoperation code execution unit to obtain abnormal speed change code logic data; perform trigger condition backtracking on the abnormal speed change code logic data to obtain abnormal speed change trigger condition data;

[0134] A causal relationship network construction module, which is used to perform linkage analysis of potential risk code segments based on the abnormal speed change trigger condition data to obtain potential risk code segment linkage data; construct a causal relationship network according to the potential risk code segment linkage data to obtain a potential risk causal relationship network;

[0135] An adaptive analysis model construction module is used to construct an elevator safety risk adaptive analysis model for the potential risk causal relationship network based on the random forest algorithm, and obtain the elevator safety risk adaptive analysis model; send the elevator safety risk adaptive analysis model to the elevator operation control center to perform the elevator safety risk adaptive analysis.

[0136] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can 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 these embodiments shown herein, but rather to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An elevator safety risk adaptive analysis method, characterized in that: The following steps are involved: Step S1: Obtain the elevator historical operation log and the elevator operation logic code; According to the elevator historical operation log, the elevator operation logic code is mapped to the malfunction code execution unit to obtain the malfunction code execution unit; Step S2: performing abnormal speed change code logic analysis on the malfunction code execution unit to obtain abnormal speed change code logic data; performing trigger condition backtracking on the abnormal speed change code logic data to obtain abnormal speed change trigger condition data; wherein step S2 includes the following steps: Step S21: Identify the abnormal speed change behavior of the elevator's historical malfunction behavior to obtain the abnormal speed change behavior of the elevator; Step S22: Analyze the speed change risk factor according to the abnormal speed change behavior of the elevator and the historical operation cleaning log of the elevator to obtain the speed change risk factor of the elevator; wherein step S22 includes the following steps: Step S221: extracting the load and personnel density of the elevator historical operation cleaning log to obtain the elevator load data and the elevator personnel density data; Step S222: performing speed change jerking fluctuation analysis on the abnormal speed change behavior of the elevator to obtain the speed change jerking fluctuation data of the elevator; Step S223: Estimating the dynamic change of the inertial gravity of the elevator load data and the elevator personnel density data according to the elevator speed change jerking fluctuation data, and obtaining the inertial gravity change data of the elevator; Step S224: obtaining the wire traction material data of the elevator traction sheave; Step S225: quantifying the indirect tension imbalance of the wire traction material data according to the ascending / descending inertial gravity change data to obtain the traction indirect tension imbalance data; wherein step S225 includes the following steps: Perform inertial gravity time series incremental difference processing on the ascending / descending inertial gravity change data to obtain inertial gravity time series incremental difference data; According to the inertial gravity time series incremental difference data, the instantaneous gravity tensile load-bearing evaluation is performed on the wire traction material data to obtain the instantaneous gravity tensile load-bearing data of the material; Based on the material instantaneous gravity tensile bearing data, a discontinuous inertial gravity similarity interval is restricted to obtain a gravity tensile discontinuous similarity interval; According to the Simpson integral method and the gravity tensile discontinuity similarity interval, the material instantaneous gravity tensile load data is subjected to the tensile load piecewise constraint integration to obtain the tensile load piecewise integral data; According to the tensile load segment integral data, the indirect tension imbalance of the wire traction material data is quantified to obtain the traction indirect tension imbalance data; Step S226: analyzing the speed change risk factor of the elevator speed change jerking fluctuation data according to the traction indirect tension imbalance data to obtain the elevator speed change risk factor; Step S23: performing abnormal speed change code logic analysis on the malfunction code execution unit based on the elevator speed change risk factor to obtain abnormal speed change code logic data; Step S24: backtracking the triggering condition of the abnormal speed change code logic data to obtain abnormal speed change triggering condition data; Step S3: performing a potential risk code segment linkage analysis based on the abnormal speed change trigger condition data to obtain potential risk code segment linkage data; constructing a causal relationship network based on the potential risk code segment linkage data to obtain a potential risk causal relationship network; Step S4: construct an elevator safety risk adaptive analysis model for the potential risk causal relationship network based on the random forest algorithm to obtain an elevator safety risk adaptive analysis model; send the elevator safety risk adaptive analysis model to the elevator operation control center to perform elevator safety risk adaptive analysis.

2. The elevator safety risk adaptive analysis method according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Obtain the elevator historical operation log and the elevator operation logic code; Step S12: Clean the elevator historical operation log to obtain the elevator historical operation cleaning log; Step S13: extracting the malfunction behavior from the elevator historical operation cleaning log to obtain the elevator historical malfunction behavior; Step S14: mapping the elevator operation logic code to the malfunction code execution unit according to the historical malfunction behavior of the elevator to obtain the malfunction code execution unit.

3. The elevator safety risk adaptive analysis method according to claim 1 is characterized in that: Step S23 includes the following steps: Step S231: locating the speed change risk abnormal code of the malfunction code execution unit based on the elevator speed change risk factor to obtain the speed change risk abnormal code; Step S232: Perform syntax reverse engineering analysis on the speed change risk abnormality code to obtain syntax analysis data of the speed change abnormality code; Step S233: performing speed change abnormal cycle condition setting analysis on the speed change abnormal code syntax parsing data to obtain the speed change abnormal cycle setting conditions; Step S234: performing variable parameter overflow control analysis on the speed change abnormality code syntax analysis data according to the speed change abnormality cycle setting condition to obtain variable parameter overflow control data; Step S235: performing function exception throwing analysis based on the speed change abnormal cycle setting conditions and the variable parameter overflow control data to obtain function exception throwing data; Step S236: Based on the speed change abnormal cycle setting conditions, variable parameter overflow control data and function abnormal throwing data, the speed change risk abnormal code is logically analyzed to obtain abnormal speed change code logic data.

4. The elevator safety risk adaptive analysis method according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: normalizing the abnormal speed change trigger condition data to obtain abnormal speed change trigger condition normalized data; Step S32: performing potential risk code segment linkage analysis on the abnormal speed change code logic data based on the abnormal speed change trigger condition normalization data to obtain potential risk code segment linkage data; Step S33: construct a causal relationship network for the abnormal speed change code logic data according to the potential risk code segment linkage data to obtain a potential risk causal relationship network.

5. The elevator safety risk adaptive analysis method according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing risk characteristic analysis on the potential risk causal relationship network to obtain a potential risk causal characteristic relationship network; Step S42: assigning risk causal relationship weights to the potential risk causal feature relationship network to obtain a potential risk relationship weight relationship network; Step S43: construct an elevator safety risk adaptive analysis model for the potential risk relationship weight relationship network based on the random forest algorithm to obtain an elevator safety risk adaptive analysis model; send the elevator safety risk adaptive analysis model to the elevator operation control center to perform elevator safety risk adaptive analysis.

6. An elevator safety risk adaptive analysis system, characterized in that: Used to execute the elevator safety risk adaptive analysis method according to claim 1, the elevator safety risk adaptive analysis system comprises: The malfunction code mapping module is used to obtain the elevator historical operation log and the elevator operation logic code; according to the elevator historical operation log, the elevator operation logic code is mapped to the malfunction code execution unit to obtain the malfunction code execution unit; The trigger condition backtracking module is used to perform abnormal speed change code logic analysis on the malfunction code execution unit to obtain abnormal speed change code logic data; perform trigger condition backtracking on the abnormal speed change code logic data to obtain abnormal speed change trigger condition data; A causal relationship network construction module is used to perform a potential risk code segment linkage analysis based on abnormal speed change trigger condition data to obtain potential risk code segment linkage data; and to construct a causal relationship network based on the potential risk code segment linkage data to obtain a potential risk causal relationship network; The adaptive analysis model construction module is used to construct an elevator safety risk adaptive analysis model for the potential risk causal network based on the random forest algorithm to obtain an elevator safety risk adaptive analysis model; the elevator safety risk adaptive analysis model is sent to the elevator operation control center to perform elevator safety risk adaptive analysis.

Images