Fault prediction method and device based on elevator real-time running state and medium

Abstract

The invention discloses a fault prediction method and device based on the real-time running state of an elevator and a medium, and relates to the technical field of data processing.The method comprises the steps that historical running data of the elevator are obtained, a fault feature database is established according to historical fault features corresponding to the historical running data, and real-time running data of the elevator are obtained; a real-time running track corresponding to the elevator is determined; determining at least one to-be-selected fault feature corresponding to the real-time operation data based on a fault feature database, and determining a target fault feature with a potential risk from the to-be-selected fault features in combination with the real-time operation trajectory; and the target fault features are input into the trained fault prediction model, and the fault type corresponding to the elevator is output in combination with the predetermined elevator operation features, so that the accuracy and the efficiency of elevator fault prediction are improved, and the downtime and the maintenance cost caused by faults are reduced.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a fault prediction method, device and medium based on the real-time operating status of an elevator. Background Art

[0002] With the acceleration of urbanization, the number and frequency of elevators, as an indispensable vertical transportation tool in modern buildings, have increased dramatically. The safety and reliability of elevators are directly related to the safety of passengers' lives and property. Therefore, elevator fault prediction and maintenance are particularly important. Traditional elevator fault prediction methods mainly rely on regular maintenance and inspections. Although this method can prevent the occurrence of faults to a certain extent, it has obvious limitations. On the one hand, regular maintenance and inspections often fail to detect potential problems in elevator operation in a timely manner, especially when the elevator runs frequently and uses intensively, the possibility of faults will greatly increase; on the other hand, traditional fault prediction methods lack intelligent and automated means, and have limited analysis and processing capabilities for elevator operation data, making it difficult to accurately predict and respond to elevator faults in a timely manner.

[0003] In recent years, with the rapid development of technologies such as the Internet of Things, big data, and artificial intelligence, elevator fault prediction methods have also been continuously innovated and improved. Among them, the fault prediction method based on the real-time operation status of the elevator has become a new research hotspot. This method predicts and identifies elevator faults by real-time monitoring of the elevator's operating data, combined with advanced algorithms and models, and has the advantages of high accuracy and fast response speed. However, the existing fault prediction methods based on the real-time operation status of the elevator still have some shortcomings. For example, some methods only focus on certain specific operating states or fault types of the elevator, and lack comprehensive fault feature recognition and analysis capabilities; in addition, some methods still have certain limitations in data processing and algorithm application, making it difficult to achieve accurate prediction and effective response to elevator faults. Summary of the invention

[0004] The embodiments of the present application provide a fault prediction method, device and medium based on the real-time operating status of an elevator to solve the above-mentioned technical problems.

[0005] On the one hand, an embodiment of the present application provides a fault prediction method based on the real-time operating status of an elevator, comprising:

[0006] Acquire historical operation data of the elevator to establish a fault feature database according to historical fault features corresponding to the historical operation data, and acquire real-time operation data of the elevator to determine the real-time operation trajectory corresponding to the elevator;

[0007] Based on the fault feature database, determining at least one fault feature to be selected corresponding to the real-time operation data, and determining a target fault feature with potential risks from the fault features to be selected in combination with the real-time operation trajectory;

[0008] The target fault feature is input into the trained fault prediction model, and combined with the predetermined elevator operation feature, the fault type corresponding to the elevator is output.

[0009] In one implementation of the present application, historical operation data of an elevator is obtained to establish a fault feature database according to historical fault features corresponding to the historical operation data, specifically including:

[0010] Obtaining historical operation data, historical maintenance records and historical fault reports corresponding to the elevator through multiple data sources, and determining historical fault features corresponding to the elevator in the historical operation data; the multiple data sources include: preset sensors, monitoring systems, and elevator control systems;

[0011] According to the historical fault characteristics, and in combination with the historical maintenance records and the historical fault reports, the historical fault cases corresponding to the elevator and the status signals corresponding to the historical fault cases are determined to construct a corresponding fault characteristic database; the status signals include: door opening in a non-unlocking area, overspeeding and main power failure.

[0012] In one implementation of the present application, obtaining the real-time operation data of the elevator to determine the real-time operation trajectory corresponding to the elevator specifically includes:

[0013] The elevator is monitored in real time by a monitoring device preset on the elevator, and real-time operation data corresponding to the elevator is collected; the real-time operation data includes the running direction, speed, floor stop status, door mechanism braking status, main power supply and safety circuit status of the elevator;

[0014] Determine the data difference between the real-time operation data at adjacent moments, and determine the real-time operation state corresponding to the elevator according to the data difference; the real-time operation state includes an upward state, a downward state and a stopped state;

[0015] According to the real-time operation data and in combination with the corresponding real-time operation status, the real-time operation trajectory corresponding to the elevator is determined; the real-time operation trajectory includes a change in the operation direction, reaching the upper and lower limits or extreme positions.

[0016] In an implementation of the present application, determining at least one candidate fault feature corresponding to the real-time operation data based on the fault feature database specifically includes:

[0017] Comparing the real-time operation data with each historical operation data in the fault feature database for similarity to obtain a corresponding number of similarity values;

[0018] At least one similarity value greater than a preset threshold is determined from the plurality of similarity values, and a fault feature corresponding to the corresponding historical operation data is determined to obtain at least one fault feature to be selected.

[0019] In one implementation of the present application, in combination with the real-time operation trajectory, a target fault feature with potential risk is determined from the candidate fault features, specifically including:

[0020] Determine a fault impact factor corresponding to the elevator to determine a potential risk value corresponding to each fault impact factor in the at least one selected fault feature;

[0021] According to the potential risk value and in combination with the real-time operation trajectory of the elevator, a probability evaluation is performed on the at least one candidate fault feature, and according to the probability evaluation result, a target fault feature with potential risk is determined from the candidate fault features.

[0022] In one implementation of the present application, the target fault feature is input into a trained fault prediction model, and combined with predetermined elevator operation features, the fault type corresponding to the elevator is output, specifically including:

[0023] Acquire the elevator operation characteristics, and in combination with the elevator operation characteristics, when the target fault characteristic is the door mechanism braking condition, identify the abnormal action mode corresponding to the door mechanism braking condition, so as to determine that the fault type corresponding to the elevator is the door mechanism braking fault; the elevator operation characteristics include the elevator model, service life, and maintenance records, and the abnormal action mode includes frequent opening and closing of doors incompletely and abnormal door opening during operation;

[0024] When the target fault feature is in the main power state, the main power abnormality mode is identified according to the key parameters corresponding to the main power, so as to determine that the fault type corresponding to the elevator is the main power failure; the main power abnormality mode includes main power failure, abnormal voltage fluctuation or abnormal current fluctuation;

[0025] When the target fault feature is the safety circuit state, the safety circuit abnormal mode is identified according to the closed state corresponding to the safety circuit to determine that the fault type corresponding to the elevator is a safety circuit fault; the safety circuit abnormal mode includes a safety circuit break.

[0026] In one implementation of the present application, before inputting the target fault feature into the trained fault prediction model, the method further includes:

[0027] Acquire multiple sample operation data corresponding to the elevator, and divide the multiple sample operation data into training sample operation data and test sample operation data; the sample operation data includes operation characteristics, fault characteristics and fault types corresponding to the elevator;

[0028] Based on the deep learning algorithm, a fault prediction model corresponding to the elevator is constructed, and the training sample operation data with the fault type marked is input into the fault prediction model until the elevator fault type output by the fault prediction model matches the marked fault type, thereby completing the training of the fault prediction model;

[0029] The performance of the trained fault prediction model is evaluated by running the test sample data, and the fault prediction model is optimized according to the evaluation result to obtain a trained fault prediction model.

[0030] In one implementation of the present application, after inputting the target fault feature into a trained fault prediction model and combining the predetermined elevator operation feature to output the fault type corresponding to the elevator, the method further includes:

[0031] Generate fault warning information corresponding to the elevator, and push the fault warning information to the management personnel; the fault warning information includes the fault type, possible fault location and possible fault cause corresponding to the elevator;

[0032] According to the fault type and possible fault cause in the fault warning information, the fault level corresponding to the elevator and the fault measures corresponding to the fault level are determined, and emergency processing of the elevator fault is performed according to the fault measures; the emergency processing at least includes emergency braking, elevator deactivation, remote repair and emergency evacuation.

[0033] On the other hand, the embodiment of the present application further provides a fault prediction device based on the real-time operating status of an elevator, the device comprising:

[0034] at least one processor;

[0035] and, a memory communicatively coupled to the at least one processor;

[0036] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a fault prediction method based on the real-time operating status of the elevator as described above.

[0037] On the other hand, an embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, which, when executed, implement a fault prediction method based on the real-time operating status of an elevator as described above.

[0038] The embodiments of the present application provide a fault prediction method, device and medium based on the real-time operation status of an elevator, which at least have the following beneficial effects:

[0039] By collecting and analyzing historical data, we can fully understand the operating status and failure modes of the elevator, providing a solid data foundation for subsequent fault prediction; by real-time monitoring of the elevator's operating data, we can promptly discover abnormal conditions in the elevator's operation and provide real-time information for fault prediction and diagnosis; by comparing real-time operating data with the fault feature database, we can quickly identify the fault features that may currently exist in the elevator, and further combine the analysis of the real-time operating trajectory to more accurately determine the target fault features with potential risks, providing precise targets for subsequent fault prediction and diagnosis; using the trained fault prediction model, we can accurately analyze and predict the target fault features, and combined with the elevator's operating characteristics, we can more accurately determine the elevator's fault type, providing timely guidance for the elevator's repair and maintenance, thereby ensuring the safe operation of the elevator, improving the accuracy and efficiency of elevator fault prediction, and reducing the downtime and maintenance costs caused by faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0041] Figure 1 A flow chart of a fault prediction method based on the real-time operating status of an elevator provided in an embodiment of the present application;

[0042] Figure 2 A schematic diagram of the internal structure of a fault prediction device based on the real-time operating status of an elevator provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0044] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0045] Figure 1 A flow chart of a fault prediction method based on the real-time operating status of an elevator provided in an embodiment of the present application.

[0046] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For the convenience of understanding and description, the following embodiments are described in detail by taking a server as an example.

[0047] It should be noted that the server may be a single device or a system consisting of multiple devices, that is, a distributed server, and this application does not make any specific limitation on this.

[0048] like Figure 1 As shown, an embodiment of the present application provides a fault prediction method based on the real-time operation status of an elevator, comprising:

[0049] 101. Obtain historical operation data of the elevator to establish a fault feature database according to historical fault features corresponding to the historical operation data, and obtain real-time operation data of the elevator to determine the corresponding real-time operation trajectory of the elevator.

[0050] Specifically, in one embodiment of the present application, historical operation data of the elevator is obtained to establish a fault feature database according to historical fault features corresponding to the historical operation data, specifically including:

[0051] Obtain the historical operation data, historical maintenance records and historical fault reports corresponding to the elevator through multiple data sources, and determine the historical fault characteristics corresponding to the elevator in the historical operation data; the multiple data sources include: preset sensors, monitoring systems, and elevator control systems;

[0052] According to the historical fault characteristics, combined with the historical maintenance records and historical fault reports, the historical fault cases corresponding to the elevator and the status signals corresponding to the historical fault cases are determined to build a corresponding fault characteristic database; the status signals include: door opening in a non-unlocking area, overspeeding and main power failure.

[0053] In one embodiment, various sensors, such as velocity sensors, acceleration sensors, displacement sensors, etc., are installed at key parts of the elevator to monitor the operating status of the elevator in real time. The sensors collect data regularly and transmit the data to the data center for storage and analysis via wired or wireless means. Monitoring cameras are installed in key areas such as the elevator car, the shaft, and the machine room to record the operation of the elevator and the behavior of passengers. The monitoring system is connected to the data center to upload monitoring video and image data in real time for subsequent analysis. The elevator control system is responsible for controlling the start, stop, acceleration, deceleration and other operating actions of the elevator, and recording the operation log of the elevator. Through the interface with the elevator control system, the elevator's operating parameters, fault codes, operation records and other information are obtained.

[0054] Integrate the data obtained from preset sensors, monitoring systems, and elevator control systems to form a complete elevator historical operation data set. Clean and preprocess the data to remove redundant and invalid information to ensure the accuracy and completeness of the data. In the historical operation data, identify the features related to elevator failures, such as abnormal vibration, speed fluctuation, current abnormality, etc. through data mining and machine learning algorithms. Associate these features with historical maintenance records and historical fault reports to determine their corresponding relationship with specific faults.

[0055] According to the historical maintenance records and historical fault reports, all the fault cases that have occurred in the elevator are sorted out, including fault time, fault phenomenon, fault cause, maintenance process and other information. In the historical fault cases, the status signals related to the fault are identified, such as opening the door in the non-unlocking area, overspeed operation, main power failure, etc. These status signals are important indicators of elevator failures and will be used for subsequent fault prediction and diagnosis. The historical fault characteristics, historical fault cases and corresponding status signals are integrated together to build the fault characteristic database of the elevator. The database adopts a structured storage method to facilitate data query, retrieval and analysis.

[0056] In one embodiment of the present application, obtaining the real-time operation data of the elevator to determine the real-time operation trajectory corresponding to the elevator specifically includes:

[0057] The elevator is monitored in real time through the monitoring device preset on the elevator, and the corresponding real-time operation data of the elevator is collected; the real-time operation data includes the elevator's running direction, speed, floor stop status, door mechanism braking status, main power supply and safety circuit status;

[0058] Determine the data difference between the real-time operation data at adjacent moments, and determine the corresponding real-time operation state of the elevator according to the data difference; the real-time operation state includes the up state, the down state and the stop state;

[0059] According to the real-time operation data and in combination with the corresponding real-time operation status, the corresponding real-time operation trajectory of the elevator is determined; the real-time operation trajectory includes changes in the operation direction, reaching the upper and lower limits or extreme positions.

[0060] In one embodiment, surveillance cameras are installed in key areas such as the elevator car, the shaft, and the machine room to record the operation of the elevator and passenger behavior. The monitoring system is connected to the data center and uploads monitoring video and image data in real time for subsequent analysis. The elevator control system is responsible for controlling the start, stop, acceleration, deceleration and other operating actions of the elevator, and records the operation log of the elevator. Through the interface with the elevator control system, the elevator's operating parameters, fault codes, operation records and other information are obtained.

[0061] Integrate the data obtained from preset sensors, monitoring systems, and elevator control systems to form a complete elevator historical operation data set. Clean and preprocess the data to remove redundant and invalid information to ensure the accuracy and completeness of the data. In the historical operation data, identify the features related to elevator failures, such as abnormal vibration, speed fluctuation, current abnormality, etc. through data mining and machine learning algorithms. Associate these features with historical maintenance records and historical fault reports to determine their corresponding relationship with specific faults.

[0062] According to the historical maintenance records and historical fault reports, all the fault cases that have occurred in the elevator are sorted out, including fault time, fault phenomenon, fault cause, maintenance process and other information. In the historical fault cases, the status signals related to the fault are identified, such as opening the door in the non-unlocking area, overspeed operation, main power failure, etc. These status signals are important indicators of elevator failures and will be used for subsequent fault prediction and diagnosis. The historical fault characteristics, historical fault cases and corresponding status signals are integrated together to build the fault characteristic database of the elevator. The database adopts a structured storage method to facilitate data query, retrieval and analysis.

[0063] 102. Based on a fault feature database, determine at least one fault feature to be selected corresponding to the real-time operation data, and determine a target fault feature with potential risks from the fault features to be selected in combination with the real-time operation trajectory.

[0064] Specifically, in one embodiment of the present application, based on the fault feature database, determining at least one fault feature to be selected corresponding to the real-time operation data specifically includes:

[0065] Compare the real-time operation data with each historical operation data in the fault feature database for similarity to obtain a number of corresponding similarity values;

[0066] At least one similarity value greater than a preset threshold is determined from a plurality of similarity values, and a fault feature corresponding to the corresponding historical operation data is determined to obtain at least one fault feature to be selected.

[0067] In one embodiment, the elevator's operating data, including running direction, speed, floor stop status, door mechanism braking status, main power supply and safety circuit status, etc., are collected in real time through a monitoring device preset on the elevator. The continuity and accuracy of the data are ensured to provide a reliable basis for subsequent similarity comparisons. The historical operating data, historical maintenance records and historical fault reports of the elevator are sorted and analyzed to build a fault feature database. The database contains multiple historical operating data and their corresponding fault features, which are used for similarity comparison with real-time operating data.

[0068] Preprocess the real-time operation data and the historical operation data in the fault feature database, including data cleaning, normalization and other steps. Ensure that the data is compared in the same scale and range to improve the accuracy of similarity calculation. Use appropriate similarity measurement methods (such as Euclidean distance, cosine similarity, etc.) to compare the real-time operation data with each historical operation data in the fault feature database. Obtain several corresponding similarity values, which reflect the degree of similarity between the real-time operation data and the historical operation data.

[0069] According to the actual application requirements and the accuracy requirements of fault prediction, a reasonable similarity threshold is set. This threshold is used to filter out historical operation data with high similarity. Among the several similarity values ​​calculated, at least one similarity value greater than the preset threshold is determined. According to these similarity values, the corresponding historical operation data is found and its fault characteristics are determined. These fault characteristics are used as candidate fault characteristics for subsequent fault prediction and diagnosis.

[0070] In one embodiment of the present application, in combination with the real-time operation trajectory, a target fault feature with potential risk is determined from the candidate fault features, specifically including:

[0071] Determine the fault impact factor corresponding to the elevator to determine the potential risk value corresponding to each fault impact factor in at least one selected fault feature;

[0072] According to the potential risk value and in combination with the real-time operation trajectory of the elevator, a probability evaluation is performed on at least one candidate fault feature, and according to the probability evaluation result, a target fault feature with potential risk is determined from the candidate fault features.

[0073] In one embodiment, by analyzing the historical fault data of the elevator, the main factors affecting the elevator failure are identified, such as the frequency of use of the elevator, the operating environment (such as temperature and humidity), maintenance, and the degree of aging of components. These factors are determined as the failure influencing factors of the elevator. Each failure influencing factor is quantified, such as quantifying the frequency of use as the number of operations per day, and quantifying the operating environment as specific temperature and humidity values. The quantified failure influencing factors will be used for the subsequent calculation of the potential risk value.

[0074] A risk value calculation model is established. The model calculates the potential risk value of each candidate fault feature based on the fault influencing factors and their corresponding quantitative values. The model can use weighted summation, fuzzy comprehensive evaluation and other methods to comprehensively consider the influence of multiple fault influencing factors. The potential risk value of each candidate fault feature is evaluated to obtain the corresponding risk value score. The higher the score, the greater the potential risk corresponding to the fault feature.

[0075] Analyze the real-time operation trajectory of the elevator and extract the operation information related to the selected fault features, such as the elevator's operating speed, acceleration, and stop floors. This information will be used for subsequent probability evaluation. Establish a probability evaluation model that combines the potential risk value and real-time operation trajectory information to perform probability evaluation on the selected fault features. The model can use methods such as Bayesian networks and Markov chains to comprehensively consider the possibility of fault occurrence and the current operating status of the elevator. According to the probability evaluation results, determine the target fault features with potential risks from the selected fault features. The target fault features are those with higher probabilities and greater potential risks, which need to be focused on and handled in a timely manner.

[0076] 103. Input the target fault feature into the trained fault prediction model, and combine it with the predetermined elevator operation feature to output the fault type corresponding to the elevator.

[0077] Specifically, in one embodiment of the present application, the target fault feature is input into the trained fault prediction model, and combined with the predetermined elevator operation feature, the fault type corresponding to the elevator is output, specifically including:

[0078] The elevator operation characteristics are obtained, and combined with the elevator operation characteristics, when the target fault characteristic is the door mechanism braking condition, the abnormal action mode corresponding to the door mechanism braking condition is identified to determine that the corresponding fault type of the elevator is the door mechanism braking fault; the elevator operation characteristics include the elevator model, service life, and maintenance records, and the abnormal action mode includes frequent door opening and closing that is not in place and abnormal door opening during operation;

[0079] When the target fault feature is in the main power supply state, the main power supply abnormal mode is identified according to the key parameters corresponding to the main power supply, so as to determine that the fault type corresponding to the elevator is the main power supply fault; the main power supply abnormal mode includes main power supply power failure, abnormal voltage fluctuation or abnormal current fluctuation;

[0080] When the target fault feature is the safety circuit state, the safety circuit abnormal mode is identified according to the closed state corresponding to the safety circuit to determine that the fault type corresponding to the elevator is a safety circuit fault; the safety circuit abnormal mode includes a safety circuit break.

[0081] In one embodiment, basic information such as the model and age of the elevator is collected, which is essential for understanding the overall performance and potential failure points of the elevator. Checking the maintenance records of the elevator to understand the maintenance history, repair records, and replaced parts of the elevator helps to evaluate the current status of the elevator and predict possible failures.

[0082] When the target fault feature is the door mechanism braking condition, further analysis is performed in combination with the elevator operation characteristics. Identify the abnormal action patterns corresponding to the door mechanism braking condition, such as frequent door opening and closing that is not in place, abnormal door opening during operation, etc. Based on these abnormal action patterns, determine that the corresponding fault type of the elevator is a door mechanism braking fault. For example, after a certain model of elevator has been used for many years, the door machine begins to frequently open and close the door in place. Combined with the maintenance records, it is found that the door machine components are close to the end of their service life, so it is judged to be a door mechanism braking fault.

[0083] When the target fault feature is the main power state, focus on the key parameters corresponding to the main power supply. Identify the abnormal mode of the main power supply, such as main power failure, abnormal voltage fluctuation or abnormal current fluctuation. According to these abnormal modes, determine the corresponding fault type of the elevator as a main power failure. For example, the elevator suddenly has a power outage during operation, and the main power supply is found to be off during inspection, so it is judged to be a main power failure.

[0084] When the target fault feature is the safety circuit state, check the corresponding closed state of the safety circuit. Identify the abnormal mode of the safety circuit, such as safety circuit disconnection. According to these abnormal modes, determine that the corresponding fault type of the elevator is a safety circuit fault. For example, the elevator suddenly stops during normal operation, and the safety circuit is found to be disconnected, so it is judged as a safety circuit fault.

[0085] Take appropriate measures for the identified fault types. For example, if the door machine brake fails, it may be necessary to replace the door machine components or adjust the door machine parameters; if the main power fails, it may be necessary to check the power line or replace the power supply equipment; if the safety circuit fails, it may be necessary to check the various components in the safety circuit and repair the circuit breakers. According to the elevator operation characteristics and target fault characteristics, formulate corresponding preventive measures. For example, strengthen the maintenance of the elevator and regularly replace the wearing parts; strengthen the inspection and maintenance of the power line to ensure the normal operation of the power supply equipment; regularly check the various components in the safety circuit to ensure that they are in good condition.

[0086] In one embodiment of the present application, before inputting the target fault feature into the trained fault prediction model, the method further includes:

[0087] Acquire multiple sample operation data corresponding to the elevator, and divide the multiple sample operation data into training sample operation data and test sample operation data; the sample operation data includes operation characteristics, fault characteristics and fault types corresponding to the elevator;

[0088] Based on the deep learning algorithm, a fault prediction model corresponding to the elevator is constructed, and the training sample operation data with the fault type labeled is input into the fault prediction model until the elevator fault type output by the fault prediction model matches the labeled fault type, thus completing the training of the fault prediction model.

[0089] The performance of the trained fault prediction model is evaluated by running the test sample data, and the fault prediction model is optimized according to the evaluation results to obtain a trained fault prediction model.

[0090] In one embodiment, a plurality of sample operation data are obtained from the monitoring system of the elevator. These data cover the information of the elevator under different operation states, including operation characteristics (such as speed, acceleration, stop floors, etc.), fault characteristics (such as abnormal sound, vibration, temperature rise, etc.) and corresponding fault types (such as door mechanism brake failure, main power failure, safety circuit failure, etc.). The collected plurality of sample operation data are randomly divided into training sample operation data and test sample operation data. The training sample operation data is used to train the fault prediction model, and the test sample operation data is used to evaluate the performance of the model.

[0091] Based on deep learning algorithms, such as convolutional neural networks (CNN), recurrent neural networks (RNN), or long short-term memory networks (LSTM), a fault prediction model for elevators is constructed. The model input is the operation characteristics and fault characteristics of the elevator, and the output is the predicted fault type. The training sample operation data with the fault type labeled is input into the fault prediction model. Through optimization methods such as back propagation algorithm and gradient descent, the model parameters are continuously adjusted so that the elevator fault type output by the model matches the labeled fault type. Repeat the training process until the prediction accuracy of the model on the training sample reaches the preset requirements, and the training of the fault prediction model is completed.

[0092] Use the test sample running data to evaluate the performance of the trained fault prediction model. Evaluation indicators include prediction accuracy, recall rate, F1 score, etc. to comprehensively measure the performance of the model. According to the performance evaluation results, the fault prediction model is optimized. Optimization methods include adjusting the model structure, increasing training data, improving the training algorithm, etc. Repeat the evaluation and optimization process until the model's performance on the test sample reaches the best, and a trained fault prediction model is obtained.

[0093] In one embodiment of the present application, after inputting the target fault feature into the trained fault prediction model and combining the predetermined elevator operation feature to output the fault type corresponding to the elevator, the method further includes:

[0094] Generate fault warning information corresponding to the elevator and push the fault warning information to the management personnel; the fault warning information includes the fault type, possible fault location and possible fault cause of the elevator;

[0095] According to the fault type and possible fault cause in the fault warning information, determine the corresponding fault level of the elevator and the fault measures corresponding to the fault level, and perform emergency processing on the elevator fault according to the fault measures; the emergency processing at least includes emergency braking, elevator deactivation, remote repair and emergency evacuation.

[0096] In one embodiment, when the elevator monitoring system detects a potential fault signal, a fault warning mechanism is triggered. The system analyzes the fault signal according to preset algorithms and rules to determine the fault type, possible fault location, and possible fault cause of the elevator. Subsequently, the system automatically generates fault warning information containing this information. The generated fault warning information will be pushed to the elevator management personnel, such as the maintenance team leader, property management personnel, etc. in a timely manner. The push method can include SMS, email, APP notification, etc., to ensure that the management personnel can receive the warning information in a timely manner.

[0097] After receiving the fault warning information, the manager will determine the corresponding fault level of the elevator according to the fault type and possible fault cause in the information, combined with the actual situation of the elevator and maintenance experience. The fault level can be divided into minor faults, general faults, serious faults, etc., and different levels correspond to different urgency and handling priorities. According to the determined fault level, the manager will formulate corresponding fault measures and carry out emergency treatment. For minor faults, only remote monitoring and recording may be required for subsequent maintenance; for general faults, maintenance personnel may need to be dispatched to the site for inspection and repair; for serious faults, such as elevator out of control, trapped people, etc., emergency braking, elevator deactivation and other measures need to be taken immediately, and emergency evacuation should be organized to ensure the safety of passengers. In some cases, if the fault can be repaired through remote operation, remote repair can also be attempted to reduce downtime and impact on passengers.

[0098] Suppose that during the operation of an elevator, the monitoring system detects an abnormal braking condition of the door mechanism, triggering a fault warning. After system analysis, it is determined that the fault type is a door mechanism braking fault, the possible fault location is the door machine controller, and the possible cause of the fault is the aging of the controller components. Subsequently, the system generates a fault warning message and pushes it to the management personnel. After receiving the warning message, the management personnel determine that the fault is a general fault based on the fault type and cause. They decide to send maintenance personnel to the site for inspection and repair. After the maintenance personnel arrived at the site, they confirmed that the cause of the fault was the aging of the door machine controller components and replaced the corresponding components. After testing, the elevator resumed normal operation.

[0099] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, the embodiment of this application also provides a fault prediction device based on the real-time operation status of the elevator, and its structure is as follows: Figure 2 shown.

[0100] Figure 2 The internal structure diagram of a fault prediction device based on the real-time operation status of an elevator provided in an embodiment of the present application. Figure 2 As shown, the device includes:

[0101] at least one processor;

[0102] and, a memory communicatively coupled to the at least one processor;

[0103] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable the at least one processor to:

[0104] Acquire the historical operation data of the elevator to establish a fault feature database according to the historical fault features corresponding to the historical operation data, and acquire the real-time operation data of the elevator to determine the real-time operation trajectory corresponding to the elevator;

[0105] Based on the fault feature database, determine at least one candidate fault feature corresponding to the real-time operation data, and determine a target fault feature with potential risks from the candidate fault features in combination with the real-time operation trajectory;

[0106] The target fault features are input into the trained fault prediction model, and combined with the predetermined elevator operation features, the corresponding fault type of the elevator is output.

[0107] The present application also provides a non-volatile computer storage medium storing computer executable instructions. When the computer executable instructions are executed, they can:

[0108] Acquire the historical operation data of the elevator to establish a fault feature database according to the historical fault features corresponding to the historical operation data, and acquire the real-time operation data of the elevator to determine the real-time operation trajectory corresponding to the elevator;

[0109] Based on the fault feature database, determine at least one candidate fault feature corresponding to the real-time operation data, and determine a target fault feature with potential risks from the candidate fault features in combination with the real-time operation trajectory;

[0110] The target fault features are input into the trained fault prediction model, and combined with the predetermined elevator operation features, the corresponding fault type of the elevator is output.

[0111] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0112] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0113] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0114] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0115] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0116] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0118] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0119] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0120] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0121] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0122] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A fault prediction method based on the real-time operation status of an elevator, characterized in that: The method comprises: Acquire historical operation data of the elevator to establish a fault feature database according to historical fault features corresponding to the historical operation data, and acquire real-time operation data of the elevator to determine the real-time operation trajectory corresponding to the elevator; Based on the fault feature database, determining at least one fault feature to be selected corresponding to the real-time operation data, and determining a target fault feature with potential risks from the fault features to be selected in combination with the real-time operation trajectory; The target fault feature is input into the trained fault prediction model, and combined with the predetermined elevator operation feature, the fault type corresponding to the elevator is output.

2. A fault prediction method based on the real-time operation status of an elevator according to claim 1, characterized in that: Acquiring historical operation data of the elevator to establish a fault feature database according to historical fault features corresponding to the historical operation data, specifically including: Obtaining historical operation data, historical maintenance records and historical fault reports corresponding to the elevator through multiple data sources, and determining historical fault features corresponding to the elevator in the historical operation data; the multiple data sources include: preset sensors, monitoring systems, and elevator control systems; According to the historical fault characteristics, and in combination with the historical maintenance records and the historical fault reports, the historical fault cases corresponding to the elevator and the status signals corresponding to the historical fault cases are determined to construct a corresponding fault characteristic database; the status signals include: door opening in a non-unlocking area, overspeeding and main power failure.

3. A fault prediction method based on the real-time operation status of an elevator according to claim 1, characterized in that: Acquiring the real-time operation data of the elevator to determine the real-time operation trajectory corresponding to the elevator, specifically includes: The elevator is monitored in real time by a monitoring device preset on the elevator, and real-time operation data corresponding to the elevator is collected; the real-time operation data includes the running direction, speed, floor stop status, door mechanism braking status, main power supply and safety circuit status of the elevator; Determine the data difference between the real-time operation data at adjacent moments, and determine the real-time operation state corresponding to the elevator according to the data difference; the real-time operation state includes an upward state, a downward state and a stopped state; According to the real-time operation data and in combination with the corresponding real-time operation status, the real-time operation trajectory corresponding to the elevator is determined; the real-time operation trajectory includes a change in the operation direction, reaching the upper and lower limits or extreme positions.

4. A fault prediction method based on the real-time operation status of an elevator according to claim 1, characterized in that: Determining at least one to-be-selected fault feature corresponding to the real-time operation data based on the fault feature database specifically includes: Comparing the real-time operation data with each historical operation data in the fault feature database for similarity to obtain a corresponding number of similarity values; At least one similarity value greater than a preset threshold is determined from the plurality of similarity values, and a fault feature corresponding to the corresponding historical operation data is determined to obtain at least one fault feature to be selected.

5. A fault prediction method based on the real-time operation status of an elevator according to claim 1, characterized in that: In combination with the real-time operation trajectory, a target fault feature with potential risk is determined from the candidate fault features, specifically including: Determine a fault impact factor corresponding to the elevator to determine a potential risk value corresponding to each fault impact factor in the at least one selected fault feature; According to the potential risk value and in combination with the real-time operation trajectory of the elevator, a probability evaluation is performed on the at least one candidate fault feature, and according to the probability evaluation result, a target fault feature with potential risk is determined from the candidate fault features.

6. A fault prediction method based on the real-time operation status of an elevator according to claim 1, characterized in that: The target fault feature is input into the trained fault prediction model, and combined with the predetermined elevator operation feature, the fault type corresponding to the elevator is output, specifically including: Acquire the elevator operation characteristics, and in combination with the elevator operation characteristics, when the target fault characteristic is the door mechanism braking condition, identify the abnormal action mode corresponding to the door mechanism braking condition, so as to determine that the fault type corresponding to the elevator is the door mechanism braking fault; the elevator operation characteristics include the elevator model, service life, and maintenance records, and the abnormal action mode includes frequent opening and closing of doors incompletely and abnormal door opening during operation; When the target fault feature is in the main power state, the main power abnormality mode is identified according to the key parameters corresponding to the main power, so as to determine that the fault type corresponding to the elevator is the main power failure; the main power abnormality mode includes main power failure, abnormal voltage fluctuation or abnormal current fluctuation; When the target fault feature is the safety circuit state, the safety circuit abnormal mode is identified according to the closed state corresponding to the safety circuit to determine that the fault type corresponding to the elevator is a safety circuit fault; the safety circuit abnormal mode includes a safety circuit break.

7. A fault prediction method based on the real-time operation status of an elevator according to claim 1, characterized in that: Before inputting the target fault feature into the trained fault prediction model, the method further includes: Acquire multiple sample operation data corresponding to the elevator, and divide the multiple sample operation data into training sample operation data and test sample operation data; the sample operation data includes operation characteristics, fault characteristics and fault types corresponding to the elevator; Based on the deep learning algorithm, a fault prediction model corresponding to the elevator is constructed, and the training sample operation data with the fault type marked is input into the fault prediction model until the elevator fault type output by the fault prediction model matches the marked fault type, thereby completing the training of the fault prediction model; The performance of the trained fault prediction model is evaluated by running the test sample data, and the fault prediction model is optimized according to the evaluation result to obtain a trained fault prediction model.

8. A fault prediction method based on the real-time operation status of an elevator according to claim 1, characterized in that: After inputting the target fault feature into the trained fault prediction model and combining it with the predetermined elevator operation feature to output the fault type corresponding to the elevator, the method further includes: Generate fault warning information corresponding to the elevator, and push the fault warning information to the management personnel; the fault warning information includes the fault type, possible fault location and possible fault cause corresponding to the elevator; According to the fault type and possible fault cause in the fault warning information, the fault level corresponding to the elevator and the fault measures corresponding to the fault level are determined, and emergency processing of the elevator fault is performed according to the fault measures; the emergency processing at least includes emergency braking, elevator deactivation, remote repair and emergency evacuation.

9. A fault prediction device based on the real-time operation status of an elevator, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; Wherein, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a fault prediction method based on the real-time operating status of an elevator as described in any one of claims 1-8.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: When the computer executable instructions are executed, a fault prediction method based on the real-time operating status of an elevator as described in any one of claims 1 to 8 is implemented.

Images