Intelligent elevator maintenance method, device, equipment and system based on artificial intelligence

Abstract

The invention discloses an intelligent elevator maintenance method, device, equipment and system based on artificial intelligence. The elevator DTU terminal collects information, uploads the information to the intelligent maintenance system and pushes the information to the elevator large model, the diagnosis model polls and positions an elevator and a project needing to be maintained according to data, the task model determiner generates a task and instructs the automatic programming model to generate a plug-in, and the maintenance personnel completes maintenance and uploads data according to the prompt of the mobile phone client. And cases are generated after evaluation and scoring of the effect evaluation model and stored in the maintenance case model, and if the cases are qualified, the elevator health degree is reset. According to the system, self-developed key technologies such as automatic programming and elevator large model building are utilized, intelligent maintenance and knowledge sharing are achieved, maintenance quality and standard unification are improved, many defects of a traditional elevator maintenance mode are effectively overcome, elevator maintenance efficiency, quality and safety are improved, reliable operation of an elevator is guaranteed, and intelligent development of the elevator maintenance industry is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of elevator maintenance, and in particular to a method, device, equipment and system for intelligent elevator maintenance based on artificial intelligence. Background Art

[0002] With the rapid advancement of urbanization, high-rise buildings are springing up like mushrooms after rain. Elevators have become an indispensable vertical transportation tool in modern urban life. While providing people with convenient travel, their safety, reliability and comfort have also become the focus of attention from all walks of life.

[0003] The traditional elevator maintenance model mainly relies on regular maintenance. This model has many problems that are difficult to overcome. First, regular maintenance often does not take into account the actual operating conditions and needs of the elevator, which can easily lead to serious waste of resources. For example, some elevators that are in good operating condition and are used less frequently may not need to be fully maintained according to a fixed cycle, but still need to follow the same maintenance process, which undoubtedly consumes a lot of manpower, material resources and time resources.

[0004] Secondly, inefficiency is another significant drawback of the traditional maintenance model. Due to the lack of accurate fault prediction and location capabilities, maintenance personnel may need to spend a lot of time checking each component of the elevator one by one during maintenance work, even if the elevator has no substantial faults or only has minor hidden dangers. This not only prolongs the maintenance time, but may also affect the normal use of people in the building due to long-term downtime, causing many inconveniences to users.

[0005] Furthermore, the problem of inconsistent maintenance standards is common in the traditional model. Different maintenance companies and maintenance personnel have different operating procedures and quality control when performing elevator maintenance tasks due to their own experience, technical level and internal standards. For example, for the inspection and maintenance of certain key components, some maintenance personnel may only conduct a simple appearance inspection, while others will conduct more in-depth and detailed performance testing and debugging. This difference may cause the elevator to face different degrees of risk in subsequent operation.

[0006] In addition, the traditional maintenance process has a serious lack of supervision mechanism. During the maintenance process, it is difficult to monitor in real time and comprehensively whether the maintenance personnel's operations are standardized and whether they perform tasks in accordance with established standards and procedures. This may lead to some maintenance work being perfunctory and cutting corners, and the relevant management departments or elevator users are unable to detect and stop it in time.

[0007] The evaluation of maintenance effect is also a major problem of the traditional model. Due to the lack of scientific and systematic evaluation methods, it is difficult to accurately judge whether a maintenance work has truly and effectively improved the operating performance of the elevator and reduced the probability of failure. Often, it can only be roughly judged by whether the elevator fails again in the subsequent short period of time, and it is impossible to deeply analyze the impact of various data and operations in the maintenance process on the long-term operating stability of the elevator.

[0008] Finally, with the rapid increase in the number of elevators, the contradiction of shortage of maintenance personnel has become increasingly prominent. The traditional maintenance model is inefficient and has cumbersome procedures, and requires a large number of maintenance personnel to meet the growing demand for elevator maintenance. However, in reality, the training speed of maintenance personnel is far behind the growth rate of the number of elevators, which further aggravates the pressure and difficulty of elevator maintenance work, making it difficult to effectively guarantee the timeliness and quality of elevator maintenance.

[0009] In summary, the traditional elevator maintenance model has many limitations in terms of resource utilization, efficiency improvement, standard unification, process supervision, effect evaluation and personnel allocation, and it is difficult to adapt to the needs of the rapid development of the modern elevator industry. Based on this severe situation, this invention actively explores the application of artificial intelligence technology in the elevator industry for innovation, aiming to effectively solve the many problems faced by elevator intelligent maintenance, and provide more reliable and efficient guarantees for the safe and stable operation of elevators. Summary of the invention

[0010] The purpose of the present invention is to provide a method, device, equipment and system for intelligent maintenance of elevators based on artificial intelligence, which innovatively uses the powerful functions of the artificial intelligence big model to realize automatic programming and generation of maintenance plug-ins. This feature gives the maintenance work a high degree of intelligence and autonomy. In the offline state, the maintenance plug-in can still play a key role, effectively breaking the dependence of traditional maintenance on the network environment, and greatly expanding the implementation scenarios and flexibility of maintenance work.

[0011] In order to achieve the above-mentioned purpose, the present invention is implemented through the following technical solutions: a method, device, equipment and system for intelligent maintenance of elevators based on artificial intelligence:

[0012] System architecture:

[0013] The system of the present invention mainly includes a mobile phone A1, an intelligent maintenance client C1 installed in a mobile phone support plug-in, a cloud-based intelligent maintenance system Y1 (including a maintenance server S1, a communication server Z1, and a database B1), and an elevator large model X1 (covering a maintenance case model M1, a state and fault model M2, a diagnosis model M3, a task model M4, an automatic programming model M5, and an effect evaluation model M6), an elevator E1, a DTU terminal T1 connected to the elevator to upload faults, and a maintenance personnel P1.

[0014] Key technologies:

[0015] Automatic programming technology: The automatic programming method of the present invention inputs the code base and programming language corresponding to a large number of maintenance projects into the automatic programming model for learning and training, and uses machine learning algorithms to understand programming rules and syntax, identify code patterns and structures, and associate maintenance projects with codes. After entering the maintenance rules, it can be converted into programming languages ​​through natural language processing according to user instructions, and automatically generate codes (plug-ins) that meet the requirements. This technology is the first of its kind in the industry.

[0016] Elevator big model construction technology: By locally deploying a general big model private cloud, inputting massive elevator industry data, and going through steps such as data cleaning, word segmentation and tokenization, data enhancement and standardization, sampling and weight adjustment, and combining with natural language processing, multiple sub-models are built according to purpose, including maintenance case model M1, status and fault model M2, diagnosis model M3, task model M4, automatic programming model M5, and effect evaluation model M6.

[0017] Intelligent maintenance system establishment technology: responsible for specific maintenance business processing, using the mainstream Web API application architecture, data interaction using JSON format, database selection relational database, based on HTTPS to achieve client and server communication. Its establishment process includes customer demand research, technical solution determination, programming development, testing and verification, and system launch.

[0018] Maintenance project and code association technology: Use AI big data model to extract program source code header comments and convert them into big data tags to achieve automatic association. Programmers add comments when implementing maintenance project functions, upload the code to the AI ​​big data model after coding and testing, and the model automatically extracts comments and tags them to achieve association. This is an innovative technology.

[0019] Maintenance rule creation technology: Based on big data tags and the latest national standards for maintenance items, the standards are texted with the help of OCR technology, and then maintenance rules are automatically created through keyword matching (intelligent word segmentation) technology. Maintenance items that do not match national standards are included in corporate standards. When updating, only the latest national standards need to be uploaded, which improves the degree of automation and intelligence. It is a self-developed innovative technology.

[0020] Elevator intelligent maintenance method steps:

[0021] Upload elevator status and fault information: Elevator E1 collects status and fault U1 in real time through DTU terminal T1, and uploads the elevator status and fault information U2 to the communication server Z1 of the intelligent maintenance system X1. After receiving the fault information, the communication server Z1 writes the fault information into the database B1 for long-term storage, and pushes the status and fault U3 to the status and fault model M2 of the elevator large model X1 for long-term storage.

[0022] Elevator maintenance demand diagnosis: The diagnostic model M3 of the elevator large model conducts regular (daily) inspections, and accurately locates the elevators that need maintenance and determines the maintenance items based on the diagnostic rules (such as elevators with a health degree <30 need maintenance and elevators with low health degrees are prioritized). For example, if elevator A has a entrapment fault, a Class A fault, or a car door opening and closing fault, its health degree is calculated to be 10, requiring maintenance, and the maintenance item is that the car door opens and closes normally; if elevator B has an emergency electric operation fault and the number of wire ropes is less than 100,000 times, its health degree is 20, requiring maintenance, and the maintenance item is replacing the wire rope, and the priority is determined, such as arranging maintenance for elevator A first.

[0023] Maintenance task generation: The task model M4 of the elevator model determines the maintenance personnel based on the elevators diagnosed by the diagnosis model M3 and the duty list, and generates maintenance tasks. If elevators A and B are under the responsibility of maintenance personnel P1, two maintenance tasks are generated, and corresponding instructions are issued to the automatic programming M5, such as generating a plug-in for elevator A (the content is the standard maintenance process + checking that the car door is open and closed normally, including uploading video and related interface information) and generating a plug-in for elevator B (the content is the standard maintenance process + replacing the wire rope, including uploading video and related interface information).

[0024] Automatic generation and push of plug-ins: After receiving the instructions, the automatic programming model M5 of the elevator model automatically analyzes and generates plug-ins that can be called by the client. After the generation is completed, it notifies the task model M4, and the task model M4 automatically pushes the task information and plug-ins to the maintenance personnel P1.

[0025] On-site maintenance operation: After receiving the task, maintenance personnel P1 takes mobile phone A1 with the smart maintenance client and task information to the elevator site, opens the client, loads the plug-in interface Load, calls the interface Run, and interactively follows the plug-in prompts to complete maintenance and record. For example, elevator A completes the standard maintenance process and checks that the car door is operating normally, and elevator B completes the standard maintenance process and replaces the wire rope.

[0026] Maintenance effect evaluation: After maintenance personnel P1 completes maintenance, the plug-in interface Upload is automatically called to upload the data and video of the maintenance process to the elevator effect evaluation model M6. The effect evaluation model M6 analyzes the data and video to determine the effect of this maintenance and give a score.

[0027] Case generation and knowledge sharing: After the effect evaluation model M6 completes the evaluation and scoring, a case is automatically generated and pushed to the elevator maintenance case model M1 to provide a reference for subsequent maintenance and realize knowledge sharing.

[0028] Elevator health reset: After maintenance is completed, the elevator health is reset to 100 and the elevator resumes normal operation.

[0029] Furthermore, an intelligent elevator maintenance method based on artificial intelligence comprises the following steps:

[0030] Step S1: The elevator collects and uploads status and fault information to the intelligent maintenance system in real time through the DTU terminal, and the intelligent maintenance system pushes it to the status and fault model of the elevator large model;

[0031] Step S2: The diagnostic model of the large elevator model is inspected according to a preset period, and based on the elevator operation data, historical fault records and diagnostic rules, the elevators that need maintenance and their maintenance items are located, and the maintenance priority is determined;

[0032] Step S3: The task model of the elevator large model determines the maintenance personnel according to the diagnosis results and the duty list, generates the maintenance tasks and sends instructions to the automatic programming model;

[0033] Step S4: The automatic programming model generates a client-callable plug-in based on the instructions and its own learning and training results, and notifies the task model to push the task information and plug-in to the maintenance personnel;

[0034] Step S5: The maintenance personnel use the mobile smart maintenance client to load the plug-in and complete the maintenance according to the prompts, while recording the maintenance process video. After completion, upload the data and video to the effect evaluation model;

[0035] Step S6: The effect evaluation model uses data analysis and image recognition technology to process the uploaded information, derives the maintenance effect and scores it, and then generates a case and pushes it to the maintenance case model;

[0036] Step S7: If the maintenance effect evaluation is qualified, the system automatically resets the elevator health to 100, so that the elevator resumes normal operation.

[0037] As a further improvement of the technical solution of the present invention, the construction of the elevator big model includes localizing the deployment of the general big model, inputting the elevator industry data, and constructing multiple sub-models through data cleaning, word segmentation and tokenization, data enhancement and standardization, sampling and weight adjustment, and natural language processing. The sub-models include at least a maintenance case model, a status and fault model, a diagnosis model, a task model, an automatic programming model, and an effect evaluation model.

[0038] As a further improvement of the technical solution of the present invention, the automatic programming model automatically generates code plug-ins based on user instructions and preset maintenance rules by learning the code libraries and programming languages ​​corresponding to a large number of maintenance projects, and the generation process involves natural language processing to convert instructions into programming languages.

[0039] As a further improvement on the technical solution of the present invention, the maintenance items and codes are automatically associated by extracting the program source code header annotations through the AI ​​big data model and converting them into big data tags. The maintenance rules are automatically created through the big data tags and the latest national standards of the maintenance items through OCR technology and keyword matching technology. The maintenance items that do not match the national standards constitute enterprise standards.

[0040] As a further improvement of the technical solution of the present invention, an intelligent elevator maintenance device based on artificial intelligence comprises:

[0041] The information collection and transmission module is installed in the elevator and DTU terminal to collect elevator status and fault information and upload it to the intelligent maintenance system;

[0042] The diagnostic module is located in the large elevator model. It performs regular inspections based on elevator operation data and historical fault information to locate elevators and maintenance items that require maintenance.

[0043] Task generation module, in the elevator model, determines the maintenance personnel and generates maintenance tasks based on the diagnosis results;

[0044] The automatic programming module, also in the elevator model, generates plug-ins according to the instructions of the task generation module;

[0045] The client module is installed on the mobile phone, receives task information and plug-ins, guides maintenance personnel to work and upload data;

[0046] The effect evaluation module is in the elevator model, which evaluates the maintenance effect and generates cases;

[0047] The knowledge sharing module is integrated into the elevator model to enable sharing and communication of maintenance cases among maintenance personnel.

[0048] As a further improvement of the technical solution of the present invention, the large elevator model also includes a maintenance case model, which is used to store cases generated by the effect evaluation module to provide a reference basis for subsequent maintenance.

[0049] As a further improvement of the technical solution of the present invention, the intelligent maintenance system includes a maintenance server, a communication server and a database. The communication server receives elevator information and stores it in the database. The maintenance server processes the elevator data and interacts with the elevator large model. The database stores elevator operation data, fault information, maintenance task information, plug-in information and maintenance case information.

[0050] An intelligent elevator maintenance device based on artificial intelligence includes an elevator, a DTU terminal, and a mobile phone. The elevator is connected to the intelligent maintenance system through the DTU terminal. The mobile phone is installed with an intelligent maintenance client and interacts with the intelligent maintenance system. The DTU terminal continuously collects elevator status and fault information. The mobile phone receives and displays task information and plug-ins to assist maintenance personnel in completing tasks and uploading data.

[0051] An intelligent elevator maintenance system based on artificial intelligence includes an intelligent maintenance system in the cloud and an elevator large model. The intelligent maintenance system and the elevator large model work together. The intelligent maintenance system is responsible for elevator data collection, storage and preliminary processing, and the elevator large model performs in-depth analysis, diagnosis, task allocation, plug-in generation, effect evaluation and knowledge management. The two together realize the intelligent elevator maintenance process.

[0052] As a further improvement of the technical solution of the present invention, the cloud-based intelligent maintenance system adopts the mainstream Web API application architecture, data interaction adopts the JSON format, the database adopts a relational database, and communication between the client and the server is realized based on HTTPS. Its establishment process includes investigating customer needs, determining technical solutions, programming development, testing and verification, and system online steps.

[0053] The present invention has the following beneficial effects:

[0054] 1. Intelligent maintenance

[0055] Innovatively leveraging the power of the AI ​​big model to automatically program and generate maintenance plug-ins, this feature gives maintenance work a high degree of intelligence and autonomy. In an offline state, maintenance plug-ins can still play a key role, effectively breaking through the traditional maintenance's dependence on the network environment, and greatly expanding the implementation scenarios and flexibility of maintenance work.

[0056] With the precise guidance of the smart plug-in, maintenance personnel can quickly locate maintenance priorities and key operating steps, significantly reducing the large amount of time wasted in the traditional maintenance mode due to blind troubleshooting and experience differences. Maintenance tasks that may have taken hours or even longer in the past can be greatly shortened to tens of minutes or even shorter with the assistance of smart plug-ins, effectively improving maintenance efficiency. This efficiency improvement not only reduces elevator downtime and reduces the impact on the normal use of elevators by people in the building, but also directly reduces the labor and material costs caused by long-term maintenance, such as reducing the overtime hours of maintenance personnel and unnecessary loss of maintenance tools and parts.

[0057] From the perspective of customer experience, elevators can resume normal operation more quickly, greatly improving customer satisfaction and convenience in elevator use, and enhancing customer trust and recognition of elevator managers and maintenance service providers.

[0058] 2. Knowledge Sharing

[0059] The present invention builds an efficient knowledge sharing ecosystem. The case data generated during each elevator maintenance process, including the type of elevator failure, maintenance operation details, plug-in information used, and the final maintenance effect evaluation, will be automatically uploaded to the maintenance case model in the elevator model. This measure enables maintenance personnel across the country to easily obtain these valuable practical experience and knowledge results.

[0060] For inexperienced maintenance personnel, they can quickly learn the methods and techniques for handling various types of elevators in various fault situations by studying these rich cases, accelerate the growth and improvement of their own professional skills, shorten the training cycle, and thus independently undertake maintenance tasks faster and ensure the quality of work. For experienced and senior maintenance personnel, these case data also provide a platform for mutual communication and learning, from which they can discover new maintenance ideas and methods, further optimize their own maintenance strategies, and also help them have a more comprehensive and in-depth grasp of the overall development trends and common problems of the elevator industry.

[0061] From the perspective of the macro-development of the elevator maintenance industry, this knowledge sharing mechanism has promoted the dissemination and inheritance of technology and experience within the industry, broken down information barriers between regions and enterprises, and is conducive to the overall improvement and balanced development of the entire industry's technical level, injecting strong impetus into the sustainable development of the elevator maintenance industry.

[0062] 3. Improve the quality of maintenance

[0063] By conducting in-depth analysis of the detailed data generated during the maintenance process and the maintenance operation video, the present invention achieves accurate evaluation and effective monitoring of the maintenance quality. At the data level, it is possible to accurately monitor the performance parameter changes of each component of the elevator before and after maintenance, such as the elevator's running speed stability, the response time and braking force of the braking system, the voltage and current fluctuations of the electrical system, etc., so as to determine whether the maintenance operation has truly achieved the expected optimization and repair effect.

[0064] In terms of video analysis, the maintenance personnel's operational standardization and completeness can be directly observed, such as whether key components are disassembled, cleaned, installed and debugged according to standard procedures, whether some important inspection links are omitted, etc. This multi-dimensional analysis and evaluation method is more accurate and scientific than the traditional method of subjectively judging the maintenance quality based solely on the subsequent operation of the elevator.

[0065] Once problems or deficiencies are found in the maintenance quality, they can be promptly fed back to the maintenance personnel for rectification and optimization, thus forming a closed-loop quality control system to ensure that every maintenance work can effectively improve the operating performance and safety of the elevator, reduce the probability of elevator failures, and provide passengers with a safer and more reliable elevator environment.

[0066] 4. Unification of maintenance standards

[0067] The present invention generates a unified maintenance plug-in through automatic programming based on rigorous maintenance standard procedures and accurate diagnostic data, which fundamentally solves the industry problem of inconsistent maintenance standards. No matter in which region or by which maintenance personnel perform elevator maintenance tasks, as long as the plug-in generated by the present invention is used, it can ensure that the elevator is fully and carefully maintained according to the same standard procedures. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0069] Figure 1 It is a system architecture diagram of an embodiment of the present invention. DETAILED DESCRIPTION

[0070] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. The exemplary embodiments and descriptions of the present invention are used to explain the present invention, but are not intended to limit the present invention.

[0071] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, upper end, lower end, top, bottom...) are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0072] In the present invention, unless otherwise clearly defined and limited, the term "connection" should be understood in a broad sense, for example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0073] In addition, in the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features; in addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0074] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0075] Reference Figure 1 In the actual operation of this AI-based elevator intelligent maintenance system, each component works closely together and follows the following detailed implementation steps:

[0076] First, ensure that the connection between elevator E1 and DTU terminal T1 is stable and reliable, the communication server Z1 has efficient and stable network reception and transmission capabilities, the database B1 operates normally and has sufficient storage space to record various elevator data, the elevator model X1 has completed precise training based on massive elevator industry data and can accurately perform complex operations such as diagnosis, task allocation, and automatic programming, the smart maintenance client C1 is fully installed on mobile phone A1 and functions normally, and the maintenance personnel P1 has received system operation training and is familiar with the entire maintenance process.

[0077] When the elevator is in operation, the DTU terminal T1 continuously collects the elevator status and fault information, including the elevator's operating speed, car position, door system status, electrical system parameters and other data. For example, the DTU terminal T1 obtains the elevator's speed data every few seconds and detects whether the elevator's safety circuit is normally connected. Once an abnormality is detected, such as abnormal fluctuations in the elevator speed or a broken safety circuit, the status and fault information U1 will be immediately sorted out, and the elevator status and fault information U2 will be uploaded to the communication service terminal Z1 of the intelligent maintenance system X1 through the preset communication protocol.

[0078] After receiving the information from the elevator, the communication server Z1 quickly writes the fault information into the database B1 for long-term storage for subsequent query and analysis. At the same time, the status and fault U3 are pushed to the status and fault model M2 of the elevator model X1 in real time. The status and fault model M2 will conduct in-depth analysis and record of these data to build a dynamic portrait of the elevator operation status.

[0079] The diagnostic model M3 of the elevator model starts the inspection task according to the preset regular inspection cycle (every day). It makes judgments based on a set of comprehensive and scientific diagnostic rules. For example, it comprehensively considers factors such as the elevator's historical fault data, recent operating parameter change trends, and wear estimation models of various components. Taking the elevator in a commercial building as an example, if an elevator has frequently had door system fault alarms in the past month, and the recent operating current fluctuations of its door machine exceed 30% of the normal range, combined with the service life and number of operations of the door machine, according to the diagnostic rules, it is calculated that the health of the elevator is only 20 (health <30 indicates that maintenance is required), and the maintenance items are accurately determined as comprehensive inspection and debugging of the door system, including performance testing of the door machine motor, sensitivity inspection of the door lock, and cleaning and lubrication of the door track. After determining the elevator that needs maintenance, the priority will also be determined based on factors such as health value, fault severity, and the use requirements of the building where the elevator is located. For example, in a large hotel with multiple elevators, if two elevators need maintenance at the same time, one of them frequently presents the risk of entrapment and its health level is only 10, while the other elevator only has a minor cabin lighting failure and its health level is 25, then the diagnostic model M3 will prioritize the elevator with a health level of 10 as a high-priority maintenance task to minimize the impact on the safety and user experience of hotel guests.

[0080] Next, the task model M4 of the large elevator model accurately determines the personnel responsible for maintenance based on the results obtained by the diagnosis model M3 and the pre-set maintenance personnel duty schedule. Assuming that a maintenance team is responsible for the maintenance of elevators in multiple areas, the task model M4 will comprehensively consider factors such as the maintenance personnel's geographical location, current task load, and maintenance experience for specific types of elevators to assign tasks. For example, for an elevator of a specific brand and model with a complex electrical fault, the task model M4 will give priority to assigning tasks to maintenance personnel P1 who is good at repairing the electrical system of the brand of elevators, is close to the customer, and has a small current task load. After determining the maintenance personnel, the task model M4 generates detailed maintenance task information and issues corresponding instructions to the automatic programming M5. For example, for the elevator door system failure of the above-mentioned commercial building, an instruction is issued to the automatic programming M5: "Generate a plug-in for the elevator, the content is standard maintenance process + comprehensive door system overhaul (including door machine motor performance test, door lock sensitivity check, door track cleaning and lubrication), and the video needs to be uploaded. The loading interface is Load, the running interface is Run, and the upload interface is Upload."

[0081] After receiving the instruction, the automatic programming model M5 of the large elevator model quickly starts the automatic analysis program. Based on the code base and algorithm model constructed by previous learning and training, combined with the specific requirements of the maintenance project, it quickly generates a plug-in that can be called by the client. For example, the automatic programming model M5 selects relevant code snippets for the door motor performance test from the code base, combines the standard code process for door lock sensitivity inspection and the operation instruction code for door track cleaning and lubrication, integrates and optimizes according to the preset plug-in architecture, and generates a complete and functionally clear maintenance plug-in. After the plug-in is generated, the task model M4 is automatically notified, and the task model M4 immediately pushes the task information and plug-in to the smart maintenance client C1 on the mobile phone A1 of the maintenance personnel P1 through the smart maintenance system.

[0082] After receiving the task notification, maintenance personnel P1 takes mobile phone A1 to the elevator site. After arriving at the site, open the smart maintenance client C1 and click the plug-in interface Load. At this time, client C1 will automatically download the corresponding plug-in from the local cache or server and load it. After loading, the maintenance personnel click the call interface Run, and client C1 will display the maintenance steps and requirements on the mobile phone screen in a clear and concise interactive interface. Taking the maintenance of the elevator door system as an example, client C1 will first prompt the maintenance personnel to turn off the elevator power and set a warning sign, and then gradually show the operation method of the door machine motor performance test, such as connecting the test instrument, starting the motor and reading the current, speed and other parameters, and require the maintenance personnel to enter the test data into the client. In the door lock sensitivity check link, the client will explain in detail how to use special tools to simulate the door lock switch action, check the door lock response time and locking strength, and provide a standard data range for maintenance personnel to compare and judge. During the entire maintenance process, the maintenance personnel complete each operation in sequence according to the plug-in prompts, and use the mobile phone to record the maintenance process.

[0083] When the maintenance personnel P1 completes all maintenance operations, he clicks the plug-in interface Upload. At this time, the mobile phone A1 will upload the data recorded during the maintenance process (such as various test parameters, replacement parts information, etc.) and the video file to the elevator effect evaluation model M6 through the network. After receiving the data and video, the effect evaluation model M6 uses advanced data analysis algorithms and image recognition technology to process them. For example, by analyzing the performance test data of the door machine motor, it is determined whether the output power and efficiency of the motor have returned to the normal range, and the difference between the door lock sensitivity inspection data and the standard value is compared. At the same time, the image recognition technology is used to perform a standardized inspection of the maintenance operations in the video, such as checking whether the maintenance personnel use the tools correctly and whether they operate in the prescribed order. Based on these analysis results, the effect evaluation model M6 accurately obtains the effect of this maintenance and scores according to the preset scoring criteria.

[0084] After the effect evaluation model M6 completes the evaluation and scoring, it automatically organizes the detailed information of this maintenance into a case and pushes it to the elevator maintenance case model M1. For example, the basic information of the elevator (brand, model, installation location, etc.), fault conditions, maintenance operation details, plug-in usage, effect evaluation data, and final score are integrated into a complete case and stored in the maintenance case model M1 for maintenance personnel across the country to query and refer to in subsequent work.

[0085] Finally, when the maintenance is completed and the effect evaluation is qualified, the system automatically resets the health of the elevator to 100, and the elevator returns to normal operation and waits for the next status monitoring and maintenance cycle.

[0086] Implementation Cases

[0087] Case 1: Maintenance of a high-rise residential elevator failure

[0088] In a high-rise residential area, one of the elevators suddenly experienced abnormal jitter and flickering cabin lighting during operation. The DTU terminal T1 quickly collected these status information and uploaded it to the intelligent maintenance system. The communication service terminal Z1 received and stored the data and pushed it to the status and fault model M2. After analysis, the diagnostic model M3 combined the historical operation data of the elevator and determined that there might be a fault in the elevator's electrical system, involving abnormal inverter parameters and loose connections of some lines. The calculation showed that the health of the elevator was 15, which was in urgent need of maintenance.

[0089] Task model M4 determines that experienced maintenance personnel P1 is responsible for the elevator maintenance task according to the duty list, and issues a command to the automatic programming model M5: "Generate a plug-in for this elevator, the content is standard maintenance process + electrical system maintenance (including inverter parameter inspection and adjustment, line connection tightness inspection, electrical component performance test), the video needs to be uploaded, the loading interface is Load, the running interface is Run, and the upload interface is Upload."

[0090] After the automatic programming model M5 generates the plug-in, P1 receives the task and goes to the site. The plug-in is loaded through the intelligent maintenance client C1 and the operation is performed according to the prompts. When checking the inverter parameters, it is found that several key parameters are out of the normal range, and adjustments are made according to the plug-in's instructions. When checking the line connection, it is found that a power cord is loose. After re-tightening, the electrical component performance test is carried out and the test data is entered into the client. The whole process is recorded and uploaded to the effect evaluation model M6.

[0091] The effect evaluation model M6 analyzes the data and video, confirms that the inverter parameters have returned to normal, the performance of the electrical components is stable, and the maintenance operations are standardized, and gives this maintenance a score of 90. The case is pushed to the maintenance case model M1 for reference and learning by other maintenance personnel. After that, the health of the elevator is reset to 100 and normal operation is restored.

[0092] Case 2: Maintenance and dispatch of elevator groups in a shopping mall

[0093] A large shopping mall has many elevators. During a routine inspection, the elevator model found that three elevators had problems to varying degrees. One elevator had a jamming phenomenon when the elevator door closed, and the health level was 25; another elevator had a slight noise when running, and the health level was 35; and another elevator had a deviation in leveling accuracy, and the health level was 20.

[0094] The diagnostic model M3 prioritizes the maintenance of elevators with leveling accuracy deviations based on the fault condition and health, because this problem may affect the safety and convenience of passengers entering and exiting the elevator. The task model M4 arranges the maintenance personnel P1 who is good at debugging the elevator mechanical system to be responsible for the maintenance task of this elevator based on the position and skills of the maintenance personnel, and generates corresponding plug-in instructions.

[0095] After P1 arrived at the site, he checked, adjusted and lubricated the elevator's traction system, guide rails and other components related to leveling accuracy according to the plug-in prompts. After completing the maintenance, he uploaded the data and video. After the effect evaluation model M6 evaluated it as qualified, it stored the case in the maintenance case model M1. At the same time, the task model M4 continued to arrange the maintenance tasks of the other two elevators, and completed the intelligent and efficient maintenance work of the entire shopping center elevator group in turn, ensuring the safe and stable operation of the shopping center elevators and improving the customer's elevator experience.

[0096] Through the above implementation methods and case studies, the entire elevator intelligent maintenance system has realized full-process intelligent operation from elevator status monitoring, fault diagnosis, task allocation, plug-in generation, on-site maintenance to effect evaluation and knowledge sharing, effectively improving the efficiency, quality and standardization of elevator maintenance.

[0097] In summary, the present invention has the following beneficial effects:

[0098] 1. Intelligent maintenance

[0099] Innovatively leveraging the power of the AI ​​big model to automatically program and generate maintenance plug-ins, this feature gives maintenance work a high degree of intelligence and autonomy. In an offline state, maintenance plug-ins can still play a key role, effectively breaking through the traditional maintenance's dependence on the network environment, and greatly expanding the implementation scenarios and flexibility of maintenance work. For example, in some old building elevators with weak network signal coverage or elevator facilities in remote areas, maintenance personnel can still carry out their work smoothly with pre-downloaded plug-ins to avoid maintenance delays due to network problems.

[0100] With the precise guidance of the smart plug-in, maintenance personnel can quickly locate maintenance priorities and key operating steps, significantly reducing the large amount of time wasted in the traditional maintenance mode due to blind troubleshooting and experience differences. Maintenance tasks that may have taken hours or even longer in the past can be greatly shortened to tens of minutes or even shorter with the assistance of smart plug-ins, effectively improving maintenance efficiency. This efficiency improvement not only reduces elevator downtime and reduces the impact on the normal use of elevators by people in the building, but also directly reduces the labor and material costs caused by long-term maintenance, such as reducing the overtime hours of maintenance personnel and unnecessary loss of maintenance tools and parts.

[0101] From the perspective of customer experience, elevators can resume normal operation more quickly, greatly improving customer satisfaction and convenience in elevator use, and enhancing customer trust and recognition of elevator managers and maintenance service providers.

[0102] 2. Knowledge Sharing

[0103] The present invention builds an efficient knowledge sharing ecosystem. The case data generated during each elevator maintenance process, including the type of elevator failure, maintenance operation details, plug-in information used, and the final maintenance effect evaluation, will be automatically uploaded to the maintenance case model in the elevator model. This measure enables maintenance personnel across the country to easily obtain these valuable practical experience and knowledge results.

[0104] For inexperienced maintenance personnel, they can quickly learn the methods and techniques for handling various types of elevators in various fault situations by studying these rich cases, accelerate the growth and improvement of their own professional skills, shorten the training cycle, and thus independently undertake maintenance tasks faster and ensure the quality of work. For experienced and senior maintenance personnel, these case data also provide a platform for mutual communication and learning, from which they can discover new maintenance ideas and methods, further optimize their own maintenance strategies, and also help them have a more comprehensive and in-depth grasp of the overall development trends and common problems of the elevator industry.

[0105] From the perspective of the macro-development of the elevator maintenance industry, this knowledge sharing mechanism has promoted the dissemination and inheritance of technology and experience within the industry, broken down information barriers between regions and enterprises, and is conducive to the overall improvement and balanced development of the entire industry's technical level, injecting strong impetus into the sustainable development of the elevator maintenance industry.

[0106] 3. Improve the quality of maintenance

[0107] By conducting in-depth analysis of the detailed data generated during the maintenance process and the maintenance operation video, the present invention achieves accurate evaluation and effective monitoring of the maintenance quality. At the data level, it is possible to accurately monitor the performance parameter changes of each component of the elevator before and after maintenance, such as the elevator's running speed stability, the response time and braking force of the braking system, the voltage and current fluctuations of the electrical system, etc., so as to determine whether the maintenance operation has truly achieved the expected optimization and repair effect.

[0108] In terms of video analysis, the maintenance personnel's operational standardization and completeness can be directly observed, such as whether key components are disassembled, cleaned, installed and debugged according to standard procedures, whether some important inspection links are omitted, etc. This multi-dimensional analysis and evaluation method is more accurate and scientific than the traditional method of subjectively judging the maintenance quality based solely on the subsequent operation of the elevator.

[0109] Once problems or deficiencies are found in the maintenance quality, they can be promptly fed back to the maintenance personnel for rectification and optimization, thus forming a closed-loop quality control system to ensure that every maintenance work can effectively improve the operating performance and safety of the elevator, reduce the probability of elevator failures, and provide passengers with a safer and more reliable elevator environment.

[0110] 4. Unification of maintenance standards

[0111] The present invention generates a unified maintenance plug-in through automatic programming based on rigorous maintenance standard procedures and accurate diagnostic data, which fundamentally solves the industry problem of inconsistent maintenance standards. No matter in which region or by which maintenance personnel perform elevator maintenance tasks, as long as the plug-in generated by the present invention is used, it can ensure that the elevator is fully and carefully maintained according to the same standard procedures.

[0112] For example, for the maintenance of the elevator door system, the plug-in will clearly stipulate a series of standard operating procedures and technical requirements, from the inspection and lubrication of the mechanical parts of the door machine to the electrical performance test of the door lock and the safety circuit verification. The maintenance personnel only need to follow the prompts of the plug-in to complete the operations in sequence. This standardized maintenance model effectively avoids the problem of uneven maintenance quality caused by differences in personal experience, different regional habits or inconsistent internal standards of the enterprise, so that elevators can be maintained and maintained in a unified and standardized manner across the country, greatly improving the stability and safety of the overall operation of elevators, and laying a solid foundation for the standardized management and healthy development of the elevator industry.

[0113] The technical solutions provided by the embodiments of the present invention are introduced in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the embodiments of the present invention. The description of the above embodiments is only applicable to help understand the principles of the embodiments of the present invention. At the same time, for those skilled in the art, according to the embodiments of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. An intelligent elevator maintenance method based on artificial intelligence, characterized in that: The following steps are involved: Step S1: The elevator collects and uploads status and fault information to the intelligent maintenance system in real time through the DTU terminal, and the intelligent maintenance system pushes it to the status and fault model of the elevator large model; Step S2: The diagnostic model of the large elevator model is inspected according to a preset period, and based on the elevator operation data, historical fault records and diagnostic rules, the elevators that need maintenance and their maintenance items are located, and the maintenance priority is determined; Step S3: The task model of the elevator large model determines the maintenance personnel according to the diagnosis results and the duty list, generates the maintenance tasks and sends instructions to the automatic programming model; Step S4: The automatic programming model generates a client-callable plug-in based on the instructions and its own learning and training results, and notifies the task model to push the task information and plug-in to the maintenance personnel; Step S5: The maintenance personnel use the mobile smart maintenance client to load the plug-in and complete the maintenance according to the prompts, while recording the maintenance process video. After completion, upload the data and video to the effect evaluation model; Step S6: The effect evaluation model uses data analysis and image recognition technology to process the uploaded information, derives the maintenance effect and scores it, and then generates a case and pushes it to the maintenance case model; Step S7: If the maintenance effect evaluation is qualified, the system automatically resets the elevator health to 100, so that the elevator resumes normal operation.

2. The elevator intelligent maintenance method based on artificial intelligence according to claim 1 is characterized in that: The construction of the elevator big model includes the local deployment of the general big model, and after inputting the elevator industry data, multiple sub-models are constructed through data cleaning, word segmentation and tokenization, data enhancement and standardization, sampling and weight adjustment, and natural language processing. The sub-models include at least a maintenance case model, a status and fault model, a diagnosis model, a task model, an automatic programming model, and an effect evaluation model.

3. The elevator intelligent maintenance method based on artificial intelligence according to claim 1 is characterized in that: The automatic programming model automatically generates code plug-ins based on user instructions and preset maintenance rules by learning the code bases and programming languages ​​corresponding to a large number of maintenance projects, and the generation process involves natural language processing to convert instructions into programming languages.

4. The intelligent elevator maintenance method based on artificial intelligence according to claim 3 is characterized in that: The maintenance items and codes are automatically associated through the AI ​​big data model to extract the program source code header annotations and convert them into big data tags. The maintenance rules are automatically created through big data tags and the latest national standards of the maintenance items through OCR technology and keyword matching technology. Maintenance items that do not match the national standards constitute enterprise standards.

5. An intelligent elevator maintenance device based on artificial intelligence, characterized in that: include: The information collection and transmission module is installed in the elevator and DTU terminal to collect elevator status and fault information and upload it to the intelligent maintenance system; The diagnostic module is located in the large elevator model. It performs regular inspections based on elevator operation data and historical fault information to locate elevators and maintenance items that require maintenance. The task generation module is set in the elevator model to determine the maintenance personnel and generate maintenance tasks according to the diagnosis results; The automatic programming module is set in the elevator model and generates plug-ins according to the instructions of the task generation module; The client module is installed on the mobile phone, receives task information and plug-ins, guides maintenance personnel to work and upload data; The effect evaluation module is in the elevator model, which evaluates the maintenance effect and generates cases; The knowledge sharing module is integrated into the elevator model to enable sharing and communication of maintenance cases among maintenance personnel.

6. The intelligent elevator maintenance device based on artificial intelligence according to claim 5, characterized in that: The elevator model also includes a maintenance case model, which is used to store cases generated by the effect evaluation module to provide a reference for subsequent maintenance.

7. The intelligent elevator maintenance device based on artificial intelligence according to claim 5 is characterized in that: The intelligent maintenance system includes a maintenance server, a communication server and a database. The communication server receives elevator information and stores it in the database. The maintenance server processes elevator data and interacts with the elevator large model. The database stores elevator operation data, fault information, maintenance task information, plug-in information and maintenance case information.

8. An intelligent elevator maintenance device based on artificial intelligence, characterized in that: It includes elevators, DTU terminals, and mobile phones. The elevators communicate with the intelligent maintenance system through the DTU terminals. The mobile phones are installed with intelligent maintenance clients and interact with the intelligent maintenance system. The DTU terminals continuously collect elevator status and fault information. The mobile phones receive and display task information and plug-ins to assist maintenance personnel in completing tasks and uploading data.

9. An intelligent elevator maintenance system based on artificial intelligence, characterized in that: It includes a cloud-based intelligent maintenance system and an elevator large model. The intelligent maintenance system and the elevator large model work together. The intelligent maintenance system is responsible for elevator data collection, storage and preliminary processing, while the elevator large model performs in-depth analysis, diagnosis, task allocation, plug-in generation, effect evaluation and knowledge management. The two together realize the elevator intelligent maintenance process.

10. According to the artificial intelligence-based elevator intelligent maintenance system of claim 9, the cloud-based intelligent maintenance system adopts the mainstream Web API application architecture, data interaction adopts the JSON format, the database adopts a relational database, and communication between the client and the server is realized based on HTTPS. The establishment process includes investigating customer needs, determining technical solutions, programming development, testing and verification, and system online steps.

Images