Intelligent property inspection system based on artificial intelligence

Abstract

The invention relates to the technical field of intelligent inspection, in particular to an intelligent property inspection system based on artificial intelligence, comprising: a plurality of inspection robots inspect an elevator according to a preset inspection path; the data acquisition module acquires the use frequency, the motor current, the motor voltage and the door motor current of the elevator; the state analysis module determines the corresponding relation and the relation duration of the motor voltage and the motor current according to the motor current and the motor voltage, determines the door motor current fluctuation condition according to the door motor current, and determines the elevator health index according to the corresponding relation, the relation duration and the door motor current fluctuation condition so as to determine the elevator abnormal opportunity; the rule analysis module judges whether elevator use is regular or not according to the use frequency and the peak time period, and determines a focus region of interest according to the judgment result or the elevator health index; and the path planning module adjusts a preset inspection path according to the elevator key concern area, the elevator abnormal opportunity, the manual instruction and the real-time machine position. The inspection efficiency and pertinence of the inspection robot are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent inspection technology, and in particular to an intelligent property inspection system based on artificial intelligence. Background Technology

[0002] To address the problems of low efficiency, easy omissions, and strong subjectivity in traditional manual inspections, the property intelligent inspection system utilizes technologies such as artificial intelligence and the Internet of Things to conduct automated and intelligent inspections of the operational status of facilities and equipment, environmental sanitation, and safety hazards within the property area. It can not only accurately detect problems in real time, but also provide rapid early warnings, thereby improving inspection efficiency and management level, and reducing labor costs and safety risks.

[0003] Chinese Patent Application Publication No. CN115924666A discloses an intelligent elevator inspection method, device, system, electronic equipment, and medium. The inspection method includes: an inspection robot located in the elevator shaft and receiving inspection tasks in real time; when it receives an inspection task, it first obtains its own positioning information and determines whether it is located within the area of ​​the inspection location information based on the positioning information; if not, it generates an inspection route based on the current positioning information and the inspection location information, and then moves to the area of ​​the inspection location information according to the inspection route, collects inspection image information of the area of ​​the inspection location information, and sends the inspection image information to the management terminal through the server; the management terminal obtains the inspection result of the area of ​​the inspection location information based on the inspection image information.

[0004] Therefore, although the above technical solutions can avoid affecting the normal operation of elevators, have high inspection safety, and save labor costs, they still have the following problems: the above technical solutions mainly rely on inspection robots to collect inspection image information to obtain inspection results, the data obtained is relatively simple, and the inspection route of the inspection robot cannot be dynamically adjusted in real time according to the actual situation. Summary of the Invention

[0005] To address this, the present invention provides an artificial intelligence-based intelligent property inspection system to overcome the problems of existing intelligent inspection systems for property management, which collect limited data and cannot dynamically adjust inspection routes in real time when inspecting elevators.

[0006] To achieve the above objectives, the present invention provides an intelligent property inspection system based on artificial intelligence, comprising: The elevator inspection module includes several inspection robots, which are used to inspect the elevator according to a preset inspection path. The data acquisition module is used to collect the daily usage frequency of the elevator, as well as the motor current, motor voltage, and door operator current during elevator operation. The status analysis module is connected to the data acquisition module and is used to determine the correspondence and duration of the motor voltage and current during the elevator lifting process based on the motor current and motor voltage within a preset time period, and to determine the fluctuation of the door machine current based on the door machine current, and to determine the elevator health index based on the correspondence, the duration of the relationship and the fluctuation of the door machine current to determine the timing of elevator abnormalities. The pattern analysis module is connected to the data acquisition module and the status analysis module respectively. It is used to determine the peak time period based on the elevator usage frequency to determine whether the use of each elevator is regular, and to determine the key areas of concern based on the usage pattern judgment results or the elevator health index. The path planning module is connected to the state analysis module, the pattern analysis module, and the elevator inspection module, respectively, and is used to adjust the preset inspection path according to the key areas of the elevator, the timing of elevator malfunctions, manual instructions, and the real-time machine position of the inspection robot.

[0007] Furthermore, the state analysis module determines the motor current fluctuation based on the motor current, determines the motor voltage fluctuation based on the motor voltage, and determines the correspondence and the duration of the relationship based on the motor current fluctuation and the motor voltage fluctuation. The corresponding relationships include constant voltage with increased current, decreased voltage with increased current, and voltage fluctuation with abnormal current.

[0008] Furthermore, the status analysis module constructs a current change waveform diagram based on the gate machine current, determines the current peak value and current trough value based on the current change waveform diagram, and determines the gate machine current fluctuation based on the current peak value and the current trough value.

[0009] Furthermore, the state analysis module determines the first health impact coefficient of the motor on the elevator health based on the correspondence and duration of the relationship between the motor current and the motor voltage, determines the second health impact coefficient of the door operator on the elevator health based on the fluctuation of the door operator current, determines the elevator health index based on the first health impact coefficient and the second health impact coefficient, and determines the elevator abnormality timing based on the elevator health index and the preset health index.

[0010] Furthermore, the state analysis module determines the relationship weight and time weight based on the corresponding relationship and the relationship duration, and determines the first health impact coefficient based on the relationship weight, the time weight, the relationship duration, and the preset duration.

[0011] Furthermore, the pattern analysis module divides a day into several time intervals based on a preset time interval, counts the frequency of elevator use in each time interval, and determines the peak time period for elevator use each day based on the usage frequency.

[0012] Furthermore, the pattern analysis module determines whether the use of each elevator is regular based on the overlapping time periods of the daily peak hours of the elevator within a preset time period and the overlapping time periods and the type of work and rest.

[0013] Furthermore, the pattern analysis module identifies key areas of interest in the elevator, including: If the health index of a single elevator is lower than the preset health index, or if the usage pattern of a single elevator is determined, then that elevator is identified as a key area of ​​concern.

[0014] Furthermore, the path planning module determines the priority focus area based on the elevator's key focus area, the timing of elevator malfunctions, and the timing and area of ​​manual instructions. It also determines the running distance of the inspection robot to reach the priority focus area based on the real-time machine position and adjusts the preset inspection path based on the running distance.

[0015] Furthermore, the path planning module determines whether there is a time overlap based on the timing of elevator malfunctions and the timing of manual instructions, determines whether there is a regional overlap based on the instruction issuance area and the key focus area, and determines the priority focus area based on the time overlap results and the regional overlap results.

[0016] Compared with existing technologies, the beneficial effects of this invention are as follows: Through the collaborative work of multiple modules, this invention achieves comprehensive collection and in-depth analysis of elevator operation data, accurately assesses the elevator's health status, and identifies potential elevator malfunction risks in advance; it determines key areas of concern based on elevator usage patterns and operating status, and dynamically optimizes inspection paths in conjunction with the real-time location of inspection robots, significantly improving inspection efficiency and targeting, and reducing labor and time costs; simultaneously, through intelligent monitoring and management, it effectively enhances elevator operation safety and reliability, ensures passenger safety, and strengthens the intelligence level and service quality of property management.

[0017] Furthermore, this invention determines a first health impact coefficient based on the correspondence between motor current and voltage and its duration, accurately capturing abnormal motor operation and promptly reflecting potential motor failure risks. A second health impact coefficient is determined using fluctuations in the door operator current, focusing on the frequently operating door operator system to sensitively detect anomalies such as door operator jamming and component wear. Combining these two factors to calculate the elevator health index constructs a comprehensive and dynamic elevator health assessment system. By comparing this system with a preset health index to determine the timing of anomalies, early warnings of elevator malfunctions can be achieved, helping inspection robots and maintenance personnel intervene in advance, improving elevator operational reliability and safety, saving property inspection time, and enhancing the quality of property safety inspections.

[0018] Furthermore, this invention combines the elevator health index and elevator usage patterns to form a dual judgment standard. The elevator health index focuses on assessing the elevator's own health status, while the usage patterns are based on actual operating scenarios. The two complement each other to construct a more comprehensive and intelligent elevator key attention area screening system, which significantly improves the accuracy and initiative of elevator maintenance management, reduces the incidence of sudden failures, saves inspection costs, and improves the operation and maintenance efficiency of the inspection system.

[0019] Furthermore, this invention rationally adjusts the inspection path based on human instructions and key areas of concern identified by the system, enabling the inspection robot to flexibly handle complex scenarios, avoiding blind actions and improving efficiency. It can prioritize handling anomalies in key elevator areas to ensure safe and stable elevator operation, while also handling other inspection tasks to guarantee comprehensiveness and integrity. This makes the robot's inspection work more efficient, intelligent, and reliable, providing strong support for elevator safety and further improving the quality of property security inspections.

[0020] Furthermore, the path planning module of this invention performs dual judgments on the time intersection of elevator anomalies and manual instructions, as well as the regional intersection of instruction issuance areas and key areas of concern. This enables it to quickly and accurately lock down the priority areas of concern, avoiding resource waste and response delays caused by mixed information. It significantly improves the timeliness and pertinence of the inspection robot's response to anomalies, effectively ensures the safe operation of key elevator areas, significantly improves the efficiency and quality of elevator inspections, and enhances the quality of property security inspections. Attached Figure Description

[0021] Figure 1 This is a connection block diagram of the intelligent property inspection system according to an embodiment of the present invention; Figure 2 This is a flowchart of a property intelligent inspection system according to an embodiment of the present invention; Figure 3 This is a flowchart illustrating the relationship between motor current and voltage in an embodiment of the present invention. Figure 4 This is a flowchart for determining the timing of elevator malfunctions in an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0023] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0024] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0025] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0026] Please see Figure 1 , Figure 2 As shown, Figure 1 This is a connection block diagram of the intelligent property inspection system according to an embodiment of the present invention. Figure 2 This is a flowchart of a property intelligent inspection system according to an embodiment of the present invention. Specifically, the present invention provides an artificial intelligence-based property intelligent inspection system, including: The elevator inspection module includes several inspection robots, which are used to inspect the elevator according to a preset inspection path. The data acquisition module is used to collect the daily usage frequency of the elevator, as well as the motor current, motor voltage, and door operator current during elevator operation. The status analysis module is connected to the data acquisition module and is used to determine the correspondence and duration of the motor voltage and current during the elevator lifting process based on the motor current and motor voltage within a preset time period, and to determine the fluctuation of the door machine current based on the door machine current, and to determine the elevator health index based on the correspondence, the duration of the relationship and the fluctuation of the door machine current to determine the timing of elevator abnormalities. The pattern analysis module is connected to the data acquisition module and the status analysis module respectively. It is used to determine the peak time period based on the elevator usage frequency to determine whether the use of each elevator is regular, and to determine the key areas of concern based on the usage pattern judgment results or the elevator health index. The path planning module is connected to the state analysis module, the pattern analysis module, and the elevator inspection module, respectively, and is used to adjust the preset inspection path according to the key areas of the elevator, the timing of elevator malfunctions, manual instructions, and the real-time machine position of the inspection robot.

[0027] It is understandable that traditional property elevator inspections suffer from problems such as low efficiency, inaccurate fault diagnosis, and unreasonable inspection route planning. Manual elevator inspections are inefficient, have limited coverage, and cannot monitor elevator operation data in real time and comprehensively to grasp the elevator's health status. Moreover, inspection routes are often fixed and cannot be flexibly adjusted according to the actual operating conditions and usage patterns of the elevator, making it difficult to promptly investigate key fault areas and detect and deal with potential risks in a timely manner.

[0028] Understandably, single data points cannot fully reflect the health status of an elevator. The operating status of the motor and door operator can respectively reflect elevator lifting and lowering malfunctions and opening / closing malfunctions. Combining these two data points provides a more comprehensive understanding of the elevator's operating status. Different motor malfunctions often lead to specific patterns of change in motor voltage and current. For example, a short circuit in the motor windings may cause an increase in current and abnormal voltage fluctuations; while damage to the motor bearings will cause periodic fluctuations in current, while the voltage will remain relatively stable. By studying the correspondence and duration of the relationship between motor voltage and current, potential motor malfunctions can be diagnosed more accurately, improving the safety and reliability of elevator operation. Furthermore, the opening and closing of elevator doors is mainly controlled by the door operator. During the door opening and closing process, the current changes with the door's movement. By collecting the door operator's current value, its operating status can be understood. For example, a sudden and sustained abnormal increase in current during door closing may indicate that the door has encountered an obstacle or that the door operator's mechanical parts are jammed; if the door operator current is too low, it may indicate a malfunction in the door operator's drive circuit or an open circuit in the motor windings.

[0029] In one specific embodiment, there are 10 to 20 inspection robots, preferably 15. Each robot is equipped with a camera. By clearly defining the number and location of the elevators to be inspected, as well as the floor structure of the building, a pre-defined inspection path can be planned for the robots. The inspection area (residential complex) can be divided into several sub-areas, with a certain number of robots assigned to each sub-area for inspection. For example, every three buildings can be divided into one sub-area, with one robot responsible for inspecting the elevators in each building. The robots inspect the elevators sequentially according to the building number, which constitutes the pre-defined inspection path. In implementation, the method for determining the pre-defined inspection path can be selected according to the actual situation; no specific limitations are imposed here, nor will they be elaborated further.

[0030] In another specific embodiment, the preset time period ranges from 15 to 30 days. Preferably, the preset time period is 20 days. In practice, the range and preferred value of the preset time period can be determined according to the actual situation. No specific limitation is made here, and it will not be elaborated further.

[0031] In one specific embodiment, the present invention can also be applied to fields with elevator equipment such as shopping malls, office buildings, industrial parks, and schools. The application scenarios of the technical solution are not limited here.

[0032] This invention achieves comprehensive collection and in-depth analysis of elevator operation data through multi-module collaborative operation, accurately assessing the elevator's health status and identifying potential malfunction risks in advance. It identifies key areas of concern based on elevator usage patterns and operating status, and dynamically optimizes inspection paths using the real-time location of inspection robots, significantly improving inspection efficiency and targeting while reducing labor and time costs. Simultaneously, through intelligent monitoring and management, it effectively enhances elevator operational safety and reliability, ensuring passenger safety and improving the intelligence level and service quality of property management.

[0033] Please see Figure 3 As shown, it is a flowchart of determining the correspondence between motor current and voltage in an embodiment of the present invention. Specifically, the state analysis module determines the motor current fluctuation based on the motor current, determines the motor voltage fluctuation based on the motor voltage, and determines the correspondence and the duration of the relationship based on the motor current fluctuation and the motor voltage fluctuation. The corresponding relationships include constant voltage with increased current, decreased voltage with increased current, and voltage fluctuation with abnormal current.

[0034] Understandably, in elevator fault diagnosis, there is usually a certain correlation between motor voltage and motor current. During normal operation, the motor current and voltage have a certain proportional relationship, which conforms to Ohm's law. When the elevator load is stable, the voltage is stable, and the current is also relatively stable. For example, during the elevator's uniform upward or downward movement, if the voltage remains near its rated value, the current will also remain within a relatively fixed range to maintain the normal operation of the motor and provide appropriate driving force.

[0035] Understandably, there are three possible relationships between motor current and motor voltage during elevator malfunctions: constant voltage with increased current, decreased voltage with increased current, and fluctuating voltage with abnormal current. For example, when a partial short circuit occurs in the motor windings, the winding resistance decreases, and the current increases significantly, while the voltage may remain at a normal level; this corresponds to a constant voltage with increased current. When the elevator's power supply line experiences poor contact or insufficient power capacity, the voltage output to the motor decreases. To maintain elevator operation, the motor needs to output the same power, so the current increases; this corresponds to a decreased voltage with increased current. If the elevator's motor controller malfunctions, the output voltage may become unstable, causing fluctuations in the motor voltage. In this case, the motor current will also change abnormally with the voltage fluctuations, no longer having a stable relationship with the normal motor voltage; this is known as voltage fluctuation with abnormal current.

[0036] In one specific embodiment, based on real-time monitoring, the current and voltage fluctuations are matched. The motor current fluctuation is determined based on the motor current, and the motor voltage fluctuation is determined based on the motor voltage. The corresponding relationship is then determined based on these two factors. When the voltage is constant, a current increase of 1 to 1.5 times within the same time period is considered a constant voltage with increasing current. When the voltage decreases by 5% to 20%, and the current increase is also 5% to 20% within the same time period, it is considered a decrease in voltage with increasing current. If the voltage fluctuation range is ±10% to ±20%, and the current fluctuation range exceeds ±20%, it is considered an abnormal voltage and current fluctuation. In practice, the method for determining the corresponding relationship can be determined according to the actual situation; no specific limitations are imposed here, and it will not be elaborated further.

[0037] In another specific embodiment, when a certain correspondence is detected between the motor current and the motor voltage fluctuations, the moment is recorded as the start time; when the correspondence no longer holds, the moment is recorded as the end time, and the difference between the start and end times is the duration of the relationship.

[0038] Specifically, the status analysis module constructs a current change waveform diagram based on the gate machine current, determines the current peak value and current trough value based on the current change waveform diagram, and determines the gate machine current fluctuation based on the current peak value and the current trough value.

[0039] Understandably, the door operator current increases and then decreases during door opening and closing. When something obstructs the elevator door's movement, the door operator needs to overcome additional resistance to drive the door, increasing the motor load and consequently the current. In cases of severe obstruction, the current may significantly exceed the rated current, even triggering the overload protection device. Faulty elevator controllers, faulty sensors, or poor wiring connections can also affect the normal operation of the door operator, causing fluctuations in the door operator current.

[0040] Please see Figure 4 As shown, it is a flowchart for determining the timing of elevator malfunctions according to an embodiment of the present invention. Specifically, the state analysis module determines the first health impact coefficient of the motor on the elevator health based on the correspondence and duration of the relationship between the motor current and the motor voltage, determines the second health impact coefficient of the door operator on the elevator health based on the fluctuation of the door operator current, determines the elevator health index based on the first health impact coefficient and the second health impact coefficient, and determines the timing of elevator malfunctions based on the elevator health index and the preset health index.

[0041] In one specific embodiment, the peak and trough values ​​of the current wave are determined based on the current fluctuation of the gate operator. Several current fluctuation amplitudes are then determined based on the pairwise corresponding peak and trough values. The current fluctuation amplitude = Second health impact coefficient = Preferably, the normal fluctuation range of the door operator current is 0.5 to 1.5A, and the elevator health index is calculated as 1 - first health impact coefficient × second health impact coefficient. In practice, the range and preferred value of the normal fluctuation range can be determined based on actual conditions; no specific limitations are imposed here, nor will they be elaborated further.

[0042] In another specific embodiment, if the elevator health index is greater than or equal to a preset health index, the elevator is determined to be normal; if the elevator health index is less than the preset health index, the elevator is determined to be abnormal. The preset health index ranges from 0.6 to 0.75, preferably 0.7. In practice, the range and preferred value of the preset health index can be determined according to the actual situation, and are not specifically limited here, nor will they be elaborated further.

[0043] This invention determines a first health impact coefficient based on the correspondence between motor current and voltage and its duration, accurately capturing abnormal motor operation and promptly reflecting potential motor failure risks. A second health impact coefficient is determined using fluctuations in the door operator current, focusing on the frequently operating door operator system to sensitively detect anomalies such as door operator jamming and component wear. Combining these two factors to calculate an elevator health index constructs a comprehensive and dynamic elevator health assessment system. By comparing this index with a preset health index to determine the timing of anomalies, early warnings of elevator malfunctions can be achieved, helping inspection robots and maintenance personnel intervene in advance, improving elevator operational reliability and safety, saving property inspection time, and enhancing the quality of property safety inspections.

[0044] Specifically, the state analysis module determines the relationship weight and time weight based on the corresponding relationship and the relationship duration, and determines the first health impact coefficient based on the relationship weight, the time weight, the relationship duration and the preset duration.

[0045] In a specific embodiment, the order of the impact of the three correspondences on elevator health from largest to smallest is: voltage fluctuation and abnormal current > voltage decrease and current increase > constant voltage and current increase. Therefore, the relationship weights correspond to the degree of impact of the relationship on elevator health. Preferably, the relationship weights are 0.5, 0.3, and 0.2, respectively. The sum of the relationship weights for the three correspondences is 1. The relationship duration can be determined by the length of duration, and the weights are arranged according to the length of duration. Preferably, the corresponding time weights are 0.5, 0.3, and 0.2. The influence coefficient of the correspondence type = ×Time weight, where the first health impact coefficient is the sum of the impact coefficients corresponding to the three relationship types. In implementation, the range and preferred values ​​of the relationship weight and time weight can be determined according to the actual situation, and are not specifically limited here, nor will they be elaborated further.

[0046] Specifically, the pattern analysis module divides a day into several time intervals based on a preset time interval, counts the frequency of elevator use in each time interval, and determines the peak time period for elevator use each day based on the usage frequency.

[0047] In one specific embodiment, the preset time interval ranges from 0.5h to 1.5h, preferably 1h, meaning each hour within a 24-hour period is considered a time interval. The usage frequency of a single elevator within each time interval is determined by the number of times the floor number buttons of a single elevator are pressed within that time interval. If the usage frequency is greater than the preset usage frequency, the corresponding time interval is identified as a peak period; if the usage frequency is less than or equal to the preset usage frequency, the corresponding time interval is not identified as a peak period. The preset usage frequency ranges from 10 to 35 times, preferably 20 times. The preset usage frequency is based on the number of times the floor number buttons of a single elevator are pressed within 1 hour. The range and preferred values ​​of the preset usage frequency and preset time interval can be determined according to actual conditions, and are not specifically limited here, nor will they be elaborated further.

[0048] Specifically, the pattern analysis module determines whether the use of each elevator is regular based on the overlapping time periods of the daily peak hours of the elevator within a preset time period and the overlapping time periods and the type of work and rest.

[0049] Understandably, overlapping time periods and overlap rates can directly reflect the consistency and stability of elevators during daily peak hours. Longer overlapping time periods indicate that the elevator is consistently used at a high frequency within a fixed timeframe, thus allowing for the determination of whether elevator usage is regular and providing a basis for identifying key areas for elevator monitoring.

[0050] It is understood that the work schedule categories include weekday work schedules and rest day work schedules. Different work schedule categories correspond to different high-frequency elevator usage states. Therefore, elevator usage patterns can be determined separately for weekday work schedules and rest day work schedules.

[0051] In one specific embodiment, by determining the peak time period for each elevator each day, the overlapping time period of elevator operation within a preset time period can be determined. Furthermore, by separately judging the overlapping peak time periods for weekdays and rest days, the overlapping time periods for the peak time periods of a single elevator corresponding to the weekday category and the rest day category can be determined. If the overlapping time period on weekdays is more than 4 hours and the overlapping time period on rest days is more than 2 hours, it indicates that the usage of a single elevator is regular; conversely, it indicates that the usage of a single elevator is irregular. In practice, the process of judging whether elevator usage is regular can be determined based on the specific judgment scenario or historical elevator usage data, etc., and is not specifically limited here, nor will it be elaborated further.

[0052] Specifically, the pattern analysis module identifies key areas of interest in the elevator, including: If the health index of a single elevator is lower than the preset health index, or if the usage pattern of a single elevator is determined, then that elevator is identified as a key area of ​​concern.

[0053] Understandably, the elevator health index dynamically assesses elevator performance based on the correlation and duration of the relationship between elevator motor voltage and electrode current, as well as fluctuations in door operator current. If the elevator health index of a single elevator falls below a preset value, it indicates a potential malfunction or performance degradation risk, thus identifying it as a key area of ​​concern. Furthermore, elevators typically exhibit certain usage patterns during operation. Combining these patterns helps determine if an elevator is used frequently and identifies key areas for monitoring. This allows inspection robots or maintenance personnel to intervene early, conducting in-depth inspections and repairs, effectively preventing escalation of faults, avoiding disruptions to passenger flow due to elevator outages, and ensuring passenger safety.

[0054] This invention combines elevator health index and elevator usage patterns to form a dual judgment standard. The elevator health index focuses on assessing the elevator's own health status, while the usage patterns are based on actual operating scenarios. The two complement each other to build a more comprehensive and intelligent elevator key attention area screening system, which significantly improves the accuracy and initiative of elevator maintenance management, reduces the incidence of sudden failures, saves inspection costs, and improves the operation and maintenance efficiency of the inspection system.

[0055] Specifically, the path planning module determines the priority area of ​​concern based on the key areas of the elevator, the timing of elevator malfunctions, and the timing and area of ​​manual instructions. It then determines the running distance of the inspection robot to reach the priority area of ​​concern based on the real-time machine position and adjusts the preset inspection path based on the running distance.

[0056] Understandably, comparing the timing of elevator malfunctions with the timing of manual instructions can determine the urgency of different tasks in terms of time. If there is time overlap, it indicates that multiple tasks may need to be processed within a similar timeframe, requiring further priority analysis. Simultaneously, judging the overlap of areas based on the instruction issuance area and the key focus area clarifies the spatial relationship between different tasks. If area overlap exists, it means the tasks may involve the same elevator, requiring a comprehensive consideration of the inspection robot's inspection area priority and execution order. By comprehensively judging the timing and area overlap, it can ensure that limited resources and time are prioritized and allocated to where they are needed.

[0057] Understandably, the operating distance directly affects the robot's travel time and energy consumption to reach the target area. By accurately calculating the operating distance, the optimal path can be selected, reducing the robot's travel time and cost. For example, if there are multiple priority areas, and the robot is closer to one of them, it can prioritize heading to that area to respond to urgent tasks as quickly as possible.

[0058] In one specific embodiment, the inspection robot has a built-in inspection area map. The running distance can be determined based on the real-time machine position of the inspection robot and the coordinate information of the priority areas on the inspection area map, combined with the coordinate positions between the two and relevant path information such as corridors and passages. If there are several priority areas corresponding to a single inspection robot, the running distance can be determined for each one, and the running distances can be sorted from smallest to largest. The priority areas are inspected according to the sorting results, and the remaining inspection tasks of the preset inspection path are then executed. This allows for a rapid response to the needs of priority areas without changing the overall inspection plan.

[0059] This invention rationally adjusts the inspection path based on human instructions and key areas of concern identified by the system, enabling the inspection robot to flexibly handle complex scenarios, avoiding blind actions and improving efficiency. It prioritizes handling anomalies in key elevator areas to ensure safe and stable elevator operation, while also handling other inspection tasks to guarantee comprehensiveness and completeness. This makes the robot's inspection work more efficient, intelligent, and reliable, providing strong support for elevator safety and further improving the quality of property security inspections.

[0060] Specifically, the path planning module determines whether there is a time overlap based on the timing of elevator malfunctions and the timing of manual instructions, determines whether there is a regional overlap based on the instruction issuance area and the key focus area, and determines the priority focus area based on the time overlap results and the regional overlap results.

[0061] Understandably, in elevator inspection scenarios, the time and location of elevator malfunctions, as well as the time and location of manual instructions, are uncertain. By comparing the relationship between elevator malfunctions and manual instructions in terms of time and location, the areas that the inspection robot needs to prioritize can be determined, enabling reasonable allocation and efficient utilization of resources. If the timing of the elevator malfunction and the timing of the manual instruction overlap on the timeline, it means there is a time overlap. Within the same time period, both the elevator malfunction and the manual instruction need to be monitored by the robot, and the corresponding area needs to be given priority. If there is no overlap, it means the times are relatively independent, and priority can be further determined based on the area. If there is an area overlap, it means that the area is both manually designated and related to the elevator malfunction, and needs to be prioritized. If there is no area overlap, a comprehensive judgment needs to be made based on the time overlap results.

[0062] In a specific embodiment, the final priority focus area can be determined by combining the results of time overlap and area overlap. If there is time overlap and area overlap (the instruction issuance area and the key focus area are elevators in the same area), then the overlap area is the priority focus area. If there is time overlap but no area overlap, then the priority is determined according to the timing of the elevator malfunction and the timing of the manual instruction issuance. The area corresponding to the earlier instruction is the priority focus area. If there is area overlap but no time overlap, then the overlap area is the priority focus area. If there is neither time overlap nor area overlap, then both the instruction issuance area and the key focus area corresponding to the timing are priority focus areas, only the order of the attention is different.

[0063] The path planning module of this invention makes dual judgments on the time intersection of elevator anomalies and manual instructions, and the area intersection of instruction issuance and key attention areas. This enables it to quickly and accurately lock the priority attention area, avoiding resource waste and response delays caused by mixed information. It significantly improves the timeliness and pertinence of the inspection robot's response to anomalies, effectively ensures the safe operation of key elevator areas, significantly improves the efficiency and quality of elevator inspections, and enhances the quality of property security inspections.

[0064] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A property intelligent inspection system based on artificial intelligence, characterized in that, include: The elevator inspection module includes several inspection robots, which are used to inspect the elevator according to a preset inspection path. The data acquisition module is used to collect the daily usage frequency of the elevator, as well as the motor current, motor voltage, and door operator current during elevator operation. The status analysis module is connected to the data acquisition module and is used to determine the correspondence and duration of the motor voltage and current during the elevator lifting process based on the motor current and motor voltage within a preset time period, and to determine the fluctuation of the door machine current based on the door machine current, and to determine the elevator health index based on the correspondence, the duration of the relationship and the fluctuation of the door machine current to determine the timing of elevator abnormalities. The pattern analysis module is connected to the data acquisition module and the status analysis module respectively. It is used to determine the peak time period based on the elevator usage frequency to determine whether the use of each elevator is regular, and to determine the key areas of concern based on the usage pattern judgment results or the elevator health index. The path planning module is connected to the state analysis module, the pattern analysis module, and the elevator inspection module, respectively, and is used to adjust the preset inspection path according to the key areas of the elevator, the timing of elevator malfunctions, manual instructions, and the real-time machine position of the inspection robot.

2. The property intelligent inspection system based on artificial intelligence according to claim 1, characterized in that, The state analysis module determines the motor current fluctuation based on the motor current, determines the motor voltage fluctuation based on the motor voltage, and determines the corresponding relationship and the duration of the relationship based on the motor current fluctuation and the motor voltage fluctuation. The corresponding relationships include constant voltage with increased current, decreased voltage with increased current, and voltage fluctuation with abnormal current.

3. The property intelligent inspection system based on artificial intelligence according to claim 2, characterized in that, The status analysis module constructs a current change waveform diagram based on the gantry current, determines the current peak value and current trough value based on the current change waveform diagram, and determines the gantry current fluctuation based on the current peak value and current trough value.

4. The property intelligent inspection system based on artificial intelligence according to claim 3, characterized in that, The state analysis module determines the first health impact coefficient of the motor on the elevator health based on the correspondence and duration of the relationship between motor current and motor voltage, determines the second health impact coefficient of the door operator on the elevator health based on the fluctuation of the door operator current, determines the elevator health index based on the first health impact coefficient and the second health impact coefficient, and determines the elevator abnormality time based on the elevator health index and the preset health index.

5. The property intelligent inspection system based on artificial intelligence according to claim 4, characterized in that, The state analysis module determines the relationship weight and time weight based on the corresponding relationship and the relationship duration, and determines the first health impact coefficient based on the relationship weight, the time weight, the relationship duration and the preset duration.

6. The property intelligent inspection system based on artificial intelligence according to claim 1, characterized in that, The pattern analysis module divides a day into several time intervals based on a preset time interval, counts the frequency of elevator use in each time interval, and determines the peak time period for elevator use each day based on the usage frequency.

7. The intelligent property inspection system based on artificial intelligence according to claim 6, characterized in that, The pattern analysis module determines whether the use of each elevator is regular based on the overlapping time periods of the daily peak hours of the elevator within a preset time period and the overlapping time periods and the type of work and rest.

8. The property intelligent inspection system based on artificial intelligence according to claim 7, characterized in that, The pattern analysis module identifies key areas of interest in the elevator, including: If the health index of a single elevator is lower than the preset health index, or if the usage pattern of a single elevator is determined, then that elevator is identified as a key area of ​​concern.

9. The intelligent property inspection system based on artificial intelligence according to claim 8, characterized in that, The path planning module determines the priority area of ​​concern based on the key areas of the elevator, the timing of elevator malfunctions, and the timing and area of ​​manual instructions. It then determines the running distance of the inspection robot to reach the priority area based on the real-time machine position and adjusts the preset inspection path based on the running distance.

10. The intelligent property inspection system based on artificial intelligence according to claim 9, characterized in that, The path planning module determines whether there is a time overlap based on the timing of elevator malfunctions and the timing of manual instructions, determines whether there is a regional overlap based on the instruction issuance area and the key focus area, and determines the priority focus area based on the time overlap results and the regional overlap results.

Images