Elevator fault prediction method, electronic equipment and medium based on data analysis

Abstract

The present invention discloses an elevator fault prediction method based on data analysis, an electronic device and a medium, and relates to the technical field of data analysis. The elevator fault prediction method based on data analysis includes the following steps: establishing a first mapping relationship and a second mapping relationship, calculating a second stability and a second accuracy, obtaining the corresponding second motor operation efficiency and second motor control state, calculating critical motor data, and constructing a fault prediction model to predict the fault time of the current motor data. The present invention establishes a mapping relationship through in-depth analysis of motor and car data, improves prediction accuracy, improves the reliability of elevator use by predicting motor failure time, effectively reduces equipment wear by timely discovering and handling problems, thereby extending the service life of the elevator, reducing overall maintenance costs, improving fault prediction capabilities, and reducing the risk of safety accidents caused by equipment failures. It provides a scientific basis for equipment management and decision-making, and promotes the realization of intelligent management.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to an elevator fault prediction method, electronic equipment and medium based on data analysis. Background Art

[0002] In recent years, elevator operation fault prediction technology is committed to improving safety and reducing maintenance costs, and improving the reliability and service life of elevators. With the continuous advancement of technology, the prediction accuracy and the intelligence level of the system will continue to improve, and high-precision sensors are used to monitor the operation status of elevators, including speed, acceleration, load, temperature, vibration and other parameters. These data provide a basis for fault prediction. Through the Internet of Things technology, elevator equipment is connected to the cloud platform to achieve real-time data transmission and remote monitoring, so that fault prediction can be carried out on a larger scale and support centralized management.

[0003] At present, in the Chinese invention patent with publication number CN 114408694 B, an elevator fault prediction system and a prediction method thereof are disclosed. The method constructs a corresponding fault prediction neural network through a multivariate regression equation and obtains a corresponding elevator fault prediction result; the instruction transmission layer is used to send the fault prediction result to the elevator master control center and send the corresponding maintenance instruction to the corresponding department. However, the relevant technology does not establish a corresponding relationship between the elevator fault and the elevator operating parameters, lacks the jointness and scientificity of fault judgment, and does not predict the elevator fault based on historical fault big data, which is easy to cause prediction errors and affect the accuracy of the system. Summary of the invention

[0004] The technical problem solved by the present invention is that the relevant technology does not establish a corresponding relationship between elevator failures and elevator operating parameters, lacks the unity and scientificity of fault judgment, and does not predict elevator failures based on historical fault big data, which can easily lead to prediction errors and affect the accuracy of the system.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In the first aspect, the elevator fault prediction method based on data analysis includes the following steps:

[0007] Step S100, collecting first motor data and first car data;

[0008] Step S200, analyzing the first motor data to obtain the first motor operating efficiency and the first motor control state, analyzing the first car data to obtain the first car stability and the first car accuracy, establishing a first mapping relationship between the first motor operating efficiency and the first stability, and establishing a second mapping relationship between the first motor control state and the first car accuracy;

[0009] Step S300, obtaining historical fault types and corresponding second car data, respectively calculating the second stability and second accuracy corresponding to each historical fault type, obtaining the corresponding second motor operation efficiency and second motor control state according to the first mapping relationship and the second mapping relationship, obtaining the corresponding second motor data according to the second motor operation efficiency and the second motor control state, the second motor data including second speed data, second output power data and second pulse signal data, and setting the second motor data to critical motor data;

[0010] Step S400, counting the time for different first motor data to reach critical motor data, recording it as the experienced time, calculating the fuzzy timing factor according to the experienced time, constructing a fault prediction model according to the fuzzy timing factor, and predicting the fault time of the current motor data through the fault prediction model.

[0011] As a preferred solution of the elevator fault prediction method based on data analysis described in the present invention, step S100 includes the following sub-steps:

[0012] Step S101, collecting first motor data, the first motor data including first speed data, first output power data and first pulse signal data, the first speed data, first output power data and first pulse signal data are obtained by a speed sensor, a power sensor and a signal sensor respectively;

[0013] Step S102, collecting first car data, the first car data including first acceleration data, first vibration value data and first stop position data, the first acceleration data, first vibration value data and first stop position data are obtained by an acceleration sensor, a vibration sensor and a position sensor respectively.

[0014] As a preferred solution of the elevator fault prediction method based on data analysis described in the present invention, the position sensor is placed according to the elevator hall and the floor, and the placement logic of the position sensor includes:

[0015] Take the lower left corner of the elevator hall as the origin, the length of the elevator hall as the x-axis, the width of the elevator hall as the y-axis, and the height of the elevator hall as the z-axis to establish a three-dimensional coordinate system, obtain the floor number, and obtain the z-axis coordinate corresponding to the floor number in the three-dimensional coordinate system, record it as the mark coordinate, and number the mark coordinate first, denoted as Q i , i is a natural number, which is expressed as a floor number. According to the cross section of the bottom surface of the elevator hall, a virtual elevator stop surface is drawn at the mark coordinates, and the vertices of the virtual elevator stop surface are numbered secondly. The second number corresponds to the first number, and the second number is expressed as Qij , j is a natural number, indicating the vertex number, a position sensor is placed at the vertex of the virtual elevator stop surface after the second number, and the position sensor is numbered a third time, the third number corresponds to the second number, and the third number is represented by Q ijm , m is a natural number, representing the sensor number.

[0016] As a preferred solution of the elevator fault prediction method based on data analysis described in the present invention, step S200 includes the following sub-steps:

[0017] Step S201, obtaining first speed data, first output power data and first pulse signal data, calculating the first motor operation efficiency according to the first speed data and the first output power data, and obtaining the first motor control state according to the first output power data and the first pulse signal data;

[0018] Step S202, obtain first acceleration data, first vibration value data and first stopping position data, calculate the first stability according to the first acceleration data and the first vibration value data, calculate the first car accuracy according to the first stopping position data, establish a first mapping relationship between the first motor operating efficiency and the first stability, and establish a second mapping relationship between the first motor control state and the first car accuracy.

[0019] As a preferred solution of the elevator fault prediction method based on data analysis described in the present invention, wherein: the generation logic of the first motor operating efficiency includes:

[0020] Obtaining first speed data and first output power data, obtaining a torque corresponding to the first speed data, calculating actual output power by a power formula, calculating a ratio of the actual output power to the first power data, and setting the ratio of the actual output power to the first power data as a first motor operating efficiency;

[0021] The acquisition logic of the first motor control state includes:

[0022] Acquire first pulse signal data and first output power data, wherein the first pulse signal data is represented as a pulse level, acquire actual output power, call a motor database, input the actual output power into the motor database, match the pulse level corresponding to the actual output power, record it as an ideal pulse level, perform a difference calculation between the pulse level and the ideal pulse level to obtain a first difference, set a first value and a second value as a difference gradient, compare the first difference with the first value and the second value, and when the first difference is greater than or equal to the first value, set the first motor control state to control first level failure, when the first difference is less than the first value and greater than or equal to the second value, set the first motor control state to control second level failure, and when the first difference is less than the second value, set the first motor control state to third level failure.

[0023] As a preferred solution of the elevator fault prediction method based on data analysis described in the present invention, the calculation logic of the first car accuracy includes:

[0024] Obtain the vertex coordinates of the stop point on the bottom surface of the car, record them as actual coordinates, match the coordinates of the corresponding position sensor according to the actual coordinates, calculate the x-axis value, y-axis value and z-axis data of the actual coordinates and the x-axis value, y-axis value and z-axis data of the coordinates of the position sensor, calculate the sum of the x-axis difference, y-axis difference and z-axis difference, record them as the first sum value, traverse the first sum values, sort the first sum values ​​in ascending order, select the first sum value with the smallest value, set the corresponding position sensor as the reference sensor, obtain the coordinates of the reference sensor, set the allowable error distance, calculate the distance between the vertex coordinates of the stop point and the coordinates of the reference sensor, record them as the actual error distance, calculate the difference between the actual error distance and the allowable error distance, record them as the second difference, calculate the ratio of the second difference to the allowable error distance, record them as the car accuracy, traverse the car accuracy corresponding to each vertex, calculate the average value of the car accuracy corresponding to each vertex, and set the average value of the car accuracy corresponding to each vertex as the first car accuracy.

[0025] As a preferred solution of the elevator fault prediction method based on data analysis described in the present invention, step S300 includes the following sub-steps:

[0026] Step S301, obtaining historical fault types and corresponding second car data, wherein the historical fault types include brake fault, guide rail wear, gear box fault and control circuit fault, and the second car data includes second acceleration data, second vibration value data and second stop position data;

[0027] Step S302, respectively calculating the second stability and the second accuracy corresponding to each historical fault type, inputting the second stability according to the first mapping relationship to obtain the corresponding second motor operation efficiency, and inputting the second accuracy according to the second mapping relationship to obtain the second motor control state;

[0028] Step S303, obtaining corresponding second motor data according to the second motor operating efficiency and the second motor control state, wherein the second motor data includes second speed data, second output power data and second pulse signal data, and setting the second motor data to critical motor data.

[0029] As a preferred solution of the elevator fault prediction method based on data analysis described in the present invention, step S400 includes the following sub-steps:

[0030] Step S401, counting the time when different first motor data reach critical motor data, recorded as elapsed time, and calculating the fuzzy timing factor according to the elapsed time. The calculation logic of the fuzzy timing factor includes:

[0031] Taking the time when the first motor data reaches the critical motor data as the dependent variable and the first motor data as the independent variable, a multivariate regression analysis is performed, the coefficient obtained by the multivariate regression analysis is used as the timing factor of the corresponding first motor data, the average of the timing factor is calculated, and the average of the timing factor is set as the fuzzy timing factor;

[0032] Step S402: construct a fault prediction model according to the fuzzy timing factor, and predict the fault time of the current motor data through the fault prediction model. The calculation expression of the fault prediction model is:

[0033] ;

[0034] in, is the time when the first motor data reaches the critical motor data, is the fuzzy timing factor, For the The first motor data, is the total number of the first motor data.

[0035] In a second aspect, the present invention provides an electronic device comprising a memory, a processor and storage in the memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in any one of the methods described above are executed.

[0036] In a third aspect, the present invention provides a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps in any one of the methods described above are executed.

[0037] The beneficial effects of the present invention are as follows: through in-depth analysis of motor and car data and establishment of mapping relationships, it is helpful to more accurately identify potential faults and improve prediction accuracy. By predicting motor failure time, preventive maintenance can be achieved, unexpected downtime can be reduced, and the reliability of elevator use can be improved. By promptly discovering and handling problems, equipment wear can be effectively reduced, thereby extending the service life of the elevator, reducing overall maintenance costs, improving fault prediction capabilities, reducing the risk of safety accidents caused by equipment failures, ensuring the safety of passengers, providing a scientific basis for equipment management and decision-making, and promoting the realization of intelligent management. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A schematic diagram of the basic flow of an elevator fault prediction method based on data analysis provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0040] Example, see Figure 1 , as an embodiment of the present invention, provides an elevator fault prediction method based on data analysis, comprising the following steps:

[0041] Step S100, collecting first motor data and first car data;

[0042] Step S200, analyzing the first motor data to obtain the first motor operating efficiency and the first motor control state, analyzing the first car data to obtain the first car stability and the first car accuracy, establishing a first mapping relationship between the first motor operating efficiency and the first stability, and establishing a second mapping relationship between the first motor control state and the first car accuracy;

[0043] Step S300, obtaining historical fault types and corresponding second car data, respectively calculating the second stability and second accuracy corresponding to each historical fault type, obtaining the corresponding second motor operation efficiency and second motor control state according to the first mapping relationship and the second mapping relationship, obtaining the corresponding second motor data according to the second motor operation efficiency and the second motor control state, the second motor data including second speed data, second output power data and second pulse signal data, and setting the second motor data to critical motor data;

[0044] Step S400, counting the time for different first motor data to reach critical motor data, recording it as the experienced time, calculating the fuzzy timing factor according to the experienced time, constructing a fault prediction model according to the fuzzy timing factor, and predicting the fault time of the current motor data through the fault prediction model.

[0045] The present invention establishes a mapping relationship through in-depth analysis of motor and car data, which helps to more accurately identify potential faults and improve prediction accuracy. By predicting the time of motor failure, preventive maintenance can be achieved, unexpected downtime can be reduced, and the reliability of elevator use can be improved. By promptly discovering and handling problems, equipment wear can be effectively reduced, thereby extending the service life of the elevator, reducing overall maintenance costs, improving fault prediction capabilities, reducing the risk of safety accidents caused by equipment failures, ensuring the safety of passengers, providing a scientific basis for equipment management and decision-making, and promoting the realization of intelligent management.

[0046] The step S100 includes the following sub-steps:

[0047] Step S101, collecting first motor data, the first motor data including first speed data, first output power data and first pulse signal data, the first speed data, first output power data and first pulse signal data are obtained by a speed sensor, a power sensor and a signal sensor respectively;

[0048] Step S102, collecting first car data, the first car data including first acceleration data, first vibration value data and first stop position data, the first acceleration data, first vibration value data and first stop position data are obtained by an acceleration sensor, a vibration sensor and a position sensor respectively.

[0049] In specific implementation, through the comprehensive collection of various key parameters of the motor and car, more abundant operating data can be obtained, which will help to make subsequent analysis more accurate and comprehensive, and provide the necessary information basis for fault prediction. The use of sensors to collect data in real time can timely reflect the operating status of the elevator and help quickly discover abnormal situations, thereby improving the safety and reliability of the elevator. Different types of data indicators, such as speed, power, acceleration and vibration, provide a multi-dimensional evaluation basis for the performance of the motor and car, which is helpful for in-depth analysis of its operating efficiency and stability. By monitoring the changes in acceleration and vibration values, early warnings can be issued in the early stages of a fault, helping maintenance personnel to take timely measures to avoid greater losses and safety hazards.

[0050] The position sensors are placed according to the elevator hall and the floors, and the placement logic of the position sensors includes:

[0051] A three-dimensional coordinate system is established with the lower left corner of the elevator hall as the origin, the length of the elevator hall as the x-axis, the width of the elevator hall as the y-axis, and the height of the elevator hall as the z-axis, and the floor number is obtained. The z-axis coordinate corresponding to the floor ground corresponding to the floor number is obtained in the three-dimensional coordinate system, which is recorded as the mark coordinate. The mark coordinate is first numbered, represented as Qi, where i is a natural number and represents the floor number. According to the cross-section of the bottom surface of the elevator hall, a virtual elevator stop surface is drawn at the mark coordinate, and the vertices of the virtual elevator stop surface are numbered, and the vertices of the virtual elevator stop surface are second numbered, the second number corresponds to the first number, the second number is represented as Qij, j is a natural number and represents the vertex number, a position sensor is placed at the vertex of the virtual elevator stop surface after the second number, and the position sensor is third numbered, the third number corresponds to the second number, the third number is represented as Qijm, where m is a natural number and represents the sensor number.

[0052] In the specific implementation, by establishing a three-dimensional coordinate system and clearly marking the coordinates, it is possible to accurately locate each floor in the elevator hall, ensuring that the elevator can accurately reach the set floor. Through the systematic method of the first, second and third numbers, each floor and its corresponding sensors can be clearly identified and managed, making subsequent maintenance and management work more efficient. Sensors are placed at the vertices of the virtual stop surface so that actual maintenance and inspection can accurately locate the position of each sensor, simplifying the maintenance and troubleshooting process. By scientifically arranging position sensors, the operating status of the elevator can be effectively monitored, ensuring that the elevator stops at the correct position, and improving safety in use.

[0053] The step S200 includes the following sub-steps:

[0054] Step S201, obtaining first speed data, first output power data and first pulse signal data, calculating the first motor operation efficiency according to the first speed data and the first output power data, and obtaining the first motor control state according to the first output power data and the first pulse signal data;

[0055] Step S202, obtain first acceleration data, first vibration value data and first stopping position data, calculate the first stability according to the first acceleration data and the first vibration value data, calculate the first car accuracy according to the first stopping position data, establish a first mapping relationship between the first motor operating efficiency and the first stability, and establish a second mapping relationship between the first motor control state and the first car accuracy.

[0056] In specific implementation, by acquiring and analyzing the first speed data and the first output power data, the operating efficiency of the motor can be effectively calculated, thereby providing a basis for subsequent optimization of the motor performance and improving the overall operating effect. By analyzing the first pulse signal data, the control state of the motor can be accurately understood, providing data support for real-time adjustment, and enhancing the responsiveness and stability of the motor. By acquiring the first acceleration data and the first vibration value data, the stability of the motor can be calculated, the dynamic performance of the equipment during operation is monitored, potential problems can be discovered early, and the safe operation of elevators and other equipment can be ensured.

[0057] The logic for generating the first motor operating efficiency includes:

[0058] Acquire first speed data and first output power data, acquire torque corresponding to the first speed data, calculate actual output power by a power formula, calculate a ratio of actual output power to the first power data, and set the ratio of actual output power to the first power data as a first motor operation efficiency;

[0059] The acquisition logic of the first motor control state includes:

[0060] Acquire first pulse signal data and first output power data, wherein the first pulse signal data is represented as a pulse level, acquire actual output power, call a motor database, input the actual output power into the motor database, match the pulse level corresponding to the actual output power, record it as an ideal pulse level, perform a difference calculation between the pulse level and the ideal pulse level to obtain a first difference, set a first value and a second value as a difference gradient, compare the first difference with the first value and the second value, and when the first difference is greater than or equal to the first value, set the first motor control state to control first level failure, when the first difference is less than the first value and greater than or equal to the second value, set the first motor control state to control second level failure, and when the first difference is less than the second value, set the first motor control state to third level failure.

[0061] In the specific implementation, by obtaining the first speed data and the first output power data and combining the torque to calculate the actual output power, the operating efficiency of the motor can be evaluated more accurately, which not only improves the accuracy of the data, but also provides the necessary basis for subsequent performance optimization. By dynamically acquiring pulse signals and output power data, combined with the motor database, the control status of the motor is monitored in real time. When performance deviations occur, the operating health of the motor can be quickly judged. Through the difference calculation and level classification mechanism, timely diagnosis of abnormal motor operation can be achieved. When the motor control state changes, the system can quickly issue an early warning to help maintenance personnel take timely measures to reduce the risk of failure.

[0062] The calculation logic of the first car accuracy includes:

[0063] Obtain the vertex coordinates of the stop point on the bottom surface of the car, record them as actual coordinates, match the coordinates of the corresponding position sensor according to the actual coordinates, calculate the x-axis value, y-axis value and z-axis data of the actual coordinates and the x-axis value, y-axis value and z-axis data of the coordinates of the position sensor, calculate the sum of the x-axis difference, y-axis difference and z-axis difference, record them as the first sum value, traverse the first sum values, sort the first sum values ​​in ascending order, select the first sum value with the smallest value, set the corresponding position sensor as the reference sensor, obtain the coordinates of the reference sensor, set the allowable error distance, calculate the distance between the vertex coordinates of the stop point and the coordinates of the reference sensor, record them as the actual error distance, calculate the difference between the actual error distance and the allowable error distance, record them as the second difference, calculate the ratio of the second difference to the allowable error distance, record them as the car accuracy, traverse the car accuracy corresponding to each vertex, calculate the average value of the car accuracy corresponding to each vertex, and set the average value of the car accuracy corresponding to each vertex as the first car accuracy.

[0064] In specific implementation, by accurately calculating the vertex coordinates of the stop points on the bottom surface of the car and the coordinates of the position sensor, the positioning error can be effectively reduced, thereby improving the accuracy of the car, automatically acquiring sensor data and comparing them, reducing the need for manual intervention, achieving a more efficient monitoring process, reducing the complexity of operation and possible human errors, and selecting the sensor corresponding to the smallest first sum value as the reference sensor to ensure the authority of the selected reference point in judging accuracy, thereby enhancing the reliability of the results, setting the allowable error distance, and calculating the actual error distance to reasonably control the error of car positioning, which helps to deal with error fluctuations that may occur in actual applications.

[0065] The step S300 includes the following sub-steps:

[0066] Step S301, obtaining historical fault types and corresponding second car data, wherein the historical fault types include brake fault, guide rail wear, gear box fault and control circuit fault, and the second car data includes second acceleration data, second vibration value data and second stop position data;

[0067] Step S302, respectively calculating the second stability and the second accuracy corresponding to each historical fault type, inputting the second stability according to the first mapping relationship to obtain the corresponding second motor operation efficiency, and inputting the second accuracy according to the second mapping relationship to obtain the second motor control state;

[0068] Step S303, obtaining corresponding second motor data according to the second motor operating efficiency and the second motor control state, wherein the second motor data includes second speed data, second output power data and second pulse signal data, and setting the second motor data to critical motor data.

[0069] In specific implementation, the system obtains historical fault types and their corresponding second car data to effectively identify and classify different fault types, thereby providing a valuable information basis for subsequent fault analysis and maintenance. The second stability and second accuracy are calculated for each historical fault type, which can provide an in-depth understanding of the impact of each fault on the car operation performance, and provide a basis for preventive maintenance and fault repair. According to the mapping relationship corresponding to the second stability and second accuracy inputs, the operating efficiency of the motor is obtained, and guidance is provided for the performance tuning of the motor and the reduction of energy consumption, thereby improving the overall operating efficiency. By calculating the control state of the second motor, the operation of the motor can be monitored in real time, and potential problems can be discovered in time, thereby increasing the reliability and safety of the system.

[0070] The step S400 includes the following sub-steps:

[0071] Step S401 , counting the time from different first motor data to critical motor data, recording it as elapsed time, and calculating the fuzzy timing factor according to the elapsed time.

[0072] The calculation logic of the fuzzy timing factor includes: taking the time when the first motor data reaches the critical motor data as the dependent variable and the first motor data as the independent variable, performing a multivariate regression analysis, using the coefficients obtained from the multivariate regression analysis as the timing factor of the corresponding first motor data, calculating the average of the timing factor, and setting the average of the timing factor as the fuzzy timing factor.

[0073] Step S402: construct a fault prediction model according to the fuzzy timing factor, and predict the fault time of the current motor data through the fault prediction model.

[0074] The calculation expression of the fault prediction model is: ,in, is the time when the first motor data reaches the critical motor data, is the fuzzy timing factor, For the The first motor data, is the total number of the first motor data.

[0075] In the specific implementation, a more accurate fault prediction model is established by counting the time it takes for different first motor data to reach the critical motor data and calculating the fuzzy timing factor. This model can effectively predict the failure time of the current motor data, thereby performing maintenance in advance and reducing the risk of sudden failures. The application of multivariate regression analysis makes fault prediction not only rely on a single data point, but also comprehensively considers multiple factors, thereby improving the scientificity and credibility of the prediction results and helping management to make more reasonable maintenance and operation decisions. The calculation logic of the fuzzy timing factor allows the prediction model to be dynamically adjusted according to the new motor data, further improving the adaptability of the model in different periods and reducing the amount of calculation, so that it can reflect the actual operating status of the current motor.

[0076] The present invention establishes a mapping relationship through in-depth analysis of motor and car data, which helps to more accurately identify potential faults and improve prediction accuracy. By predicting the time of motor failure, preventive maintenance can be achieved, unexpected downtime can be reduced, and the reliability of elevator use can be improved. By promptly discovering and handling problems, equipment wear can be effectively reduced, thereby extending the service life of the elevator, reducing overall maintenance costs, improving fault prediction capabilities, reducing the risk of safety accidents caused by equipment failures, ensuring the safety of passengers, providing a scientific basis for equipment management and decision-making, and promoting the realization of intelligent management.

[0077] Another embodiment of the present invention provides an electronic device, including a memory, a processor, and storage in the memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in any one of the above elevator fault prediction methods based on data analysis are executed.

[0078] Another embodiment of the present invention provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps in any one of the above elevator fault prediction methods based on data analysis are executed.

[0079] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0080] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. The elevator fault prediction method based on data analysis is characterized in that: The following steps are involved: Step S100, collecting first motor data and first car data; Step S200, analyzing the first motor data to obtain the first motor operating efficiency and the first motor control state, analyzing the first car data to obtain the first car stability and the first car accuracy, establishing a first mapping relationship between the first motor operating efficiency and the first stability, and establishing a second mapping relationship between the first motor control state and the first car accuracy; Step S300, obtaining historical fault types and corresponding second car data, wherein the historical fault types include brake fault, guide rail wear, gear box fault and control circuit fault, respectively calculating the second stability and second accuracy corresponding to each historical fault type, obtaining the corresponding second motor operation efficiency and second motor control state according to the first mapping relationship and the second mapping relationship, obtaining the corresponding second motor data according to the second motor operation efficiency and the second motor control state, wherein the second motor data includes second speed data, second output power data and second pulse signal data, and setting the second motor data as critical motor data; Step S400, counting the time when different first motor data reach critical motor data, recorded as elapsed time, calculating the fuzzy timing factor according to the elapsed time, constructing a fault prediction model according to the fuzzy timing factor, and predicting the fault time of the current motor data through the fault prediction model. The calculation expression of the fault prediction model is: ， in, is the time when the first motor data reaches the critical motor data, is the fuzzy timing factor, For the The first motor data, is the total number of the first motor data.

2. The elevator fault prediction method based on data analysis according to claim 1, characterized in that: The step S100 includes the following sub-steps: Step S101, collecting first motor data, the first motor data including first speed data, first output power data and first pulse signal data, the first speed data, first output power data and first pulse signal data are obtained by a speed sensor, a power sensor and a signal sensor respectively; Step S102, collecting first car data, the first car data including first acceleration data, first vibration value data and first stop position data, the first acceleration data, first vibration value data and first stop position data are obtained by an acceleration sensor, a vibration sensor and a position sensor respectively.

3. The elevator fault prediction method based on data analysis according to claim 2, characterized in that: The position sensors are placed according to the elevator hall and the floors, and the placement logic of the position sensors includes: Take the lower left corner of the elevator hall as the origin, the length of the elevator hall as the x-axis, the width of the elevator hall as the y-axis, and the height of the elevator hall as the z-axis to establish a three-dimensional coordinate system, obtain the floor number, and obtain the z-axis coordinate corresponding to the floor number in the three-dimensional coordinate system, record it as the mark coordinate, and number the mark coordinate first, denoted as Q i , i is a natural number, which is expressed as a floor number. According to the cross section of the bottom surface of the elevator hall, a virtual elevator stop surface is drawn at the mark coordinates, and the vertices of the virtual elevator stop surface are numbered secondly. The second number corresponds to the first number, and the second number is expressed as Q ij , j is a natural number, indicating the vertex number, a position sensor is placed at the vertex of the virtual elevator stop surface after the second number, and the position sensor is numbered a third time, the third number corresponds to the second number, and the third number is represented by Q ijm , m is a natural number, representing the sensor number.

4. The elevator fault prediction method based on data analysis according to claim 1, characterized in that: The step S200 includes the following sub-steps: Step S201, obtaining first speed data, first output power data and first pulse signal data, calculating the first motor operation efficiency according to the first speed data and the first output power data, and obtaining the first motor control state according to the first output power data and the first pulse signal data; Step S202, obtain first acceleration data, first vibration value data and first stopping position data, calculate the first stability according to the first acceleration data and the first vibration value data, calculate the first car accuracy according to the first stopping position data, establish a first mapping relationship between the first motor operating efficiency and the first stability, and establish a second mapping relationship between the first motor control state and the first car accuracy.

5. The elevator fault prediction method based on data analysis according to claim 4, characterized in that: The logic for generating the first motor operating efficiency includes: Obtaining first speed data and first output power data, obtaining a torque corresponding to the first speed data, calculating actual output power by a power formula, calculating a ratio of the actual output power to the first power data, and setting the ratio of the actual output power to the first power data as a first motor operating efficiency; The acquisition logic of the first motor control state includes: Acquire first pulse signal data and first output power data, wherein the first pulse signal data is represented as a pulse level, acquire actual output power, call a motor database, input the actual output power into the motor database, match the pulse level corresponding to the actual output power, record it as an ideal pulse level, perform a difference calculation between the pulse level and the ideal pulse level to obtain a first difference, set a first value and a second value as a difference gradient, compare the first difference with the first value and the second value, and when the first difference is greater than or equal to the first value, set the first motor control state to control first level failure, when the first difference is less than the first value and greater than or equal to the second value, set the first motor control state to control second level failure, and when the first difference is less than the second value, set the first motor control state to third level failure.

6. The elevator fault prediction method based on data analysis according to claim 4, characterized in that: The calculation logic of the first car accuracy includes: Obtain the vertex coordinates of the stop point on the bottom surface of the car, record them as actual coordinates, match the coordinates of the corresponding position sensor according to the actual coordinates, calculate the x-axis value, y-axis value and z-axis data of the actual coordinates and the x-axis value, y-axis value and z-axis data of the coordinates of the position sensor, calculate the sum of the x-axis difference, y-axis difference and z-axis difference, record them as the first sum value, traverse the first sum values, sort the first sum values ​​in ascending order, select the first sum value with the smallest value, set the corresponding position sensor as the reference sensor, obtain the coordinates of the reference sensor, set the allowable error distance, calculate the distance between the vertex coordinates of the stop point and the coordinates of the reference sensor, record them as the actual error distance, calculate the difference between the actual error distance and the allowable error distance, record them as the second difference, calculate the ratio of the second difference to the allowable error distance, record them as the car accuracy, traverse the car accuracy corresponding to each vertex, calculate the average value of the car accuracy corresponding to each vertex, and set the average value of the car accuracy corresponding to each vertex as the first car accuracy.

7. The elevator fault prediction method based on data analysis according to claim 1, characterized in that: The step S300 includes the following sub-steps: Step S301, obtaining historical fault types and corresponding second car data, wherein the second car data includes second acceleration data, second vibration value data and second stop position data; Step S302, respectively calculating the second stability and the second accuracy corresponding to each historical fault type, inputting the second stability according to the first mapping relationship to obtain the corresponding second motor operation efficiency, and inputting the second accuracy according to the second mapping relationship to obtain the second motor control state; Step S303, obtaining corresponding second motor data according to the second motor operating efficiency and the second motor control state, wherein the second motor data includes second speed data, second output power data and second pulse signal data, and setting the second motor data to critical motor data.

8. The elevator fault prediction method based on data analysis according to claim 1, characterized in that: The calculation logic of the fuzzy timing factor includes: A multivariate regression analysis is performed with the time when the first motor data reaches the critical motor data as the dependent variable and the first motor data as the independent variable. The coefficients obtained from the multivariate regression analysis are used as the timing factors of the corresponding first motor data, the average of the timing factors is calculated, and the average of the timing factors is set as the fuzzy timing factor.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the elevator fault prediction method based on data analysis described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the elevator fault prediction method based on data analysis according to any one of claims 1 to 8 is implemented.

Images