Elevator on-demand maintenance method based on dynamic prediction

Abstract

The invention discloses an elevator on-demand maintenance method based on dynamic prediction, which comprises the following steps of: evaluating the health degree of an elevator by comprehensively considering the running state data and the use condition data of the elevator and utilizing an elevator health degree evaluation model based on an LSTM (Long Short Term Memory) algorithm, obtaining a maintenance priority evaluation result according to the evaluation result, and further generating a maintenance strategy; maintenance resource limitation is considered, and maintenance strategy optimization is carried out according to the availability of maintenance personnel, tools and equipment and the maintenance cost; in the actual execution process of the maintenance strategy, the running state, the maintenance plan and the execution condition of the elevator are monitored; and optimizing the maintenance strategy by adopting an optimization algorithm according to the feedback information. According to the method, the elevator maintenance efficiency and safety can be improved, resource waste is reduced, and meanwhile, personalized and dynamic maintenance strategies are provided.

Description

Technical Field

[0001] The present invention relates to the field of elevator on-demand maintenance, and in particular to an elevator on-demand maintenance method based on dynamic prediction. Background Art

[0002] As an indispensable means of transportation in modern cities, elevators undertake the important task of transporting people and goods. In order to ensure the safe and reliable operation of elevators, maintenance is an indispensable link. Traditional elevator maintenance usually adopts the method of regular maintenance, that is, maintenance and inspection at fixed time intervals. However, the regular maintenance method has the following problems: First, the maintenance frequency is inconsistent. Sometimes maintenance may be frequent, and sometimes maintenance is not performed for a long time, resulting in waste of resources and unstable maintenance effects; second, it is difficult to accurately assess maintenance needs. Traditional methods mainly rely on experience and fixed cycles for maintenance, and cannot fully consider the actual operation and use of elevators, resulting in inaccurate maintenance plans and unsatisfactory results; third, the maintenance cost is high, and regular maintenance requires a lot of manpower and material resources, resulting in unnecessary waste.

[0003] With the rapid development of sensor technology, big data processing and artificial intelligence algorithms, maintenance methods based on data analysis have gradually attracted attention. This method collects elevator operation status data and usage data, and uses data analysis and predictive analysis algorithms to dynamically predict elevator maintenance needs and optimize maintenance plans. However, the existing elevator maintenance methods based on data analysis still have some problems, including imperfect data collection and processing, low prediction accuracy, and insufficiently refined maintenance strategy generation and optimization. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention proposes an on-demand maintenance method for elevators based on dynamic prediction, which aims to solve the problems of inconsistency, inaccuracy and high cost in traditional elevator maintenance methods. By comprehensively considering the operating status and usage data of the elevator, a predictive maintenance model is established using a predictive analysis algorithm to achieve accurate prediction of elevator maintenance needs and optimization of maintenance plans, thereby improving elevator maintenance efficiency and safety. Based on existing maintenance regulations and usage scenario data, the present invention formulates an overall solution and technical implementation plan to achieve intelligent elevator maintenance that can achieve "on-demand maintenance and on-demand inspection".

[0005] The specific technical solutions are as follows:

[0006] An elevator on-demand maintenance method based on dynamic prediction includes the following steps:

[0007] Step 1: Obtain elevator maintenance data in real time and pre-process it, then extract the key features of elevator maintenance in the data, and assign weight values ​​to the importance of elevator maintenance according to the features; maintenance data includes operation status data and usage data; operation status data includes elevator operation time, speed, acceleration, and temperature; usage data includes elevator operation frequency and peak period;

[0008] Step 2: Extract statistical features of key features of elevator maintenance in each maintenance cycle; Based on historical maintenance data, perform weighted summation of the results of each maintenance project in the same maintenance cycle to obtain the elevator health score, classify the elevator health according to the elevator health score, and use the classification result as the training label of the maintenance cycle; Arrange the statistical features of all maintenance cycles corresponding to the training labels to obtain the training data set; Build and train an elevator health assessment model based on the LSTM algorithm;

[0009] Step 3: After the elevator historical maintenance data and the real-time collected elevator operation data are processed by S1, they are input into the trained elevator health assessment model, the elevator health assessment result is output, and the maintenance priority assessment result is obtained accordingly;

[0010] Step 4: Generate a maintenance strategy based on the elevator health assessment result and the priority assessment result;

[0011] Step 5: Consider maintenance resource constraints and optimize maintenance strategies based on the availability of maintenance personnel, tools and equipment, and maintenance costs;

[0012] Step 6: During the actual implementation of the maintenance strategy, monitor the elevator operating status, maintenance plan and execution status; and optimize the maintenance strategy using an optimization algorithm based on the feedback information.

[0013] Furthermore, in the step one, the preprocessing includes: data cleaning, data outlier processing, data missing value processing, and classified storage of data.

[0014] Furthermore, in the step 2, statistical feature extraction is performed on the key features of elevator maintenance in each maintenance cycle, specifically:

[0015] The preprocessed elevator operation data are grouped based on the maintenance cycle, and the mathematical statistical features of the elevator operation data in each maintenance cycle are extracted. For binary data with only two states, the number of times these two states exist is counted in each maintenance cycle; for continuous data with multiple states, mathematical statistical features are calculated in each maintenance cycle, including: maximum value, minimum value, average value, and variance calculation; all the obtained mathematical statistical features are spliced ​​to obtain the statistical feature data of the maintenance cycle as training data.

[0016] Furthermore, the elevator health is divided into four categories. If the elevator health score is 0-10 points, the corresponding elevator health assessment result is normal and no maintenance is required;

[0017] If the elevator health score is between 11 and 25, the corresponding elevator health assessment result is "needs attention", which means maintenance is required and the maintenance priority is low;

[0018] If the elevator health score is 26-35 points, the corresponding elevator health assessment result is that it is determined to be in need of maintenance, and the maintenance priority is medium;

[0019] If the elevator health score is 36-45 points, the corresponding elevator health assessment result is that it is determined to require maintenance and the maintenance priority is high.

[0020] Furthermore, the elevator health assessment model includes five layers in sequence: an input layer, an LSTM layer one, an LSTM layer two, a fully connected layer, and an output layer;

[0021] The input layer is used to accept time series data of multiple features as an input sequence;

[0022] The LSTM layer 1 includes multiple LSTM units for capturing the basic temporal relationship between features; the number of LSTM units is between 20 and 100;

[0023] The LSTM layer 2 includes multiple LSTM units for further extracting deeper temporal relationships between features; the number of LSTM units is between 20 and 100;

[0024] The fully connected layer is used to extract potential interaction relationships between input features;

[0025] The output of the fully connected layer is connected to the output layer, which outputs the elevator health score predicted by the model.

[0026] Furthermore, the elevator health assessment model is trained using the training data set, and the elevator health assessment model is optimized using a mean square error loss function and a stochastic gradient descent optimization algorithm during the training process.

[0027] Furthermore, the maintenance strategy includes: allocation of maintenance personnel and allocation of maintenance time.

[0028] Furthermore, in step six, the optimization algorithm uses a genetic algorithm, and the specific steps of using the genetic algorithm to optimize the maintenance strategy are as follows:

[0029] (1) Modeling of maintenance optimization problem: Determine the optimization goal and constraints. The optimization goal includes minimizing the maintenance cost and ensuring the timeliness of elevator maintenance. The constraints include ensuring that the spare parts warehouse meets the maintenance demand and that each elevator completes maintenance once within a specified period.

[0030] The maintenance cost C is the sum of the maintenance costs of all elevators by all maintenance personnel, and the expression is as follows:

[0031]

[0032] In the formula, c i,j is the labor cost of maintenance personnel i serving elevator j; t i,j is the transportation cost of maintenance personnel i serving elevator j; p i,j The cost of spare parts when maintenance personnel i services elevator j;

[0033] The timeliness of elevator maintenance is calculated by the following expression:

[0034]

[0035] Where Reward is the sum of the incentives for the incentive algorithm to prioritize the allocation of maintenance resources to high-priority elevators, and Penalty is the sum of the penalties for failing to maintain high-priority elevators in a timely manner; R j is the priority coefficient of elevator j maintenance, P is the penalty coefficient, threshold is the priority coefficient threshold at which elevator maintenance is judged as high priority; α is the reward coefficient;

[0036] The fitness function of elevator maintenance optimization is obtained, and the expression is as follows:

[0037] Fitness=w1*C+w2*R

[0038] In the formula, w1 represents the weight coefficient of minimizing maintenance cost to the fitness function, and w2 represents the weight coefficient of maintenance timeliness to the fitness function;

[0039] The constraint expression for the spare parts library to meet maintenance requirements is as follows:

[0040]

[0041] In the formula, x ij Indicates whether elevator j has been assigned to maintenance personnel i, x ij =1 indicates that the task has been assigned, x ij =0 means no task is assigned; q ij is the spare parts required by maintenance personnel i to maintain elevator j, and S is the total amount of spare parts in the warehouse;

[0042] The constraint expression for each elevator to complete maintenance once within the specified period is as follows:

[0043]

[0044] (2) Randomly generate N elevator maintenance assignment tasks as the initial solution, and take the existing maintenance task assignment party as one of the initial solutions, N∈[20,100]; after generating the initial solution, check whether the initial solution meets the constraint requirements. If not, discard the initial solution and generate a new initial solution. All initial solutions constitute the initial population;

[0045] (3) Calculating the fitness of all initial solutions according to the fitness function, retaining the top 10% of the initial solutions with the highest fitness to the next generation population; assigning the probability of the remaining 90% of the initial solutions being selected as the parent generation according to the fitness level, and the higher the fitness, the higher the probability of being selected as the parent generation;

[0046] Randomly select 2 parents from the initial solution with assigned probabilities to perform crossover and random mutation to generate offspring, and repeat the operation of random selection and generation of offspring until 0.9*N offspring are generated. The generated offspring and the top 10% initial solutions with the highest fitness form a new population;

[0047] (4) Repeat step (3) until the highest comfort value in the population approaches 0, then the loop is terminated and the maintenance allocation plan with the highest comfort value is output as the optimal solution.

[0048] The beneficial effects of the present invention are:

[0049] Based on continuously updated data, the present invention formulates maintenance demand forecast optimization strategies, integrates complex factors such as elevator aging and retrofit elevators into the original forecast model, optimizes the accuracy of the model algorithm, and enhances the accuracy, practicality and adaptability of the original model. At the same time, accurate and comprehensive maintenance data will be opened to users to enhance users' trust in personalized and dynamic maintenance strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 The present invention provides a flowchart of an on-demand elevator maintenance method based on dynamic prediction. DETAILED DESCRIPTION

[0051] The present invention will be described in detail below according to the accompanying drawings and preferred embodiments, and the purpose and effect of the present invention will become more clear. The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0052] like Figure 1As shown, an elevator on-demand maintenance method based on dynamic prediction includes the following steps:

[0053] S1: Analysis of the problem of on-demand maintenance of elevators.

[0054] In this step, the formulation of elevator maintenance strategy is disassembled in detail, including maintenance items, maintenance standards, maintenance basis, maintenance scenarios, etc. These details will be used for subsequent data collection, analysis and prediction.

[0055] S2: Data collection.

[0056] Collect historical elevator maintenance data and elevator operation data.

[0057] Specifically, the elevator historical maintenance data includes the elevator machine room environment, operating device status, drive host vibration, brake status, encoder status, etc.;

[0058] In this embodiment, the data in the quarterly maintenance list of an elevator company is used as an example of the historical maintenance data of the elevator, and the maintenance items are used as the characteristic data. The results of each item are divided into three situations: normal (meets the requirements, and the test and experimental functions are normal), abnormal (found to be non-compliant, and needs to be adjusted or replaced), and none (the elevator does not have this item or function). According to the needs of elevator maintenance, the characteristic value of the characteristic data with abnormal results is scored as 1, and the characteristic value of the characteristic data with normal or none results is scored as 0. That is, if it reaches 1 point, it means that the item needs maintenance.

[0059] Specifically, elevator operation data refers to elevator operation status data and usage data collected by installing various sensors in the elevator, such as acceleration sensors, temperature sensors, sound sensors, etc. The following are some sample data collection:

[0060] Operation status data, including: elevator operation time, speed, acceleration, temperature and other information.

[0061] Usage data, including: elevator operation frequency, peak hours and other information.

[0062] S3: Maintenance data analysis and feature engineering.

[0063] In this step, the data collected by S2 is preprocessed and feature engineered.

[0064] Data preprocessing: The collected elevator maintenance data and elevator operation data are cleaned, processed for outliers, and processed for missing values ​​to ensure the accuracy and completeness of the data.

[0065] Feature engineering: Select key features of elevator maintenance from the preprocessed historical elevator maintenance data and elevator operation data, and assign weight values ​​according to the importance of the features to elevator maintenance.

[0066] In this embodiment, 45 key features of elevator maintenance are extracted, as shown in Table 1. In Table 1, the requirements for judging the "machine room and pulley room environment" numbered 1 as normal are cleanliness, intact doors and windows, and normal lighting; the requirements for the "manual emergency operation device status" numbered 2 are that the device is complete and located at the specified position; the requirements for the "drive host status" numbered 3 are that there is no abnormal vibration and abnormal sound during operation; the requirements for the "brake clearance status" numbered 5 are that the brake lining and the brake wheel should not rub when opened, and the clearance value meets the requirements of the manufacturing unit; the "brake self-monitoring status" numbered 6 specifically refers to the self-monitoring status of the brake when it is used as the stopping subsystem of the car accidental movement protection device; The requirement for "encoder status" No. 7 is to be clean and firmly installed; the requirement for "oil cup status on guide shoe" No. 13 specifically refers to whether the oil amount in the oil cup is appropriate and whether there is any leakage; the requirement for "engagement length of floor door locking element" No. 29 is to be no less than 7mm; the requirement for "pit environment status" No. 30 is to be clean, free of water seepage and accumulation, and normal lighting; the requirement for "reducer lubricating oil status" No. 33 is to have an appropriate amount of lubricating oil and no leakage; the requirement for "traction wheel groove and suspension device cleanliness, wire rope status" No. 37 is to be free of severe grease, have uniform tension, and meet the requirements of the manufacturing unit.

[0067] Table 1 Elevator maintenance feature number table

[0068]

[0069] According to the importance of these key features to elevator maintenance, these key features are divided into three levels: A, B, and C. The weights are assigned to Class A features as 0.2, Class B features as 0.5, and Class C features as 1. The classification is shown in Table 2.

[0070] Table 2 Elevator maintenance feature classification and weight assignment table

[0071]

[0072] S4: Elevator health prediction and maintenance needs assessment, mainly including the following steps:

[0073] S4.1: First, build and train the elevator health assessment model, which is implemented through the following steps:

[0074] S4.1.1: Construct training data set: Group the pre-processed elevator operation data based on the maintenance cycle, and extract the mathematical and statistical features of the elevator operation data in each maintenance cycle to obtain the training data of the maintenance cycle. Specifically, for the elevator door opening and closing state, which is binary data, the number of door opening and closing times is counted in each maintenance cycle; for continuous data such as elevator running speed, elevator running acceleration, and elevator running temperature, the maximum value, minimum value, average value, variance and other mathematical and statistical features are calculated in each maintenance cycle; all the obtained mathematical and statistical features are spliced ​​to obtain the statistical feature data (i.e., training data) of the maintenance cycle.

[0075] The historical maintenance data processed by S3 is used to perform weighted summation on the results of each maintenance item in the same maintenance cycle to obtain the elevator health score. The elevator health is classified according to the elevator health score, and the obtained health classification result is used as the training label of the maintenance cycle.

[0076] In this embodiment, the elevator health classification is specifically performed according to the method shown in Table 3 below.

[0077] Table 3 Elevator health scores and elevator maintenance requirements

[0078] Elevator Health Score Elevator maintenance requirements and priorities 0-10 points normal 11-25 points Need attention, maintenance low priority 26-35 points Warning, maintenance medium priority 36-45 points Fault, maintenance high priority

[0079] The statistical features of all maintenance cycles are arranged correspondingly with the training labels to obtain the training data set.

[0080] S4.1.2: Construct an elevator health assessment model: The elevator health assessment model is implemented based on the LSTM algorithm. The model consists of five layers in sequence: input layer, LSTM layer one, LSTM layer two, fully connected layer, and output layer.

[0081] Input layer: used to accept time series data with multiple features as input sequence.

[0082] LSTM layer 1: contains multiple LSTM units, which are used to capture the basic temporal relationship between features. The number of LSTM units can be set according to needs, generally between 20 and 100.

[0083] LSTM layer 2: also contains multiple LSTM units, which are used to further extract deeper temporal relationships between features; the number of LSTM units can be the same as or different from that of LSTM layer 1, and the number of LSTM units is also between 20 and 100.

[0084] Fully connected layer: used to extract potential interactions between input features.

[0085] Output layer: Connect the output of the fully connected layer to the output layer to output the elevator health score predicted by the model.

[0086] S4.1.3: Use the training data set constructed in S4.1.1 to train the elevator health assessment model and use appropriate loss functions and optimization algorithms during the training process, such as the mean squared error (MSE) loss function and the stochastic gradient descent (SGD) optimization algorithm to optimize the model.

[0087] S4.2: The historical elevator maintenance data and the real-time collected elevator operation data are used as the elevator data to be evaluated. After processing, they are input into the trained elevator health assessment model for calculation and analysis to obtain real-time elevator health assessment results.

[0088] S4.3: Maintenance demand assessment: Determine whether the elevator needs maintenance and the maintenance priority based on the elevator health assessment result. Specifically, if the elevator health assessment result is normal, it is determined that maintenance is not required; if the elevator health assessment result is "needs attention", it is determined that maintenance is required and the maintenance priority is low; if the elevator health assessment result is "warning", it is determined that maintenance is required and the maintenance priority is medium; if the elevator health assessment result is "fault", it is determined that maintenance is required and the maintenance priority is high.

[0089] In this step, when the elevator operation data is evaluated in real time, a maintenance demand prediction curve for the elevator can be generated based on the elevator health assessment model to achieve real-time prediction of the elevator maintenance demand. The curve reflects the future trend of the elevator health score and triggers maintenance instructions when the score reaches the maintenance priority index threshold.

[0090] S5: Generate maintenance strategy.

[0091] In this step, a targeted maintenance strategy is generated based on the elevator health assessment results and the maintenance priority assessment results obtained in S4. The maintenance strategy includes: maintenance personnel allocation, maintenance time allocation, etc.

[0092] In this embodiment, for normal elevators, two inspection and maintenance personnel will be dispatched every month for maintenance; for elevators that need attention and have a low maintenance priority, one inspection and maintenance personnel and one senior maintenance specialist will be dispatched to inspect them every two weeks; for warning elevators with a medium maintenance priority, two senior maintenance specialists will be dispatched to complete the inspection of the elevator within one week; for faults, three senior maintenance specialists will be dispatched to complete the inspection of the elevator within 24 hours.

[0093] S6: Optimization of maintenance strategy.

[0094] Maintenance resource optimization: Consider the limitation of maintenance resources and optimize the maintenance strategies generated by S5. Adjust the arrangement and priority of maintenance strategies according to factors such as the availability and cost of maintenance personnel, tools and equipment to maximize maintenance efficiency and resource utilization.

[0095] Maintenance feedback and optimization: Collect feedback information during the maintenance process, including maintenance records, fault repair status, maintenance costs, etc. Analyze feedback information, evaluate maintenance results, and identify potential problems and room for improvement. Optimize and adjust maintenance strategies based on feedback information to improve maintenance quality and efficiency.

[0096] Continuous improvement: Regularly evaluate the effectiveness and feasibility of maintenance strategies and make continuous improvements based on actual conditions. Based on data such as elevator health assessment, maintenance execution and maintenance feedback, continuously optimize maintenance strategies and processes to adapt to changing needs and environments.

[0097] Specifically, in this step, the maintenance strategy is continuously optimized and adjusted according to the actual situation and needs, which can make the maintenance demand forecast continue to be accurate. According to the passage of time and the actual data fed back during the maintenance execution process, the data collection frequency, feature extraction method and data analysis algorithm are adjusted to optimize the maintenance strategy and process. Or, an optimization algorithm (such as genetic algorithm, simulated annealing algorithm, etc.) is used to optimize and adjust the maintenance strategy to achieve the reasonable allocation of maintenance resources and the optimization of maintenance effect.

[0098] This embodiment will further explain the maintenance strategy based on the genetic algorithm. The specific steps are as follows:

[0099] (7.1) Modeling of maintenance optimization problem:

[0100] Determine the optimization objectives and constraints. The optimization objectives include minimizing maintenance costs and ensuring the timeliness of elevator maintenance, while the constraints include ensuring that the spare parts warehouse meets maintenance needs and that each elevator must complete maintenance within a specified period.

[0101] The optimization objective can be modeled as follows.

[0102] ① Considering the optimization goal of minimizing maintenance cost, the maintenance cost C is the sum of the maintenance costs of all maintenance personnel for all elevators. The optimization objective function can be expressed as:

[0103]

[0104] In the formula, c i,j is the labor cost of maintenance personnel i serving elevator j; t i,j is the transportation cost of maintenance personnel i serving elevator j; pi,j is the spare parts cost when maintenance personnel i services elevator j.

[0105] ② Considering the optimization goal of ensuring the timeliness of elevator maintenance, the elevator maintenance timeliness coefficient can be expressed as:

[0106]

[0107] Where Reward is the sum of the incentives for the incentive algorithm to prioritize the allocation of maintenance resources to high-priority elevators, and Penalty is the sum of the penalties for failing to maintain high-priority elevators in a timely manner.

[0108] Specifically, for elevator j:

[0109]

[0110] In the formula, R j is the priority coefficient of elevator j maintenance, P is the penalty coefficient, which is used to adjust the penalty intensity; threshold is the priority coefficient threshold for elevator maintenance to be judged as high priority, that is, for elevator maintenance that meets R j >threshold, it is considered as a high priority.

[0111]

[0112] Where α is the reward coefficient, which is used to indicate the intensity of the reward for handling high-priority maintenance issues.

[0113] All optimization objective functions are integrated according to the weights to obtain the fitness function of elevator maintenance optimization:

[0114] Fitness=w1*C+w2*R

[0115] Where w1 represents the weight coefficient of minimizing maintenance cost to the fitness function, and w2 represents the weight coefficient of maintenance timeliness to the fitness function.

[0116] Constraints can be modeled as follows:

[0117] ①Each elevator must complete maintenance once within the prescribed period:

[0118]

[0119] In the formula, the variable x ij Used to indicate whether elevator j is assigned to maintenance personnel i, x ij =1 means the task is assigned, x ij =0 means no task is assigned.

[0120] ② The spare parts library meets maintenance needs:

[0121]

[0122] In the formula, q ij are the spare parts required by maintenance personnel i to maintain elevator j, and S is the total amount of spare parts in the warehouse.

[0123] (7.2) Randomly generate N elevator maintenance assignment tasks as the initial solution, and take the existing maintenance task assignment party as one of the initial solutions, usually N∈[20,100]; after generating the initial solution, check whether the initial solution meets the constraint requirements. If not, discard the initial solution and generate a new initial solution. Finally, all the initial solutions constitute the initial population.

[0124] (7.3) The fitness of all initial solutions is calculated according to the fitness function, and the top 10% of the initial solutions with the highest fitness are retained to the next generation of the population; the remaining 90% of the initial solutions are assigned the probability of being selected as the parent according to their fitness. The higher the fitness, the higher the probability of being selected as the parent.

[0125] Randomly select 2 parents from the initial solution with assigned probabilities to perform crossover and random mutation to generate offspring, and repeat this operation until 0.9*N offspring are generated. The generated offspring and the top 10% initial solutions with the highest fitness form a new population.

[0126] (7.4) Repeat step (7.3) until the highest comfort value in the population approaches 0, then the loop is terminated and the maintenance allocation plan with the highest comfort value is output as the optimal solution.

[0127] S8: Visualization of maintenance strategy execution and monitoring.

[0128] In this step, the generated maintenance plan is implemented in actual operation, and the elevator operation status, maintenance plan and execution are monitored and displayed through visualization technology. The maintenance plan is implemented in actual operation, and maintenance execution and monitoring are carried out.

[0129] Use data visualization, dashboards, reports and other technologies to visualize and monitor elevator operating status, maintenance plans and execution status, and assist in real-time monitoring of maintenance status.

[0130] Those skilled in the art can understand that the above are only preferred examples of the invention and are not intended to limit the invention. Although the invention is described in detail with reference to the above examples, those skilled in the art can still modify the technical solutions recorded in the above examples or replace some of the technical features therein with equivalents. Any modification, equivalent replacement, etc. made within the spirit and principle of the invention shall be included in the protection scope of the invention.

Claims

1. An elevator on-demand maintenance method based on dynamic prediction, characterized in that: The following steps are involved: Step 1: Obtain elevator maintenance data in real time and pre-process it, then extract the key features of elevator maintenance in the data, and assign weight values ​​to the importance of elevator maintenance according to the features; maintenance data includes operation status data and usage data; operation status data includes elevator operation time, speed, acceleration, and temperature; usage data includes elevator operation frequency and peak period; Step 2: Extract statistical features of elevator maintenance key features in each maintenance cycle; Based on historical maintenance data, the results of each maintenance project in the same maintenance cycle are weighted and summed to obtain the elevator health score. The elevator health score is then used to classify the elevator health, and the classification result is used as the training label for the maintenance cycle. Arrange the statistical features of all maintenance cycles corresponding to the training labels to obtain the training data set; Build and train an elevator health assessment model based on the LSTM algorithm; Step 3: After the elevator historical maintenance data and the real-time collected elevator operation data are processed by S1, they are input into the trained elevator health assessment model, the elevator health assessment result is output, and the maintenance priority assessment result is obtained accordingly; Step 4: Generate a maintenance strategy based on the elevator health assessment result and the priority assessment result; Step 5: Consider maintenance resource constraints and optimize maintenance strategies based on the availability of maintenance personnel, tools and equipment, and maintenance costs; Step 6: During the actual implementation of the maintenance strategy, monitor the elevator operation status, maintenance plan and execution; And based on the feedback information, the optimization algorithm is used to optimize the maintenance strategy.

2. The elevator on-demand maintenance method based on dynamic prediction according to claim 1 is characterized in that: In the step 1, the preprocessing includes: data cleaning, data outlier processing, data missing value processing, and classified storage of data.

3. The elevator on-demand maintenance method based on dynamic prediction according to claim 1 is characterized in that: In the step 2, statistical feature extraction is performed on the key features of elevator maintenance in each maintenance cycle, specifically: The preprocessed elevator operation data are grouped based on the maintenance cycle, and the mathematical statistical features of the elevator operation data in each maintenance cycle are extracted. For binary data with only two states, the number of times these two states exist is counted in each maintenance cycle; for continuous data with multiple states, mathematical statistical features are calculated in each maintenance cycle, including: maximum value, minimum value, average value, and variance calculation; all the obtained mathematical statistical features are spliced ​​to obtain the statistical feature data of the maintenance cycle as training data.

4. The elevator on-demand maintenance method based on dynamic prediction according to claim 1 is characterized in that: The elevator health is divided into four categories. If the elevator health score is 0-10 points, the corresponding elevator health assessment result is normal and no maintenance is required; If the elevator health score is between 11 and 25, the corresponding elevator health assessment result is "needs attention", which means maintenance is required and the maintenance priority is low; If the elevator health score is 26-35 points, the corresponding elevator health assessment result is that it is determined to be in need of maintenance, and the maintenance priority is medium; If the elevator health score is 36-45 points, the corresponding elevator health assessment result is that it is determined to require maintenance and the maintenance priority is high.

5. The elevator on-demand maintenance method based on dynamic prediction according to claim 1 is characterized in that: The elevator health assessment model includes five layers in sequence: input layer, LSTM layer 1, LSTM layer 2, fully connected layer, and output layer; The input layer is used to accept time series data of multiple features as an input sequence; The LSTM layer 1 includes multiple LSTM units for capturing the basic temporal relationship between features; the number of LSTM units is between 20 and 100; The LSTM layer 2 includes multiple LSTM units for further extracting deeper temporal relationships between features; the number of LSTM units is between 20 and 100; The fully connected layer is used to extract potential interaction relationships between input features; The output of the fully connected layer is connected to the output layer, which outputs the elevator health score predicted by the model.

6. The elevator on-demand maintenance method based on dynamic prediction according to claim 1 is characterized in that: The training data set is used to train the elevator health assessment model, and during the training process, the mean square error loss function and the stochastic gradient descent optimization algorithm are used to optimize the elevator health assessment model.

7. The elevator on-demand maintenance method based on dynamic prediction according to claim 1 is characterized in that: The maintenance strategy includes: allocation of maintenance personnel and allocation of maintenance time.

8. The elevator on-demand maintenance method based on dynamic prediction according to claim 1, characterized in that: In step 6, the optimization algorithm uses a genetic algorithm, and the specific steps of using the genetic algorithm to optimize the maintenance strategy are as follows: (1) Modeling of maintenance optimization problem: Determine the optimization goal and constraints. The optimization goal includes minimizing the maintenance cost and ensuring the timeliness of elevator maintenance. The constraints include ensuring that the spare parts warehouse meets the maintenance demand and that each elevator completes maintenance once within a specified period. The maintenance cost C is the sum of the maintenance costs of all elevators by all maintenance personnel, and the expression is as follows: In the formula, c i,j is the labor cost of maintenance personnel i serving elevator j; t i,j is the transportation cost of maintenance personnel i serving elevator j; p i,j The cost of spare parts when maintenance personnel i services elevator j; The timeliness of elevator maintenance is calculated by the following expression: Where Reward is the sum of the incentives for the incentive algorithm to prioritize the allocation of maintenance resources to high-priority elevators, and Penalty is the sum of the penalties for failing to maintain high-priority elevators in a timely manner; R j is the priority coefficient of elevator j maintenance, P is the penalty coefficient, threshold is the priority coefficient threshold at which elevator maintenance is judged as high priority; α is the reward coefficient; The fitness function of elevator maintenance optimization is obtained, and the expression is as follows: Fitness=w1*C+w2*R In the formula, w1 represents the weight coefficient of minimizing maintenance cost to the fitness function, and w2 represents the weight coefficient of maintenance timeliness to the fitness function; The constraint expression for the spare parts library to meet maintenance requirements is as follows: In the formula, x ij Indicates whether elevator j has been assigned to maintenance personnel i, x ij =1 indicates that the task has been assigned, x ij =0 means no task is assigned; q ij is the spare parts required by maintenance personnel i to maintain elevator j, and S is the total amount of spare parts in the warehouse; The constraint expression for each elevator to complete maintenance once within the specified period is as follows: (2) Randomly generate N elevator maintenance assignment tasks as the initial solution, and take the existing maintenance task assignment party as one of the initial solutions, N∈[20,100]; after generating the initial solution, check whether the initial solution meets the constraint requirements. If not, discard the initial solution and generate a new initial solution. All initial solutions constitute the initial population; (3) Calculating the fitness of all initial solutions according to the fitness function, retaining the top 10% of the initial solutions with the highest fitness to the next generation population; assigning the probability of the remaining 90% of the initial solutions being selected as the parent generation according to the fitness level, and the higher the fitness, the higher the probability of being selected as the parent generation; Randomly select 2 parents from the initial solution with assigned probabilities to perform crossover and random mutation to generate offspring, and repeat the operation of random selection and generation of offspring until 0.9*N offspring are generated. The generated offspring and the top 10% initial solutions with the highest fitness form a new population; (4) Repeat step (3) until the highest comfort value in the population approaches 0, then the loop is terminated and the maintenance allocation plan with the highest comfort value is output as the optimal solution.

Images