Evaluation system and method applied to elevator maintenance and repair quality

Abstract

The invention discloses an evaluation system and method applied to elevator maintenance and repair quality, and belongs to the field of elevator maintenance management. An elevator maintenance and repair quality evaluation set is set by setting an evaluation index set; historical elevator data are collected, evaluation index features are extracted, and an evaluation index feature matrix is constructed; constructing an initial support vector machine model and setting related parameters; the training initial support vector machine model is equal to the training initial support vector machine model, and a trained support vector machine model is obtained; the trained support vector machine model is tested, and after testing is completed, a final support vector machine model is obtained; and collecting current elevator data, extracting current elevator evaluation index feature data from the current elevator data, and obtaining an evaluation result of the current elevator maintenance and repair quality by using the final support vector machine model. Scientific basis is provided for maintenance and management of the elevator, and the operation efficiency and safety of the elevator are improved.

Description

[0001] Technical Field The present invention belongs to the technical field of elevator maintenance management, and particularly relates to an evaluation system and method for elevator maintenance and repair quality.

[0002] Background Art With the acceleration of the urbanization process, elevators, as indispensable vertical transportation tools in modern buildings, their safety and reliability have been increasingly emphasized. The quality of elevator maintenance and repair is directly related to the operating status and service life of elevators, and thus affects the safety and comfort of passengers. However, the current evaluation of elevator maintenance and repair quality often relies on manual inspection and experience judgment, with problems such as strong subjectivity and inconsistent evaluation criteria. Summary of the Invention

[0003] (I) Technical Problems to be Solved Aiming at the problems in the related technologies, the present invention provides an evaluation system and method for elevator maintenance and repair quality. By establishing a scientific and comprehensive elevator maintenance and repair quality evaluation system, it is of great significance for improving elevator management level and ensuring the safe operation of elevators.

[0004] (II) Technical Solutions To solve the above technical problems, the present invention is realized through the following technical solutions: The present invention is an evaluation method for elevator maintenance and repair quality, including the following steps: S1. Collect the operation data and maintenance record data of historical elevators; obtain historical elevator data; set an evaluation index set, and set an elevator maintenance and repair quality evaluation set; according to the set evaluation index set, extract the characteristics of each evaluation index in the evaluation index set from the historical elevator data, and construct an evaluation index feature matrix; S2. Construct an initial support vector machine model and set relevant parameters; divide the evaluation index feature matrix into an evaluation index feature training matrix and an evaluation index feature test matrix; according to the elevator maintenance and repair quality evaluation set, set a label for each elevator data in the evaluation index feature training matrix and the evaluation index feature test matrix to obtain an evaluation index feature training label set and an evaluation index feature test set; S3. Use the gradient descent method, the evaluation index feature training matrix and the evaluation index feature training label set to train the initial support vector machine model to obtain a trained support vector machine model; S4. Input the evaluation index feature test matrix into the trained support vector machine model for testing. After the testing is completed, obtain a final support vector machine model; S5. Collect the current elevator data, extract the current elevator evaluation index feature data from the current elevator data, and use the final support vector machine model to obtain the evaluation result of the current elevator maintenance and repair quality.

[0005] Preferably, the S1 includes the following steps: S11. Collect the operation data and maintenance record data of historical elevators; obtain the historical elevator data; S12. Set the evaluation index set , where a i represents the i-th evaluation index of the elevator maintenance and repair quality, and n represents the total number of elevator maintenance and repair quality evaluation indexes in the evaluation index set; S13. Set the elevator maintenance and repair quality evaluation set , b 1 represents excellent, b 2 represents good, b 3 represents poor; S14. According to the set evaluation index set, extract the features of each evaluation index in the evaluation index set from the historical elevator data, and construct the evaluation index feature matrix A, as follows, ; Among them, Ain represents the feature data of the n-th evaluation index of the i-th elevator data in the evaluation index feature matrix; m represents that the evaluation index feature matrix has m elevator data; The above steps establish an evaluation model for elevator maintenance and repair quality by analyzing historical data, so as to better understand the performance and potential problems of elevators, and provide decision support for future maintenance; these steps also provide a data basis for elevator fault prediction and preventive maintenance, and help improve the safety and reliability of elevators.

[0006] Preferably, the S2 includes the following steps: S21. Construct an initial support vector machine model, set the penalty parameter as c, the learning rate as k, and set the kernel function as the Gaussian kernel function, as follows, the function expression is as follows:

[0007] Among them, d 1 and d 2 represent the data sample points of two historical elevator data, and v represents the parameter of the Gaussian kernel function; S22. Set the training data ratio of the initial support vector machine model as e 1 and the test data ratio as e 2 , according to the training data ratio as e 1 and the test data ratio as e 2Divide the evaluation index feature matrix A into an evaluation index feature training matrix B and an evaluation index feature test matrix C as follows: ; ; where Bin represents the feature data of the nth evaluation index of the ith elevator data in the evaluation index feature training matrix; o represents that there are o elevator data in the evaluation index feature matrix; Cin represents the feature data of the nth evaluation index of the ith elevator data in the evaluation index feature matrix; g represents that there are g elevator data in the evaluation index feature matrix; S23. According to the elevator maintenance and repair quality evaluation set , set a label for each elevator data in the evaluation index feature training matrix B and the evaluation index feature test matrix C, and construct an evaluation index feature training label set and an evaluation index feature test set , where h i represents the label of the ith elevator data in the evaluation index feature training matrix, and j i represents the label of the ith elevator data in the evaluation index feature training matrix; An initial support vector machine model is constructed through the above steps; by setting the penalty parameter, learning rate and Gaussian kernel function, the model can learn the pattern of elevator maintenance and repair quality from the evaluation index feature matrix; dividing the evaluation index feature matrix into a training matrix and a test matrix helps the model learn features during training and verify the prediction ability of the model during testing; setting labels for each elevator data and constructing a training label set and a test set can guide the model to learn and evaluate the performance of the model during testing; by training the support vector machine model, the maintenance and repair quality of the elevator can be effectively evaluated and predicted, providing a scientific basis for the maintenance and management of the elevator, and improving the operation efficiency and safety of the elevator.

[0008] Preferably, S3 includes the following steps: S31. Bring the evaluation index feature training matrix and the evaluation index feature training label set into the initial support vector machine model for training, and use the gradient descent method to train the initial support vector machine model in combination with the evaluation index feature training matrix and the evaluation index feature training label set to obtain a trained support vector machine model; Through the above steps, the model can better adapt to the training data and improve the prediction accuracy.

[0009] Preferably, S31 includes the following steps: S311. Maximize the margin by minimizing the objective function, and finally achieve the purpose of optimizing the support vector machine model. The formula for minimizing the objective function is as follows: ; where w is the weight vector, u is the bias term, c is the penalty parameter, y i is the label of the i-th elevator data, and x i is the feature vector of the i-th elevator data; o is the total number of elevator data in the evaluation index feature training matrix; The gradient of the objective function with respect to w is as follows, ; where is the indicator function, which returns 1 when the condition holds and 0 otherwise; The gradient of the objective function with respect to u is as follows, ; S312. According to the gradient descent algorithm, update w and u through the following formula, as follows, ; S313. Set the objective function threshold to α and the maximum number of iterations to l 1 , and the current number of iterations is l 2 ; Repeat S311 and S312, and stop the iteration when the objective function value ≤ α or l 2 ≥ l 1 to obtain the trained support vector machine model; In the above steps, the parameters of the model are iteratively adjusted by the gradient descent method to minimize the difference between the model prediction value and the actual value; enabling the model to better adapt to the training data and improve the prediction accuracy; obtaining the trained support vector machine model, which can be used to evaluate and predict the maintenance and repair quality of new elevator data.

[0010] Preferably, the said S4 includes the following steps: S41. Set the accuracy threshold to p 1 , input the evaluation index feature test set matrix into the trained support vector machine model for testing, obtain the test result, and compare the test result with the evaluation index feature test label set to obtain the test accuracy p 2 ; S42. When p 2 ≥ p 1 , regard the trained support vector machine model as the final support vector machine model; S43. When p 2 < p 1 , continue to optimize the trained support vector machine model to obtain the final support vector machine prediction model; By testing and optimizing the support vector machine model, the accuracy and reliability of the model can be improved, thus more accurately evaluating the maintenance and repair quality of elevators.

[0011] Preferably, the steps of further optimizing the trained support vector machine model in the above to obtain the final support vector machine prediction model include the following: S431. Return the maximum training iteration number q of the support vector machine model set in S31, where the current iteration number is q. 1 , and repeat S31 and S41. 2 ; S432. When q 2 ≥q 1 or p 2 ≥p 1 , stop the iteration to obtain the final support vector machine model. The above steps further ensure that the final support vector machine model has sufficient accuracy to effectively evaluate and predict the maintenance and repair quality of elevators.

[0012] Preferably, the above S5 includes the following steps: S51. Collect the operation data and maintenance record data of the current elevator to obtain the current elevator data; extract the feature data of each evaluation index in the evaluation index set from the current elevator data; obtain the current elevator evaluation index feature data. S52. Substitute the current elevator index feature data into the final support vector machine model to obtain the evaluation result of the current elevator maintenance and repair quality. The above steps can timely detect problems existing in the elevator through the evaluation of the current elevator, and take corresponding measures for maintenance and repair, thus avoiding potential safety risks; at the same time, these steps also provide data support for the fault prediction and preventive maintenance of the elevator, helping to improve the operation efficiency and safety of the elevator.

[0013] An evaluation system applied to the maintenance and repair quality of elevators includes an evaluation standard setting module, a data collection module, a model training module, a model testing module, and an evaluation module for the maintenance and repair quality of elevators. The evaluation standard setting module is used to set the evaluation index set affecting the evaluation result of the elevator maintenance and repair quality, and set the elevator maintenance and repair quality evaluation set including the evaluation result of the elevator maintenance and repair quality. The data collection module is used to collect historical elevator data, extract the features of each evaluation index from the historical elevator data, construct an evaluation index feature matrix; and divide the evaluation index feature matrix into an evaluation index feature training matrix and an evaluation index feature test matrix; and set an evaluation index feature training label matrix and an evaluation index feature test label matrix; collect current elevator data, extract the features of the current elevator data evaluation index, and obtain the current elevator evaluation index feature data; The model training module is used to construct an initial support vector machine model, use the evaluation index feature training matrix and the evaluation index feature training label matrix, and combine the gradient descent method to train the initial support vector machine model to obtain the trained initial support vector machine model; The model testing module is used to test using the evaluation index feature test matrix and the evaluation index feature test label matrix. After the test is completed, a final support vector machine model is obtained; The evaluation module for the elevator maintenance and repair quality is used to input the current elevator evaluation index feature data into the final support vector machine model to obtain an evaluation result.

[0014] (III)Advantages The present invention has the following advantages: The advantages of the present invention are mainly reflected in the following aspects: By establishing a scientific and comprehensive elevator maintenance and repair quality evaluation system, the present invention improves the objectivity and accuracy of elevator management level; the traditional elevator maintenance and repair quality evaluation mainly relies on manual inspection and experience judgment, with strong subjectivity and inconsistent evaluation criteria; while the present invention collects the operation data and maintenance record data of historical elevators, establishes an evaluation index set, constructs an evaluation index feature matrix, and combines with a support vector machine model for training and testing, making the evaluation process more objective and accurate, and helping to improve the scientificity and effectiveness of elevator maintenance management.

[0015] The present invention provides an evaluation result for the elevator maintenance and repair quality, which helps to improve the safety and reliability of the elevator; by analyzing historical data and evaluation results, the performance and potential problems of the elevator can be better understood, providing decision-making support for future maintenance; at the same time, these data also provide a basis for elevator fault prediction and preventive maintenance, helping to detect and solve potential problems in advance and improve the safety and reliability of the elevator.

[0016] The method of the present invention can effectively evaluate and predict the maintenance and repair quality of elevators, provide a scientific basis for the maintenance and management of elevators, and improve the operation efficiency and safety of elevators; by training a support vector machine model, the patterns of elevator maintenance and repair quality can be learned, and the evaluation results can be obtained based on the current elevator data; these evaluation results can provide a scientific basis for the maintenance and management of elevators, and contribute to improving the operation efficiency and safety of elevators.

[0017] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0019] Figure 1 It is a schematic diagram of a system and method for evaluating the maintenance and repair quality of elevators applied to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The technical solutions in the embodiments of the invention will be clearly and completely described below with reference to the drawings in the embodiments of the invention. Obviously, the described embodiments are only some embodiments of the invention, not all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the invention without creative efforts belong to the scope of protection of the invention.

[0021] In the description of the present invention, it should be understood that the terms "opening", "upper", "lower", "top", "middle", "inner", etc. indicating the orientation or position relationship are only for the convenience of describing the invention and simplifying the description, rather than indicating or implying that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation of the invention.

[0022] Embodiment 1: Please refer to Figure 1 , the present invention is an evaluation method for the maintenance and repair quality of elevators, including the following steps: S1. Collect the operation data and maintenance record data of historical elevators; obtain the historical elevator data; set an evaluation index set and an evaluation set for the maintenance and repair quality of elevators; extract the features of each evaluation index in the evaluation index set from the historical elevator data according to the set evaluation index set, and construct an evaluation index feature matrix; The step S1 includes the following steps: S11. Collect the operation data and maintenance record data of historical elevators; obtain historical elevator data; S12. Set the evaluation index set , where a i represents the i-th evaluation index of the elevator maintenance and repair quality, and n represents the total number of elevator maintenance and repair quality evaluation indexes in the evaluation index set; S13. Set the elevator maintenance and repair quality evaluation set , b 1 represents excellent, b 2 represents good, b 3 represents poor; S14. According to the set evaluation index set, extract the characteristics of each evaluation index in the evaluation index set from the historical elevator data, and construct an evaluation index feature matrix A as follows, ; where Ain represents the characteristic data of the n-th evaluation index of the i-th elevator data in the evaluation index feature matrix; m represents that the evaluation index feature matrix has m elevator data; S2. Construct an initial support vector machine model and set relevant parameters; divide the evaluation index feature matrix into an evaluation index feature training matrix and an evaluation index feature test matrix; according to the elevator maintenance and repair quality evaluation set, set a label for each elevator data in the evaluation index feature training matrix and the evaluation index feature test matrix to obtain an evaluation index feature training label set and an evaluation index feature test set; The S2 includes the following steps: S21. Construct an initial support vector machine model, set the penalty parameter as c, the learning rate as k, and set the kernel function as the Gaussian kernel function, as follows, the function expression is as follows:

[0023] where d 1 and d 2 represent data sample points of two different working conditions, and v represents the parameter of the Gaussian kernel function; S22. Set the training data ratio of the initial support vector machine model as e 1 and the test data ratio as e 2 , according to the training data ratio as e 1 and the test data ratio as e 2 divide the evaluation index feature matrix A into an evaluation index feature training matrix B and an evaluation index feature test matrix C, as follows, ; ; Among them, Bin represents the feature data of the nth evaluation index of the ith elevator data in the evaluation index feature training matrix; o represents that there are o elevator data in the evaluation index feature matrix; Cin represents the feature data of the nth evaluation index of the ith elevator data in the evaluation index feature matrix; g represents that there are g elevator data in the evaluation index feature matrix; S23. According to the elevator maintenance and repair quality evaluation set , set a label for each elevator data in the evaluation index feature training matrix B and the evaluation index feature test matrix C, and construct the evaluation index feature training label set and the evaluation index feature test set , where h i represents the label of the ith elevator data in the evaluation index feature training matrix, and j i represents the label of the ith elevator data in the evaluation index feature training matrix; S3. Use the gradient descent method, the evaluation index feature training matrix, and the evaluation index feature training label set to train the initial support vector machine model to obtain the trained support vector machine model; The S3 includes the following steps: S31. Substitute the evaluation index feature training matrix and the evaluation index feature training label set into the initial support vector machine model for training, and use the gradient descent method combined with the evaluation index feature training matrix and the evaluation index feature training label set to train the initial support vector machine model to obtain the trained support vector machine model; The S31 includes the following steps: S311. Maximize the margin by minimizing the objective function, and finally achieve the purpose of optimizing the support vector machine model. The formula for minimizing the objective function is as follows, ; Among them, w is the weight vector, u is the bias term, c is the penalty parameter, y i is the label of the ith elevator data, and x i is the feature vector of the ith elevator data; o is the total number of elevator data in the evaluation index feature training matrix; The gradient of the objective function with respect to w is as follows, ; Among them is the indicator function, which returns 1 when the condition is true and 0 otherwise; The gradient of the objective function with respect to u is as follows, ; S312. According to the gradient descent algorithm, update w and u through the following formula, as follows, ; S313. Set the objective function threshold to α and the maximum number of iterations to l 1 , where the current number of iterations is l 2 ; Repeat S311 and S312. When the objective function value ≤ α or l 2 ≥ l 1 , stop the iteration to obtain the trained support vector machine model; S4. Input the evaluation index feature test matrix into the trained support vector machine model for testing. After the test is completed, obtain the final support vector machine model; S4 includes the following steps: S41. Set the accuracy threshold to p 1 . Input the evaluation index feature test set matrix into the trained support vector machine model for testing to obtain the test result. Compare the test result with the evaluation index feature test label set to obtain the test accuracy p 2 ; S42. When p 2 ≥ p 1 , use the trained support vector machine model as the final support vector machine model; S43. When p 2 < p 1 , continue to optimize the trained support vector machine model to obtain the final support vector machine prediction model; The step of continuing to optimize the trained support vector machine model to obtain the final support vector machine prediction model in 43 includes the following steps: S431. Return to S31 to set the maximum number of training iterations q of the trained support vector machine model 1 , where the current number of iterations is q 2 , and repeat S31 and S41; S432. When q 2 ≥ q 1 or p 2 ≥ p 1 , stop the iteration to obtain the final support vector machine model; S5. Collect the current elevator data, extract the current elevator evaluation index feature data from the current elevator data, and use the final support vector machine model to obtain the evaluation result of the current elevator maintenance and repair quality; S5 includes the following steps: S51. Collect the operation data and maintenance record data of the current elevator to obtain the current elevator data; extract the feature data of each evaluation index in the evaluation index set from the current elevator data; obtain the current elevator evaluation index feature data; S52. Input the current elevator index feature data into the final support vector machine model to obtain the evaluation result of the current elevator maintenance and repair quality.

[0024] Embodiment 2: An evaluation system for elevator maintenance and repair quality, which sets an evaluation standard module, a data collection module, a model training module, a model testing module, and an evaluation module for elevator maintenance and repair quality; The evaluation standard setting module is used to set an evaluation index set that affects the evaluation result of elevator maintenance and repair quality, and set an elevator maintenance and repair quality evaluation set that includes the evaluation result of elevator maintenance and repair quality; The data collection module is used to collect historical elevator data, extract the features of each evaluation index from the historical elevator data, and construct an evaluation index feature matrix; and divide the evaluation index feature matrix into an evaluation index feature training matrix and an evaluation index feature testing matrix; and set an evaluation index feature training label matrix and an evaluation index feature testing label matrix; collect current elevator data, extract the features of the current elevator data evaluation index, and obtain the current elevator evaluation index feature data; The model training module is used to construct an initial support vector machine model, use the evaluation index feature training matrix and the evaluation index feature training label matrix, and combine the gradient descent method to train the initial support vector machine model to obtain the trained initial support vector machine model; The model testing module is used to test with the evaluation index feature testing matrix and the evaluation index feature testing label matrix. After the testing is completed, the final support vector machine model is obtained; The evaluation module for elevator maintenance and repair quality is used to input the current elevator evaluation index feature data into the final support vector machine model to obtain the evaluation result.

[0025] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0026] The above-disclosed preferred embodiments of the invention are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principle and practical application of the invention, so that those skilled in the art in the relevant technical field can understand and utilize the invention well.

Claims

1. A method for evaluating the quality of elevator maintenance and repair, characterized in that: The following steps are involved: S1. Collect historical elevator operation data and maintenance record data; obtain historical elevator data; Set an evaluation indicator set and an elevator maintenance and repair quality evaluation set; according to the set evaluation indicator set, extract the characteristics of each evaluation indicator in the evaluation indicator set from historical elevator data and construct an evaluation indicator feature matrix; S2. Construct an initial support vector machine model and set relevant parameters; divide the evaluation index feature matrix into an evaluation index feature training matrix and an evaluation index feature test matrix; according to the elevator maintenance and repair quality evaluation set, set a label for each elevator data in the evaluation index feature training matrix and the evaluation index feature test matrix to obtain the evaluation index feature training label set and the evaluation index feature test set; S3, training the initial support vector machine model using a gradient descent method, an evaluation indicator feature training matrix, and an evaluation indicator feature training label set to obtain a trained support vector machine model; S4, inputting the evaluation index feature test matrix into the trained support vector machine model for testing, and obtaining the final support vector machine model after the test is completed; S5. Collect current elevator data, extract characteristic data of current elevator evaluation indicators from the current elevator data, and use the final support vector machine model to obtain the evaluation results of the current elevator maintenance and repair quality.

2. The method for evaluating the quality of elevator maintenance and repair according to claim 1, characterized in that: The S1 comprises the following steps: S11. Collect historical elevator operation data and maintenance record data; obtain historical elevator data; S12. Set the evaluation index set , where a i represents the i-th evaluation index of elevator maintenance and repair quality, and n represents the total number of elevator maintenance and repair quality evaluation indexes in the evaluation index set; S13. Set up the elevator maintenance and repair quality assessment set , b1 means excellent, b2 means good, and b3 means poor; S14. According to the set evaluation index set, the characteristics of each evaluation index in the evaluation index set are extracted from the historical elevator data, and the evaluation index characteristic matrix A is constructed as follows: ； Among them, Ain represents the characteristic data of the nth evaluation indicator of the i-th elevator data in the evaluation indicator feature matrix; m represents that there are m elevator data in the evaluation indicator feature matrix.

3. The method for evaluating the quality of elevator maintenance and repair according to claim 1, characterized in that: The S2 comprises the following steps: S21. Construct an initial support vector machine model, set the penalty parameter to c, the learning rate to k, and the kernel function to the Gaussian kernel function, as follows. The function expression is as follows:

4. Among them, d1 and d2 represent the data sample points of two historical elevator data, and v represents the parameters of the Gaussian kernel function; S22, setting the training data ratio of the initial support vector machine model to e1 and the test data ratio to e2, dividing the evaluation index feature matrix A into the evaluation index feature training matrix B and the evaluation index feature test matrix C according to the training data ratio e1 and the test data ratio e2, as follows, ； ； Among them, Bin represents the characteristic data of the nth evaluation indicator of the i-th elevator data in the evaluation indicator feature training matrix; o represents that the evaluation indicator feature matrix has a total of o elevator data; Cin represents the characteristic data of the nth evaluation indicator of the i-th elevator data in the evaluation indicator feature matrix; g represents that the evaluation indicator feature matrix has a total of g elevator data; S23, according to the elevator maintenance and repair quality assessment set , set a label for each elevator data in the evaluation indicator feature training matrix B and the evaluation indicator feature test matrix C, and construct the evaluation indicator feature training label set and evaluation metric feature test set , where h i represents the label of the i-th elevator data in the evaluation index feature training matrix, j i Represents the label of the i-th elevator data in the evaluation indicator feature training matrix.

5. The method for evaluating the quality of elevator maintenance and repair according to claim 1, characterized in that: The S3 comprises the following steps: S31, bringing the evaluation index feature training matrix and the evaluation index feature training label set into the initial support vector machine model for training, using the gradient descent method in combination with the evaluation index feature training matrix and the evaluation index feature training label set to train the initial support vector machine model, to obtain a trained support vector machine model; Preferably, the S31 comprises the following steps: S311, maximize the interval by minimizing the objective function, and finally achieve the purpose of optimizing the support vector machine model. The formula for minimizing the objective function is as follows: ； Among them, w is the weight vector, u is the bias term, c is the penalty parameter, and y i is the label of the i-th elevator data, x i is the feature vector of the i-th elevator data; o is the total number of elevator data in the evaluation index feature training matrix; The gradient of the objective function with respect to w is as follows, ； in It is an indicator function that returns 1 when the condition is met, otherwise it returns 0; The gradient of the objective function with respect to u is as follows, ； S312, according to the gradient descent algorithm, update w and u by the following formula, as follows, ； S313, set the objective function threshold to α, the maximum number of iterations to l1, and the current number of iterations to l2; repeat S311 and S312, and stop iteration when the objective function value ≤α or l2≥l1 to obtain the trained support vector machine model.

6. The method for evaluating the quality of elevator maintenance and repair according to claim 1, characterized in that: The S4 comprises the following steps: S41, setting the accuracy threshold to p1, inputting the evaluation index feature test set matrix into the trained support vector machine model for testing, obtaining the test result, and comparing the test result with the evaluation index feature test label set to obtain the test accuracy p2; S42, when p2≥p1, using the trained support vector machine model as the final support vector machine model; S43. When p2<p1, continue to optimize the trained support vector machine model to obtain the final support vector machine prediction model.

7. The method for evaluating the quality of elevator maintenance and repair according to claim 5, characterized in that: Continuing to optimize the trained support vector machine model in step 43 to obtain the final support vector machine prediction model comprises the following steps: S431, return to S31 to set the maximum training iteration number q1 of the trained support vector machine model, the current iteration number is q2, and repeat S31 and S41; S432. When q2≥q1 or p2≥p1, stop iteration to obtain the final support vector machine model.

8. The method for evaluating the quality of elevator maintenance and repair according to claim 1, characterized in that: The S5 comprises the following steps: S51, collecting the operation data and maintenance record data of the current elevator to obtain the current elevator data; extracting the characteristic data of each evaluation index in the evaluation index set from the current elevator data; obtaining the characteristic data of the current elevator evaluation index; S52, bringing the current elevator index feature data into the final support vector machine model to obtain the evaluation result of the current elevator maintenance and repair quality.

9. A system for implementing the method for evaluating the quality of elevator maintenance and repair as claimed in any one of claims 1 to 7, characterized in that: Setting evaluation standard module, data collection module, model training module, model testing module, and elevator maintenance and repair quality evaluation module; The evaluation standard setting module is used to set an evaluation index set that affects the elevator maintenance and repair quality evaluation result, and set an elevator maintenance and repair quality evaluation set that includes the elevator maintenance and repair quality evaluation result; The data collection module is used to collect historical elevator data, extract the characteristics of each evaluation index from the historical elevator data, and construct an evaluation index characteristic matrix; And the evaluation index feature matrix is ​​divided into an evaluation index feature training matrix and an evaluation index feature test matrix; And set the evaluation indicator feature training label matrix and the evaluation indicator feature test label matrix; collect the current elevator data, extract the characteristics of the current elevator data evaluation indicators, and obtain the current elevator evaluation indicator feature data; The model training module is used to construct an initial support vector machine model, use the evaluation index feature training matrix and the evaluation index feature training label matrix, and combine the gradient descent method to train the initial support vector machine model to obtain a trained initial support vector machine model; The model testing module is used to test using an evaluation index feature test matrix and an evaluation index feature test label matrix. After the test is completed, the final support vector machine model is obtained; The elevator maintenance and repair quality evaluation module is used to bring the current elevator evaluation index feature data into the final support vector machine model to obtain the evaluation result.

Images