Elevator anomaly detection method and device, computer device and storage medium

Abstract

The application relates to an elevator anomaly detection method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a detection parameter set corresponding to a target elevator in a to-be-detected time period; the detection parameter set comprises a detection parameter value corresponding to a detection parameter; based on a training mean value and a training standard deviation corresponding to the detection parameter, the detection parameter value corresponding to the detection parameter is preprocessed to obtain a target parameter set corresponding to the to-be-detected time period; the training mean value and the training standard deviation are determined based on a plurality of training parameter sets; the training parameter set is used for training an initial anomaly detection model to obtain a target anomaly detection model; and based on the target parameter set corresponding to the to-be-detected time period and the target anomaly detection model, an anomaly detection result of the target elevator is obtained. The method can improve the accuracy of elevator anomaly detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automation, and in particular to an elevator anomaly detection method and device, computer equipment and a storage medium. BACKGROUND

[0002] With the development of automation technology, elevators are widely used in various scenarios. In order to ensure stable operation of the elevator, it is necessary to periodically detect the elevator for anomalies, and to discover and repair faults of the elevator in a timely manner.

[0003] In the prior art, maintenance personnel periodically detect the elevator for anomalies, and the anomaly detection result depends on the experience and skills of the maintenance personnel, resulting in low accuracy of the anomaly detection result. SUMMARY

[0004] Therefore, it is necessary to provide an elevator anomaly detection method and device, computer equipment, computer readable storage medium and computer program product capable of improving the accuracy of elevator anomaly detection.

[0005] In a first aspect, the present application provides an elevator anomaly detection method. The method comprises:

[0006] obtaining a set of detection parameters corresponding to a target elevator in a to-be-detected time period; the set of detection parameters includes a detection parameter value corresponding to a detection parameter;

[0007] based on the training mean and the training standard deviation corresponding to the detection parameter, pre-processing the detection parameter value corresponding to the detection parameter to obtain a target parameter set corresponding to the to-be-detected time period; the training mean and the training standard deviation are determined based on a plurality of training parameter sets, the training parameter set is used to train an initial anomaly detection model to obtain a target anomaly detection model;

[0008] based on the target parameter set corresponding to the to-be-detected time period and the target anomaly detection model, obtaining an anomaly detection result of the target elevator.

[0009] In one embodiment, the anomaly detection result of the target elevator is obtained based on the target parameter set corresponding to the to-be-detected time period and the target anomaly detection model, comprising:

[0010] based on the order of the plurality of to-be-detected time periods, the plurality of target parameter sets are combined into an initial matrix;

[0011] for each element value in the initial matrix, the element value is converted into a corresponding gray value to obtain a gray matrix;

[0012] based on the gray matrix, a detection feature image is generated;

[0013] inputting the detection feature image into the target anomaly detection model to obtain an anomaly detection result of the target elevator.

[0014] In one embodiment, the training of the initial anomaly detection model to obtain the target anomaly detection model comprises:

[0015] obtaining a plurality of training parameter sets corresponding to a plurality of training time periods; the training parameter set comprises a training parameter value corresponding to a training parameter;

[0016] For each training parameter, the mean and standard deviation of the training parameter value corresponding to the training parameter in the plurality of training parameter sets are calculated to obtain the training mean and training standard deviation corresponding to the training parameter;

[0017] Based on the training mean and training standard deviation corresponding to the training parameter, the training parameter set corresponding to the training time period is preprocessed to obtain a processed parameter set corresponding to the training time period;

[0018] Based on the processed parameter sets corresponding to a continuous preset number of training time periods, a training feature image is generated;

[0019] The initial anomaly detection model is trained based on a plurality of training feature images to obtain a target anomaly detection model.

[0020] In one embodiment, the obtaining of the detection parameter set corresponding to the to-be-detected time period of the target elevator comprises:

[0021] Obtaining the sampling voltage value and the sampling current value corresponding to each sampling time point of the hoisting machine corresponding to the target elevator in the to-be-detected time period;

[0022] For each sampling voltage value, based on the voltage zero point offset and the voltage scale factor of the hoisting machine, the actual voltage value corresponding to the sampling voltage value is determined;

[0023] For each sampling current value, based on the current zero point offset and the current scale factor of the hoisting machine, the actual current value corresponding to the sampling current value is determined;

[0024] Based on the sampling voltage value, the actual voltage value and the actual current value corresponding to each sampling time point, the detection parameter set corresponding to the to-be-detected time period of the target elevator is determined.

[0025] In one embodiment, the determination of the detection parameter set corresponding to the to-be-detected time period of the target elevator based on the sampling voltage value, the actual voltage value and the actual current value corresponding to each sampling time point comprises:

[0026] determine a detection angular velocity value corresponding to the to-be-detected time period based on the sampling voltage values corresponding to the plurality of sampling time points;

[0027] determine a detection voltage value corresponding to the to-be-detected time period based on the actual voltage values corresponding to the plurality of sampling time points;

[0028] determine a detection current value corresponding to the to-be-detected time period based on the actual current values corresponding to the plurality of sampling time points;

[0029] determine a detection power value corresponding to the to-be-detected time period based on the actual voltage values and the actual current values corresponding to the plurality of sampling time points;

[0030] obtain a detection parameter set corresponding to the to-be-detected time period of the target elevator based on the detection angular velocity value, the detection voltage value, the detection current value, and the detection power value.

[0031] In an embodiment, the determination of the detection angular velocity value corresponding to the to-be-detected time period based on the sampling voltage values corresponding to the plurality of sampling time points comprises:

[0032] for each phase sampling voltage, determine a number of zero-crossing points in the to-be-detected time period based on the directions of the sampling voltage values corresponding to any two adjacent sampling time points;

[0033] determine a phase voltage frequency based on the length of the to-be-detected time period and the number of zero-crossing points;

[0034] average the plurality of phase voltage frequencies to obtain a target voltage frequency;

[0035] determine the detection angular velocity value corresponding to the to-be-detected time period based on the target voltage frequency and the number of pole pairs of the traction machine.

[0036] In a second aspect, the present application further provides an elevator anomaly detection device. The device comprises:

[0037] an acquisition module configured to acquire a detection parameter set corresponding to a to-be-detected time period of a target elevator; the detection parameter set comprises detection parameter values corresponding to detection parameters;

[0038] a preprocessing module configured to preprocess the detection parameter values corresponding to the detection parameters based on a training mean value and a training standard deviation corresponding to the detection parameters, to obtain a target parameter set corresponding to the to-be-detected time period; the training mean value and the training standard deviation are determined based on a plurality of training parameter sets, and the training parameter sets are used to train an initial anomaly detection model to obtain a target anomaly detection model;

[0039] The detection module is configured to obtain an abnormality detection result of the target elevator based on the target parameter set corresponding to the to-be-detected time period and the target abnormality detection model.

[0040] In a third aspect, the present application also provides a computer device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method in any one of the first aspect when executing the computer program.

[0041] In a fourth aspect, the present application also provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the method in any one of the first aspect when executed by a processor.

[0042] In a fifth aspect, the present application also provides a computer program product, comprising a computer program, and the computer program implements the steps of the method in any one of the first aspect when executed by a processor.

[0043] The elevator abnormality detection method, device, computer device, storage medium and computer program product described above obtain a detection parameter set corresponding to a to-be-detected time period of a target elevator, pre-process a detection parameter value corresponding to a detection parameter based on a training mean value and a training standard deviation corresponding to the detection parameter, and obtain a target parameter set corresponding to the to-be-detected time period. Since the training mean value and the training standard deviation are determined based on a plurality of training parameter sets, and the training parameter sets are used to train an initial abnormality detection model to obtain a target abnormality detection model, it can be understood that the target parameter set obtained by pre-processing the detection parameter set using the training mean value and the training standard deviation corresponding to the training parameter calculated based on the training parameter set is more suitable for the target abnormality detection model trained based on the training parameter set. Based on the target parameter set corresponding to the to-be-detected time period and the target abnormality detection model, an abnormality detection result of the target elevator is obtained, thereby improving the accuracy of the abnormality detection result. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 An application environment diagram of the elevator abnormality detection method in an embodiment;

[0045] Figure 2 A flowchart of the elevator abnormality detection method in an embodiment;

[0046] Figure 3 A flowchart of the step of determining an abnormality detection result in an embodiment;

[0047] Figure 4 A schematic diagram of a detection feature image in an embodiment;

[0048] Figure 5Flowchart for determining steps of the target anomaly detection model in one embodiment;

[0049] Figure 6 Flowchart for determining steps of the detection parameter set in one embodiment;

[0050] Figure 7 Flowchart for determining steps of the detection parameter set in another embodiment;

[0051] Figure 8 Flowchart for determining steps of the angular velocity value in one embodiment;

[0052] Figure 9 Flowchart for elevator anomaly detection in one embodiment;

[0053] Figure 10 Structural block diagram of the elevator anomaly detection device in one embodiment;

[0054] Figure 11 Internal structure diagram of the computer device in one embodiment. DETAILED DESCRIPTION

[0055] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not used to limit the present application.

[0056] The elevator anomaly detection method provided by the embodiments of the present application can be applied to, for example, Figure 1The application environment shown. Among them, the traction machine 102 is the core component of the elevator system, mainly used to drive the elevator car and the counterweight to run up and down, realize the rise and fall of the elevator; the data collector 104 is used to collect the voltage value and current value on the traction machine frequency converter, the data collector can be a sensor, the sampling frequency of the data collector can be set according to the actual demand, for example, the sampling frequency of the data collector is set to 2 kilohertz or more than 2 kilohertz; the computer equipment 106 is used to process the voltage value and current value collected by the data collector 104 to determine the abnormal detection result of the elevator abnormal detection. The data collector 104 and the computer equipment 106 can be located in the electrical control room of the elevator, and the data collector 104 can include a voltage sensor and a current sensor. The computer equipment 106 can be, but is not limited to, various industrial computers, personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The computer equipment 106 can be used alone to execute the elevator abnormal detection method provided in the present application, and the computer equipment 106 and the server can also be used cooperatively to execute the elevator abnormal detection method provided in the present application, and the server can be implemented by an independent server or a server cluster composed of multiple servers.

[0057] In one embodiment, as shown in Figure 2 An elevator abnormal detection method is provided, and the present embodiment takes the method applied to a computer device as an example for illustration, including steps 202 to 206.

[0058] Step 202, obtaining a set of detection parameters corresponding to a target elevator in a to-be-detected time period; the set of detection parameters includes a detection parameter value corresponding to a detection parameter.

[0059] The target elevator refers to an elevator for which an abnormality is detected. The to-be-detected time period refers to a time period during which the target elevator is detected for an abnormality. The detection parameter set refers to a set of detection parameter values, and the detection parameter set includes detection parameter values corresponding to detection parameters. The detection parameter refers to a parameter representing an operating condition of the target elevator, and the detection parameter can be at least one of a detection voltage, a detection current, a detection power, and a detection angular velocity. For example, the detection parameter includes a detection current and a detection power, or the detection parameter includes a detection voltage, a detection current, and a detection power, or the detection parameter includes a detection current, a detection power, and a detection angular velocity, or the detection parameter includes a detection voltage, a detection current, a detection power, and a detection angular velocity. The detection parameter value refers to a parameter value representing an operating condition of the target elevator, and the detection parameter value corresponds to the detection parameter. One detection parameter corresponds to at least one detection parameter value. For example, if a traction machine uses a three-phase power supply for power supply, the detection voltage corresponds to three detection voltage values, i.e., a detection voltage value of phase A, a detection voltage value of phase B, and a detection voltage value of phase C. The detection current corresponds to three detection current values, i.e., a detection current value of phase A, a detection current value of phase B, and a detection current value of phase C. The detection power corresponds to three detection power values, i.e., a detection power value of phase A, a detection power value of phase B, and a detection power value of phase C. Alternatively, the detection angular velocity corresponds to one detection angular velocity value.

[0060] For example, the computer device obtains detection parameter values corresponding to each detection parameter of the target elevator in the to-be-detected time period, and forms a detection parameter set from the detection parameter values corresponding to the plurality of detection parameters.

[0061] In step 204, the detection parameter values corresponding to the detection parameters are preprocessed based on the training mean value and the training standard deviation corresponding to the detection parameters, to obtain a target parameter set corresponding to the to-be-detected time period. The training mean value and the training standard deviation are determined based on a plurality of training parameter sets. The training parameter set is used to train an initial abnormality detection model to obtain a target abnormality detection model.

[0062] The training mean refers to a mean value calculated based on the detection parameter values corresponding to the detection parameters in the plurality of training parameter sets, and the training mean corresponds to each detection parameter. The training standard deviation refers to a standard deviation calculated based on the detection parameter values corresponding to the detection parameters in the plurality of training parameter sets, and the training standard deviation corresponds to each detection parameter. The detection parameter corresponds to a set of training means and training standard deviations. The preprocessing refers to a standardization process of the detection parameter values. The target parameter set refers to a set obtained by preprocessing each detection parameter value in the detection parameter set. The training parameter set refers to a detection parameter set used to train the initial anomaly detection model. The initial anomaly detection model refers to an anomaly detection model that has not been trained. The target anomaly detection model refers to a trained anomaly detection model. The target anomaly detection model can be a convolutional neural network (CNN). For example, the target anomaly detection model is a ResNet (Residual Network) in the convolutional neural network, such as ResNet 50. ResNet 50 uses a Bottle neck Block compared to ResNet 18, which reduces the number of channels through a 1x1 convolutional layer, reduces the amount of calculation and the amount of parameters, and then performs convolution operation through a 3x3 convolutional layer, so that ResNet 50 reduces the calculation cost while ensuring the network depth, improves the operation efficiency, and because of the increase in the depth of the network, ResNet 50 can learn more texture details of the feature image, better distinguish normal feature images and abnormal feature images, and improve the accuracy of anomaly detection.

[0063] For example, the computer device obtains the training mean and the training standard deviation corresponding to each detection parameter, performs standardization processing on each detection parameter value corresponding to the detection parameter based on the training mean and the training standard deviation corresponding to the detection parameter, obtains a target parameter value corresponding to each detection parameter value, and obtains a target parameter set based on the target parameter value corresponding to each detection parameter.

[0064] In one embodiment, step 204 further includes: obtaining a plurality of training parameter sets corresponding to a plurality of training time periods; the training parameter set includes a training parameter value corresponding to the detection parameter; for each detection parameter, calculating the mean and the standard deviation of the training parameter values corresponding to the detection parameter in the plurality of training parameter sets to obtain the training mean and the training standard deviation corresponding to the detection parameter.

[0065] In an embodiment, before step 204, the method further comprises: obtaining a plurality of training parameter sets corresponding to a plurality of training time periods; each training parameter set comprises a training parameter value corresponding to a training parameter; for each training parameter, calculating a mean value and a standard deviation of the training parameter values corresponding to the training parameter in the plurality of training parameter sets to obtain a training mean value and a training standard deviation corresponding to the training parameter; and preprocessing the training parameter set corresponding to the training time period based on the training mean value and the training standard deviation corresponding to the training parameter to obtain a processed parameter set corresponding to the training time period; and generating a training feature image based on the processed parameter sets corresponding to a preset number of continuous training time periods; and training the initial anomaly detection model based on the plurality of training feature images to obtain the target anomaly detection model.

[0066] In an embodiment, before step 204, the method further comprises: based on the plurality of detection parameter sets corresponding to a plurality of to-be-detected time periods, grouping the plurality of detection parameter sets into a detection matrix based on the sequence of the plurality of to-be-detected time periods; and step 204 comprises: preprocessing the detection parameter value corresponding to the detection parameter in the initial matrix based on the training mean value and the training standard deviation corresponding to the detection parameter to obtain an initial matrix; converting each element value in the initial matrix into a corresponding gray value to obtain a gray matrix; and generating a detection feature image based on the gray matrix.

[0067] Step 206: obtaining an anomaly detection result of the target elevator based on the target parameter set corresponding to the to-be-detected time period and the target anomaly detection model.

[0068] The anomaly detection result refers to a result of anomaly detection of the target elevator, and the anomaly detection result comprises at least one of a detection result and an anomaly probability, for example, the anomaly detection result can be one of normal and failure, or the anomaly detection result can be an anomaly probability.

[0069] For example, the computer device generates a detection feature image based on the plurality of target parameter sets corresponding to the plurality of to-be-detected time periods, inputs the detection feature image into the target anomaly detection model, and obtains the anomaly detection result of the target elevator.

[0070] In an embodiment, the plurality of target parameter sets are grouped into an initial matrix based on the sequence of the plurality of to-be-detected time periods; each element value in the initial matrix is converted into a corresponding gray value to obtain a gray matrix; and the gray matrix is input into the target anomaly detection model to obtain the anomaly detection result of the target elevator.

[0071] In an embodiment, after step 206, the method further comprises: in the case that the anomaly detection result is failure, generating failure prompt information corresponding to the target elevator. The failure prompt information can be a prompt sound or a prompt message.

[0072] In this embodiment, the target parameters set corresponding to the to-be-detected time period of the target elevator is obtained, the detection parameter values corresponding to the detection parameters are preprocessed based on the training mean and the training standard deviation corresponding to the detection parameters, and the target parameter set corresponding to the to-be-detected time period is obtained. Since the training mean and the training standard deviation are determined based on the plurality of training parameter sets, and the training parameter set is used to train the initial abnormality detection model to obtain the target abnormality detection model, it can be understood that the target parameter set obtained by preprocessing the detection parameter set using the training mean and the training standard deviation corresponding to the training parameter set calculated from the training parameter set is more suitable for the target abnormality detection model trained using the training parameter set. Based on the target parameter set corresponding to the to-be-detected time period and the target abnormality detection model, the abnormality detection result of the target elevator is obtained, thereby improving the accuracy of the abnormality detection result.

[0073] In one embodiment, as shown in Figure 3 Based on the target parameter set corresponding to the to-be-detected time period and the target abnormality detection model, the abnormality detection result of the target elevator is obtained, including:

[0074] Step 302, based on the sequence of the plurality of to-be-detected time periods, the plurality of target parameter sets are combined into an initial matrix.

[0075] The initial matrix refers to a matrix composed of the target parameter sets corresponding to the plurality of to-be-detected time periods in the order of the plurality of to-be-detected time periods. For example, there are 20 target parameter sets corresponding to to-be-detected time periods, each target parameter set includes 10 target parameter values, which are the target voltage value of phase A, the target voltage value of phase B, the target voltage value of phase C, the target current value of phase A, the target current value of phase B, the target current value of phase C, the target power value of phase A, the target power value of phase B, the target power value of phase C, and the target angular velocity value. Then a 20x10 initial matrix is formed, and the 10 target parameter values of each row are a target parameter set corresponding to a to-be-detected time period.

[0076] Exemplarily, the computer device combines the target parameter sets corresponding to the preset number of to-be-detected time periods into an initial matrix in the order of the preset number of to-be-detected time periods.

[0077] Step 304, for each element value in the initial matrix, the element value is converted into a corresponding gray value to obtain a gray matrix.

[0078] The gray value refers to a numerical value representing the lightness and darkness. The value range of the gray value can be 0 to 255. The gray matrix refers to a matrix composed of gray values, and the size of the gray matrix is the same as that of the initial matrix.

[0079] Exemplarily, for each element value in the initial matrix, the computer device converts the element value into a corresponding gray value based on a preset mapping relationship, to obtain a gray matrix corresponding to the initial matrix.

[0080] In step 306, a detection feature image is generated based on the gray matrix.

[0081] The detection feature image refers to a feature gray image generated according to the gray matrix. It can be understood that each element in the gray matrix represents the gray value of a pixel point in the detection feature image. For example, as shown in Figure 4 The left image is a detection feature image with a normal abnormality detection result, and the right image is a detection feature image with an abnormal abnormality detection result.

[0082] Exemplarily, the computer device generates a detection feature image corresponding to the gray matrix.

[0083] In step 308, the detection feature image is input into a target abnormality detection model to obtain an abnormality detection result of the target elevator.

[0084] Exemplarily, the computer device inputs the detection feature image into the target abnormality detection model, and the target abnormality detection model outputs an abnormality detection result. The computer device obtains the abnormality detection result of the target elevator.

[0085] In this embodiment, the gray matrix is used to generate a detection feature image, that is, the correlation between the gray values in the gray matrix is converted into the adjacent relationship on the Y axis, the continuous relationship in time is converted into the adjacent relationship on the X axis, and the detection feature image is input into the target abnormality detection model. When the convolution kernel slides in the Y axis direction, it will analyze the feature performance of different gray values in the same time window. When the convolution kernel slides in the X axis direction, it will analyze the change of the same gray value in the adjacent time window. Through convolution processing, the target abnormality detection model can analyze the corresponding relationship between the gray values of each physical quantity in the same time period and the change trend of the gray values in different time periods, thereby improving the accuracy of the abnormality detection result.

[0086] In one embodiment, as shown in Figure 5 The initial abnormality detection model is trained to obtain a target abnormality detection model, including:

[0087] In step 502, a training parameter set corresponding to a plurality of training time periods is obtained. The training parameter set includes a training parameter value corresponding to a detection parameter.

[0088] The training parameter set refers to a set composed of training parameter values, and the training parameter set includes training parameter values corresponding to the training time period of the training parameter.

[0089] The computer device obtains a plurality of training parameter sets corresponding to a plurality of training time periods.

[0090] The computer device calculates the mean and standard deviation of the training parameter values corresponding to the detection parameter in the plurality of training parameter sets for each detection parameter, to obtain the training mean and training standard deviation corresponding to the detection parameter.

[0091] The mean refers to the average value of the data set, and the standard deviation refers to a value representing the degree of dispersion between each value in the data set and the mean.

[0092] The computer device obtains the training parameter values corresponding to the detection parameter from the plurality of training parameter sets for each detection parameter, and calculates the mean and standard deviation of the obtained plurality of training parameter values, to obtain the training mean and training standard deviation corresponding to the detection parameter.

[0093] The computer device preprocesses the training parameter set corresponding to the training time period based on the training mean and training standard deviation corresponding to the detection parameter, to obtain a processing parameter set corresponding to the training time period.

[0094] The processing parameter set refers to a set composed of processing parameter values. The processing parameter value refers to a value obtained by preprocessing the training parameter value.

[0095] The computer device normalizes each training parameter value in the training parameter set based on the training mean and training standard deviation of the detection parameter corresponding to the training parameter value, to obtain a processing parameter value corresponding to the training parameter value, and obtains the processing parameter set corresponding to the training time period based on the processing parameter value corresponding to each training parameter value in the training parameter set.

[0096] The computer device generates a training feature image based on the processing parameter sets corresponding to a continuous preset number of training time periods.

[0097] The preset number refers to a number set in advance, which can be set according to actual needs and is not limited herein, for example, the preset number is 20 or 30. The training feature image refers to a feature grayscale image generated based on the processing parameter sets corresponding to a continuous preset number of training time periods. The size of the training feature image is the same as that of the detection feature image.

[0098] Exemplarily, the computer device generates a training matrix by arranging the target parameter sets corresponding to the preset number of training time periods in the order of the succession of the preset number of training time periods, converts each element value in the training matrix into a corresponding gray value based on a preset mapping relationship, to obtain a sample matrix corresponding to the training matrix, and generates a training feature image corresponding to the sample matrix.

[0099] At step 510, the initial anomaly detection model is trained based on the plurality of training feature images to obtain a target anomaly detection model.

[0100] Exemplarily, the computer device trains the initial anomaly detection model based on the plurality of training feature images and anomaly detection labels corresponding to the training feature images to obtain the target anomaly detection model. The anomaly detection label refers to an identifier representing an anomaly detection result corresponding to the training feature image.

[0101] In this embodiment, the training parameter set corresponding to the training time period is preprocessed by the training mean and the training standard deviation corresponding to the detection parameter to obtain a processed parameter set corresponding to the training time period. The preprocessing eliminates the influence caused by the different dimensions between different detection parameters. The training feature image is generated based on the processed parameter sets corresponding to the preset number of continuous training time periods. The initial anomaly detection model is trained based on the plurality of training feature images to obtain the target anomaly detection model. This not only improves the performance and stability of the target anomaly detection model, but also improves the accuracy of the target anomaly detection model by training the initial anomaly detection model using the plurality of training feature images.

[0102] In one embodiment, as Figure 6 The method comprises the following steps.

[0103] At step 602, the sample voltage value and the sample current value corresponding to each sampling time point of the target elevator corresponding traction machine in the to-be-detected time period are obtained.

[0104] The sampling voltage value refers to the voltage value of the traction machine corresponding to the target elevator at the sampling time point, which can be understood as AD (Analog to Digital) conversion of the analog voltage signal provided for the traction machine corresponding to the target elevator, that is, the sampling voltage value corresponding to the plurality of sampling time points can be obtained. The sampling voltage value is not a real voltage value, and the sampling voltage value represents the voltage amplitude at the sampling time point. The sampling current value refers to the current value of the traction machine corresponding to the target elevator at the sampling time point, which can be understood as AD conversion of the analog current signal provided for the traction machine corresponding to the target elevator, that is, the sampling current value corresponding to the plurality of sampling time points can be obtained. The sampling current value is not a real current value, and the sampling current value represents the current amplitude at the sampling time point.

[0105] Exemplarily, the computer device obtains the analog voltage signal and the analog current signal of the traction machine corresponding to the target elevator in the to-be-detected time period through the data collector, samples the analog voltage signal based on the preset frequency to obtain the sampling voltage value corresponding to each sampling time point, and samples the analog current signal based on the preset frequency to obtain the sampling current value corresponding to each sampling time point.

[0106] In one embodiment, the traction machine corresponding to the target elevator uses a three-phase power supply for power supply. The computer device obtains the analog voltage signal corresponding to phase A, the analog voltage signal corresponding to phase B, the analog voltage signal corresponding to phase C, the analog current signal corresponding to phase A, the analog current signal corresponding to phase B, and the analog current signal corresponding to phase C of the above-mentioned traction machine in the to-be-detected time period through the data collector. The computer device samples the analog voltage signal corresponding to phase A based on the preset frequency to obtain the sampling voltage value corresponding to phase A at each sampling time point, samples the analog voltage signal corresponding to phase B based on the preset frequency to obtain the sampling voltage value corresponding to phase B at each sampling time point, samples the analog voltage signal corresponding to phase C based on the preset frequency to obtain the sampling voltage value corresponding to phase C at each sampling time point, samples the analog current signal corresponding to phase A based on the preset frequency to obtain the sampling current value corresponding to phase A at each sampling time point, samples the analog current signal corresponding to phase B based on the preset frequency to obtain the sampling current value corresponding to phase B at each sampling time point, and samples the analog current signal corresponding to phase C based on the preset frequency to obtain the sampling current value corresponding to phase C at each sampling time point.

[0107] In step 604, for each sampling voltage value, the actual voltage value corresponding to the sampling voltage value is determined based on the voltage zero-point offset and the voltage proportion factor of the traction machine.

[0108] The voltage zero-point offset refers to a reference offset for correcting a hardware or noise in a voltage measurement. The voltage scale factor refers to a proportional relationship between a sampling voltage value and an actual voltage value.

[0109] Exemplarily, for each sampling voltage value, the computer multiplies a difference between the sampling voltage value and a voltage zero-point offset corresponding to the sampling voltage value by a voltage scale factor to obtain an actual voltage value corresponding to the sampling voltage value.

[0110] In an embodiment, the target elevator corresponds to a hoisting machine powered by a three-phase power supply, and the actual voltage value of the A phase , the actual voltage value of the B phase , and the actual voltage value of the C phase are calculated according to the following formulas:

[0111] Formula (1)

[0112] where t is a sampling time point; is a sampling voltage value of the A phase at the sampling time point; is a voltage zero-point offset corresponding to the A phase; is a voltage scale factor corresponding to the A phase;

[0113] is a sampling voltage value of the B phase at the sampling time point; is a voltage zero-point offset corresponding to the B phase; is a voltage scale factor corresponding to the B phase; is a sampling voltage value of the C phase at the sampling time point; is a voltage zero-point offset corresponding to the C phase; is a voltage scale factor corresponding to the C phase.

[0114] Step 606, for each sampling current value, based on a current zero-point offset and a current scale factor of the hoisting machine, determine an actual current value corresponding to the sampling current value.

[0115] The current zero-point offset refers to a reference offset for correcting a hardware or noise in a current measurement. The current scale factor refers to a proportional relationship between a sampling current value and an actual current value.

[0116] Exemplarily, for each sampling current value, the computer device multiplies a difference between the sampling current value and a current zero-point offset corresponding to the sampling current value by a current scale factor to obtain an actual current value corresponding to the sampling current value.

[0117] In an embodiment, the target elevator corresponds to a hoisting machine powered by a three-phase power supply, and the actual current value of the A phase the actual current value corresponding to phase B the actual current value corresponding to phase C The calculation formula is as follows:

[0118] Formula (2)

[0119] Where t is a sampling time point; is the sampling current value of phase A corresponding to the sampling time point; is the current zero point offset corresponding to phase A; is the current proportion factor corresponding to phase A; is the sampling current value of phase B corresponding to the sampling time point; is the current zero point offset corresponding to phase B;

[0120] is the current proportion factor corresponding to phase B; is the sampling current value of phase C corresponding to the sampling time point; is the current zero point offset corresponding to phase C; is the current proportion factor corresponding to phase C.

[0121] Step 608, based on the sampling voltage value, the actual voltage value and the actual current value corresponding to each sampling time point, determine the detection parameter set corresponding to the to-be-detected time period of the target elevator.

[0122] Exemplarily, the computer device determines the detection angular velocity value corresponding to the to-be-detected time period based on the sampling voltage value corresponding to the plurality of sampling time points, determines the detection voltage value, the detection current value and the detection power value corresponding to the to-be-detected time period based on the actual voltage value and the actual current value corresponding to the plurality of sampling time points, and obtains the detection parameter set corresponding to the to-be-detected time period of the target elevator based on the detection angular velocity value, the detection voltage value, the detection current value and the detection power value corresponding to the to-be-detected time period.

[0123] In this embodiment, for each sampling voltage value, the actual voltage value corresponding to the sampling voltage value is determined based on the voltage zero point offset and the voltage proportion factor of the traction machine, for each sampling current value, the actual current value corresponding to the sampling current value is determined based on the current zero point offset and the current proportion factor of the traction machine, and the detection parameter set corresponding to the to-be-detected time period of the target elevator is determined based on the sampling voltage value, the actual voltage value and the actual current value corresponding to each sampling time point, which provides accurate basic data for subsequent determination of the abnormal detection result of the target elevator.

[0124] In one embodiment, as Figure 7The detection parameter set corresponding to the to-be-detected time period of the target elevator is determined based on the sampling voltage value, the actual voltage value, and the actual current value corresponding to each sampling time point.

[0125] At step 702, the detection angular velocity value corresponding to the to-be-detected time period is determined based on the sampling voltage values corresponding to the plurality of sampling time points.

[0126] The detection angular velocity value refers to a value representing the angular velocity of the traction machine in the to-be-detected time period.

[0127] For example, the computer device determines the number of zero-crossing points in the to-be-detected time period based on the sampling voltage values corresponding to the plurality of sampling time points using the zero-crossing point method, and determines the detection angular velocity value corresponding to the to-be-detected time period based on the number of zero-crossing points.

[0128] At step 704, the detection voltage value corresponding to the to-be-detected time period is determined based on the actual voltage values corresponding to the plurality of sampling time points.

[0129] For example, the computer device calculates the mean value of the actual voltage values corresponding to the plurality of sampling time points to obtain the detection voltage value corresponding to the to-be-detected time period.

[0130] In one embodiment, the traction machine corresponding to the target elevator is powered by a three-phase power supply, the actual voltage value of the sampling point corresponding to phase A is the actual voltage value of the sampling point corresponding to phase B is and the actual voltage value of the sampling point corresponding to phase C is The calculation formula of the detection voltage value is as follows:

[0131] Formula (3)

[0132] Formula (4)

[0133] Formula (5)

[0134] wherein, is the detection voltage value of phase A in the to-be-detected time period;

[0135] is the detection voltage value of phase B in the to-be-detected time period; is the detection voltage value of phase C in the to-be-detected time period; t is the sampling time point; and n is the number of sampling time points in the to-be-detected time period.

[0136] At step 706, the detection current value corresponding to the to-be-detected time period is determined based on the actual current values corresponding to the plurality of sampling time points.

[0137] Exemplarily, the computer device calculates a mean value of the actual current values corresponding to the plurality of sampling time points to obtain the detection current value corresponding to the to-be-detected time period.

[0138] In an embodiment, the hoisting machine corresponding to the target elevator is powered by a three-phase power supply, and the actual current value corresponding to the A phase , the actual current value corresponding to the B phase , and the actual current value corresponding to the C phase , the calculation formula of the detection current value is as follows:

[0139] Formula (6)

[0140] Formula (7)

[0141] Formula (8)

[0142] wherein, is the detection current value corresponding to the A phase in the to-be-detected time period; is the detection current value corresponding to the B phase in the to-be-detected time period; is the detection current value corresponding to the C phase in the to-be-detected time period; t is a sampling time point; and n is the number of sampling time points in the to-be-detected time period.

[0143] In step 708, based on the actual voltage values and the actual current values corresponding to the plurality of sampling time points, a detection power value corresponding to the to-be-detected time period is determined.

[0144] Exemplarily, for each sampling time point, the computer device multiplies the actual voltage value corresponding to the sampling time point by the actual current value to obtain an actual power value corresponding to the sampling time point, calculates a mean value of the actual power values corresponding to the plurality of sampling time points to obtain the detection power value corresponding to the to-be-detected time period.

[0145] In an embodiment, the hoisting machine corresponding to the target elevator is powered by a three-phase power supply, and the calculation formula of the detection power value corresponding to the to-be-detected time period is as follows:

[0146] Formula (9)

[0147] Formula (10)

[0148] Formula (11)

[0149] wherein, is the to-be-detected time period; is the detection power value corresponding to the A phase in the to-be-detected time period; the detection power value of the B phase corresponding to the to-be-detected time period; the detection power value of the C phase corresponding to the to-be-detected time period; t is a sampling time point; and n is the number of sampling time points in the to-be-detected time period.

[0150] At step 710, based on the detection angular velocity value, the detection voltage value, the detection current value, and the detection power value, a detection parameter set of the target elevator corresponding to the to-be-detected time period is obtained.

[0151] For example, the computer device assembles the detection angular velocity value, the detection voltage value, the detection current value, and the detection power value corresponding to the to-be-detected time period into the detection parameter set of the target elevator corresponding to the to-be-detected time period.

[0152] In one embodiment, the hoisting machine corresponding to the target elevator is powered by a three-phase power supply. The computer device assembles the detection angular velocity value corresponding to the to-be-detected time period, the detection voltage value of the A phase corresponding to the to-be-detected time period, the detection voltage value of the B phase corresponding to the to-be-detected time period, the detection voltage value of the C phase corresponding to the to-be-detected time period, the detection current value of the A phase corresponding to the to-be-detected time period, the detection current value of the B phase corresponding to the to-be-detected time period, the detection current value of the C phase corresponding to the to-be-detected time period, the detection power value of the A phase corresponding to the to-be-detected time period, the detection power value of the B phase corresponding to the to-be-detected time period, and the detection power value of the C phase corresponding to the to-be-detected time period into the detection parameter set of the target elevator corresponding to the to-be-detected time period.

[0153] In this embodiment, the detection parameter set of the target elevator corresponding to the to-be-detected time period is determined by the sampling voltage value, the actual voltage value, and the actual current value of each sampling time point, thereby providing accurate basic data for subsequent determination of the abnormal detection result of the target elevator.

[0154] In one embodiment, as Figure 8 indicated above, the detection angular velocity value corresponding to the to-be-detected time period is determined based on the sampling voltage value corresponding to the plurality of sampling time points, including:

[0155] At step 802, for each phase sampling voltage, the number of zero-crossing points in the to-be-detected time period is determined based on the direction of the sampling voltage values corresponding to any two adjacent sampling time points.

[0156] The direction of the sampling voltage value refers to the polarity of the sampling voltage value, which can be represented by "+" and "-". The number of zero-crossing points refers to the total number of zero-crossing points of the sampling voltage value in the to-be-detected time period. It can be understood that if the directions of the sampling voltage values corresponding to two adjacent sampling times are opposite, it is a zero-crossing point, and the total number of zero-crossing points in the to-be-detected time period is the number of zero-crossing points.

[0157] Exemplarily, the computer device determines, for each phase, a number of zero-crossing points in the to-be-detected time period based on a direction of the sampled voltage values corresponding to any two adjacent sampling time points.

[0158] At step 804, the phase voltage frequency is determined based on the length of the to-be-detected time period and the number of zero-crossing points.

[0159] The length refers to the time length of the to-be-detected time period, for example, the length is 0.1 seconds. The phase voltage frequency refers to the voltage frequency of one phase, for example, the phase voltage frequency of phase A, the phase voltage frequency of phase B, and the phase voltage frequency of phase C.

[0160] Exemplarily, the computer device divides, for each phase, the number of zero-crossing points of the phase by twice the length to obtain the phase voltage frequency of the phase.

[0161] In one embodiment, the calculation formula of the phase voltage frequency is as follows:

[0162] Formula (12)

[0163] P is a phase identifier, and P can be A, B, or C; is the phase voltage frequency of phase P; N is the number of zero-crossing points; T S is the length of the to-be-detected time period.

[0164] At step 806, the target voltage frequency is obtained by averaging the plurality of phase voltage frequencies.

[0165] Exemplarily, the computer device averages the plurality of phase voltage frequencies to obtain the target voltage frequency.

[0166] In one embodiment, the target elevator corresponds to a traction machine that is powered by a three-phase power supply, and the calculation formula of the target voltage frequency is as follows:

[0167] Formula (13)

[0168] wherein, is the phase voltage frequency of phase A; is the phase voltage frequency of phase B;

[0169] is the phase voltage frequency of phase C.

[0170] At step 808, the detection angular velocity value corresponding to the to-be-detected time period is determined based on the target voltage frequency and the number of pole pairs of the traction machine.

[0171] The number of pole pairs refers to the number of magnetic pole pairs inside the motor of the traction machine.

[0172] Exemplarily, the computer device determines the detection angular velocity value corresponding to the to-be-detected time period based on a ratio between the target voltage frequency and the pole pair number of the traction machine.

[0173] In one embodiment, the detection angular velocity value corresponding to the to-be-detected time period is determined based on a ratio between the target voltage frequency and the pole pair number of the traction machine. The calculation formula is as follows:

[0174] Formula (14)

[0175] wherein, is the target voltage frequency; and P is the pole pair number of the traction machine.

[0176] In this embodiment, the detection angular velocity value corresponding to the to-be-detected time period is determined based on the sampling voltage values corresponding to the plurality of sampling time points, which provides accurate basic data for subsequent determination of the detection parameter set corresponding to the to-be-detected time period of the target elevator.

[0177] In one exemplary embodiment, a flowchart of the elevator anomaly detection is as shown in Figure 9 , which includes:

[0178] An anomaly detection model training process. The industrial computer obtains a plurality of training parameter sets corresponding to a plurality of training time periods. For each detection parameter, the industrial computer obtains a training parameter value corresponding to the detection parameter from the plurality of training parameter sets, calculates the mean and standard deviation of the plurality of obtained training parameter values, and obtains the training mean and training standard deviation corresponding to the detection parameter. For each training parameter value in the training parameter set, the training parameter value is standardized based on the training mean and training standard deviation of the detection parameter corresponding to the training parameter value, to obtain a processed parameter value corresponding to the training parameter value. Based on the processed parameter value corresponding to each training parameter value in the training parameter set, a processing parameter set corresponding to the training time period is obtained. Based on the sequence of a preset number of consecutive training time periods, a target parameter set corresponding to the preset number of training time periods is formed into a training matrix. For each element value in the training matrix, the element value is converted into a corresponding gray value based on a preset mapping relationship, to obtain a sample matrix corresponding to the training matrix, and a training feature image corresponding to the sample matrix is generated. Based on a plurality of training feature images and anomaly detection labels corresponding to the training feature images, an initial anomaly detection model is trained to obtain a target anomaly detection model.

[0179] The elevator anomaly detection process. The hoisting machine corresponding to the target elevator uses a three-phase power supply for power supply. The industrial computer obtains the analog voltage signal corresponding to phase A, the analog voltage signal corresponding to phase B and the analog voltage signal corresponding to phase C of the above hoisting machine in the detection time period through the voltage sensor, obtains the analog current signal corresponding to phase A, the analog current signal corresponding to phase B and the analog current signal corresponding to phase C of the above hoisting machine in the detection time period through the current sensor, the industrial computer samples the analog voltage signal corresponding to phase A based on the preset frequency to obtain the sampling voltage value corresponding to phase A at each sampling time point, samples the analog voltage signal corresponding to phase B based on the preset frequency to obtain the sampling voltage value corresponding to phase B at each sampling time point, and samples the analog voltage signal corresponding to phase C based on the preset frequency to obtain the sampling voltage value corresponding to phase C at each sampling time point; the analog current signal corresponding to phase A is sampled based on the preset frequency to obtain the sampling current value corresponding to phase A at each sampling time point, the analog current signal corresponding to phase B is sampled based on the preset frequency to obtain the sampling current value corresponding to phase B at each sampling time point, and the analog current signal corresponding to phase C is sampled based on the preset frequency to obtain the sampling current value corresponding to phase C at each sampling time point.

[0180] For each sampling time point, the actual voltage value corresponding to phase A is determined using formula (1) , the actual voltage value corresponding to phase B and the actual voltage value corresponding to phase C ; the actual current value corresponding to phase A , the actual current value corresponding to phase B and the actual current value corresponding to phase C are determined using formula (2).

[0181] The industrial computer uses formulas (3), (4) and (5) to calculate the detection voltage value of phase A in the detection time period, the detection voltage value of phase B in the detection time period and the detection voltage value of phase C in the detection time period, respectively; uses formulas (6), (7) and (8) to calculate the detection current value of phase A in the detection time period, the detection current value of phase B in the detection time period and the detection current value of phase C in the detection time period, respectively; uses formulas (9), (10) and (11) to calculate the detection power value of phase A in the detection time period, the detection power value of phase B in the detection time period and the detection power value of phase C in the detection time period, respectively.

[0182] For phase A, the industrial computer determines the number of zero-crossing points of phase A in the to-be-detected time period using the zero-crossing point method, substitutes the number of zero-crossing points of phase A in the to-be-detected time period into formula (12) to obtain the phase voltage frequency of phase A; determines the number of zero-crossing points of phase B in the to-be-detected time period using the zero-crossing point method, substitutes the number of zero-crossing points of phase B in the to-be-detected time period into formula (12) to obtain the phase voltage frequency of phase B; determines the number of zero-crossing points of phase C in the to-be-detected time period using the zero-crossing point method, substitutes the number of zero-crossing points of phase C in the to-be-detected time period into formula (12) to obtain the phase voltage frequency of phase C. Substitute the phase voltage frequency of phase A, the phase voltage frequency of phase B, and the phase voltage frequency of phase C into formula (13) to obtain the target voltage frequency; substitute the target voltage frequency into formula (14) to obtain the detection angular velocity value corresponding to the to-be-detected time period.

[0183] The industrial computer substitutes the detection angular velocity value corresponding to the to-be-detected time period, the detection voltage value of phase A corresponding to the to-be-detected time period, the detection voltage value of phase B corresponding to the to-be-detected time period, the detection voltage value of phase C corresponding to the to-be-detected time period, the detection current value of phase A corresponding to the to-be-detected time period, the detection current value of phase B corresponding to the to-be-detected time period, the detection current value of phase C corresponding to the to-be-detected time period, the detection power value of phase A corresponding to the to-be-detected time period, the detection power value of phase B corresponding to the to-be-detected time period, and the detection power value of phase C corresponding to the to-be-detected time period into a detection parameter set corresponding to the to-be-detected time period of the target elevator.

[0184] Based on the detection parameter sets corresponding to the preset number of continuous to-be-detected time periods, based on the sequence of the plurality of to-be-detected time periods, the plurality of detection parameter sets are combined into a detection matrix; based on the training mean value and the training standard deviation corresponding to the detection parameters, the detection parameter values corresponding to the detection parameters in the initial matrix are preprocessed to obtain an initial matrix; for each element value in the initial matrix, the element value is converted into a corresponding gray value to obtain a gray matrix; based on the gray matrix, a detection feature image is generated. The detection feature image is input into the target anomaly detection model to obtain an anomaly detection result of the target elevator.

[0185] In the case of the anomaly detection result being a fault, a fault prompt information corresponding to the target elevator is generated.

[0186] In this embodiment, the detection parameter set corresponding to the to-be-detected time period of the target elevator is obtained, the detection parameter value corresponding to the detection parameter is preprocessed based on the training mean value and the training standard deviation corresponding to the detection parameter, and the target parameter set corresponding to the to-be-detected time period is obtained. Since the training mean value and the training standard deviation are determined based on the plurality of training parameter sets, and the training parameter set is used to train the initial anomaly detection model to obtain the target anomaly detection model, it can be understood that the target parameter set obtained by preprocessing the detection parameter set using the training mean value and the training standard deviation corresponding to the training parameter calculated based on the training parameter set is more suitable for the target anomaly detection model trained based on the training parameter set. Based on the target parameter set corresponding to the to-be-detected time period and the target anomaly detection model, the anomaly detection result of the target elevator is obtained, thereby improving the accuracy of the anomaly detection result.

[0187] It should be understood that, although each step in the flowchart involved in each of the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each of the above embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps.

[0188] Based on the same inventive concept, the embodiments of the present application also provide an elevator anomaly detection device for implementing the above-mentioned elevator anomaly detection method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more elevator anomaly detection device embodiments provided below can refer to the limitations of the elevator anomaly detection method described above, which will not be repeated here.

[0189] In one embodiment, as shown in Figure 10 An elevator anomaly detection device is provided, comprising: an acquisition module, a preprocessing module and a detection module, wherein:

[0190] The acquisition module 1002 is configured to acquire a detection parameter set corresponding to a to-be-detected time period of a target elevator; the detection parameter set includes a detection parameter value corresponding to a detection parameter;

[0191] The preprocessing module 1004 is configured to perform preprocessing on the detection parameter value corresponding to the detection parameter based on the training mean value and the training standard deviation corresponding to the detection parameter, to obtain a target parameter set corresponding to the to-be-detected time period; the training mean value and the training standard deviation are determined based on a plurality of training parameter sets; the training parameter sets are used to train an initial anomaly detection model to obtain a target anomaly detection model.

[0192] The detection module 1006 is configured to obtain an anomaly detection result of the target elevator based on the target parameter set corresponding to the to-be-detected time period and the target anomaly detection model.

[0193] In one embodiment, the detection module 1006 is further configured to: group the plurality of target parameter sets into an initial matrix based on the sequence of the plurality of to-be-detected time periods; convert each element value in the initial matrix into a corresponding gray value to obtain a gray matrix; generate a detection feature image based on the gray matrix; and input the detection feature image into the target anomaly detection model to obtain the anomaly detection result of the target elevator.

[0194] In one embodiment, the elevator anomaly detection apparatus further includes a training module, which is configured to: obtain a plurality of training parameter sets corresponding to a plurality of training time periods; the training parameter sets include training parameter values corresponding to detection parameters; for each detection parameter, calculate a mean value and a standard deviation of the training parameter values corresponding to the detection parameter in the plurality of training parameter sets to obtain a training mean value and a training standard deviation corresponding to the detection parameter; perform preprocessing on the training parameter set corresponding to the training time period based on the training mean value and the training standard deviation corresponding to the detection parameter to obtain a processed parameter set corresponding to the training time period; generate a training feature image based on the processed parameter sets corresponding to a continuous preset number of training time periods; and train an initial anomaly detection model based on a plurality of training feature images to obtain a target anomaly detection model.

[0195] In one embodiment, the acquisition module 1002 is further configured to: acquire a sampling voltage value and a sampling current value of a corresponding hoisting machine of the target elevator at each sampling time point in the to-be-detected time period; for each sampling voltage value, determine an actual voltage value corresponding to the sampling voltage value based on a voltage zero-point offset and a voltage scale factor of the hoisting machine; for each sampling current value, determine an actual current value corresponding to the sampling current value based on a current zero-point offset and a current scale factor of the hoisting machine; and determine a detection parameter set corresponding to the to-be-detected time period of the target elevator based on the sampling voltage value, the actual voltage value, and the actual current value corresponding to each sampling time point.

[0196] In an embodiment, the acquisition module 1002 is further configured to: determine a detection angular velocity value corresponding to the to-be-detected time period based on the sampling voltage values corresponding to the plurality of sampling time points; determine a detection voltage value corresponding to the to-be-detected time period based on the actual voltage values corresponding to the plurality of sampling time points; determine a detection current value corresponding to the to-be-detected time period based on the actual current values corresponding to the plurality of sampling time points; determine a detection power value corresponding to the to-be-detected time period based on the actual voltage values and the actual current values corresponding to the plurality of sampling time points; and obtain a detection parameter set corresponding to the to-be-detected time period of the target elevator based on the detection angular velocity value, the detection voltage value, the detection current value, and the detection power value.

[0197] In an embodiment, the acquisition module 1002 is further configured to: determine, for each phase sampling voltage, a number of zero-crossing points in the to-be-detected time period based on the directions of the sampling voltage values corresponding to any two adjacent sampling time points; determine a phase voltage frequency based on the length of the to-be-detected time period and the number of zero-crossing points; average the plurality of phase voltage frequencies to obtain a target voltage frequency; and determine a detection angular velocity value corresponding to the to-be-detected time period based on the target voltage frequency and the pole pair number of the traction machine.

[0198] The above-described various modules in the elevator anomaly detection apparatus can be implemented in whole or in part by software, hardware, and combinations thereof. The above-described various modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform the operations corresponding to the above-described various modules.

[0199] In an embodiment, a computer device is provided, which can be a terminal, and an internal structure diagram of the computer device can be as shown in FIG. 8. Figure 11The computer device shown in the figure includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be realized through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to realize an elevator anomaly detection method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0200] Those skilled in the art can understand that, Figure 11 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0201] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in the above method embodiments.

[0202] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps in the above method embodiments.

[0203] In one embodiment, a computer program product is provided, including a computer program, and the computer program is executed by a processor to implement the steps in the above method embodiments.

[0204] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties.

[0205] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments of each method. Any reference to memory, database or other medium used in the embodiments provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0206] The technical features of the above embodiments can be combined in any way. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0207] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A method for detecting elevator anomalies, characterized in that, The method includes: Obtain the set of detection parameters for the target elevator during the time period to be detected; the set of detection parameters includes the detection parameter values ​​corresponding to the detection parameters; Based on the training mean and training standard deviation corresponding to the detection parameters, the detection parameter values ​​corresponding to the detection parameters are preprocessed to obtain the target parameter set corresponding to the time period to be detected; the training mean and training standard deviation are determined based on multiple training parameter sets, which are used to train the initial anomaly detection model to obtain the target anomaly detection model; training the initial anomaly detection model to obtain the target anomaly detection model includes: acquiring multiple training parameter sets corresponding to multiple training time periods; the training parameter sets include training parameter values ​​corresponding to the detection parameters; for each detection parameter, calculating the mean and standard deviation of the training parameter values ​​corresponding to the detection parameter in the multiple training parameter sets to obtain the training mean and training standard deviation corresponding to the detection parameter; preprocessing the training parameter set corresponding to the training time period based on the training mean and training standard deviation corresponding to the detection parameters to obtain the processing parameter set corresponding to the training time period; generating training feature images based on a consecutive preset number of processing parameter sets corresponding to training time periods; and training the initial anomaly detection model based on the multiple training feature images to obtain the target anomaly detection model; Based on the target parameter set corresponding to the time period to be detected and the target anomaly detection model, the anomaly detection result of the target elevator is obtained.

2. The method according to claim 1, characterized in that, The method of obtaining the anomaly detection result of the target elevator based on the target parameter set corresponding to the time period to be detected and the target anomaly detection model includes: Based on the chronological order of the multiple time periods to be detected, the multiple sets of target parameters are combined into an initial matrix; For each element value in the initial matrix, the element value is converted into a corresponding grayscale value to obtain a grayscale matrix; Based on the grayscale matrix, a detection feature image is generated; The detected feature image is input into the target anomaly detection model to obtain the anomaly detection result of the target elevator.

3. The method according to claim 1, characterized in that, The generation of training feature images based on a set of processing parameters corresponding to a consecutive preset number of training time periods includes: Based on the sequential order of a predetermined number of consecutive training time periods, a training matrix is ​​formed from the target parameter sets corresponding to the predetermined number of training time periods; For each element value in the training matrix, based on a preset mapping relationship, the element value is converted into a corresponding grayscale value to obtain the sample matrix corresponding to the training matrix; Generate the training feature image corresponding to the sample matrix.

4. The method according to claim 1, characterized in that, The acquisition of the set of detection parameters for the target elevator during the time period to be detected includes: Obtain the sampling voltage and sampling current values ​​of the traction machine corresponding to the target elevator at each sampling time point during the detection time period; For each sampled voltage value, the actual voltage value corresponding to the sampled voltage value is determined based on the voltage zero offset and voltage scaling factor of the traction machine. For each sampled current value, the actual current value corresponding to the sampled current value is determined based on the current zero offset and current scaling factor of the traction machine. Based on the sampled voltage value, actual voltage value, and actual current value corresponding to each sampling time point, the set of detection parameters for the target elevator corresponding to the time period to be detected is determined.

5. The method according to claim 4, characterized in that, The method for determining the set of detection parameters for the target elevator during the time period to be detected, based on the sampled voltage value, actual voltage value, and actual current value corresponding to each sampling time point, includes: Based on the sampling voltage values ​​corresponding to multiple sampling time points, the detection angular velocity value corresponding to the time period to be detected is determined; Based on the actual voltage values ​​corresponding to multiple sampling time points, the detection voltage value corresponding to the time period to be detected is determined; Based on the actual current values ​​corresponding to multiple sampling time points, the detection current value corresponding to the time period to be detected is determined; Based on the actual voltage and actual current values ​​corresponding to multiple sampling time points, the detection power value corresponding to the time period to be detected is determined; Based on the detected angular velocity value, detected voltage value, detected current value, and detected power value, a set of detection parameters for the target elevator corresponding to the time period to be detected is obtained.

6. The method according to claim 5, characterized in that, The step of determining the detection angular velocity value corresponding to the time period to be detected based on the sampling voltage values ​​corresponding to multiple sampling time points includes: For each phase sampling voltage, the number of zero crossings within the time period to be detected is determined based on the direction of the sampling voltage values ​​corresponding to any two adjacent sampling time points. The phase voltage frequency is determined based on the duration of the time period to be detected and the number of zero crossings; The target voltage frequency is obtained by averaging the multiple phase voltage frequencies. Based on the target voltage frequency and the number of pole pairs of the traction machine, the detection angular velocity value corresponding to the time period to be detected is determined.

7. An elevator anomaly detection device, characterized in that, The device includes: The acquisition module is used to acquire the set of detection parameters corresponding to the target elevator during the time period to be detected; the set of detection parameters includes the detection parameter values ​​corresponding to the detection parameters; A preprocessing module is used to preprocess the detection parameter values ​​corresponding to the detection parameters based on the training mean and training standard deviation of the detection parameters to obtain a target parameter set corresponding to the time period to be detected. The training mean and training standard deviation are determined based on multiple training parameter sets, which are used to train an initial anomaly detection model to obtain a target anomaly detection model. The process of training the initial anomaly detection model to obtain the target anomaly detection model includes: acquiring multiple training parameter sets corresponding to multiple training time periods; the training parameter sets include training parameter values ​​corresponding to the detection parameters; for each detection parameter, calculating the mean and standard deviation of the training parameter values ​​corresponding to the detection parameter in the multiple training parameter sets to obtain the training mean and training standard deviation of the detection parameter; preprocessing the training parameter set corresponding to the training time period based on the training mean and training standard deviation of the detection parameters to obtain a processing parameter set corresponding to the training time period; generating training feature images based on a consecutive preset number of processing parameter sets corresponding to training time periods; and training the initial anomaly detection model based on the multiple training feature images to obtain the target anomaly detection model. The detection module is used to obtain the anomaly detection result of the target elevator based on the target parameter set corresponding to the time period to be detected and the target anomaly detection model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images