Escalator monitoring method and device and escalator fault prediction method, device and equipment

Abstract

The invention provides an escalator monitoring method which is applied to an escalator monitoring device and relates to the technical field of elevators, the escalator monitoring device comprises a plurality of information processing modules, and the escalator monitoring method comprises the steps that a plurality of operation parameters of an escalator are collected; at least one of the information processing modules executes a first preset operation so as to collect and store the currently collected operation parameters, and different information processing modules store at least one different operation parameter; polling a plurality of information processing modules, and determining at least one abnormal operation parameter and abnormal time information of the operation parameter according to a polling result to obtain escalator monitoring data; and releasing the escalator monitoring data to the message forwarding server, wherein the escalator monitoring data is configured to enable the escalator fault prediction device to predict the escalator fault according to the escalator monitoring data based on the support vector machine. The invention further provides an escalator monitoring device, an escalator fault prediction method and device, equipment, a medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the technical field of elevators, and in particular to an escalator monitoring method and device, and an escalator fault prediction method, device and equipment. Background Art

[0002] The number of escalators in use is very large. The original escalator maintenance method has certain limitations. Due to problems such as waste of human resources and inadequate maintenance, escalators are often accompanied by safety hazards during operation.

[0003] With the development of embedded technology, network technology and the gradual change of people's values, the maintenance mode of escalators is also changing from passive fault repair to active preventive maintenance. An indispensable link in this transformation process is the status monitoring of escalators. Only by understanding the current status information of escalators can we make targeted efforts and formulate reasonable maintenance plans based on this. In this way, unnecessary waste of manpower, financial resources, time and other resources can be avoided, and safety hazards caused by inadequate maintenance can be eliminated.

[0004] Therefore, how to monitor the status of the escalator has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of the above problems, the present disclosure provides an escalator monitoring method and device, and an escalator fault prediction method, device and equipment.

[0006] According to a first aspect of the present disclosure, an escalator monitoring method is provided, which is applied to an escalator monitoring device, wherein the escalator monitoring device includes a plurality of information processing modules, and the escalator monitoring method includes:

[0007] Collect multiple operating parameters of escalators;

[0008] At least one of the plurality of information processing modules performs a first preset operation to store the currently collected operating parameters, wherein different information processing modules store at least one different operating parameter;

[0009] Polling the operating parameters stored in the plurality of information processing modules, and determining at least one abnormal operating parameter and abnormal time information of the operating parameter according to the polling result, so as to obtain escalator monitoring data;

[0010] The escalator monitoring data is published to a message forwarding service end, and the escalator monitoring data is configured to enable an escalator fault prediction device to predict escalator faults based on the escalator monitoring data based on a support vector machine.

[0011] According to an embodiment of the present disclosure, the first preset operation includes:

[0012] Creating at least one reading thread for at least one operating parameter;

[0013] Reading the operating parameter from a sensor that collects the operating parameter through at least one of the reading threads;

[0014] The operating parameters read are stored in different registers respectively through the main thread.

[0015] According to an embodiment of the present disclosure, at least one of the information processing modules includes at least one first register and a plurality of second registers, and at least one of the operating parameters includes a temperature parameter, a humidity parameter, and a vibration parameter;

[0016] The storing the read operating parameters into different registers respectively through the main thread includes:

[0017] When at least one of the temperature parameter, the humidity parameter, and the vibration parameter is abnormal, updating a flag bit in the first register for indicating the abnormal type according to the abnormality;

[0018] The read temperature parameter, humidity parameter and vibration parameter are stored in different second registers respectively.

[0019] According to an embodiment of the present disclosure, the plurality of information processing modules include a first information processing module and a second information processing module, the first information processing module includes at least one of the first registers and a plurality of the second registers, the second information processing module is configured with a third register, and at least one of the operating parameters further includes a distance parameter between the handrail of the escalator and a reference point and an escalator fault code;

[0020] The storing the read operating parameters into different registers respectively through the main thread also includes the following steps performed by the first information processing module:

[0021] When there is an abnormality in the distance parameter, updating a flag bit in the first register for indicating the type of abnormality according to the existing abnormality;

[0022] storing the read temperature parameter, humidity parameter, vibration parameter and distance parameter in different second registers respectively;

[0023] The storing the read operating parameters into different registers respectively through the main thread also includes the following steps performed by the second information processing module:

[0024] According to the escalator fault code, a flag bit in the third register used to characterize the fault type is updated.

[0025] According to an embodiment of the present disclosure, the flag bit used to characterize the abnormality type in the first register includes: at least one of a speed abnormality flag bit, a controller abnormality flag bit, a motor abnormality flag bit, a reduction gear box abnormality flag bit, and a handrail belt system abnormality flag bit;

[0026] When the distance parameter is abnormal, updating the flag bit in the first register for representing the abnormal type according to the abnormality includes:

[0027] When the read operating parameter reaches a preset threshold, it is determined that an abnormality exists in the operating parameter, and a flag bit in the first register that matches the abnormality is set to a first value.

[0028] According to an embodiment of the present disclosure, the escalator monitoring method further includes:

[0029] When it is determined that at least one of the operating parameters is invalid data, at least a sensor for collecting the operating parameter is reset.

[0030] According to an embodiment of the present disclosure, at least one of the reading threads includes a vibration sensor reading thread and a temperature and humidity sensor reading thread with decreasing priorities, and the priority of the main thread is higher than that of the vibration sensor reading thread.

[0031] According to an embodiment of the present disclosure, at least one of the reading threads further includes a fault code reading thread, and the priority of the fault code reading thread is between the vibration sensor reading thread and the temperature and humidity sensor reading thread; and / or,

[0032] At least one of the reading threads further includes a distance measuring sensor data reading thread, and a priority of the distance measuring sensor data reading thread is between the vibration sensor reading thread and the temperature and humidity sensor reading thread.

[0033] According to an embodiment of the present disclosure, the first preset operation further includes:

[0034] The reading thread sends a pointer to the main thread via a mailbox, wherein the pointer points to a temporary storage address of the operating parameter read by the reading thread;

[0035] The main thread obtains the operating parameters read by the reading thread according to the temporary storage address, and stores the operating parameters in a register.

[0036] According to an embodiment of the present disclosure, polling the operating parameters stored in the plurality of information processing modules, and determining at least one abnormal operating parameter and abnormal time information of the operating parameter according to the polling result to obtain escalator monitoring data, includes:

[0037] When at least one flag bit of the first register in at least one information processing module includes the first value, at least one abnormality is determined, and it is determined whether any of the operating parameters stored in the second register exceeds a preset range;

[0038] When there is an operating parameter in the second register that exceeds the preset range, determining that the operating parameter is abnormal;

[0039] For abnormal operating parameters,

[0040] Counting the duration of the operation parameter exceeding the preset range to obtain a single abnormal duration of the operation parameter;

[0041] Summarizing the single abnormal durations to obtain a cumulative abnormal duration of the operating parameter;

[0042] The single abnormality duration and the cumulative abnormality duration constitute the abnormality time information of the operating parameter.

[0043] According to an embodiment of the present disclosure, the plurality of operating parameters further include electrical parameters, which are read and stored by an electronic electric energy meter;

[0044] The polling of the operating parameters stored in the plurality of information processing modules and determining at least one abnormal operating parameter and abnormal time information of the operating parameter according to the polling result to obtain escalator monitoring data further includes:

[0045] Obtaining electrical parameters in the electronic electric energy meter;

[0046] When there is an operating parameter exceeding the preset range in the second register and the electrical parameter meets the validity condition, the step of counting the duration of the operating parameter exceeding the preset range is performed.

[0047] According to an embodiment of the present disclosure, publishing the escalator monitoring data to the message forwarding service end includes:

[0048] The escalator fault code in the third register in the second information processing module is obtained, and the escalator monitoring data and the escalator fault code are packaged and forwarded through MQTT.

[0049] A second aspect of the present disclosure further provides an escalator fault prediction method, which is applied to an escalator fault prediction device, wherein the escalator fault prediction method comprises:

[0050] consuming escalator monitoring data from a message forwarding service end, the escalator monitoring data including abnormal time information of at least one operating parameter determined by the escalator monitoring end;

[0051] The escalator failure is predicted based on the abnormal time information of the operating parameters through the pre-trained support vector machine model.

[0052] According to an embodiment of the present disclosure, the escalator fault prediction method further includes a training step of the support vector machine model, and the training step includes:

[0053] Obtain escalator monitoring data samples and escalator fault code samples forwarded by the escalator monitoring terminal;

[0054] The support vector machine model to be trained is trained according to the acquired escalator monitoring data samples and the escalator fault code samples.

[0055] The third aspect of the present disclosure further provides an escalator fault prediction method, which is applied to an escalator fault prediction device, wherein the escalator fault prediction device includes an escalator monitoring device and an escalator fault prediction device, the escalator monitoring device includes a plurality of information processing modules, and the escalator fault prediction method includes the following steps performed by the escalator monitoring device:

[0056] The escalator monitoring terminal includes a plurality of information processing modules, and the escalator monitoring method includes:

[0057] Collect multiple operating parameters of escalators;

[0058] At least one of the plurality of information processing modules performs a first preset operation to store the currently collected operating parameters, wherein different information processing modules store at least one different operating parameter;

[0059] Polling the operating parameters stored in the plurality of information processing modules, and determining at least one abnormal operating parameter and abnormal time information of the operating parameter according to the polling result, so as to obtain escalator monitoring data;

[0060] Publishing the escalator monitoring data to a message forwarding server;

[0061] The escalator fault prediction method further comprises the following steps performed by the escalator fault prediction device:

[0062] Consuming the escalator monitoring data from the message forwarding server;

[0063] The escalator failure is predicted based on the abnormal time information of the operating parameters through the pre-trained support vector machine model.

[0064] A fourth aspect of the present disclosure further provides an escalator monitoring device, wherein the escalator monitoring device includes a plurality of sensors, a plurality of information processing modules, a monitoring module, and a forwarding module;

[0065] Multiple sensors are used to collect multiple operating parameters of the escalator;

[0066] The plurality of information processing modules are used to execute a first preset operation to store the currently collected operating parameters, wherein different information processing modules store at least one different operating parameter;

[0067] The monitoring module is used to poll the operating parameters stored in the plurality of information processing modules, and determine at least one abnormal operating parameter and abnormal time information of the operating parameter according to the polling result, so as to obtain escalator monitoring data;

[0068] The forwarding module is used to publish the escalator monitoring data to the message forwarding service end, and the escalator monitoring data is configured to enable the escalator fault prediction device to predict escalator faults based on the escalator monitoring data based on a support vector machine.

[0069] A fifth aspect of the present disclosure further provides an escalator fault prediction device, wherein the escalator fault prediction device comprises a first acquisition module and a prediction module;

[0070] The first acquisition module is used to consume escalator monitoring data from the message forwarding service end, and the escalator monitoring data includes abnormal time information of at least one of the operating parameters determined by the escalator monitoring end;

[0071] The prediction module is used to predict the failure of the escalator according to the abnormal time information of the operating parameters through a pre-trained support vector machine model.

[0072] The sixth aspect of the present disclosure also provides an escalator fault prediction device, wherein the escalator fault prediction device includes an escalator monitoring device and an escalator fault prediction device, the escalator monitoring device includes multiple sensors, multiple information processing modules, a monitoring module and a forwarding module, and the escalator fault prediction device includes a first acquisition module and a prediction module

[0073] Multiple sensors are used to collect multiple operating parameters of the escalator;

[0074] The plurality of information processing modules are used to execute a first preset operation to store the currently collected operating parameters, wherein different information processing modules store at least one different operating parameter;

[0075] The monitoring module is used to poll the operating parameters stored in the plurality of information processing modules, and determine at least one abnormal operating parameter and abnormal time information of the operating parameter according to the polling result, so as to obtain escalator monitoring data;

[0076] The forwarding module is used to publish the escalator monitoring data to the message forwarding server;

[0077] The first acquisition module is used to consume escalator monitoring data from the message forwarding server;

[0078] The prediction module is used to predict the failure of the escalator according to the abnormal time information of the operating parameters through a pre-trained support vector machine model.

[0079] The seventh aspect of the present disclosure provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the above-mentioned escalator monitoring method or escalator fault prediction method.

[0080] The eighth aspect of the present disclosure also provides a computer program product, including a computer program, which implements the above-mentioned escalator monitoring method or escalator fault prediction method when executed by a processor.

[0081] One or more of the above embodiments have the following advantages or beneficial effects:

[0082] The escalator fault monitoring method of the embodiment of the present disclosure performs two-way processing on the real-time data collected by the sensor through the information processing module and the monitoring module, and obtains the escalator monitoring data including the abnormal time information. Therefore, the escalator monitoring device does not need to upload a large number of real-time operating parameters, so that it can adapt to the bandwidth limitation of the message forwarding mechanism, so that the interaction between the monitoring module and the escalator fault prediction device can be realized through the message forwarding mechanism, ensuring the fast communication between the monitoring module at the front end and the escalator fault prediction device at the back end. At the same time, the escalator monitoring data including the abnormal time information can be directly used for the support vector machine to predict the escalator fault. Compared with the solution of directly uploading the operating parameters, the escalator monitoring data generated by the embodiment of the present disclosure can better reflect the operating status of the escalator. Therefore, it can enable the support vector machine to predict the escalator fault more quickly and accurately, thereby achieving more effective active prevention. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0084] Figure 1 The application scenario diagram of the escalator monitoring method, escalator fault prediction method, device, equipment, storage medium and program product according to the embodiments of the present disclosure is schematically shown;

[0085] Figure 2 A flowchart of an escalator monitoring method according to an embodiment of the present disclosure is schematically shown;

[0086] Figure 3 A flowchart schematically shows a first preset operation according to an embodiment of the present disclosure;

[0087] Figure 4 A flowchart schematically shows the interaction between threads according to an embodiment of the present disclosure;

[0088] Figure 5 One of the flow charts for storing operating parameters according to an embodiment of the present disclosure is schematically shown;

[0089] Figure 6 The second flowchart of storing operating parameters according to an embodiment of the present disclosure is schematically shown;

[0090] Figure 7 Schematically shows a third flowchart of storing operating parameters according to an embodiment of the present disclosure;

[0091] Figure 8 Schematically shows one of the flow charts for generating abnormal time information according to an embodiment of the present disclosure;

[0092] Fig. 9 The second flowchart of generating abnormal time information according to an embodiment of the present disclosure is schematically shown;

[0093] Fig.10 A flowchart of an escalator fault prediction method according to an embodiment of the present disclosure is schematically shown;

[0094] Fig.11 A schematic diagram of determining a hyperplane according to an embodiment of the present disclosure is schematically shown;

[0095] Fig.12 A flowchart of support vector machine training according to an embodiment of the present disclosure is schematically shown;

[0096] Fig.13 The structure block diagram of the escalator monitoring device according to the embodiment of the present disclosure is schematically shown;

[0097] Fig.14 The structure block diagram of the escalator fault prediction device according to the embodiment of the present disclosure is schematically shown;

[0098] Fig.15 A block diagram of an electronic device suitable for implementing an escalator monitoring method or an escalator fault prediction method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0099] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0100] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0101] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0102] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0103] It should be noted that the escalator monitoring method, escalator fault prediction method, device, equipment, storage medium and program product provided by the embodiments of the present disclosure relate to the field of elevator technology. In the technical scheme of the present disclosure, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved are in compliance with the provisions of relevant laws and regulations, necessary confidentiality measures are taken, and do not violate public order and good customs.

[0104] An embodiment of the present disclosure provides an escalator monitoring method, which is applied to an escalator monitoring device. The escalator monitoring device includes multiple information processing modules. The escalator monitoring method includes: collecting multiple operating parameters of the escalator; at least one of the multiple information processing modules executes a first preset operation to store the currently collected operating parameters, wherein different information processing modules store at least one different operating parameter; polling the operating parameters stored by multiple information processing modules, and determining at least one abnormal operating parameter and abnormal time information of the operating parameter based on the polling result to obtain escalator monitoring data; publishing the escalator monitoring data to a message forwarding server, and the escalator monitoring data is configured to enable an escalator fault prediction device to predict escalator faults based on the escalator monitoring data based on a support vector machine.

[0105] In this way, the escalator monitoring device does not need to upload a large amount of real-time data, so it can adapt to the bandwidth limitation of the message forwarding mechanism, so that the interaction between the escalator monitoring device and the escalator fault prediction device can be realized through the message forwarding mechanism, ensuring the fast communication between the escalator monitoring device located at the front end and the escalator fault prediction device located in the cloud. At the same time, the escalator monitoring data including abnormality marks and abnormality time information can be directly used for the support vector machine to predict escalator failures. Compared with the solution of directly uploading the operating parameters, the escalator monitoring data generated by the embodiment of the present disclosure can also enable the support vector machine to predict escalator failures more quickly and more accurately, thereby achieving more effective active prevention.

[0106] Figure 1 The application scenario diagram of the escalator monitoring method, escalator fault prediction method, device, equipment, storage medium and program product according to the embodiments of the present disclosure is schematically shown.

[0107] like Figure 1 As shown, the application scenario according to this embodiment may include an escalator monitoring device 100, and the escalator monitoring device 100 includes an escalator monitoring device 101 arranged at the front end and an escalator fault prediction device 102 arranged at the rear end.

[0108] The escalator monitoring device 101 may include multiple sensors 1011, multiple information processing modules 1012, and a monitoring module 1013. The sensor 1011 is used to collect the real-time operating parameters of the escalator, the information processing module 1012 is used to collect and process the operating parameters collected by the sensor 1011, and the monitoring module 1013 is used to extract information such as abnormal time information from the real-time data stored in the monitoring information processing module 1012, and summarize it into escalator monitoring data. Each information processing module 1012 can have an independent processor and memory. The monitoring module 1013 is also used to publish the escalator monitoring data to the message forwarding service end, so that the escalator fault prediction device 102 can subscribe to the relevant topic from the message forwarding end to consume the message, and then predict the escalator fault.

[0109] Optionally, the multiple sensors 1011 may include a temperature and humidity sensor 1011, a distance sensor 1011, a vibration sensor 1011, etc. The temperature and humidity sensor 1011 may obtain the temperature and humidity of the escalator room and the temperature and humidity around the escalator, the distance sensor 1011 may obtain the tightness of the handrail of the escalator, and the vibration sensor 1011 may obtain the vibration data of the motor and reduction gear box of the escalator. The information processing module 1012 and the monitoring module 1013 may be networked through the Modbus protocol, and the information processing module 1012 may process and summarize the above data (i.e., operating parameters) and then communicate with the monitoring module 1013 through the Modbus protocol.

[0110] Optionally, the escalator monitoring device 101 may further include an electronic energy meter 1014, which may obtain electrical parameters during the operation of the escalator, such as power parameters, etc. The electronic energy meter 1014 may directly communicate with the monitoring module 1013 via the Modbus protocol.

[0111] Modbus is a serial communication protocol. As a standard, open and free bus protocol widely used in industrial fields, Modbus has the characteristics of simple data frame format and easy user use.

[0112] The Modbus protocol is a master / slave architecture protocol. There is one node that is the master, and the other nodes that use the Modbus protocol to participate in the communication are slaves. Each slave device has a unique address.

[0113] For a single escalator, the monitoring module 1013 serves as the host, and three slaves are mounted thereunder, namely, an electronic energy meter 1014 and at least two information processing modules 1012. One of the two information processing modules 1012 may also be configured with a second Modbus interface, so that the information processing module 1012 can serve as the host to communicate with the escalator control system (serving as a slave) through the Modbus protocol to obtain the escalator fault code.

[0114] The escalator monitoring device 101 can be set at the front end, for example, embedded in the escalator equipment. The escalator fault prediction device 102 can be set at the back end, for example, in a server in the cloud. Among them, the server can be a server that provides various services, such as a background management server that provides support for websites browsed by users using terminal devices (only as an example). The background management server can analyze and process the received user request and other data, and feed back the processing results (such as obtaining or generating pages, information or data according to user requests, etc.) to the terminal device.

[0115] It should be noted that the escalator monitoring method provided in some embodiments of the present disclosure can generally be executed by the escalator monitoring device 101 , and the escalator fault prediction method provided in some embodiments of the present disclosure can be executed by the escalator fault prediction device 102 .

[0116] The following will be based on Figure 1 The scene described by Figure 2 to Figure 9 The escalator monitoring method in some disclosed embodiments is described in detail. The escalator monitoring method in the embodiment is applied to an escalator monitoring device 101 . The escalator monitoring device 101 includes a plurality of information processing modules 1012 .

[0117] Figure 2 The flowchart of the escalator monitoring method according to the embodiment of the present disclosure is schematically shown.

[0118] like Figure 2 As shown, the escalator monitoring method of this embodiment includes steps S210 to S240.

[0119] It should be noted that although Figure 2 The steps in the figure are shown in sequence as indicated by the arrows, but the steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of the steps, and they can be executed in other orders. Moreover, at least some of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0120] In step S210, a plurality of operating parameters of the escalator are collected.

[0121] In an embodiment of the present disclosure, multiple operating parameters of the escalator can be collected separately by multiple sensors 1011. The multiple operating parameters may include temperature and humidity parameters, vibration parameters, and distance parameters for determining the tightness of the escalator handrail, etc. The embodiment of the present disclosure determines whether there is an abnormality in the relevant functions of the escalator through a combination of these operating parameters, and generates escalator monitoring data for the prediction of escalator failures.

[0122] In step S220, at least one of the plurality of information processing modules 1012 executes a first preset operation to store the currently collected operating parameters, wherein different information processing modules 1012 store at least one different operating parameter.

[0123] In an embodiment of the present disclosure, the first preset operation may include collecting, processing and storing the operating parameters collected by the sensor 1011. The multiple sensors 1011 and the multiple information processing modules 1012 are networked through the Modbus protocol.

[0124] Optionally, each information processing module 1012 can collect and store operating parameters collected by multiple sensors 1011, and different information processing modules 1012 can collect operating parameters collected by different sensors 1011. For example, multiple information processing modules 1012 may include a first information processing module 1012 and a second information processing module 1012. The first information processing module 1012 can collect operating parameters at the near end of the escalator, such as temperature and humidity parameters near the escalator and distance parameters between the handrail surface and a preset reference point for determining the tightness of the escalator handrail, etc. The second information processing module 1012 can collect temperature and humidity parameters of the machine room and fault codes in the escalator control system, etc.

[0125] In an embodiment of the present disclosure, when storing operating parameters, the information processing module 1012 may first judge the operating parameters to determine whether there are any abnormalities in the operating parameters (for example, too high or too low, etc.). When there are abnormalities in the operating parameters, corresponding abnormality markings may be performed, and the abnormality markings, the operating parameters with the abnormalities, and other operating parameters collected at the same time may be stored together.

[0126] In step S230, the operation parameters stored in the plurality of information processing modules 1011 are polled, and at least one abnormal operation parameter and abnormal time information of the operation parameter are determined according to the polling result to obtain escalator monitoring data.

[0127] In the embodiment of the present disclosure, the monitoring module 1013 can poll multiple information processing modules 1012, and for at least one information processing module 1012, the abnormality can be determined according to the abnormality mark stored in the information processing module 1012, and the abnormal operation parameter can be determined from the operation parameters stored simultaneously with the abnormality mark. For the abnormal operation parameter, the single abnormality duration and the cumulative abnormality duration can be counted, and then, the single abnormality duration and the cumulative abnormality duration together constitute the abnormal time information of the operation parameter, and then, the abnormal time information of the operation parameter constitutes the escalator monitoring data.

[0128] For example, when a temperature anomaly occurs, the duration of the last time the temperature and humidity parameters exceed the preset value can be counted to obtain the duration of a single anomaly of the temperature and humidity parameters, and the obtained single anomaly duration can be added to the total duration of the previous anomalies to obtain the cumulative anomaly duration.

[0129] In step S240, the escalator monitoring data is published to the message forwarding server, and the escalator monitoring data is configured to enable the escalator fault prediction device 102 to predict escalator faults based on the escalator monitoring data based on the support vector machine.

[0130] In an embodiment of the present disclosure, the message forwarding escalator fault prediction device can realize message forwarding between the monitoring module 1013 and the escalator fault prediction device 102 through MQTT. For example, the monitoring module 1013 can package the escalator monitoring data and publish it to the specified topic of the message forwarding escalator fault prediction device. The escalator fault prediction device 102 can subscribe to the topic and consume messages from it.

[0131] Therefore, the escalator fault monitoring method of the embodiment of the present disclosure performs two-way processing on the real-time data collected by the sensor 1011 through the information processing module 1012 and the monitoring module 1013, and obtains the escalator monitoring data including the abnormal time information. Therefore, the escalator monitoring device (specifically the monitoring module 1013) does not need to upload a large amount of real-time operating parameters, so that it can adapt to the bandwidth limitation of the message forwarding mechanism, so that the interaction between the monitoring module 1013 and the escalator fault prediction device 102 can be realized through the message forwarding mechanism, ensuring the fast communication between the monitoring module 1013 at the front end and the escalator fault prediction device 102 at the back end. At the same time, the escalator monitoring data including the abnormal time information can be directly used for the prediction of the escalator fault by the support vector machine. Compared with the solution of directly uploading the operating parameters, the escalator monitoring data generated by the embodiment of the present disclosure can better reflect the operating status of the escalator. Therefore, the support vector machine can predict the escalator fault more quickly and accurately, thereby realizing more effective active prevention.

[0132] Combine the following Figures 2 to 9The escalator monitoring method of the embodiment of the present disclosure is further described.

[0133] Figure 3 The flowchart of the first preset operation according to the embodiment of the present disclosure is schematically shown as follows: Figure 3 As shown, in some specific embodiments, the first preset operation includes steps S221 to S223.

[0134] In step S221, at least one reading thread is created for at least one operating parameter.

[0135] In an embodiment of the present disclosure, after the sensor 1011 is initialized, the information processing module 1012 can dynamically create a reading thread based on the idle thread and the completed thread, for example, a temperature and humidity sensor 1011 reading thread and a vibration sensor 1011 reading thread.

[0136] In step S222, the operating parameters are read from the sensor 1011 for collecting the operating parameters through at least one reading thread.

[0137] In an embodiment of the present disclosure, multiple information processing modules 1012 can selectively create different reading threads according to the different collected sensors 1011. For example, multiple information processing modules 1012 include a first information processing module 1012 and a second information processing module 1012. The first information processing module 1012 can create a laser sensor 1011 reading thread to read the distance parameter between the escalator handrail surface and a preset reference point from the laser sensor 1011, wherein the distance parameter can be used to determine the tightness of the escalator handrail. The second information processing module 1012 can create an escalator controller reading thread to read fault codes in the mobile escalator controller.

[0138] It should be noted that when the support vector machine needs to be trained, the second information processing module 1012 reads the fault code from the escalator controller, and the support vector machine predicts the fault according to the abnormal time information of the operating parameters, and compares it with the read fault code for training. After the support vector machine training is completed, the second information processing module 1012 no longer reads the fault code from the escalator controller, and the support vector machine can complete the fault prediction based only on the abnormal time information of the operating parameters.

[0139] In step S223, the read operating parameters are stored in different registers respectively through the main thread.

[0140] In the embodiment of the present disclosure, different operating parameters may be stored in different registers, that is, one register is configured for each operating parameter.

[0141] In some specific embodiments, at least one reading thread includes a vibration sensor 1011 reading thread and a temperature and humidity sensor 1011 reading thread, and the priority of the main thread is higher than the vibration sensor 1011 reading thread and the temperature and humidity sensor 1011 reading thread. Optionally, the priority of the vibration sensor 1011 reading thread is higher than the temperature and humidity sensor 1011 reading thread.

[0142] In some specific embodiments, at least one reading thread further includes a fault code reading thread, and the priority of the fault code reading thread is between the vibration sensor 1011 reading thread and the temperature and humidity sensor 1011 reading thread. And / or, at least one reading thread further includes a distance sensor 1011 data reading thread, and the priority of the distance sensor 1011 data reading thread is between the vibration sensor 1011 reading thread and the temperature and humidity sensor 1011 reading thread.

[0143] In an embodiment of the present disclosure, multiple reading threads have different priorities. For example, the priorities of the above five threads are, from high to low, the main thread, the vibration sensor 1011 reading thread, the fault code reading thread, the ranging sensor 1011 data reading thread, and the temperature and humidity sensor 1011 reading thread.

[0144] Figure 4 A flowchart of the interaction between threads according to an embodiment of the present disclosure is schematically shown. Figure 4 As shown, in some specific embodiments, the first preset operation also includes steps S224 and S225.

[0145] In step S224, the reading thread sends a pointer to the main thread via a mailbox, where the pointer points to a temporary storage address of the operating parameters read by the reading thread.

[0146] In step S225, the main thread obtains the operating parameters read by the reading thread according to the temporary storage address, and stores the operating parameters in the register.

[0147] In an embodiment of the present disclosure, when using a mailbox to send information with a relatively large amount of data, a pointer can be sent to point the pointer to a memory address or the address of a data buffer (that is, a temporary storage address). In this way, the mailbox that receives the pointer can process the content at the address pointed to by the pointer in the email.

[0148] For example, the main thread receives emails from other reading threads through a mailbox, obtains operating parameters in the memory or data buffer according to a temporary storage address pointed to by a pointer in the email, and loads the operating parameters into corresponding registers.

[0149] In some specific embodiments, at least one information processing module 1012 includes at least one first register and multiple second registers, and at least one operating parameter includes a temperature parameter, a humidity parameter, and a vibration parameter. In an embodiment of the present disclosure, the first register may include a special function register, and the first register is configured with multiple exception types and a flag bit of each exception type. The second register may include a holding register, and the second register is configured with at least one operating parameter and the value of the operating parameter.

[0150] Figure 5 One of the flow charts for storing operating parameters according to an embodiment of the present disclosure is schematically shown. Figure 5 As shown, step S223 includes S2231 and S2232.

[0151] In step S2231, when at least one of the temperature parameter, the humidity parameter and the vibration parameter is abnormal, the flag bit in the first register for indicating the abnormal type is updated according to the abnormality. Otherwise, step S2232 may be directly executed.

[0152] In the embodiments of the present disclosure, a reference range can be configured in advance for each operating parameter, and when the operating parameter exceeds the reference range, the operating parameter can be judged to be abnormal. For example, after the information processing module 1012 is initialized, the preset parameters of W25Q128 are read through the SPI interface, and these preset parameters include the equipment number of the escalator and the preset threshold value used to judge whether the operating parameter is abnormal.

[0153] For example, the first register is configured with multiple abnormality types, including low temperature operation, loose handrails, abnormal vibration, tight handrails, high humidity operation and high temperature operation. When the temperature parameter exceeds the preset temperature threshold (the temperature is too high), it is determined that there is an abnormality in the temperature and humidity parameters. At this time, the high temperature operation flag position in the first register can be set to "1", otherwise, the high temperature operation flag position in the first register is set to "0".

[0154] For example, the preset temperature threshold of the computer room can be set to 0-50°C, and the preset temperature threshold of the outside can be set to 0-65°C.

[0155] For example, the preset humidity threshold of the computer room may be set to 20-75% RH, and the preset humidity threshold of the outside may be set to 25-70% RH.

[0156] For example, the preset distance threshold may be set to 8 to 15 cm.

[0157] For example, the vibration parameters may include the escalator motor acceleration and the reduction gearbox acceleration, and the preset motor acceleration threshold may be set to -25 to 25 m / s 2, the preset reduction gearbox acceleration threshold can be set to -10~10m / s 2 .

[0158] In step S2232, the read temperature parameter, humidity parameter and vibration parameter are stored in different second registers respectively.

[0159] For example, the information processing module 1012 includes a plurality of second registers, including a register for storing temperature parameters, a register for storing humidity, and a register for storing vibration parameters, etc. In step S2232, the read temperature parameters, humidity parameters, and vibration parameters can be stored in the plurality of second registers, respectively.

[0160] Optionally, each second register may also be configured with a register storage content description, data type, coefficient, unit, etc.

[0161] Optionally, the information processing module 1012 also includes a register for storing module positions. For example, the first information processing module 1012 is located at the near end of the escalator, and the second information processing module 1012 is located in the escalator machine room, etc.

[0162] In some specific embodiments, the multiple information processing modules 1012 include a first information processing module 1012 and a second information processing module 1012, the first information processing module 1012 includes at least one first register and multiple second registers, the second information processing module 1012 is configured with a third register, and at least one operating parameter also includes a distance parameter between the escalator handrail and a reference point and an escalator fault code.

[0163] In an embodiment of the present disclosure, the second information processing module also includes at least one first register and multiple second registers, but the multiple second registers in the first information processing module may include a second register for storing distance parameters. The second information processing module 1012 does not set the second register for storing distance parameters, but instead sets a third register for storing escalator fault codes.

[0164] Figure 6 The second flowchart of storing operating parameters according to an embodiment of the present disclosure is schematically shown. Figure 6 As shown, for step S223, the first information processing module executes steps S2233 and S2234 in addition to step S2231, wherein step S2231 can be combined with step S2233 and step S2232 can be combined with step S2234.

[0165] In step S2233, when there is an abnormality in the distance parameter, the flag bit in the first register used to characterize the abnormality type is updated according to the existing abnormality.

[0166] For example, when the distance parameter is greater than a preset distance threshold, it can be determined that the armrest becomes loose (or tight), and thus, the flag position of the loose armrest (or tight armrest) in the first register can be set to "1".

[0167] In step S2234, the read temperature parameter, humidity parameter, vibration parameter and distance parameter are stored in different second registers respectively.

[0168] For example, the plurality of second registers include a register for storing temperature parameters, a register for storing humidity, a register for storing vibration parameters, and a register for storing distance parameters, etc. In step S2234, the read temperature parameters, humidity parameters, vibration parameters, and distance parameters may be stored in the plurality of second registers, respectively.

[0169] Figure 7 The third flowchart of storing operating parameters according to an embodiment of the present disclosure is schematically shown. Figure 7 As shown, for step S223, the second information processing module executes step S2235 in addition to steps S2231 and S2232.

[0170] In step S2235, according to the escalator fault code, the flag bit used to characterize the fault type in the third register is updated.

[0171] In the embodiment of the present disclosure, the third register is configured with multiple fault types and flags for each fault type. For example, according to the operating parameters that can be collected by the sensor 1011 in the embodiment of the present disclosure, the fault types are configured in the third register, which are SPE (speed abnormality), CTRE (controller abnormality), MO (motor abnormality) and GE (reduction gear box abnormality). The second information processing module 1012 sets the flag position of the corresponding fault type to "1" according to the acquired fault code, otherwise, sets the flag position to "0".

[0172] In some specific embodiments, the flag bits in the first register used to characterize the abnormality type include: at least one of: a speed abnormality flag bit, a controller abnormality flag bit, a motor abnormality flag bit, a reduction gear box abnormality flag bit, and a handrail belt system abnormality flag bit.

[0173] When there is an exception in the distance parameter, the flag bit used to characterize the exception type in the first register is updated according to the existing exception, including:

[0174] When the read operating parameter reaches a preset threshold, it is determined that an abnormality exists in the operating parameter, and a flag bit matching the abnormality in the first register is set to a first value.

[0175] In some specific embodiments, the escalator monitoring method further includes step S410.

[0176] In step S410, when it is determined that at least one operating parameter is invalid data, at least the sensor 1011 for collecting the operating parameter is reset.

[0177] In an embodiment of the present disclosure, a data anomaly flag can be configured in the first register of the information management module. If the monitoring module 1013 finds that the operating parameters are invalid data, the data anomaly flag in the first register can be modified by writing a single register instruction and setting it to "1" to achieve a software reset of all sensors 1011.

[0178] In the embodiment of the present disclosure, the data collected by the sensor 1011 at a high sampling frequency will inevitably be interfered and generate noise during transmission. In order to improve the sampling accuracy and data validity of the sensor 1011, the collected data can be processed by digital filtering.

[0179] Digital filtering is a supplement to hardware filtering. There are many types of escalator sensors 1011 with different transmission distances and complex installation environments. In order to avoid signal distortion caused by on-site environmental interference during data transmission, different digital filtering processes can be used for different sensors 1011.

[0180] In some specific embodiments, the monitoring module 1013 body is a Raspberry Pi 4B, and the monitoring module 1013 polls the register of the corresponding slave (such as the information processing module 1012 or the electronic energy meter 1014) through the Modbus-RTU protocol to obtain data. If only the operating parameters are obtained and forwarded, then the data processing will increase the computing pressure. Therefore, in the embodiment of the present disclosure, the monitoring module 1013 processes the operating parameters, specifically, the single duration of the current abnormal operating parameters and the cumulative total time of the abnormal operating parameters are counted, and then the escalator monitoring data is obtained.

[0181] Optionally, the monitoring module 1013 is set to start automatically when the computer is turned on. For example, the Python program of the monitoring module 1013 runs automatically after the computer is turned on.

[0182] Optionally, the monitoring module 1013 needs to unpack the received data after polling, that is, assign the elements of the tuple to corresponding variables in a preset order.

[0183] Figure 8 A flowchart of generating abnormal time information according to an embodiment of the present disclosure is schematically shown. Figure 8 As shown, in some specific embodiments, step S230 includes steps S231 to S235.

[0184] In step S231, when at least one flag bit of the first register in at least one information processing module 1012 includes the first value, at least one abnormality is determined, and it is determined whether there is an operating parameter exceeding a preset range among the operating parameters stored in the second register. Otherwise, the step ends.

[0185] In step S232, when there are operating parameters in the second register that are beyond the preset range, it is determined that there is an abnormality in the operating parameters. Otherwise, this step ends.

[0186] For the abnormal operating parameters, execute steps S233 to S235.

[0187] In step S233, the duration of the operation parameter exceeding the preset range is counted to obtain the single abnormal duration of the operation parameter.

[0188] In step S234, the single abnormal durations are summarized to obtain the cumulative abnormal duration of the operating parameter.

[0189] In step S235, the single abnormality duration and the cumulative abnormality duration constitute abnormality time information of the operating parameters.

[0190] In the embodiment of the present disclosure, for each operating parameter, the execution logic of the statistics of a single abnormal duration and a cumulative abnormal duration is substantially the same, and the following description is made taking the excessively high external ambient temperature as an example.

[0191] For example, when the temperature in the first register is too high, the abnormal flag is "1", and the temperature parameter in the second register is greater than the high temperature threshold, the Python3 time module can be called to complete the time statistics. For the duration of a single abnormality, the start time and end time of the temperature parameter being higher than the high temperature threshold can be counted, and the duration of the single abnormality can be calculated accordingly. After the first calculation of the duration of a single abnormality, the duration of the single abnormality calculated by the word can be used as the cumulative abnormality duration and stored. Afterwards, each time the duration of a single abnormality is calculated, the currently calculated duration of the single abnormality is added to the cumulative abnormality duration stored last time to obtain the latest cumulative abnormality duration.

[0192] In some specific embodiments, the plurality of operating parameters further include electrical parameters, which are read and stored by the electronic electric energy meter 1014 . Fig. 9 The second flowchart of generating abnormal time information according to an embodiment of the present disclosure is schematically shown. Fig. 9 As shown, step S230 also includes step S236 and step S237.

[0193] In step S237 , electrical parameters in the electronic electric energy meter 1014 are obtained.

[0194] In an embodiment of the present disclosure, the electrical parameters may include main circuit voltage, main circuit current, active power, power factor, and total energy consumption, etc.

[0195] In step S238, when there is an operating parameter exceeding the preset range in the second register and the electrical parameter meets the valid condition, a step of counting the duration of the operating parameter exceeding the preset range is performed. Otherwise, this step ends.

[0196] Optionally, the normal value range of the main circuit voltage can be set to 361~399V, the normal value range of the main circuit current can be set to 0~6A, the normal value of active power can be set to 0~4KW, the normal value range of reactive power can be set to 0~20var, and the normal value of power factor can be set to 0.75~0.95.

[0197] Taking the external environment temperature as an example, when the temperature abnormal flag in the first register is "1", and the temperature parameter in the second register is greater than the high temperature threshold, it is determined whether the active power is greater than 0. When the active power is greater than 0, it means that the escalator is in operation, otherwise it is in standby. When the above conditions are met, the Python3 time module can be called to complete the time statistics.

[0198] Optionally, the electrical parameters are stored in a register of the electronic energy meter 1014 , which also includes descriptions, data types, coefficients, units, etc.

[0199] In some specific embodiments, step S240 includes step S241.

[0200] In step S241, the escalator fault code in the third register in the second information processing module 1012 is obtained, and the escalator monitoring data and the escalator fault code are packaged and forwarded through MQTT.

[0201] In the embodiment of the present disclosure, the monitoring module 1013 determines the escalator fault code by judging the flag bit of the fault type in the third register obtained by the second information processing module 1012, and then determines whether the escalator has a specific fault.

[0202] In the embodiment of the present disclosure, the server agent used by MQTT is the cloud deployment server of EMQX. After the cloud deployment is completed, when the client initiates a connection, it is necessary to provide the deployment name, connection address and port number. In the access control, it is necessary to set the customer ID, subscription and publication topics, etc. for each client. Optionally, EMQX also provides a SQL rule engine, that is, the content forwarded by MQTT can be directly stored in the specified database, considering factors such as stability.

[0203] In the embodiment of the present disclosure, the sampling speed of the information processing module 1012 is relatively high. Due to the limitation of the transmission bandwidth, the monitoring module 1013 cannot directly forward the operating parameters from the information processing module 1012 through MQTT, and these operating parameters cannot intuitively reflect the operating status of the escalator. Therefore, in the embodiment of the present disclosure, the monitoring module 1013 processes these operating parameters to ensure that the transmitted data can reflect the operating status of the escalator to the greatest extent without very strict time requirements.

[0204] Some embodiments of the present disclosure also provide an escalator fault prediction method, which is applied to an escalator fault prediction device 102. Fig.10 The flowchart of the escalator fault prediction method in the embodiment of the present disclosure is schematically shown. Fig.10 As shown, the escalator fault prediction method of this embodiment includes step S310 and step S320.

[0205] In step S310 , escalator monitoring data is consumed from the message forwarding service end, where the escalator monitoring data includes abnormal time information of at least one operating parameter determined by the escalator monitoring device 101 .

[0206] In an embodiment of the present disclosure, the escalator fault prediction device 102 parses the MQTT data packet of the subscribed topic and transfers it to the MySQL database.

[0207] In an embodiment of the present disclosure, a database is created in MySQL, and the unpacked data is transferred to a main table in the database.

[0208] In step S320, the escalator failure is predicted based on the abnormal time information of the operating parameters using the pre-trained support vector machine model.

[0209] Support vector machine (SVM) is a binary classification model and a type of supervised learning algorithm in machine learning in the field of artificial intelligence. Its main function is to judge the possibility of the outcome of an event with only two possible outcomes, that is, to deal with the so-called binary classification problem. This type of problem is a widespread problem in reality and is also one of the main forms of pattern recognition. The main implementation method of traditional support vector machines is to select a hyperplane to split the sample data, and put forward requirements for the degree of segmentation, that is, the distance between the sample points closest to the hyperplane after the sample data is split needs to be the largest. These points closest to the hyperplane are called support vectors, and these support vectors in turn define the hyperplane. Support vector machines can be divided into three categories according to their types, namely hard margin support vector machines, soft margin support vector machines, and kernel function support vector machines.

[0210] Fig.11 A schematic diagram of determining a hyperplane according to an embodiment of the present disclosure is schematically shown. Fig.11 As shown in the figure, these data points are represented by white and black dots on the two-dimensional plane. Many straight lines in the figure (straight lines in two-dimensional space are hyperplanes in multi-dimensional space) separate these points, but only the segmentation plane represented by the dotted line has the best generalization ability. From the perspective of distance, it is to find a hyperplane so that the distance between the points on both sides of the hyperplane and the hyperplane is as large as possible, that is, the interval is maximized. The stronger the generalization ability of such a hyperplane is, the higher the confidence of the predicted sample after the model prediction is.

[0211] In the embodiment of the present disclosure, the escalator fault prediction device 102 is intended to subscribe to the escalator monitoring data published by the escalator monitoring device 101, and find a matching type of escalator fault based on the abnormal time information of one or more operating parameters in the escalator monitoring data (specifically, the single abnormal duration and cumulative abnormal duration of the operating parameters described in the above embodiment), thereby predicting the escalator fault.

[0212] Optionally, the embodiments of the present disclosure can predict at least five types of faults based on the escalator monitoring data, namely, abnormal escalator running speed, control unit damage, motor abnormality, reduction gearbox damage and handrail belt abnormality.

[0213] In some specific embodiments, the escalator fault prediction method further includes a support vector machine model training step. Fig.12 The flowchart of the support vector machine training in the embodiment of the present disclosure is schematically shown. Fig.12 As shown, the training step includes step S410 to step S440.

[0214] In step S410, the escalator monitoring data samples and escalator fault code samples forwarded by the escalator monitoring terminal are obtained.

[0215] In step S420, the support vector machine model to be trained is trained according to the acquired escalator monitoring data samples and escalator fault code samples.

[0216] In the embodiment of the present disclosure, the sensor 1011 collects the operating parameters that are critical to the operation of the escalator, which are the tightness of the handrail, the ambient temperature and humidity of the escalator, the temperature and humidity of the escalator machine room, the vibration of the reduction gear box and the motor, and the real-time power of the escalator main circuit and other escalator operation related electrical parameters. The monitoring module 1013 can poll the information of all slaves (information processing module 1012 and electronic electric energy meter 1014). However, the monitoring module 1013 does not directly upload the collected real-time operating parameters to the escalator fault prediction device 102. The reason is that the bandwidth limitation of MQTT cannot form a high-speed transmission of the big data stream between the monitoring module 1013 and the escalator fault prediction device 102. At the same time, the real-time operating parameters of the escalator cannot intuitively reflect the quality of the escalator operation status. Therefore, the embodiment of the present disclosure introduces the concept of abnormal time information. When the real-time operating parameters of the escalator are transferred through the monitoring module 1013, the single abnormal duration and the cumulative abnormal duration of the currently abnormal operating parameters are screened through the reasonable range of each operating parameter set in advance. The escalator fault prediction device 102 receives and transfers the messages published by the monitoring module 1013 to the database after subscribing to the relevant topics through MQTT. The combined sample data corresponding to the abnormal time information of various abnormalities received and the escalator fault code are used as the input for the support vector machine model training. After the model training is completed, the abnormal time information of the escalator's current abnormal operating parameters is used as input to obtain the predicted probability of occurrence of the fault.

[0217] The embodiment of the present disclosure solves the problems of collecting, organizing and analyzing the operating parameters of the escalator, and can provide data support for on-demand maintenance. The embodiment of the present disclosure reasonably selects the sensor 1011, and realizes the networking with the monitoring module 1013 through the information management module to process and transmit the operating parameters collected by these sensors 1011 to the monitoring module 1013.

[0218] The embodiment of the present disclosure realizes the networking of the information management module with the monitoring module 1013 and the data forwarding between the monitoring module 1013 and the escalator fault prediction device 102 through communication protocols such as Modbus and MQTT, thereby ensuring stable data stream transmission.

[0219] The embodiment of the present disclosure combines data such as the single abnormal duration and the cumulative abnormal duration of the operating parameters with the support vector machine, trains the fault prediction model through the data with fault labels, and thus realizes the function of fault prediction. The embodiment of the present disclosure can predict the escalator's operating speed abnormality, control unit abnormality, motor abnormality, reduction gear box abnormality, and handrail belt system abnormality by sorting and analyzing the operating parameters collected by the sensor 1011.

[0220] Some embodiments of the present disclosure also disclose an escalator fault prediction method, which is applied to an escalator fault prediction device. Figure 1 , Figure 2 and Fig.10 As shown, the escalator fault prediction device includes an escalator monitoring device 101 and an escalator fault prediction device 102 , the escalator monitoring device 101 includes a plurality of information processing modules 1012 , and the escalator fault prediction method includes steps S210 to S240 executed by the escalator monitoring device 101 .

[0221] In step S210, a plurality of operating parameters of the escalator are collected.

[0222] In step S220, at least one of the plurality of information processing modules 1012 executes a first preset operation to store the currently collected operating parameters, wherein different information processing modules 1012 store at least one different operating parameter.

[0223] In step S230, the operation parameters stored in the plurality of information processing modules 1012 are polled, and at least one abnormal operation parameter and abnormal time information of the operation parameter are determined according to the polling result to obtain escalator monitoring data.

[0224] In step S240, the escalator monitoring data is published to the message forwarding server.

[0225] The escalator fault prediction method further includes the following steps performed by the escalator fault prediction device 102:

[0226] In step S310, escalator monitoring data is consumed from the message forwarding service end.

[0227] In step S320, the escalator failure is predicted based on the abnormal time information of the operating parameters using the pre-trained support vector machine model.

[0228] Based on the above escalator monitoring method, the present disclosure also provides an escalator monitoring device. Fig.13 The device is described in detail.

[0229] Fig.13 The structural block diagram of the escalator monitoring device according to an embodiment of the present disclosure is schematically shown.

[0230] like Fig.13 As shown, the escalator monitoring device 101 of this embodiment includes multiple sensors 1011, multiple information processing modules 1012 and a monitoring module 1013.

[0231] The multiple sensors 1011 are used to collect multiple operating parameters of the escalator. In one embodiment, the sensors 1011 can be used to perform the step S210 described above, which will not be described in detail here.

[0232] The plurality of information processing modules 1012 are used to perform the first preset operation to store the currently collected operating parameters, wherein different information processing modules 1012 store at least one different operating parameter. In one embodiment, the information processing module 1012 can be used to perform the step S220 described above, which will not be described in detail here.

[0233] The monitoring module 1013 is used to poll the operating parameters stored in the multiple information processing modules 1012, and determine at least one abnormal operating parameter and abnormal time information of the operating parameter according to the polling result to obtain escalator monitoring data.

[0234] The escalator monitoring data is published to the message forwarding server, and the escalator monitoring data is configured to enable the escalator fault prediction device to predict the escalator fault based on the escalator monitoring data based on the support vector machine. In one embodiment, the monitoring module 1013 can be used to execute the steps S230 and S240 described above, which will not be repeated here.

[0235] According to an embodiment of the present disclosure, any multiple modules in the information processing module 1012 and the monitoring module 1013 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the information processing module 1012 and the monitoring module 1013 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one of the information processing module 1012 and the monitoring module 1013 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be executed.

[0236] Based on the above escalator fault prediction method, the present disclosure also provides an escalator fault prediction device. Fig.14 The device is described in detail.

[0237] Fig.14 The structural block diagram of the escalator fault prediction device according to an embodiment of the present disclosure is schematically shown.

[0238] like Fig.14 As shown, the escalator fault prediction device 102 of this embodiment includes a first acquisition module 1021 and a prediction module 1022 .

[0239] The first acquisition module 1021 is used to consume escalator monitoring data from the message forwarding server, and the escalator monitoring data includes abnormal time information of at least one operating parameter determined by the escalator monitoring terminal. In one embodiment, the first acquisition module 1021 can be used to execute step S310 described above, which will not be repeated here.

[0240] The prediction module 1022 is used to predict the failure of the escalator according to the abnormal time information of the operating parameters through the pre-trained support vector machine model. In one embodiment, the prediction module 1022 can be used to execute the step S320 described above, which will not be repeated here.

[0241] According to an embodiment of the present disclosure, any multiple modules in the first acquisition module 1021 and the prediction module 1022 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first acquisition module 1021 and the prediction module 1022 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one of the first acquisition module 1021 and the prediction module 1022 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be performed.

[0242] The present disclosure also provides an escalator fault prediction device, combined with Figure 1 , Fig.13 and Fig.14As shown, the escalator fault prediction device 100 includes an escalator monitoring device 101 and an escalator fault prediction device 102. The escalator monitoring device 101 includes multiple sensors 1011, multiple information processing modules 1012 and a monitoring module 1013. The escalator fault prediction device 102 includes a first acquisition module 1021 and a prediction module 1022.

[0243] The multiple sensors 1011 are used to collect multiple operating parameters of the escalator.

[0244] The multiple information processing modules 1012 are used to execute a first preset operation to store the currently collected operating parameters, wherein different information processing modules 1012 store at least one different operating parameter.

[0245] The monitoring module 1013 is used to poll the operating parameters stored in the multiple information processing modules 1012, and determine at least one abnormal operating parameter and abnormal time information of the operating parameter according to the polling result to obtain escalator monitoring data.

[0246] The forwarding module is used to publish escalator monitoring data to the message forwarding server.

[0247] The first acquisition module is used to consume escalator monitoring data from the message forwarding service end.

[0248] The prediction module is used to predict escalator failures based on abnormal time information of operating parameters using a pre-trained support vector machine model.

[0249] Fig.15 A block diagram of an electronic device suitable for implementing an escalator monitoring method or an escalator fault prediction method according to an embodiment of the present disclosure is schematically shown.

[0250] like Fig.15 As shown, the electronic device 200 according to an embodiment of the present disclosure includes a processor 201, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 202 or a program loaded from a storage part 208 to a random access memory (RAM) 203. The processor 201 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 201 may also include an onboard memory for caching purposes. The processor 201 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0251] In RAM 203, various programs and data required for the operation of electronic device 200 are stored. Processor 201, ROM 202 and RAM 203 are connected to each other via bus 204. Processor 201 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 202 and / or RAM 203. It should be noted that the program can also be stored in one or more memories other than ROM 202 and RAM 203. Processor 201 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0252] According to an embodiment of the present disclosure, the electronic device 200 may further include an input / output (I / O) interface 205, which is also connected to the bus 204. The electronic device 200 may further include one or more of the following components connected to the I / O interface 205: an input portion 206 including a keyboard, a mouse, etc.; an output portion 207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 208 including a hard disk, etc.; and a communication portion 209 including a network interface card such as a LAN card, a modem, etc. The communication portion 209 performs communication processing via a network such as the Internet. A drive 210 is also connected to the I / O interface 205 as needed. A removable medium 211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 210 as needed, so that a computer program read therefrom is installed into the storage portion 208 as needed.

[0253] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0254] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 202 and / or RAM 203 described above and / or one or more memories other than ROM 202 and RAM 203.

[0255] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the item recommendation method provided by the embodiment of the present disclosure.

[0256] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 201. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0257] In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and downloaded and installed through the communication part 209, and / or installed from the removable medium 211. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0258] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 209, and / or installed from the removable medium 211. When the computer program is executed by the processor 201, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0259] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0260] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0261] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0262] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. An escalator monitoring method, applied to an escalator monitoring device, characterized in that: The escalator monitoring device includes a plurality of information processing modules, and the escalator monitoring method includes: Collect multiple operating parameters of escalators; At least one of the plurality of information processing modules performs a first preset operation to store the currently collected operating parameters, wherein different information processing modules store at least one different operating parameter; Polling the operating parameters stored in the plurality of information processing modules, and determining at least one abnormal operating parameter and abnormal time information of the operating parameter according to the polling result, so as to obtain escalator monitoring data; The escalator monitoring data is published to a message forwarding service end, and the escalator monitoring data is configured to enable an escalator fault prediction device to predict escalator faults based on the escalator monitoring data based on a support vector machine.

2. The escalator monitoring method according to claim 1, characterized in that: The first preset operation includes: Creating at least one reading thread for at least one operating parameter; Reading the operating parameter from a sensor that collects the operating parameter through at least one of the reading threads; The operating parameters read are stored in different registers respectively through the main thread.

3. The escalator monitoring method according to claim 2, characterized in that: At least one of the information processing modules includes at least one first register and a plurality of second registers, and at least one of the operating parameters includes a temperature parameter, a humidity parameter, and a vibration parameter; The storing the read operating parameters into different registers respectively through the main thread includes: When at least one of the temperature parameter, the humidity parameter, and the vibration parameter is abnormal, updating a flag bit in the first register for indicating the abnormal type according to the abnormality; The read temperature parameter, humidity parameter and vibration parameter are stored in different second registers respectively.

4. The escalator monitoring method according to claim 3, characterized in that: The plurality of information processing modules include a first information processing module and a second information processing module, the first information processing module includes at least one of the first register and a plurality of the second registers, the second information processing module is configured with a third register, and at least one of the operating parameters further includes a distance parameter between the handrail of the escalator and a reference point and an escalator fault code; The storing the read operating parameters into different registers respectively through the main thread also includes the following steps performed by the first information processing module: When there is an abnormality in the distance parameter, updating a flag bit in the first register for indicating the type of abnormality according to the existing abnormality; storing the read temperature parameter, humidity parameter, vibration parameter and distance parameter in different second registers respectively; The storing the read operating parameters into different registers respectively through the main thread also includes the following steps performed by the second information processing module: According to the escalator fault code, a flag bit in the third register used to characterize the fault type is updated.

5. The escalator monitoring method according to claim 3, characterized in that: The flag bit used to characterize the abnormality type in the first register includes: at least one of a speed abnormality flag bit, a controller abnormality flag bit, a motor abnormality flag bit, a reduction gear box abnormality flag bit, and a handrail belt system abnormality flag bit; When the distance parameter is abnormal, updating the flag bit in the first register for representing the abnormal type according to the abnormality includes: When the read operating parameter reaches a preset threshold, it is determined that an abnormality exists in the operating parameter, and a flag bit in the first register that matches the abnormality is set to a first value.

6. The escalator monitoring method according to claim 3, characterized in that: The escalator monitoring method also includes: When it is determined that at least one of the operating parameters is invalid data, at least a sensor for collecting the operating parameter is reset.

7. The escalator monitoring method according to claim 2, characterized in that: At least one of the reading threads includes a vibration sensor reading thread and a temperature and humidity sensor reading thread with decreasing priorities, and the priority of the main thread is higher than that of the vibration sensor reading thread.

8. The escalator monitoring method according to claim 7, characterized in that: At least one of the reading threads further includes a fault code reading thread, the priority of the fault code reading thread is between the vibration sensor reading thread and the temperature and humidity sensor reading thread; and / or, At least one of the reading threads further includes a distance measuring sensor data reading thread, and a priority of the distance measuring sensor data reading thread is between the vibration sensor reading thread and the temperature and humidity sensor reading thread.

9. The escalator monitoring method according to claim 2, characterized in that: The first preset operation also includes: The reading thread sends a pointer to the main thread via a mailbox, wherein the pointer points to a temporary storage address of the operating parameter read by the reading thread; The main thread obtains the operating parameters read by the reading thread according to the temporary storage address, and stores the operating parameters in a register.

10. The escalator monitoring method according to claim 7, characterized in that: The polling of the operating parameters stored in the plurality of information processing modules and determining at least one abnormal operating parameter and abnormal time information of the operating parameter according to the polling result to obtain escalator monitoring data includes: When at least one flag bit of the first register in at least one information processing module includes the first value, at least one abnormality is determined, and it is determined whether any of the operating parameters stored in the second register exceeds a preset range; When there is an operating parameter in the second register that exceeds the preset range, determining that the operating parameter is abnormal; For abnormal operating parameters, Counting the duration of the operation parameter exceeding the preset range to obtain a single abnormal duration of the operation parameter; Summarizing the single abnormal durations to obtain a cumulative abnormal duration of the operating parameter; The single abnormality duration and the cumulative abnormality duration constitute the abnormality time information of the operating parameter.

11. The escalator monitoring method according to claim 10, characterized in that: The plurality of operating parameters also include electrical parameters, which are read and stored by an electronic electric energy meter; The polling of the operating parameters stored in the plurality of information processing modules and determining at least one abnormal operating parameter and abnormal time information of the operating parameter according to the polling result to obtain escalator monitoring data further includes: Obtaining electrical parameters in the electronic electric energy meter; When there is an operating parameter exceeding the preset range in the second register and the electrical parameter meets the validity condition, the step of counting the duration of the operating parameter exceeding the preset range is performed.

12. The escalator monitoring method according to claim 4, characterized in that: The step of publishing the escalator monitoring data to the message forwarding server includes: The escalator fault code in the third register in the second information processing module is obtained, and the escalator monitoring data and the escalator fault code are packaged and forwarded through MQTT.

13. An escalator fault prediction method, applied to an escalator fault prediction device, characterized in that: The escalator fault prediction method comprises: consuming escalator monitoring data from a message forwarding service end, the escalator monitoring data including abnormal time information of at least one operating parameter determined by the escalator monitoring end; The escalator failure is predicted based on the abnormal time information of the operating parameters through the pre-trained support vector machine model.

14. The escalator failure prediction method according to claim 13, characterized in that: The escalator fault prediction method further includes a training step of the support vector machine model, wherein the training step includes: Obtain escalator monitoring data samples and escalator fault code samples forwarded by the escalator monitoring terminal; The support vector machine model to be trained is trained according to the acquired escalator monitoring data samples and the escalator fault code samples.

15. An escalator fault prediction method, applied to an escalator fault prediction device, characterized in that: The escalator fault prediction device comprises an escalator monitoring device and an escalator fault prediction device, the escalator monitoring device comprises a plurality of information processing modules, and the escalator fault prediction method comprises the following steps performed by the escalator monitoring device: The escalator monitoring terminal includes a plurality of information processing modules, and the escalator monitoring method includes: Collect multiple operating parameters of escalators; At least one of the plurality of information processing modules performs a first preset operation to store the currently collected operating parameters, wherein different information processing modules store at least one different operating parameter; Polling the operating parameters stored in the plurality of information processing modules, and determining at least one abnormal operating parameter and abnormal time information of the operating parameter according to the polling result, so as to obtain escalator monitoring data; Publishing the escalator monitoring data to a message forwarding server; The escalator fault prediction method further comprises the following steps performed by the escalator fault prediction device: Consuming the escalator monitoring data from the message forwarding server; The escalator failure is predicted based on the abnormal time information of the operating parameters through the pre-trained support vector machine model.

16. An escalator monitoring device, characterized in that: The escalator monitoring device includes multiple sensors, multiple information processing modules, a monitoring module and a forwarding module; Multiple sensors are used to collect multiple operating parameters of the escalator; The plurality of information processing modules are used to execute a first preset operation to store the currently collected operating parameters, wherein different information processing modules store at least one different operating parameter; The monitoring module is used to poll the operating parameters stored in the plurality of information processing modules, and determine at least one abnormal operating parameter and abnormal time information of the operating parameter according to the polling result, so as to obtain escalator monitoring data; The forwarding module is used to publish the escalator monitoring data to the message forwarding service end, and the escalator monitoring data is configured to enable the escalator fault prediction device to predict escalator faults based on the escalator monitoring data based on a support vector machine.

17. An escalator fault prediction device, characterized in that: The escalator fault prediction device comprises a first acquisition module and a prediction module; The first acquisition module is used to consume escalator monitoring data from the message forwarding service end, and the escalator monitoring data includes abnormal time information of at least one of the operating parameters determined by the escalator monitoring end; The prediction module is used to predict the failure of the escalator according to the abnormal time information of the operating parameters through a pre-trained support vector machine model.

18. An escalator fault prediction device, characterized in that: The escalator fault prediction device comprises an escalator monitoring device and an escalator fault prediction device, wherein the escalator monitoring device comprises a plurality of sensors, a plurality of information processing modules, a monitoring module and a forwarding module, and the escalator fault prediction device comprises a first acquisition module and a prediction module; Multiple sensors are used to collect multiple operating parameters of the escalator; The plurality of information processing modules are used to execute a first preset operation to store the currently collected operating parameters, wherein different information processing modules store at least one different operating parameter; The monitoring module is used to poll the operating parameters stored in the plurality of information processing modules, and determine at least one abnormal operating parameter and abnormal time information of the operating parameter according to the polling result, so as to obtain escalator monitoring data; The forwarding module is used to publish the escalator monitoring data to the message forwarding server; The first acquisition module is used to consume escalator monitoring data from the message forwarding server; The prediction module is used to predict the failure of the escalator according to the abnormal time information of the operating parameters through a pre-trained support vector machine model.

19. A computer-readable storage medium, characterized in that: Executable instructions are stored thereon, and when the instructions are executed by the processor, the processor executes the escalator monitoring method according to any one of claims 1 to 12 or the escalator fault prediction method according to any one of claims 13 to 15.

20. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the escalator monitoring method according to any one of claims 1 to 12 or the escalator fault prediction method according to any one of claims 13 to 15.

Images