KR20230135198A - Apparatus and method for detecting failure prediction of construction heavy equipment - Google Patents

Abstract

It relates to a device and method for predicting failure of the control unit through monitoring the PLC (Programmable Logic Controller) device of heavy construction equipment, including collecting control data from the PLC (Programmable Logic Controller) of construction equipment, and classifying the collected control data by characteristics. Classifying, identifying an error signal from the classified control data, calculating an error frequency based on the identified error signal, calculating an error frequency for the control data based on the calculated error frequency. It may include predicting a failure probability for the control device of the heavy construction equipment by analyzing trends, and notifying the failure prediction of the control device based on the predicted failure probability.

Description

Failure prediction device and method for heavy construction equipment {APPARATUS AND METHOD FOR DETECTING FAILURE PREDICTION OF CONSTRUCTION HEAVY EQUIPMENT}

The present invention relates to a failure prediction device for heavy construction equipment, and more specifically, to a failure prediction device and method for heavy construction equipment for predicting failure of the control unit through monitoring the PLC (Programmable Logic Controller) device of the heavy construction equipment.

In general, heavy construction equipment is used for work that is very dangerous due to the nature of equipment operation or requires heavy momentum that is difficult to handle with human power, so it includes devices with various special functions.

These devices with various functions can be controlled through control devices such as control levers or control buttons disposed for each device.

However, existing heavy construction equipment has a physically expanded structure in which corresponding control devices are added whenever devices performing special functions are added, so it takes a lot of time and money to manage each control device. There was a problem.

Additionally, due to the nature of heavy construction equipment, if the control device does not operate correctly or operates abnormally, a situation is bound to occur in which the safety of workers as well as workers related to industrial equipment or heavy construction equipment is seriously threatened.

Therefore, in the future, there is a need to develop a failure prediction device that can efficiently manage multiple control devices deployed in construction equipment and at the same time detect and monitor failure signs of the control devices in advance.

Republic of Korea Patent No. 10-1678027 (November 15, 2016)

The technical problem to be achieved by an embodiment of the present invention is to collect control data from the PLC (Programmable Logic Controller) of heavy construction equipment, analyze the trend of error occurrence frequency in the control data, and detect and monitor failure signs of the control device in advance. The goal is to provide a device and method for predicting failure of heavy construction equipment.

The technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below. You will be able to.

In order to solve the above technical problems, a method for predicting failure of heavy construction equipment according to an embodiment of the present invention includes collecting control data from a PLC (Programmable Logic Controller) of heavy construction equipment, and characterizing the collected control data. Classifying by category, identifying an error signal from the classified control data, calculating an error frequency based on the identified error signal, and generating an error for the control data based on the calculated error frequency. It may include predicting a failure probability for the control device of the heavy construction equipment by analyzing frequency trends, and notifying the failure prediction of the control device based on the predicted failure probability.

In an alternative embodiment of the method for predicting failure of heavy construction equipment, the step of collecting the control data includes performing a communication connection with the PLC of the heavy construction equipment, and when communication is connected with the PLC of the heavy construction equipment, the PLC of the heavy construction equipment is connected to the PLC of the heavy construction equipment. Control data corresponding to the control device of the heavy construction equipment is requested, and when control data corresponding to the control device is received from the PLC of the heavy construction equipment, the received control data can be collected.

In an alternative embodiment of the method for predicting failure of heavy construction equipment, the step of collecting the control data may be accomplished through a wired communication connection through an Ethernet or serial communication port of the PLC, or through a wireless communication connection through a network communication port.

In an alternative embodiment of the method for predicting failure of heavy construction equipment, the step of classifying the collected control data by characteristics includes parsing the collected control data by header to identify the control data, and storing the identified control data in the Heavy construction equipment can be classified by control device.

In an alternative embodiment of the method for predicting failure of heavy construction equipment, the step of classifying the collected control data by characteristics includes calculating the importance of the classified control data and identifying the error signal based on the calculated importance. Control data can be selected for

In an alternative embodiment of the method for predicting failure of heavy construction equipment, the step of identifying the error signal includes checking whether an abnormal signal value or an error identification signal value exists within a data block from the classified control data, and determining whether an abnormal signal value or an error identification signal value exists within the data block. If the abnormal signal value or error identification signal value exists, the control data can be recognized as containing an error.

In an alternative embodiment of the method for predicting failure of heavy construction equipment, the step of checking whether the abnormal signal value exists includes comparing the data in the data block with preset normal data and, if the data is different from the normal data, the data block It can be recognized that an abnormal signal value exists within.

In an alternative embodiment of the method for predicting failure of heavy construction equipment, the step of checking whether the error identification signal value exists includes checking whether an error identification value having 0 or a negative number exists in the data block, and determining whether the 0 or negative number exists. If an error identification value exists, it can be recognized that an error identification signal value exists in the data block.

In an alternative embodiment of the method for predicting failure of heavy construction equipment, the step of calculating the error occurrence frequency is performed under any one of a first condition in which the error signal occurs in the same data and a second condition in which the error signal occurs in the same location. If satisfied, it can be calculated by increasing the error occurrence frequency for the corresponding control data by 1.

In an alternative embodiment of the method for predicting failure of heavy construction equipment, the step of calculating the error frequency occurs when both the first condition that the error signal occurs from the same data and the second condition that the error signal occurs at the same location are satisfied. It can be calculated by increasing the error occurrence frequency for control data by 1.

In an alternative embodiment of the method for predicting failure of heavy construction equipment, the step of predicting the failure probability includes at least one of an error occurrence continuation rate, an error occurrence cycle, and an error occurrence increase rate for a preset period based on the error occurrence frequency. The probability of failure for the control device can be predicted by analyzing the error occurrence frequency trend including the elements.

In an alternative embodiment of the method for predicting failure of heavy construction equipment, the step of predicting the failure probability includes inputting the error occurrence frequency into a pre-trained neural network model to analyze the trend of error occurrence frequency for the control data and predicting the failure probability. The failure probability of heavy equipment control devices can be predicted.

In an alternative embodiment of the method for predicting failure of heavy construction equipment, the step of notifying the failure prediction of the control device includes generating and providing notification information including the predicted failure control device information and failure probability information to prevent the failure of the control device. Predictions can be made known.

Meanwhile, a failure prediction device for heavy construction equipment according to an embodiment of the present invention is a failure prediction device for heavy construction equipment to provide a method for predicting failure of heavy construction equipment, and includes a processor including one or more cores, and a memory, The processor collects control data from the PLC (Programmable Logic Controller) of the heavy construction equipment, classifies the collected control data by characteristics, identifies an error signal from the classified control data, and detects the identified error signal. Based on this, the error occurrence frequency is calculated, the error occurrence frequency trend for the control data is analyzed based on the calculated error occurrence frequency, the failure probability of the control device of the heavy construction equipment is predicted, and the predicted failure probability is calculated. Based on this, the failure prediction of the control device can be announced.

The effects of the failure prediction device and method for heavy construction equipment according to the present invention will be described as follows.

The present invention collects control data from the PLC of heavy construction equipment and analyzes trends in the error occurrence frequency of the control data to detect and monitor failure signs of the control device in advance.

In addition, the present invention can detect and monitor failure signs of PLC-based control devices in advance, thereby improving safety at industrial and construction sites, and detecting signs of failure in advance to ensure equipment safety. It can operate more safely and smoothly, increasing productivity.

Further scope of applicability of the present invention will become apparent from the detailed description that follows. However, since various changes and modifications within the spirit and scope of the present invention may be clearly understood by those skilled in the art, the detailed description and specific embodiments such as preferred embodiments of the present invention should be understood as being given only as examples.

1 is a diagram for explaining a failure prediction device for heavy construction equipment according to the present invention.
Figure 2 is a schematic diagram showing a network function of a neural network model, according to an embodiment of the present invention.
Figure 3 is a flowchart illustrating a method for predicting failure of heavy construction equipment according to the present invention.

Hereinafter, the present invention will be described in more detail with reference to the drawings.

The suffixes “module” and “part” for the components used in the following description are simply given in consideration of the ease of writing this specification, and the “module” and “part” may be used interchangeably.

Furthermore, embodiments of the present invention will be described in detail below with reference to the accompanying drawings and the contents described in the accompanying drawings, but the present invention is not limited or limited by the embodiments.

The terms used in this specification are general terms that are currently widely used as much as possible while considering the function in the present invention, but this may vary depending on the intention or custom of a person skilled in the art or the emergence of new technology. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in this case, the meaning will be described in the description of the relevant invention. Therefore, we would like to clarify that the terms used in this specification should be interpreted based on the actual meaning of the term and the overall content of this specification, not just the name of the term.

Additionally, throughout this specification, neural network, neural network, and network function may be used with the same meaning. A neural network may consist of a set of interconnected computational units, which can generally be referred to as “nodes.” These “nodes” may also be referred to as “neurons.” A neural network is composed of at least two or more nodes. The nodes (or neurons) that make up neural networks may be interconnected by one or more “links.”

1 is a diagram for explaining a failure prediction device for heavy construction equipment according to the present invention.

As shown in FIG. 1, the failure prediction device 100 of the present invention may be connected to heavy construction equipment 200 for communication.

Here, the construction equipment 200 includes a control device 220 that controls the operation of the device based on data received from the power unit 210, and a PLC (Programmable Logic Controller) 230 that controls the control device 220. ) may include.

In addition, the PLC 230 of the construction equipment 200 is connected to the failure prediction device 100 of the present invention and can transmit control data of the control device 220.

The failure prediction device 100 of the present invention may include other configurations for performing a computing environment, and only some of the disclosed configurations may constitute the failure prediction device 100.

The failure prediction device 100 may include a processor 110, a memory 130, and a network unit 150.

In the present invention, the processor 110 collects control data from the PLC 230 of the construction equipment 200, classifies the collected control data by characteristics, identifies error signals from the classified control data, and identifies The error occurrence frequency is calculated based on the error signal, and the error occurrence frequency trend for the control data is analyzed based on the calculated error occurrence frequency to predict the failure probability of the control device of heavy construction equipment, based on the predicted failure probability. This can inform the failure prediction of the control device.

And, when collecting control data, the processor 110 performs a communication connection with the PLC 230 of the heavy construction equipment 200, and when connected to the PLC 230 of the heavy construction equipment 200, the heavy construction equipment 200 ) requests control data corresponding to the control device 220 of the heavy construction equipment 200 from the PLC 230, and receives control data corresponding to the control device 220 from the PLC 230 of the heavy construction equipment 200. This allows you to collect the received control data.

As an example, when collecting control data, the processor 110 may be connected to wired communication through an Ethernet or serial communication port of the PLC 230, or may be connected to wireless communication through a network communication port, which is one embodiment. However, it is not limited to this.

Additionally, when collecting control data, the processor 110 may collect control data by being connected to a single PLC 230 if there is only one PLC 230 of the heavy construction equipment 200.

In some cases, when collecting control data, if there are multiple PLCs 230 of the heavy construction equipment 200, the processor 110 may be connected to the plurality of PLCs 230 and collect control data for each PLC. there is.

Here, when the processor 110 collects control data, if there is a plurality of PLCs 230 of the heavy construction equipment 200, the plurality of PLCs 230 are connected sequentially according to a preset priority to collect control data. It can be collected.

For example, when setting priorities, the processor 110 determines the operation time, operation risk, operation error rate, and number of control devices connected to each PLC 230 of the control devices 220 included in the heavy construction equipment 200. Priority can be set based on at least one of the conditions.

For example, when the processor 110 sets the priority, the order in which communication is connected to the PLC 230 of the control device 220 with a large operating time is the PLC 230 of the control device 220 with a small operating time. It may be faster than the order of communication connection.

In some cases, when the processor 110 sets the priority, the order in which communication is connected to the PLC 230 of the control device 220 with a high operational risk is the PLC 230 of the control device 220 with a low operational risk. It may be faster than the order of communication connection.

In another case, when setting the priority, the processor 110 determines that the order in which communication is connected to the PLC 230 of the control device 220 with a high operation error rate is the PLC of the control device 220 with a low operation error rate ( 230) may be faster than the communication connection sequence.

As another case, when the processor 110 sets the priority, the order in which the processor 110 communicates with the PLC 230 connected to a large number of control devices 200 is the PLC connected to a small number of control devices 200. It may be faster than the order of communication connection to (230).

Next, when classifying the collected control data by characteristics, the processor 110 parses the collected control data by header to identify the control data, and classifies the identified control data by control device of the heavy construction equipment 200. You can.

Here, when classifying the collected control data by characteristics, the processor 110 may calculate the importance of the classified control data and select control data for identifying an error signal based on the calculated importance.

For example, when calculating the importance, the processor 110 may calculate the importance based on at least one of the following conditions: the operation time of the control device 220, the operation risk, and the operation error rate.

For example, when the processor 110 calculates the importance, the control device 220 with a long operation time may have a higher importance than the control device 220 with a small operation time.

In some cases, when calculating the importance, the processor 110 may assign a higher importance to the control device 220 with a high operational risk than the control device 220 with a low operational risk.

As another case, when calculating the importance, the processor 110 may assign a higher importance to the control device 220 with a high operational error rate than the control device 220 with a low operational error rate.

Additionally, when selecting control data for identifying an error signal, the processor 110 selects control data for identifying an error signal if the calculated importance is greater than or equal to a preset reference value, and selects the control data for identifying the error signal if the calculated importance is less than the preset reference value. If , it may not be selected as control data to identify the error signal.

Next, when classifying the collected control data by characteristics, the processor 110 may classify the collected control data by control device of the heavy construction equipment 200 using the K-means algorithm. This is only an example and is not limited thereto.

Next, when identifying an error signal, the processor 110 checks whether an abnormal signal value or an error identification signal value exists in the data block from the classified control data, and determines whether the abnormal signal value or an error identification signal value exists in the data block. If exists, the control data can be recognized as containing an error.

Here, when checking the presence or absence of an abnormal signal value, the processor 110 compares the data in the data block with preset normal data, and if the data is different from the normal data, it may recognize that an abnormal signal value exists in the data block. .

In some cases, when checking the presence or absence of an error identification signal value, the processor 110 checks whether an error identification value with 0 or a negative number exists in the data block, and if an error identification value with 0 or a negative number exists, the data block It can be recognized that an error identification signal value exists within the block.

And, when calculating the error occurrence frequency, the processor 110 determines whether an error signal is generated from the same data if it satisfies any one of the first condition and the second condition that the error signal occurs at the same location. It can be calculated by increasing the error occurrence frequency by 1.

In some cases, when calculating the error occurrence frequency, the processor 110 generates an error for the corresponding control data if both the first condition that the error signal occurs in the same data and the second condition that the error signal occurs in the same location are satisfied. It can be calculated by increasing the frequency by 1.

Next, when calculating the error occurrence frequency, the processor 110 may classify and store the error occurrence frequency by control data of each control device.

Here, when the processor 110 classifies and stores the error occurrence frequency by control data of each control device, the processor 110 may accumulate and store the error occurrence frequency corresponding to each control data by hour, date, month, and year.

Next, when predicting the failure probability, the processor 110 determines an error occurrence frequency trend that includes at least one element of the error occurrence rate, error occurrence cycle, and error occurrence increase rate for a preset period based on the error occurrence frequency. Through analysis, the failure probability of the control device can be predicted.

Here, when predicting the probability of failure, the processor 110 may predict that the probability of failure for the control device increases as the error occurrence rate during a preset period increases.

In some cases, when predicting the probability of failure, the processor 110 may predict that the probability of failure for the control device increases as the error occurrence period during a preset period becomes shorter.

In another case, when predicting the probability of failure, the processor 110 may predict that the probability of failure for the control device increases as the increase rate of error occurrence during a preset period increases.

In addition, when predicting the failure probability, the processor 110 inputs the error occurrence frequency into a pre-trained neural network model to analyze the error occurrence frequency trend for control data and predict the failure probability for the control device of heavy construction equipment. there is.

Here, the pre-trained neural network model takes the error occurrence frequency as an input and analyzes the error occurrence frequency trend including at least one of the error occurrence rate, error occurrence cycle, and error occurrence increase rate during a preset period to control the error occurrence frequency trend. You can learn in advance to predict the probability of failure.

Next, when predicting the failure probability, the processor 110 determines a normal level ranging from 0 to 4%, a caution level ranging from 5% to 29%, a warning level ranging from 30% to 69%, and a warning level ranging from 70% to 70%. It is possible to predict a failure probability including any one failure level among risk levels with a 100% range, but this is only an example and is not limited thereto.

Here, when predicting the failure probability, the processor 110 may check whether the predicted failure probability is at a normal level, and if it is not at a normal level, the processor 110 may classify the corresponding control device as a control device that can fail.

Next, when notifying the failure prediction of the control device, the processor 110 may generate and provide notification information including the predicted failure control device information and failure probability information to inform the failure prediction of the control device.

For example, when notifying the failure prediction of the control device 220, the processor 110 may use a first notification method to output a specific sound through a speaker, a second notification method to vibrate a vibrator, and a third notification method to turn on/off a warning light. Abnormal signs of the control device 200 can be notified by at least one of the notification method and the fourth notification method that outputs a warning sign including at least one text, video, picture, design, or message on the display screen.

Additionally, the neural network model of the present invention described above may be a deep neural network. Throughout this specification, neural network, network function, and neural network may be used interchangeably. A deep neural network (DNN) may refer to a neural network that includes a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks allow you to identify latent structures in data. In other words, it is possible to identify the potential structure of a photo, text, video, voice, or music (e.g., what object is in the photo, what the content and emotion of the text are, what the content and emotion of the voice are, etc.) . Deep neural networks include convolutional neural network (CNN), recurrent neural network (RNN), restricted Boltzmann machine (RBM), and deep belief network (DBN). , may include Q network, U network, Siamese network, etc.

A convolutional neural network is a type of deep neural network and includes a neural network including a convolutional layer. Convolutional neural networks are a type of multilayer perceptrons designed to use minimal preprocessing. A CNN may consist of one or several convolutional layers and artificial neural network layers combined with them. CNN can utilize additional weights and pooling layers. Thanks to this structure, CNN can fully utilize input data with a two-dimensional structure. Convolutional neural networks can be used to recognize objects in images. A convolutional neural network can process image data by representing it as a matrix with dimensions. For example, in the case of image data encoded in RGB (red-green-blue), each R, G, and B color can be represented as a two-dimensional (for example, in the case of a two-dimensional image) matrix. That is, the color value of each pixel of image data can be a component of the matrix, and the size of the matrix can be the same as the size of the image. Therefore, image data can be represented as three two-dimensional matrices (three-dimensional data array).

In a convolutional neural network, the convolutional process (input and output of the convolutional layer) can be performed by moving the convolutional filter and multiplying the matrix components at each position of the image with the convolutional filter. The convolutional filter may be composed of an n*n matrix. A convolutional filter may consist of a fixed type of filter that is generally smaller than the total number of pixels in the image. In other words, when m*m images are input to a convolutional layer (for example, a convolutional layer with a convolutional filter size of n*n), a matrix representing n*n pixels including each pixel of the image This can be a convolutional filter and component product (i.e., product of each component of the matrix). A component that matches the convolutional filter can be extracted from the image by multiplying it with the convolutional filter. For example, a 3*3 convolutional filter to extract upper and lower straight line components from an image would be structured as [[0,1,0], [0,1,0], [0,1,0]] You can. When a 3*3 convolutional filter for extracting upper and lower straight line components from an image is applied to the input image, upper and lower straight line components that match the convolutional filter can be extracted and output from the image. The convolutional layer can apply a convolutional filter to each matrix for each channel representing the image (i.e., R, G, and B colors in the case of an R, G, and B coded image). The convolutional layer can apply a convolutional filter to the input image and extract features that match the convolutional filter from the input image. The filter value of the convolutional filter (i.e., the value of each element of the matrix) can be updated by backpropagation during the learning process of the convolutional neural network.

A subsampling layer is connected to the output of the convolutional layer, which simplifies the output of the convolutional layer and reduces memory usage and computation. For example, when inputting the output of a convolutional layer to a pooling layer with a 2*2 max pooling filter, the image can be compressed by outputting the maximum value included in each patch for each 2*2 patch in each pixel of the image. You can. The above-described pooling may be a method of outputting the minimum value in a patch or the average value of the patch, and any pooling method may be included in the present invention.

A convolutional neural network may include one or more convolutional layers and subsampling layers. A convolutional neural network can extract features from an image by repeatedly performing a convolutional process and a subsampling process (for example, the above-described max pooling, etc.). Through an iterative convolutional process and subsampling process, the neural network can extract global features of the image.

The output of the convolutional layer or subsampling layer can be input to a fully connected layer. A fully connected layer is a layer in which all neurons in one layer and all neurons in neighboring layers are connected. A fully connected layer may refer to a structure in a neural network where all nodes of each layer are connected to all nodes of other layers.

According to an embodiment of the present invention, the processor 110 may be composed of one or more cores, such as a central processing unit (CPU) of a failure prediction device, and a general purpose graphics processing unit (GPGPU). unit) and a processor for data analysis and deep learning, such as a tensor processing unit (TPU). The processor 110 may read a computer program stored in the memory 130 and perform data processing for machine learning according to an embodiment of the present invention. According to one embodiment of the present invention, the processor 110 may perform calculations for learning a neural network. The processor 110 performs neural network learning, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating the weights of the neural network using backpropagation. calculations can be performed. At least one of the CPU, GPGPU, and TPU of the processor 110 may process learning of the network function. For example, CPU and GPGPU can work together to process learning of network functions and data classification using network functions. Additionally, in one embodiment of the present invention, the processors of a plurality of failure prediction devices can be used together to process learning of network functions and data classification using network functions. Additionally, the computer program executed in the failure prediction device according to an embodiment of the present invention may be a CPU, GPGPU, or TPU executable program.

According to one embodiment of the present invention, the memory 130 may store a computer program for providing a failure prediction judgment result of the control device, and the stored computer program may be read and driven by the processor 120. The memory 130 may store any type of information generated or determined by the processor 110 and any type of information received by the network unit 150.

According to one embodiment of the present invention, the memory 130 is a flash memory type, hard disk type, multimedia card micro type, or card type memory (e.g. For example, SD or It may include at least one type of storage medium among Read-Only Memory (Read-Only Memory), magnetic memory, magnetic disk, and optical disk.

The failure prediction device 100 may operate in connection with web storage that performs a storage function of the memory 130 on the Internet. The description of the memory described above is only an example and is not limited thereto.

The network unit 150 according to an embodiment of the present invention may be connected to the construction equipment 200 through wireless communication through a high-speed communication modem and wired communication through the communication unit.

In addition, the network unit 150 can transmit and receive failure prediction determination result information of the control device, etc. to other failure prediction determination devices and servers. In addition, the network unit 150 enables communication between a plurality of failure prediction devices, so that operations for failure prediction judgment or model learning of the control device are distributed and performed in each of the plurality of failure prediction devices. . The network unit 150 can enable communication between a plurality of failure prediction devices to distribute and process operations for failure prediction judgment of a control device or model learning using a network function.

The network unit 150 according to an embodiment of the present invention may operate based on any type of wired or wireless communication technology currently used and implemented, such as short-distance, long-distance, wired, and wireless, and other networks. It can also be used in

The failure prediction device 100 of the present invention may further include an output unit and an input unit.

The output unit according to an embodiment of the present invention may display a user interface (UI) for providing a failure prediction judgment result of the control device. The output unit may output any form of information generated or determined by the processor 110 and any form of information received by the network unit 150.

In one embodiment of the present invention, the output unit includes a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), and an organic light-emitting diode (OLED). , a flexible display, or a 3D display. Some of these display modules may be transparent or light-transmissive so that the outside can be viewed through them. This may be referred to as a transparent display module, and representative examples of the transparent display module include TOLED (Transparent OLED).

The input unit according to an embodiment of the present invention may receive user input. The input unit may include keys and/or buttons on a user interface or physical keys and/or buttons for receiving user input. A computer program for controlling the display according to embodiments of the present invention may be executed according to user input through the input unit.

The input unit according to embodiments of the present invention may receive a signal by detecting the user's button operation or touch input, or may receive a voice or movement of the user through a camera or microphone and convert it into an input signal. For this purpose, speech recognition technology or motion recognition technology can be used.

The input unit according to embodiments of the present invention may be implemented as an external input device connected to the failure prediction device 100. For example, the input device may be at least one of a touch pad, a touch pen, a keyboard, or a mouse for receiving user input, but this is only an example and is not limited thereto.

The input unit according to an embodiment of the present invention can recognize a user's touch input. The input unit according to an embodiment of the present invention may have the same configuration as the output unit. The input unit may be configured as a touch screen implemented to receive a user's selection input. The touch screen may be any one of a contact capacitive type, an infrared light sensing type, a surface ultrasonic (SAW) type, a piezoelectric type, and a resistive type. The detailed description of the touch screen described above is merely an example according to an embodiment of the present invention, and various touch screen panels may be employed in the failure prediction device 100. The input unit configured as a touch screen may include a touch sensor. The touch sensor may be configured to convert changes in pressure applied to a specific part of the input unit or capacitance generated in a specific part of the input unit into an electrical input signal. The touch sensor may be configured to detect not only the location and area of the touch, but also the pressure at the time of touch. When there is a touch input to the touch sensor, the corresponding signal(s) are sent to the touch controller. The touch controller may process the signal(s) and then transmit corresponding data to processor 110. Accordingly, the processor 110 can recognize which area of the input unit has been touched.

In one embodiment of the present invention, the server may include other components for performing the server environment of the server. A server can include any type of device. A server may be a digital device equipped with a processor and computing power with memory, such as a laptop computer, notebook computer, desktop computer, web pad, or mobile phone.

A server (not shown) that performs an operation to provide a user terminal with a user interface displaying a failure prediction judgment result of a control device according to an embodiment of the present invention may include a network unit, a processor, and memory.

The server may create a user interface according to embodiments of the present invention. A server may be a computing system that provides information to a client (eg, a user terminal) through a network. The server may transmit the created user interface to the user terminal. In this case, the user terminal may be any type of failure prediction device 100 that can access the server. The processor of the server may transmit the user interface to the user terminal through the network unit. The server according to embodiments of the present invention may be, for example, a cloud server. The server may be a web server that processes the service. The types of servers described above are only examples and are not limited thereto.

Therefore, the present invention collects control data from the PLC of heavy construction equipment and analyzes trends in the error occurrence frequency of the control data to detect and monitor failure signs of the control device in advance.

In addition, the present invention can detect and monitor failure signs of PLC-based control devices in advance, thereby improving safety at industrial and construction sites, and detecting signs of failure in advance to ensure equipment safety. It can operate more safely and smoothly, increasing productivity.

Figure 2 is a schematic diagram showing a network function of a neural network model, according to an embodiment of the present invention.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. A neural network can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network consists of at least one node. Nodes (or neurons) that make up neural networks may be interconnected by one or more links.

Within a neural network, one or more nodes connected through a link may form a relative input node and output node relationship. The concepts of input node and output node are relative, and any node in an output node relationship with one node may be in an input node relationship with another node, and vice versa. As described above, input node to output node relationships can be created around links. One or more output nodes can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the data of the output node may be determined based on the data input to the input node. Here, the link connecting the input node and the output node may have a weight. Weights may be variable and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. The output node value can be determined based on the weight.

As described above, in a neural network, one or more nodes are interconnected through one or more links to form an input node and output node relationship within the neural network. The characteristics of the neural network can be determined according to the number of nodes and links within the neural network, the correlation between the nodes and links, and the value of the weight assigned to each link. For example, if the same number of nodes and links exist and two neural networks with different weight values of the links exist, the two neural networks may be recognized as different from each other.

A neural network may consist of a set of one or more nodes. A subset of nodes that make up a neural network can form a layer. Some of the nodes constituting the neural network may form one layer based on the distances from the first input node. For example, a set of nodes with a distance n from the initial input node may constitute n layers. The distance from the initial input node can be defined by the minimum number of links that must be passed to reach the node from the initial input node. However, this definition of a layer is arbitrary for explanation purposes, and the order of a layer within a neural network may be defined in a different way than described above. For example, a layer of nodes may be defined by distance from the final output node.

The initial input node may refer to one or more nodes in the neural network through which data is directly input without going through links in relationships with other nodes. Alternatively, in a neural network network, in the relationship between nodes based on links, it may mean nodes that do not have other input nodes connected by links. Similarly, the final output node may refer to one or more nodes that do not have an output node in their relationship with other nodes among the nodes in the neural network. Additionally, hidden nodes may refer to nodes constituting a neural network other than the first input node and the last output node.

The neural network according to an embodiment of the present invention is a neural network in which the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as it progresses from the input layer to the hidden layer. You can. In addition, the neural network according to another embodiment of the present invention may be a neural network in which the number of nodes in the input layer may be less than the number of nodes in the output layer, and the number of nodes decreases as it progresses from the input layer to the hidden layer. there is. In addition, the neural network according to another embodiment of the present invention is a neural network in which the number of nodes in the input layer may be greater than the number of nodes in the output layer, and the number of nodes increases as it progresses from the input layer to the hidden layer. You can. The neural network according to another embodiment of the present invention may be a neural network that is a combination of the above-described neural networks.

A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to the input layer and output layer. Deep neural networks allow you to identify latent structures in data. In other words, it is possible to identify the potential structure of a photo, text, video, voice, or music (e.g., what object is in the photo, what the content and emotion of the text are, what the content and emotion of the voice are, etc.) . Deep neural networks include convolutional neural networks (CNN), recurrent neural networks (RNN), auto encoders, generative adversarial networks (GAN), and restricted Boltzmann machines (RBM). machine), deep belief network (DBN), Q network, U network, Siamese network, Generative Adversarial Network (GAN), etc. The description of the deep neural network described above is only an example and is not limited thereto.

In one embodiment of the present invention, the network function may include an autoencoder. An autoencoder may be a type of artificial neural network to output output data similar to input data. The autoencoder may include at least one hidden layer, and an odd number of hidden layers may be placed between input and output layers. The number of nodes in each layer may be reduced from the number of nodes in the input layer to an intermediate layer called the bottleneck layer (encoding), and then expanded symmetrically and reduced from the bottleneck layer to the output layer (symmetrical to the input layer). Autoencoders can perform nonlinear dimensionality reduction. The number of input layers and output layers can be corresponded to the dimension after preprocessing of the input data. In an auto-encoder structure, the number of nodes in the hidden layer included in the encoder may have a structure that decreases as the distance from the input layer increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, not enough information may be conveyed, so if it is higher than a certain number (e.g., more than half of the input layers, etc.) ) may be maintained.

A neural network may be trained in at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Learning of a neural network may be a process of applying knowledge for the neural network to perform a specific operation to the neural network.

Neural networks can be trained to minimize output errors. In neural network learning, learning data is repeatedly input into the neural network, the output of the neural network and the error of the target for the learning data are calculated, and the error of the neural network is transferred from the output layer of the neural network to the input layer in the direction of reducing the error. This is the process of updating the weight of each node in the neural network through backpropagation. In the case of teacher learning, learning data in which the correct answer is labeled in each learning data is used (i.e., labeled learning data), and in the case of non-teacher learning, the correct answer may not be labeled in each learning data. That is, for example, in the case of teacher learning regarding data classification, the learning data may be data in which each learning data is labeled with a category. Labeled training data is input to the neural network, and the error can be calculated by comparing the output (category) of the neural network with the label of the training data. As another example, in the case of non-teachable learning for data classification, the error can be calculated by comparing the input training data with the neural network output. The calculated error is backpropagated in the reverse direction (i.e., from the output layer to the input layer) in the neural network, and the connection weight of each node in each layer of the neural network can be updated according to backpropagation. The amount of change in the connection weight of each updated node may be determined according to the learning rate. The neural network's calculation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently depending on the number of repetitions of the learning cycle of the neural network. For example, in the early stages of neural network training, a high learning rate can be used to increase efficiency by allowing the neural network to quickly achieve a certain level of performance, and in the later stages of training, a low learning rate can be used to increase accuracy.

In the learning of neural networks, the training data can generally be a subset of real data (i.e., the data to be processed using the learned neural network), and thus the error for the training data is reduced, but the error for the real data is reduced. There may be an incremental learning cycle. Overfitting is a phenomenon in which errors in actual data increase due to excessive learning on training data. For example, a phenomenon in which a neural network that learned a cat by showing a yellow cat fails to recognize that it is a cat when it sees a non-yellow cat may be a type of overfitting. Overfitting can cause errors in machine learning algorithms to increase. To prevent such overfitting, various optimization methods can be used. To prevent overfitting, methods such as increasing the learning data, regularization, dropout to disable some of the network nodes during the learning process, and use of a batch normalization layer can be applied. You can.

Figure 3 is a flowchart illustrating a method for predicting failure of heavy construction equipment according to the present invention.

As shown in Figure 3, the present invention can collect control data from the PLC of heavy construction equipment (S110).

Here, the present invention can be connected by wired communication through an Ethernet or serial communication port of the PLC, or wirelessly through a network communication port.

In some cases, according to the present invention, if the heavy construction equipment has a plurality of PLCs, the plurality of PLCs may be connected sequentially according to a preset priority to collect control data.

And, the present invention can classify the collected control data by characteristics (S120).

Here, the present invention can identify the control data by parsing the collected control data by header, and classify the identified control data by control device of heavy construction equipment.

In some cases, the present invention can calculate the importance of classified control data and select control data for identifying an error signal based on the calculated importance.

Next, the present invention can identify an error signal from the classified control data (S130).

Here, the present invention checks whether an abnormal signal value or an error identification signal value exists in a data block from the classified control data, and if the abnormal signal value or an error identification signal value exists in the data block, the control data includes an error. It can be recognized as doing.

That is, in the present invention, when checking the presence or absence of an abnormal signal value, the data in the data block can be compared with preset normal data, and if the data is different from the normal data, it can be recognized that an abnormal signal value exists in the data block.

In some cases, the present invention, when checking the presence or absence of an error identification signal value, checks whether an error identification value with 0 or a negative number exists in the data block, and if an error identification value with 0 or a negative number exists in the data block. It may be recognized that an error identification signal value exists.

Next, the present invention can calculate the error occurrence frequency based on the identified error signal (S140).

Here, in the present invention, when calculating the error occurrence frequency, if the error signal satisfies any one of the first condition that the error signal occurs in the same data and the second condition that the error signal occurs in the same location, an error occurs for the corresponding control data. It can be calculated by increasing the frequency by 1.

In some cases, the present invention, when calculating the error occurrence frequency, if both the first condition that the error signal occurs in the same data and the second condition that the error signal occurs in the same location are satisfied, the error occurrence frequency for the corresponding control data is adjusted. It can also be calculated by increasing 1.

In addition, the present invention can predict the failure probability of the control device of heavy construction equipment by analyzing the trend of error occurrence frequency for control data based on the calculated error occurrence frequency (S150).

Here, the present invention analyzes the error occurrence frequency trend including at least one of the error occurrence rate, error occurrence cycle, and error occurrence increase rate for a preset period based on the error occurrence frequency to determine the failure probability for the control device. can be predicted.

In some cases, the present invention may input the error frequency into a pre-trained neural network model to analyze the error frequency trend for control data and predict the probability of failure for the control device of heavy construction equipment.

Here, the pre-trained neural network model takes the error occurrence frequency as an input and analyzes the error occurrence frequency trend including at least one of the error occurrence rate, error occurrence cycle, and error occurrence increase rate during a preset period to control the error occurrence frequency trend. You can learn in advance to predict the probability of failure.

Next, the present invention can inform the failure prediction of the control device based on the predicted failure probability (S160).

Here, the present invention can notify the failure prediction of the control device by generating and providing notification information including the predicted failure control device information and failure probability information.

As an example, the present invention includes a first notification method that outputs a specific sound through a speaker when notifying a failure prediction of a control device, a second notification method that vibrates a vibrator, a third notification method that turns on/off a warning light, and a display screen. Abnormal signs of the control device 200 can be notified by at least one of the fourth notification methods that output a warning sign including at least one text, video, picture, design, or message.

In this way, the present invention can collect control data from the PLC of heavy construction equipment and analyze trends in the error occurrence frequency of the control data to detect and monitor failure signs of the control device in advance.

In addition, the present invention can detect and monitor failure signs of PLC-based control devices in advance, thereby improving safety at industrial and construction sites, and detecting signs of failure in advance to ensure equipment safety. It can operate more safely and smoothly, increasing productivity.

The features, structures, effects, etc. described in the present inventions above are included in at least one embodiment of the present invention, and are not necessarily limited to only one embodiment. Furthermore, the features, structures, effects, etc. illustrated in each embodiment can be combined or modified and implemented in other embodiments by a person with ordinary knowledge in the field to which the embodiments belong. Therefore, contents related to such combinations and modifications should be construed as being included in the scope of the present invention.

In addition, although the above description has been made focusing on the examples, this is only an example and does not limit the present invention, and those skilled in the art will understand the above examples without departing from the essential characteristics of the present embodiment. You will be able to see that various modifications and applications are possible. For example, each component specifically shown in the examples can be modified and implemented. And these variations and differences in application should be construed as being included in the scope of the present invention as defined in the appended claims.

100: Abnormality detection device
110: processor
130: memory
150: Network unit
200: Heavy construction equipment
210: Power unit
220: Control device
230: PLC

Claims (10)

Collecting control data from a PLC (Programmable Logic Controller) of heavy construction equipment;
Classifying the collected control data by characteristics;
identifying an error signal from the classified control data;
calculating an error occurrence frequency based on the identified error signal;
Predicting a failure probability for the control device of the heavy construction equipment by analyzing a trend of error occurrence frequency for the control data based on the calculated error occurrence frequency; and
A method for predicting failure of heavy construction equipment, comprising the step of notifying a failure prediction of the control device based on the predicted failure probability. According to claim 1,
The step of collecting the control data is,
Perform a communication connection with the PLC of the heavy construction equipment, and when communication is connected with the PLC of the heavy construction equipment, control data corresponding to the control device of the heavy construction equipment is requested from the PLC of the heavy construction equipment, and the control data is controlled from the PLC of the heavy construction equipment. A failure prediction method for heavy construction equipment, characterized in that when control data corresponding to the device is received, the received control data is collected. According to claim 1,
The step of classifying the collected control data by characteristics is,
A method for predicting failure of heavy construction equipment, characterized in that the collected control data is parsed by header to identify the control data, and the identified control data is classified by control device of the heavy construction equipment. According to claim 1,
The step of identifying the error signal is,
The presence or absence of an abnormal signal value or an error identification signal value in a data block is confirmed from the classified control data, and if the abnormal signal value or an error identification signal value is present in the data block, the control data is recognized as containing an error. A method for predicting failure of heavy construction equipment, characterized in that: According to clause 4,
The step of checking whether the abnormal signal value exists is,
A method for predicting failure of heavy construction equipment, characterized in that comparing the data in the data block with preset normal data and recognizing that an abnormal signal value exists in the data block if the data is different from the normal data. According to clause 4,
The step of checking whether the error identification signal value exists is,
Heavy construction equipment, characterized in that it checks whether an error identification value having 0 or a negative number exists in the data block, and if the error identification value having 0 or a negative number exists, it recognizes that an error identification signal value exists in the data block. Failure prediction method. According to claim 1,
The step of calculating the error occurrence frequency is,
If the error signal satisfies any one of the first condition occurring in the same data and the second condition occurring in the same location, the error frequency for the corresponding control data is increased by 1 to calculate the error signal. Method for predicting failure of heavy equipment. According to claim 1,
The step of calculating the error occurrence frequency is,
Failure prediction of heavy construction equipment, characterized in that if the error signal satisfies both the first condition that the error signal occurs in the same data and the second condition that it occurs in the same location, the error frequency for the corresponding control data is increased by 1. method. According to claim 1,
The step of predicting the failure probability is,
Predicting the failure probability for the control device by analyzing the error occurrence frequency trend including at least one of the error occurrence rate, error occurrence cycle, and error occurrence increase rate during a preset period based on the error occurrence frequency. A method for predicting failure of heavy construction equipment. A failure prediction device for heavy construction equipment to provide a method for predicting failure of heavy construction equipment,
A processor including one or more cores; and
contains memory,
The processor,
Collect control data from the PLC (Programmable Logic Controller) of the construction equipment,
The collected control data is classified by characteristics,
Identifying error signals from the classified control data,
Calculate the error frequency based on the identified error signal,
Based on the calculated error frequency, predict the probability of failure for the control device of the heavy construction equipment by analyzing the error frequency trend for the control data,
A failure prediction device for heavy construction equipment, characterized in that it informs the failure prediction of the control device based on the predicted failure probability.

Images