Remote monitoring method and system for operation state of electromechanical equipment

Abstract

The embodiment of the invention discloses a remote monitoring method and system for the running state of electromechanical equipment, which greatly simplifies the calculated speed value by acquiring image information and setting a sampling period of one second without calculating the speed by acquiring the displacement, and calculates the displacement and the speed of a sampling interval by different methods, thereby improving the accuracy of the operation state of the electromechanical equipment. The difference value V = Vt-Vt-1 between the current speed and the previous speed and the difference value S = Stre-St-1re between the distance of the current mechanical motion and the distance of the previous mechanical motion are calculated, the probability of misjudgment is reduced through mutual judgment of S and V, and the accuracy of the curve is improved; through mutual correction of Vt and Stre, the accuracy of a speed curve is improved, data are processed through edge nodes, the motion state of equipment is obtained, the computing power of the edge nodes is fully utilized, the pressure of a cloud or a server is relieved, the running state of the equipment is informed through a heartbeat packet in the normal state, and a data packet is sent in the abnormal state. And the link bandwidth is prevented from being occupied by sending the sampling data to the cloud in real time.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of electromechanical equipment operation monitoring, in particular to a remote monitoring method and system for the running state of electromechanical equipment. BACKGROUND

[0002] In recent years, with the rapid development of science and technology, various electromechanical equipment has been developed to replace the use of existing labor, among which the punch press has become the fastest and most effective method to replace labor in the stamping process. Punching is a processing method in which a punch driven by a punch press cooperates with a stamping die to apply force to a sheet to break or shape the material. In common punching, the breaking or deformation of the sheet can be classified into shearing and cutting, drawing, forming, bending and other types, and in the drawing process, the sheet will produce complex stress and deformation, including compression, bending, drawing tension and friction, Figure 1 is a drawing process diagram, Figure 2 is a drawing process curve of the punch press, (1) and (4) sections are the fast approach of the punch to the workpiece and the fast increase of the punch, the two sections are not in contact with the workpiece, so the faster the better, to achieve high production efficiency; (2) and (3) sections are the main part of processing the workpiece, after the punch contacts the workpiece, it enters the (2) stage, the punch pulls the workpiece into the die at a set speed, and the distance of the punch moving down in the (2) stage is the depth of the drawing, after the punch moves to the set depth, it enters the (3) stage and stays for a short time, the purpose is to give the workpiece time to produce plastic deformation, if the punch is lifted too fast, the workpiece will produce a rebound phenomenon. In the stamping process, the blank pulled into the mother die by the punch will produce necking if the strain rate is too large, resulting in uneven wall thickness of the finished product or cracking, selecting the appropriate punch speed can avoid this phenomenon, therefore, obtaining the movement trajectory curve of the punch, especially the speed curve, plays an important role in determining the working state of the punch and the quality of the stamping product.

[0003] In the existing remote monitoring technology of the operating status of electromechanical equipment, the corresponding parameters can be obtained by installing specific sensors at the punch, and then the edge node transmits the collected parameter values ​​to the cloud or server in real time. The server obtains the motion curve of the punch based on the collected values, and then determines the operating status of the electromechanical equipment. However, the edge node transmits the collected parameter values ​​to the cloud or server in real time, resulting in a large amount of data transmission, which occupies a large amount of link bandwidth and affects the transmission of other important data. At the same time, the computing power of the edge node cannot be fully utilized. Sensors usually require high-precision and high-reliability sensors. Such sensors are usually expensive, resulting in high subsequent maintenance and maintenance costs. In order to obtain the punch speed value, the existing technology usually first obtains the moving distance of the punch and obtains the speed value by calculation, which makes the process cumbersome. Due to the working characteristics of the punch, such as Figure 2 Before and after the intersection of parts (1) and (2), or before and after the intersection of parts (2) and (3), or before and after the intersection of parts (3) and (4), the speed values ​​differ greatly. When the speed value is obtained by calculating the moving distance, it is usually judged whether the difference between it and the speed value obtained last time is greater than a specific threshold. If it is greater, it is determined that the speed value belongs to the value after the inflection point, and it is determined that the speed value obtained this time is a normal value. However, in actual application, due to the influence of various factors, it is usually not reached when the speed value is greater than a specific threshold. Figure 2 Before and after the intersection of parts (1) and (2), as in stage (1), the difference between the two adjacent values ​​may be greater than the set specific threshold. Using this single judgment method is prone to misjudgment, resulting in an inaccurate trajectory curve. At the same time, when obtaining the moving curve based on the obtained speed value, in order to ensure the accuracy of the curve, it is usually necessary to perform complex processing and fitting of the data, which makes the curve calculation complicated and places high requirements on the equipment. Summary of the Invention

[0004] In view of this, the present invention provides a remote monitoring method and system for the operating status of electromechanical equipment, which effectively solves the problems of large link bandwidth occupancy and insufficient utilization of edge node computing power, simplifies the cost of obtaining motion curves, the tedious calculation process, and the complex processing and fitting process.

[0005] In a first aspect, the present invention provides a method for remotely monitoring the operating status of electromechanical equipment, comprising: Image A of the mechanical motion is collected with a sampling period of one second t , t=1, ..., n; the captured image includes an observation point and a reference point of the mechanical motion, wherein the reference point is a point whose position remains unchanged during the mechanical motion, and the observation point is a point whose position changes during the mechanical motion; Get shooting parameter information; Get image A tThe pixel coordinate P of the observation point in the image t pc , according to the pixel coordinate P t pc and P t-1 pc , and the shooting parameter information, calculate the speed V of the mechanical movement t .

[0006] Get image A t The pixel coordinates of the reference point P t rpc , according to the pixel coordinate P t pc and P t-1 pc , reference point pixel coordinates P t rpc The actual distance S between the observation point and the reference point on the mechanical equipment is calculated using the captured parameter information t re , the actual distance of mechanical movement is S t re -S t-1 re ; Calculate the difference between the current speed and the previous speed △V=V t -V t-1 , and the difference between the current mechanical movement distance and the previous mechanical movement distance △S=S t re -S t-1 re If △V is greater than the first threshold and △S is greater than the second threshold, then V t and S t re Store and obtain a speed curve and a position curve based on the stored multiple speed values ​​and distance values; if △V is greater than a first threshold and △S is less than a second threshold, then S t re The value of V t value, and V t and S t re Store and obtain a speed curve and a position curve based on the stored multiple speed values ​​and distance values; if △V is less than a first threshold value and △S is greater than a second threshold value; then V t The value of S t re value, and V t and S t re storing and obtaining a speed curve and a position curve based on the stored plurality of speed values ​​and distance values; Input the speed curve and the position curve into the trained neural network model to identify the running state of the device; Based on the running state of the device, determine whether to send a heartbeat packet or a curve data packet to the cloud to make the cloud determine whether to issue an alarm message according to the received packet type.

[0007] In optional embodiments, in the above-mentioned method embodiments of the present application, the method further comprises: if ΔV is less than a first threshold value and ΔS is less than a second threshold value, determining the values of ΔV and ΔS, if ΔV is greater than ΔS, taking the value of V t re as the value of Vt; if ΔV is less than ΔS, taking the value of V t as the value of S t re t t re store and obtain the speed curve and the position curve based on the stored multiple speed values and distance values.

[0008] In optional embodiments, in the above-mentioned method embodiments of the present application, the parameter information of the shooting includes the distance D between the shooting point and the plane of the mechanical motion track, the pixel distance s of the image, and the distance d between the shooting point and the imaging plane.

[0009] In optional embodiments, in the above-mentioned method embodiments of the present application, the collection device can be a photographing device or a video recording device.

[0010] In optional embodiments, in the above-mentioned method embodiments of the present application, based on the running state of the device, determine whether to send a heartbeat packet or a curve data packet to the cloud, specifically: When the running state of the device output by the neural network is normal, send a heartbeat packet to the cloud, and when the cloud receives the heartbeat packet, it is considered that the running state of the electromechanical device is normal; when the running state of the device output by the neural network is abnormal, send the sampling values on the most recent complete speed curve and position curve to the cloud as a data packet.

[0011] In a second aspect, the present application provides a remote monitoring system for the running state of an electromechanical device, which comprises: an information collection node: collecting images A t , t = 1,..., n at a sampling period of one second during mechanical motion, wherein the collected images include an observation point and a reference point of the mechanical motion, the reference point is a point with fixed position during the mechanical motion, and the observation point is a point with changing position during the mechanical motion; an edge computing node: obtaining the parameter information of the shooting; obtaining images A t ​​The pixel coordinate P of the observation point in the image t pc , according to the pixel coordinate P t pc and P t-1 pc , and the shooting parameter information, calculate the speed V of the mechanical movement t .

[0012] Get image A t The pixel coordinates of the reference point P t rpc , according to the pixel coordinate P t pc and P t-1 pc , reference point pixel coordinates P t rpc The actual distance S between the observation point and the reference point on the mechanical equipment is calculated using the captured parameter information t re , the actual distance of mechanical movement is S t re -S t-1 re ; Calculate the difference between the current speed and the previous speed △V=V t -V t-1 , and the difference between the current mechanical movement distance and the previous mechanical movement distance △S=S t re -S t-1 re If △V is greater than the first threshold and △S is greater than the second threshold, then V t and S t re Store and obtain a speed curve and a position curve based on the stored multiple speed values ​​and distance values; if △V is greater than a first threshold and △S is less than a second threshold, then S t re The value of V t value, and V t and S t re Store and obtain a speed curve and a position curve based on the stored multiple speed values ​​and distance values; if △V is less than a first threshold value and △S is greater than a second threshold value; then V t The value of S t re value, and V t and S t re storing and obtaining a speed curve and a position curve based on the stored plurality of speed values ​​and distance values; Input the speed curve and the position curve into the trained neural network model to identify the running state of the device; Determine to send a heartbeat packet or a curve data packet to the cloud based on the running state of the device. Cloud: Determine whether to issue an alarm information according to the received packet type.

[0013] In an optional implementation, in the above-mentioned system embodiments of the present application, the edge computing node further comprises: if △V is less than a first threshold value and △S is less than a second threshold value, determining the value of △V and the value of △S, if △V is greater than △S, taking the value of V t re as the value of Vt; if △V is less than △S, taking the value of V t as the value of S t re ; taking the value of V t and the value of S t re Store and obtain the speed curve and the position curve based on the stored multiple speed values and distance values.

[0014] In an optional implementation, in the above-mentioned system embodiments of the present application, the photographed parameter information comprises the distance D between the shooting point and the plane of the mechanical motion track, the pixel distance s of the image, and the distance d between the shooting point and the imaging plane.

[0015] In an optional implementation, in the above-mentioned system embodiments of the present application, the collection device can be a photographing device or a video recording device.

[0016] In an optional implementation, in the above-mentioned system embodiments of the present application, based on the running state of the device, it is determined to send a heartbeat packet or a curve data packet to the cloud, specifically: When the running state of the device output by the neural network is normal, a heartbeat packet is sent to the cloud, and when the cloud receives the heartbeat packet, it is considered that the running state of the electromechanical device is normal; when the running state of the device output by the neural network is abnormal, the sampling values on the latest complete speed curve and position curve are sent to the cloud to form a data packet.

[0017] In a third aspect, an electronic device is provided, which comprises a memory and a processor coupled with the memory; the memory stores program instructions, and the program instructions, when executed by the processor, cause the electronic device to perform the method of the first aspect.

[0018] In a fourth aspect, a computer readable storage medium is provided, which comprises a computer program, and when the computer program runs on an electronic device, causes the electronic device to perform the method of the first aspect.

[0019] The embodiment of the present application provides a remote monitoring method and system for the running state of a mechanical and electrical device, which comprises the following steps: t acquiring an image A t by collecting the image of the mechanical movement at a sampling period of one second t pc according to the pixel coordinate P t pc and the parameter information of the shooting t-1 pc and calculating the speed V t of the mechanical movement t The speed value can be obtained through the information in the adjacent two images, the sampling period of one second is set by collecting the image information, the speed value is greatly simplified without calculating the speed through the displacement, the displacement and the speed of the sampling interval are respectively calculated by different methods, and the difference AV=V t-1 -V t and the difference AS=S re -S t-1 re The probability of misjudgment is reduced and the accuracy of the curve is improved by judging each other through AS and AV; when AV is less than a first threshold value and AS is less than a second threshold value, the value of AV and AS is judged, if AV is greater than AS, it is indicated that the calculated V t and V t-1 have a large deviation t , and since the values of V t and S re calculated by the above method of the present application are the same, in order to ensure that the obtained curve is more accurate, the value of V t is replaced by S t re , so that the accuracy of the speed curve is improved, the data is processed through the edge node, and the running state of the device is obtained, the computing capacity of the edge node is fully utilized, the pressure of the cloud or the server is reduced, the running state of the device is informed through the heartbeat packet in the normal time, and the data packet is sent in the abnormal time, so that the real-time sending of the sampling data to the cloud is avoided, and a large amount of link bandwidth is occupied.

[0020] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application will be realized and achieved by the structure particularly pointed out in the description and the drawings.

[0021] In order to make the above objects, features and advantages of the present application more clear and easily understood, the following will specifically describe the preferred embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0022] The above and other objects, features and advantages of the present application will become more apparent from the following description when taken in conjunction with the accompanying drawings, in which: Figure 1 Schematic diagram of drawing process; Figure 2 Drawing process stamping curve of punch; Figure 3 Flow chart of a remote monitoring method of a running state of a mechanical and electrical equipment provided by an embodiment of the present application; Figure 4 Schematic diagram of punch; Figure 5 Schematic diagram of parameter information for shooting; Figure 6 Schematic diagram of speed calculation method; Figure 7 Schematic diagram of displacement calculation method; Figure 8 Embodiment block diagram of a remote monitoring system of a running state of a mechanical and electrical equipment shown by the present application. DETAILED DESCRIPTION

[0023] The present application is described below based on embodiments, but the present application is not limited to these embodiments only. In the following detailed description of the present application, some specific details are described in detail. The present application can also be fully understood without the description of these details by those skilled in the art. In order to avoid confusion of the essence of the present application, well-known methods, processes, flows, elements and circuits are not described in detail.

[0024] In addition, those of ordinary skill in the art should understand that the drawings provided herein are for illustrative purposes only and the drawings are not necessarily drawn to scale.

[0025] Unless the context clearly requires otherwise, throughout the description, the words "comprise", "comprising", and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is to say, in the sense of "including, but not limited to".

[0026] In the description of the present application, it should be understood that the terms "first", "second" and the like are used only for the purpose of description and should not be construed as indicating or implying relative importance. In addition, in the description of the present application, unless otherwise stated, the meaning of "multiple" is two or more.

[0027] The present application provides a remote monitoring method of a running state of a mechanical and electrical equipment.Figure 3 This is a method flow chart of an embodiment of a remote monitoring method for the operating status of electromechanical equipment provided by the present invention.

[0028] like Figure 3 As shown, according to one embodiment of the present invention, the remote monitoring method for the operating status of electromechanical equipment comprises at least the following steps: Image A of the mechanical motion is collected with a sampling period of one second t , t=1, ..., n; the captured image includes an observation point and a reference point of the mechanical motion, wherein the reference point is a point whose position remains unchanged during the mechanical motion, and the observation point is a point whose position changes during the mechanical motion; Specifically, since the punch head only moves up and down in one plane when the punch press is working, a photographing device, such as a high-speed camera, can be fixed in front of the punch press to capture images of the punch head at a cycle of 1 second, or a video recorder can be used to obtain a video of the punch head at work, from which multiple video frame images are obtained at intervals of 1 second. Figure 4 In the punch press shown in , point O can be used as a reference point and point P as an observation point, and they can be marked on the punch press with specific colors to facilitate subsequent processing.

[0029] Get the shooting parameter information.

[0030] like Figure 5 As shown, the edge computing node obtains the shooting parameter information, which includes the distance D between the shooting point and the plane where the mechanical motion trajectory is located, the distance d between the shooting point and the imaging plane, and the pixel distance s of the image.

[0031] The edge computing node obtains image A t The pixel coordinates P of the observation point in the image t pc , according to the pixel coordinate P t pc and P t-1 pc , and the shooting parameter information, calculate the speed V of the mechanical movement t .

[0032] Specifically, refer to Figure 6 The schematic diagram shown, for example Figure 6 (a) is the image at time t-1, where the pixel coordinates of the observation point P are P t-1 pc is (0,1500), Figure 6 (b) is the image at time t, where the pixel coordinates P of the observation point P are t pc= (0,1380). Since the positions of the acquisition equipment and mechanical equipment are fixed, and the acquisition equipment parameters are pre-set and unchanged during the shooting process, the range of the captured images is consistent. Figure 6 The pixel coordinates in (b) correspond to Figure 6 The coordinate values ​​in (a) are consistent, which can be understood as Figure 6 (a) with Figure 6 (b) After merging, we can get Figure 6 Schematic diagram of (c), therefore, the pixel coordinate distance at time t-1 and time t is 1500-1380=120 (pixels), and the moving distance of the observation point in the image is calculated based on the pixel coordinate distance and the pixel distance s. For example, if the pixel distance s is 2 (um), the moving distance of the observation point in the image is 120*2=240um. The actual moving distance of the reference point during the mechanical movement is calculated based on the moving distance of the observation point in the image, the distance D between the shooting point and the plane where the mechanical motion trajectory is located, and the distance d between the shooting point and the imaging plane. For example, D=1 meter, d=6mm, and from "actual moving distance of the reference point during the mechanical movement / distance D between the shooting point and the plane where the mechanical motion trajectory is located=moving distance of the observation point in the image / distance d between the shooting point and the imaging plane", the actual moving distance of the reference point during the mechanical movement is 0.04m. Since the sampling period is 1 second, the speed of the punch movement is also 0.04.

[0033] Reference Figure 7 The schematic diagram shown, for example Figure 7 (a) is the image at time t-1, where the pixel coordinates P of the observation point P are assumed to be t-1 pc The coordinates of the reference point are (0,1500) and (0,300). Therefore, the pixel coordinate distance between the observation point and the reference point at time t-1 is 1500-300=1200 (pixels). The distance between the observation point and the reference point in the image is calculated based on the pixel coordinate distance and the pixel distance s. For example, if the pixel distance s is 2 (um), the movement distance of the observation point in the image is 1200*2=2400um. The actual movement distance of the reference point during the mechanical movement is calculated based on the movement distance between the observation point and the reference point in the image, the distance D between the shooting point and the plane where the mechanical motion trajectory is located, and the distance d between the shooting point and the imaging plane. For example, D=1 meter and d=6mm. According to "the actual distance between the observation point and the reference point / the distance D between the shooting point and the plane where the mechanical motion trajectory is located=the distance between the observation point and the reference point in the image / the distance d between the shooting point and the imaging plane", the actual distance between the observation point and the reference point at time t-1 is 0.4m. Figure 7 (b) is the image at time t, where the pixel coordinates P of the observation point P are assumed to be t-1 pcFor (0, 1380), the coordinate of the reference point is (0, 300), according to the same algorithm, the actual distance between the observation point and the reference point at time t is 0.36m, thus the actual distance of the mechanical movement from t-1 to t is 0.04m.

[0034] The difference between the current speed and the previous speed is calculated as ΔV=V t -V t-1 , and the difference between the current distance of the mechanical movement and the previous distance of the mechanical movement is calculated as ΔS=S t re -S t-1 re If ΔV is greater than a first threshold value and ΔS is greater than a second threshold value, then the value of V t and the value of S t re are stored, and a speed curve and a position curve are obtained based on the stored multiple speed values and distance values; if ΔV is greater than the first threshold value and ΔS is less than the second threshold value, then the value of S t re is taken as the value of Vt, and Vt and S t re are stored, and a speed curve and a position curve are obtained based on the stored values; if ΔV is less than the first threshold value and ΔS is greater than the second threshold value, then the value of V t t is taken as the value of S re , and V t and S t re are stored, and a speed curve and a position curve are obtained based on the stored values.

[0035] In order to avoid the error value of the current calculated speed value and the previous deviation being too large due to some uncertain factors, but being misjudged as the value of different stages because the difference is greater than the threshold value, such as the values before and after the intersection of (3) and (4) in Figure 2 , thus misjudging the error value as a correct value, resulting in an inaccurate trajectory curve. In the present application, the difference between the current speed and the previous speed is calculated as ΔV=V t -V t-1 , and the difference between the current distance of the mechanical movement and the previous distance of the mechanical movement is calculated as ΔS=S t re -S t-1 re If ΔV is greater than a first threshold value, then it is further judged whether ΔS is greater than a second threshold value, if both are greater, then the value of V t is considered as a correct value; similarly, when ΔS is greater than the second threshold value, it is further judged whether ΔV is greater than the first threshold value, if both are greater, then the value of S t reThe value of is the correct value. By judging each other by △S and △V, the probability of misjudgment is reduced and the accuracy of the curve is improved.

[0036] If △V is less than the first threshold and △S is less than the second threshold, then determine the size of △V and △S. If △V is greater than △S, then set S t re The value of V t If △V is less than △S, then V t The value of S t re The value of Vt and S t re A speed curve and a position curve are stored and obtained based on the stored plurality of speed values ​​and distance values.

[0037] In the present invention, when ΔV is less than the first threshold and ΔS is less than the second threshold, it means that V at time t is t and S t re Not in Figure 2 The values ​​before and after the intersection of parts (3) and (4) are the same in different sections according to the working characteristics of the punch, such as Figure 2 The speed of each segment at different time points is the same, and the displacement of two adjacent sampling intervals is also the same. Therefore, when V at time t t and S t re Not in Figure 2 When the values ​​before and after the intersection of (3) and (4) are determined, the values ​​of △V and △S are determined. If △V is greater than △S, the calculated V t and V t-1 The deviation is large, because the vt and S calculated by the above method of the present invention are t re The values ​​are the same, so in order to ensure that the obtained curve is more accurate, V t The value of S is replaced by t re , thereby improving the accuracy of the speed curve. Similarly, if △V is less than △S, it means that the calculated S t re and S t-1 re The deviation is large, then S t re The value of V is replaced by t ; V t and S t re A speed curve and a position curve are stored and obtained based on the stored plurality of speed values ​​and distance values.

[0038] The speed curve and the position curve are input into the trained neural network model to identify the running state of the device.

[0039] Specifically, the edge computing device inputs the speed curve and the position curve into the trained neural network model, and outputs the running state of the device, which includes normal or abnormal.

[0040] Based on the running state of the device, it is determined whether to send a heartbeat packet or a curve data packet to the cloud, so that the cloud determines whether to send an alarm information according to the received packet type.

[0041] In the prior art, the heartbeat packet is usually used to determine whether the link between the two communication parties is smooth, and the size of the heartbeat packet is usually very small, and the link resource occupation is extremely low. In the present application, when the neural network outputs the running state of the device as normal, the heartbeat packet is sent to the cloud, and when the neural network outputs the running state of the device as abnormal, the sampling values on the latest complete speed curve and position curve are sent to the cloud as a data packet. The running state of the device is informed by the heartbeat packet in normal time, and the data packet is sent in abnormal time, which avoids occupying a large amount of link bandwidth by sending sampling data to the cloud in real time. When the cloud receives the curve data packet, it can determine that the running state of the electromechanical device is abnormal, and at this time the cloud can send an alarm information to the user terminal to remind the user to handle it as soon as possible.

[0042] Reference Figure 8 An embodiment block diagram of a remote monitoring system for the running state of an electromechanical device is shown in the present application: As Figure 8 shown, the system includes: Information acquisition node: acquiring image A t , t = 1,..., n; the sampling image set includes an observation point and a reference point of mechanical movement, the reference point is a point with fixed position in the process of mechanical movement, and the observation point is a point with changing position in the process of mechanical movement; obtaining the parameter information of shooting; Edge computing node: obtaining the parameter information of shooting; Obtaining the observation point in image A t Pixel coordinates P t pc , according to the pixel coordinates P t pc and P t-1 pc , and the parameter information of shooting, the speed V t of mechanical movement is calculated.

[0043] Obtaining the observation point in image A tThe pixel coordinates of the reference point P t rpc , according to the pixel coordinate P t pc and P t-1 pc , reference point pixel coordinates P t rpc The actual distance S between the observation point and the reference point on the mechanical equipment is calculated using the captured parameter information t re , the actual distance of mechanical movement is S t re -S t-1 re ; Calculate the difference between the current speed and the previous speed △V=V t -V t-1 , and the difference between the current mechanical movement distance and the previous mechanical movement distance △S=S t re -S t-1 re If △V is greater than the first threshold and △S is greater than the second threshold, then V t and S t re Store and obtain a speed curve and a position curve based on the stored multiple speed values ​​and distance values; if △V is greater than a first threshold and △S is less than a second threshold, then S t re The value of V t value, and V t and S t re Store and obtain a speed curve and a position curve based on the stored multiple speed values ​​and distance values; if △V is less than a first threshold value and △S is greater than a second threshold value; then V t The value of S t re value, and V t and S t re storing and obtaining a speed curve and a position curve based on the stored plurality of speed values ​​and distance values; Input the speed curve and position curve into the trained neural network model to identify the operating status of the equipment; Based on the operating status of the device, determine to send a heartbeat packet or a curve data packet to the cloud; Cloud: Determine whether to issue an alarm message based on the type of packet received.

[0044] In optional embodiments, in the above-mentioned system embodiments of the present application, the edge computing node further comprises: if the △V is less than the first threshold value and the △S is less than the second threshold value, judging the values of the △V and the △S, if the △V is greater than the △S, taking the value of the S t re as the value of the Vt; if the △V is less than the △S, taking the value of the V t as the value of the S t re ; taking the value of the V t and the S t re are stored and the speed curve and the position curve are obtained based on the stored multiple speed values and distance values.

[0045] In optional embodiments, in the above-mentioned system embodiments of the present application, the parameter information of the shooting comprises the distance D between the shooting point and the plane of the mechanical motion track, the pixel distance s of the image, and the distance d between the shooting point and the imaging plane.

[0046] In optional embodiments, in the above-mentioned system embodiments of the present application, the acquisition device can be a photographing device or a video recording device.

[0047] In optional embodiments, in the above-mentioned system embodiments of the present application, based on the running state of the device, it is determined whether to send a heartbeat packet or a curve data packet to the cloud, specifically: when the running state of the neural network output device is normal, a heartbeat packet is sent to the cloud, and when the cloud receives the heartbeat packet, it is considered that the running state of the electromechanical device is normal; when the running state of the neural network output device is abnormal, a data packet composed of the sampling values on the latest complete speed curve and position curve is sent to the cloud.

[0048] The present application also provides an electronic device, which comprises: a processor; a memory, wherein the memory stores computer readable instructions, and the computer readable instructions are executed by the processor to implement the above-mentioned remote monitoring method of the running state of the electromechanical device.

[0049] The present application also provides a computer readable storage medium, which stores computer executable instructions, and when the computer executable instructions are executed on the electronic device, the electronic device executes the above-mentioned remote monitoring method of the running state of the electromechanical device.

[0050] The computer readable storage medium can be implemented using any appropriate combination of computer readable media. The computer readable media can be computer readable storage media or computer readable signal media. The computer readable storage media can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage media include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, the computer readable storage media can be any tangible medium that can contain, or store computer readable program code for use by or in connection with an instruction execution system, apparatus, or device.

[0051] The computer readable signal media can include a computer readable program code propagated across a network, such as the Internet, a local area network, a wide area network, a wired network, or a wireless network. The computer readable signal media can also include computer readable program code propagated across a carrier wave in a network, such as the Internet, a local area network, a wide area network, a wired network, or a wireless network. The computer readable signal media can be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport program code.

[0052] The computer readable program code can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, radio frequency (RF), etc., or any suitable combination of the foregoing.

[0053] Computer program code for carrying out operations of the present specification can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0054] The embodiments of the present application further provide a computer program product, which, when running on a computer, enables the computer to perform some or all of the steps of the above method embodiments.

[0055] From the above description of the embodiments, those skilled in the art can understand that, for the convenience and brevity of description, only the division of the above functional modules is taken as an example for illustration, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0056] The above describes the basic principles of the present disclosure in combination with specific embodiments, but it should be pointed out that the advantages, advantages, effects and the like mentioned in the present disclosure are only examples and cannot be considered as the must-have of each embodiment of the present disclosure. In addition, the above specific details are only for the purpose of example and for the purpose of understanding, and do not limit the present disclosure to the above specific details.

[0057] Each embodiment in the specification is described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same or similar parts between each embodiment can be referred to each other. For system embodiments, since they are basically corresponding to method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0058] The block diagrams of the devices, apparatuses, equipment, systems involved in the present disclosure are only as illustrative examples and are not intended to require or imply that the connection, arrangement, configuration must be as shown in the block diagrams. As those skilled in the art will recognize, the devices, apparatuses, equipment, systems can be connected, arranged, configured in any manner. Words such as "include", "contain", "have", and the like are open-ended words, mean "including but not limited to", and can be used interchangeably. The words "or" and "and" used herein mean the word "and / or", and can be used interchangeably, unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably.

[0059] The methods and apparatuses of the present disclosure can be implemented in numerous ways. For example, the methods and apparatuses of the present disclosure can be implemented using software, hardware, firmware, or any combination of software, hardware, and firmware. The above described order of steps for the methods is for illustration only and the steps of the methods of the present disclosure are not limited to the order described above unless otherwise specifically stated. Furthermore, in some embodiments, the present disclosure can also be implemented as a program recorded in a recording medium, which includes machine readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the methods according to the present disclosure.

[0060] It should also be noted that in the apparatuses, equipment and methods of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions of the present disclosure. The above description of the disclosed aspects is provided so that any person skilled in the art can make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other aspects without departing from the scope of the present disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0061] The above description is merely the preferred embodiments of the present application, and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A remote monitoring method for the operating status of electromechanical equipment, characterized in that: The method comprises: Image A of the mechanical motion is collected with a sampling period of one second t , t=1, ..., n; the captured image includes an observation point and a reference point of the mechanical motion, wherein the reference point is a point whose position remains unchanged during the mechanical motion, and the observation point is a point whose position changes during the mechanical motion; Get shooting parameter information; Get image A t The pixel coordinates P of the observation point in the image t pc , according to the pixel coordinate P t pc and P t-1 pc , and the shooting parameter information, calculate the speed V of the mechanical movement t ; Get image A t The pixel coordinates of the reference point P t rpc , according to the pixel coordinate P t pc and P t-1 pc , reference point pixel coordinates P t rpc The actual distance S between the observation point and the reference point on the mechanical equipment is calculated using the captured parameter information t re , the actual distance of mechanical movement is S t re -S t-1 re ; Calculate the difference between the current speed and the previous speed △V=V t -V t-1 , and the difference between the current mechanical movement distance and the previous mechanical movement distance △S=S t re -S t-1 re If △V is greater than the first threshold and △S is greater than the second threshold, then V t and S t re Store and obtain a speed curve and a position curve based on the stored multiple speed values ​​and distance values; if △V is greater than the first threshold and △S is less than the second threshold, then S t re The value of V t value, and V t and S t re Store and obtain a speed curve and a position curve based on the stored multiple speed values ​​and distance values; if △V is less than the first threshold and △S is greater than the second threshold; then V t The value of S t re value, and V t and S t re storing and obtaining a speed curve and a position curve based on the stored plurality of speed values ​​and distance values; Input the speed curve and position curve into the trained neural network model to identify the operating status of the equipment; Based on the operating status of the device, it is determined to send a heartbeat packet or a curve data packet to the cloud, so that the cloud determines whether to issue an alarm message according to the received packet type.

2. The remote monitoring method for the operating status of electromechanical equipment according to claim 1, further comprising: If △V is less than the first threshold and △S is less than the second threshold, then determine the size of △V and △S. If △V is greater than △S, then set S t re The value of V t If △V is less than △S, then V t The value of S t re The value of V t and S t re A speed curve and a position curve are stored and obtained based on the stored plurality of speed values ​​and distance values.

3. The remote monitoring method for the operating status of electromechanical equipment according to claim 1, characterized in that: The shooting parameter information includes the distance D between the shooting point and the plane where the mechanical motion trajectory is located, the pixel distance s of the image, and the distance d between the shooting point and the imaging plane.

4. The remote monitoring method for the operating status of electromechanical equipment according to claim 1, characterized in that: The acquisition device may be a photographing device or a video recording device.

5. The remote monitoring method for the operating status of electromechanical equipment according to claim 1, characterized in that: Based on the operating status of the device, determine whether to send a heartbeat packet or a curve data packet to the cloud, specifically: When the operating status of the neural network output device is normal, a heartbeat packet is sent to the cloud. When the cloud receives the heartbeat packet, it considers that the operating status of the electromechanical equipment is normal. When the operating status of the neural network output device is abnormal, the sampling values ​​of the most recent complete speed curve and position curve are combined into a data packet and sent to the cloud.

6. A remote monitoring system for the operating status of electromechanical equipment, the system comprising: Information acquisition node: collects image A of mechanical motion with a sampling period of one second t , t=1, ..., n; the captured image includes an observation point and a reference point of the mechanical motion, wherein the reference point is a point whose position remains unchanged during the mechanical motion, and the observation point is a point whose position changes during the mechanical motion; Edge computing node: obtains shooting parameter information; Get image A t The pixel coordinates P of the observation point in the image t pc , according to the pixel coordinate P t pc and P t-1 pc , and the shooting parameter information, calculate the speed V of the mechanical movement t ; Get image A t The pixel coordinates of the reference point P t rpc , according to the pixel coordinate P t pc and P t-1 pc , reference point pixel coordinates P t rpc The actual distance S between the observation point and the reference point on the mechanical equipment is calculated using the captured parameter information t re , the actual distance of mechanical movement is S t re -S t-1 re ; Calculate the difference between the current speed and the previous speed △V=V t -V t-1 , and the difference between the current mechanical movement distance and the previous mechanical movement distance △S=S t re -S t-1 re If △V is greater than the first threshold and △S is greater than the second threshold, then V t and S t re Store and obtain a speed curve and a position curve based on the stored multiple speed values ​​and distance values; if △V is greater than the first threshold and △S is less than the second threshold, then S t re The value of V t value, and V t and S t re Store and obtain a speed curve and a position curve based on the stored multiple speed values ​​and distance values; if △V is less than the first threshold and △S is greater than the second threshold; then V t The value of S t re value, and V t and S t re storing and obtaining a speed curve and a position curve based on the stored plurality of speed values ​​and distance values; Input the speed curve and position curve into the trained neural network model to identify the operating status of the equipment; Based on the operating status of the device, determine to send a heartbeat packet or a curve data packet to the cloud; Cloud: Determine whether to issue an alarm message based on the type of packet received.

7. The remote monitoring system for the operating status of electromechanical equipment according to claim 6, characterized in that: If △V is less than the first threshold and △S is less than the second threshold, then determine the size of △V and △S. If △V is greater than △S, then set S t re The value of Vt is taken as the value of V; if △V is less than △S, then V t The value of S t re The value of V t and S t re A speed curve and a position curve are stored and obtained based on the stored plurality of speed values ​​and distance values.

8. The remote monitoring system for the operating status of electromechanical equipment according to claim 6, characterized in that: The shooting parameter information includes the distance D between the shooting point and the plane where the mechanical motion trajectory is located, the pixel distance s of the image, and the distance d between the shooting point and the imaging plane.

9. The remote monitoring system for the operating status of electromechanical equipment according to claim 6, characterized in that: The acquisition device is a photo taking device or a video recording device.

10. The remote monitoring method for the operating status of electromechanical equipment according to claim 6, characterized in that: Based on the operating status of the device, determine whether to send a heartbeat packet or a curve data packet to the cloud, specifically: When the operating status of the neural network output device is normal, a heartbeat packet is sent to the cloud. When the cloud receives the heartbeat packet, it considers that the operating status of the electromechanical equipment is normal. When the operating status of the neural network output device is abnormal, the sampling values ​​of the most recent complete speed curve and position curve are combined into a data packet and sent to the cloud.

Images