Remote monitoring method and system for industrial production

Abstract

The invention discloses a remote monitoring method and system for industrial production, and relates to the technical field of remote monitoring. The method comprises the following steps: collecting working state data information of industrial production equipment, and uploading the working state data information to a monitoring server; constructing an equipment topological graph based on the equipment in the park, and generating a visual interface; constructing a monitoring data prediction model based on deep learning; inputting the collected data into the trained monitoring data prediction model; and generating an alarm scheme according to a matching result of the monitoring data prediction model, and sending the scheme to a mobile terminal of a manager. The internet is connected to industrial equipment and a system through the internet of things technology so as to monitor the state and the performance of the industrial equipment and the system in real time, potential problems and equipment fault signs of the equipment are recognized in time through remote monitoring, and the industrial data management strength and the monitoring strength of the park are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of remote monitoring, and in particular relates to a remote monitoring method and system for industrial production. Background Art

[0002] In the modern industrial field, automated control is one of the key factors to improve production efficiency, reduce costs, and ensure product quality and safety. With the continuous advancement of science and technology, remote monitoring technology has gradually become a new engine for industrial automation, bringing unprecedented opportunities and challenges to industrial production. Remote monitoring technology is based on the Internet and sensor technology. By closely connecting the physical world with the digital world, it realizes the seamless collaboration of equipment, systems and data. The widespread application of remote monitoring technology will bring revolutionary changes to the field of industrial automation, thereby promoting industrial production into the era of intelligence and digitalization. However, with the continuous expansion of the scale of industrial parks, more and more devices are connected, making the existing industrial remote monitoring equipment types complicated, resulting in the problem of untimely detection of equipment anomalies and incomplete data monitoring, which in serious cases brings great economic losses to industrial parks. Summary of the invention

[0003] The purpose of the present invention is to provide a remote monitoring method and system for industrial production, which connects the Internet to industrial equipment and systems through the Internet of Things technology to monitor their status and performance in real time, and uses remote monitoring to promptly identify potential problems of equipment and signs of equipment failure, thereby solving the problems of untimely discovery of problems and incomplete data monitoring of existing industrial production equipment.

[0004] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0005] The present invention is a remote monitoring method for industrial production, comprising the following steps:

[0006] Step S1: Collect the working status data information of each industrial production equipment in the current production process of the industrial park and upload it to the monitoring server;

[0007] Step S2: Install cameras and environmental collection sensors at multiple locations in the park, and upload the collected data information to the monitoring server;

[0008] Step S3: construct a device topology map based on the devices in the park and generate a visual interface;

[0009] Step S4: constructing a monitoring data prediction model based on deep learning;

[0010] Step S5: input the collected data into the trained monitoring data prediction model;

[0011] Step S6: Generate an alarm plan based on the matching result of the monitoring data prediction model, and send the plan to the manager's mobile terminal.

[0012] As a preferred technical solution, in step S1, the working status data information of each industrial production equipment is divided into an equipment working status sequence according to the equipment ID; the equipment working status sequence includes a threshold interval corresponding to the sensor data and a reference image corresponding to the image data; the monitoring server has built-in sensor data monitoring indicators and image data monitoring indicators for the equipment working status sequence, and sets a monitoring period for the equipment working status sequence, so as to obtain the equipment working status sequence of each industrial production equipment in real time.

[0013] As a preferred technical solution, in step S2, the camera captures images of license plates of vehicles entering and leaving the park and faces of people, and pre-processes the captured images, including cropping, background removal, denoising and contrast enhancement.

[0014] As a preferred technical solution, the camera collects the image and sends it to the monitoring server; the server performs feature recognition on the image through an analysis algorithm; the feature recognition process is as follows:

[0015] Step S21: Detect and locate the position of the face in the uploaded image or video, and separate the face from the background;

[0016] Step S22: aligning the detected face, including: rotating, translating and scaling the face;

[0017] Step S23: extracting distinctive features from the aligned face images, and detecting and locating facial feature points;

[0018] Step S24: After the facial features are extracted, they are compared with the known facial features in the database to perform identity verification.

[0019] As a preferred technical solution, in step S3, the specific process of constructing a device topology map for visualization is as follows:

[0020] Step S31: mapping the connection sequence and assembly relationship between the industrial production equipment into a node in a horizontal directed topology graph;

[0021] Step S32: constructing a horizontal directed topology graph according to the connection relationship between the nodes;

[0022] Step S33: Map each feature variable of the data collected by the camera and the environment collection sensor into a node in the vertical topology graph, and adopt a full interconnection method between the nodes to construct a vertical directed topology graph;

[0023] Step S34: Match the horizontal directed topology map and the vertical directed topology map to construct a visualized device topology map.

[0024] As a preferred technical solution, in step S5, the construction process of the monitoring data prediction model is as follows:

[0025] Step S51: using historically monitored sensor data and image data as a training set and a test set in proportion;

[0026] Step S52: input the training set into the monitoring data prediction model for training until the loss function training is stable, and save the model parameters;

[0027] Step S53: input the test set into the monitoring data prediction model for testing until it meets the preset requirements;

[0028] Step S54: Output the monitoring data prediction model.

[0029] As a preferred technical solution, in step S5, feature extraction is performed on the sensor data and image data of historical monitoring, and the average value of the characteristic variable parameters is obtained. The average standard deviation of other characteristic variable parameters in the time range before the monitoring time is obtained based on the characteristic variable parameter values ​​of other characteristic variable parameters in the time range before the monitoring time and the characteristic variable parameter average values ​​of other characteristic variable parameters in the historical monitoring period, and the equipment whose standard deviation is less than the threshold is marked as a fault state.

[0030] Remote monitoring is the use of a computer host to monitor and control remote devices over the Internet. The remote monitoring system is a software and hardware system composed of the control end and the controlled end that can realize information exchange. The application of this system basically realizes the operation, management and application of networked devices involved in life scenarios, realizes remote intelligent management, and forms a cloud-based application model for various types of equipment management; the core modules mainly involved in the remote monitoring system are data acquisition and information exchange of database data. Data acquisition is to unify the data resources of various networked devices into the cloud to form a resource database of equipment data. The data acquisition system compares the collected data with the equipment in real time through the information interaction module. The equipment administrator at the control end needs to perform corresponding operations based on the equipment status information transmitted on site, and the equipment at the controlled end responds according to the analog signal transmitted from the control end.

[0031] The present invention is a remote monitoring system for industrial production, comprising a sensor, a camera, an IoT data acquisition intelligent gateway, an IoT cloud platform monitoring server and a mobile intelligent terminal;

[0032] The sensor and camera transmit the collected information to the programmable controller PLC; the programmable controller PLC performs A / D conversion on the analog signal in the input signal, and performs logical operation analysis with the switch signal in the input signal, and the operation result is sent to the IoT data acquisition intelligent gateway in a standard data format; the IoT data acquisition intelligent gateway uploads the data to the IoT cloud platform monitoring server through the Internet; the image of the camera is connected to the IoT cloud platform monitoring server through the Internet; the cloud platform monitoring server has a built-in database, and the database cloud platform database can view information such as the company to which the equipment belongs, brand, type, model, and operating status;

[0033] The mobile intelligent terminal is used to access the Internet of Things cloud platform monitoring server, the real-time status data and on-site video of the obstetrics industrial park, and can receive alarm information.

[0034] The high reliability of this monitoring system is mainly guaranteed by the programmable controller PLC and other components. PLC is an industrial-grade programmable controller with no rotating parts, can work continuously, has low requirements for the working environment, and has extremely high reliability. The low operating and maintenance costs mainly depend on the high reliability of the components and the versatility and popularity of the IoT cloud platform.

[0035] As a preferred technical solution, the sensor includes one or more temperature sensors, smoke sensors, humidity sensors and floor water sensors.

[0036] As a preferred technical solution, the Internet of Things cloud platform monitoring server is used to perform real-time data comparison between the collected data and the equipment through the information interaction module. The administrator performs corresponding operations based on the equipment status information transmitted on site, and the controlled equipment responds according to the analog signal transmitted from the control end.

[0037] The present invention has the following beneficial effects:

[0038] The present invention connects the Internet to industrial equipment and systems through the Internet of Things technology to monitor their status and performance in real time, and uses remote monitoring to promptly identify potential equipment problems and signs of equipment failure, thereby improving the industrial data management and monitoring efforts of the park.

[0039] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0041] Figure 1 A flow chart of a remote monitoring method for industrial production according to the present invention;

[0042] Figure 2 The figure is a schematic diagram of the structure of a remote monitoring system for industrial production according to the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0045] In order to make the purpose, technical solution and advantages of this application clearer, the following Figure 1 The implementation methods of the present application are described in further detail.

[0046] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-2 It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] Embodiment 1

[0048] See also Figure 1 As shown, the present invention is a remote monitoring method for industrial production, comprising the following steps:

[0049] Step S1: Collect the working status data information of each industrial production equipment in the current production process of the industrial park and upload it to the monitoring server;

[0050] Step S2: Install cameras and environmental collection sensors at multiple locations in the park, and upload the collected data information to the monitoring server;

[0051] Step S3: construct a device topology map based on the devices in the park and generate a visual interface;

[0052] Step S4: constructing a monitoring data prediction model based on deep learning;

[0053] Step S5: input the collected data into the trained monitoring data prediction model;

[0054] Step S6: Generate an alarm plan based on the matching result of the monitoring data prediction model, and send the plan to the manager's mobile terminal.

[0055] In step S1, the working status data information of each industrial production equipment is divided into an equipment working status sequence according to the equipment ID; the equipment working status sequence includes a threshold interval corresponding to the sensor data and a reference image corresponding to the image data; the monitoring server has built-in sensor data monitoring indicators and image data monitoring indicators of the equipment working status sequence, and sets a monitoring period for the equipment working status sequence, which is used to obtain the equipment working status sequence of each industrial production equipment in real time.

[0056] In step S2, the camera collects images of license plates of vehicles entering and leaving the park and faces of people, and pre-processes the collected images, including cropping, background removal, denoising and contrast enhancement.

[0057] The camera collects the image and sends it to the monitoring server; the server uses the analysis algorithm to perform feature recognition on the image; the feature recognition process is as follows:

[0058] Step S21: Detect and locate the position of the face in the uploaded image or video, and separate the face from the background;

[0059] Step S22: aligning the detected face, including: rotating, translating and scaling the face;

[0060] Step S23: extracting distinctive features from the aligned face images, and detecting and locating facial feature points;

[0061] Step S24: After the facial features are extracted, they are compared with the known facial features in the database to perform identity verification.

[0062] In step S3, the specific process of constructing a device topology map for visualization is as follows:

[0063] Step S31: mapping the connection sequence and assembly relationship between the industrial production equipment into a node in a horizontal directed topology graph;

[0064] Step S32: constructing a horizontal directed topology graph according to the connection relationship between the nodes;

[0065] Step S33: Map each feature variable of the data collected by the camera and the environment collection sensor into a node in the vertical topology graph, and adopt a full interconnection method between the nodes to construct a vertical directed topology graph;

[0066] Step S34: Match the horizontal directed topology map and the vertical directed topology map to construct a visualized device topology map.

[0067] In step S5, the construction process of the monitoring data prediction model is as follows:

[0068] Step S51: using historically monitored sensor data and image data as a training set and a test set in proportion;

[0069] Step S52: input the training set into the monitoring data prediction model for training until the loss function training is stable, and save the model parameters;

[0070] Step S53: input the test set into the monitoring data prediction model for testing until it meets the preset requirements;

[0071] Step S54: Output the monitoring data prediction model.

[0072] In step S5, feature extraction is performed on the sensor data and image data of historical monitoring, and the average value of the characteristic variable parameters is obtained. The average standard deviation of other characteristic variable parameters in the time range before the monitoring time is obtained based on the characteristic variable parameter values ​​of other characteristic variable parameters in the time range before the monitoring time and the characteristic variable parameter average values ​​of other characteristic variable parameters in the historical monitoring period, and the equipment whose standard deviation is less than the threshold is marked as a fault state.

[0073] Embodiment 2

[0074] Remote monitoring is the use of a computer host to monitor and control remote devices over the Internet. The remote monitoring system is a software and hardware system composed of the control end and the controlled end that can realize information exchange. The application of this system basically realizes the operation, management and application of networked devices involved in life scenarios, realizes remote intelligent management, and forms a cloud-based application model for various types of equipment management; the core modules mainly involved in the remote monitoring system are data acquisition and information exchange of database data. Data acquisition is to unify the data resources of various networked devices into the cloud to form a resource database of equipment data. The data acquisition system compares the collected data with the equipment in real time through the information interaction module. The equipment administrator at the control end needs to perform corresponding operations based on the equipment status information transmitted on site, and the equipment at the controlled end responds according to the analog signal transmitted from the control end.

[0075] See also Figure 2As shown, the present invention is a remote monitoring system for industrial production, which can be used to execute the method content of embodiment 1 and subsequent embodiment 3 of the present invention, including: a sensor, a camera, an Internet of Things data acquisition intelligent gateway, an Internet of Things cloud platform monitoring server and a mobile intelligent terminal;

[0076] The sensor and camera transmit the collected information to the programmable controller PLC; the programmable controller PLC performs A / D conversion on the analog signal in the input signal, and performs logical operation analysis with the switch signal in the input signal, and the operation result is sent to the IoT data acquisition intelligent gateway in a standard data format; the IoT data acquisition intelligent gateway uploads the data to the IoT cloud platform monitoring server through the Internet; the camera image is connected to the IoT cloud platform monitoring server through the Internet; the cloud platform monitoring server has a built-in database, and the database cloud platform database can view information such as the company to which the equipment belongs, brand, type, model, and operating status;

[0077] The PLC system of a programmable controller generally includes a PLC host, a switch quantity module, a special function module and a program. Commonly used PLC systems in China include Siemens, Mitsubishi, Schneider, Delta, Huichuan, Yonghong and Panasonic. This test system uses a Delta programmable controller PLC host. This host contains a switch quantity module, selects one temperature measurement module 04PT and one A / D conversion module 04AD, and assembles the PLC host, temperature measurement module and A / D conversion module together. If the medical record warehouse is very large and there are many temperature points or humidity points that need to be measured, it is allowed to use multiple temperature measurement modules and multiple A / D conversion modules spliced ​​together for use;

[0078] The mobile smart terminal is used to access the IoT cloud platform monitoring server, the real-time status data of the obstetrics and gynecology industrial park and on-site video, and can receive alarm information.

[0079] The high reliability of this monitoring system is mainly guaranteed by the programmable controller PLC and other components. PLC is an industrial-grade programmable controller with no rotating parts, can work continuously, has low requirements for the working environment, and has extremely high reliability. The low operating and maintenance costs mainly depend on the high reliability of the components and the versatility and popularity of the IoT cloud platform.

[0080] The sensors include one or more of temperature sensors, smoke sensors, humidity sensors, and floor water sensors.

[0081] The IoT cloud platform monitoring server is used to compare the collected data with the equipment in real time through the information interaction module. The administrator performs corresponding operations based on the equipment status information transmitted on site, and the equipment on the controlled end responds according to the analog signal transmitted from the control end.

[0082] It is worth noting that in the above system embodiment, the various units included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0083] In addition, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiments can be completed by instructing related hardware through a program, and the corresponding program can be stored in a computer-readable storage medium.

[0084] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A remote monitoring method for industrial production, characterized in that: The steps include: Step S1: Collect the working status data information of each industrial production equipment in the current production process of the industrial park and upload it to the monitoring server; Step S2: Install cameras and environmental collection sensors at multiple locations in the park, and upload the collected data information to the monitoring server; Step S3: construct a device topology map based on the devices in the park and generate a visual interface; Step S4: constructing a monitoring data prediction model based on deep learning; Step S5: input the collected data into the trained monitoring data prediction model; Step S6: Generate an alarm plan based on the matching result of the monitoring data prediction model, and send the plan to the manager's mobile terminal.

2. A remote monitoring method for industrial production according to claim 1, characterized in that: In the step S1, the working status data information of each industrial production equipment is divided into an equipment working status sequence according to the equipment ID; the equipment working status sequence includes a threshold interval corresponding to the sensor data and a reference image corresponding to the image data; the monitoring server has built-in sensor data monitoring indicators and image data monitoring indicators of the equipment working status sequence, and sets a monitoring period for the equipment working status sequence, so as to obtain the equipment working status sequence of each industrial production equipment in real time.

3. A remote monitoring method for industrial production according to claim 1, characterized in that: In step S2, the camera collects images of license plates of vehicles entering and leaving the park and faces of people, and pre-processes the collected images, including cropping, background removal, denoising and contrast enhancement.

4. A remote monitoring method for industrial production according to claim 3, characterized in that: The camera collects the image and sends it to the monitoring server; the server performs feature recognition on the image through an analysis algorithm; the feature recognition process is as follows: Step S21: Detect and locate the position of the face in the uploaded image or video, and separate the face from the background; Step S22: aligning the detected face, including: rotating, translating and scaling the face; Step S23: extracting distinctive features from the aligned face images, and detecting and locating facial feature points; Step S24: After the facial features are extracted, they are compared with the known facial features in the database to perform identity verification.

5. A remote monitoring method for industrial production according to claim 1, characterized in that: In step S3, the specific process of constructing a device topology map for visualization is as follows: Step S31: mapping the connection sequence and assembly relationship between the industrial production equipment into a node in a horizontal directed topology graph; Step S32: constructing a horizontal directed topology graph according to the connection relationship between the nodes; Step S33: Map each feature variable of the data collected by the camera and the environment collection sensor into a node in the vertical topology graph, and adopt a full interconnection method between the nodes to construct a vertical directed topology graph; Step S34: Match the horizontal directed topology map and the vertical directed topology map to construct a visualized device topology map.

6. A remote monitoring method for industrial production according to claim 1, characterized in that: In step S5, the construction process of the monitoring data prediction model is as follows: Step S51: using historically monitored sensor data and image data as a training set and a test set in proportion; Step S52: input the training set into the monitoring data prediction model for training until the loss function training is stable, and save the model parameters; Step S53: input the test set into the monitoring data prediction model for testing until it meets the preset requirements; Step S54: Output the monitoring data prediction model.

7. A remote monitoring method for industrial production according to claim 1, characterized in that: In step S5, feature extraction is performed on the sensor data and image data of historical monitoring, and the average value of the characteristic variable parameters is obtained. The average standard deviation of other characteristic variable parameters in the time range before the monitoring time is obtained based on the characteristic variable parameter values ​​of other characteristic variable parameters in the time range before the monitoring time and the characteristic variable parameter average values ​​of other characteristic variable parameters in the historical monitoring period, and the equipment whose standard deviation is less than the threshold is marked as a fault state.

8. A remote monitoring system for industrial production, comprising sensors, cameras, an IoT data acquisition intelligent gateway, an IoT cloud platform monitoring server and a mobile intelligent terminal, characterized in that: The sensor and camera transmit the collected information to the programmable controller PLC; the programmable controller PLC performs A / D conversion on the analog signal in the input signal, and performs logical operation analysis on the switch signal in the input signal, and the operation result is sent to the Internet of Things data acquisition intelligent gateway in a standard data format; the Internet of Things data acquisition intelligent gateway uploads the data to the Internet of Things cloud platform monitoring server through the Internet; the image of the camera is connected to the Internet of Things cloud platform monitoring server through the Internet; the mobile intelligent terminal is used to access the Internet of Things cloud platform monitoring server, the real-time status data of the obstetrics industrial park and the on-site video, and can receive alarm information.

9. A remote monitoring system for industrial production according to claim 8, characterized in that: The sensors include one or more temperature sensors, smoke sensors, humidity sensors, and floor water sensors.

10. A remote monitoring system for industrial production according to claim 8, characterized in that: The IoT cloud platform monitoring server is used to perform real-time data comparison between the collected data and the equipment through the information interaction module. The administrator performs corresponding operations based on the equipment status information transmitted on site, and the equipment on the controlled end responds based on the analog signal transmitted from the control end.

Images