Service platform development method and system based on Internet of Things intelligent cloud architecture

Abstract

The invention is suitable for the technical field of platform service, and provides a service platform development method and system based on an Internet of Things intelligent cloud architecture, and the method comprises the steps: obtaining the Internet of Things intelligent cloud architecture; real-time data information is uploaded to the Internet of Things intelligent cloud architecture, a real-time curve is drawn according to a recording result, a health curve is drawn according to historical data, the real-time curve and the health curve are compared, and the current equipment operation state is judged according to a comparison result; obtaining fault data according to a comparison result, determining a specific fault type according to health curves of different parameters, matching a corresponding processing scheme according to the fault type, obtaining a safety gradient, and matching different early warning levels according to different gradients; and performing prediction according to the real-time data information, comparing a prediction result with a health threshold value, generating a maintenance plan according to the optimal maintenance time, and sending the maintenance plan to the terminal. The problems that an existing service platform cannot monitor the real-time data of existing equipment and cannot judge whether the operation condition of the equipment is normal or not are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of platform services, and particularly relates to a service platform development method and system based on an Internet of Things intelligent cloud architecture. Background Art

[0002] With the rapid development of industrial automation and intelligent manufacturing, the stability and efficiency of equipment have become important factors affecting production efficiency and product quality. During the long-term operation of industrial equipment, faults often occur due to factors such as component wear, insufficient lubrication, and load fluctuations, resulting in equipment downtime, production delays, and adverse effects on the continuity of the production line and production costs. Therefore, how to accurately predict the fault trend of equipment in advance and perform precise maintenance before the occurrence of equipment faults is the key to improving equipment operation efficiency, reducing production losses, and lowering maintenance costs.

[0003] In the traditional equipment management mode, most equipment maintenance relies on regular inspections and manual checks, which not only fails to accurately grasp the health status of the equipment but also has problems such as high maintenance costs, long downtime, and low efficiency. With the continuous development of industrial equipment monitoring technology, more and more industrial enterprises have begun to adopt the combination of Internet of Things technology and cloud computing.

[0004] However, the existing service platforms have the problem that they cannot monitor the real-time data of existing equipment and cannot determine whether the operation status of the equipment is normal. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a service platform development method based on an Internet of Things intelligent cloud architecture, aiming to solve the problems proposed in the third part of the background art.

[0006] The embodiments of the present invention are implemented as follows. A service platform development method based on an Internet of Things intelligent cloud architecture, the method includes:

[0007] Obtain an Internet of Things intelligent cloud architecture, which is used to transmit the massive data generated by Internet of Things devices to the cloud for processing and analysis;

[0008] Upload real-time data information to the Internet of Things intelligent cloud architecture, draw a real-time curve according to the recording result, draw a health curve according to historical data, compare the real-time curve with the health curve, and determine the current device operation status according to the comparison result;

[0009] Obtain fault data according to the comparison result, determine the specific fault type according to the health curves of different parameters, match the corresponding processing scheme according to the fault type, obtain the safety gradient, and match different warning levels according to different gradients;

[0010] Predict according to real-time data information, compare the prediction result with the health threshold, obtain the optimal maintenance time, generate a maintenance plan according to the optimal maintenance time, and send the maintenance plan to the terminal.

[0011] Preferably, the steps of uploading the real-time data information to the Internet of Things intelligent cloud architecture, drawing a real-time curve according to the recording result, drawing a health curve according to the historical data, comparing the real-time curve with the health curve, and determining the current device operation status according to the comparison result specifically include:

[0012] Obtain real-time data information, which is obtained through Internet of Things sensors, upload the real-time data information to the Internet of Things intelligent cloud architecture, record the real-time data information through the Internet of Things intelligent cloud architecture, and draw a real-time curve according to the recording result. The real-time curve is the real-time state of the device working.

[0013] Obtain historical data, and the Internet of Things intelligent cloud architecture draws a health curve according to the historical data. The health curve is the normal range of the device working, and the health curve includes multiple parameters.

[0014] Take the health curve as the reference value, compare the real-time curve with the health curve, obtain the comparison result, and determine the current device operation status according to the comparison result.

[0015] Preferably, the steps of obtaining fault data according to the comparison result, determining the specific fault type according to the health curves of different parameters, matching the corresponding treatment plan according to the fault type, obtaining the safety gradient, and matching different warning levels according to different gradients specifically include:

[0016] Obtain fault data according to the comparison result. The judgment basis of the fault data is that the real-time curve exceeds the health curve, and determine the specific fault type according to the health curves of different parameters.

[0017] Obtain the fault treatment plan, match the corresponding treatment plan according to the fault type, send the treatment plan to the terminal, and obtain the safety gradient. The safety gradient is different gradients from the critical value of the normal range.

[0018] The safety gradient is divided into five levels of gradients, match different warning levels according to different gradients, and send a warning signal to the terminal.

[0019] Preferably, the steps of predicting according to the real-time data information, comparing the prediction result with the health threshold, obtaining the optimal maintenance time, generating a maintenance plan according to the optimal maintenance time, and sending the maintenance plan to the terminal specifically include:

[0020] Predict according to the real-time data information to obtain a prediction result. The prediction is used to identify abnormal trends according to the device operation data.

[0021] Obtain a health threshold, where the health threshold is the critical value of the normal range. Compare the prediction result with the health threshold. If it is determined that the prediction result exceeds the health threshold, there is an abnormal trend.

[0022] Then obtain the optimal maintenance time, where the optimal maintenance time is based on the production plan and the remaining life. Generate a maintenance plan according to the optimal maintenance time and send the maintenance plan to the terminal.

[0023] Preferably, the parameters include temperature, vibration, pressure, and mechanical component wear.

[0024] Another object of the embodiments of the present invention is to provide a service platform development system based on the Internet of Things intelligent cloud architecture. The system includes:

[0025] The Internet of Things intelligent cloud architecture module obtains the Internet of Things intelligent cloud architecture, which is used to transmit the massive data generated by the Internet of Things devices to the cloud for processing and analysis.

[0026] The curve module uploads real-time data information to the Internet of Things intelligent cloud architecture, draws a real-time curve according to the recording result, draws a health curve according to the historical data, compares the real-time curve with the health curve, and determines the current device operation status according to the comparison result.

[0027] The fault and warning module obtains fault data according to the comparison result, determines the specific fault type according to the health curve of different parameters, matches the corresponding treatment plan according to the fault type, obtains the safety gradient, and matches different warning levels according to different gradients.

[0028] The maintenance module makes a prediction according to the real-time data information, compares the prediction result with the health threshold, obtains the optimal maintenance time, generates a maintenance plan according to the optimal maintenance time, and sends the maintenance plan to the terminal.

[0029] Preferably, the curve module includes:

[0030] The real-time curve unit obtains real-time data information, which is obtained through Internet of Things sensors, uploads the real-time data information to the Internet of Things intelligent cloud architecture, records the real-time data information through the Internet of Things intelligent cloud architecture, and draws a real-time curve according to the recording result. The real-time curve is the real-time state of the device operation.

[0031] The health curve unit obtains historical data, and the Internet of Things intelligent cloud architecture draws a health curve according to the historical data. The health curve is the normal range of the device operation, and the health curve includes multiple parameters.

[0032] The curve comparison unit uses the health curve as the reference value, compares the real-time curve with the health curve, obtains the comparison result, and determines the current device operation status according to the comparison result.

[0033] Preferably, the fault and warning module includes:

[0034] A fault unit that obtains fault data based on the comparison result. The basis for determining the fault data is that the real-time curve exceeds the healthy curve, and the specific fault type is determined according to the healthy curves of different parameters;

[0035] A safety gradient unit that obtains a fault handling solution, matches the corresponding handling solution according to the fault type, sends the handling solution to the terminal, and obtains the safety gradient, where the safety gradient is different gradients from the critical value of the normal range;

[0036] A warning unit that divides the safety gradient into five levels of gradients, matches different warning levels according to different gradients, and sends a warning signal to the terminal.

[0037] Preferably, the maintenance module includes:

[0038] A trend prediction unit that makes a prediction based on real-time data information to obtain a prediction result, where the prediction is used to identify an abnormal trend according to the equipment operation data;

[0039] A health threshold unit that obtains the health threshold, which is the critical value of the normal range, compares the prediction result with the health threshold, and if it is determined that the prediction result exceeds the health threshold, there is an abnormal trend;

[0040] A maintenance unit that obtains the optimal maintenance time, which is based on the production plan and the remaining life, generates a maintenance plan according to the optimal maintenance time, and sends the maintenance plan to the terminal.

[0041] Preferably, the parameters include temperature, vibration, pressure, and mechanical component wear.

[0042] A method for developing a service platform based on an Internet of Things intelligent cloud architecture provided by an embodiment of the present invention includes obtaining the Internet of Things intelligent cloud architecture, obtaining real-time data information, uploading the real-time data information to the Internet of Things intelligent cloud architecture, recording the real-time data information through the Internet of Things intelligent cloud architecture, drawing a real-time curve according to the recording result, obtaining historical data, drawing a health curve by the Internet of Things intelligent cloud architecture based on the historical data, using the health curve as a reference value, comparing the real-time curve with the health curve to obtain a comparison result, determining the current operating state of the device according to the comparison result, obtaining fault data according to the comparison result, determining the specific fault type according to the health curves of different parameters, obtaining a fault handling solution, matching the corresponding handling solution according to the fault type, sending the handling solution to the terminal, obtaining a safety gradient, dividing the safety gradient into five levels of gradients, matching different warning levels according to different gradients, sending a warning signal to the terminal, making a prediction based on the real-time data information to obtain a prediction result, obtaining a health threshold, comparing the prediction result with the health threshold, then obtaining the optimal maintenance time, generating a maintenance plan according to the optimal maintenance time, and sending the maintenance plan to the terminal, which solves the problem that the existing service platform cannot monitor the real-time data of existing devices and cannot determine whether the operating condition of the device is normal. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flowchart of a method for developing a service platform based on an Internet of Things intelligent cloud architecture provided by an embodiment of the present invention;

[0044] Figure 2 It is a flowchart of the steps of uploading real-time data information to the Internet of Things intelligent cloud architecture and comparing the real-time curve with the health curve provided by an embodiment of the present invention;

[0045] Figure 3 It is a flowchart of the steps of determining the specific fault type according to the health curves of different parameters and matching different warning levels according to different gradients provided by an embodiment of the present invention;

[0046] Figure 4 It is a flowchart of the steps of making a prediction based on the real-time data information and generating a maintenance plan according to the optimal maintenance time provided by an embodiment of the present invention;

[0047] Figure 5 It is an architecture diagram of a service platform development system based on an Internet of Things intelligent cloud architecture provided by an embodiment of the present invention;

[0048] Figure 6 It is an architecture diagram of a curve module provided by an embodiment of the present invention;

[0049] Figure 7 It is an architecture diagram of a fault and warning module provided by an embodiment of the present invention;

[0050] Figure 8This is the architecture diagram of the maintenance module provided by the embodiments of the present invention. Detailed implementation manners

[0051] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0052] It can be understood that the terms "first", "second", etc. used in the present application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish the first element from another element. For example, without departing from the scope of the present application, the first xx script may be referred to as the second xx script, and similarly, the second xx script may be referred to as the first xx script.

[0053] As Figure 1 shown, a service platform development method based on the Internet of Things (IoT) intelligent cloud architecture provided by the embodiments of the present invention includes:

[0054] S100. Obtain an IoT intelligent cloud architecture, which is used to transmit the massive data generated by IoT devices to the cloud for processing and analysis.

[0055] In this step, an IoT intelligent cloud architecture is obtained. The IoT intelligent cloud architecture is a distributed architecture integrating IoT devices, network communication, cloud computing, big data analysis, and artificial intelligence technologies, and is used to manage, analyze, and optimize the massive data from IoT devices. Its core function is to collect the real-time data of IoT devices and upload the data to the cloud for storage, processing, and analysis;

[0056] The IoT intelligent cloud architecture of industrial devices mainly consists of six core parts: a device layer, a network communication layer, a cloud computing layer, a data storage layer, an analysis and decision-making layer, and an application layer. The key operation data of production devices are collected in real time through the device layer, and the network communication layer is responsible for securely and stably transmitting the data collected by industrial devices to the cloud platform. The cloud computing layer is used to store, analyze, and optimize industrial device data, the data storage layer is used to store the massive data generated by industrial devices, and the cloud is used to perform intelligent analysis and prediction on the device operation data.

[0057] S200. Upload the real-time data information to the IoT intelligent cloud architecture, draw a real-time curve according to the recording result, draw a health curve according to the historical data, compare the real-time curve with the health curve, and determine the current device operation state according to the comparison result.

[0058] In this step, real-time data information is uploaded to the Internet of Things intelligent cloud architecture. The Internet of Things sensors are installed at key parts of industrial equipment and are responsible for collecting equipment operation status parameters. Temperature sensors detect the temperatures of motors, bearings, and hydraulic systems. Vibration sensors detect mechanical vibration conditions to identify bearing or gear damage. Current and voltage sensors are used to monitor the load conditions of motors and power supply systems;

[0059] Based on the recorded results, a real-time curve is drawn. The device operation status curve will be processed and drawn in real time. The real-time curve reflects the current state of the device. A health curve is drawn based on historical data. The health curve is based on historical data analysis and is used to define the normal operation state of the device. The real-time curve is compared with the health curve to judge the operation state of the device. According to the comparison result, the current device operation state is determined, whether it belongs to a healthy state, mild abnormality, moderate abnormality, or severe abnormality.

[0060] S300, obtain fault data according to the comparison result, determine the specific fault type according to the health curves of different parameters, match the corresponding treatment plan according to the fault type, obtain the safety gradient, and match different warning levels according to different gradients.

[0061] In this step, fault data is obtained according to the comparison result. The real-time curve of the device reflects the current operation state, while the health curve provides the normal working range. When the real-time curve deviates from the health curve by more than the set threshold, it is determined that the device is operating abnormally, and the fault data is recorded. The health curves of different parameters represent different device states, and the specific fault type is determined according to the health curves of different parameters;

[0062] Match the corresponding treatment plan according to the fault type. According to different fault types, the system automatically matches appropriate maintenance plans and executes corresponding adjustment measures. Obtain the safety gradient. The safety gradient is used to define the severity of device faults and match different warning levels.

[0063] S400, make a prediction based on the real-time data information, compare the prediction result with the health threshold, obtain the optimal maintenance time, generate a maintenance plan according to the optimal maintenance time, and send the maintenance plan to the terminal.

[0064] In this step, a prediction is made based on the real-time data information. The trend of device parameters is analyzed through linear regression methods to predict short-term changes. The device parameters include temperature, vibration, current, pressure, load changes, and maintenance history. The prediction result is compared with the health threshold. Prediction value < health threshold → The device state is normal and no maintenance is required; Prediction value is close to the health threshold → The device may have problems and maintenance needs to be arranged; Prediction value exceeds the health threshold → The device may be faulty and maintenance should be arranged immediately;

[0065] Obtain the optimal maintenance time, where the optimal maintenance time = predicted failure occurrence time - safety buffer time. Generate a maintenance plan based on the optimal maintenance time. The maintenance plan includes maintenance tasks, executors, work order numbers, and estimated man-hours, and send the maintenance plan to the terminal.

[0066] As Figure 2 shown, as a preferred embodiment of the present invention, the steps of uploading real-time data information to the Internet of Things intelligent cloud architecture, drawing a real-time curve according to the recording result, drawing a health curve according to historical data, comparing the real-time curve with the health curve, and determining the current device operation state according to the comparison result specifically include:

[0067] S201, obtain real-time data information. The real-time data information is obtained through Internet of Things sensors, upload the real-time data information to the Internet of Things intelligent cloud architecture, record the real-time data information through the Internet of Things intelligent cloud architecture, and draw a real-time curve according to the recording result. The real-time curve is the real-time state of the device working.

[0068] In this step, obtain real-time data information. The real-time data information is obtained through Internet of Things sensors. The temperature sensor detects the temperature of the motor, bearing, and hydraulic system. The vibration sensor detects the mechanical vibration condition to identify bearing or gear damage. The current and voltage sensors are used to monitor the load conditions of the motor and power supply system;

[0069] Upload the real-time data information to the Internet of Things intelligent cloud architecture, upload it to the cloud platform for processing through the network transport layer, perform RESTful API data transmission through HTTP / HTTPS, record the real-time data information through the Internet of Things intelligent cloud architecture, store device information through a relational database, and draw a real-time curve according to the recording result. The real-time curve is the real-time state of the device working;

[0070] The real-time curve is a time series curve drawn based on the real-time data of the device, intuitively showing the operation state of the device. The horizontal axis (X-axis) is time (milliseconds, seconds, or minutes), and the vertical axis (Y-axis) is device parameters (temperature, vibration, or current).

[0071] S202, obtain historical data. The Internet of Things intelligent cloud architecture draws a health curve according to the historical data. The health curve is the normal range of the device working, and the health curve includes multiple parameters.

[0072] In this step, obtain historical data. By recording the operation data of industrial devices for a long time, a historical data database is formed. The Internet of Things cloud platform usually uses big data storage to store historical data. The Internet of Things intelligent cloud architecture draws a health curve according to the historical data. The health curve is a curve of the normal operation range of the device calculated based on historical data, used to define the ideal operation state of the device under different loads and different working conditions;

[0073] The health curve includes the changing trends of multiple key parameters, including the average value curve (the normal operating value of the device), the maximum / minimum fluctuation range (the acceptable upper and lower limits of the device parameters), and the states under different working conditions (such as high-load and low-load states). The health curve includes multiple parameters, such as temperature, vibration amplitude, current power supply, pressure, flow rate, and noise.

[0074] S203: Use the health curve as the reference value, compare the real-time curve with the health curve to obtain the comparison result, and determine the current operating state of the device according to the comparison result.

[0075] In this step, use the health curve as the reference value. The health curve is the normal operating range of the device calculated based on historical data, representing the best working state of the device under different working conditions. The real-time curve is the curve drawn after collecting the device data in real time through the Internet of Things sensors, reflecting the current working state of the device. Compare the real-time curve with the health curve and perform the absolute deviation calculation: D = ∣X 实时 -X 健康 ∣ / X 健康 , where D is the absolute deviation value, X 实时 is the corresponding value of the real-time curve, and X 健康 is the corresponding value of the health curve. D ≤ 10% represents that the device is operating normally, 10% < D ≤ 30% represents a slight deviation, 30% < D ≤ 50% represents an obvious abnormality, and D > 50% represents a serious abnormality.

[0076] As Figure 3 shown, as a preferred embodiment of the present invention, the steps of obtaining fault data according to the comparison result, determining the specific fault type according to the health curves of different parameters, matching the corresponding treatment plan according to the fault type, obtaining the safety gradient, and matching different warning levels according to different gradients specifically include:

[0077] S301: Obtain fault data according to the comparison result. The basis for determining the fault data is that the real-time curve exceeds the health curve, and determine the specific fault type according to the health curves of different parameters.

[0078] In this step, obtain fault data according to the comparison result. The real-time curve represents the current operating state of the device, and the health curve represents the normal operating range of the device. When the real-time curve exceeds the range set by the health curve, it indicates that the device may have a fault, and the system will record the fault data;

[0079] Determine the specific fault type according to the health curves of different parameters. The health curve of each device includes multiple key parameters, and the abnormalities of different parameters can point to different fault types. For example, if the vibration of the spindle of a CNC machine tool > 0.5mm, it may be that the bearing is damaged; if the pressure of a hydraulic press > 4.0MPa, it may be that the pipeline is blocked.

[0080] S302. Obtain a fault handling solution, match the corresponding handling solution according to the fault type, send the handling solution to the terminal, and obtain the safety gradient, where the safety gradient is different gradients from the critical value of the normal range.

[0081] In this step, to obtain a fault handling solution, after the system identifies the fault type, it will automatically match the best handling solution from the maintenance knowledge base and match the corresponding handling solution according to the fault type.

[0082] Table 1: Handling Solution Table

[0083]

[0084] Send the handling solution to the terminal, send it to different terminals to ensure that relevant personnel receive the notice in a timely manner.

[0085] Obtain the safety gradient. The safety gradient is the degree of deviation of the current state of the device from the normal range, which is used to divide the severity level of the fault to ensure that the maintenance personnel adopt the most appropriate maintenance strategy.

[0086] S303. Divide the safety gradient into five levels of gradients, match different warning levels according to different gradients, and send a warning signal to the terminal.

[0087] In this step, the safety gradient is divided into five levels of gradients, and the safety gradient is based on the degree of deviation of the device parameters.

[0088] Table 2: Safety Gradient Table

[0089]

[0090] Match different warning levels according to different gradients, send a warning signal to multiple terminals to ensure that relevant personnel can respond quickly and ensure the optimal maintenance decision.

[0091] Such as Figure 4 As shown, as a preferred embodiment of the present invention, the step of predicting according to real-time data information, comparing the prediction result with the health threshold, obtaining the optimal maintenance time, generating a maintenance plan according to the optimal maintenance time, and sending the maintenance plan to the terminal specifically includes:

[0092] S401. Predict according to real-time data information to obtain a prediction result, where the prediction is used to identify abnormal trends based on device operation data.

[0093] In this step, predictions are made based on real-time data information. The trends of device parameters are analyzed through linear regression methods to predict short-term changes. The device parameters include temperature, vibration, current, pressure, load changes, and maintenance history. The predicted results are compared with the health thresholds. Prediction value < health threshold → The device is in normal condition and does not require maintenance; Prediction value close to the health threshold → The device may have problems and maintenance needs to be arranged; Prediction value exceeds the health threshold → The device may malfunction and maintenance should be arranged immediately.

[0094] S402, obtain the health threshold, where the health threshold is the critical value of the normal range. Compare the predicted result with the health threshold. If it is determined that the predicted result exceeds the health threshold, there is an abnormal trend.

[0095] In this step, obtain the health threshold. The health threshold is the critical value when the device is in normal operation. Exceeding this range means the device may enter an abnormal state and corresponding measures need to be taken. Compare the predicted result with the health threshold;

[0096] Prediction value < health threshold → The device is in normal condition and does not require maintenance; Prediction value close to the health threshold → The device may have problems and maintenance needs to be arranged; Prediction value exceeds the health threshold → The device may malfunction and maintenance should be arranged immediately;

[0097] That is, there is an abnormal trend. If the trend suddenly changes, the parameter rises significantly in a short period of time. For example, if the temperature rises by 10°C in a short time due to overload, it is determined as abnormal heat dissipation.

[0098] S403, then obtain the optimal maintenance time. The optimal maintenance time is based on the production plan and the remaining life. Generate a maintenance plan according to the optimal maintenance time and send the maintenance plan to the terminal.

[0099] In this step, then obtain the optimal maintenance time. Optimal maintenance time = Predicted failure time - Safety buffer time. The production plan avoids maintenance during peak production periods to reduce downtime losses. The remaining life predicts how much time the device can still operate stably in the future to ensure that maintenance is completed before the failure occurs;

[0100] Generate a maintenance plan according to the optimal maintenance time. The maintenance plan includes maintenance tasks, execution personnel, work order numbers, and estimated working hours. The maintenance plan will be pushed to different terminals to ensure that relevant personnel respond in a timely manner.

[0101] As Figure 5 shown, a service platform development system based on the Internet of Things intelligent cloud architecture provided by an embodiment of the present invention includes:

[0102] The Internet of Things intelligent cloud architecture module 100 is used to obtain the Internet of Things intelligent cloud architecture, and the Internet of Things intelligent cloud architecture is used to transmit the massive data generated by the Internet of Things devices to the cloud for processing and analysis.

[0103] In this system, the IoT Smart Cloud Architecture module 100 obtains the IoT Smart Cloud Architecture. The IoT Smart Cloud Architecture is a distributed architecture that integrates IoT devices, network communication, cloud computing, big data analysis, and artificial intelligence technologies, and is used to manage, analyze, and optimize the massive data from IoT devices. Its core function is to collect the real-time data of IoT devices and upload the data to the cloud for storage, processing, and analysis;

[0104] The IoT Smart Cloud Architecture of industrial devices mainly consists of six core parts: the device layer, the network communication layer, the cloud computing layer, the data storage layer, the analysis and decision-making layer, and the application layer. The key operation data of production devices are collected in real time through the device layer, and the network communication layer is responsible for securely and stably transmitting the data collected by industrial devices to the cloud platform. The cloud computing layer is used to store, analyze, and optimize industrial device data, the data storage layer is used to store the massive data generated by industrial devices, and the cloud is used to perform intelligent analysis and prediction on the device operation data.

[0105] The curve module 200 is used to upload real-time data information to the IoT Smart Cloud Architecture, draw real-time curves according to the recording results, draw health curves according to historical data, compare the real-time curves with the health curves, and determine the current device operation status according to the comparison results.

[0106] In this system, the curve module 200 uploads real-time data information to the IoT Smart Cloud Architecture. IoT sensors are installed at key parts of industrial devices and are responsible for collecting device operation status parameters. Temperature sensors detect the temperature of motors, bearings, and hydraulic systems, vibration sensors detect mechanical vibration conditions to identify bearing or gear damage, and current and voltage sensors are used to monitor the load conditions of motors and power systems;

[0107] According to the recording results, real-time curves will be drawn. The device operation status curves will be processed and drawn in real time. The real-time curves reflect the current state of the device. Health curves are drawn according to historical data. The health curves are based on historical data analysis and are used to define the normal operation state of the device. The real-time curves are compared with the health curves to judge the operation state of the device. According to the comparison results, the current device operation status is determined to belong to one of the healthy state, mild anomaly, moderate anomaly, and severe anomaly.

[0108] The fault and warning module 300 is used to obtain fault data according to the comparison results, determine the specific fault type according to the health curves of different parameters, match the corresponding processing solutions according to the fault type, obtain the safety gradient, and match different warning levels according to different gradients.

[0109] In this system, the fault and warning module 300 obtains fault data based on the comparison result. The real-time curve of the device reflects the current operating state, while the health curve provides the normal working range. When the real-time curve deviates from the health curve by more than the set threshold, it is determined that the device is operating abnormally, and the fault data is recorded. The health curves of different parameters represent different device states, and the specific fault type is determined according to the health curves of different parameters;

[0110] Match the corresponding treatment plan according to the fault type. According to different fault types, the system automatically matches an appropriate maintenance plan and executes the corresponding adjustment measures to obtain the safety gradient. The safety gradient is used to define the severity of the device fault and match different warning levels.

[0111] The maintenance module 400 is used to make predictions based on the real-time data information, compare the prediction result with the health threshold, obtain the optimal maintenance time, generate a maintenance plan according to the optimal maintenance time, and send the maintenance plan to the terminal.

[0112] In this system, the maintenance module 400 makes predictions based on the real-time data information, analyzes the trend of device parameters through the linear regression method to predict short-term changes. The device parameters include temperature, vibration, current, pressure, load changes, and maintenance history. Compare the prediction result with the health threshold. Prediction value < health threshold → The device state is normal and no maintenance is required; Prediction value is close to the health threshold → The device may have problems and maintenance needs to be arranged; Prediction value exceeds the health threshold → The device may malfunction and maintenance should be arranged immediately;

[0113] Obtain the optimal maintenance time. The optimal maintenance time = the predicted fault occurrence time - the safety buffer time. Generate a maintenance plan according to the optimal maintenance time. The maintenance plan includes maintenance tasks, executors, work order numbers, and estimated working hours, and send the maintenance plan to the terminal.

[0114] As Figure 6 shown, as a preferred embodiment of the present invention, the curve module 200 includes:

[0115] The real-time curve unit 201 is used to obtain real-time data information. The real-time data information is obtained through Internet of Things sensors, upload the real-time data information to the Internet of Things intelligent cloud architecture, record the real-time data information through the Internet of Things intelligent cloud architecture, and draw a real-time curve according to the recording result. The real-time curve is the real-time state of the device working.

[0116] In this module, the real-time curve unit 201 obtains real-time data information. The real-time data information is obtained through Internet of Things sensors. The temperature sensor detects the temperature of the motor, bearing, and hydraulic system. The vibration sensor detects the mechanical vibration condition to identify bearing or gear damage. The current and voltage sensors are used to monitor the load condition of the motor and power supply system;

[0117] Upload real-time data information to the Internet of Things intelligent cloud architecture, upload it to the cloud platform through the network transmission layer for processing, perform RESTful API data transmission through HTTP / HTTPS, record real-time data information through the Internet of Things intelligent cloud architecture, store device information in a relational database, and draw a real-time curve based on the recording result. The real-time curve is the real-time state of the device operation;

[0118] The real-time curve is a time-series curve drawn based on the real-time data of the device, visually showing the operating state of the device. The horizontal axis (X-axis) is time (milliseconds, seconds or minutes), and the vertical axis (Y-axis) is the device parameter (temperature, vibration or current).

[0119] The health curve unit 202 is used to obtain historical data. The Internet of Things intelligent cloud architecture draws a health curve based on the historical data. The health curve is the normal range of the device operation, and the health curve includes multiple parameters.

[0120] In this module, the health curve unit 202 obtains historical data. By recording the operation data of industrial devices for a long time, a historical data database is formed. The Internet of Things cloud platform usually uses big data storage to store historical data. The Internet of Things intelligent cloud architecture draws a health curve based on the historical data. The health curve is a curve of the normal operation range of the device calculated based on the historical data, used to define the ideal operation state of the device under different loads and different working conditions;

[0121] The health curve includes the change trends of multiple key parameters, including the average value curve (the normal operation value of the device), the maximum / minimum fluctuation range (the acceptable upper and lower limits of the device parameter), and the state under different working conditions (such as high-load and low-load states). The health curve includes multiple parameters, and the parameters include temperature, vibration amplitude, current power supply, pressure, flow rate and noise.

[0122] The curve comparison unit 203 is used to use the health curve as a reference value, compare the real-time curve with the health curve, obtain the comparison result, and determine the current device operation state based on the comparison result.

[0123] In this module, the curve comparison unit 203 uses the health curve as a reference value. The health curve is the normal operation range of the device calculated based on the historical data, representing the best working state of the device under different working conditions. The real-time curve is a curve drawn after real-time collecting device data through the Internet of Things sensor, reflecting the current working state of the device. Compare the real-time curve with the health curve and perform absolute deviation calculation: D = ∣X 实时 -X 健康 ∣ / X 健康 , D is the absolute deviation value, X 实时 is the corresponding value of the real-time curve, X 健康The corresponding value of the health curve, where D ≤ 10% indicates normal equipment operation, 10% < D ≤ 30% indicates a slight deviation, 30% < D ≤ 50% indicates an obvious abnormality, and D > 50% indicates a serious abnormality.

[0124] As Figure 7 shown, as a preferred embodiment of the present invention, the fault and early warning module 300 includes:

[0125] A fault unit 301 for obtaining fault data based on the comparison result. The basis for determining the fault data is that the real-time curve exceeds the health curve, and the specific fault type is determined according to the health curves of different parameters.

[0126] In this module, the fault unit 301 obtains fault data based on the comparison result. The real-time curve represents the current operating state of the equipment, and the health curve represents the normal operating range of the equipment. When the real-time curve exceeds the range set by the health curve, it indicates that the equipment may malfunction, and the system will record the fault data;

[0127] The specific fault type is determined according to the health curves of different parameters. The health curve of each equipment contains multiple key parameters, and the abnormality of different parameters can point to different fault types. For example, if the vibration of the spindle of a CNC machine tool > 0.5mm, it may be a bearing damage, and if the pressure of a hydraulic press > 4.0MPa, it may be a pipeline blockage.

[0128] A safety gradient unit 302 for obtaining a fault handling solution, matching the corresponding handling solution according to the fault type, sending the handling solution to the terminal, and obtaining the safety gradient, where the safety gradient is different gradients from the critical value of the normal range.

[0129] In this module, the safety gradient unit 302 obtains the fault handling solution. After the system identifies the fault type, it will automatically match the best handling solution from the maintenance knowledge base and match the corresponding handling solution according to the fault type.

[0130] Send the handling solution to the terminal, send it to different terminals to ensure that relevant personnel receive the notice in time;

[0131] Obtain the safety gradient. The safety gradient is the degree of deviation of the current state of the equipment from the normal range, which is used to divide the severity level of the fault to ensure that the operation and maintenance personnel adopt the most appropriate maintenance strategy.

[0132] An early warning unit 303 for dividing the safety gradient into five levels of gradients, matching different early warning levels according to different gradients, and sending an early warning signal to the terminal.

[0133] In this module, the early warning unit 303 divides the safety gradient into five levels of gradients, and the safety gradient is based on the degree of deviation of the equipment parameters;

[0134] Match different warning levels according to different gradients, send warning signals to multiple terminals to ensure that relevant personnel can respond quickly and ensure optimal maintenance decisions.

[0135] As Figure 8 shown, as a preferred embodiment of the present invention, the maintenance module 400 includes:

[0136] A trend prediction unit 401 for predicting according to real-time data information to obtain a prediction result, and the prediction is used to identify an abnormal trend according to device operation data.

[0137] In this module, the trend prediction unit 401 predicts according to real-time data information, analyzes the trend of device parameters by linear regression method, predicts short-term changes, and the device parameters include temperature, vibration, current, pressure, load change and maintenance history. Compare the prediction result with the health threshold. Prediction value < health threshold → The device is in normal state and does not require maintenance; Prediction value is close to the health threshold → The device may have problems and maintenance needs to be arranged; Prediction value exceeds the health threshold → The device may malfunction and maintenance should be arranged immediately.

[0138] A health threshold unit 402 for obtaining a health threshold, where the health threshold is the critical value of the normal range, comparing the prediction result with the health threshold, and if it is determined that the prediction result exceeds the health threshold, there is an abnormal trend.

[0139] In this module, the health threshold unit 402 obtains the health threshold, which is the critical value of the device in the normal operation state. Exceeding this range means that the device may enter an abnormal state and corresponding measures need to be taken. Compare the prediction result with the health threshold;

[0140] Prediction value < health threshold → The device is in normal state and does not require maintenance; Prediction value is close to the health threshold → The device may have problems and maintenance needs to be arranged; Prediction value exceeds the health threshold → The device may malfunction and maintenance should be arranged immediately;

[0141] That is, there is an abnormal trend. If the trend suddenly changes, the parameter will rise sharply in a short time. For example, if the temperature rises by 10°C in a short time due to overload, it is determined as abnormal heat dissipation.

[0142] A maintenance unit 403 for obtaining the optimal maintenance time, where the optimal maintenance time is based on the production plan and the remaining life, generating a maintenance plan according to the optimal maintenance time, and sending the maintenance plan to the terminal.

[0143] In this module, the maintenance unit 403 obtains the optimal maintenance time. The optimal maintenance time = predicted failure time - safety buffer time. The production plan avoids maintenance during the production peak period to reduce downtime losses. The remaining life predicts how much time the device can still operate stably in the future to ensure that maintenance is completed before the failure occurs;

[0144] Generate a maintenance plan according to the optimal maintenance time. The maintenance plan includes maintenance tasks, executors, work order numbers, and estimated man-hours. The maintenance plan will be pushed to different terminals to ensure that relevant personnel can respond in a timely manner.

[0145] In one embodiment, a computer device is provided. The computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented:

[0146] Obtain an Internet of Things (IoT) intelligent cloud architecture, which is used to transmit the massive data generated by IoT devices to the cloud for processing and analysis;

[0147] Upload real-time data information to the IoT intelligent cloud architecture, draw a real-time curve according to the recording results, draw a health curve according to historical data, compare the real-time curve with the health curve, and determine the current device operation status according to the comparison result;

[0148] Obtain fault data according to the comparison result, determine the specific fault type according to the health curves of different parameters, match the corresponding processing solutions according to the fault type, obtain the safety gradient, and match different warning levels according to different gradients;

[0149] Make a prediction based on the real-time data information, compare the prediction result with the health threshold, obtain the optimal maintenance time, generate a maintenance plan according to the optimal maintenance time, and send the maintenance plan to the terminal.

[0150] In one embodiment, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, the processor is caused to execute the following steps:

[0151] Obtain an Internet of Things (IoT) intelligent cloud architecture, which is used to transmit the massive data generated by IoT devices to the cloud for processing and analysis;

[0152] Upload real-time data information to the IoT intelligent cloud architecture, draw a real-time curve according to the recording results, draw a health curve according to historical data, compare the real-time curve with the health curve, and determine the current device operation status according to the comparison result;

[0153] Obtain fault data according to the comparison result, determine the specific fault type according to the health curves of different parameters, match the corresponding processing solutions according to the fault type, obtain the safety gradient, and match different warning levels according to different gradients;

[0154] Make a prediction based on the real-time data information, compare the prediction result with the health threshold, obtain the optimal maintenance time, generate a maintenance plan according to the optimal maintenance time, and send the maintenance plan to the terminal.

[0155] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0156] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0157] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0158] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the appended claims.

[0159] The above is only the preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for developing a service platform based on the Internet of Things intelligent cloud architecture, characterized in that, The method includes: Obtain an Internet of Things intelligent cloud architecture, which is used to transmit a large amount of data generated by Internet of Things devices to the cloud for processing and analysis; Upload real-time data information to the Internet of Things intelligent cloud architecture, draw a real-time curve according to the recording result, draw a health curve according to historical data, compare the real-time curve with the health curve, and determine the current device operation status according to the comparison result; Obtain fault data according to the comparison result, determine the specific fault type according to the health curves of different parameters, match the corresponding processing scheme according to the fault type, obtain the safety gradient, and match different warning levels according to different gradients; Make a prediction based on the real-time data information, compare the prediction result with the health threshold, obtain the optimal maintenance time, generate a maintenance plan according to the optimal maintenance time, and send the maintenance plan to the terminal.

2. A method for developing a service platform based on the Internet of Things intelligent cloud architecture according to claim 1, characterized in that, The step of uploading real-time data information to the Internet of Things intelligent cloud architecture, drawing a real-time curve according to the recording result, drawing a health curve according to historical data, comparing the real-time curve with the health curve, and determining the current device operation status according to the comparison result specifically includes: Obtain real-time data information, which is obtained through Internet of Things sensors, upload the real-time data information to the Internet of Things intelligent cloud architecture, record the real-time data information through the Internet of Things intelligent cloud architecture, and draw a real-time curve according to the recording result. The real-time curve is the real-time state of the device operation; Obtain historical data, and the Internet of Things intelligent cloud architecture draws a health curve according to the historical data. The health curve is the normal range of the device operation, and the health curve includes multiple parameters; Use the health curve as the reference value, compare the real-time curve with the health curve, obtain the comparison result, and determine the current device operation status according to the comparison result.

3. A method for developing a service platform based on the Internet of Things intelligent cloud architecture according to claim 1, characterized in that, The step of obtaining fault data according to the comparison result, determining the specific fault type according to the health curves of different parameters, matching the corresponding processing scheme according to the fault type, obtaining the safety gradient, and matching different warning levels according to different gradients specifically includes: Obtain fault data according to the comparison result. The judgment basis of the fault data is that the real-time curve exceeds the health curve, and determine the specific fault type according to the health curves of different parameters; Obtain a fault processing scheme, match the corresponding processing scheme according to the fault type, send the processing scheme to the terminal, and obtain the safety gradient. The safety gradient is different gradients from the critical value of the normal range; The safety gradient is divided into five levels of gradients, and different warning levels are matched according to different gradients, and a warning signal is sent to the terminal.

4. A method for developing a service platform based on the Internet of Things intelligent cloud architecture according to claim 1, characterized in that, The step of making a prediction based on the real-time data information, comparing the prediction result with the health threshold, obtaining the optimal maintenance time, generating a maintenance plan according to the optimal maintenance time, and sending the maintenance plan to the terminal specifically includes: Make a prediction based on the real-time data information to obtain a prediction result. The prediction is used to identify abnormal trends according to the device operation data; Obtain the health threshold, which is the critical value of the normal range, compare the prediction result with the health threshold. If it is determined that the prediction result exceeds the health threshold, there is an abnormal trend; Then obtain the optimal maintenance time, which is based on the production plan and the remaining life. Generate a maintenance plan according to the optimal maintenance time and send the maintenance plan to the terminal.

5. A method for developing a service platform based on the Internet of Things intelligent cloud architecture according to claim 3, characterized in that, The parameters include temperature, vibration, pressure, and mechanical component wear.

6. A service platform development system based on the Internet of Things intelligent cloud architecture, characterized in that, The system includes: An Internet of Things intelligent cloud architecture module that obtains the Internet of Things intelligent cloud architecture, which is used to transmit the massive data generated by Internet of Things devices to the cloud for processing and analysis; A curve module that uploads real-time data information to the Internet of Things intelligent cloud architecture, draws a real-time curve based on the recording results, draws a health curve based on historical data, compares the real-time curve with the health curve, and determines the current device operating status according to the comparison result; A fault and warning module that obtains fault data according to the comparison result, determines the specific fault type according to the health curves of different parameters, matches the corresponding processing solution according to the fault type, obtains the safety gradient, and matches different warning levels according to different gradients; A maintenance module that makes a prediction based on the real-time data information, compares the prediction result with the health threshold, obtains the optimal maintenance time, generates a maintenance plan according to the optimal maintenance time, and sends the maintenance plan to the terminal.

7. A service platform development system based on the Internet of Things intelligent cloud architecture according to claim 6, characterized in that, The curve module includes: A real-time curve unit that obtains real-time data information, which is obtained through Internet of Things sensors, uploads the real-time data information to the Internet of Things intelligent cloud architecture, records the real-time data information through the Internet of Things intelligent cloud architecture, and draws a real-time curve according to the recording results. The real-time curve is the real-time state of the device operation; A health curve unit that obtains historical data, and the Internet of Things intelligent cloud architecture draws a health curve according to the historical data. The health curve is the normal range of the device operation, and the health curve includes multiple parameters; A curve comparison unit that uses the health curve as a reference value, compares the real-time curve with the health curve, obtains the comparison result, and determines the current device operating status according to the comparison result.

8. A service platform development system based on the Internet of Things intelligent cloud architecture according to claim 7, characterized in that, The fault and warning module includes: A fault unit that obtains fault data according to the comparison result. The basis for determining the fault data is that the real-time curve exceeds the health curve, and determines the specific fault type according to the health curves of different parameters; A safety gradient unit that obtains a fault handling solution, matches the corresponding processing solution according to the fault type, sends the processing solution to the terminal, and obtains the safety gradient. The safety gradient is different gradients from the critical value of the normal range; A warning unit that divides the safety gradient into five levels of gradients, matches different warning levels according to different gradients, and sends a warning signal to the terminal.

9. A service platform development system based on the Internet of Things intelligent cloud architecture according to claim 8, characterized in that, The maintenance module includes: A trend prediction unit that makes a prediction based on the real-time data information and obtains a prediction result. The prediction is used to identify abnormal trends based on device operation data; A health threshold unit that obtains the health threshold, which is the critical value of the normal range, compares the prediction result with the health threshold, and if it is determined that the prediction result exceeds the health threshold, there is an abnormal trend; A maintenance unit that then obtains the optimal maintenance time, which is based on the production plan and the remaining life, generates a maintenance plan according to the optimal maintenance time, and sends the maintenance plan to the terminal.

10. A service platform development system based on the Internet of Things intelligent cloud architecture according to claim 9, characterized in that, The parameters include temperature, vibration, pressure, and mechanical component wear.

Images