Complex equipment production site old equipment data acquisition and control method based on non-intrusive automation

Abstract

The invention discloses a non-intrusive automation-based old equipment data acquisition and control method for a complex equipment production site, and the method comprises the steps: selecting the type and number of sensors according to the structure, function and operation mode of a to-be-acquired and controlled object; selecting a non-intrusive automation framework; according to the structure and the form corresponding to the selected non-intrusive framework, corresponding hardware and non-intrusive software modules are connected to a field object to be collected and controlled, and a collection and control device based on the non-intrusive framework is formed; performing parameter adjustment on the acquisition and control equipment to obtain acquisition target data and corresponding data during control; identifying or predicting the sensor for collecting the target data; automatic data acquisition and automatic parameter control of the acquisition and control equipment are carried out, and the results of automatic data acquisition and automatic parameter control are fed back and recorded. According to the method, the old equipment does not need to be subjected to structural change or shutdown operation, so that the production continuity is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of data acquisition and control, and in particular to a method for data acquisition and control of obsolete equipment at a complex equipment production site based on non-invasive automation. Background Art

[0002] In the production site of complex equipment, some equipment has been in use for a long time, its control interface is outdated or has no control interface, and the equipment has no post-maintenance, resulting in the equipment being unable to connect with the information system. The existing feasible solutions are to carry out technical transformation, install new parts, new devices, and new accessories on the old equipment to improve the technical performance. This method not only has high transformation risks, but also causes equipment downtime and production suspension, delaying production plans and other problems. Summary of the invention

[0003] In view of this, the present invention provides a method for collecting and controlling obsolete equipment data at a complex equipment production site based on non-invasive automation.

[0004] The present invention discloses a method for collecting and controlling data of obsolete equipment at a complex equipment production site based on non-invasive automation, which comprises:

[0005] Step 1: Determine the objects to be collected and controlled on site, and select the type and quantity of sensors according to the structure, function and operation mode of the objects to be collected and controlled;

[0006] Step 2: Choose a non-intrusive automation framework;

[0007] Step 3: According to the structure and form of the selected non-intrusive framework, the corresponding hardware and non-intrusive software modules are connected to the objects to be collected and controlled on site to form a collection and control device based on the non-intrusive framework; the collection and control device is adjusted to obtain target data and control parameters. The target data include displacement, force, temperature, flow, pressure, vibration signal, speed, power, current, voltage, power factor, gas composition and humidity;

[0008] Step 4: Use data analysis to identify or predict the sensor that collects the target data;

[0009] Step 5: Carry out automated data collection and automated parameter control of the acquisition and control equipment, and provide feedback and record the results of automated data collection and automated parameter control.

[0010] Furthermore, the step 1 comprises:

[0011] If the structure of the object to be collected and controlled is simple, choose the deep learning method; otherwise, if the structure of the object to be collected and controlled is complex, choose the edge computing method.

[0012] Furthermore, the step 2 comprises:

[0013] A matching non-intrusive method is selected based on the sensor. If the sensor's measurement is within the monitoring range, the framework acquisition method is accessed, otherwise the edge computing module is configured.

[0014] Furthermore, the parameter adjustment of the acquisition and control equipment includes:

[0015] Optimize the location of acquisition and control nodes, configure parameters, and configure edge computing modules.

[0016] Furthermore, the step 3 comprises:

[0017] Perform hardware optimization of old equipment, including hardware replacement, hardware connection detection and hardware replacement result evaluation;

[0018] When evaluating the results of hardware replacement, first evaluate the compatibility of the hardware replacement with the old equipment hardware. Then, based on the impact of the hardware interface on data acquisition and control, evaluate the impact of the hardware replacement on the acquisition of target data and the control results of the target device.

[0019] Furthermore, the step 4 comprises:

[0020] When the data is unpredictable or biased, repeat step 3, otherwise proceed to step 5; when predicting data, combine historical collected data, equipment conditions and production goals, predict the data of the required parameters of the equipment to be collected and calculate the target equipment operation value, determine the target state of control and action, and when the required data or operation value cannot be predicted, repeat step 3, otherwise proceed to step 5.

[0021] Furthermore, the step 5 comprises:

[0022] The target device is used to perform result analysis to collect and control the results of automated data collection and automated parameter control of the equipment and record them, and analyze the effectiveness of collection and control; based on the analysis of the effectiveness of collection and control, analyze the effectiveness of the collection and control equipment and automated data collection and automated parameter control; wherein the results of automated data collection and automated parameter control of the collection and control equipment include the results of control feedback, the results of automated data collection and automated control, the target device data source, the target device data analysis and data visualization.

[0023] Furthermore, the step 3 also includes:

[0024] Evaluate the matching degree between the hardware and the non-intrusive automation framework; the hardware connection detection is performed by detecting the data transmission speed at the connection; if the data transmission speed at the hardware connection is lower than the preset value, the antenna is increased or the hardware data transmission protocol is optimized to complete the data connection task between the hardware device and the acquisition platform; when the data connection task between the hardware device and the acquisition platform is completed, the non-intrusive automation framework and the acquisition target device hardware are tested for matching degree, and matching degree detection, sensor calibration and sensor recalibration are used to evaluate the performance of automated data acquisition and parameter control.

[0025] Furthermore, when adopting the deep control method based on deep learning, first optimize the matching degree between the hardware and the automated control method, and then optimize the impact of the automated control method on the operating equipment, optimize the impact of the software and hardware on the control of the target equipment, and achieve optimized control of the target equipment operation value, complete the accurate collection of control data, and then optimize the deep acquisition and control system results analysis; optimize the deep acquisition and control equipment, and analyze the impact of hardware performance and software performance.

[0026] Furthermore, after completing the matching of the non-intrusive automation framework with the hardware of the target device for acquisition, the matching degree of the non-intrusive automation framework and the hardware of the target device for control are tested. When the data consistency meets the requirements, the acquisition and control results are analyzed according to the impact of the automation control method on the control system. The deep learning method is used to obtain the target device data and the target device operation value, and the accurate acquisition of the acquisition data and the accurate acquisition of the control data are completed.

[0027] Due to the adoption of the above technical solution, the present invention has the following advantages:

[0028] Application of non-invasive automation methods: Unlike the prior art of directly modifying old equipment and invasive data collection, the present invention adopts a non-invasive automation method. By selecting appropriate sensors and data collection methods, this method does not require structural changes or shutdown operations on old equipment, avoids interference with the production process, and ensures the continuity of production. Compared with traditional equipment modification methods, it greatly improves the convenience and flexibility of the data collection and control process, while reducing equipment downtime and maintenance costs.

[0029] Combination of multi-dimensional data collection and edge computing: This solution uses a variety of sensors to collect diversified data (including displacement, force, temperature, pressure, etc.), and combines edge computing to realize local data processing and real-time feedback. This method improves the accuracy and response speed of data collection, especially in complex working conditions, it can obtain accurate operating parameters in real time, significantly improving the overall control accuracy and efficiency of the system. Compared with the existing technology that relies only on the central processing system, this solution reduces network latency problems and improves the system's adaptability.

[0030] Application of automatic parameter adjustment and deep learning: The present invention uses an automatic parameter adjustment method combined with a deep learning algorithm to optimize the acquisition and control equipment, and can predict and control the optimization based on historical data and real-time data, thus enhancing the intelligence level of the system. In the prior art, manual parameter adjustment is usually inefficient and error-prone, while this invention reduces manual intervention and improves the efficiency and accuracy of parameter adjustment by introducing automatic parameter adjustment and deep learning algorithms.

[0031] Equipment automation control feedback and optimization: Compared with the existing technology, this solution places special emphasis on the feedback and optimization functions of equipment automation control. Through real-time monitoring and data recording of the control process, the system can analyze the control effect and make self-adjustments to ensure the long-term stability and efficiency of the system. Compared with the simple acquisition control method in the existing technology, this solution enhances the reliability and flexibility of the system through the feedback mechanism and reduces the risk of misoperation during equipment operation.

[0032] Hardware optimization and compatibility enhancement of old equipment: For old equipment, the present invention proposes a method of hardware optimization and matching detection, which can replace and upgrade hardware under the premise of ensuring device compatibility. Compared with the device incompatibility problems that may be caused by the prior art, the present invention ensures the effective connection between old equipment and the new acquisition system through the optimization and performance evaluation of the hardware interface, thereby improving the compatibility of the entire system and the stability of data transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0034] Figure 1 The process of automated data collection and control according to an embodiment of the present invention;

[0035] Figure 2 is a selection and configuration flow chart of an embodiment of the present invention;

[0036] Figure 3 A data prediction and hardware optimization cycle decision flow chart of an embodiment of the present invention;

[0037] Figure 4 The present invention is a flowchart of hardware and automation framework matching detection and optimization according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The present invention is further described in conjunction with the accompanying drawings and embodiments, and the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field should fall within the scope of protection of the embodiments of the present invention.

[0039] To avoid the problem of invasive equipment modification: the existing technology usually requires structural modification or shutdown of old equipment, affecting production continuity. The present invention adopts a non-invasive automation method to achieve real-time collection and control of equipment without shutdown and modification.

[0040] In view of the problem of limited data collection types: the data types collected by the existing technology are relatively single and cannot fully monitor the equipment status. The present invention collects multi-dimensional data such as displacement, temperature, pressure, vibration, etc. through multiple sensors to improve the comprehensiveness and accuracy of equipment monitoring.

[0041] In view of the problem of data processing delay and lack of real-time performance: the traditional system relies on the central processing system, there is network delay, which affects the real-time performance. The present invention optimizes the data processing speed through edge computing technology and realizes real-time collection and control feedback.

[0042] Aiming at the problem that equipment parameter adjustment is complex and relies on manual work: the equipment parameter adjustment in the prior art relies on manual work, which is inefficient and prone to errors. The present invention introduces automatic parameter adjustment and deep learning algorithms to reduce manual intervention and improve parameter adjustment efficiency and accuracy.

[0043] Aiming at the problem of poor compatibility of old equipment and difficulty in hardware upgrade: traditional methods are difficult to achieve compatibility between old equipment and new systems. The present invention ensures the compatibility of old equipment and the feasibility of upgrade through hardware optimization and interface matching detection.

[0044] In view of the problem of insufficient feedback and optimization of control effect: the existing system lacks an effective control effect feedback mechanism. The present invention realizes system self-optimization and adjustment through automated control feedback and historical data analysis, thereby improving the accuracy and stability of control.

[0045] See also Figure 1-Figure 4 The present invention provides an embodiment of a method for collecting and controlling old equipment data at a complex equipment production site based on non-intrusive automation, which comprises the following steps:

[0046] Step 1: Determine the objects to be collected and controlled on site; then select the type and quantity of sensors according to the structure, function and operation mode of the objects to be collected and controlled;

[0047] Step 2: Select the non-intrusive automation framework: According to the selection of the sensor, a matching non-intrusive acquisition and control method will be selected. When the sensor measurement is not within the monitoring range of the system sensor or detector, the acquisition method based on the access framework will be selected;

[0048] Step 3: According to the structure and form of the selected non-intrusive framework, the corresponding hardware and non-intrusive software modules are connected to the objects to be collected and controlled on site to form a collection and control device based on the non-intrusive framework; the collection and control device is adjusted to obtain the collection target data and the corresponding data when controlling. The collected target data includes displacement, force, temperature, flow, pressure, vibration signal, speed, power, current, voltage, power factor, gas composition and humidity;

[0049] Step 4: Use data analysis to identify or predict the sensors that collect the target data. When the data is unpredictable or biased, combine the historical collected data, equipment conditions and production goals during data prediction to predict the data of the required parameters of the equipment to be collected and calculate the target equipment operation value to determine the target state of control and action. When the required data or operation value cannot be predicted, repeat step 3, otherwise proceed to the next step;

[0050] Step 5: Carry out automated data collection and automated parameter control of the acquisition and control equipment, and provide feedback and record the results of automated data collection and automated parameter control.

[0051] In step 1, if the structure of the object to be collected and controlled is simple, the working principle is relatively easy to understand, and there are relatively sufficient operators, then the automation method based on deep learning is selected. Otherwise, if the structure of the object to be collected and controlled is complex, the working principle is difficult to understand, and there are no operators, then the automation method of old equipment based on edge computing is selected. Automation methods based on deep learning: including image recognition, pattern recognition, predictive analysis, etc., usually use algorithms such as convolutional neural networks (CNN) and recursive neural networks (RNN) to process and analyze data.

[0052] In step 1, the focus is on sensor selection, while the subsequent instructions further guide the selection of appropriate automation methods by considering the complexity of the object and the operator's situation. Sensor selection and automation methods are interrelated to ensure that the overall system can operate efficiently. Specifically, simple objects may be suitable for deep learning methods, while complex objects are more suitable for edge computing. This logic ensures that appropriate choices are made in different situations.

[0053] In step 3, Figure 2 As shown, the acquisition and control equipment is adjusted, including optimizing the acquisition and control node locations, configuring parameters, and configuring edge computing modules.

[0054] In step 3, if the structure of the automation control object is simple, the working principle is relatively easy to understand, and there are relatively sufficient operators, then the automation method based on deep learning control is selected; otherwise, if the structure of the automation control object is complex, the working principle is difficult to understand, and there are no operators, then the automation method based on edge computing is selected.

[0055] In step 3, when optimizing the automation method, the historical data and historical control tasks of the acquisition and control equipment are analyzed, the data interface, data processing flow, data storage flow and data visualization interface are optimized, and the data interface optimization results, data processing flow optimization results, data storage flow optimization results and data visualization flow optimization results are obtained.

[0056] In step 3, after selecting the non-intrusive method, the old equipment hardware optimization is also performed, and the old equipment hardware optimization includes hardware replacement, hardware connection detection and hardware replacement result evaluation, such as Figure 3 shown.

[0057] In step 3, when evaluating the hardware replacement results, first evaluate the compatibility between the hardware replacement and the old equipment hardware, and then analyze the impact of the hardware interface on data acquisition and control to evaluate the impact of the hardware replacement on the acquisition of target data and the control results of the target device.

[0058] like Figure 3 As shown, the step of providing feedback on the results of automated data collection and automated parameter control obtained in step 5 includes: using the target device to execute the results to analyze the results of automated data collection and automated parameter control of the collection and control equipment; recording the results of automated data collection and automated parameter control of the collection and control equipment, and analyzing the effectiveness of the collection and control; and analyzing the effectiveness of the collection and control equipment and the automated data collection and automated parameter control based on the analysis of the effectiveness of the collection and control.

[0059] In the step of recording the results of automated data collection and automated parameter control obtained in step 5, the results of control feedback, the results of automated data collection and automated control, the target device data source, the target device data analysis and data visualization are recorded.

[0060] In step 3, see Figure 4After the non-intrusive acquisition method is deployed, an evaluation of the matching degree between the hardware and the acquisition framework will also be obtained; the hardware connection detection is performed by detecting the data transmission speed at the connection; if the data transmission speed at the hardware connection is low, the antenna is increased or the hardware data transmission protocol is optimized to complete the data connection task between the hardware device and the acquisition platform; when the data connection task between the hardware device and the acquisition platform is completed, the non-intrusive automation framework and the acquisition target device hardware are matched, and the matching degree detection, sensor calibration and sensor recalibration are used to evaluate the performance of automated data acquisition and parameter control; the acquisition and control equipment are adjusted, including optimizing the acquisition and control node position, configuring parameters, configuring edge computing modules, and obtaining the acquisition target data and the corresponding position data, parameter data, and edge computing result data when performing control.

[0061] In step 3, when adopting the deep control method based on deep learning, first optimize the matching degree between the hardware and the automated control method, and then optimize the influence of the software and hardware on the control of the target device based on the impact analysis of the automated control method on the operating device, so as to optimize the target device to control the target device operation value and complete the accurate collection of control data.

[0062] In step 3, after obtaining the optimized control target device operation value and completing the accurate collection of control data, the depth collection and control system result analysis is also optimized; the depth collection and control equipment is optimized to analyze the impact of hardware performance and software performance.

[0063] After completing the matching degree between the hardware and the deep learning automated control method, the non-intrusive automation framework is tested for matching degree with the hardware of the target control device. When the data consistency is high, the collection and control results are analyzed based on the impact of the automated control method on the control system. The deep learning method is used to obtain the target device data and target device operation value, and the accurate collection of the collection data and the accurate collection of the control data are completed.

[0064] When adopting the deep control method based on deep learning, the deep learning method is optimized and the acquisition and control results are analyzed, the acquisition and control results are recorded, and the target device data analysis results are generated into a visual interface.

[0065] In step 3, when optimizing the automation method, the historical data and historical control tasks of the acquisition and control equipment are analyzed, the data interface, data processing flow, data storage flow and data visualization interface are optimized, and the data interface optimization results, data processing flow optimization results, data storage flow optimization results and data visualization flow optimization results are obtained.

[0066] For ease of understanding, the present invention provides the following more specific embodiments:

[0067] Efficient data collection and control of old equipment at the production site. The specific implementation method includes multiple steps, each of which has necessary and optional structures to ensure the integrity and feasibility of the solution.

[0068] Implementation method 1:

[0069] First, select old equipment that needs to be collected and controlled, such as conveyor belts that have been used on the production line for more than 10 years, and make improvements to the problems of low efficiency and high failure rate. Install displacement sensors, temperature sensors, and vibration sensors to monitor the motion state of the conveyor belt, the operating temperature of the equipment, and potential mechanical failures, respectively. Through non-invasive automation technology, build an automated data processing framework based on deep learning, connect sensors and data processing units, intelligently analyze the operating status of the equipment, and automatically adjust the equipment. Data transmission is connected wirelessly, the collection frequency is set, and the control strategy is adjusted in real time according to the operating status of the equipment. The collected data is analyzed by the deep learning model, and the equipment operating parameters are automatically adjusted according to the prediction results to ensure safe and efficient operation of the equipment. The data results are fed back through the system, and the equipment performance is regularly analyzed and optimized, and reports are generated to evaluate the operating efficiency and make further improvements.

[0070] Implementation method 2:

[0071] A gas compressor is selected as the object of collection and control. Pressure sensors, flow sensors and temperature sensors are selected and installed at the gas outlet, air inlet and outside the equipment to monitor the operating status. Edge computing technology is used to perform real-time data processing and automatic control through the edge computing unit to avoid data delay. The sensor is connected to the edge computing unit wirelessly, and the collected data is transmitted to the edge computing system in real time for analysis and adjustment of the equipment. This implementation method can further choose to integrate a fault alarm function to notify the operator in time and optimize the equipment operation strategy. The data is analyzed and fed back, and the equipment performance is continuously adjusted according to the actual operation results to keep the equipment running efficiently.

[0072] Implementation method three:

[0073] It is suitable for motors with simple structures. The basic operating parameters of the equipment are monitored by installing current sensors and temperature sensors. The sensors are installed near the power cord and on the equipment housing respectively. The collected data is used to analyze the operating status of the motor. Deep learning or edge computing can be used for data processing, and data transmission is carried out by wired or wireless means. After collecting and analyzing the data, the operating frequency is controlled according to the actual operating status of the motor to ensure efficient operation of the equipment. This solution can choose to add a speed sensor according to needs to enhance the monitoring effect, and a simple control interface can be used to enable operators to manage the operating status of the equipment more conveniently.

[0074] The key points and protection points of the present invention are mainly reflected in the following aspects:

[0075] Application of non-intrusive data acquisition and control technology: The core technology of this invention is to use non-intrusive methods to achieve data acquisition and automatic control of old equipment. By installing sensors and performing data acquisition and control without significantly modifying or interfering with old equipment, the original functions of the equipment are ensured to be intact and it is easy to deploy and apply quickly.

[0076] Automated control methods based on deep learning or edge computing: In the process of intelligent transformation of old equipment, this invention proposes two different automated control methods based on deep learning or edge computing. According to the complexity and operating principle of the equipment, the most suitable control method is selected to ensure that the control accuracy and efficiency of the equipment are greatly improved. This flexible intelligent control solution is a key technical point protected in this invention.

[0077] Multi-sensor combination and optimization: According to different equipment types and functions, multiple sensors (such as temperature, vibration, displacement, pressure, etc.) are selected for combination, and the comprehensive monitoring of the equipment operation status is achieved in a non-invasive manner, and edge computing is combined for real-time optimization and adjustment. This multi-sensor combination and dynamic adjustment technology plays a key role in equipment status monitoring and fault prediction, and is the focus of invention protection.

[0078] Automated data collection and control feedback mechanism: This invention proposes an automated data collection and feedback control mechanism for old equipment. By collecting and analyzing equipment operation data in real time, it automatically adjusts the equipment's operating parameters to ensure that the equipment is always in the best working state. This feedback mechanism ensures that the equipment can quickly adjust according to data changes, avoid equipment failure or excessive energy consumption, and enhance the safety and efficiency of equipment operation.

[0079] Data transmission and hardware matching optimization: In the present invention, data transmission optimization and hardware and acquisition platform matching evaluation are also important technical points. By detecting sensor connection and data transmission rate, antenna gain or transmission protocol optimization is performed to ensure efficient connection between hardware equipment and non-intrusive acquisition framework and data transmission stability, thereby ensuring the reliability and real-time performance of the automation control system.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for data collection and control of obsolete equipment at a complex equipment production site based on non-invasive automation, characterized in that: include: Step 1: Determine the objects to be collected and controlled on site, and select the type and quantity of sensors according to the structure, function and operation mode of the objects to be collected and controlled; Step 2: Choose a non-intrusive automation framework; Step 3: Connect the corresponding hardware and non-intrusive software modules to the objects to be collected and controlled on site according to the structure and form of the selected non-intrusive framework, so as to form a collection and control device based on the non-intrusive framework; Adjust the parameters of the acquisition and control equipment to obtain target data and control parameters. The target data include displacement, force, temperature, flow, pressure, vibration signal, speed, power, current, voltage, power factor, gas composition and humidity; Step 4: Use data analysis to identify or predict the sensor that collects the target data; Step 5: Carry out automated data collection and automated parameter control of the acquisition and control equipment, and provide feedback and record the results of automated data collection and automated parameter control.

2. The method according to claim 1, characterized in that The step 1 comprises: If the structure of the object to be collected and controlled is simple, choose the deep learning method; otherwise, if the structure of the object to be collected and controlled is complex, choose the edge computing method.

3. The method according to claim 1, characterized in that The step 2 comprises: Select a matching non-intrusive method based on the sensor. If the sensor's measurement is within the monitoring range, access the framework collection method, otherwise configure the edge computing module.

4. The method according to claim 1, characterized in that: The parameter adjustment of the acquisition and control equipment includes: Optimize the location of acquisition and control nodes, configure parameters, and configure edge computing modules.

5. The method according to claim 1, characterized in that The step 3 comprises: Perform hardware optimization of old equipment, including hardware replacement, hardware connection detection and hardware replacement result evaluation; When evaluating the results of hardware replacement, first evaluate the compatibility of the hardware replacement with the old equipment hardware. Then, based on the impact of the hardware interface on data acquisition and control, evaluate the impact of the hardware replacement on the acquisition of target data and the control results of the target device.

6. The method according to claim 1, characterized in that The step 4 comprises: When the data is unpredictable or biased, repeat step 3, otherwise proceed to step 5; when predicting data, combine historical collected data, equipment conditions and production goals, predict the data of the required parameters of the equipment to be collected and calculate the target equipment operation value, determine the target state of control and action, and when the required data or operation value cannot be predicted, repeat step 3, otherwise proceed to step 5.

7. The method according to claim 1, characterized in that The step 5 comprises: The target device is used to perform result analysis to collect and control the results of automated data collection and automated parameter control of the equipment and record them, and analyze the effectiveness of collection and control; based on the analysis of the effectiveness of collection and control, analyze the effectiveness of the collection and control equipment and automated data collection and automated parameter control; wherein the results of automated data collection and automated parameter control of the collection and control equipment include the results of control feedback, the results of automated data collection and automated control, the target device data source, the target device data analysis and data visualization.

8. The method according to claim 1, characterized in that The step 3 also includes: Evaluate the matching degree between the hardware and the non-intrusive automation framework; the hardware connection detection is performed by detecting the data transmission speed at the connection; if the data transmission speed at the hardware connection is lower than the preset value, the antenna is increased or the hardware data transmission protocol is optimized to complete the data connection task between the hardware device and the acquisition platform; when the data connection task between the hardware device and the acquisition platform is completed, the non-intrusive automation framework and the acquisition target device hardware are tested for matching degree, and matching degree detection, sensor calibration and sensor recalibration are used to evaluate the performance of automated data acquisition and parameter control.

9. The method according to claim 1, characterized in that: When adopting the deep control method based on deep learning, first optimize the matching degree between hardware and automated control method, then analyze the impact of automated control method on operating equipment, optimize the impact of software and hardware on target equipment control, optimize the target equipment operation value, complete the accurate collection of control data, and then optimize the deep acquisition and control system results analysis; optimize deep acquisition and control equipment, and analyze the impact of hardware performance and software performance.

10. The method according to claim 8, characterized in that After completing the matching of the non-intrusive automation framework and the hardware of the target device for acquisition, the matching degree of the non-intrusive automation framework and the hardware of the target device for control are tested. When the data consistency meets the requirements, the collection and control results are analyzed according to the impact of the automation control method on the control system. The deep learning method is used to obtain the target device data and the target device operation value, and the accurate collection of the acquisition data and the accurate collection of the control data are completed.

Images