Equipment precision management early warning system and method based on Internet of Things

Abstract

The invention relates to an equipment precision management early warning system and method based on the Internet of Things, and aims to solve the technical problem that an existing equipment management system lacks a data analysis and evaluation mechanism. The technical scheme is that the system comprises a data acquisition module, a data analysis and processing module, a function precision evaluation module, an early warning prompt module and a storage management module; the equipment precision management early warning method comprises the following steps of data acquisition and system initialization configuration, data analysis and processing, data precision evaluation, early warning prompt and data storage. The system can accurately monitor, evaluate and manage the functional precision of various industrial production devices, guarantees the reliable operation of the devices, and improves the production quality of products.

Description

Technical Field

[0001] The present invention belongs to the technical field of industrial equipment management, and particularly relates to an Internet of Things device precision management warning system and method. Background Art

[0002] In today's industrial production field, numerous devices play a crucial role in the production process, such as numerically controlled machine tools, automated production line equipment, precision instruments and meters, etc. The functional precision of these devices directly affects the quality of the final product, production efficiency, and the service life of the devices themselves. However, there are many deficiencies in equipment management at present;

[0003] On the one hand, most enterprises rely on manual regular inspections and simple conventional detection means for monitoring the functional precision of equipment. Manual inspections are prone to omissions and it is difficult to achieve real-time and continuous monitoring. It is impossible to promptly capture the instantaneous precision deviation of the equipment during operation. Conventional detections usually have a long interval time and cannot dynamically reflect the real-time state of the equipment, resulting in some potential precision problems not being discovered as early as possible, which may further cause quality defects in the produced products and affect the economic benefits of the enterprise.

[0004] On the other hand, even if some enterprises are equipped with certain data acquisition devices, they lack effective data analysis and evaluation mechanisms. The collected data is often simply recorded and the key information contained therein, such as the change trend of the equipment functional precision, cannot be deeply mined. It is also impossible to accurately judge whether the current precision state poses a threat to production. At the same time, after discovering precision problems, due to the lack of timely warnings and perfect management processes, it is difficult to arrange timely response measures such as repairs and adjustments, making the equipment may be in a non-optimal operating state for a long time, and even further exacerbating the wear of the equipment, increasing the probability of failures, and seriously affecting the continuity and stability of production. Summary of the Invention

[0005] The purpose of the present invention is to solve the above problems and provide an Internet of Things device precision management warning system and method.

[0006] To solve the above technical problems, the technical solution adopted by the present invention is:

[0007] An Internet of Things device precision management warning system includes a data acquisition module, a data analysis and processing module, a functional precision evaluation module, a warning and prompt module, and a storage and management module;

[0008] The data acquisition module includes a displacement sensor, a pressure sensor, a temperature sensor, and a vibration sensor, which are respectively installed at the detection positions of corresponding equipment components, and continuously collect the physical parameters of different components during the operation of the equipment in real time, and perform analog-to-digital conversion and data encapsulation preprocessing on the data;

[0009] The data analysis and processing module receives the collected data from the data acquisition module, and performs cleaning, fusion, and feature extraction on the data;

[0010] The function accuracy evaluation module compares and calculates the data output by the data analysis and processing module according to the preset accuracy standards and mathematical models for different types of equipment and their respective functional links, obtains the accuracy indicators of the current functions of the equipment, determines whether the data is within the normal range, and analyzes the change trend of the accuracy, providing a decision-making basis for equipment maintenance and adjustment;

[0011] The warning and prompt module determines the warning level according to the data output by the accuracy evaluation module, and issues warning information in various ways to ensure that equipment maintenance and management personnel can learn about the abnormal equipment accuracy in a timely manner and take corresponding treatment measures;

[0012] The storage management module is responsible for classifying and storing the data involved in the operation of the entire system;

[0013] The data acquisition module is electrically connected to the data analysis and processing module, the data analysis and processing module is electrically connected to the function accuracy evaluation module, the function accuracy evaluation module is electrically connected to the warning and prompt module, and the storage management module is electrically connected to the data acquisition module, the data analysis and processing module, the function accuracy evaluation module, and the warning and prompt module respectively.

[0014] Furthermore, the warning information methods in the warning and prompt module include popping up a warning window on the monitoring terminal, sending a text message to the equipment maintenance and management personnel, or pushing a mobile application message.

[0015] Furthermore, the data archiving method in the storage management module is chronological order, equipment number, or data type.

[0016] An equipment accuracy management and warning method based on the Internet of Things includes the following steps:

[0017] Step 1) Data acquisition and system initialization configuration: Each sensor in the data acquisition module obtains the running physical parameter data of each component of the equipment in real time during the normal operation of the equipment, and the collected data is preprocessed and then transmitted to the data analysis and processing module and the storage management module;

[0018] Import the pre-established accuracy standard database and mathematical model for the equipment into the function accuracy evaluation module to complete the initialization configuration of the system;

[0019] Step 2) Data analysis and processing, and the specific analysis and processing steps are as follows:

[0020] Step 2.1) Data cleaning: Through data cleaning, statistical analysis is carried out to identify and eliminate outliers and noise data caused by sensor failures and electromagnetic interference;

[0021] The data cleaning adopts an improved Z-score and sliding window joint detection method:

[0022]

[0023] Where is the median within the sliding window, is the robust standard deviation; when |z i | > 3, it is determined as an outlier, and spline interpolation is used for compensation:

[0024]

[0025] Step 2.2) Data fusion: Through the data fusion algorithm, multiple data from different sensors but related to the same device function are fused and processed;

[0026] Step 2.3) Feature extraction: Using the feature extraction algorithm, key feature parameters in the data are extracted to form an effective data set that can characterize the device function state, and it is transmitted to the accuracy evaluation module and the storage management module;

[0027] Step 3) Data accuracy evaluation: According to the imported accuracy standard database and mathematical model for this device, the operating parameters of each component of the device are compared and calculated one by one to obtain the dynamic deviation index between the collected data after analysis and processing and the standard value in the accuracy standard database. At the same time, combined with historical data and trend analysis method, it is judged whether the change trend of this accuracy index tends to be stable, gradually deteriorates or is improving, and comprehensively judge whether the functional accuracy state of the current components of the device is qualified, and output the evaluation result to the early warning prompt module and the storage management module;

[0028] The mathematical formula for the dynamic deviation index between the collected data and the standard value in the accuracy standard database is:

[0029]

[0030] Where: x(t) is the actual measurement value at time t; x std is the standard accuracy theoretical value; Δ std = x max - x min is the standard allowable deviation;

[0031] The determination rule for the functional accuracy state of device components is:

[0032]

[0033] The trend coefficient based on Exponentially Weighted Moving Average (EWMA) is:

[0034] γ(t) = λ·δ(t) + (1 - λ)·γ(t - 1)

[0035] Where: λ ∈ (0, 1): forgetting factor (typical value is 0.2)

[0036] The decision rule for the direction of the change trend is:

[0037]

[0038] Step 4) Early warning prompt: When the precision evaluation module determines that a certain functional precision index of the equipment parts exceeds the preset normal threshold range, the early warning prompt module immediately activates the early warning mechanism; at the same time, it sends a text message notification containing the same detailed content to the pre-stored equipment maintenance management personnel, and pushes the corresponding early warning message on the mobile device management application to remind the equipment maintenance management personnel to pay attention in time and take measures;

[0039] The decision rule for the early warning prompt is:

[0040]

[0041] Where: S(t) represents the comprehensive score of the current precision state of the equipment, and the formula is:

[0042]

[0043] S th1 represents the demarcation threshold between the normal state and the early warning prompt, and S th2 represents the demarcation threshold between the early warning prompt and the emergency early warning

[0044] Step 5) Data storage: The storage management module receives the data from each module in real time and stores them classified according to the time stamp, equipment number or data type.

[0045] Furthermore, the key characteristic parameters in the step 2.3) include the mean value, variance, peak value, deviation, and actual measurement value.

[0046] Furthermore, the data in the storage management module in the step 5) includes the original acquisition data, the analyzed and processed data, the precision evaluation result data, and the early warning prompt data.

[0047] Compared with the prior art, the beneficial effects of the present invention are:

[0048] 1. The functional precision management system of the present invention can continuously and stably manage the functional precision of the equipment in an all-round way, effectively ensure the reliable operation of the equipment and the improvement of the product production quality, and bring significant economic benefits and management benefits to industrial production enterprises;

[0049] 2. Each module of the present invention collaborates with and closely cooperates with each other to form a complete closed-loop management system, jointly realizing the efficient management of the functional accuracy of the equipment.

[0050] 3. The present invention is a system that can accurately monitor, evaluate, and manage the functional accuracy of various industrial production equipment, ensuring the reliable operation of the equipment and improving the production quality of products. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic structural diagram of the precision management warning system of the present invention;

[0052] Figure 2 It is a schematic flow diagram of the precision management warning method of the present invention;

[0053] Figure 3 It is a schematic flow diagram of the data analysis and processing of the present invention; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] The present invention will be further described below with reference to the drawings and embodiments.

[0055] Embodiment

[0056] Taking a numerically controlled machine tool as an example, as Figure 1 shown, an Internet of Things device-based precision management warning system includes a data acquisition module, a data analysis and processing module, a functional accuracy evaluation module, a warning prompt module, and a storage management module;

[0057] The data analysis and processing module receives the acquired data from the data acquisition module through wired or wireless means, cleans the data, eliminates interference information such as outliers and noise data, and then uses algorithms such as data fusion and feature extraction to integrate and extract features from the data, converting the chaotic raw data into effective feature data that can intuitively reflect the functional state of the equipment, providing a high-quality data basis for subsequent accuracy evaluation.

[0058] The functional accuracy evaluation module compares and calculates the data output by the data analysis and processing module according to the pre-set accuracy standards and mathematical models for different types of equipment and their respective functional links, obtains the accuracy indicators of the current functions of the equipment, determines whether the data is within the normal range, and analyzes the change trend of the accuracy, providing a decision-making basis for equipment maintenance and adjustment;

[0059] The early warning prompt module determines the early warning level according to the data output by the accuracy evaluation module. Once it is determined that the functional accuracy of the device deviates and reaches a preset threshold, it issues an early warning message by popping up a warning window on the monitoring terminal, sending a text message to the device maintenance management personnel, or pushing a mobile application message, ensuring that the device maintenance management personnel can learn about the abnormal device accuracy in a timely manner and take corresponding treatment measures immediately;

[0060] The storage management module is responsible for classifying and storing the data involved in the operation process of the entire system, such as the original acquisition data, the processed feature data, the accuracy evaluation results, and the early warning record information, according to the time sequence, device number, or data type, for convenient subsequent traceability query. It also helps the enterprise comprehensively analyze the historical operation status of the device and provides data support for optimizing the device management strategy.

[0061] The data acquisition module is electrically connected to the data analysis and processing module, the data analysis and processing module is electrically connected to the functional accuracy evaluation module, the functional accuracy evaluation module is electrically connected to the early warning prompt module, and the storage management module is respectively electrically connected to the data acquisition module, the data analysis and processing module, the functional accuracy evaluation module, and the early warning prompt module.

[0062] As Figures 2-3 shown, a device accuracy management and early warning method based on the Internet of Things includes the following steps:

[0063] Step 1) Data acquisition and system initialization configuration: Install a high-precision displacement sensor at the spindle part of the CNC machine tool to monitor the radial runout and axial runout of the spindle, and collect the displacement data of the spindle every 10 milliseconds; install a pressure sensor and a displacement sensor at the guide rail to detect the pressure on the guide rail and the displacement of the slider respectively, and feedback the pressure value on the guide rail once per second; set a temperature sensor at the position of the fan bearing to monitor the temperature change during the operation of the fan, etc. During the installation process, ensure that the sensors are firmly installed, accurately positioned, and calibrated and debugged to ensure the accuracy of the collected data. Each sensor collects the physical parameters of different components during the operation of the device in real time and continuously. These parameters cover multiple dimensions such as the mechanical motion state and working environment information of the CNC machine tool, and the sensors have the characteristics of high precision and high sensitivity to ensure the accuracy and reliability of the collected data. Then, perform analog-to-digital conversion and data encapsulation preprocessing on the data;

[0064] Connect the data acquisition module to the control system of the numerically controlled machine tool and the upper computer through wired or wireless communication. In the upper computer system software, according to the model, specifications and production process requirements of the equipment, set corresponding data acquisition frequencies, measurement ranges and other parameters for different sensors. At the same time, import the precision standard database pre-developed for this equipment, including the normal range values of various functional precisions, precision evaluation algorithm models, etc., to complete the initialization configuration work of the system.

[0065] Step 2) Data analysis and processing. The specific analysis and processing steps are as follows:

[0066] Step 2.1) Data cleaning: Through data cleaning, statistically analyze and identify and eliminate outliers and noise data caused by sensor failures and electromagnetic interference.

[0067] The data cleaning adopts an improved Z-score and sliding window joint detection method:

[0068]

[0069] where is the median within the sliding window, is the robust standard deviation; when ∣z i ∣>3, it is determined as an outlier, and spline interpolation is used for compensation:

[0070]

[0071] Step 2.2) Data fusion: Through the data fusion algorithm, fuse multiple data from different sensors on the numerically controlled machine tool, such as fusing multi-dimensional data such as the displacement, temperature and vibration of the machine tool spindle to more comprehensively reflect the actual operating state of the spindle.

[0072] Step 2.3) Feature extraction: Use the feature extraction algorithm to extract key feature parameters such as the mean, variance, peak value, etc. from the data to form an effective data set that can characterize the functional state of the equipment, and transfer it to the precision evaluation module and the storage management module.

[0073] Step 3) Data accuracy evaluation: According to the imported accuracy standard database and mathematical model for the device, compare and calculate the operating parameters of each component of the device one by one to obtain the dynamic deviation index between the collected data after analysis and processing and the standard value in the accuracy standard database. For example, for the radial runout accuracy of the spindle of a numerically controlled machine tool, compare and calculate the actually collected and processed displacement data with the preset radial runout accuracy standard range to obtain the specific value of the current spindle radial runout accuracy and the deviation degree from the standard value. At the same time, combine historical data and trend analysis method to judge whether the change trend of this accuracy index tends to be stable, gradually deteriorate or is improving, comprehensively determine whether the functional accuracy status of the current components of the device is qualified, and output the evaluation result to the early warning prompt module and the storage management module;

[0074] The mathematical formula for the dynamic deviation index between the collected data and the standard value in the accuracy standard database is:

[0075]

[0076] Where: x(t) is the actual measured value at time t; x std is the standard accuracy theoretical value; Δ std =x max -x min is the standard allowable deviation;

[0077] The determination rule for the functional accuracy status of device components is:

[0078]

[0079] The trend coefficient based on the exponentially weighted moving average (EWMA) is:

[0080] γ(t)=λ·δ(t)+(1-λ)·γ(t - 1)

[0081] In the formula: λ∈(0,1): Forgetting factor (typical value is 0.2)

[0082] The determination rule for the direction of the change trend is:

[0083]

[0084] Step 4) Early warning prompt: When the precision evaluation module determines that a certain functional precision index of the equipment component exceeds the preset normal threshold range, the early warning prompt module immediately activates the early warning mechanism. For example, if the radial runout precision deviation of the spindle of a numerically controlled machine tool exceeds the set maximum allowable value, the early warning prompt module will pop up a prominent warning window on the monitoring terminal, displaying the specific information of the abnormal spindle precision, including the deviation value, the time of the abnormality, etc.; at the same time, it will send a text message notification containing the same detailed content to the pre-stored equipment maintenance management personnel, and push the corresponding early warning message on the mobile device management application, reminding the equipment maintenance management personnel to pay attention in time and take measures, such as shutting down for inspection, adjusting the spindle components, etc., to restore the normal precision of the equipment;

[0085] The decision-making judgment rule for the early warning prompt is:

[0086]

[0087] Among them: S(t) represents the comprehensive score of the current precision state of the equipment, and the formula is:

[0088]

[0089] S th1 represents the demarcation threshold between the normal state and the early warning prompt, and S th2 represents the demarcation threshold between the early warning prompt and the emergency early warning;

[0090] Step 5) Data storage: The storage management module receives the data from each module in real time, including the original acquisition data, the data after analysis and processing, the precision evaluation result data, and the early warning prompt data, and classifies and stores them according to the time stamp, equipment number, and data type. For example, the original data of each sensor of the numerically controlled machine tool collected every day is stored in a folder named after the current date, and the data of each sensor is stored separately as a file; the precision evaluation results are recorded in the corresponding table of the database in sequence according to the evaluation time, which is convenient for querying the change of the equipment precision state within a certain period of time at any time. When in-depth maintenance, performance analysis, or quality traceability of the equipment is required, relevant personnel can input the corresponding retrieval conditions through the query interface provided by the system to quickly obtain the required data information and provide data support for further decision-making.

Claims

1. A precision management early warning system based on IoT equipment, characterized in that: It includes data acquisition module, data analysis and processing module, function accuracy assessment module, early warning module and storage management module; The data acquisition module includes a displacement sensor, a pressure sensor, a temperature sensor and a vibration sensor, which are respectively installed at the detection positions of the corresponding equipment parts, collect the physical parameters of different parts during the operation of the equipment in real time and continuously, and perform analog-to-digital conversion and data packaging preprocessing on the data; The data analysis and processing module receives the collected data from the data collection module, and performs data cleaning, fusion, and feature extraction processing; The functional accuracy assessment module compares and calculates the data output by the data analysis and processing module according to the pre-set accuracy standards and mathematical models formulated for different types of equipment and their various functional links, obtains the accuracy index of each function of the equipment, determines whether the data is within the normal range, and analyzes the change trend of the accuracy, providing a decision-making basis for equipment maintenance and adjustment; The early warning prompt module determines the early warning level according to the data output by the accuracy evaluation module, and issues early warning information in a variety of ways to ensure that the equipment maintenance management personnel can be informed of the abnormal equipment accuracy at the first time and take corresponding treatment measures in time; The storage management module is responsible for classifying, storing and archiving the data involved in the operation of the entire system; The data acquisition module is electrically connected to the data analysis and processing module, the data analysis and processing module is electrically connected to the function accuracy assessment module, the function accuracy assessment module is electrically connected to the early warning prompt module, and the storage management module is electrically connected to the data acquisition module, the data analysis and processing module, the function accuracy assessment module, and the early warning prompt module respectively.

2. According to claim 1, the early warning system based on the precision management of Internet of Things equipment is characterized in that: The warning information mode in the warning prompt module includes popping up a warning window on the monitoring terminal, sending a text message to the equipment maintenance manager, or pushing a mobile phone application message.

3. According to claim 1, the early warning system based on the precision management of Internet of Things equipment is characterized in that: The data archiving method in the storage management module is time sequence, device number or data type.

4. A device precision management early warning method based on the Internet of Things device precision management early warning system according to any one of claims 1 to 3, characterized in that: The steps include: Step 1) Data acquisition and system initialization configuration: Each sensor in the data acquisition module acquires the operating physical parameter data of each component of the equipment in real time during the normal operation of the equipment, and the collected data is pre-processed and transmitted to the data analysis and processing module and the storage management module; Import the accuracy standard database and mathematical model pre-established for the device into the functional accuracy assessment module to complete the initial configuration of the system; Step 2) Data analysis and processing. The specific analysis and processing steps are as follows: Step 2.1) Data cleaning: Through data cleaning, statistical analysis is used to identify and eliminate outliers and noise data caused by sensor failure and electromagnetic interference; Data cleaning uses an improved Z-score and sliding window joint detection method: in is the median in the sliding window, is the robust standard deviation; when |z i When |>3, it is determined as an outlier and compensated by spline interpolation: Step 2.2) Data fusion: Multiple data from different sensors but related to the same device function are fused through data fusion algorithm; Step 2.3) Feature extraction: Use feature extraction algorithm to extract key feature parameters from the data, form a valid data set that can characterize the functional status of the equipment, and pass it to the accuracy assessment module and storage management module; Step 3) Data accuracy assessment: According to the imported accuracy standard database and mathematical model for the equipment, the operating parameters of each component of the equipment are compared and calculated one by one, and the dynamic deviation index between the collected data after analysis and processing and the standard value in the accuracy standard database is obtained. At the same time, combined with historical data and trend analysis method, it is judged whether the change trend of the accuracy index is stabilizing, gradually deteriorating or improving, and whether the functional accuracy status of the current components of the equipment is qualified is comprehensively judged, and the evaluation results are output to the early warning prompt module and the storage management module; The mathematical formula for the dynamic deviation index between the collected data and the standard value in the accuracy standard database is: Where: x(t) is the actual measured value at time t; x std is the theoretical value of standard accuracy; Δ std =x max -x min is the standard allowable deviation; The rules for determining the functional accuracy status of equipment parts are: The trend coefficient based on the exponentially weighted moving average (EWMA) is: γ(t)=λ·δ(t)+(1-λ)·γ(t-1) Where: λ∈(0,1): forgetting factor (typical value is 0.2) The rules for determining the direction of the changing trend are: Step 4) Early warning: When the accuracy assessment module determines that a functional accuracy index of a device component exceeds the preset normal threshold range, the early warning module immediately activates the early warning mechanism; at the same time, a text message notification containing the same detailed content is sent to the pre-stored equipment maintenance manager, and the corresponding early warning message is pushed on the mobile device management application to remind the equipment maintenance manager to pay attention and take measures in time; The decision-making rules for early warning prompts are: Where: S(t) represents the comprehensive score of the current accuracy status of the device, and the formula is: S th1 Indicates the demarcation threshold between normal state and warning prompt, S th2 Indicates the demarcation threshold between early warning and emergency warning; Step 5) Data storage: The storage management module receives data from each module in real time and stores them by categories according to timestamp, device number or data type.

5. According to claim 4, a method for early warning based on the precision management of Internet of Things devices is characterized in that: The key characteristic parameters in step 2.3) include mean, variance, peak, deviation, and actual measurement value.

6. According to claim 4, a method for early warning based on the precision management of Internet of Things devices is characterized in that: The data stored in the management module in step 5) includes original collected data, analyzed and processed data, accuracy assessment result data and early warning prompt data.

Images