Big data processing analysis system based on cloud platform

Abstract

The invention discloses a big data processing and analyzing method based on a cloud platform. The method comprises the following steps of S1, collecting characteristic data of equipment in an operation state by arranging a sensor on the equipment; s2, analyzing the state of the part through a special visual acquisition module and an AI visual algorithm, and uploading the state to a cloud platform; s3, analyzing the operation state of the equipment through an anomaly detection module, and uploading the operation state to the cloud platform; s4, positioning the position of the fault equipment and the personnel distribution position through a positioning unit, and reasonably distributing technical personnel; s5, predicting the equipment state in the next day through a prediction module, and uploading a result to the cloud platform; s6, predicting the use time of the raw materials, and performing automatic replenishment before the raw materials are about to be used up; s7, the data are converted into a visual chart through an equipment state visualization module, and the method has the advantages that human resources are reasonably distributed, and stable operation of equipment is ensured.

Description

Technical Field

[0001] This invention relates to the field of big data processing and analysis technology, specifically to a big data processing and analysis system based on a cloud platform. Background Technology

[0002] A cloud platform refers to a hardware-based service that provides computing, networking, and storage capabilities.

[0003] Currently, factory production activities are inseparable from the safe and stable operation of equipment. Equipment operating on fixed procedures inevitably encounters problems, especially in the production of components. Even minor issues with production equipment can affect the final product quality. Traditional production models typically employ one or even several technicians to ensure safe and stable operation. However, since equipment operates stably most of the time, minimal technical supervision is required, leading to a waste of human resources. Minor equipment malfunctions are often difficult to detect, and continued production under these circumstances results in defective components and wasted raw materials. While some factories have adopted digital technology to monitor equipment, the results have been less than ideal, only slightly reducing the need for technical personnel and not addressing the issue of irrational human resource allocation. Therefore, designing a cloud-based big data processing and analysis system that rationally allocates human resources and ensures stable equipment operation to save costs is essential. Summary of the Invention

[0004] The purpose of this invention is to provide a big data processing and analysis system based on a cloud platform to solve the problems mentioned in the background art.

[0005] To address the aforementioned technical problems, this invention provides the following technical solution: a big data processing and analysis method based on a cloud platform, comprising the following steps: Step S1: Collect characteristic data of the device itself during operation by deploying sensors on the device; Step S2: Analyze the status of the components using a proprietary vision acquisition module and AI vision algorithms, and upload the data to the cloud platform; Step S3: Analyze the equipment operating status through the anomaly detection module and upload it to the cloud platform; Step S4: Locate the faulty equipment and personnel distribution using the positioning unit, and allocate technical personnel accordingly; Step S5: Predict the device status for the next day using the prediction module and upload the results to the cloud platform; Step S6: Predict the raw material usage time using the prediction module and automatically replenish the raw materials before they are about to run out; Step S7: Transform the data into visual charts using the device status visualization module.

[0006] According to the above technical solution, the collection of the device's own characteristic data during operation includes: The device collects data such as temperature, vibration frequency, and noise in real time by using temperature sensors, vibration frequency sensors, and noise monitoring sensors installed on the device. Collect device status information data set S n = (S1, S2, ... S6) and upload it to the cloud platform, where S1 represents a data packet containing data such as temperature, vibration frequency and noise, so that the device's operating status can be predicted based on the magnitude of data changes.

[0007] According to the above technical solution, the step of analyzing the state of components using a proprietary visual acquisition module and AI visual algorithms, and uploading the data to the cloud platform, includes: Visual images of components are captured using a proprietary vision acquisition module. After the images are acquired, they are transmitted to the AI ​​vision algorithm via a data interface; AI vision algorithms perform AI analysis and calculations on the collected visual data of parts and upload the calculation results to the cloud platform.

[0008] According to the above technical solution, the step of performing AI analysis and calculation and uploading the calculation results to the cloud platform includes: The methods used by the anomaly detection module for analysis mainly include analysis of equipment operating status, analysis of actual component size data, and analysis of component feature information. The specific method for analyzing equipment operating status is as follows: The analysis database and historical database of the cloud platform are retrieved through the data transmission module, and the collected equipment operating status data set S is retrieved from the analysis database. n The range of indicators K for various equipment operation data compiled by technicians from the historical database is retrieved. a -K b When K a n <K b When the equipment meets the normal operating requirements, it operates safely and stably; otherwise, when S... n <K a or S n >K b If the equipment malfunctions, the anomaly detection module will immediately respond by instructing the equipment control unit to stop the equipment from operating. ​The specific method for analyzing the actual size data of parts is as follows: The data transmission module retrieves the set of part size data M in the analysis database. Based on the perfect part mirror projection set according to the part production requirements, an overlap-coverage size analysis is performed. When the overlap rate is greater than 95%, the part size is qualified and the equipment continues production. When the qualification rate is less than or equal to 95%, the parts are judged as unqualified and will be separated from the conveyor belt and enter the defective product queue. When three or more defective products appear consecutively, the equipment control unit controls the equipment to stop running and issues an alarm. The specific method for analyzing component feature information is as follows: When the equipment is running stably, the instantaneous state of the component leaving the equipment will not change. The instantaneous visual image data of the component is acquired and analyzed through the anomaly detection module. When all components are of type A, the equipment is running normally. When a component is of type B, there is a problem in the component production. The anomaly detection module immediately calls the equipment control unit to control the equipment to stop running.

[0009] According to the above technical solution, the step of locating the faulty equipment and personnel distribution through the positioning unit and rationally allocating technical personnel includes: By installing positioning units in the wristbands of equipment and technicians, the equipment and technicians can be located in real time. The anomaly detection module can be used to determine equipment failures. The positioning unit can be used to locate the location of the technicians. By using the factory workshop circuit diagram that has been entered into the database in advance, the distance between the technicians and the equipment can be calculated. The information of the nearest technician can be identified and bound to the equipment. The information status of the technician can be changed to busy status. After the maintenance is completed, the busy status will be released to idle status. The methods for personnel allocation mainly include calculating and judging the distance between technical personnel and equipment, and adjusting the dispatch status of technical personnel.

[0010] According to the above technical solution, the step of predicting the equipment status for the next day using the prediction module includes: Based on the various status data of the equipment, establish line chart models. The range of data changes on the line chart model represents the stability of the equipment. The larger the range of change, the greater the probability of the equipment's occurrence. Conversely, the smaller the range of change, the more stable the equipment's status.

[0011] According to the above technical solution, the steps for automatic replenishment include: The specific method for calculating the approximate usage time of a batch of raw materials using the prediction module is as follows: the usage time of a batch of raw materials is calculated based on the weight of the raw materials using the fault prediction module. ; Where M is the total mass of the raw materials, K 总 Let m be the total quantity of goods produced, 'm' be the weight of a component, and 'a' be the loss rate in producing that component, with 0. <a<1,K 天 D represents the total number of parts produced in a day, where t is the time required to produce one part, and since the part is relatively large, the production time is relatively long. t is measured in hours. 总 The number of days since the raw materials were purchased is D. 总 The system will pop up a notification window to remind you that raw materials need to be replenished, and ask if you want to replenish the stock. If you confirm that you want to replenish the stock, the system will send an order to the supplier via the Internet with a requirement that the goods be delivered within a few days.

[0012] According to the above technical solution, the step of converting data into a visual chart includes: By processing and analyzing the above data through the cloud platform, the equipment's own attributes, including temperature, vibration frequency, noise, etc., are plotted into a line graph model and displayed on the control equipment page. The data uploaded by the fault prediction module is also displayed on the page using a chart model through the cloud platform.

[0013] According to the above technical solution, the cloud platform-based big data processing and analysis system includes: A cloud platform is used to store the databases required by the system and to provide users with technical support. The equipment acquisition module is used to process and analyze the acquired visual images and collect data on the equipment's operating status, including temperature, vibration frequency, and noise. The processing and analysis module is used to detect the operating status of the equipment, control the equipment based on the judgment results, and predict equipment failures and raw material usage. The device status visualization module is used to project and provide feedback on the device's operating status onto a webpage.

[0014] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: The present invention, by setting an anomaly detection module, can analyze the operating status of the equipment, confirm the faulty equipment information based on the anomaly of the data, and use the positioning unit to locate the location of the faulty equipment and the personnel distribution location to rationally allocate technical personnel, enabling enterprises to rationally allocate human resources and ensure stable equipment operation, thereby reducing the enterprise's operating costs. During the equipment production process, the prediction module can predict the usage time of raw materials and automatically replenish the raw materials before they are about to run out, reducing the enterprise's human resource investment in purchasing raw materials. Attached Figure Description

[0015] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a cloud platform-based big data processing and analysis method provided in Embodiment 1 of the present invention. Figure 2 This is a schematic diagram of the module composition of the big data processing and analysis system based on a cloud platform provided in Embodiment 2 of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example 1: Figure 1 This is a flowchart of a cloud-based big data processing and analysis method provided in Embodiment 1 of the present invention. This embodiment can be applied to scenarios of routine equipment operation and maintenance. The method can be executed by the cloud-based big data processing and analysis system provided in this embodiment. Figure 1 As shown, the method specifically includes the following steps: Step S1: Collect characteristic data of the device itself during operation by deploying sensors on the device; For example, in this embodiment of the invention, during the production of parts for equipment, data such as equipment temperature, vibration frequency, and noise are collected in real time by means of temperature sensors, vibration frequency sensors, and noise monitoring sensors arranged on the equipment, and a set of equipment status information data S is collected. n = (S1, S2, ... S6) and upload it to the cloud platform, where S1 represents a data packet containing data such as temperature, vibration frequency and noise, so that the device's operating status can be predicted based on the magnitude of data changes.

[0018] Step S2: Analyze the status of the components using a proprietary vision acquisition module and AI vision algorithms, and upload the data to the cloud platform; For example, in this embodiment of the invention, a dedicated visual acquisition module is electrically connected to an AI visual algorithm, and the AI ​​visual algorithm is network-connected to a cloud platform. During the production of parts by the equipment, the dedicated visual acquisition module captures visual images of the parts. This visual module includes, but is not limited to, a camera module. After capturing the images, they are transmitted to the AI ​​visual algorithm through a data interface. The AI ​​visual algorithm performs AI analysis and calculation on the captured visual data of the parts and uploads the calculation results to the cloud platform. The dedicated visual acquisition module is located above the part production conveyor belt, capturing visual images of the produced parts from various directions. Some visual acquisition modules are located at the part exit, capturing visual images of the parts' position and posture on the conveyor belt immediately after production, providing visual image data for the AI ​​visual algorithm to monitor the equipment's production status.

[0019] For example, the main methods for AI vision algorithms to perform analysis and calculation include calculating the number of parts, calculating the actual size data of the reconstructed parts, and recognizing the feature points set for the parts. Specifically, the method for calculating the number of parts is as follows: the vision acquisition module located at the part output outlet captures images of the parts. Each time a part leaves the production equipment, an auto-incrementing method is triggered to insert data into the historical database. Each added data entry increments the data record ID. The AI ​​vision algorithm retrieves the historical database to calculate the number of records, and the calculated number of records represents the part production output, facilitating part quantity calculation and saving piece counting time. The method for calculating the actual size data of the reconstructed parts is as follows: the analysis database is retrieved to obtain visual images of the parts from various directions. The AI ​​vision algorithm then uses the obtained visual image data to create a mirror projection of the parts. The mirror projection data set M = (M1, M2, ..., M8) is collected and uploaded to the cloud platform, providing data for the anomaly detection module to detect part quality, reducing the data processing load of the anomaly detection module, and optimizing the system's operating speed. The specific method for identifying feature points set for components is as follows: the feature points of the equipment include specific shapes, labels, and positions. The above feature points of the equipment are pre-entered into the AI ​​vision algorithm. The AI ​​vision algorithm identifies and marks the feature points set for the components on the visual image. When three feature points are identified, it is recorded as Class A, and vice versa. When there are fewer than three feature points, it is recorded as Class B. The analysis results are uploaded to the cloud platform. The setting of feature points provides feature references for the visual module to collect visual image data of the components from various directions.

[0020] Step S3: Analyze the equipment operating status through the anomaly detection module and upload it to the cloud platform; For example, in this embodiment of the invention, the data transmission module is connected to the cloud platform network, and the data transmission module is electrically connected to the anomaly detection module. The data transmission module retrieves data from the cloud platform and transmits it to the anomaly detection module. The anomaly detection module performs detection and analysis on the data retrieved by the data transmission module and uploads the analysis results to the cloud platform.

[0021] For example, the analysis methods performed by the anomaly detection module mainly include analysis of equipment operating status, analysis of actual component size data, and analysis of component feature information. Specifically, the analysis of equipment operating status involves: retrieving the analysis database and historical database from the cloud platform via the data transmission module, and retrieving the collected equipment operating status data set S from the analysis database. n The range of indicators K for various equipment operation data compiled by technicians from the historical database is retrieved. a -K b When K a n <K b When the equipment meets the normal operating requirements, it operates safely and stably; otherwise, when S... n <K a or S n >K b If the equipment malfunctions, the anomaly detection module will immediately respond by instructing the equipment control unit to stop the equipment from operating. This avoids increased costs caused by the inability to resolve problems in a timely manner. The specific method for analyzing the actual size data of parts is as follows: The data transmission module retrieves the part size data set M from the analysis database. Based on the perfect part mirror projection set according to the part production requirements, an overlap-based size analysis is performed. When the overlap rate is greater than 95%, the part size is considered qualified, and the equipment continues production. When the qualification rate is less than or equal to 95%, the parts are judged as unqualified and will be separated from the conveyor belt into the defective product queue. When three or more defective products appear consecutively, the equipment control unit stops the equipment and issues an alarm. This method saves manpower investment in part quality inspection, improves the part qualification rate, and thus reduces raw material loss and saves costs. The specific method for analyzing part characteristic information is as follows: The instantaneous state of the parts leaving the equipment does not change during stable operation. Instantaneous visual image data of the parts is acquired and analyzed through the anomaly detection module. When all parts are of type A, the equipment operates normally. When parts are of type B, a problem occurs in part production, and the anomaly detection module immediately activates the equipment control unit to stop the equipment, thus improving raw material utilization.

[0022] Step S4: Locate the faulty equipment and personnel distribution using the positioning unit, and allocate technical personnel accordingly; ​For example, in this embodiment of the invention, by installing a positioning unit in the equipment and the technician's wristband, the equipment and technician are located in real time. The anomaly detection module determines the equipment malfunction, the positioning unit locates the technician's position, and the distance between the technician and the equipment is calculated by pre-entering the factory workshop circuit diagram into the database. The information of the nearest technician is determined and bound to the equipment, and the information status of the technician is changed to busy. After the maintenance is completed, the busy status will be released to idle status.

[0023] For example, the personnel deployment method mainly includes calculating and judging the distance between technicians and equipment, and adjusting the dispatch status of technicians. Specifically, the method for calculating and judging the distance between technicians and equipment is as follows: A route database is established, recording factory routes and equipment locations and uploading them to a cloud platform. An anomaly detection module confirms faulty equipment information. A positioning unit locates the equipment and the positions of available technicians in the database. The closest available technician is selected through comparison. The cloud platform sends a signal to the technician's wristband, causing it to vibrate and display the faulty equipment code on the wristband screen. The technician can then proceed to the equipment for repair based on the code. This facilitates the dispatch of technicians and avoids the problems of manpower shortages or overcapacity associated with traditional equipment maintenance models. It allows for the maintenance of as many devices as possible with limited manpower, effectively reducing the waste of human resources. Sending a signal to the technician's wristband via the cloud platform binds the wristband information to the faulty equipment and changes the wristband status to "under maintenance." Furthermore, binding the wristband to the faulty equipment information implements an equipment maintenance responsibility system, facilitating accountability for equipment problems.

[0024] Step S5: Predict the device status for the next day using the prediction module and upload the results to the cloud platform; For example, line chart models are established based on various equipment status data. The amplitude of data fluctuations on the line chart model represents the stability of the equipment; the larger the amplitude, the greater the probability of equipment failure, and vice versa. Access control cards are used to identify the number of personnel on duty and their information, which is then uploaded to the cloud platform. When the number of personnel on duty is less than the factory's set threshold N for on-duty technical personnel, the warning value for the amplitude of fluctuation will be adjusted to AB, appropriately reducing the sensitivity of equipment failure prediction, alleviating human resource shortages, and preventing situations where personnel cannot be deployed while equipment remains in an alarm state. When the number of personnel on duty is greater than the factory's set threshold N for on-duty technical personnel, the warning value for the amplitude of fluctuation will be adjusted to ab, increasing the sensitivity of equipment failure prediction, strengthening equipment inspection, preventing minor faults from becoming major faults, reducing equipment downtime and repair time, and reducing production costs. Where A...<a,B> b, the warning range represented by AB is larger than the warning range represented by ab, that is, ab is included in AB.

[0025] Step S6: Predict the raw material usage time using the prediction module and automatically replenish the raw materials before they are about to run out; For example, the specific method for calculating the approximate usage time of a batch of raw materials through the prediction module is as follows: the usage time of a batch of raw materials is calculated based on the weight of the raw materials through the fault prediction module. ; Where M is the total mass of the raw materials, K 总 Let m be the total quantity of goods produced, 'm' be the weight of a component, and 'a' be the loss rate in producing that component, with 0. <a<1,K 天 D represents the total number of parts produced in a day, where t is the time required to produce one part, and since the part is relatively large, the production time is relatively long. t is measured in hours. 总 The number of days since the raw materials were purchased is D. 总 The system will pop up a notification window to remind you that raw materials are about to be replenished, and ask if you want to replenish them. If you confirm that you want to replenish them, the system will send an order to the supplier via the Internet with a requirement for delivery within a few days. This eliminates the need for manual procurement of raw materials, saves on human resources, and reduces production costs.

[0026] Step S7: Transform the data into visual charts using the device status visualization module.

[0027] For example, by processing and analyzing the above data through a cloud platform, the equipment's own attributes, including temperature, vibration frequency, and noise, can be plotted into a line graph model and displayed on the control device page. Data uploaded by the fault prediction module can also be displayed on the page using a chart model via the cloud platform. This facilitates equipment management for technicians, allowing one person to manage multiple devices, thus saving significant human resources and costs.

[0028] Example 2: Example 2 of the present invention provides a big data processing and analysis system based on a cloud platform. Figure 2 This is a schematic diagram of the module composition of the cloud platform-based big data processing and analysis system provided in Embodiment 2 of the present invention, as shown below. Figure 2 As shown, the system includes: A cloud platform is used to store the databases required by the system and to provide users with technical support. The equipment acquisition module is used to process and analyze the acquired visual images and collect data on the equipment's operating status, including temperature, vibration frequency, and noise. The processing and analysis module is used to detect the operating status of the equipment, control the equipment based on the judgment results, and predict equipment failures and raw material usage. The device status visualization module is used to project and provide feedback on the device's operating status onto a webpage.

[0029] In some embodiments of the present invention, the cloud platform includes: The route database is used to store data on the location of equipment and walkways in the factory. Historical database, used to store data collected by the vision module and processed by AI vision algorithms, as well as device status data; The analysis database stores data processed by the processing module.

[0030] In some embodiments of the present invention, the device status acquisition module includes: The vision module is used to capture images of the manufactured parts and collect visual image data of the parts. AI vision algorithms are used to process and analyze visual image data; The sensor module is used to collect data such as temperature, vibration frequency, and noise during equipment operation.

[0031] In some embodiments of the present invention, the processing and analysis module includes: The data transmission module is used to retrieve data from the cloud platform's database. The anomaly detection module is used to detect the operating status of the equipment, determine whether its operating status is normal, and determine the faulty equipment information to dispatch technicians to repair it. The prediction module is used to predict the operating status of the equipment for the next day and the shelf life of a batch of raw materials. The positioning unit is used to locate faulty equipment and technical personnel. The equipment control unit is used by the anomaly detection module to control the operation of the equipment after determining the equipment information.

[0032] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0033] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A cloud platform-based big data processing analysis method, characterized in that: The method comprises the following steps: Step S1: Collecting self characteristic data under the running state of the equipment by laying sensors on the equipment; Step S2: Analyzing the state of the parts by a special visual acquisition module and an AI visual algorithm, and uploading the cloud platform; Step S3: Analyzing the running state of the equipment by an abnormality detection module, and uploading the cloud platform; Step S4: Locating the position of the faulty equipment and the position of the personnel distribution to reasonably allocate technical personnel by a positioning unit; including: Step S5: Predicting the state of the equipment for the next day by a prediction module, and uploading the result to the cloud platform; including: Step S6: Predicting the raw material usage time by the prediction module, and automatically replenishing the raw materials before they are about to run out; including: Calculating the usage time of a batch of raw materials by the fault prediction module based on the weight of the raw materials; ； where M is the total mass of raw materials, K 总 is the total number of products produced, m is the weight of a component, a is the loss rate of producing the component and 0 < a < 1, K 天 is the total number of components produced in a day, t is the time required to produce a component and t is measured in hours, D 总 is the number of days the raw materials are used, when the number of days that have passed since the raw materials were purchased is close to D 总 , the system will pop up a prompt window to remind that the raw materials will soon be replenished, prompting whether to proceed with the replenishment, and when it is determined to proceed with the replenishment, the system sends an order to the supplier through the Internet and attaches a requirement for delivery within a few days. Step S7: Converting the data into visual charts by an equipment state visualization module. 2.The cloud platform based big data processing analysis method of claim 1, wherein: The collecting of self characteristic data under the running state of the equipment by laying sensors on the equipment comprises: Collecting the temperature, vibration frequency and noise data of the equipment in real time by the temperature sensor, vibration frequency sensor and noise monitoring sensor of the equipment itself; A collection of device status information data sets S n = (S1, S2,... S6) and upload to the cloud platform, where S1 represents a data packet containing temperature, vibration frequency and noise data. 3.The cloud platform based big data processing analysis method of claim 2, wherein: The step of analyzing the state of the parts by a special visual acquisition module and an AI visual algorithm, and uploading the cloud platform comprises: Capturing the visual image of the parts by the special visual acquisition module; Transmitting the captured image to the AI visual algorithm through the data interface; The AI visual algorithm performs AI analysis and calculation on the captured visual data of the parts, and uploads the calculation result to the cloud platform. 4.The cloud platform based big data processing analysis method of claim 3, wherein: The step of performing AI analysis and calculation, and uploading the calculation result to the cloud platform comprises: The analysis database number and the historical database of the cloud platform are called through the data transmission module, the collected equipment running state data set S is called from the analysis database n The index range K of each data in the equipment running which is sorted by the technical personnel is called from the historical database a -K b When K a <S n <K b , the equipment meets the normal operation requirements, the equipment is safely and stably operated, otherwise, when S n <K a or S n >K b , the equipment is abnormally operated, the abnormal detection module immediately reacts to mobilize the equipment control unit to control the equipment to stop operating; Retrieving the part size data set M in the analysis database through the data transmission module, performing coincident coverage size analysis according to the perfect part mirror projection set according to the production requirements of the parts, when the coincidence rate is greater than 95%, the part size is qualified, and the equipment continues to produce, when the qualified rate is less than or equal to 95%, it is determined that the unqualified parts will be separated from the conveyor belt and enter the defective product queue, when 3 or more than 3 defective products appear continuously, the equipment control unit controls the equipment to stop running and sends an alarm; Obtaining the instantaneous visual image data of the parts, and analyzing by the abnormality detection module, when the parts are all A class, the equipment is running normally, when the parts appear B class, the part production has a problem, the abnormality detection module immediately mobilizes the equipment control unit to control the equipment to stop running.

5. The cloud platform based big data processing analysis method according to claim 4, characterized in that: The step of converting the data into visual charts comprises: Through the cloud platform, the above data is processed and analyzed, the equipment self attributes including temperature data, vibration frequency data and noise data are drawn into a line chart model, and displayed on the control equipment page, and the data uploaded by the fault prediction module is displayed on the page by the chart model through the cloud platform.

Images