A production event based device sensor data adaptive acquisition system

Abstract

The application provides a production event-based device sensing data adaptive acquisition system, relates to the technical field of industrial internet of things, and comprises a tracking data acquisition module configured to acquire device operation data of a corresponding device; a data acquisition anomaly detection module, the data acquisition anomaly detection module is configured to perform device anomaly detection according to the device operation data, and generate a device data acquisition anomaly type when device operation data acquisition is abnormal; a data acquisition anomaly adjustment module configured to select a corresponding data acquisition anomaly processing strategy according to the device data acquisition anomaly type; and the data acquisition anomaly processing strategy is used to instruct the tracking data acquisition module to adjust an original data acquisition scheme or complete the device operation data according to historical data of the device until complete device operation data is acquired. The application solves the problem that data cannot be effectively stored due to excessive device data and the like in the prior art through the system.

Description

Technical Field

[0001] This invention relates to the field of industrial Internet of Things (IoT) technology, and in particular to an adaptive acquisition system for device sensor data based on production events. Background Technology

[0002] In the current industrial manufacturing sector, with the deep integration of the Industrial Internet of Things (IIoT) and intelligent manufacturing concepts, data acquisition and monitoring of the production process have become the core foundation for realizing equipment status awareness, process optimization, quality traceability, and intelligent production management. A typical industrial data acquisition and management system usually includes key entities such as equipment, monitoring points, and gateways. "Equipment" refers to the specific physical hardware units involved in industrial production, such as machine tools, sensors, and controllers. A "monitoring point" is the smallest monitoring unit for the operating status of equipment, corresponding to a specific operating parameter, such as speed, temperature, operating status switching quantity, voltage, and current. A single device can be associated with multiple monitoring points. Each monitoring point, in addition to defining parameter types, is usually configured with strategy information such as the acquisition frequency to determine the data sampling time interval. The "gateway," acting as a bridge connecting the field device network and the upper-level information system, is an IoT gateway device with functions such as protocol conversion, data aggregation, and forwarding, enabling interconnection between different sensing networks and between local field networks and remote communication networks. The gateway is responsible for periodically collecting equipment operating parameter data based on the location configuration, temporarily storing it locally, and then uploading the data to a higher-level monitoring platform or business system through push or providing interface services.

[0003] Based on this architecture, "two-level material tracking" technology is widely used to achieve refined process control of production materials. This technology aims to dynamically capture the flow status and progress of materials between processes by monitoring specific key events of production equipment in real time (such as production start, production end, material input, and material output). These events are pushed to various downstream business systems (such as Manufacturing Execution System (MES), Warehouse Management System (WMS), and Quality Management System (QMS)) via asynchronous communication middleware such as message queues, driving them to complete a series of business activities such as inventory updates, production scheduling, and quality traceability, thereby forming a data flow from production events to a closed business loop.

[0004] However, in some application scenarios requiring deep integration of production event and process data, after receiving a secondary material tracking event, the business system often needs to further request the industrial data acquisition system to obtain detailed sensor data collected by the corresponding equipment within a specific production cycle (usually between the start and end of production) for advanced analysis, process verification, or compliance recording. In actual system integration and operation, existing technical solutions often face the following inherent defects, leading to data acquisition process failures or compromised system stability: Missing event data: Due to reasons such as abnormal communication of field equipment, defects in the event reporting program, or unreliable network transmission, the event sequence of secondary material tracking may be incomplete. For example, the equipment may only report the "production end" event, while the "production start" event is missing, causing the business system to be unable to accurately define the effective time window of the production process, and thus unable to initiate an effective data query request to the data acquisition system.

[0005] System performance bottlenecks caused by large data volume requests manifest in two typical scenarios. First, logical errors in the secondary material tracking program or abnormalities in equipment production (such as continuous idling or failure to shut down equipment in a timely manner) can lead to abnormally extended calculated production cycle time ranges. Second, even with normal tracking and production, if the collection frequency of target points is set too high, massive amounts of collected data records will be generated within a given time window. When the business system initiates requests based on this huge time range or high-density data volume, the backend interface of the industrial data acquisition system will face extremely high real-time data processing and retrieval loads, easily causing a sharp increase in interface response time, exhaustion of service process resources, or even crashes. Simultaneously, the requesting party often interrupts the call due to timeouts, resulting in data acquisition failure.

[0006] Limitations on data persistence capabilities of business systems: Even if a business system can successfully obtain complete data from the industrial data acquisition system interface, the returned dataset may be too large, exceeding the storage capacity limits preset by the business-side database for the corresponding fields (such as the upper limit of text field length, the storage threshold of big data objects, etc.). This results in the data not being stored in the business database normally, causing subsequent business operations to be interrupted due to data loss, and the entire acquisition process is essentially still considered a failure.

[0007] The root cause of these problems lies in the lack of flexible and adaptive coordination and protection mechanisms between the production event flow, process data acquisition flow, and business processing flow in the existing technical architecture. The system's ability to cope with abnormal data scale, abnormal time range, and storage constraints is insufficient, resulting in poor robustness of the overall chain. This makes it difficult to adapt to the changing production rhythms and data conditions in complex industrial environments, hindering the reliable implementation of advanced manufacturing applications based on deep data fusion. Summary of the Invention

[0008] This application provides an adaptive acquisition system for equipment sensor data based on production events, in order to solve the problem in the prior art that large amounts of data cannot be effectively stored due to the occasional large amount of sensor data during the equipment's production cycle.

[0009] The system includes: A tracking data acquisition module, configured to acquire device operation data of the corresponding device; A data acquisition anomaly detection module is configured to perform device anomaly detection based on the device operation data, and generate a device data acquisition anomaly type when an anomaly occurs in the acquisition of device operation data. A data acquisition anomaly adjustment module is configured to select a corresponding data acquisition anomaly handling strategy based on the type of data acquisition anomaly of the device. The data acquisition anomaly handling strategy is used to instruct the tracking data acquisition module to adaptively adjust the original data acquisition scheme or supplement the device operation data based on the device's historical data until complete device operation data is acquired.

[0010] Preferably, the equipment operation data includes equipment production parameters and equipment production tracking events, wherein the equipment production tracking events include equipment production start tracking events and equipment production end tracking events.

[0011] Preferably, the tracking data acquisition module includes: The first type of equipment operation data sensor includes a plurality of first equipment operation data sensors, which are configured to acquire the equipment production parameters of the corresponding equipment. The second type of equipment operation data sensor includes at least two second equipment operation data sensors, which are respectively configured to acquire the equipment production start tracking event and the equipment production end tracking event.

[0012] Preferably, the data acquisition anomaly detection module is further configured to: Based on the equipment production parameters and the equipment production tracking events, equipment anomaly detection is performed. When an anomaly occurs in the equipment production parameters or the equipment production tracking events, the equipment operation data is determined to be abnormal, and a first equipment anomaly type or a second equipment anomaly type is generated. The first equipment anomaly type corresponds to the anomaly in the equipment production parameters, and the second equipment anomaly type corresponds to the anomaly in the equipment production tracking events.

[0013] Preferably, the second type of equipment anomaly includes the absence of the equipment production start tracking event or the absence of the equipment production end tracking event; The equipment production parameters include several equipment production sub-parameters. The same first equipment operation data sensor corresponds to several equipment production sub-parameters of the same type. The first equipment anomaly type includes the absence of at least one of the equipment production sub-parameters.

[0014] Preferably, the data acquisition anomaly adjustment module is further configured to: A first data acquisition anomaly handling strategy is generated based on the first device anomaly type; the first data acquisition anomaly handling strategy is used to instruct the tracking data acquisition module to adaptively adjust the original data acquisition scheme until complete device operation data is acquired; A second data acquisition anomaly handling strategy is generated based on the second type of device anomaly; the second data acquisition anomaly handling strategy is used to instruct the tracking data acquisition module to adaptively complete the device operation data based on the device's historical data until complete device operation data is obtained.

[0015] Preferably, the tracking data acquisition module further includes a first data acquisition anomaly execution unit, which is configured to adaptively adjust the original data acquisition scheme according to the first data acquisition anomaly handling strategy until complete device operation data is acquired. The adaptive adjustment of the original data acquisition scheme includes: Reduce the acquisition frequency of the first type of equipment operation data sensor to obtain the equipment production parameters until complete equipment production parameters are obtained, and adjust the data acquisition frequency of the first type of equipment operation data sensor back to the original frequency after the current data acquisition cycle.

[0016] Preferably, the tracking data acquisition module further includes a second data acquisition anomaly execution unit, which is configured to adaptively complete the device operation data based on the device's historical data according to the second data acquisition anomaly handling strategy, until complete device operation data is acquired; The adaptive completion of the device operation data based on the device's historical data includes: When the equipment production start tracking event is missing, extract the production end time of the previous cycle of the equipment from the historical data and set it as the equipment production start tracking event for the current data acquisition cycle. When the equipment production stop tracking event is missing, extract the production start time of the next cycle of the equipment from the historical data and set it as the equipment production stop tracking event of the current data acquisition cycle. When the equipment production start tracking event is missing or the equipment production stop tracking event is missing, and there is no previous cycle and next cycle of the equipment within the first time range, the average production cycle duration of historical data within the second time range is obtained, and the missing equipment production start tracking event and the missing equipment production stop tracking event of the current data acquisition week are obtained based on the average production cycle duration.

[0017] Preferably, the system further includes: A cloud data storage module, configured to store all data generated in the system to a cloud server; A local data storage unit, configured to store all data generated in the system to a local server.

[0018] Preferably, the system further includes: A visualization module is configured to visualize the entire process of the system acquiring data.

[0019] As described above, this application provides an adaptive acquisition system for equipment sensor data based on production events. The system includes a tracking data acquisition module configured to acquire equipment operating data of the corresponding equipment; a data acquisition anomaly detection module configured to detect equipment anomalies based on the equipment operating data and generate a data acquisition anomaly type when an anomaly occurs; and a data acquisition anomaly adjustment module configured to select a corresponding data acquisition anomaly handling strategy based on the data acquisition anomaly type. The data acquisition anomaly handling strategy instructs the tracking data acquisition module to adaptively adjust the original data acquisition scheme or supplement the equipment operating data based on historical equipment data until complete equipment operating data is acquired. This application solves the problem in the prior art where large amounts of data cannot be effectively stored due to occasional large amounts of sensor data during the equipment's production cycle. Attached Figure Description

[0020] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of an adaptive acquisition system for equipment sensor data based on production events, as described in this application. Figure 2 for Figure 1 A schematic diagram of the tracking data acquisition module. Detailed Implementation

[0022] 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.

[0023] It should be noted that the brief descriptions of terms in this application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning.

[0024] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0025] Figure 1 This is a schematic diagram of an adaptive acquisition system for equipment sensor data based on production events, as described in this application.

[0026] See Figure 1 As can be seen, this embodiment provides an adaptive acquisition system for equipment sensor data based on production events, the system comprising: The tracking data acquisition module is configured to acquire the device operation data of the corresponding device.

[0027] Specifically, in this embodiment, the tracking data acquisition module acquires the device operation data of the device to be acquired, and uses this as a data basis for subsequent adaptive adjustments.

[0028] The equipment operation data includes equipment production parameters and equipment production tracking events, which include equipment production start tracking events and equipment production end tracking events.

[0029] It should be noted that the acquired equipment operation data may be incomplete, such as missing a certain parameter in the equipment production parameters, or missing the equipment production start tracking event or the equipment production end tracking event. Therefore, there is a need for subsequent adaptive acquisition of these missing data.

[0030] The system also includes: The data acquisition anomaly detection module is configured to perform device anomaly detection based on the device operation data, and generate a device data acquisition anomaly type when an anomaly occurs in the acquisition of device operation data.

[0031] Specifically, in this embodiment, since the data loss situations in the device operation data are not the same, and different adaptive acquisition is required for different data loss situations, a data acquisition anomaly detection module is set up to perform device anomaly detection on the device operation data, thereby obtaining the device data acquisition anomaly type used to characterize the data loss type.

[0032] The system also includes: A data acquisition anomaly adjustment module is configured to select a corresponding data acquisition anomaly handling strategy based on the type of data acquisition anomaly of the device. The data acquisition anomaly handling strategy is used to instruct the tracking data acquisition module to adaptively adjust the original data acquisition scheme or supplement the device operation data based on the device's historical data until complete device operation data is acquired.

[0033] Specifically, in this embodiment, the data acquisition anomaly adjustment module selects the corresponding data acquisition anomaly handling strategy according to the type of device data acquisition anomaly, thereby achieving adaptive acquisition of missing data.

[0034] The methods for obtaining missing data mainly include adaptively adjusting the original data acquisition scheme and supplementing the device operation data based on the device's historical data.

[0035] Figure 2 for Figure 1 A schematic diagram of the tracking data acquisition module.

[0036] See Figure 2 Furthermore, in some embodiments, the tracking data acquisition module includes: The first type of equipment operation data sensor includes a plurality of first equipment operation data sensors, which are configured to acquire the equipment production parameters of the corresponding equipment. The second type of equipment operation data sensor includes at least two second equipment operation data sensors, which are respectively configured to acquire the equipment production start tracking event and the equipment production end tracking event.

[0037] Specifically, in this embodiment, different types of data are acquired through device operation data sensors of different functional types. That is, the device production parameters of the corresponding device are acquired through the first device operation data sensor in the first type of device operation data sensor, and the device production start tracking event and the device production end tracking event are acquired through the second device operation data sensor in the second type of device operation data sensor.

[0038] It should be noted that the second type of equipment operation data sensor mentioned above includes at least two second equipment operation data sensors. The two second equipment operation data sensors are used to acquire the equipment production start tracking event and the equipment production end tracking event, respectively. However, the second type of equipment operation data sensor can not only acquire these two data. The number of second equipment operation data sensors in the second type of equipment operation data sensor can be expanded according to different needs to acquire different data, thereby adapting to different needs.

[0039] Furthermore, in some embodiments, the data acquisition anomaly detection module is further configured to: Based on the equipment production parameters and the equipment production tracking events, equipment anomaly detection is performed. When an anomaly occurs in the equipment production parameters or the equipment production tracking events, the equipment operation data is determined to be abnormal, and a first equipment anomaly type or a second equipment anomaly type is generated. The first equipment anomaly type corresponds to the anomaly in the equipment production parameters, and the second equipment anomaly type corresponds to the anomaly in the equipment production tracking events.

[0040] Specifically, in this embodiment, when the equipment production parameters or the equipment production tracking event are abnormal, the data acquisition anomaly detection module generates the first equipment anomaly type or the second equipment anomaly type, and thereby instructs the data acquisition anomaly adjustment module to generate different data acquisition anomaly handling strategies.

[0041] The second type of equipment anomaly includes the absence of the equipment production start tracking event or the absence of the equipment production end tracking event; the equipment production parameters include several equipment production sub-parameters, and the same first equipment operation data sensor corresponds to several equipment production sub-parameters of the same type, and the first type of equipment anomaly includes the absence of at least one of the equipment production sub-parameters.

[0042] Furthermore, in some embodiments, the data acquisition anomaly adjustment module is also configured to: A first data acquisition anomaly handling strategy is generated based on the first device anomaly type; the first data acquisition anomaly handling strategy is used to instruct the tracking data acquisition module to adaptively adjust the original data acquisition scheme until complete device operation data is acquired; A second data acquisition anomaly handling strategy is generated based on the second type of device anomaly; the second data acquisition anomaly handling strategy is used to instruct the tracking data acquisition module to adaptively complete the device operation data based on the device's historical data until complete device operation data is obtained.

[0043] Specifically, in this embodiment, the data acquisition anomaly adjustment module generates different data acquisition anomaly handling strategies, thereby instructing the tracking data acquisition module to perform different adaptive processing.

[0044] Furthermore, in some embodiments, the tracking data acquisition module further includes a first data acquisition exception execution unit, which is configured to adaptively adjust the original data acquisition scheme according to the first data acquisition exception handling strategy until complete device operation data is acquired. The adaptive adjustment of the original data acquisition scheme includes: Reduce the acquisition frequency of the first type of equipment operation data sensor to obtain the equipment production parameters until complete equipment production parameters are obtained, and adjust the data acquisition frequency of the first type of equipment operation data sensor back to the original frequency after the current data acquisition cycle.

[0045] Specifically, in this embodiment, in cases where equipment production is abnormal, secondary tracking event sending is abnormal, or the equipment sensor points themselves collect data at too high a frequency, resulting in interface service abnormalities or interface read timeouts when the business system requests data from the industrial data acquisition system, the data acquisition may fail to be acquired due to excessively large data volumes.

[0046] When the interface service side of the industrial data acquisition system queries the database to obtain the collected data based on three parameters: sensor point number, equipment start and end production time, it first determines the amount of data to be collected based on the parameters, and then estimates whether the amount will cause interface service abnormalities, read timeouts, data that is too large to be stored, or unnecessary large amounts of data that lead to storage waste and read time consumption.

[0047] The logic for requesting device sensor data to predict whether it will cause anomalies includes the following steps: When a request fails, an additional request will be made to the interface for obtaining the sensor location's sampling frequency to obtain the sampling frequency of the location and store it on the business side.

[0048] The next time a request is made, the sampling frequency will be reduced based on the original sampling point frequency. This reduction involves increasing the sampling interval in integer multiples of the original sampling point frequency. If the acquisition still fails, the sampling interval at which the acquisition failed is recorded as twice the original sampling point frequency. This process continues, with the sampling interval increasing in integer multiples until the data is successfully acquired and stored locally. The sampling interval at which the acquisition was successful is recorded and will be used continuously for subsequent data acquisition.

[0049] For example, if the sampling frequency of a point in the industrial data acquisition platform is once every 50 milliseconds, then the sampling interval will be continuously increased to an integer multiple when the sampling fails: 50 milliseconds, 200 milliseconds, 400 milliseconds, etc. If the sampling is successful at 400 milliseconds, then the successful sampling interval for that point will be recorded as 400 milliseconds, and the sampling interval for subsequent acquisitions of data from that point will be 400 milliseconds.

[0050] The sensor data will be relatively distorted after the frequency is reduced, so subsequent periodic data acquisition will attempt to continue acquiring data in the normal way without reducing the frequency. If the acquisition is successful and the data can be successfully stored, the original frequency will be restored for data acquisition.

[0051] It should be noted that the frequency reduction is an automatic frequency reduction selected based on data acquisition timeout or values ​​that are too large to be stored. The focus is on automatic frequency reduction to ensure that no data is lost. In addition, it will periodically try to acquire data using non-frequency reduction methods. If non-frequency acquisition is successful, it will continue to acquire data using non-frequency reduction methods.

[0052] Furthermore, in some embodiments, the tracking data acquisition module further includes a second data acquisition anomaly execution unit, which is configured to adaptively complete the device operation data based on the device's historical data according to the second data acquisition anomaly handling strategy, until complete device operation data is acquired; The adaptive completion of the device operation data based on the device's historical data includes: When the equipment production start tracking event is missing, extract the production end time of the previous cycle of the equipment from the historical data and set it as the equipment production start tracking event for the current data acquisition cycle. When the equipment production stop tracking event is missing, extract the production start time of the next cycle of the equipment from the historical data and set it as the equipment production stop tracking event of the current data acquisition cycle. When the equipment production start tracking event is missing or the equipment production stop tracking event is missing, and there is no previous cycle and next cycle of the equipment within the first time range, the average production cycle duration of historical data within the second time range is obtained, and the missing equipment production start tracking event and the missing equipment production stop tracking event of the current data acquisition week are obtained based on the average production cycle duration.

[0053] Specifically, in this embodiment, when the production tracking events of the device are not fully sent, the start or end events are missing, resulting in the inability to obtain a valid start and time.

[0054] If a start event is missing, the production end time of the previous device in the production process is retrieved to replace the missing start time of the current device. If an end event is missing, the production start time of the next device in the production process is retrieved to replace the missing end time of the current device. If the device has no previous device or no next device, the successful tracking event history of the device is retrieved first. The duration of the history can be dynamically configured, defaulting to the most recent month, and records where data acquisition failed are removed. Then, the average value is used to estimate the production cycle time of the device under a single material. Finally, based on the estimated production cycle time, the device sensor point data is retrieved from the industrial data acquisition platform.

[0055] It should be noted that there are two types of completion: one is to automatically use the events of the adjacent devices as supplementary events when the production events of the equipment are missing; the other is to select the historical average production time of the equipment as the time range for acquisition if there are no adjacent devices, in order to ensure that no data is missing.

[0056] The ultimate goal of both frequency reduction and data completion is to ensure that data is not missing to the greatest extent possible, and both are done automatically, not manually.

[0057] Furthermore, in some embodiments, the system further includes: A cloud data storage module, configured to store all data generated in the system to a cloud server; A local data storage unit, configured to store all data generated in the system to a local server.

[0058] Specifically, in this embodiment, cloud data storage is performed through the cloud data storage module, and local data storage is performed through the local data storage unit.

[0059] The local data storage unit stores data without any missing data, and the cloud data storage module can update the data according to the data stored in the local data storage unit.

[0060] Furthermore, in some embodiments, the system further includes: A visualization module is configured to visualize the entire process of the system acquiring data.

[0061] Specifically, in this embodiment, the entire process of the visualization system is visualized through the visualization module, and interactive functions are integrated to enable quick system adjustments.

[0062] For example: In a smart quality project of a certain company, data collection at equipment points in a certain process is obtained based on the equipment's secondary tracking events. Before using the automatic frequency conversion function to acquire equipment sensor data within the process cycle, a single factory had approximately 50,000 secondary tracking events per day, resulting in approximately 20,000 requests to the industrial data acquisition system interface. Over 100 instances of data acquisition failure or ineffective storage occurred due to reasons such as abnormal secondary tracking event transmission, equipment production malfunctions, or excessively high sensor sampling frequencies. The probability of data acquisition failure reached 0.5%. After adopting the solution in this embodiment, the probability of data acquisition failure was reduced to 0.08%.

[0063] This embodiment has the following advantages: This embodiment improves the success rate of acquiring data from the device by estimating and determining the acquisition frequency of sensor data points, thereby reducing the failure rate of acquiring data due to excessive data volume.

[0064] For ease of explanation, the above description has been provided in conjunction with specific embodiments. However, the discussion in some embodiments is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. Various modifications and variations can be obtained based on the above teachings. The selection and description of the above embodiments are for the purpose of better explaining the contents of this disclosure, thereby enabling those skilled in the art to better utilize the embodiments.

Claims

1. An adaptive acquisition system for equipment sensor data based on production events, characterized in that, The system includes: The tracking data acquisition module is configured to acquire equipment operation data of a corresponding device. The tracking data acquisition module includes a first type of equipment operation data sensor, which comprises a plurality of first equipment operation data sensors, configured to acquire equipment production parameters of the corresponding device. It also includes a second type of equipment operation data sensor, comprising at least two second equipment operation data sensors, each configured to acquire a tracking event for the start of equipment production and a tracking event for the end of equipment production. A data acquisition anomaly detection module is configured to perform device anomaly detection based on the device operation data, and generate a device data acquisition anomaly type when an anomaly occurs in the acquisition of device operation data. A data acquisition anomaly adjustment module is configured to select a corresponding data acquisition anomaly handling strategy based on the type of data acquisition anomaly of the device; the data acquisition anomaly handling strategy is used to instruct the tracking data acquisition module to adaptively adjust the original data acquisition scheme or supplement the device operation data based on the device's historical data until complete device operation data is acquired. The equipment operation data includes equipment production parameters and equipment production tracking events, which include equipment production start tracking events and equipment production end tracking events. The data acquisition anomaly detection module is also configured to: Based on the equipment production parameters and the equipment production tracking events, equipment anomaly detection is performed. When anomalies occur in the equipment production parameters or the equipment production tracking events, the equipment operation data is determined to be abnormal, and a first equipment anomaly type or a second equipment anomaly type is generated. The first equipment anomaly type corresponds to anomalies in the equipment production parameters, and the second equipment anomaly type corresponds to anomalies in the equipment production tracking events. The data acquisition anomaly adjustment module is also configured to: A first data acquisition anomaly handling strategy is generated based on the first device anomaly type; the first data acquisition anomaly handling strategy is used to instruct the tracking data acquisition module to adaptively adjust the original data acquisition scheme until complete device operation data is acquired; A second data acquisition anomaly handling strategy is generated based on the second type of device anomaly; the second data acquisition anomaly handling strategy is used to instruct the tracking data acquisition module to adaptively complete the device operation data based on the device's historical data until complete device operation data is acquired; The tracking data acquisition module further includes a first data acquisition anomaly execution unit, which is configured to adaptively adjust the original data acquisition scheme according to the first data acquisition anomaly handling strategy until complete device operation data is acquired. The adaptive adjustment of the original data acquisition scheme includes: Reduce the acquisition frequency of the first type of equipment operation data sensor to obtain the equipment production parameters until the complete equipment production parameters are obtained, and adjust the data acquisition frequency of the first type of equipment operation data sensor back to the original frequency after the current data acquisition cycle. The tracking data acquisition module further includes a second data acquisition anomaly execution unit, which is configured to adaptively complete the device operation data based on the device's historical data according to the second data acquisition anomaly handling strategy, until complete device operation data is acquired. The adaptive completion of the device operation data based on the device's historical data includes: When the equipment production start tracking event is missing, extract the production end time of the previous cycle of the equipment from the historical data and set it as the equipment production start tracking event for the current data acquisition cycle. When the equipment production stop tracking event is missing, extract the production start time of the next cycle of the equipment from the historical data and set it as the equipment production stop tracking event of the current data acquisition cycle. When the equipment production start tracking event is missing or the equipment production stop tracking event is missing, and there is no previous cycle and next cycle of the equipment within the first time range, the average production cycle duration of historical data within the second time range is obtained, and the missing equipment production start tracking event and the missing equipment production stop tracking event of the current data are obtained based on the average production cycle duration.

2. The adaptive acquisition system for equipment sensor data based on production events according to claim 1, characterized in that, The second type of equipment anomaly includes the absence of the equipment production start tracking event or the absence of the equipment production end tracking event; The equipment production parameters include several equipment production sub-parameters. The same first equipment operation data sensor corresponds to several equipment production sub-parameters of the same type. The first equipment anomaly type includes the absence of at least one of the equipment production sub-parameters.

3. The adaptive acquisition system for equipment sensor data based on production events according to claim 1, characterized in that, The system also includes: A cloud data storage module, configured to store all data generated in the system to a cloud server; A local data storage unit, configured to store all data generated in the system to a local server.

4. The adaptive acquisition system for equipment sensor data based on production events according to claim 1, characterized in that, The system also includes: A visualization module is configured to visualize the entire process of the system acquiring data.

Images