Smart factory monitoring data dynamic detection method, system, equipment and storage medium

Abstract

The present invention relates to the technical field of data processing, and in particular to a method, system, device and storage medium for dynamic detection of monitoring data of a smart factory. The method is applied to dynamically detect production monitoring data of production line equipment in a smart factory, and the method comprises: using data sensors pre-installed on each production line equipment to perform anomaly detection and extract abnormal equipment in the production line; for each abnormal equipment, using a pre-built equipment anomaly assessment model to perform quantitative analysis on the abnormal equipment and obtain an equipment anomaly index; obtaining real-time video image information of the abnormal equipment, and extracting operator information of the abnormal equipment based on the real-time video image information; considering the work experience of the operator information, correcting the equipment anomaly index of the abnormal equipment and obtaining the corrected equipment anomaly index; it can realize comprehensive monitoring of the entire production process and help to discover problems caused by improper collaborative operation of multiple devices.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method, system, device and storage medium for dynamic detection of monitoring data of a smart factory. Background Art

[0002] With the promotion of the concept of Industry 4.0 and the development of intelligent manufacturing technology, smart factories have become an important direction for the transformation and upgrading of modern manufacturing industry. Smart factories integrate advanced information technology, automation technology and intelligent technology to achieve high automation and intelligence of the production process, significantly improving production efficiency and product quality. However, with the increasing complexity of production systems, how to effectively monitor the operating status of equipment on the production line and promptly discover and solve potential problems has become a major challenge facing smart factories.

[0003] Existing smart factory monitoring methods only focus on the status monitoring of a single device, that is, by installing various types of sensors on the equipment, collecting data on the equipment's operating status in real time and performing simple threshold judgments. They lack an overall grasp of the production process and find it difficult to discover problems caused by improper collaboration of multiple devices. When equipment abnormalities are detected, existing methods can usually only provide simple alarm prompts and lack in-depth fault diagnosis and cause analysis capabilities, which to a certain extent limits the efficiency and effectiveness of fault handling. Summary of the invention

[0004] To solve the above technical problems, the present invention provides a smart factory monitoring data dynamic detection method, system, device and storage medium that can achieve comprehensive monitoring of the entire production process and help discover problems caused by improper collaborative operation of multiple devices.

[0005] In a first aspect, the present invention provides a method for dynamic detection of monitoring data of a smart factory, the method being applied to dynamically detect production monitoring data of production line equipment in a smart factory, the method comprising:

[0006] Use data sensors pre-installed on each production line equipment to perform anomaly detection and extract abnormal equipment in the production line;

[0007] For each abnormal device, use the pre-built device abnormality assessment model to perform quantitative analysis on the abnormal device and obtain the device abnormality index;

[0008] Acquire real-time video image information of the abnormal device, and extract operator information of the abnormal device based on the real-time video image information;

[0009] Considering the work experience of the operator information, correcting the device abnormality index of the abnormal device to obtain a corrected device abnormality index;

[0010] In response to the corrected device abnormality index being not higher than a preset device abnormality threshold, determining that the abnormal device is improperly operated;

[0011] In response to the corrected equipment abnormality index being higher than a preset equipment abnormality threshold, calculating an equipment abnormality index of an adjacent production line equipment;

[0012] Based on the equipment abnormality index of the adjacent production line equipment, the abnormality accumulation weight is calculated for the corrected equipment abnormality index to obtain the equipment abnormality accumulation weight index;

[0013] In response to the equipment abnormality accumulation index being not higher than the preset equipment abnormality threshold, it is determined that the production coordination between the abnormal equipment and the adjacent production line equipment is abnormal; in response to the equipment abnormality accumulation index being higher than the preset equipment abnormality threshold, it is determined that the abnormal equipment itself is faulty.

[0014] Furthermore, anomaly detection is performed to extract abnormal equipment in the production line, including:

[0015] From the historical production records of each production line equipment acquired in advance, the production monitoring data of the equipment in the best working state is selected as the benchmark production data;

[0016] For each production line equipment, feature extraction is performed on the benchmark production data to obtain a benchmark production state vector; the benchmark production state vector includes equipment state features and equipment energy efficiency features;

[0017] Acquire the production monitoring data of each production line equipment in real time, extract features and obtain the real-time production status vector;

[0018] Considering the preset error range, the difference analysis is performed between the real-time production state vector and the reference production state vector, and the production line equipment whose difference exceeds the preset error range is extracted and marked as abnormal equipment.

[0019] Furthermore, the equipment status characteristics include temperature, pressure, vibration frequency and current; the equipment energy efficiency characteristics include production capacity per unit time and energy consumption per unit time.

[0020] Furthermore, the calculation formula of the device abnormality index is:

[0021] ;

[0022] Among them, K represents the equipment abnormality index, , , , , as well as Respectively represent the primary weight coefficients of temperature, pressure, vibration frequency, current, capacity per unit time, and energy consumption per unit time; and Respectively represent the secondary weight coefficients of equipment status characteristics and equipment energy efficiency characteristics; , , , , and They respectively represent the degree of temperature deviation, pressure deviation, vibration frequency deviation, current deviation, production capacity deviation per unit time, and energy consumption deviation per unit time.

[0023] Furthermore, considering the working experience of the operator information, the device abnormality index of the abnormal device is corrected to obtain the corrected device abnormality index, including:

[0024] Based on the operator information, extract the operator's work experience, including years of work experience, number of training records, and operation proficiency score;

[0025] Calculate an experience correction factor based on the operator's work experience; the experience correction factor is used to adjust the equipment abnormality index;

[0026] The calculated empirical correction factor is applied to the equipment abnormality index for correction. The correction formula is:

[0027] ;

[0028] in, represents the equipment abnormality index after operator correction, and b represents the empirical correction factor.

[0029] Furthermore, the method for setting the preset device abnormality threshold is:

[0030] Collect historical production data, including data of equipment in normal operating conditions and known abnormal conditions;

[0031] Perform statistical analysis on historical data, calculate the mean, standard deviation, maximum and minimum values ​​of each feature, and identify abnormal points in historical data;

[0032] Draw the distribution map of each feature, identify the distribution of the corresponding feature under normal and abnormal conditions, and determine the cutoff point;

[0033] Cluster the historical data to find the cluster centers of normal and abnormal states, and set the preset device abnormality threshold as the boundary of the normal state cluster center.

[0034] Furthermore, the calculation formula of the abnormal accumulation index is:

[0035] ;

[0036] in, represents the abnormal accumulation index, represents the device abnormality index after correction of the abnormal device, Indicates the device abnormality index of the upstream adjacent device. Indicates the device abnormality index of the downstream adjacent device. and They represent the weight coefficients of the upstream adjacent device and the downstream adjacent device respectively. If the device anomaly index of the adjacent device exceeds the corresponding preset device anomaly threshold, the device anomaly index of the adjacent device is a positive value, indicating a negative impact; if the device anomaly index of the adjacent device does not exceed the corresponding preset device anomaly threshold, the device anomaly index of the adjacent device is a negative value, indicating a positive impact.

[0037] On the other hand, the present application also provides a smart factory monitoring data dynamic detection system, the system comprising:

[0038] The data sensor module is used to collect data on the equipment's operating status in real time using data sensors pre-installed on the equipment on each production line, and to perform preliminary anomaly detection to extract abnormal equipment on the production line;

[0039] The device anomaly assessment module is used to perform quantitative analysis on each abnormal device using a pre-built device anomaly assessment model to obtain a device anomaly index for each abnormal device;

[0040] The video image information acquisition module is used to obtain real-time video image information of abnormal equipment; through video cameras and other devices, it captures the operating status of the equipment and the information of the operator;

[0041] An operator information extraction module is used to extract operator information of abnormal equipment based on real-time video image information;

[0042] The equipment abnormality index correction module is used to correct the equipment abnormality index of the abnormal equipment by taking into account the work experience of the operator information and obtaining the corrected equipment abnormality index;

[0043] A preliminary determination module is used to make a preliminary determination in response to the corrected device abnormality index: if the corrected device abnormality index is not higher than the preset device abnormality threshold, it is determined that the abnormal device is improperly operated; if the corrected device abnormality index is higher than the preset device abnormality threshold, the adjacent device abnormality index calculation module is started;

[0044] The adjacent equipment abnormality index calculation module is used to calculate the equipment abnormality index of the adjacent production line equipment and pass the result to the abnormality accumulation calculation module;

[0045] The abnormal accumulation weight calculation module is used to calculate the abnormal accumulation weight of the corrected equipment abnormality index based on the equipment abnormality index of the adjacent production line equipment, obtain the equipment abnormality accumulation weight index, and pass the result to the final determination module;

[0046] The final judgment module is used to make a final judgment in response to the equipment abnormality accumulation index: if the equipment abnormality accumulation index is not higher than the preset equipment abnormality threshold, it is judged that the production coordination of the abnormal equipment and the adjacent production line equipment is abnormal; if the equipment abnormality accumulation index is higher than the preset equipment abnormality threshold, it is judged that the abnormal equipment itself is faulty.

[0047] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0048] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0049] Compared with the prior art, the present invention has the following beneficial effects: the abnormal degree of abnormal equipment is quantitatively analyzed through the equipment abnormality evaluation model to obtain the equipment abnormality index, and in combination with real-time video image information and operator information, in-depth fault diagnosis and cause analysis can be performed, which is helpful to quickly locate the source of the problem and improve the efficiency and effect of fault handling; the equipment abnormality index of the abnormal equipment is corrected considering the work experience of the operator information, so that the judgment result is more in line with the actual situation, which is helpful to improve the accuracy and reliability of the judgment; according to the level of the equipment abnormality accumulation index, the calculation range is dynamically expanded until all production line equipment involved in the abnormal accumulation is found, and the dynamic expansion mechanism enables the present invention to adapt to production systems of different scales and complexities, improving its applicability and flexibility; when the equipment abnormality index or the equipment abnormality accumulation index exceeds the preset threshold, an early warning can be issued in time, and detailed fault information and recommended processing measures can be provided, providing powerful decision-making support for managers, which is helpful to quickly respond to and solve problems; the present invention not only focuses on the status monitoring of a single device, but also realizes comprehensive monitoring of the entire production process by calculating the abnormality index of adjacent and indirectly adjacent devices, which is helpful to find problems caused by improper collaborative operation of multiple devices, thereby improving the accuracy and comprehensiveness of monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flow chart of the present invention;

[0051] Figure 2 It is the structural diagram of the dynamic detection system of smart factory monitoring data. DETAILED DESCRIPTION

[0052] In the description of this application, those skilled in the art should know that this application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, this application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, this application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0053] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0054] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0055] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0056] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0057] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0058] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0059] The present application is described below in conjunction with the drawings in the present application.

[0060] Embodiment 1: Figure 1 As shown, the method for dynamic detection of monitoring data of a smart factory of the present invention is applied to dynamically detect the production monitoring data of production line equipment in a smart factory, and specifically comprises the following steps:

[0061] Step S1, using data sensors pre-installed on each production line equipment to perform anomaly detection and extract abnormal equipment in the production line;

[0062] Step S1 is to use the data sensors pre-installed on each production line equipment to perform abnormality detection, so as to extract the abnormal equipment in the production line. The specific steps are as follows:

[0063] Step S11, from the historical production records of each production line equipment obtained in advance, the production monitoring data of the equipment in the best working state is selected as the benchmark production data; the best working state refers to the time period when the equipment operates stably, the production efficiency is high and there is no obvious fault, and these data are obtained from the production management system, historical maintenance records and operation logs; the data selection criteria are: 1) the equipment has a long operating time and no fault record; 2) high production efficiency and product quality meets the standards; 3) low energy consumption and low operating cost; 4) experienced operators and standardized operations;

[0064] Step S12: for each production line equipment, extract features from the benchmark production data to obtain a benchmark production state vector; the benchmark production state vector includes equipment state features and equipment energy efficiency features; determine the equipment state features and equipment energy efficiency features to be extracted; the equipment state features include parameters such as equipment temperature, pressure, vibration frequency, and current; the equipment energy efficiency features include the equipment's production capacity per unit time and its energy consumption per unit time;

[0065] Step S13, using the installed sensors to obtain the production monitoring data of each production line equipment in real time, and perform feature extraction to obtain the real-time production state vector; according to the operating characteristics of the production line equipment and the parameters to be monitored, select the appropriate sensor type, such as temperature sensors for monitoring temperature changes, pressure sensors for detecting pressure conditions, etc.; according to the specifications and requirements, correctly install the sensors at the key parts of the production line equipment to ensure that the sensors can accurately and stably collect data; the sensors obtain the operating data of the production line equipment in real time; perform necessary preprocessing on the collected real-time data, such as removing noise, processing outliers, etc., to improve the quality and reliability of the data; extract the features corresponding to the reference production state vector from the real-time data to form a real-time production state vector;

[0066] Step S14, considering the preset error range, perform difference analysis on the real-time production state vector and the reference production state vector, extract the production line equipment whose difference exceeds the preset error range, and mark it as abnormal equipment; reasonably set the preset error range according to the operating characteristics and production requirements of the equipment; the setting of the error range should comprehensively consider factors such as the normal fluctuation range of the equipment, process requirements and fault tolerance; compare the real-time production state vector with the reference production state vector item by item, calculate the difference value of each feature, and various mathematical operations and measurement methods can be used, such as Euclidean distance, cosine similarity, etc.; compare the calculated difference with the preset error range; if the difference exceeds the preset error range, it is considered that the production line equipment may be abnormal; mark the equipment outside the error range as abnormal equipment.

[0067] In the above steps, through high-frequency data collection and real-time monitoring, the abnormal state of the equipment can be quickly discovered and the fault response time can be reduced; various types of sensors cover the key parts of the equipment to ensure comprehensive monitoring of the equipment's operating status; automatic extraction and analysis of abnormal data and generation of abnormal reports reduce the need for manual intervention and improve efficiency; by adjusting the type and number of sensors, as well as the setting of the error range, the needs of different equipment and application scenarios can be flexibly responded to; by comparing the baseline production state vector and the real-time production state vector, the abnormal state of the equipment can be identified more accurately and false alarms and missed alarms can be reduced.

[0068] Step S2: for each abnormal device, use a pre-built device abnormality assessment model to perform quantitative analysis on the abnormal device to obtain a device abnormality index;

[0069] In step S2, the abnormal degree of the abnormal equipment is quantified using the equipment abnormality assessment model. The implementation of the equipment abnormality assessment model is as follows:

[0070] Step S21, calculating the difference between the real-time production state vector and the reference production state vector in various characteristics; wherein the production state vector includes equipment state characteristics and equipment energy efficiency characteristics; equipment state characteristics include temperature, pressure, vibration frequency, and current; equipment energy efficiency characteristics include production capacity per unit time and energy consumption per unit time; for each characteristic, calculating the difference between the real-time production state vector and the reference production state vector; the formula is as follows:

[0071] Difference = real-time production status value - benchmark production status value;

[0072] Here is an example:

[0073] Temperature difference: △T=T r -T b ;

[0074] Pressure difference: △P=P r -P b ;

[0075] Vibration frequency difference: △F=F r -F b ;

[0076] Current difference: ΔI=I r -I b ;

[0077] Capacity difference per unit time: △C=C r -C b ;

[0078] Energy consumption difference per unit time: △E=E r -E b ;

[0079] Among them, T r Indicates the real-time temperature value, T b Indicates the reference temperature value; P r Indicates the real-time pressure value, P b Indicates the reference pressure value; F r Indicates the real-time vibration frequency value, F b Indicates the reference vibration frequency value; I r Indicates the real-time current value, I b Indicates the reference current value; C r represents the real-time capacity per unit time, C b Indicates the production capacity per unit time; E r Indicates the real-time energy consumption per unit time, E b Indicates the energy consumption per base unit time;

[0080] Step S22: Calculate the degree of deviation between each feature difference and the preset error range of the corresponding feature; set a reasonable error range for each feature, the preset error range is [L, U], where L is the lower limit and U is the upper limit, and the degree of deviation is calculated as follows:

[0081] Temperature deviation: ;

[0082] Pressure deviation degree: ;

[0083] Vibration frequency deviation degree: ;

[0084] Current deviation degree: ;

[0085] Degree of capacity deviation per unit time: ;

[0086] Energy consumption deviation degree per unit time: ;

[0087] in, Indicates the upper limit of the temperature preset error range, Indicates the lower limit of the temperature preset error range; Indicates the upper limit of the preset error range of the pressure. Indicates the lower limit of the pressure preset error range; Indicates the upper limit of the preset error range of the vibration frequency, Indicates the lower limit of the preset error range of the vibration frequency; Indicates the upper limit of the current preset error range, Indicates the lower limit of the current preset error range; Indicates the upper limit of the preset error range of production capacity per unit time. Indicates the lower limit of the preset error range of production capacity per unit time; Indicates the upper limit of the preset error range of energy consumption per unit time, Indicates the lower limit of the preset error range of energy consumption per unit time;

[0088] Step S23: weight the deviation degree corresponding to each feature to obtain the equipment abnormality index; set a corresponding first-level weight for each feature to reflect its importance in the respective type feature set, and set a second-level weight for the equipment status feature and the equipment energy efficiency feature to reflect the importance of the two feature sets in the equipment abnormality assessment. The weight setting is determined according to the importance of the feature and historical data statistics; multiply the deviation degree of each feature by its corresponding weight, and then sum them to obtain the equipment abnormality index; the formula is as follows:

[0089] ;

[0090] Among them, K represents the equipment abnormality index, , , , , as well as Respectively represent the primary weight coefficients of temperature, pressure, vibration frequency, current, capacity per unit time, and energy consumption per unit time; and Respectively represent the secondary weight coefficients of equipment status characteristics and equipment energy efficiency characteristics.

[0091] In this step, by calculating the difference between each feature, the deviation between the current state of the equipment and the normal state can be accurately reflected, thereby improving the accuracy of anomaly detection. Secondly, by setting a reasonable preset error range and calculating the degree of deviation, the abnormality of each feature can be evaluated more finely, reducing false positives and negatives. Thirdly, by setting primary and secondary weights for each feature, the importance of equipment status features and energy efficiency features is comprehensively considered to ensure the comprehensiveness and scientific nature of anomaly evaluation.

[0092] Step S3, obtaining real-time video image information of the abnormal device, and extracting operator information of the abnormal device based on the real-time video image information;

[0093] In step S3, the real-time video image information of the abnormal device is obtained, and the operator information of the abnormal device is extracted based on the information; the specific implementation steps are as follows:

[0094] Video image information acquisition: Install high-definition video cameras at key locations on the production line to ensure that they cover abnormal equipment and its operating area; the cameras should have sufficient resolution and frame rate to capture clear video images; the video cameras capture the operating status of abnormal equipment and the behavior of operators in real time, and the video stream is transmitted to the central monitoring system via a wired or wireless network; the real-time video image data is stored in the server of the central monitoring system for subsequent processing and analysis;

[0095] Video image processing: Preprocessing of real-time video images, including denoising, enhancement, cropping, etc., to ensure that the image quality meets the requirements of subsequent analysis; using computer vision technology (such as convolutional neural network CNN) to detect targets in video images and identify the position and action of operators; common target detection algorithms include YOLO, SSD, etc.; extracting features from the detected operator images, including facial features, body posture, gestures, etc.; these features can help the system more accurately identify the identity and behavior of operators;

[0096] Operator information extraction: Use face recognition technology to compare the extracted facial features with the pre-stored operator database to identify the specific operator identity; combine the operator's body posture and gestures to analyze whether their operating behavior complies with the regulations; common behavior analysis algorithms include skeleton detection and motion recognition; record the extracted operator information (including name, work number, work experience, etc.) and associate it with the abnormal information of the abnormal equipment to generate an operator information record.

[0097] In this step, by capturing and transmitting video images in real time through high-definition video cameras, the operator information of abnormal equipment can be quickly obtained, thereby improving the fault response speed. The use of advanced computer vision technology and face recognition algorithms can accurately identify the identity and behavior of the operator and reduce false alarms and missed alarms. By combining video image information and sensor data, the abnormal conditions of the equipment and the behavior of the operator can be comprehensively evaluated to provide richer fault diagnosis information. Video image processing, feature extraction and operator information extraction are automatically performed to reduce the need for manual intervention and improve efficiency.

[0098] Step S4, taking into account the work experience of the operator information, correcting the device abnormality index of the abnormal device to obtain a corrected device abnormality index;

[0099] Since the operator's experience and skill level have a direct impact on the operating status of the equipment; experienced operators are usually able to perform operations more accurately and reduce the occurrence of equipment failures; conversely, inexperienced operators may cause equipment abnormalities; by taking the operator's work experience into consideration and correcting the equipment abnormality index, the actual abnormality of the equipment can be more accurately assessed, reducing false alarms and missed alarms caused by improper operation; the specific implementation is as follows:

[0100] From the operator information extracted in step S3, the identity information of the operator is obtained, including name, work number, etc.; the work experience of the operator is queried from the operator database, including years of work experience, training records, operation proficiency, etc.;

[0101] Evaluate the operator's experience and skill level based on his / her years of service; operators with longer years of service are considered to have higher experience and skill levels; review the operator's training records to evaluate the content and frequency of training they have received; operators with rich training records are usually more proficient in operating the equipment; evaluate the operator's operating proficiency based on his / her historical operating records; operators with good operating records are usually able to perform operations more accurately;

[0102] Based on the operator's work experience, the experience correction factor is calculated; the experience correction factor is used to adjust the equipment abnormality index so that it more accurately reflects the actual abnormality of the equipment; the experience correction factor is calculated using a linear or nonlinear method; for example, the correction factor can be calculated using the weighted sum of years of work, training records, and operating proficiency; the formula is as follows:

[0103] ;

[0104] Where b represents the experience correction factor, Y represents the operator's working years, t represents the number of training records of the operator, and S represents the operator's operation proficiency score. , as well as They represent the weight coefficients of working experience, training record and operation proficiency respectively, and can be adjusted according to actual needs;

[0105] The calculated empirical correction factor b is applied to the equipment abnormality index K for correction; the corrected equipment abnormality index is calculated by the following formula:

[0106] ;

[0107] in, Indicates the equipment abnormality index after operator correction.

[0108] In this step, by considering the operator's work experience, including years of work, training records and operating proficiency, the abnormal situation of the equipment can be evaluated more comprehensively, which helps to reduce misjudgments due to improper operation and improve the accuracy of abnormality detection; using the correction factor to adjust the equipment abnormality index can more accurately reflect the actual degree of abnormality of the equipment and avoid errors caused by relying solely on sensor data; by correcting the equipment abnormality index, false alarms caused by insufficient operator experience can be effectively reduced, and unnecessary troubleshooting and maintenance work can be avoided; the corrected equipment abnormality index can more accurately identify real equipment failures, reduce underreporting due to improper operation, and ensure timely detection and handling of potential problems.

[0109] Step S5: in response to the calibrated device abnormality index being not higher than the preset device abnormality threshold, determining that the abnormal device is operating improperly; in response to the calibrated device abnormality index being higher than the preset device abnormality threshold, calculating the device abnormality index of the adjacent production line device;

[0110] By setting the preset device abnormality threshold, you can distinguish whether the device abnormality is caused by improper operation or by problems with the device itself or adjacent devices. The method for setting the preset device abnormality threshold is as follows:

[0111] Collect a large amount of historical production data, including data of the equipment in normal operation and known abnormal conditions; the data should cover various operating conditions and failure modes of the equipment; collect historical data of various sensors on the equipment (such as temperature, pressure, vibration frequency, current, etc.); collect the operation records of operators, including operation time, operation content, operation results, etc.;

[0112] Performing statistical analysis on historical data and calculating statistical indicators such as the mean, standard deviation, maximum value, and minimum value of each feature can help understand the operating range of the device under normal conditions; using statistical methods (such as mean plus or minus standard deviation, percentiles, etc.) to identify abnormal points in historical data and understand the characteristic performance of the device under abnormal conditions; drawing distribution diagrams of each feature, observing its distribution under normal and abnormal conditions, and finding obvious dividing points;

[0113] Use clustering algorithms (such as K-means) to cluster historical data, find the cluster centers of normal and abnormal states, and set the threshold as the boundary of the normal state cluster center;

[0114] The threshold is adjusted dynamically according to the operating status of the device and environmental changes; for example, an online learning algorithm (such as an adaptive filter) is used to update the threshold in real time.

[0115] Compare the calibrated device abnormality index with the preset device abnormality threshold to determine the specific cause of the abnormal device and decide on the next treatment measures; the specific implementation steps are as follows:

[0116] Obtaining the corrected device abnormality index from step S4; comparing the corrected device abnormality index with a preset device abnormality threshold;

[0117] If the corrected device abnormality index is not higher than the preset device abnormality threshold, a detailed abnormality report is generated, including the name of the abnormal device, abnormal characteristics, corrected abnormality index, operator information, etc.; relevant personnel are notified by email, SMS or system message, informing them of improper operation of the abnormal device and suggesting training on operating specifications or adjustment of operating methods; abnormal events are recorded in the database for subsequent analysis and improvement;

[0118] If the corrected equipment abnormality index is higher than the preset equipment abnormality threshold, the production line equipment adjacent to the abnormal equipment is identified according to the topological structure of the production line, where the adjacent equipment refers to the equipment that is directly connected to or closely cooperates with the abnormal equipment on the production line; the production monitoring data of the adjacent equipment is acquired in real time using the sensors installed on the adjacent equipment; the production monitoring data of the adjacent equipment is quantitatively analyzed using the method described in step S2 to obtain the equipment abnormality index of the adjacent equipment.

[0119] Step S6, based on the equipment abnormality index of the adjacent production line equipment, performing abnormality accumulation weight calculation on the corrected equipment abnormality index to obtain the equipment abnormality accumulation weight index;

[0120] In step S6, the abnormal accumulation weight calculation is to comprehensively consider the abnormal conditions of the abnormal equipment and its adjacent equipment and evaluate the abnormal degree of the entire production process; the abnormal accumulation weight index is used to comprehensively evaluate the abnormal conditions of the abnormal equipment and its adjacent equipment; the abnormal accumulation weight index is obtained by weighted summing the corrected equipment abnormality index and the equipment abnormality index of the adjacent equipment; the specific calculation method is as follows:

[0121] Step S61: Set a weight for each adjacent device to reflect its importance in the abnormality assessment; the weight can be determined according to the location, function and historical data of the device; if the device abnormality index of the adjacent device exceeds its own preset device abnormality threshold, a negative impact is provided to the abnormal device; if the device abnormality index of the adjacent device does not exceed its own preset device abnormality threshold, a positive impact is provided to the abnormal device;

[0122] Step S62: According to the abnormal influence of adjacent equipment, the corrected equipment abnormality index is adjusted and the abnormal accumulation index is calculated; the formula is as follows:

[0123] ;

[0124] in, represents the abnormal accumulation index, represents the device abnormality index after correction of the abnormal device, Indicates the device abnormality index of the upstream adjacent device. Indicates the device abnormality index of the downstream adjacent device. and They represent the weight coefficients of the upstream adjacent device and the downstream adjacent device respectively. If the device anomaly index of the adjacent device exceeds the corresponding preset device anomaly threshold, the device anomaly index of the adjacent device is a positive value, indicating a negative impact; if the device anomaly index of the adjacent device does not exceed the corresponding preset device anomaly threshold, the device anomaly index of the adjacent device is a negative value, indicating a positive impact.

[0125] In this step, by comprehensively evaluating the abnormal conditions of the abnormal device and its adjacent devices, especially considering the impact of the adjacent devices, the abnormal degree of the device can be judged more accurately and false alarms and missed alarms can be reduced; the abnormal accumulation index takes into account the abnormal conditions of multiple devices and their mutual impact, providing a more comprehensive abnormal evaluation result, which is helpful for in-depth analysis of the cause of the fault; by adjusting the weights and abnormal impacts of adjacent devices, the needs of different devices and application scenarios can be flexibly responded to.

[0126] Step S7: In response to the equipment abnormality accumulation index not being higher than the preset equipment abnormality threshold, it is determined that the abnormal equipment and the adjacent production line equipment have production coordination abnormalities; in response to the equipment abnormality accumulation index being higher than the preset equipment abnormality threshold, it is determined that the abnormal equipment itself has a fault;

[0127] In step S7, the device abnormality accumulation index is compared with the preset device abnormality threshold to finally determine the abnormal conditions of the abnormal device and its adjacent devices; the specific determination is as follows:

[0128] Compare the device anomaly accumulation index with the preset device anomaly threshold:

[0129] If the equipment abnormality accumulation index is not higher than the preset equipment abnormality threshold, a detailed abnormality report is generated, including the name of the abnormal equipment, abnormality characteristics, equipment abnormality accumulation index, equipment abnormality index of adjacent equipment, etc.; relevant personnel are notified by email, SMS or system message, informing them of the abnormal production coordination of the abnormal equipment and its adjacent equipment, and suggesting production process optimization or equipment coordination; abnormal events are recorded in the database for subsequent analysis and improvement;

[0130] If the equipment abnormality accumulation index is higher than the preset equipment abnormality threshold, a detailed fault report will be generated, including the name of the abnormal equipment, abnormal characteristics, equipment abnormality accumulation index, etc.; maintenance personnel will be notified by email, SMS or system message, informing them of the abnormal equipment's own fault and suggesting equipment maintenance or replacement; the fault event will be recorded in the database for subsequent analysis and improvement.

[0131] In this step, by setting a reasonable preset device abnormality threshold, the abnormal situation of the equipment can be judged more accurately, reducing false alarms and missed alarms; the equipment abnormality accumulation index comprehensively considers the abnormal situation of the abnormal equipment and its adjacent equipment, providing a more comprehensive abnormality assessment result, which is helpful for in-depth analysis of the cause of the fault; by adjusting the threshold setting method and dynamic adjustment mechanism, it can flexibly respond to the needs of different equipment and application scenarios; automatically compare the abnormality accumulation index and determine the fault type, reducing the need for manual intervention; through real-time data processing and abnormality evaluation, the abnormal situation of the equipment can be quickly discovered and the fault response speed can be improved.

[0132] Embodiment 2: Figure 2 As shown, the smart factory monitoring data dynamic detection system of the present invention specifically includes the following modules:

[0133] The data sensor module is used to collect data on the equipment's operating status in real time using data sensors pre-installed on the equipment on each production line, and to perform preliminary anomaly detection to extract abnormal equipment on the production line;

[0134] The device anomaly assessment module is used to perform quantitative analysis on each abnormal device using a pre-built device anomaly assessment model to obtain a device anomaly index for each abnormal device;

[0135] The video image information acquisition module is used to obtain real-time video image information of abnormal equipment; through video cameras and other devices, it captures the operating status of the equipment and the information of the operator;

[0136] An operator information extraction module is used to extract operator information of abnormal equipment based on real-time video image information;

[0137] The equipment abnormality index correction module is used to correct the equipment abnormality index of the abnormal equipment by taking into account the work experience of the operator information and obtaining the corrected equipment abnormality index;

[0138] A preliminary determination module is used to make a preliminary determination in response to the corrected device abnormality index: if the corrected device abnormality index is not higher than the preset device abnormality threshold, it is determined that the abnormal device is improperly operated; if the corrected device abnormality index is higher than the preset device abnormality threshold, the adjacent device abnormality index calculation module is started;

[0139] The adjacent equipment abnormality index calculation module is used to calculate the equipment abnormality index of the adjacent production line equipment and pass the result to the abnormality accumulation calculation module;

[0140] The abnormal accumulation weight calculation module is used to calculate the abnormal accumulation weight of the corrected equipment abnormality index based on the equipment abnormality index of the adjacent production line equipment, obtain the equipment abnormality accumulation weight index, and pass the result to the final determination module;

[0141] The final judgment module is used to make a final judgment in response to the equipment abnormality accumulation index: if the equipment abnormality accumulation index is not higher than the preset equipment abnormality threshold, it is judged that the production coordination of the abnormal equipment and the adjacent production line equipment is abnormal; if the equipment abnormality accumulation index is higher than the preset equipment abnormality threshold, it is judged that the abnormal equipment itself is faulty.

[0142] The various variations and specific embodiments of the smart factory monitoring data dynamic detection method in the aforementioned embodiment 1 are also applicable to the smart factory monitoring data dynamic detection system in this embodiment. Through the aforementioned detailed description of the smart factory monitoring data dynamic detection method, those skilled in the art can clearly know the implementation method of the smart factory monitoring data dynamic detection system in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0143] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0144] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for dynamic detection of monitoring data of a smart factory, characterized in that: The method is applied to dynamically detect production monitoring data of production line equipment in a smart factory, and the method comprises: Use data sensors pre-installed on each production line equipment to perform anomaly detection and extract abnormal equipment in the production line; For each abnormal device, use the pre-built device abnormality assessment model to perform quantitative analysis on the abnormal device and obtain the device abnormality index; Acquire real-time video image information of the abnormal device, and extract operator information of the abnormal device based on the real-time video image information; Considering the working experience of the operator information, correcting the device abnormality index of the abnormal device to obtain a corrected device abnormality index; In response to the corrected device abnormality index being not higher than a preset device abnormality threshold, determining that the abnormal device is improperly operated; In response to the corrected equipment abnormality index being higher than a preset equipment abnormality threshold, calculating an equipment abnormality index of an adjacent production line equipment; Based on the equipment abnormality index of the adjacent production line equipment, the abnormality accumulation weight is calculated for the corrected equipment abnormality index to obtain the equipment abnormality accumulation weight index; In response to the equipment abnormality accumulation index not being higher than a preset equipment abnormality threshold, it is determined that the abnormal equipment and the adjacent production line equipment have production coordination abnormalities; in response to the equipment abnormality accumulation index being higher than a preset equipment abnormality threshold, it is determined that the abnormal equipment itself has a fault; performing abnormality detection to extract abnormal equipment in the production line, including: From the historical production records of each production line equipment acquired in advance, the production monitoring data of the equipment in the best working state is selected as the benchmark production data; For each production line equipment, feature extraction is performed on the benchmark production data to obtain a benchmark production state vector; the benchmark production state vector includes equipment state features and equipment energy efficiency features; the equipment state features include temperature, pressure, vibration frequency and current; the equipment energy efficiency features include production capacity per unit time and energy consumption per unit time; Acquire the production monitoring data of each production line equipment in real time, extract features and obtain the real-time production status vector; Considering a preset error range, performing a difference analysis between the real-time production state vector and the reference production state vector, extracting production line equipment whose difference exceeds the preset error range, and marking it as abnormal equipment; The operation of the equipment abnormality assessment model includes: Calculating the difference between the real-time production state vector and the reference production state vector in various characteristics; Calculate the degree of deviation between each feature difference and the preset error range of the corresponding feature; The deviation degree corresponding to each feature is weighted and the equipment abnormality index is obtained; The method for obtaining the abnormal accumulation index of equipment includes: A weight is set for each neighbor device to reflect its importance in anomaly assessment; According to the abnormal impact of adjacent equipment, adjust the corrected equipment abnormality index and calculate the abnormal accumulation index; The calculation formula of the abnormal accumulation index is: ； in, represents the abnormal accumulation index, represents the device abnormality index after correction of the abnormal device, Indicates the device abnormality index of the upstream adjacent device. Indicates the device abnormality index of the downstream adjacent device. and They represent the weight coefficients of the upstream adjacent device and the downstream adjacent device respectively. If the device anomaly index of the adjacent device exceeds the corresponding preset device anomaly threshold, the device anomaly index of the adjacent device is a positive value, indicating a negative impact; if the device anomaly index of the adjacent device does not exceed the corresponding preset device anomaly threshold, the device anomaly index of the adjacent device is a negative value, indicating a positive impact.

2. The method for dynamic detection of smart factory monitoring data according to claim 1, characterized in that: The calculation formula of the equipment abnormality index is: ； Among them, K represents the equipment abnormality index, , , , , as well as Respectively represent the primary weight coefficients of temperature, pressure, vibration frequency, current, capacity per unit time, and energy consumption per unit time; and Respectively represent the secondary weight coefficients of equipment status characteristics and equipment energy efficiency characteristics; , , , , and They respectively represent the degree of temperature deviation, pressure deviation, vibration frequency deviation, current deviation, production capacity deviation per unit time, and energy consumption deviation per unit time.

3. The method for dynamic detection of smart factory monitoring data according to claim 2, characterized in that: Considering the working experience of the operator information, the device abnormality index of the abnormal device is corrected to obtain the corrected device abnormality index, including: Based on the operator information, extract the operator's work experience, including years of work experience, number of training records, and operation proficiency score; Calculate an experience correction factor based on the operator's work experience; the experience correction factor is used to adjust the equipment abnormality index; The calculated empirical correction factor is applied to the equipment abnormality index for correction. The correction formula is: ； in, represents the equipment abnormality index after operator correction, and b represents the empirical correction factor.

4. The method for dynamic detection of smart factory monitoring data according to claim 3, characterized in that: The method for setting the preset device abnormality threshold is: Collect historical production data, including data of equipment in normal operating conditions and known abnormal conditions; Perform statistical analysis on historical data, calculate the mean, standard deviation, maximum and minimum values ​​of each feature, and identify abnormal points in historical data; Draw the distribution map of each feature, identify the distribution of the corresponding feature under normal and abnormal conditions, and determine the cutoff point; Cluster the historical data to find the cluster centers of normal and abnormal states, and set the preset device abnormality threshold as the boundary of the normal state cluster center.

5. A smart factory monitoring data dynamic detection system, characterized in that: The system is applied to the smart factory monitoring data dynamic detection method according to claim 1, and the system includes: The data sensor module is used to collect data on the equipment's operating status in real time using data sensors pre-installed on the equipment on each production line, and to perform preliminary anomaly detection to extract abnormal equipment on the production line; The device anomaly assessment module is used to perform quantitative analysis on each abnormal device using a pre-built device anomaly assessment model to obtain a device anomaly index for each abnormal device; The video image information acquisition module is used to obtain real-time video image information of abnormal equipment; through the video camera, it captures the operating status of the equipment and the information of the operator; An operator information extraction module is used to extract operator information of abnormal equipment based on real-time video image information; The equipment abnormality index correction module is used to correct the equipment abnormality index of the abnormal equipment by taking into account the work experience of the operator information and obtaining the corrected equipment abnormality index; A preliminary determination module is used to make a preliminary determination in response to the corrected device abnormality index: if the corrected device abnormality index is not higher than the preset device abnormality threshold, it is determined that the abnormal device is improperly operated; if the corrected device abnormality index is higher than the preset device abnormality threshold, the adjacent device abnormality index calculation module is started; The adjacent equipment abnormality index calculation module is used to calculate the equipment abnormality index of the adjacent production line equipment and pass the result to the abnormality accumulation calculation module; The abnormal accumulation weight calculation module is used to calculate the abnormal accumulation weight of the corrected equipment abnormality index based on the equipment abnormality index of the adjacent production line equipment, obtain the equipment abnormality accumulation weight index, and pass the result to the final determination module; The final judgment module is used to make a final judgment in response to the equipment abnormality accumulation index: if the equipment abnormality accumulation index is not higher than the preset equipment abnormality threshold, it is judged that the production coordination of the abnormal equipment and the adjacent production line equipment is abnormal; if the equipment abnormality accumulation index is higher than the preset equipment abnormality threshold, it is judged that the abnormal equipment itself is faulty.

6. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 4 are implemented.

Images