Computer data intelligent identification system and method

Abstract

The invention discloses a computer data intelligent identification system and method, and relates to the technical field of data intelligent identification. Equipment state parameters are obtained by carrying out real-time monitoring and state evaluation on equipment in a large-scale factory, comprehensive analysis is carried out according to the equipment state parameters to obtain the latest acquisition frequency of the equipment, the data acquisition frequency can be dynamically adjusted according to the equipment state, self-adaption of computer data acquisition of the large-scale factory is achieved, and the data acquisition efficiency is improved. The change of the equipment state is better reflected, and the validity and timeliness of data acquisition are ensured; through comprehensive analysis of equipment operation values, vibration abnormal values, important scores and the like of all equipment in the large-scale factory, the production state of the large-scale factory is judged, corresponding decisions are output, changes of the production state can be quickly responded, the risk of equipment faults to production is reduced, and the safety and stability of the production process are ensured; and meanwhile, an automatic decision output module can reduce errors and delay of manual judgment and improve the decision speed and accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent data recognition, and in particular to a computer data intelligent recognition system and method. Background Art

[0002] Computer data recognition refers to the process of analyzing, identifying and understanding large amounts of data using computers and related technologies. This process usually involves data mining, machine learning, artificial intelligence and other technologies and methods, aiming to extract valuable information, patterns or knowledge from the data. For large factories, this computer data recognition can identify abnormal data in the factory equipment and perform early warning operations. Therefore, computer data recognition is particularly important for large intelligent factories. Data quality directly affects the accuracy of recognition results. Computer data produced must be highly timely in order to make correct and effective decisions for production. Currently, when factories use computer data for recognition, they usually set the data collection cycle based on the technicians' understanding of the process. This data collection method has great limitations and is insufficient to cover all possible changes or abnormal situations, resulting in low confidence in the recognition results and inability to make accurate decisions for production. Summary of the invention

[0003] The main purpose of the present invention is to provide a computer data intelligent recognition system and method to overcome the problems mentioned in the above background technology.

[0004] To achieve the above object, according to one aspect of the present invention, a computer data intelligent recognition system is provided, the system comprising: a database, a data recognition module and a decision output module; According to the received collection instructions, the database controls the sensors connected to it to collect data to obtain production information and maintenance information; the production information includes the operating power, operating temperature and operating amplitude of each device; the maintenance information includes maintenance records; The data identification module identifies the equipment based on its operating information to obtain the equipment's status parameters; the operating information includes the operating temperature, operating power and operating amplitude of each equipment in the factory, and the status parameters include the equipment operating value and vibration abnormality value; The decision output module performs a comprehensive analysis based on the received state parameters to obtain the production interference index of each device, and outputs decision opinions based on the index, wherein the decision opinions include production suspension and maintenance decisions, equipment maintenance decisions, and no adjustment decisions; The specific steps of equipment maintenance decision-making are: Step 1: Record highly interfering devices and moderately interfering devices as maintenance devices, and sort the maintenance devices in descending order according to their corresponding production interference indexes to obtain a maintenance list; select the maintenance device with the largest production interference index as the target device; Step 2: Retrieve the maintenance records of each maintenance personnel, where the maintenance records include the number of maintenance times and the production interference index of the equipment corresponding to each maintenance, recorded as Sdk, the maintenance start time and the maintenance end time; calculate the time difference between the maintenance start time and the maintenance end time to obtain the maintenance duration, recorded as Mk, where k=1,2,3...K, K is a positive integer, K represents the total number of maintenance times, and k represents any one of the maintenance; obtain the current number of equipment to be maintained by the maintenance personnel, recorded as L, and substitute it with the production interference index Sdk and the maintenance duration Mk into the set formula The maintenance time effectiveness value LM of the maintenance personnel is calculated, where f1, f2, and f3 are respectively the set proportional coefficients; thus, the maintenance time effectiveness value corresponding to each maintenance personnel can be obtained; Step 3: Select the maintenance personnel with the largest maintenance time value as the target maintenance personnel, and assign the target equipment to the target maintenance personnel, thereby increasing the number of equipment to be maintained by the target maintenance personnel by one; when the maintenance personnel completes the maintenance of a maintenance equipment, the number of equipment to be maintained by the corresponding maintenance personnel is reduced by one; the number of equipment to be maintained by each maintenance personnel is updated to step 2; Step 4: Repeat steps 1 to 3 until all maintenance equipment is completed.

[0005] Furthermore, the specific process of comprehensive analysis based on the received status parameters is as follows: 201: Set an important score for each model of equipment, extract each equipment model, and compare it with all the set models to match the corresponding important score; substitute the important score S, equipment operation value Yg and vibration abnormality value Hg of each equipment into the set formula The production interference index Sd corresponding to each device is calculated, where d1 and d2 are respectively the set proportional coefficients; 202: Compare and analyze the production interference index of each device with the set interference range to divide the equipment corresponding to the production interference index into high interference equipment, medium interference equipment and low interference equipment, and count the cumulative number of high interference equipment, medium interference equipment and low interference equipment respectively, and record them as U1, U2 and U3 respectively; sum up the production interference indexes corresponding to high interference equipment, medium interference equipment and low interference equipment to obtain high interference value, medium interference value and low interference value, and record them as U4, U5 and U6 respectively; substitute U1, U2, U3, U4, U5 and U6 into the set formula The production decision value Un is calculated, where n1, n2, and n3 are the set proportional coefficients, and n1>n2>n3>0; 203: When the production decision value is greater than the maximum value in the set decision interval, the shutdown and maintenance decision is output; when the production decision value is in the set decision interval, the equipment maintenance decision is output; when the production decision value is less than the minimum value in the set decision interval, the no adjustment decision is output.

[0006] Furthermore, the specific process of identification based on the operation information of the device is as follows: 401: retrieve the operating power and operating temperature at each collection moment, and conduct in-depth analysis on the operating status of the equipment to obtain the equipment operating value; 402: Retrieving the operation amplitude corresponding to each acquisition moment, and performing quantitative analysis on the vibration state of the corresponding equipment to obtain a vibration abnormality value; 403: Substitute the equipment operation value Yg and the vibration abnormality value Hg into the set formula The latest acquisition frequency P is calculated, where r1 and r2 are the set proportional coefficients, and β is the frequency conversion coefficient. The latest acquisition frequency of each device can be obtained, and an acquisition instruction is generated according to the latest acquisition frequency of each device. The instruction is sent to the database to guide the database to collect data from each device.

[0007] Furthermore, the specific process of in-depth analysis of the operating status of the equipment based on the operating power and operating temperature is as follows: 501: Set each model of equipment to correspond to a design parameter, extract each equipment model, and compare it with all the set models to match the corresponding design parameters, where the design parameters include design temperature and design power; substitute the design temperature HT, design power HW, operating temperature Tq and operating power Wq into the set formula Calculate and obtain the equipment standard value TWq at each collection moment, where b1 and b2 are the set proportional coefficients, q=1, 2, 3...Q, Q is a positive integer, Q represents the total number of collection moments, and q represents the sequence number of any collection moment; 502: construct a two-dimensional rectangular coordinate system with time as the horizontal coordinate and the equipment standard value as the vertical coordinate, input the equipment standard value into the coordinate axis according to its corresponding collection time, and record the position of the equipment standard value in the coordinate axis as the standard point, and use a smooth curve to connect the standard points in sequence to obtain a curve graph of the equipment annotation value changing with time; 503: Performing a graphical trend analysis on the curve graph of the equipment annotation value changing over time to obtain the equipment operation value.

[0008] Furthermore, the specific process of performing graphical trend analysis on the curve graph of the equipment annotation value changing over time is as follows: 601: Draw a tangent line of the curve at each standard point, and calculate the slope of the tangent line using the least square method to obtain the standard slope corresponding to each standard point, which is recorded as Zq; 602: The standard slope greater than zero is recorded as the positive correlation slope, and it is compared with the set positive correlation interval to analyze and classify the positive correlation slope into high positive correlation, moderate positive correlation and low positive correlation. The number of high positive correlation, moderate positive correlation and low positive correlation is counted respectively, and they are recorded as G1, G2 and G3 respectively; the total value of the positive slope is calculated by summing up the positive correlation slopes and recorded as G4; G1, G2, G3 and G4 are substituted into the set formula The positive correlation value Ga is calculated, where a1, a2, and a3 are respectively set proportional coefficients, and a1>a2>a3>0; The negative correlation slope is obtained by taking the absolute value of the standard slope less than zero. Similarly, the negative correlation slope is compared and analyzed to obtain the negative correlation value, which is recorded as Aa. 603: Substitute the standard slope Zq, positive correlation value Ga, negative correlation value Aa and the equipment standard value TWq at each acquisition time into the set formula The equipment operation value Yg is obtained by calculation, where g1, g2, and g3 are the set proportional coefficients, and are the average values ​​of the standard slopes of each standard point.

[0009] Furthermore, the specific process of quantitatively analyzing the vibration state of the equipment based on the operating amplitude is as follows: 701: Set each device model to correspond to a normal amplitude range, and compare the device model with all the set models to match the corresponding normal amplitude range; 702: retrieve the running amplitude at each acquisition moment and record it as Fq, compare the running amplitude at each acquisition moment with the normal amplitude range to obtain the relative amplitude and record it as Dq; substitute the running amplitude Fq and the relative amplitude Dq at each acquisition moment into the set formula The amplitude risk value ZDq at each acquisition moment is calculated, where α is the set correction factor; 703: construct a two-dimensional rectangular coordinate system with time as the horizontal coordinate and amplitude risk value as the vertical coordinate, input the position of the amplitude risk value into the coordinate axis according to its corresponding collection time as the risk point, and connect the risk points in sequence with a smooth curve to obtain a curve graph of the amplitude risk value of the equipment changing with time; 704: Performing a graphical trend analysis on a curve graph of the amplitude risk value of the equipment changing over time to obtain a vibration abnormality value.

[0010] Furthermore, the specific process of performing graphical trend analysis on the curve graph of the equipment's amplitude risk value changing over time is as follows: Draw a tangent line at each risk point and calculate the slope of the tangent line to obtain the vibration slope of each risk point, which is recorded as Hq; The risk slopes greater than zero are summed up to obtain the risk increase value, recorded as X1, and the risk slopes less than zero are summed up and the absolute value is taken to obtain the risk reduction value, recorded as X2; Substitute the vibration slope Hq, risk increase value Z1, risk reduction value Z2 and the amplitude risk value ZDq at each acquisition time into the set formula The calculated vibration abnormal value Hg, where g4, g5, and g6 are the set proportional coefficients, is the average risk slope of each risk point.

[0011] In order to achieve the above object, according to another aspect of the present invention, a computer data intelligent recognition method is provided, the method comprising the following steps: R1: Based on the received collection instructions, each sensor is controlled to collect data to obtain production information and maintenance information; the production information includes the operating power, operating temperature and operating amplitude of each device; the maintenance information includes maintenance records; R2: Identify based on the equipment's operating information to obtain the equipment's status parameters; the operating information includes the operating temperature, operating power and operating amplitude of each device in the factory, and the status parameters include the equipment's operating value and vibration abnormality value; R3: Perform a comprehensive analysis based on the received status parameters to obtain the production interference index of each device, and output decision opinions based on this, where the decision opinions include production suspension and maintenance decisions, equipment maintenance decisions, and no adjustment decisions; The specific steps of equipment maintenance decision-making are: Step 1: Record highly interfering devices and moderately interfering devices as maintenance devices, and sort the maintenance devices in descending order according to their corresponding production interference indexes to obtain a maintenance list; select the maintenance device with the largest production interference index as the target device; Step 2: Retrieve the maintenance records of each maintenance personnel, where the maintenance records include the number of maintenance times and the production interference index of the equipment corresponding to each maintenance, recorded as Sdk, the maintenance start time and the maintenance end time; calculate the time difference between the maintenance start time and the maintenance end time to obtain the maintenance duration, recorded as Mk, where k=1,2,3...K, K is a positive integer, K represents the total number of maintenance times, and k represents any one of the maintenance; obtain the current number of equipment to be maintained by the maintenance personnel, recorded as L, and substitute it with the production interference index Sdk and the maintenance duration Mk into the set formula The maintenance time effectiveness value LM of the maintenance personnel is calculated, where f1, f2, and f3 are respectively the set proportional coefficients; thus, the maintenance time effectiveness value corresponding to each maintenance personnel can be obtained; Step 3: Select the maintenance personnel with the largest maintenance time value as the target maintenance personnel, and assign the target equipment to the target maintenance personnel, thereby increasing the number of equipment to be maintained by the target maintenance personnel by one; when the maintenance personnel completes the maintenance of a maintenance equipment, the number of equipment to be maintained by the corresponding maintenance personnel is reduced by one; the number of equipment to be maintained by each maintenance personnel is updated to step 2; Step 4: Repeat steps 1 to 3 until all maintenance equipment is completed.

[0012] Beneficial effects of the present invention: The present invention obtains equipment status parameters by real-time monitoring and status evaluation of equipment in large factories, performs comprehensive analysis based on equipment status parameters to obtain the latest equipment acquisition frequency, and can dynamically adjust data acquisition frequency based on equipment status to achieve self-adaptation of computer data acquisition in large factories. Compared with fixed-cycle acquisition methods, the present invention can better reflect changes in equipment status, more comprehensively cover possible changes and abnormal conditions of equipment, ensure the effectiveness and timeliness of data acquisition, thereby improving the accuracy of identifying equipment status, and further providing technical support for making accurate production decisions; The present invention conducts a comprehensive analysis of the equipment operation values, vibration abnormality values ​​and important scores of each equipment in a large factory, thereby judging the production status of the large factory and outputting corresponding decisions (such as shutdown for inspection and repair, equipment maintenance or no adjustment required). It can quickly respond to changes in production status, reduce the risk of equipment failure to production, and ensure the safety and stability of the production process; at the same time, the automated decision output module can reduce errors and delays in manual judgment, improve the speed and accuracy of decision-making, and thus improve the efficiency of overall production management. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings: Figure 1 is a schematic diagram of system module connection of the present invention; Figure 2 It is a schematic flow chart of the method of the present invention. DETAILED DESCRIPTION

[0014] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0015] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0016] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so as to describe the embodiments of the present invention described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0017] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] According to an embodiment of the present invention, Figure 1 As shown, a computer data intelligent recognition system is provided, which includes: a database, a data recognition module and a decision output module; Based on the received collection instructions, the database communicates with various sensors to obtain production data, where the production data includes the operation information of the equipment and the maintenance records of the maintenance personnel. The operation information includes the operation temperature, operation power and operation amplitude of each device in the factory. The data identification module identifies the operating status of each device in the large factory based on the operating information and maintenance information of each device in the large factory to obtain the status parameters of each device in the large factory, where the status parameters include the equipment operating value and the vibration abnormality value, specifically: The operating temperature and operating power corresponding to each collection time are retrieved and recorded as Tq and Wq respectively, where q=1,2,3...Q, Q is a positive integer, Q represents the total number of collection times, and q represents the sequence number of any collection time; Set a design parameter for each model of equipment, where the design parameter includes the design temperature and the design power (usually refers to the rated power), and record them as HT and HW respectively; it should be noted that the design parameter refers to the most suitable working parameter determined by the equipment manufacturing process, which is generally described and recorded in detail in the technical manual or design specification of the equipment; By setting the formula The equipment standard value TWq at each acquisition time is calculated, where b1 and b2 are respectively the set proportional coefficients. It can be seen from the formula that when the operating temperature and operating power of the equipment are closer to the design parameters, it means that the equipment is closer to the standard state during operation, and the standard value is larger; correspondingly, when the operating temperature and operating power of the equipment are farther away from the design parameters, it means that the equipment is more deviated from the standard state during operation, and the standard value is smaller. A two-dimensional rectangular coordinate system is constructed with time as the horizontal coordinate and the equipment standard value as the vertical coordinate. The equipment standard value is input into the coordinate axis according to its corresponding collection time, and the position of the equipment standard value in the coordinate axis is recorded as the standard point. A smooth curve is used to connect the standard points in sequence to obtain a curve chart of the equipment annotation value changing with time; a tangent line is drawn at each standard point, and the slope of the tangent line is calculated using the least squares method to obtain the standard slope corresponding to each standard point, which is recorded as Zq; it should be noted that when the standard slope is greater than zero, the equipment standard value at the standard point shows an increasing trend; when the standard slope is less than zero, the equipment standard value at the standard point shows a decreasing trend; The standard slope greater than zero is recorded as the positive correlation slope, and it is compared with the set positive correlation interval for analysis. When the positive correlation slope is greater than the set upper limit of the positive correlation interval, it means that the increasing trend of the equipment standard value at the standard point is more obvious, and a high positive correlation is accumulated; when the positive correlation slope is within the set positive correlation interval, a moderate positive correlation is accumulated; when the positive correlation slope is less than the set lower limit of the positive correlation interval, a low positive correlation is accumulated; the number of high positive correlation, moderate positive correlation and low positive correlation is counted respectively, and they are recorded as G1, G2, and G3 respectively; the total value of the positive slope is calculated by summing up the positive correlation slopes and recorded as G4; using the set formula The positive correlation value Ga is calculated, where a1, a2, and a3 are respectively the set proportional coefficients, and a1>a2>a3>0; the coefficient of the total positive slope value is calculated and analyzed according to the magnitude of each positive correlation slope, which can better measure the increase in positive correlation; Take the absolute value of the standard slope less than zero to get the negative correlation slope, and compare it with the set negative correlation interval. When the negative correlation slope is greater than the upper limit of the set negative correlation interval, it means that the decreasing trend of the equipment standard value at the standard point is more obvious, and a high negative correlation is accumulated; when the negative correlation slope is within the set negative correlation interval, a moderate negative correlation is accumulated; when the negative correlation slope is less than the lower limit of the set negative correlation interval, a low negative correlation is accumulated; the number of high negative correlation, moderate negative correlation and low negative correlation is counted respectively, and they are recorded as A1, A2, and A3 respectively; the total value of the negative slope is calculated by summing up the negative correlation slopes and recorded as A4; using the set formula The negative correlation value Aa is calculated, where a4, a5, and a6 are respectively the set proportional coefficients, and a4>a5>a6>0; the coefficient of the total negative slope is calculated and analyzed according to the magnitude of each negative correlation slope, which can better measure the increase in negative correlation; The standard slope Zq, positive correlation value Ga, negative correlation value Aa and the equipment standard value TWq at each acquisition time are calculated by the set formula The equipment operation value Yg is obtained by calculation, where g1, g2, and g3 are respectively the set proportional coefficients, and are the standard slope averages of each standard point. It can be seen from the formula that when the positive correlation value is larger, it means that the increasing trend of the equipment standard value is larger, which means that the operating parameters of the equipment are more in line with the design requirements, and the equipment operation value is larger; when the negative correlation value is larger, it means that the decreasing trend of the equipment standard value is larger, which means that the operating parameters of the equipment are less in line with the design requirements, and the equipment operation value is smaller; when the standard slope changes more, that is, the equipment standard value fluctuates more, it means that the equipment is more unstable, and the equipment operation value is smaller; Set a normal amplitude range for each model of equipment. It should be noted that the normal amplitude range refers to the vibration amplitude range obtained by benchmark measurement after the initial installation of the equipment or after sufficient debugging. Therefore, when the equipment is running well, the vibration amplitude should fluctuate within this normal range and will not significantly exceed or fall below this range. If the vibration amplitude frequently exceeds the set normal range during actual operation, it means that the risk of problems with the indicated equipment is relatively high, such as imbalance, looseness or other mechanical failures. Compare the equipment model with all the set models to match the corresponding normal amplitude range. The running amplitude at each acquisition moment is retrieved and recorded as Fq. The running amplitude at each acquisition moment is compared with the normal amplitude range to obtain the relative amplitude. The specific comparison method is: When the amplitude is greater than the upper limit of the normal amplitude interval, the upper limit of the normal amplitude interval is used as the relative amplitude; when the amplitude is within the normal amplitude interval, the amplitude is used as the relative amplitude; when the amplitude is less than the lower limit of the normal amplitude interval, the lower limit of the normal amplitude interval is used as the relative amplitude; thus, the relative amplitude corresponding to the amplitude at each acquisition moment can be obtained and recorded as Dq; using the set formula The amplitude risk value ZDq at each acquisition moment is calculated, where α is the set correction factor; a two-dimensional rectangular coordinate system is constructed with time as the horizontal coordinate and the amplitude risk value as the vertical coordinate, and the position of the amplitude risk value input into the coordinate axis according to its corresponding acquisition moment is recorded as the risk point, and a smooth curve is used to connect the risk points in sequence to obtain a curve of the amplitude risk value of the equipment changing with time; a tangent line is drawn at each risk point, and the slope of the tangent line is calculated to obtain the vibration slope of each risk point, which is recorded as Hq; the risk slopes greater than zero are summed up to obtain the risk increase value, which is recorded as X1, and the risk slopes less than zero are summed up and the absolute value is taken to calculate the risk reduction value, which is recorded as X2; using the set formula The calculated vibration abnormal value Hg, where g4, g5, and g6 are the set proportional coefficients, is the risk slope mean of each risk point; it can be seen from the formula that the greater the vibration risk value at each acquisition moment, the greater the vibration abnormal value; the greater the increasing trend of the overall change trend of the vibration risk value and the smaller the decreasing trend, the greater the vibration abnormal value; the more volatile the vibration risk value is, the more unstable the vibration of the equipment is, and the greater the vibration abnormal value is; The equipment operation value Yg and the vibration abnormal value Hg are calculated by the set formula The latest acquisition frequency P is calculated, where r1 and r2 are the set proportional coefficients, and β is the frequency conversion coefficient. It can be seen from the formula that when the equipment operation value is larger, it means that the equipment operation state is more normal, and the acquisition frequency is smaller; when the vibration abnormality value is larger, it means that the equipment vibration state is abnormal, and the risk of failure is greater, then the acquisition frequency is larger; it should be noted that the larger the acquisition frequency, the more frequent the acquisition times; thus, the latest acquisition frequency of each device can be obtained, and the acquisition instruction is generated according to the latest acquisition frequency of each device, and it is sent to the database to guide the database to collect data from each device; By conducting real-time monitoring and status evaluation of equipment in large factories, we can obtain equipment status parameters, conduct comprehensive analysis based on the equipment status parameters to obtain the latest data collection frequency of the equipment, and dynamically adjust the data collection frequency according to the equipment status to achieve self-adaptation of computer data collection in large factories. Compared with the fixed-cycle collection method, it can better reflect changes in equipment status, more comprehensively cover all possible changes and abnormal conditions of equipment, ensure the effectiveness and timeliness of data collection, thereby improving the accuracy of identifying equipment status and making more accurate production decisions.

[0019] The decision output module conducts a comprehensive analysis based on the equipment operation value Yg and vibration abnormality value Hg of each equipment in a large factory to judge the production status and output decision opinions; specifically: Set an importance score for each model of equipment. It should be noted that the importance score refers to the importance of the equipment for the production of large factories. For example, equipment that provides production power, supports key production processes, or directly affects product quality (large pumps that provide production power) will usually have a higher importance score. Extract each equipment model and compare it with all the set models to match the corresponding importance score, which is recorded as S. The importance score S, equipment operation value Yg, and vibration abnormality value Hg of each equipment are calculated through the set formula The production interference index Sd corresponding to each device is calculated, where d1 and d2 are respectively the set proportional coefficients; Compare and analyze the production interference index of each device with the set interference interval. When the production interference index is greater than the maximum value in the set interference interval, a high interference device is accumulated; when the production interference index is in the set interference interval, a medium interference device is accumulated; when the production interference index is less than the minimum value in the set interference interval, a low interference device is accumulated; the cumulative number of high interference devices, medium interference devices and low interference devices is counted respectively, and they are recorded as U1, U2 and U3 respectively; the production interference indexes corresponding to high interference devices, medium interference devices and low interference devices are summed up to obtain high interference values, medium interference values ​​and low interference values, and they are recorded as U4, U5 and U6 respectively; using the set formula The production decision value Un is calculated, where n1, n2, and n3 are the set proportional coefficients, and n1>n2>n3>0. It can be seen from the formula that the greater the degree of interference of equipment in a large factory, the greater the risk of production, which may seriously damage large equipment and cause great losses, especially when some equipment in a large factory is of high value. The greater the production decision value; Compare and analyze the production decision value with the set decision interval. When the production decision value is greater than the maximum value in the set decision interval, it means that there is a very high risk in production. Then the shutdown and maintenance decision is output, and the production is controlled to be shut down for maintenance. When the production decision value is within the set decision interval, the equipment maintenance decision is output and equipment maintenance is performed. The specific operation steps of equipment maintenance are as follows: Step 1: Record highly interfering devices and moderately interfering devices as maintenance devices, and sort the maintenance devices in descending order according to their corresponding production interference indexes to obtain a maintenance list; select the maintenance device with the largest production interference index as the target device; Step 2: Retrieve the maintenance records of each maintenance personnel, where the maintenance records include the number of maintenance times and the production interference index of the equipment corresponding to each maintenance, recorded as Sdk, the maintenance start time and the maintenance end time; calculate the time difference between the maintenance start time and the maintenance end time to get the maintenance duration, and record it as Mk, where k=1,2,3...K, K is a positive integer, K represents the total number of maintenance times, and k represents any one of the maintenance; obtain the current number of equipment to be maintained by the maintenance personnel, and record it as L; the number of equipment to be maintained L, the production interference index Sdk and the maintenance duration Mk are calculated through the set formula The maintenance time effectiveness value LM of the maintenance personnel is calculated, where f1, f2, and f3 are respectively the set proportional coefficients; thus, the maintenance time effectiveness value corresponding to each maintenance personnel can be obtained; Step 3: Select the maintenance personnel with the largest maintenance time value as the target maintenance personnel, and assign the target equipment to the target maintenance personnel, thereby increasing the number of equipment to be maintained by the target maintenance personnel by one; when the maintenance personnel completes the maintenance of a maintenance equipment, the number of equipment to be maintained by the corresponding maintenance personnel is reduced by one; the number of equipment to be maintained by each maintenance personnel is updated to step 2; Step 4: Repeat steps 1 to 3 until all maintenance equipment is completed; When the production decision value is less than the minimum value in the set decision interval, it means that the risk of production is very small and can be ignored, so the output does not need to adjust the decision; By comprehensively analyzing the equipment operating values, vibration abnormalities, and important scores of each device in a large factory, the production status of the large factory can be judged and corresponding decisions (such as shutdown for inspection and repair, equipment maintenance, or no adjustment) can be output. This can quickly respond to changes in production status, reduce the risk of equipment failure to production, and ensure the safety and stability of the production process. At the same time, the automated decision output module can reduce errors and delays in manual judgment, improve the speed and accuracy of decision-making, and thus improve the efficiency of overall production management.

[0020] According to an embodiment of the present invention, Figure 2 As shown, a computer data intelligent recognition method is also provided, the method comprising the following steps: R1: Based on the received collection instructions, each sensor is controlled to collect data to obtain production information and maintenance information; the production information includes the operating power, operating temperature and operating amplitude of each device; the maintenance information includes maintenance records; R2: Identify based on the equipment's operating information to obtain the equipment's status parameters; the operating information includes the operating temperature, operating power and operating amplitude of each device in the factory, and the status parameters include the equipment's operating value and vibration abnormality value; R3: Perform a comprehensive analysis based on the received status parameters to obtain the production interference index of each device, and output decision opinions based on this, where the decision opinions include production suspension and maintenance decisions, equipment maintenance decisions, and no adjustment decisions; The specific steps of equipment maintenance decision-making are: Step 1: Record highly interfering devices and moderately interfering devices as maintenance devices, and sort the maintenance devices in descending order according to their corresponding production interference indexes to obtain a maintenance list; select the maintenance device with the largest production interference index as the target device; Step 2: Retrieve the maintenance records of each maintenance personnel, where the maintenance records include the number of maintenance times and the production interference index of the equipment corresponding to each maintenance, recorded as Sdk, the maintenance start time and the maintenance end time; calculate the time difference between the maintenance start time and the maintenance end time to obtain the maintenance duration, recorded as Mk, where k=1,2,3...K, K is a positive integer, K represents the total number of maintenance times, and k represents any one of the maintenance; obtain the current number of equipment to be maintained by the maintenance personnel, recorded as L, and substitute it with the production interference index Sdk and the maintenance duration Mk into the set formula The maintenance time effectiveness value LM of the maintenance personnel is calculated, where f1, f2, and f3 are respectively the set proportional coefficients; thus, the maintenance time effectiveness value corresponding to each maintenance personnel can be obtained; Step 3: Select the maintenance personnel with the largest maintenance time value as the target maintenance personnel, and assign the target equipment to the target maintenance personnel, thereby increasing the number of equipment to be maintained by the target maintenance personnel by one; when the maintenance personnel completes the maintenance of a maintenance equipment, the number of equipment to be maintained by the corresponding maintenance personnel is reduced by one; the number of equipment to be maintained by each maintenance personnel is updated to step 2; Step 4: Repeat steps 1 to 3 until all maintenance equipment is completed.

[0021] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A computer data intelligent recognition system, characterized in that: include: Data identification module and decision output module; The data identification module performs identification based on the operation information of the equipment to obtain the status parameters of the equipment; The decision output module performs a comprehensive analysis based on the received state parameters to obtain the production interference index of each device, and outputs decision opinions based on this, where the decision opinions include shutdown and maintenance decisions, equipment maintenance decisions, and no adjustment decisions; the specific steps of equipment maintenance decisions are: Step 1: Record highly interfering equipment and moderately interfering equipment as maintenance equipment, and sort each maintenance equipment in descending order according to its corresponding production interference index to obtain a maintenance list; The maintenance equipment with the largest production interference index is selected as the target equipment; Step 2: retrieve the maintenance records of each maintenance personnel, where the maintenance records include the number of maintenances and the production interference index of the equipment corresponding to each maintenance, the maintenance start time and the maintenance end time; calculate the time difference between the maintenance start time and the maintenance end time to obtain the maintenance duration; The number of equipment to be maintained by the maintenance personnel is obtained, and the number is normalized with the production interference index and the maintenance time and the value is taken. The maintenance time efficiency value of the maintenance personnel is obtained by numerical analysis; thus, the maintenance time efficiency value corresponding to each maintenance personnel can be obtained; Step 3: Select the maintenance personnel with the largest maintenance time value as the target maintenance personnel, and assign the target equipment to the target maintenance personnel, thereby increasing the number of equipment to be maintained by the target maintenance personnel by one; when the maintenance personnel completes the maintenance of a maintenance equipment, the corresponding number of equipment to be maintained by the maintenance personnel is reduced by one; update the number of equipment to be maintained by each maintenance personnel to step 2; repeat steps 1 to 3 until all maintenance equipment is completed.

2. A computer data intelligent recognition system according to claim 1, characterized in that: The specific process of comprehensive analysis based on the received status parameters is as follows: 201: Set an important score for each model of equipment, extract each equipment model, and compare it with all the set models to match the corresponding important score; normalize the important score, equipment operation value and vibration abnormal value of each equipment and take their values, and analyze the values ​​to obtain the production interference index corresponding to each equipment; 202: Compare and analyze the production interference index of each device with the set interference range to divide the devices corresponding to the production interference index into high interference devices, medium interference devices and low interference devices, count the cumulative times of high interference devices, medium interference devices and low interference devices respectively, and sum the production interference indexes corresponding to the high interference devices, medium interference devices and low interference devices to obtain the high interference value, medium interference value and low interference value respectively; perform formula calculation and analysis on the cumulative times of high interference devices, the cumulative times of medium interference devices, the cumulative times of low interference devices, the high interference value, the medium interference value and the low interference value to obtain the production decision value; 203: When the production decision value is greater than the maximum value in the set decision interval, the shutdown and maintenance decision is output; when the production decision value is in the set decision interval, the equipment maintenance decision is output; when the production decision value is less than the minimum value in the set decision interval, the no adjustment decision is output.

3. A computer data intelligent recognition system according to claim 1, characterized in that: Also includes database; Based on the received collection instructions, the database collects data by controlling the sensors connected to it to obtain production information and maintenance information; the production information includes the operating power, operating temperature and operating amplitude of each device; the maintenance information includes maintenance records.

4. A computer data intelligent recognition system according to claim 1, characterized in that: The specific process of identification based on the operation information of the equipment is as follows: 401: retrieve the operating power and operating temperature at each collection moment, and conduct in-depth analysis on the operating status of the equipment to obtain the equipment operating value; 402: Retrieving the operation amplitude corresponding to each acquisition moment, and performing quantitative analysis on the vibration state of the corresponding equipment to obtain a vibration abnormality value; 403: The latest acquisition frequency is obtained by formulating and analyzing the equipment operation value and the vibration abnormality value, thereby obtaining the latest acquisition frequency of each device, generating an acquisition instruction according to the latest acquisition frequency of each device, and sending it to the database to guide the database to collect data from each device.

5. A computer data intelligent recognition system according to claim 4, characterized in that: The specific process of in-depth analysis of the operating status of the equipment based on operating power and operating temperature is as follows: 501: Set each device model to correspond to a design parameter, extract each device model, and compare it with all the set models to match the corresponding design parameters, where the design parameters include design temperature and design power; normalize the design temperature, design power, operating temperature and operating power and take their values, analyze the values ​​to obtain the device standard value, and thus obtain the device standard value at each collection time; 502: construct a two-dimensional rectangular coordinate system with time as the horizontal coordinate and the equipment standard value as the vertical coordinate, input the equipment standard value into the coordinate axis according to its corresponding collection time, and record the position of the equipment standard value in the coordinate axis as the standard point, and use a smooth curve to connect the standard points in sequence to obtain a curve graph of the equipment annotation value changing with time; 503: Performing a graphical trend analysis on the curve graph of the equipment annotation value changing over time to obtain the equipment operation value.

6. A computer data intelligent recognition system according to claim 5, characterized in that: The specific process of performing graphical trend analysis on the curve chart of equipment annotation value changing over time is as follows: 601: Draw a tangent line of the curve at each standard point, and calculate the slope of the tangent line using the least square method to obtain the standard slope corresponding to each standard point; 602: Recording a standard slope greater than zero as a positive correlation slope, and comparing and analyzing it with a set positive correlation interval to divide the positive correlation slope into high positive correlation, moderate positive correlation and low positive correlation, respectively counting the number of high positive correlation, moderate positive correlation and low positive correlation, and summing up the positive correlation slopes to obtain a total positive slope value; formulating and analyzing the number of high positive correlations, the number of moderate positive correlations, the number of low positive correlations and the total positive slope value to obtain a positive correlation value; Taking the absolute value of the standard slope less than zero gives the negative correlation slope. Similarly, comparing and analyzing the negative correlation slopes gives the negative correlation value. 603: The standard slope, the positive correlation value, the negative correlation value and the equipment standard value at each acquisition time are calculated and analyzed by formulating a formula to obtain the equipment operation value.

7. A computer data intelligent recognition system according to claim 4, characterized in that: The specific process of quantitatively analyzing the vibration state of the equipment based on the operating amplitude is as follows: 701: Set each device model to correspond to a normal amplitude range, and compare the device model with all the set models to match the corresponding normal amplitude range; 702: Retrieving the operating amplitude at each collection moment, comparing the operating amplitude at each collection moment with the normal amplitude range to obtain a relative amplitude; performing formulaic calculation and analysis on the operating amplitude and the relative amplitude at each collection moment to obtain an amplitude risk value at each collection moment; 703: construct a two-dimensional rectangular coordinate system with time as the horizontal coordinate and amplitude risk value as the vertical coordinate, input the position of the amplitude risk value into the coordinate axis according to its corresponding collection time as the risk point, and connect the risk points in sequence with a smooth curve to obtain a curve graph of the amplitude risk value of the equipment changing with time; 704: Performing a graphical trend analysis on a curve graph of the amplitude risk value of the equipment changing over time to obtain a vibration abnormality value.

8. A computer data intelligent recognition system according to claim 7, characterized in that: The specific process of performing graphical trend analysis on the curve of the equipment's amplitude risk value changing over time is as follows: Draw a tangent line at each risk point and calculate the slope of the tangent line to obtain the vibration slope of each risk point; The risk slopes greater than zero are summed up to obtain the risk increase value, and the risk slopes less than zero are summed up and the absolute value is taken to obtain the risk reduction value; The vibration slope, risk increase value, risk reduction value and amplitude risk value at each acquisition moment are normalized and their values ​​are taken, and the vibration abnormality value is obtained by numerical analysis.

9. A computer data intelligent recognition method, characterized in that Applied to a computer data intelligent recognition system as claimed in any one of claims 1 to 8, the method comprises the following steps: R1: Based on the received collection instructions, each sensor is controlled to collect data to obtain production information and maintenance information; the production information includes the operating power, operating temperature and operating amplitude of each device; the maintenance information includes maintenance records; R2: Identify based on the equipment's operating information to obtain the equipment's status parameters; the operating information includes the operating temperature, operating power and operating amplitude of each device in the factory, and the status parameters include the equipment's operating value and vibration abnormality value; R3: Perform a comprehensive analysis based on the received status parameters to obtain the production interference index of each device, and output decision opinions based on this, where the decision opinions include production suspension and maintenance decisions, equipment maintenance decisions, and no adjustment decisions.

Images