67 results about "Process capability index" patented technology

The invention provides an MES-based power distribution cabinet quality inspection analysis and process regulation and control method and system, and the method comprises the steps: converting a quality inspection standard into an executable rule, generating a standardized quality inspection template, evaluating the quality of a single project and a batch, monitoring the mean value and fluctuation of a production process based on a statistical process control theory, and calculating a process capability index. A dynamic threshold value formula is combined to adjust a control limit in real time, process stability is evaluated, equipment data is standardized, production batches are associated, data consistency is verified and ensured, graded early warning is performed according to the deviation degree, a machine learning model is combined to realize predictive maintenance, process parameters are dynamically corrected, historical data are analyzed through machine learning, and the process quality is improved. According to the method, high-order feature quantification influence factors are extracted, abnormal parameter combination is detected in combination with an isolated forest, a process strategy library is updated, closed-loop optimization is formed, full-process automation from data acquisition, real-time analysis and parameter adaptive adjustment to predictive maintenance is realized, and quality inspection efficiency and process stability are improved.

The invention discloses a flexible circuit board production quality monitoring method and system based on data feedback, and the method comprises the steps: collecting the physical parameters of development etching, drilling and copper plating processes, such as line width, line distance, aperture, roundness and copper thickness, and workshop temperature and humidity and dust concentration data; generating a single-variable control chart for a single-process physical parameter, generating a multivariable T2 control chart for a multi-coupling parameter process, and calculating a process stability index and a comprehensive fluctuation index; inputting the abnormal data into a BP neural network, identifying an abnormal mode type and outputting characteristic parameters; generating a parameter correction instruction according to the abnormal mode and the characteristic parameters, and adjusting equipment parameters in real time; recalculating the process capability index based on the adjusted data, and triggering secondary feedback if the process capability index does not reach the standard; and dynamically adjusting the threshold value of the control chart according to the standard deviation and the mean value of the process capability indexes of the continuous batches. Production key parameters are comprehensively covered, abnormity is found in time, accurate and comprehensive detection is achieved, real-time adjustment is achieved, stability and controllability are ensured, and the product quality is improved.

The invention relates to a titanium alloy smelting quality management method and system. The method comprises the steps that real-time monitoring data in the titanium alloy smelting process are collected; classifying and storing the real-time monitoring data to obtain historical process data; performing equipment abnormity early warning based on the equipment operation data and a preset first early warning rule, and generating first early warning information; obtaining a process capability index based on the process control node data, performing process data deviation early warning based on the obtained process capability index and a preset second early warning rule, and generating second early warning information; performing product manufacturing and detection early warning based on the ingot casting product manufacturing and detection data and a preset third early warning rule, and generating third early warning information; and displaying and processing the first early warning information, the second early warning information and the third early warning information in a man-machine interaction mode. Effective guidance is provided for quality management of titanium alloy smelting, and potential problems can be found and eliminated in time.

The invention relates to the technical field of welding, and particularly discloses an anti-fatigue welding process for a long-distance pipeline supporting steel structure. The process comprises the steps that a font groove structure is determined, and pre-welding polishing pretreatment and layered welding are conducted; fatigue samples of weld toe areas with different arc radiuses are collected, crack feature coordinates and stress concentration coefficients are extracted, failure modes are divided based on clustering, the arc radiuses are verified as main control factors of fatigue failure through multiple linear regression, and a core control range is determined by combining process capability indexes; carrying out fatigue verification on the basis of core parameter extension radius gradient, carrying out process compatibility matching in combination with a controllable interval and a thermal deformation interval of equipment, and outputting a radius candidate value through a response surface method; on-site construction constraints are collected, laboratory path space compatibility is analyzed, a formed track is optimized in a segmented mode, and constraint compensation factors are embedded. The anti-fatigue performance of the weld toe area of the supporting steel structure can be improved, and quality guarantee is provided for welding of the long-distance pipeline supporting steel structure.

The invention provides a glyceryl triacetate production parameter control method and system based on reinforcement learning, and relates to the technical field of optimization control methods, and the method comprises the steps: obtaining the production parameters of glyceryl triacetate; based on the kinetic model, constructing a kinetic equation of the esterification reaction of glycerol and acetic acid; constructing a digital twinborn simulation environment of the glyceryl triacetate production process; defining a reinforcement learning framework by taking a digital twin simulation environment as a scene; according to the reinforcement learning framework, taking the Elman neural network as a state predictor, and predicting the state of the glyceryl triacetate; solving the reinforcement learning framework through an MO-MPO algorithm, and determining an optimal control strategy and an optimal production parameter sequence corresponding to the optimal control strategy; judging whether the process capability index is smaller than a process capability index threshold value or not; if yes, continuing to solve the reinforcement learning framework; otherwise, outputting an optimal production parameter sequence; and controlling the optimal production parameter sequence through a PID (Proportion Integration Differentiation) control algorithm.

The invention discloses a production management method and device based on weight control, equipment and a storage medium. The method comprises the steps of obtaining a target weight interval of a product based on a preset process capability index; acquiring the actual weight of the current product; and comparing the actual weight of the current product with the target weight interval corresponding to the current product to obtain a test result. By utilizing the method, the target weight interval of the product is accurately determined through the preset process capability index, the final test result is determined by comparing the target weight interval with the target weight interval, the product can be timely found to be a box A and a goods B according to the test result, and the risk of mixed loading can be effectively solved.

The invention provides an index anomaly identification method and device, equipment and a storage medium, and the method comprises the steps: obtaining all index parameters in a production process in a current time period and all corresponding production parameters; calculating an index sequence formed by each process capability index corresponding to each index parameter and each production parameter, namely a first sequence and a second sequence; screening the abnormal process capability indexes in the first sequence according to a preset abnormal rule, and determining a first abnormal interval; and screening each process capability index in the second sequence based on the first abnormal interval, determining a second abnormal interval, and determining an index abnormality reason based on the second abnormal interval. Therefore, the index abnormality can be quickly positioned and the abnormality reason can be quickly determined while the index abnormality identification is realized, so that the index parameter control level is improved, and the production quality is ensured.

The invention belongs to the technical field of flight quality evaluation, and discloses a time sequence fusion model-based flight quality comprehensive evaluation method, which comprises the following steps of: obtaining a flight subject completion degree through a ratio of an actual flight subject completion content item to a flight subject action element; establishing a key evaluation index of each flight action according to the flight subject, and obtaining the flight quality accuracy of each evaluation index based on the improved process capability index model; setting an evaluation index influence factor according to the severity level of the flight subject evaluation index to the flight; obtaining evaluation scores of all flight actions according to the flight quality accuracy and the influence factors, and obtaining a single-sortie flight quality evaluation score in combination with the flight subject completion degree; and according to the historical sortie evaluation score of the pilots of the fleet, based on a time sequence influence attenuation fusion formula, obtaining the comprehensive evaluation score of the flight quality of the pilots and the fleet.

The invention discloses a unique optimal continuous sampling inspection scheme for risk control improvement. The method comprises the following steps: giving an average detection quality limit and second-class risks; collecting data; carrying out normality test on the latest data, if the fitting degree exceeds a threshold value, calculating the qualified rate and the lower confidence limit of the process, otherwise, stopping the machine for adjustment; comparing the qualified rate estimated value with the effective interval, comparing the average detection quality limit with the process capability critical value, and making a decision; if the number of the continuous qualified products is in the effective working interval, calculating the number ioj of the continuous qualified products and the test score foj, and determining the sample size n and the process yield index key value s0; and executing the optimal continuous sampling inspection scheme. Newest data is kept and recorded, a process capability index and a qualified rate estimator are calculated, and after comparison, a decision for executing an integrated control scheme or shutdown adjustment is made. The method is suitable for a scene without inspection capability limitation under large-scale continuous production, and can meet quality requirements at the lowest cost, eliminate risk control difference and control two types of risks at a set level.

The present invention discloses a method for evaluating production line stability based on a fault tree, comprising the following steps: obtaining multiple parameters of each device on the production line collected by sensors over a period of time, calculating the process capability index corresponding to each parameter, inputting the obtained process capability index corresponding to each parameter of each device into a pre-trained multiple linear regression model to obtain a stability index for the device, and inputting the stability index of each device into a pre-built fault tree-based stability analysis model to obtain a final stability judgment result for the device. The present invention can solve the technical problem that existing machine learning methods are complex for production lines, require long training times, and are unable to adapt to the real-time requirements of production environments in actual deployment and operation.

The invention discloses an integrated control scheme for an optimal single-level continuous sampling inspection and process capability index, and the scheme comprises the steps: firstly setting AOQL, AFIL, alpha and beta, and guaranteeing the stability of production data through normality inspection; and then, calculating a process qualified rate and a lower confidence limit thereof, and judging whether production halt adjustment is needed or further inspection is executed according to the qualified rate. Then, related quality indicators are calculated, and sampling inspection parameters are determined. The integrated control scheme is executed according to a preset inspection rule. And finally, through continuous monitoring and adjustment, it is ensured that the production quality meets the requirement. The method is suitable for process quality control with limited inspection capability. The integrated control scheme aims at reducing two risks while meeting the quality and cost requirements, is suitable for the process with the tolerance requirement on the production line, and realizes the comprehensive control of the quality, the cost and the risk.

The embodiment of the invention discloses a quality problem two-dimensional positioning method and device based on the industrial internet, and relates to the technical field of household appliance production quality analysis, based on the method, a first event triggered by process nodes crossing different production lines can be managed in a centralized manner based on the industrial internet, and after the first event is monitored, the first event can be sent to the industrial internet; the method comprises the following steps: quickly positioning a first topological path based on a pre-constructed topological model, screening out a first candidate topological node set based on a process capability index, screening out a second candidate topological node set based on a process control state, and preferentially identifying a second topological node from the first candidate topological node set. And preferentially identifying the third topological node from the second candidate topological node set, thereby effectively improving the efficiency of positioning the root cause node and the failure handle node by reducing the screening range on the basis of ensuring the screening success rate.

The application discloses a flexible circuit board production quality monitoring method and system based on data feedback, collects physical parameters such as line width, line spacing, hole diameter, roundness and copper thickness of developing etching, drilling and copper plating processes, and workshop temperature and humidity and dust concentration data, generates a single variable control chart for single process physical parameters, generates a multivariate T 2 Control chart for multiple coupling parameter processes, calculates process stability index and comprehensive fluctuation index, inputs abnormal data into a BP neural network, identifies abnormal mode types and outputs characteristic parameters, generates parameter correction instructions according to the abnormal mode and the characteristic parameters, adjusts equipment parameters in real time, recalculates the process capability index based on the adjusted data, triggers secondary feedback if the process capability index does not meet the standard, and dynamically adjusts the control chart threshold value according to the standard deviation and mean value of the process capability index of continuous batches. The application comprehensively covers key production parameters, discovers abnormalities in time, accurately and comprehensively detects, adjusts in real time to ensure stability and controllability, and improves product quality.

The invention discloses an abnormal network equipment identification method and device. The method comprises the following steps: obtaining performance index parameter sets of a first network device newly accessed to a network and a plurality of second network devices accessed to the network in a passive optical network in a preset time period; determining at least one second target network device with the same model and / or the same version as the first network device according to the performance index parameter set of the first network device and each second network device; determining a specification boundary value according to the performance index parameter set of the first network device, and determining a process capability index of each second target network device according to the specification boundary value and the performance index parameter set of each second target network device; and for each second target network device, determining whether the second target network device has quality abnormality according to the process capability index of the second target network device. The technical problem that the related technology cannot accurately identify the abnormal network device whose performance index parameter is degraded but does not reach the poor-quality standard is solved.

A process capability index warning system and a warning method for the same are provided. The system includes a process capability index calculation device, which determines whether a quantity of test samples of the test device within a cycle of a warning interval is less than a quantity threshold. When the quantity of the test samples is less than the quantity threshold, the quantity of the test samples is accumulated until an end of a next cycle of the warning interval. When the quantity of the test samples is not less than the quantity threshold, the process capability index calculation device calculates and obtains process capability index values, and determines whether or not the process capability index values are less than an index threshold. When any of the process capability index values is less than the index threshold, the process capability index calculation device sends a warning message.

The invention discloses an optimal four-parameter continuous sampling inspection and process capability index integrated control scheme. The method comprises the following specific steps: 1, giving two types of risks, namely a long-term average inspection number limit and an average detection quality upper limit; 2, checking the normality of the latest production data, if so, calculating the qualified rate and lower confidence limit of the process, otherwise, stopping the machine for adjustment; 3, decisions of inspection exemption, production halt or continuous inspection are made according to the qualified rate and the effective working interval; if so, calculating a key index in a limit process state; if in the effective working interval, an integrated control parameter # imgabs0 # 4 is calculated, and optimal four-parameter continuous sampling inspection (io3, fo3, 50, 4) is executed; 5, keeping recording the newest # imgabs 1 # data, calculating a process capability index # imgabs 2 # and a process qualification rate # imgabs 3 #, if the # imgabs 4 # and the # imgabs 5 #, returning to the step 4; if the # imgabs6 # is detected, the machine is stopped for adjustment; and if the # imgabs7 # and the # imgabs8 # are detected, returning to the step 2. The method is suitable for production quality control with limited inspection capability, and balancing quality, cost and risk.

The invention discloses an optimal relaxed single-level continuous sampling OCSP-V and process capability index Cpmk integrated control scheme. The method comprises the following steps: setting a detection number limit, a detection quality upper limit and a risk value; carrying out normality test on the latest production data, if the latest production data are qualified, calculating a process qualification rate and a lower confidence limit, otherwise, stopping the machine; calculating a pIOL value, a process capability and an index in a limit process state; and comparing the process qualified rate with the effective working interval, and deciding to execute the optimal scheme. In the effective interval, the number of continuous qualified products, the inspection score, the sample size and the process capability index key value are calculated, and an integrated control scheme is executed; and keeping recording the latest # imgabs0 # data, calculating a process capability index and a process qualification rate, and comparing the process capability index and the process qualification rate. The method is suitable for production quality control with tolerance upper and lower limit requirements and limited inspection capability, can meet quality, cost and two kinds of risk control at the same time, and can control the risk at a set level.

This application relates to a method, apparatus, electronic device, and storage medium for dynamic process capability assessment. In this disclosure, an access control threshold is first calculated; in the absence of historical data, multi-level random simulations are performed to generate a virtual sample set, and then initial prior distribution parameters are determined; if it is determined that the measured samples to be assessed in the current group pass the access control threshold verification, the prior distribution parameters are recursively updated based on the sample statistical parameters to obtain posterior distribution parameters characterizing the current manufacturing process. Then, a first probability that the process mean is within a preset mean interval, a second probability that the process standard deviation is less than a preset standard deviation limit, and a third probability that the process capability index is greater than or equal to the process capability index target are calculated to obtain the process capability assessment result for the current manufacturing process. This disclosure has at least one advantage: it does not rely on historical data, has a data quality filtering mechanism, and is applicable to small sample scenarios.

The application provides a supply chain data traceability monitoring method and system and a storage medium, relates to the technical field of supply chain quality traceability, and comprises the following steps: collecting production data of different material batches in each link of a supply chain, including raw material performance, processing process parameters and quality inspection results; calculating process capability indexes of each node through an industrial internet gateway, synchronously uploading the production data to the cloud, converting the production data into a vector format, and generating a cross-organization data sequence with material batches as the main line; analyzing link correlation based on the sequence, and constructing a quality influence topology graph dynamically reflecting the influence weight of process parameters on the final quality; when a quality inspection finds a batch quality defect, combining the topology graph and the parameter deviation of the defective batch, calculating the prediction probability of the upstream link as the source of the defect, and generating a visual report showing the most possible source link and the conduction path of the defect, so that accurate traceability of the supply chain quality defect and visual presentation of the influence path can be realized.

This invention belongs to the field of substrate manufacturing technology, specifically relating to a real-time quality monitoring data processing method for IC substrate manufacturing. It includes establishing a standardized data collection system for the entire IC substrate manufacturing process, enabling real-time collection, standardized processing, and storage of multi-dimensional quality data; intelligent analysis of the multi-dimensional quality data; construction of a defect identification model; and completion of defect classification and initial cause judgment. This invention extracts core quality features from quality indicator data, equipment operating status data, process parameter data, and environmental data, integrating them into a unified quality feature vector. Combined with a convolutional neural network model and a rule engine fusion algorithm, it overcomes the limitations of traditional single-threshold judgment. In particular, by calculating the process capability index CPK and the defect impact index, it achieves multi-level accurate classification of defects and initial cross-process cause judgment, improving defect identification accuracy and enabling early detection of potential defect trends.

This invention discloses a quality control method, apparatus, and system for printed circuit boards (PCBs), relating to the field of PCB manufacturing technology. The method includes: acquiring data collected by various sensors of a PCB manufacturing equipment at each time point within a preset time period; calculating the process capability index of the PCB manufacturing equipment at each time point; connecting the process capability indices at all time points to form a real-time process capability index curve; comparing the real-time process capability index curve with historical process capability index curves; determining whether the PCB manufacturing equipment is abnormal based on the comparison result; if the PCB manufacturing equipment is abnormal, calculating the abnormality level based on the comparison result, and generating control instructions for controlling the PCB manufacturing equipment to perform corresponding actions based on the abnormality level. This method can effectively avoid the problems of PCB defects and increased PCB production costs caused by abnormal process capability indices.

The present invention relates to the field of CNC machining, and specifically to a method for evaluating the process capability index of CNC machining parts, comprising the following steps: a first step: constructing a skew-normal process capability index of a position-scale distribution; a second step: replacing any quantile with a quantile of a standardized distribution; a third step: calculating the process capability index of a skew-normal distribution; and a fourth step: evaluating the process capability index. The present invention proposes a robust non-normal process capability index. This new index has a reasonable construction principle and a simple structure, can remain robust to changes in skewness, is easy to calculate, has a unified dimension, and can effectively evaluate the capability of a production process. The index not only covers the existing mainstream process capability index forms, but is also applicable to all position-scale family distributions, or distribution types that can be converted into this distribution family.

The invention mainly relates to the technical field of air conditioner control. In order to obtain the quality analysis condition in the air conditioner commodity inspection process in time, the commodity inspection data analysis method and system suitable for the air conditioner are provided, and operation parameters, collected by a commodity inspection machine, of the air conditioner under the refrigeration working condition and the heating working condition in a set time period are collected; the method comprises the steps of analyzing operation parameters, collected by a commodity inspection machine, of an air conditioner under a refrigeration working condition and a heating working condition within a set time period, obtaining process precision and process capability indexes within the set time period, analyzing the normal distribution condition of the operation parameters of the air conditioner, obtaining the Sigma level of the commodity inspection process within the set time period, and obtaining the Sigma level of the commodity inspection process within the set time period; the overall process quality condition of each time period and the parameter deviation condition of each single machine can be known in time, and meanwhile, the data analysis result can be subjected to chart visualization through a large screen.

The invention discloses an integrated control scheme for optimally improving single-level continuous sampling inspection (OCSP-2) and process capability index (Cpmk). The integrated control scheme mainly comprises the following steps: giving AOQ, AFIL, alpha and beta; performing normal test on the production process by using the latest n pieces of production data; if the normal fitting degree exceeds a threshold value, continuing the steps, otherwise, stopping the machine for adjustment; calculating # imgabs0 #, comparing the # imgabs0 # with the effective interval, making decisions of inspection exemption, production halt or execution, and if the # imgabs0 # is in the effective interval, calculating and executing an integrated control scheme; and keeping recording the newest data # imgabs 1 #, calculating and comparing corresponding parameters by using the newest data # imgabs 1 #, and finally making a decision of continuing to execute the integrated control scheme or shutdown adjustment. The method is suitable for process quality control with limited inspection capability. The integrated control scheme aims to meet quality and cost requirements and reduce first and second risks, is suitable for a process with tolerance requirements on a production line, and realizes comprehensive control of quality, cost and risks.

The invention provides a method for monitoring and analyzing the stability of an injection molding process. The method comprises the following steps: detecting an injection pressure value of injection molding equipment according to a set acquisition frequency; wherein the set acquisition frequency is set according to actual working condition requirements; determining a process capability index of the injection molding equipment according to the injection pressure value; judging whether the process capability index of the injection molding equipment is within a set threshold range or not, if yes, determining that the injection molding equipment is stable, and if not, generating an early warning instruction and executing early warning; according to the invention, the injection pressure of the injection molding equipment is continuously acquired for multiple times, the injection molding process capability index value is determined according to the acquired injection pressure value, and the influence of factors such as temperature and a mold is considered in the determination process, so that the stability of the current injection molding equipment can be accurately judged, frequent shutdown of injection molding production is effectively prevented, and the production efficiency is improved. And the production continuity and yield are ensured.

The invention provides an instance-based unlocking and locking mechanism tolerance optimization method and system. Belongs to the field of intelligent firearm manufacturing. According to the method, on the basis of ensuring that the assembly precision is qualified, the machining cost and the procedure capability index are comprehensively considered, and the tolerance of the unlocking and locking mechanism is designed and optimized. According to the method, on the basis of an unlocking and locking mechanism tolerance instance library, through analysis and calculation of contribution degrees, product processing cost and quality loss optimization targets are constructed, a target optimization model with process capability indexes and tolerance accumulation as constraint conditions is established, and the processing cost and the assembly quality loss are balanced. The design precision under precision manufacturing can be met, the production efficiency is improved, the part quality is improved, and the production cost is further reduced.

The present invention discloses an optimal multi-level continuous sampling inspection and process capability index integration method, comprising the following steps: setting the current average detection quality limit and the long-term average inspection number limit; calculating the normal fit, when the normal fit is greater than or equal to the preset value, calculating the process qualified product rate estimate and its lower confidence limit, otherwise stopping production for repair; calculating the continuous qualified product number and inspection score of the optimal multi-level continuous sampling inspection, determining the risk control sample size and the key value of the process capability index; executing the optimal multi-level inspection scheme; comparing the key value of the process capability index with the process capability index estimate, the process qualified product rate estimate and the lower confidence limit of the process qualified product rate estimate at the same time, and making a decision to continue the inspection, return to the normal fit or terminate production. The present invention meets the quality and risk constraints at the lowest cost, realizes the simultaneous control and quantitative control of two types of risks, and is suitable for production process control without inspection capability restrictions.

An automatic data analysis and report generation method, an electronic device and a storage medium, the method comprising: uploading a plurality of logs of a plurality of test stations to a log storage directory of a log storage server through an internal network, the plurality of test stations of a production line generating the plurality of logs; according to a set screening condition, a plurality of target logs meeting the screening condition in the log storage catalog are transmitted to a process capability index (CPK) and a measurement repeatability and reproducibility (GRAMP), and a plurality of target logs meeting the screening condition in the log storage catalog are transmitted to the CPK and the GRAMP; r) a report generation server; and analyzing the plurality of target logs through the CPK and GRR report generation server, automatically generating a CPK / GRR report, and sending the CPK / GRR report to a user personal computer.

Embodiments of the present application relate to the field of data processing, and disclose a factory process capability index evaluation method and device, a server and a storage medium. In the embodiments of the present application, a to-be-downloaded file is obtained according to each download address; wherein the to-be-downloaded file in the download address is updated according to a preset time period; data cleaning is performed on the to-be-downloaded file to obtain parameters used for calculating a process capability index; the parameters are loaded to a database; the process capability index is calculated according to the parameters in the database; and the calculation result and the parameters are displayed. The implementation of the present application is not limited to the evaluation of the factory process capability index in only a certain specific format, supports multiple data formats and performs data cleaning, can realize batch processing and calculation of parameters, automatically downloads the massive test data of each factory to the local in increments, loads the increments to the database, integrates the calculation results, and displays the results by using a report.

The invention discloses a monitoring method and device of test equipment, equipment, a medium and a product. The method comprises the following steps: acquiring test data from test sites; calculating a process capability index and a standard deviation value of each test site through a rolling window in a preset time interval based on the test data; and comparing the process capability index and the standard deviation value with matched preset thresholds, when the process capability index or the standard deviation value meets an abnormal alarm condition, triggering a multi-mode alarm of the corresponding test site, and forbidding at least one abnormal test site, thereby realizing real-time monitoring of each test site, and improving the test efficiency. Abnormities of a process capability index or a standard deviation value of a certain station can be found in time, unqualified devices are prevented from being continuously produced, multi-mode alarm can adapt to different environments, and response efficiency is improved; only the abnormal site is forbidden, and the parallel working state of the normal site is reserved, so that the shutdown of the whole equipment can be avoided, and the equipment utilization rate and the whole production efficiency are improved.