Multi-station online detection system and detection method for battering ram

Abstract

The invention discloses a battering ram multi-station online detection system and detection method, and belongs to the technical field of battering ram production detection. The system comprises a single-station basic detection unit, a multi-station traceability linkage core module, an abnormal conduction path analysis module and a self-adaptive threshold optimization module which interact through an industrial Ethernet, and is additionally provided with a key process multi-dimensional reinspection unit, a dynamic interference compensation module and the like. The method is based on the system, and detection is realized through station data acquisition and preprocessing, dynamic interference compensation, comprehensive quality evaluation, quantitative traceability, grading processing, threshold optimization and data storage. The core of the method is that a quality problem root station is accurately positioned through a quantitative model, an abnormal conduction path is traced, a detection threshold value is dynamically optimized in combination with traceability data, a'detection-traceability-optimization 'closed loop is formed, the problems that traditional manual traceability is low in precision, poor in efficiency and disjoint in traceability and detection are solved, the method is adaptive to a flexible production scene, resource waste is reduced, and production efficiency is improved. And the production quality and efficiency of the battering ram are improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of impact ram production detection, and particularly relates to an impact ram multi-station online detection system and a detection method. BACKGROUND

[0002] The existing impact ram production is mostly manually or mechanically assembled in multiple stations. Due to the negligence of the previous operation or the quality problem of the parts, unqualified workpieces are easily flowed into the next operation, resulting in waste of production resources and reduction of production efficiency.

[0003] To solve this problem, some production lines have set up basic detection devices such as CCD vision detection in a single station, but the technical defects of the quality problem tracing link have become the key bottleneck restricting the production efficiency and quality control level. After the existing technology finds the quality problem, it mostly relies on manual investigation of the previous operation records or simply speculates the root cause through the sequence correlation of the operation, and the impact ram assembly quality is affected by multiple stations and multiple parameters. The manual tracing not only has low positioning accuracy, but also has a root positioning error of 2-3 stations, and is easy to misjudge the root station, miss the related operation, and other problems, resulting in repeated occurrence of similar quality problems. At the same time, the detection data of each station is independent of each other, and when the terminal detection finds unqualified workpieces, it cannot trace the transmission process from the root station to the current station, and it is difficult to accurately identify the key nodes of abnormal transmission, so that the improvement measures lack pertinence. In addition, manual tracing needs to call multiple historical records of stations, compare operation parameters, and the average tracing time is 5-10 minutes, during which the production line needs to be suspended or run at low speed, causing production stagnation loss. Especially in the flexible production line mixed production scene of multiple models, the process parameters and station adaptation requirements of different models of impact rams are different, which further increases the complexity of manual tracing and reduces the tracing efficiency. More importantly, the existing technology is only used to solve the processing of a single unqualified workpiece, and for the same source quality problem that occurs frequently, it cannot optimize the detection threshold and adjust the detection focus through the tracing result, resulting in a "two-piece" between tracing and detection, and it is difficult to fundamentally improve the quality control level. SUMMARY

[0004] In view of the problems in the prior art, the present application proposes the following technical solutions: The impact ram multi-station online detection system and detection method comprises a single-station basic detection unit for realizing real-time data interaction through an industrial Ethernet, a multi-station traceability linkage core module, an abnormal conduction path analysis module and a self-adaptive threshold optimization module; the single-station basic detection unit collects assembly deviations and equipment operation parameters of each station, and transmits the preprocessed data bound with a unique workpiece identification; the multi-station traceability linkage core module integrates a quantitative traceability model, accurately locates the root station and associated impact stations of a quality problem by calculating a root attribution coefficient; the abnormal conduction path analysis module traces the conduction process of an abnormality from the root station to the current station and identifies key nodes based on the time sequence of detection data and the parameter correlation; and the self-adaptive threshold optimization module dynamically updates quality judgment thresholds in combination with traceability data to form a "detection-traceability-optimization" closed loop.

[0005] As a preferred embodiment of the above technical solution, the key process multi-dimensional reinspection unit is arranged after the impact ram assembly key process, integrates a CCD vision detection module, a force sensor, a vibration sensor and a data fusion module, collects multi-dimensional data of assembly space deviation, impact contact force and instantaneous vibration acceleration, and generates comprehensive quality evaluation data.

[0006] As a preferred embodiment of the above technical solution, the dynamic interference compensation module is internally provided with an interference compensation algorithm, calls synchronous detection data of a previous station, and corrects the original data of the current station sensor through the formula: is an interference compensation factor, and the value range is 0-0.8; is a distance reference value, and is fixed at 2 m; , is the original force and vibration acceleration data collected by the sensor of the current station; , is the corrected effective data.

[0007] As a preferred embodiment of the above technical solution, the single-station basic detection unit comprises a CCD vision sensor and a data preprocessing module, the CCD vision sensor collects x / y / z axis deviation data (Δx, Δy, Δz), the equipment sensor collects assembly pressure (F 工 ), working speed (v 工 ) and running vibration (a 工 ), the data preprocessing module adopts a mean filter with a window size of 5 for noise reduction, and the unique workpiece identification code contains model, online time and serial information of the workpiece.

[0008] ​As a preferred embodiment of the above technical solution, in the quantitative tracing model of the multi-station tracing linkage core module, the formula for calculating the root cause attribution coefficient R is as follows: in: This is the workstation weighting coefficient. =0.8 is the distance attenuation coefficient. For workstation spacing, For process correlation; The time decay factor, =0.5 is the time decay coefficient. , The current and the number are respectively Inspection time per workstation; This represents the overall quality assessment value for the j-th workstation. The adaptive threshold is set to n, which is the number of preceding associated workstations (default 3).

[0009] As a preferred embodiment of the above technical solution, the abnormal propagation path analysis module uses the following formula: Tracing the transmission of abnormalities; among which For conduction strength, , This refers to the deviation value of the core parameters of the workstation. The conduction attenuation coefficient, =0.3 is the attenuation coefficient. For workstation spacing, S represents the standard deviation threshold for the parameter; S≥0.3 indicates strong conduction, 0.1≤S<0.3 indicates weak conduction, and S<0.1 indicates no conduction.

[0010] As a preferred embodiment of the above technical solution, the threshold iteration formula of the adaptive threshold optimization module is: in For learning rate, when production fluctuates greatly =0.03-0.05, when production is stable =0.01-0.02; For sample size; For source tracing weight coefficients, when there are high-frequency root cause anomalies =1.5, when the fixed conduction path is abnormal =1.2, during occasional anomalies =0.8.

[0011] As a preferred embodiment of the above technical solution, it also includes a data storage module and a flexible production parameter database; the data storage module stores data on the entire process of detection, traceability, processing and optimization; the flexible production parameter database stores assembly standard parameters, process correlation and abnormal conduction attenuation coefficient data of different types of impact rammers, providing support for each module.

[0012] A multi-station online detection method for impact tamping, based on the above-mentioned system implementation, includes: Step 1: Basic detection and data synchronization at each workstation. Sensors at each workstation collect parameter data, which is then preprocessed and bound to the workstation number, timestamp, and unique workpiece identifier code before transmission and storage. Step 2: The dynamic interference compensation module calls the synchronous detection data of the adjacent workstations in the previous step, and corrects the original force and vibration data of the current workstation through the correction formula; Step 3: The multi-dimensional re-inspection unit for key processes receives valid data, calculates the comprehensive quality assessment value Q through a multi-physics field coupled detection model, and determines whether to trigger the traceability process; Step 4: The multi-workstation traceability linkage core module calculates the root cause attribution coefficient through the quantitative traceability model, locates the root cause workstation by combining the judgment rules, and the anomaly propagation path analysis module traces the propagation process and generates a path diagram. Step 5: Execute the coordinated processing strategy according to the source tracing results and Q-values; Step 6: The adaptive threshold optimization module iteratively updates the detection threshold based on the source data; Step 7: The data storage module stores all relevant data throughout the process and supports multi-dimensional query and traceability.

[0013] As a preferred embodiment of the above technical solution, the hierarchical processing strategy in step 5 is as follows: Level 1 anomalies (0.8≤ < Send compensation instructions and deviation warnings; Level 2 anomalies ( ≤ <1.2) Suspend the corresponding workstation and formulate a rectification plan; Level 3 abnormality ( ≥1.2) Lock the workpiece and strengthen the detection of key nodes.

[0014] The beneficial effects of this invention are as follows: 1. Accurate and efficient source tracing significantly improves quality control: By calculating the root cause attribution coefficient through a quantitative source tracing model and combining it with anomaly transmission path analysis, the root cause workstation and related affected workstations of quality problems are accurately located, significantly reducing the root cause location error and avoiding misjudgment and omissions in manual source tracing; at the same time, the source tracing time is shortened from the traditional 5-10 minutes to real-time response, reducing production line downtime losses and adapting to flexible production line multi-model mixed production scenarios.

[0015] 2. Form a "detection-tracing-optimization" closed loop to fundamentally reduce the recurrence of quality problems: dynamically update the detection threshold based on the tracing results, strengthen the detection sensitivity of the associated parameters of high-frequency problems, and enable the detection system to have self-learning and dynamic adaptation capabilities, solving the problem of disconnection between tracing and detection in the prior art, and continuously improving the production quality stability.

[0016] 3. Strongly targeted rectification measures reduce production resource waste: through a hierarchical linkage processing strategy, execute differentiated rectification programs according to the abnormality level and tracing results, accurately identify the key nodes of abnormality transmission, provide a clear direction for rectification, reduce invalid rectification actions, and avoid resource waste caused by the flow of unqualified workpieces into subsequent processes. DETAILED DESCRIPTION

[0017] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be described clearly and completely below with reference to the embodiments.

[0018] Multi-station online detection system for impact ram The system includes a single-station basic detection unit, a key process multi-dimensional re-inspection unit, a dynamic interference compensation module, a self-adaptive threshold optimization module, a multi-station tracing linkage core module, an abnormality transmission path analysis module, a data storage module, and a flexible production parameter database. Each module realizes real-time data interaction through an industrial Ethernet: The basic detection unit is arranged at each station of the impact ram assembly and includes a CCD vision sensor and a data preprocessing module, which are used to collect x / y / z axis deviation data (Δx, Δy, Δz) of each station part assembly, and simultaneously collect device operating parameters such as assembly pressure (F 工 ), operating speed (v 工 ), and running vibration (a 工 ). After noise reduction by mean filtering (window size of 5), the "parameter data + station number + time stamp" is bound and transmitted with the workpiece unique identification code to provide basic data support for tracing.

[0019] The key process multi-dimensional re-inspection unit is arranged after the key process of the impact ram assembly, integrates a CCD vision detection module, a force sensor, a vibration sensor, and a data fusion module, and is used to collect multi-dimensional data such as assembly space deviation, impact contact force, and instantaneous vibration acceleration. After fusion processing, comprehensive quality evaluation data are generated to provide a basis for abnormality determination and tracing.

[0020] The dynamic interference compensation module has a built-in interference compensation algorithm, calls synchronous detection data of previous stations, corrects the original data of the current station sensor through a compensation formula, eliminates the influence of cross-station dynamic interference, and ensures the accuracy of the detection data.

[0021] Adaptive threshold optimization module: based on Bayesian iterative algorithm, combined with traceability data dynamic update quality judgment threshold, realize the self-learning and dynamic adaptation of detection system.

[0022] Multi-station traceability linkage core module: as the core of the system, integrating quantitative traceability model, root cause station judgment algorithm and traceability result output unit, receiving multi-dimensional detection data, multi-station correlation parameters, calculating root attribution coefficient and correlation station influence weight through quantitative formula, accurately positioning the root cause station and correlation influence station of quality problem.

[0023] Abnormal conduction path analysis module: based on the time sequence and parameter correlation of multi-station detection data, tracing the conduction process of quality abnormality from root cause station to current station, identifying key nodes, deviation amplification coefficient and coupling interference parameters of abnormal conduction, and generating abnormal conduction path diagram.

[0024] Data storage module: real-time storage of each station detection data, correction data, comprehensive quality evaluation value, threshold iteration record, traceability data, linkage processing log and other information, supporting multi-dimensional query and traceability.

[0025] Flexible production parameter database: storing data such as assembly standard parameters, station spacing parameters, weight coefficient initial values, process correlation degree, and abnormal conduction attenuation coefficient of different models of impact rammer, providing data support for each module.

[0026] Impact rammer multi-station online detection method The method is realized based on the above system, with core reinforcement of traceability related steps, specifically including the following steps: Step 1: single-station basic detection and data synchronization The CCD vision sensor of each station collects x / y / z axis deviation data (Δx, Δy, Δz) of part assembly, the device sensor collects assembly pressure (F 工 ), operation speed (v 工 ), running vibration (a 工 ) and other parameters, and the data preprocessing module transmits the "parameter data + station number + timestamp" to the multi-station traceability linkage core module and data storage module after noise reduction by mean filtering (window size is 5). At the same time, the system automatically records the unique identification code of each workpiece (including model information, online time, and serial number of workstations), realizing one-to-one correspondence between workpiece and multi-station data.

[0027] Step 2: dynamic disturbance compensation The dynamic disturbance compensation module calls the synchronous detection data of the previous adjacent station (previous station force sensor data F 前序 , vibration sensor data a 前序 ), combined with the distance between the current station and the previous station The force and vibration original data of the current station are corrected by the following formula: wherein, is an interference compensation factor, with a value range of 0-0.8; is a distance reference value, fixed at 2 m; , is the original force and vibration acceleration data collected by the current station sensor; , is the corrected effective data.

[0028] Step 3: Multi-dimensional coupling evaluation The multi-dimensional re-inspection unit of the key process receives the effective data after dynamic interference compensation, and calculates the comprehensive quality evaluation value Q through the multi-physical field coupling detection model, as follows: wherein, is an actual assembly space deviation value; is the maximum assembly deviation threshold value allowed by the impact ram of this model, called from the flexible production parameter database; , , is the weight coefficient of each dimension parameter, satisfying + + =1, the initial value is determined by the analytic hierarchy process ( =0.5, =0.3, =0.2), and is dynamically adjusted by an adaptive algorithm subsequently; is the standard assembly contact force reference value of this process, is the standard vibration acceleration reference value of this process, both called from the flexible production parameter database ( obtained by statistical analysis of more than 1000 sets of qualified product data, for the same reason). When ≥ (an adaptive threshold value), the traceability process is triggered; When , only the data is stored, without starting the traceability. Step 4: Multi-station quantitative traceability The multi-station traceability linkage core module receives the ​Process correlation degree ), accurate traceability is realized through the following quantitative model. It includes: 4.1 Root attribution coefficient calculation Formula symbol definition: is the root attribution coefficient, the value range is 0-n (n is the number of previous correlation stations, the default n=3, which can be adjusted according to the length of the production line), The closer the value is to an integer , the higher the confidence that the station is the root station; =0 is the current station, =1-n is the previous 1-n station; is the comprehensive quality evaluation value of the workpiece of the th station (Q =0 is the current abnormal workpiece value, ≥1 is the detection value of the same workpiece corresponding to the previous station), is the adaptive decision threshold of the current process.

[0029] is the station weight coefficient, which is determined by the "distance attenuation factor" and "process correlation degree": is the distance (unit: m) between the th station and the current station, =0.8 is the distance attenuation coefficient (calibrated by 1000 groups of traceability cases); is the process correlation degree between the th station and the current station (such as the =0.95 between the previous core component assembly station and the terminal detection station, and the =0.3-0.6 of auxiliary stations, which is called from the flexible production parameter database). is the time attenuation factor, is the detection time of the current station, is the detection time of the th station, =0.5 is the time attenuation coefficient, which is used to correct the influence of the difference in detection time of different stations on traceability (the closer the detection time, the higher the weight). Root station determination rule: ∈[ -0.2, +0.2] =0,1,...,n): determine the first station as the unique root station; ∈( +0.2, +1-0.2): determine the first station and the first +1 station as the joint root station (the anomaly is caused by the joint influence of the two stations), and allocate the influence weight according to the ratio of . When all corresponding ≤0, it is determined that the current station has a sudden anomaly (such as a transient failure of the device or a batch defect of the part), and the traceability result is marked as "current station independent anomaly".

[0030] 4.2 Abnormal Conduction Path Tracing Trace the conduction process of the deviation from the root station to the current station through the abnormal conduction intensity formula: Formula symbol definition: is the abnormal conduction intensity from the first station to the first +1 station, S≥0.3 is determined as "strong conduction" (the deviation is significantly amplified in this path), 0.1≤S<0.3 is "weak conduction", and S<0.1 is "no conduction"; is the core parameter deviation value (such as assembly space deviation , force parameter deviation ) of the first station, is the corresponding parameter deviation value of the first +1 station; is the conduction attenuation coefficient, is the distance between the first station and the first +1 station, =0.3 is the attenuation coefficient (based on deviation conduction test calibration of different station distances); is the standard deviation threshold of the parameter (called from the flexible production parameter database). Path tracing output: the system automatically generates an abnormal conduction path diagram, labels the root station, key conduction stations (path nodes with S≥0.3), deviation amplification multiple, and parameter deviation contribution of each station, and intuitively presents the complete process of the anomaly from generation to manifestation.

[0031] Step 5: Hierarchical linkage processing The process linkage control module executes targeted processing strategies based on the traceability results (root cause station, joint root cause station, transmission path), replacing the traditional unified processing method: Level 1 anomaly (0.8≤ < If the source is traced back to a slight deviation in a single workstation, calculate the compensation parameters. ( (To maximize the transmission intensity), a compensation command is sent to the next workstation, and a deviation warning is pushed to the source workstation at the same time; Level 2 abnormality ( ≤ <1.2): If it is a single source workstation, suspend operations at that workstation and send out a source tracing report (including the source attribution coefficient). (Abnormal parameters, transmission paths), guide staff to make targeted rectifications; if it is a joint root cause workstation, suspend related workstations, analyze the collaborative impact mechanism, and formulate a comprehensive rectification plan; Level 3 abnormality ( ≥1.2): Lock the non-conforming workpiece and trigger the scrapping process. At the same time, based on the source tracing results, analyze the key nodes of abnormal transmission and strengthen the detection parameters of the workstation at that node (such as increasing the detection frequency and reducing the detection threshold). Step 6: Source tracing result-driven detection optimization The adaptive threshold optimization module incorporates source data into the threshold iteration model, achieving a closed loop of "source tracing-optimization": in, For the first The new detection threshold after the next iteration The threshold for pre-detection. The learning rate is controlled by dynamically adjusting the threshold value: this is useful when production fluctuates greatly (e.g., during line changes or batch replacements of parts). =0.03-0.05; Production is stable (no level 2 or higher abnormalities for 1 consecutive hour) =0.01-0.02, the system automatically adjusts based on production stability. The number of data samples for threshold iteration. Let be the source tracing weight coefficient, if the th If the traceability result for a workpiece is "high-frequency root cause station anomaly" (the traceability frequency for this station is ≥3 times in the past hour), then... 1.5; If it is "abnormal fixed conduction path", then =1.2; if it is an "occasional anomaly", then = 0.8. Through this formula, the detection threshold is tilted towards the parameter direction associated with the high-frequency problem, and the detection sensitivity for root cause workstation abnormalities is enhanced. Step 7: Full-process data storage and traceability The data storage module, as the "data hub" of the system, stores the traceability-related data of the full-process impact ram assembly detection in real time and completely based on an industrial-grade distributed database architecture, builds a full-link data archive of "data collection-traceability analysis-linkage processing-optimization iteration", and completely solves the pain points of "fragmentation of traceability data, inefficient query, and inability to support production optimization in reverse" in the prior art.

[0032] The stored data not only includes core traceability results, but also associates basic data of each preceding link and optimization data of each subsequent link to form a complete data chain: Basic detection raw data: x / y / z axis deviation raw values (Δx, Δy, Δz) collected by CCD vision sensors at each workstation, raw force values of force sensors , raw acceleration of vibration sensors , and denoised data after data preprocessing, corrected data after dynamic interference compensation , , with each piece of data bound to a workstation number, a collection timestamp, and a unique workpiece identification code; Multi-dimensional evaluation data: comprehensive quality evaluation values of key processes , and historical iteration records of adaptive decision thresholds ; Core traceability data: complete calculation process of root cause attribution coefficients , root cause workstation determination results, abnormality transmission intensity S, transmission attenuation coefficient k, deviation amplification factor, and structured data of abnormality transmission path diagram (node workstation, transmission sequence, key transmission node marker); Linkage processing data: hierarchical linkage processing instructions, staff rectification operation logs (rectification time, rectification measures, review results), and unqualified workpiece disposal records (scrap identification, unique identification code, disposal time); Optimization iteration data: assignment basis of traceability weight coefficients (abnormal type, high-frequency abnormality frequency statistics, and transmission path fixedness determination results), and threshold optimization logs.

[0033] The system supports query requirements in different scenarios such as production management, quality analysis, and problem troubleshooting, provides multiple core query dimensions, and the query results can be exported as structured reports (Excel / CSV format).

[0034] The above examples are only used to illustrate the technical solutions of the present application, and not to limit them.

Claims

1. A multi-station online detection system for impact rammers, characterized in that, The system comprises a single-station basic detection unit for real-time data interaction through industrial Ethernet, a multi-station traceability linkage core module, an abnormal conduction path analysis module, and a self-adaptive threshold optimization module. The single-station basic detection unit collects assembly deviations and equipment operation parameters of each station, and transmits the data after preprocessing and binding with the unique identification of the workpiece. The multi-station traceability linkage core module integrates a quantitative traceability model, and accurately locates the root station and associated impact stations of quality problems by calculating the root attribution coefficient. The abnormal conduction path analysis module traces the conduction process from the root station to the current station and identifies the key nodes based on the time series of detection data and the parameter correlation. The self-adaptive threshold optimization module dynamically updates the quality judgment threshold combined with the traceability data, forming a "detection-traceability-optimization" closed loop.

2. The multi-station in-line inspection system for impact rammers according to claim 1, characterized in that, The system further comprises a key process multi-dimensional reinspection unit, which is arranged after the impact ram assembly key process, integrates a CCD vision detection module, a force sensor, a vibration sensor, and a data fusion module, collects multi-dimensional data such as assembly space deviation, impact contact force, and instantaneous vibration acceleration, and generates comprehensive quality evaluation data.

3. The multi-station online detection system for impact rammers according to claim 1, characterized in that, The system further comprises a dynamic interference compensation module, which has an interference compensation algorithm built-in, calls the synchronous detection data of the previous station, and modifies the force and vibration raw data of the current station through the formula: Correct the current station sensor raw data; wherein is the interference compensation factor, the value range is 0-0.8; is the distance reference value, fixed at 2m; , is the original force and vibration acceleration data collected by the current station sensor; , is the corrected effective data.

4. The multi-station in-line inspection system for impact rammers according to claim 1, wherein, The single-station basic detection unit comprises a CCD visual sensor and a data preprocessing module, the CCD visual sensor collects x / y / z axis deviation data (Δx, Δy, Δz), the equipment sensor collects assembly pressure (F 工 ), operation speed (v 工 ), and operation vibration (a 工 ), the data preprocessing module adopts mean filtering denoising with a window size of 5, and the unique identification code of the workpiece contains model, online time, and serial information of the transfer station.

5. The multi-station in-line inspection system for impact rammers according to claim 1, wherein, In the quantitative traceability model of the multi-station traceability linkage core module, the calculation formula of the root attribution coefficient R is: wherein: is a work station weight coefficient, is a distance attenuation coefficient, is a work station spacing, is a process correlation degree; is a time decay factor, is a time decay factor, , are the current and the jth station detection time, respectively; are the current and the jth station detection time, respectively; is the jth station comprehensive quality evaluation value, is an adaptive decision threshold, and n is the number of previous associated stations by default 3.

6. The multi-station in-line inspection system for impact rammers according to claim 1, wherein, The abnormal conduction path analysis module traces the conduction process from the root station to the current station and identifies the key nodes based on the time series of detection data and the parameter correlation. Trace back abnormal conduction; wherein For conduction intensity, 、 For station core parameter deviation value, for the conduction attenuation coefficient, = 0.3 is the attenuation coefficient, is the station spacing, is the parameter standard deviation threshold; S≥0.3 is strong conduction, 0.1≤S<0.3 is weak conduction, and S<0.1 is no conduction.

7. The multi-station in-line inspection system for impact rammers according to claim 1, wherein, The threshold iteration formula of the self-adaptive threshold optimization module is: wherein = 0.03 - 0.05 for high production fluctuations = 0.01 - 0.02 for stable production = 0.01 - 0.02 for stable production = sample size = 1.5 for high-frequency root cause anomalies = 1.2 for fixed conduction path anomalies = 1.2 for fixed conduction path anomalies = 0.8 for sporadic anomalies 8. The multi-station inline detection system for impact rammers according to claim 1, characterized in that, The system further comprises a data storage module and a flexible production parameter database. The data storage module stores the detection, traceability, processing, and optimization data of the whole process; The flexible production parameter database stores the assembly standard parameters, process correlation, and abnormal conduction attenuation coefficient data of different types of impact rams, and provides support for each module.

9. A method for multi-station online detection of a rammer, characterized in that, The system is implemented based on any one of claims 1-8, comprising: Step 1: Single-station basic detection and data synchronization. Each station sensor collects parameter data, which is transmitted and stored after preprocessing and binding with the station number, timestamp, and workpiece unique identification code; Step 2: The dynamic interference compensation module calls the synchronous detection data of the previous adjacent station, and modifies the force and vibration raw data of the current station through the correction formula; Step 3: The key process multi-dimensional reinspection unit receives valid data, calculates the comprehensive quality evaluation value Q through the multi-physical field coupling detection model, and judges whether to trigger the traceability process; Step 4: The multi-station traceability linkage core module calculates the root attribution coefficient through the quantitative traceability model, locates the root station combined with the judgment rule, and the abnormal conduction path analysis module traces the conduction process and generates a path diagram; Step 5: According to the traceability results and Q value, execute the linkage processing strategy; Step 6: The self-adaptive threshold optimization module iteratively updates the detection threshold based on the traceability data; Step 7: The data storage module stores the whole-process related data, supporting multi-dimensional query and traceability.

10. The multi-station in-line inspection method of claim 9, wherein, The hierarchical processing strategy in step 5 is as follows: Level 1 anomalies (0.8≤ < Send compensation instructions and deviation warnings; Level 2 anomalies ( ≤ <1.2) Suspend the corresponding workstation and formulate a rectification plan; Level 3 abnormality ( ≥1.2) Lock the workpiece and strengthen the detection of key nodes.

Images