Shaving board production abnormal event intelligent detection and diagnosis system

Abstract

The invention relates to the technical field of shaving board production, in particular to a shaving board production abnormal event intelligent detection and diagnosis system which comprises a parameter time sequence acquisition module, an abnormal point recognition module, a collaborative feature judgment module, a synchronous trend analysis module and an abnormal attribution positioning module. According to the method, continuous trend analysis and node sequence integration are carried out on various process parameters in the production process, a dynamic linkage system of batch information and parameter fluctuation is established, synchronous identification of abnormal parameters and nodes is realized, and parameter collaborative mutation and trend synchronous offset between process links are taken as a core basis for abnormality diagnosis; according to the method, the comprehensive precision of batch affiliation, exception types and node positioning is improved, the exception event tracking capability under the multi-node and multi-parameter condition is enhanced, the integration and exception traceability of parameter data in the whole production process are optimized, the quality risk caused by parameter fluctuation and process exception is reduced, and the risk management and control capability in the whole production process is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of particleboard production, and particularly to an intelligent detection and diagnosis system for abnormal events in particleboard production. Background Technique

[0002] The particleboard production field mainly involves a series of technological processes such as wood raw material pretreatment, particle preparation, particle drying, sizing, mat forming, hot pressing and curing, cooling and humidity adjustment, surface treatment, and finished product grading. This field focuses on core matters such as raw material selection, process parameter control, product quality inspection, and production process management, covering all stages of the production process, and has relatively high requirements for the automation and intelligence of the process. Among them, the traditional intelligent detection and diagnosis system for abnormal events in particleboard production refers to identifying and judging problems such as abnormal equipment operation, process parameter fluctuations, raw material ratio deviations, and board defects during the production process. Usually, methods such as on-site manual inspections, manual recording and analysis of production data, fixed threshold alarms, static monitoring of process parameters, and regular sampling inspections of samples are used to identify and judge, and the abnormal types and their causes are initially determined through manual experience and statistical analysis.

[0003] The existing technology relies on manual data collection, static monitoring of parameters, and empirical judgment in the particleboard production link. It is difficult to map process parameter fluctuations and batch changes in real time, and it is impossible to automatically perceive multi-node collaborative abnormalities. The on-site alarm method is limited by a single threshold setting, and the production batch traceability is not comprehensive. In some process links, it is difficult to respond in a timely manner to parameter abnormalities or equipment abnormalities, resulting in missed detections and misjudgments of abnormal events, fuzzy batch positioning, and affecting production stability and subsequent quality assurance. Summary of the Invention

[0004] The purpose of the present invention is to solve the deficiencies existing in the prior art and propose an intelligent detection and diagnosis system for abnormal events in particleboard production.

[0005] To achieve the above purpose, the present invention adopts the following technical solution: An intelligent detection and diagnosis system for abnormal events in particleboard production, the system includes: The parameter time series acquisition module analyzes the change trend based on the particle moisture content sampling channel, compares the relationship between the sizing dosage and the batch number, calculates the correspondence between the hot pressing temperature and the forming speed, judges the matching state of the process nodes, and integrates the acquisition time sequence of each parameter to obtain a parameter time series set; The abnormal point identification module analyzes the particle moisture content fluctuation based on the parameter time series set, judges the correspondence between the mat density and the batch number, compares the change range of the hot pressing temperature and the forming speed, and identifies the abnormal fluctuation of the batch parameters to obtain the abnormal parameter distribution characteristics; The collaborative feature determination module compares the change directions of the paving density and the main shaft rotation speed according to the abnormal parameter distribution characteristics, analyzes the parameter combination of the shaving paving equipment and the hot pressing system inlet, determines the collaborative state of the process parameters, and obtains the process collaborative mutation index; The synchronous trend analysis module analyzes the change trend of the sizing amount based on the process collaborative mutation index, calculates the trend difference between the paving pressure and the main shaft rotation speed, compares the fluctuation synchronism of the process parameters, determines the node trend consistency, and obtains the trend deviation feature quantity.

[0006] The improvement of the present invention is that the parameter time series set includes parameter type identification, time node marking, and sequence integrity information, the abnormal parameter distribution characteristics include abnormal type identification, abnormal occurrence node, and abnormal duration interval, the process collaborative mutation index includes collaborative abnormal identification, parameter linkage mode, and associated node characteristics, and the trend deviation feature quantity includes trend consistency index, deviation degree classification, and trend change identification.

[0007] The improvement of the present invention is that the parameter time series acquisition module includes: The moisture content analysis sub-module analyzes the change of the shaving moisture content in a continuous time period based on the shaving moisture content sampling channel, classifies the change direction of the collected signals at adjacent time nodes, compares the increase or decrease in different time periods, determines the continuity and consistency of the moisture content change, screens the fluctuation performance, and obtains the moisture content trend characteristics; The sizing attribution recognition sub-module compares the time distribution of the sizing amount acquisition data and the corresponding batch number based on the moisture content trend characteristics, determines whether there is overlap or deviation in the attribution between each group of sizing amount information and the batch number, analyzes the matching situation between the batch and the sizing data, identifies the abnormal attribution relationship, and obtains the sizing attribution characteristics; The parameter linkage integration sub-module compares the changes of the hot pressing temperature and the forming speed at the same time node according to the sizing attribution characteristics, determines the consistency of the change directions of each parameter, screens the linkage performance, and integrates the parameters and the time nodes to obtain the parameter time series set.

[0008] The improvement of the present invention is that the abnormal point recognition module includes: The moisture content fluctuation recognition sub-module analyzes the change trend of the shaving moisture content data in the target time period based on the parameter time series set, determines the change direction and amplitude between consecutive time series data, identifies the segments with continuously increasing or decreasing change amplitudes, and locates the time sections with concentrated changes in the data sequence to obtain the moisture content mutation interval segment; The parameter attribution relationship judgment sub-module compares the corresponding relationship between the synchronous data of the sizing amount and the paving density and the batch number based on the moisture content mutation interval segment, and determines whether the paving density sampling sequence is consistent with the batch of the mutation section to obtain the parameter batch matching state distribution; The batch fluctuation difference identification sub-module compares the hot pressing temperature and forming speed of the corresponding batches according to the parameter batch matching state distribution, calculates the changes in the paving density and the main shaft speed, calculates the fluctuation levels of the parameters of each batch, and judges the fluctuation performance between batches to obtain the abnormal parameter distribution characteristics.

[0009] The improvement of the present invention is that the collaborative feature determination module includes: The direction matching sub-module compares the change direction of the paving density with the change direction of the main shaft speed feedback signal according to the abnormal parameter distribution characteristics, judges whether the trends of the two are consistent within the same batch, optimizes the judgment criteria for trend deviation, and obtains the trend direction matching coefficient; The combination relationship sub-module calls the trend direction matching coefficient, compares the synchronous change characteristics of the paving speed, roll gap, initial hot pressing temperature and plate feeding pressure, identifies the key parameter combinations of the synchronous change characteristics, optimizes the interaction relationship between the parameters, and obtains the change range of the parameter combination; The collaborative state sub-module calculates the collaborative change level of the paving density change amount and the main shaft speed offset amount based on the change range of the parameter combination, compares the trend fluctuations and linkage frequencies between nodes, and obtains the process collaborative mutation index.

[0010] The improvement of the present invention is that the synchronous trend analysis module includes: The trend calculation sub-module analyzes the time series data of the sizing amount based on the process collaborative mutation index, judges the change direction of the sizing amount under each batch number, compares the change rates in the time periods before and after the mutation nodes, and calculates the trend slope interval of the sizing amount of each batch over time; The pressure and speed comparison sub-module calculates the change ranges of the paving pressure and the main shaft speed in the same time period according to the trend slope interval, compares the synchronism of the pressure and speed trends, and obtains the trend difference range; The trend consistency determination sub-module calls the trend difference range, analyzes the number of intersections and synchronous intervals of the trends of each parameter on the time axis according to the distribution direction difference at the different process nodes, identifies the consistent sections of the trend fluctuations between the parameters, and obtains the trend deviation characteristic quantity.

[0011] The improvement of the present invention is that the system further includes: The abnormal attribution positioning module judges the abnormal attribution of the sudden change nodes of the chip moisture content, the changes in the paving density and the main shaft speed based on the trend deviation characteristic quantity, identifies the batch number of the abnormal nodes and the event information, integrates the abnormal correlation information of the process parameters, and obtains the batch abnormal characteristic positioning information; The batch abnormal characteristic positioning information includes batch positioning identification, abnormal event type, and node attribution identification.

[0012] The improvement of the present invention is that the abnormal attribution positioning module includes: The abnormal fluctuation attribution sub-module analyzes the fluctuation relationship between the sudden change node of the moisture content of the wood chips and the change of the paving density based on the trend offset feature quantity, compares the linkage situation between the spindle speed and other process parameters, identifies and classifies the nodes with abnormal fluctuations; and obtains the abnormal fluctuation index. The batch positioning and integration sub-module analyzes and integrates the event information and process parameters of each batch based on the abnormal fluctuation index, judges the batch association when the abnormal fluctuation occurs, locates the abnormal batch and process nodes, and obtains the batch abnormal feature positioning data.

[0013] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In the present invention, by performing continuous trend analysis and node sequence integration on various process parameters in the production process, a dynamic linkage system of batch information and parameter fluctuations is established to realize the synchronous identification of abnormal parameters and nodes. The parameter co-mutation and trend synchronous offset between process links are used as the core basis for abnormal diagnosis, improving the comprehensive accuracy of batch attribution, abnormal type and node positioning, enhancing the abnormal event tracking ability under multi-node and multi-parameter conditions, and optimizing the integration and abnormal traceability of parameter data in the entire production process, reducing the quality risk caused by parameter fluctuations and process abnormalities, and optimizing the risk control ability in the entire production process. Description of the Drawings

[0014] Figure 1 is the system flow chart of the present invention; Figure 2 is the flow chart of the parameter time series acquisition module in the present invention; Figure 3 is the flow chart of the abnormal point identification module in the present invention; Figure 4 is the flow chart of the collaborative feature determination module in the present invention; Figure 5 is the flow chart of the synchronous trend analysis module in the present invention; Figure 6 is the flow chart of the abnormal attribution positioning module in the present invention. Detailed Embodiment

[0015] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and 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.

[0016] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by terms such as "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined. Embodiment

[0017] Please refer to Figure 1 , the present invention provides a technical solution: an intelligent detection and diagnosis system for abnormal events in particleboard production includes: The parameter time series acquisition module analyzes the change trend of the particle moisture content acquisition signal based on the particle moisture content sampling channel, compares the attribution between the sizing amount input channel data and the batch number, calculates the corresponding relationship between the hot pressing temperature change and the forming speed feedback signal, judges the matching state of the process node information, and integrates the parameter acquisition time sequence to obtain a parameter time series set; The abnormal point identification module analyzes the fluctuation performance of the particle moisture content within the target time period based on the parameter time series set, judges the corresponding relationship between the mat density sampling sequence and the batch number, compares the change amplitudes of the hot pressing temperature and the forming speed, and identifies the abnormal fluctuations between batch parameters to obtain the abnormal parameter distribution characteristics; The collaborative feature determination module compares the change directions of the mat density data and the main shaft speed feedback according to the abnormal parameter distribution characteristics, analyzes the combined characteristics of the particle matting equipment parameters and the parameters in the inlet area of the hot pressing system, judges the collaborative state between each group of process parameters, optimizes the relevance of the node parameter combination, and obtains the process collaborative mutation index; The synchronous trend analysis module analyzes the change trend of the sizing amount based on the process collaborative mutation index, calculates the trend difference between the matting pressure detection channel and the main shaft speed control unit, compares the synchronous states of the fluctuations of each process parameter, judges the consistency between the node trends, and obtains the trend offset characteristic quantity; The abnormal attribution positioning module analyzes the distribution information of the batch abnormal data based on the trend offset characteristic quantity, judges the abnormal attribution of the particle moisture content mutation node, the change direction of the mat density, and the strong and weak combination of the main shaft speed, identifies the batch and event information of the abnormal node, and integrates the abnormal correlation information of the process parameters to obtain the batch abnormal characteristic positioning information.

[0018] The parameter time series set includes parameter type identification, time node markers, and sequence integrity information. The abnormal parameter distribution characteristics include abnormal type identification, abnormal occurrence nodes, and abnormal duration intervals. The process collaborative mutation index includes collaborative anomaly identification, parameter linkage mode, and associated node characteristics. The trend deviation feature quantity includes trend consistency index, deviation degree classification, and trend change identification. The batch abnormal feature location information includes batch location identification, abnormal event type, and node attribution identification.

[0019] In Module 1, the chip moisture content sampling channel refers to a dedicated acquisition line or device installed on the particleboard production line for real-time detection and recording of the moisture content of chip raw materials. The sizing dosage input channel refers to sensors, data interfaces, or system paths for monitoring and recording the sizing agent addition amount, capable of collecting the sizing dosage used for each batch of materials. The batch number is the unique code assigned to each batch of raw materials or finished products entering the production process, used for production process tracking, parameter binding, and traceability. The attribution status refers to the state where parameter data such as sizing dosage and moisture content are archived in the data management system in one-to-one correspondence with the corresponding batch numbers, ensuring that each data point clearly belongs to a certain batch. The correspondence relationship is used to describe the mapping or association between two parameters, such as the mutual influence and associated trend over time between the change in hot pressing temperature and the feedback of forming speed. The process node information refers to the relevant parameter, status, and identification information of the key processes or process stages (such as sizing, mat forming, hot pressing, etc.) on the particleboard production line, used to clarify the location and link where the data occurs.

[0020] In Module 2, the fluctuation performance refers to the continuous change of the chip moisture content over a specific period during the production process, including its dynamic trends such as growth, decrease, or mutation. The mat forming density refers to the mass density per unit volume or unit area when the chip raw materials are laid on the board blank during production, which is an important process parameter affecting the performance of the board. The corresponding status refers to the attribution and distribution status of the mat forming density acquisition sequence under the mapping of batch numbers, ensuring that density data and production batch data can be matched and traced with each other. The change amplitude is used to describe the magnitude of the change in a parameter within a specific period or batch, such as the fluctuation range of hot pressing temperature or forming speed. Abnormal fluctuations refer to the situation where certain parameters (such as moisture content, hot pressing temperature) show abnormal and drastic changes within a short period, exceeding the normal production fluctuation range.

[0021] In Module 3, the paving density data is the time-series data actually collected, reflecting the density change during the paving process for each batch; the spindle speed refers to the actual speed of the rotating shaft related to the main power output of the equipment, which is an important parameter for measuring the operating state of the forming equipment; the combined feature groups the change trends of multiple parameters such as paving density, spindle speed, and hot pressing inlet temperature at the same node or within the same time segment for comprehensive analysis of the process state; the collaborative state indicates whether multiple parameters (such as paving density and spindle speed) show similar trends, synchronous changes, mutual responses, or abnormal linkages during the production of the same batch.

[0022] In Module 4, the change trend refers to the change direction of a certain process parameter (such as the sizing dosage) over production time, which can be rising, falling, stable, or sudden; the paving pressure detection channel specifically refers to the dedicated sensor or signal acquisition line for real-time monitoring of the pressure change during the paving process of the particleboard raw materials; the spindle speed control unit is the equipment for adjusting and providing real-time feedback on the spindle speed to ensure that the equipment speed is stable within the process requirements; the consistency between node trends is to compare whether the change trends of various parameters at different process nodes (such as paving and hot pressing) for the same batch are synchronous, convergent, or different.

[0023] In Module 5, the abnormal attribution locates the abnormal fluctuations of parameters during the production process and determines which process node and batch the abnormality belongs to when it occurs; the abnormal node refers to the production process link or process point that is determined to have undergone abnormal changes during the parameter trend analysis or abnormal event tracing.

[0024] Please refer to Figure 2 , the parameter time-series acquisition module includes: The moisture content analysis sub-module analyzes the change of the moisture content of the particles in a continuous time period based on the particle moisture content sampling channel. By classifying the change directions of the signals collected at adjacent time nodes, comparing the increase or decrease in different time segments, judging the continuity and consistency of the moisture content change, and screening out the fluctuation performance, the moisture content trend characteristics are obtained; Extract real-time data from the on-line moisture detection equipment installed on the particleboard conveyor line. During the execution process, first number the continuously collected data point by point in chronological order and divide it into several time periods, each time period covering a fixed duration (such as 60 seconds). Classify the numerical change trends between adjacent collection points in each period into directions. When the moisture content value at a certain time point is less than the next point, it is marked as the rising direction; if it is greater, it is marked as the falling direction; if the absolute value of the difference between the two is less than or equal to 0.2%, it is marked as stable. Then, identify the direction change sequences in multiple time periods in turn, combine them into fluctuation segments, and mark the start and end times, change directions, and change amplitudes of each fluctuation segment. Judge whether the maximum change in the fluctuation segment exceeds 1.5%. This threshold is set based on the normal floating range of the moisture content of the particle raw material from 10% to 13%. If it exceeds, it is classified as an abnormal segment, and perform a difference operation on the time intervals between the fluctuation segments. If the interval time between any two segments does not exceed 3 minutes, it is marked as continuous fluctuation. Further compare whether the directions of the continuous fluctuation segments are consistent. If the directions are all rising or all falling, it is considered to have consistency. Then, extract the starting value and ending value in the fluctuation segment to calculate the change rate and obtain the trend slope. When the slope is higher than a 0.05% increase per minute, it is judged to have an obvious trend. Screen out the significant, continuous, and direction-consistent fluctuation segments within the batch according to the above process, organize the segments into moisture content trend characteristic information, and record its start and end times, trend direction, change amplitude, and the batch code to which it belongs.

[0025] Based on the moisture content trend characteristics, the sizing attribution recognition sub-module compares the time distribution of the sizing amount collection data with the corresponding batch number, judges whether there is overlap or deviation in the attribution between each group of sizing amount information and the batch number, analyzes the matching situation between the batch and the sizing data, identifies the abnormal attribution relationship, and obtains the sizing attribution characteristics; Extract the sizing dosage data whose time range overlaps, compare the timestamp of each sizing record with the moisture content trend time period, calculate the time difference between the sizing data recording time point and the midpoint of the trend segment. If the absolute value of this time difference is less than or equal to 2 minutes, it is considered to belong to the batch corresponding to this trend segment. Records with a time difference exceeding 2 minutes are marked as records with attribution deviation. This 2-minute threshold is set according to the actual response lag duration of the sizing equipment. Through historical data statistics, more than 90% of the normal data is concentrated within 1 minute. Then, calculate the average value for the sizing dosage records in each batch and compare the difference with the previous batch. When the change range of the average sizing dosage between batches exceeds 3%, it is determined that there is a mutation in the sizing dosage of this batch. This 3% determination criterion is set according to the production ratio regulations. For example, in a certain batch record, the sizing dosage is 68 kg, and the previous batch is 70.5 kg, with a difference of 2.5 kg, and the corresponding ratio is approximately 3.5%, exceeding the threshold, so it is marked as attribution abnormal. Then, combining the two conditions of time attribution and dosage mutation between batches, mark all records that simultaneously meet the conditions of attribution deviation or excessive mutation amplitude as sizing attribution abnormal data.

[0026] The parameter linkage integration sub-module compares the changes in the hot pressing temperature and the forming speed at the same time node according to the sizing attribution characteristics, judges the consistency of the change directions of each parameter, screens the linkage performance, and integrates the parameters and time nodes to obtain a parameter time series set; Extract the corresponding hot pressing temperature and forming speed data in sequence, align the two types of parameters on the time axis, and construct parameter pairs at the same time point. For each group of data, first judge whether the temperature change direction and the speed change direction of the two adjacent points are the same. If the directions are the same, it is classified as co-directional linkage. Then, count the proportion of the number of records with consistent linkage in the total number of records in the whole group of data. When this proportion is not less than 0.75, mark this batch as a high-consistency batch. This judgment is set based on the empirical rule that the temperature and speed usually change positively under normal production conditions. Then, organize all the time nodes with high-consistency characteristics into event records, and centrally integrate the corresponding parameter names, values, and timestamps into sequence entries. Merge each parameter into the unified parameter time series set in chronological order. If there are records where the temperature and speed change simultaneously and show a co-directional relationship at a certain time point, they are included in the linkage event sequence to form a trend data set of the hot pressing temperature and the forming speed at the same time point for subsequent multi-parameter collaborative determination.

[0027] Please refer to Figure 3 , the abnormal point identification module includes: Based on the parameter time series set, the moisture content fluctuation identification sub-module analyzes the change trend of the moisture content data of the wood chips in the target time period, judges the change direction and amplitude between consecutive time series data, identifies the segments with continuously increasing or decreasing change amplitudes, and locates the time intervals with concentrated changes in the data sequence to obtain the moisture content mutation interval segments; Sequentially process the time series moisture content data formed during the production process of each batch of wood chip raw materials. Read the moisture content values at each time node in the sequence in turn, perform a difference operation on the values between two adjacent time nodes, and record the positive or negative sign of the difference. If the result of subtracting the value of the previous node from the current node value is greater than 0, it is marked as the upward direction; if it is less than 0, it is the downward direction; if the absolute value is less than 0.2%, it is regarded as a stable segment. Then combine the point segments with consistent direction markings into a trend segment. Each trend segment records its start time, end time, direction type, and maximum change amplitude. During this process, sum up the change amplitudes of each segment. If the amplitude continuously exceeds 1.5% and the duration is greater than 3 minutes, it is marked as a significant trend segment. The amplitude threshold of 1.5% is obtained by taking the average offset value after statistical calculation based on the normal moisture content fluctuation range of the wood chips from 10% to 13% and adding a safety margin. Further, search for continuously increasing or decreasing segments among all the trend segments. If the maximum difference between them exceeds 2%, it is recorded as a strong trend segment. For example, the original moisture content data of a certain batch is 12.4%, 12.9%, 13.5%, 13.8%, 13.9%, 14.3%, 14.5%. In this sequence, it continuously increases from the first value to the last value, the difference is 2.1%, and the duration is 5 minutes, meeting the mutation judgment conditions. Then scan all the sequences for segments that meet the above conditions, record the start and end time nodes in the parameter time series set, and combine their batch numbers and time tags to locate the time intervals with mutations in the continuous trend segments of the moisture content within this batch, constituting the moisture content mutation interval segments.

[0028] Based on the moisture content mutation interval segments, the parameter attribution relationship judgment sub-module compares the corresponding relationship between the synchronous data of the sizing amount and the mat density and the batch number, and judges whether the mat density sampling sequence is consistent with the batch of the mutation segment to obtain the parameter batch matching status distribution; Extract the sizing consumption acquisition data and paving density acquisition data within this time period, record their timestamps, data values, and batch numbers respectively. For each sizing record and paving density record, check whether its timestamp is within the mutation interval time range. If it exists, extract its corresponding batch number and compare it with the batch number of the mutation interval. If the batch number of the sizing or density data is the same as that of the mutation interval, it is considered that the parameter belongs to the same mutation section. If the batch numbers are different but the time coverage overlaps, it is marked as a conflict in attribution. Then, count the attribution of the sizing data and paving density data within each mutation section, record the number of consistencies and conflicts respectively, calculate the consistency ratio of attribution and classify and output it. For paragraphs with an attribution ratio less than 0.8, the matching status is considered unstable. The determination basis of the attribution ratio is adjusted and set according to the statistical value of the historical data attribution matching rate in the production system being above 90%. Specifically, if the mutation section time is from 10:00 to 10:10 and the corresponding batch number is B103, and the sizing data times within this time period are 10:01 and 10:04 respectively, with corresponding batch numbers B103 and B102, then the first sizing record has consistent attribution, and the second record has a different batch number and is marked as a conflict in attribution. Integrate the batch attribution comparison results of all sizing data and paving density data within each mutation section to generate the batch matching status distribution information of each parameter.

[0029] The batch fluctuation difference identification sub-module compares the hot pressing temperature and forming speed of the corresponding batches according to the batch matching status distribution of the parameters, calculates the variation of the paving density and the main shaft speed, and uses the formula: ; Calculate the fluctuation level of each batch parameter , and judge the fluctuation performance between batches to obtain the abnormal parameter distribution characteristics. Among them, represents the hot pressing temperature data at the th moment, reflecting the temperature state of the hot pressing link in the production process, represents the forming speed data at the th moment, reflecting the equipment operation speed of the forming process link, represents the paving density data at the th moment, reflecting the density of the raw materials in the paving link of the production line, represents the main shaft speed data at the th moment, reflecting the real-time operation state of the equipment's main power output component, represents the change range of the moisture content within the th time period, reflecting the change of the moisture content of the raw materials in the production process, represents the total number of time periods participating in the calculation, that is, the length of the data time series, Denotes the minimum stability factor set to prevent the denominator from being zero.

[0030] The fluctuation level of each batch parameter refers to the variation range or fluctuation degree among the various process parameters (such as hot pressing temperature, forming speed, mat density, main shaft speed, etc.) collected in different batches during the production process. The fluctuation reflects the instability or abnormal fluctuation in the production process and helps detect potential abnormal situations.

[0031] Map the assigned batch number information to each process parameter one by one. Select the data sequence length within the production time period of batch B01 to be 5 sample points, and sequentially obtain the actual measured values of each parameter at each time point. Set the hot pressing temperature sequence within this batch as: ; The forming speed is: ; The mat density is: ; The main shaft speed is: ; The moisture content change is: ; Perform normalization processing on each parameter to unify the scale for calculation. Adopt the Min - Max normalization method and set the upper and lower limit ranges of each parameter. Among them, the normalization interval of the hot pressing temperature is , the forming speed is , the mat density is , the main shaft speed is , the moisture content change is , and the normalization processing results are as follows: ; ; ; ; ; Substitute the above normalization results into the calculation formula. Among them, , the stability factor takes the value , calculate the numerator part: The first term: ; The second term: ; The third term: ; The fourth term: ; The fifth term: ; The sum of the numerator is: ; The denominator part is: ; The calculation result is: ; This result indicates that in the normalized dimension, the multi-parameter collaborative fluctuation value of batch B01 is , significantly lower than the benchmark fluctuation determination threshold , representing that there is no mutation trend between the key process parameters of this batch. The change between the hot pressing temperature and the forming speed is basically stable. The difference fluctuation between the paving density and the main shaft speed is also extremely small. Moreover, the change range of the raw material moisture is within the conventional deviation range. This numerical result can be directly used as the input characteristic quantity of batch stability in the subsequent analysis of the collaborative state of the process for further processing.

[0032] Please refer to Figure 4 , the collaborative feature determination module includes: According to the abnormal parameter distribution characteristics, the direction matching sub-module compares the change direction of the paving density with the change direction of the feedback signal of the main shaft speed, judges whether the trends of the two are consistent within the same batch, optimizes the judgment criteria for trend deviation, and obtains the trend direction matching coefficient; Extract the time periods and batch numbers marked as abnormal parameters in each batch, and obtain the time series data of the paving density and the main shaft speed within the corresponding batch from the parameter time series set. During the execution process, traverse the batch numbers in sequence, and judge the trend direction of the two types of parameters within the same time period in the time-aligned manner. Calculate the numerical difference between every two adjacent time points of the paving density. If the subtraction of the latter point from the former point is greater than zero, this segment is marked as an upward trend. If it is less than zero, it is marked as a downward trend. If the absolute difference does not exceed 0.1 kg / m³, it is judged as a stable trend. The trend judgment of the main shaft speed data also adopts the same standard. Then, pair and judge the two sets of trend marks within each time period. If the trend directions are the same, it is recorded as consistent trends. If they are opposite, it is marked as inconsistent. The stable state is excluded as a neutral segment not included in the judgment. Then, calculate the ratio of the number of time periods with consistent trends to the total number of judgment time periods within the entire batch as the trend direction consistency ratio. This ratio value is the trend direction matching coefficient. The range of this coefficient is set between 0 and 1. When the value is greater than or equal to 0.75, it is judged that the trend matching is good. This threshold is the standard value set based on the average value of the direction consistency ratio in the statistics of historical stable batches. For example, if a batch has 20 judgment time periods and 15 of them are judged to have consistent trends, the matching coefficient is 0.75, and this batch is marked as having good trend direction matching. If the matching coefficient is less than 0.5, it is considered that there is an obvious deviation trend, and this batch will be recorded as matching abnormal. The matching coefficients and matching judgment results of each batch form the trend direction matching coefficient data set.

[0033] The combined relationship sub-module calls the trend matching coefficient, compares the synchronous change characteristics of the paving speed, roll gap, initial hot pressing temperature, and board feeding pressure, identifies the key parameter combinations of the synchronous change characteristics, optimizes the interaction relationship between the parameters, and obtains the change range of the parameter combinations. Process the parameter calls for each batch number with good matching one by one, extract the time series data related to the four types of parameters of paving speed, roll gap, initial hot pressing temperature, and board feeding pressure in the corresponding batch, pair these four groups of parameters one by one in chronological order, analyze the numerical change trends of each parameter at the same time node, judge the positive and negative signs of the difference between every two adjacent time nodes, and identify the local trend direction of the parameter accordingly. In each time period, if the trend direction marks of the four parameters are exactly the same, it is marked as a trend synchronous segment; if three parameters are the same and the remaining one is stable or in a different direction, it is recorded as a partially synchronous segment; if the four parameters are in different directions, it is recorded as a trend separation segment. Count each type of segment and record its time range, and then calculate the average change range of the four types of parameters in the trend synchronous segment respectively. This range is the average value of the absolute differences between adjacent time points. For example, in a certain batch, the initial hot pressing temperature rises from 170 °C to 176 °C, with a change of 6 °C. If this change spans 3 time periods, the average change range is 2 °C. Continue to summarize the parameter change ranges of all time periods, calculate the difference value between each parameter and the average change value of its three parameters in the synchronous segment. When the difference value is less than the set deviation threshold, the parameter is determined to be a key synchronous parameter. The deviation threshold is set to twice the historical fluctuation standard deviation of each parameter. In particleboard production, the standard deviation of the paving speed is usually 0.15 meters per minute, so the synchronous recognition deviation threshold is 0.3 meters per minute. When the paving speed of a certain batch has an average change of 0.8 meters per minute in the synchronous segment and is consistent with the changes of the other three parameters, with a difference of 0.1 meters per minute, the paving speed is marked as a key synchronous parameter. Identify the combinations of key synchronous change parameters in batches with good trend matching, and output the overall change range of each type of combination in the synchronous segment as the result of the parameter combination change range.

[0034] Based on the change range of the parameter combination, the coordination state sub-module calculates the coordination change level between the paving density change and the spindle speed offset, compares the trend fluctuations and linkage frequencies between nodes, and uses the formula: ; Obtain the process coordination mutation index , where represents the number of linkage nodes within the range of the combined change amplitude, represents the paving density change in the th node, represents the spindle speed offset in the th node, represents the The linkage structure parameters corresponding to the variation range of parameter combinations within a node represent the main shaft control feedback delay within the th node, and represent the difference between the paving feedback signal and the main shaft change within the

[0035] The process synergy mutation index is a key index used to evaluate the synergy changes among multiple process parameters during the production process of particleboard. By comprehensively analyzing the changes of multiple parameters (such as paving density, main shaft speed, hot pressing temperature, etc.) during the production process, it is judged whether there are synchronous fluctuations, consistent trends, or abnormal linkages among the parameters. It measures whether the changes of parameters are coordinated among different process nodes (such as paving, hot pressing, etc.), and whether there are abnormal mutations or abnormal fluctuations

[0036] First, extract the change in paving density in the th linkage node. During the production process with batch number 20240518, at , , the paving density values , , are respectively collected. The density change amounts for the two time periods are , . To eliminate the dimensional influence brought by different parameter units, the data is normalized using the maximum-minimum normalization method. Taking the historical density range , , the calculation gives: ; ; Then, extract the offset of the main shaft speed . At the same time points, the main shaft speeds are , , , and the change amounts , are obtained. The speed reference intervals are , , and the normalization gives: ; ; Select the nodes that satisfy and as the collaborative analysis nodes. Only satisfies the condition. Therefore , then extract the linkage structure parameters corresponding to the variation range of the parameter combination , estimated by the sum of the squares of the standard deviations of the normalized density and the rotational speed change. Let the standard deviation of the paving density in this section be , then after normalization it is , the standard deviation of the rotational speed is , normalized to , obtain: ; Main axis regulation feedback delay represents the time delay from the signal transmission to the actual regulation. If the node delay is , the maximum response time is , normalized to: ; Difference between the paving feedback signal and the main axis change is calculated from the Euclidean distance between two normalized curves. Let the two vectors be , , calculate: ; For , substitute into: , , , , , obtain: ; ; ; This result shows that at the th node, the co-mutation index indicates that there is a mutational inconsistent co-relationship between the paving density and the main axis rotational speed at this time point, with typical characteristics of parameter linkage imbalance, which is used for subsequent trend deviation feature extraction and abnormal node positioning. This formula reflects the parameter linkage strength through the product term , and measures the disturbance structure strength and delay through the square root term . The denominator ensures the inhibitory effect of the difference between the fluctuation trends on the overall calculation result, thereby achieving stable and balanced co-mutation recognition.

[0037] Please refer to Figure 5 , the synchronous trend analysis module includes: The trend calculation sub-module analyzes the time series data of sizing dosage based on the process co-mutation index, determines the change direction of sizing dosage under each batch number, compares the change rates in the time periods before and after the mutation nodes, and calculates the trend slope intervals of sizing dosage over time for each batch; Extract the time series data of sizing dosage within the batch according to the batch number, read and sort the timestamps and sizing dosage values of each data record, and construct the change trajectory of sizing dosage on the time axis. Subsequently, take the difference in sizing dosage between adjacent time points as the change amount per unit time. If the value of the latter data point is greater than that of the former data point, mark this segment as an upward trend; otherwise, it is a downward trend. If the difference in sizing dosage between two points is within the range of ±1 kg and the sizing dosage of this batch fluctuates around 70 kg in total, it is regarded as a stable trend. Then, group the data segments with consistent change directions in each batch, extract the start and end times and sizing dosage in each group, calculate the change rate of each group. The rate is the total difference in sizing dosage divided by the duration length. For example, if the sizing dosage of a batch rises from 66 kg to 74 kg between 8:00 and 8:10, the rate is 0.8 kg per minute. This rate is used to compare the trend differences before and after the mutation node of this batch. Then, with the mutation node as the center, take two time periods before and after respectively, and repeat the calculation of the sizing change rate. If the difference in rates before and after is greater than 1.5 kg per minute, record it as a trend mutation segment. This threshold is determined by the maximum load change boundary determined by the stability of the sizing equipment applying a control rate within the range of ±1 kg per minute. Finally, calculate the trend rates of each segment for the sizing dosage data of each batch, sort all the rate values within the batch, and extract the difference between the highest rate and the lowest rate as the sizing trend slope interval of this batch. For example, if the maximum rate is 1.8 kg per minute and the minimum rate is 0.2 kg per minute, the trend slope interval is 1.6 kg per minute. Organize all batch numbers and their corresponding slope intervals to construct a sizing trend slope interval data table.

[0038] The pressure and rotational speed comparison sub-module calculates the change amplitudes of the paving pressure and the main shaft rotational speed in the same time period according to the trend slope interval, compares the synchronicity of the pressure and rotational speed trends, and uses the formula: ; Obtain the trend difference amplitude , where represents the paving pressure detection data at the th time node, represents the main shaft rotational speed feedback data at the th time node, is the total number of time nodes; The trend difference amplitude refers to the difference measure between the change trends of different process parameters (such as paving pressure and main shaft rotational speed), reflecting the fluctuation synchronicity of these two parameters during the production process.

[0039] The paving pressure and the main shaft speed are monitored in real time through sensors and the production control system respectively. If during the sizing process, the paving pressure changes at 4 time nodes and the main shaft speed also changes at the corresponding time nodes, it is necessary to calculate the change amplitudes of the paving pressure and the main shaft speed. From time node 1 to time node 4, the data of the paving pressure and the main shaft speed are as follows: Time node 1: Paving pressure = 1000N, main shaft speed = 1500RPM; Time node 2: Paving pressure = 1100N, main shaft speed = 1600RPM; Time node 3: Paving pressure = 1200N, main shaft speed = 1700RPM; Time node 4: Paving pressure = 1300N, main shaft speed = 1800RPM; Perform normalization processing on the data of the paving pressure and the main shaft speed: Normalization of paving pressure: Maximum value: 1300N, minimum value: 1000N; Perform normalization calculation on the pressure value of each time node: Time node 1: ; Time node 2: ; Time node 3: ; Time node 4: ; Normalization of main shaft speed: Maximum value: 1800RPM, minimum value: 1500RPM; Perform normalization calculation on the speed value of each time node: Time node 1: ; Time node 2: ; Time node 3: ; Time node 4: ; The normalized data is as follows: Paving pressure: [0, 0.3333, 0.6667, 1.0]; Main shaft speed: [0, 0.3333, 0.6667, 1.0]; Substitute into the formula for calculation: ; ; The result shows that the trend difference amplitude , indicating that the changing trends of the paving pressure and the main shaft speed are exactly the same within the selected time nodes, which means that there is no deviation between the paving pressure and the main shaft speed within this time period, indicating that the changes of these two process parameters are completely synchronized within this time period.

[0040] The trend consistency determination sub-module calls the trend difference amplitude, and analyzes the number of cross times and the synchronization interval of each parameter trend on the time axis according to the distribution direction difference under different process nodes, identifies the consistent section of the trend fluctuation between parameters, and obtains the trend offset characteristic quantity; Extract the parameter trend marks recorded in each key process node (such as sizing, paving, hot pressing) from the parameter time series set, arrange the trend directions of each type of parameter in chronological order, record whether it is rising, falling or stable, and compare the trend direction sequences between every two different parameters one by one on the time axis, and judge whether their trend directions are the same at each time point. If the trend directions are the same, it is marked as a consistent point. If the directions are opposite, it is marked as a cross point. If any of them is in a stable state, this point is skipped and not counted. Then count the number of trend crosses that appear on the entire time axis. This number is used to evaluate the deviation frequency of the change paces between parameters. For example, if the sizing amount and the initial hot pressing temperature cross the trend direction 12 times within one hour, then on average, a direction change hedge occurs every 5 minutes. This value is much higher than the average cross reference value of 3 times per hour between stable parameters, indicating that the trends are not synchronized. Then find the time period when the trends are exactly the same, that is, within this time period, the trend directions of all participating parameters are the same and the duration exceeds 3 minutes, which is recorded as the trend synchronization interval. Then record the start and end times of the trend synchronization interval, the participating parameters and the consistent trend direction. If the total duration of the synchronization section accounts for more than 60% of the total duration of the entire time axis, it is determined that this parameter group has a trend consistency characteristic. If it is less than 30%, it is determined that the trend fluctuation is inconsistent. The setting of this interval ratio judgment threshold is based on historical data comparison statistics. Among them, the synchronization section ratio of 90% of the high consistency batches is concentrated above 60%. Finally, extract the number of trend crosses, the start and end times of the trend synchronization interval, the participating parameter identification and the proportion to form the trend offset characteristic quantity.

[0041] Please refer to Figure 6 , the abnormal attribution positioning module includes: The abnormal fluctuation attribution sub-module analyzes the fluctuation relationship between the sudden change node of the chip moisture content and the change of the paving density based on the trend offset characteristic quantity, compares the linkage situation between the main shaft speed and other process parameters, and identifies and classifies the nodes of abnormal fluctuation; obtains the abnormal fluctuation index; All the identified trend shift batch data are batch numbered and grouped, and the marked shavings moisture content mutation node time points and the corresponding moisture content change amplitudes in the batch are extracted, and the nodes are arranged in chronological order to form a mutation sequence. Then, the sampling data sequence of the paving density acquisition channel is obtained within the same time range, and the density difference between two adjacent moments is judged. If the change amplitude exceeds 0.4 kilograms per cubic meter and the direction is consistent with the moisture content change, the segment is marked as a fluctuation coupling segment. The difference judgment threshold of 0.4 is set according to the average density change range in the normal production stable batch, and then the fluctuation coupling segments corresponding to each mutation node are summarized, and the fluctuation start time, end time and fluctuation direction are recorded, and the paving density fluctuation is recorded. The sequence is linked with the spindle speed sampling sequence for judgment, and the trend of the change direction of the spindle speed in the same time period is extracted. If the speed direction is opposite to the density direction, it is marked as reverse linkage, if the directions are consistent, it is marked as positive linkage, if the fluctuation direction is not obvious or the absolute value of the change is less than 1.5 revolutions per minute, it is recorded as a neutral segment. The threshold is set to ±2 revolutions per minute with reference to the daily floating range of the spindle speed. Finally, the coupling situation of each fluctuation segment is paired with the trend mark of the spindle speed, and they are classified into three categories: consistent coupling, reverse coupling or invalid coupling. The frequency of each type of coupling in each batch is counted. If the frequency of the same type of coupling accounts for more than half of all mutation nodes, it is considered that there is a stable abnormal linkage behavior in the batch, which constitutes an abnormal fluctuation indicator.

[0042] The batch location and integration submodule analyzes and integrates the event information and process parameters of each batch based on the abnormal fluctuation index, determines the batch association when the abnormal fluctuation occurs, locates the abnormal batch and process node, and obtains the batch abnormal feature location data; Read all batch numbers marked as abnormal linkage and their parameter fluctuation nodes one by one, compare the time series of other parameter records in the batch, extract all process parameters with change behavior in the time period corresponding to the abnormal node, including glue dosage, plate feeding pressure, hot pressing initial temperature and paving speed, construct the change amplitude and change direction identification in the time period for each parameter, and align them according to the time axis, mark the sections with three or more parameters changing synchronously in the same time period, and extract the batch number corresponding to the time period. If the section has been classified as a coupling section in the abnormal fluctuation index, it is further confirmed as a valid section belonging to the abnormal node. The ratio of the number of valid sections belonging to the abnormality in the batch to the number of time periods in the whole batch is counted. If the ratio exceeds 0.3, the batch is marked as an abnormal batch. The threshold is determined based on the historical distribution of the proportion of normal fluctuation batches in production, and the number of batches with a proportion higher than 0.25 accounts for 80% of the total number of abnormalities. Then extract the process node information of all abnormal sections in the abnormal batch, including the equipment number, the corresponding process stage (such as paving, hot pressing, glue application) and the sampling parameter name, to form the abnormal node identification and form the batch abnormality feature positioning data.

[0043] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent detection and diagnosis system for abnormal events in particleboard production, characterized in that, The system includes: The parameter time series acquisition module is based on the particle moisture content sampling channel, analyzes its change trend, compares the relationship between the sizing dosage and the batch number, calculates the correspondence between the hot pressing temperature and the forming speed, judges the matching state of the process nodes, integrates the acquisition time sequence of each parameter, and obtains a parameter time series set; The abnormal point identification module is based on the parameter time series set, analyzes the fluctuation of the particle moisture content, judges the correspondence between the matting density and the batch number, compares the change ranges of the hot pressing temperature and the forming speed, identifies the abnormal fluctuation of the batch parameters, and obtains the abnormal parameter distribution characteristics; The collaborative feature determination module, according to the abnormal parameter distribution characteristics, compares the change directions of the matting density and the main shaft speed, analyzes the parameter combination of the particle matting equipment and the inlet of the hot pressing system, judges the collaborative state of the process parameters, and obtains a process collaborative mutation index; The synchronous trend analysis module is based on the process collaborative mutation index, analyzes the change trend of the sizing dosage, calculates the trend difference between the matting pressure and the main shaft speed, compares the synchronism of the process parameter fluctuations, judges the consistency of the node trends, and obtains a trend deviation feature quantity.

2. The intelligent detection and diagnosis system for abnormal events in particleboard production according to claim 1, wherein The parameter time series set includes parameter type identification, time node marking, and sequence integrity information. The abnormal parameter distribution characteristics include abnormal type identification, abnormal occurrence node, and abnormal duration interval. The process collaborative mutation index includes collaborative abnormal identification, parameter linkage mode, and associated node characteristics. The trend deviation feature quantity includes trend consistency index, deviation degree classification, and trend change identification.

3. The intelligent detection and diagnosis system for abnormal events in particleboard production according to claim 1, characterized in that, The parameter time series acquisition module includes: The moisture content analysis sub-module is based on the particle moisture content sampling channel, analyzes the change of the particle moisture content in a continuous time period, classifies the change of the acquisition signal direction at adjacent time nodes, compares the increase or decrease in different time periods, judges the continuity and consistency of the moisture content change, filters the fluctuation performance, and obtains the moisture content trend characteristics; The sizing attribution identification sub-module, based on the moisture content trend characteristics, compares the time distribution of the sizing dosage acquisition data and the corresponding batch number, judges whether there is overlap or deviation in the attribution between each group of sizing dosage information and the batch number, analyzes the matching situation of the batch and the sizing data, identifies the abnormal attribution relationship, and obtains the sizing attribution characteristics; The parameter linkage integration sub-module, according to the sizing attribution characteristics, compares the changes of the hot pressing temperature and the forming speed at the same time node, judges the consistency of the change directions of each parameter, filters the linkage performance, and integrates the parameters and the time nodes to obtain a parameter time series set.

4. The intelligent detection and diagnosis system for abnormal events in particleboard production according to claim 1, characterized in that The abnormal point identification module includes: The moisture content fluctuation identification sub-module is based on the parameter time series set, analyzes the change trend of the particle moisture content data in the target time period, judges the change direction and amplitude between consecutive time series data, identifies the segments with continuously increasing or decreasing change amplitudes, and locates the time period with concentrated changes in the data sequence to obtain the moisture content mutation interval segment; The parameter attribution relationship judgment sub-module, based on the moisture content mutation interval segment, compares the synchronous data of the sizing dosage and the matting density and the corresponding relationship of the batch number, judges whether the matting density sampling sequence is consistent with the batch of the mutation segment, and obtains the parameter batch matching state distribution; The batch fluctuation difference identification sub-module compares the hot pressing temperature and forming speed of the corresponding batches according to the parameter batch matching status distribution, calculates the changes in paving density and spindle speed, calculates the fluctuation levels of the parameters of each batch, and judges the fluctuation performance between batches to obtain the abnormal parameter distribution characteristics.

5. The intelligent detection and diagnosis system for abnormal events in particleboard production according to claim 1, wherein The collaborative feature determination module includes: The direction matching sub-module compares the change direction of the paving density with the change direction of the spindle speed feedback signal according to the abnormal parameter distribution characteristics, judges whether the trends of the two are consistent within the same batch, optimizes the judgment criterion for trend deviation, and obtains the trend direction matching coefficient; The combination relationship sub-module calls the trend direction matching coefficient, compares the synchronous change characteristics of the paving speed, roll gap, initial hot pressing temperature and board feeding pressure, identifies the key parameter combinations of the synchronous change characteristics, optimizes the interaction relationship between the parameters, and obtains the change range of the parameter combination; The collaborative state sub-module calculates the collaborative change level of the paving density change amount and the spindle speed offset amount based on the change range of the parameter combination, compares the trend fluctuation and linkage frequency between nodes, and obtains the process collaborative mutation index.

6. The intelligent detection and diagnosis system for abnormal events in particleboard production according to claim 1, wherein The synchronous trend analysis module includes: The trend calculation sub-module analyzes the time series data of the sizing amount based on the process collaborative mutation index, judges the change direction of the sizing amount under each batch number, compares the change rates in the time periods before and after the mutation node, and calculates the trend slope interval of the sizing amount of each batch over time; The pressure and speed comparison sub-module calculates the change ranges of the paving pressure and the spindle speed in the same time period according to the trend slope interval, compares the synchronism of the pressure and speed trends, and obtains the trend difference range; The trend consistency determination sub-module calls the trend difference range, analyzes the number of intersections and synchronous intervals of the trends of each parameter on the time axis according to the distribution direction difference under the different process nodes, identifies the consistent sections of the trend fluctuations between the parameters, and obtains the trend deviation characteristic quantity.

7. The intelligent detection and diagnosis system for abnormal events in particleboard production according to claim 1, characterized in that, The system further includes: The abnormal attribution positioning module judges the abnormal attribution of the sudden change node of the chip moisture content, the changes in paving density and spindle speed based on the trend deviation characteristic quantity, identifies the batch and event information of the abnormal node, integrates the abnormal correlation information of the process parameters, and obtains the batch abnormal characteristic positioning information; The batch abnormal characteristic positioning information includes batch positioning identification, abnormal event type, and node attribution identification.

8. The intelligent detection and diagnosis system for abnormal events in particleboard production according to claim 7, characterized in that, The abnormal attribution positioning module includes: The abnormal fluctuation attribution sub-module analyzes the fluctuation relationship between the sudden change node of the chip moisture content and the change in paving density based on the trend deviation characteristic quantity, compares the linkage situation between the spindle speed and other process parameters, and identifies and classifies the nodes of abnormal fluctuations; obtains the abnormal fluctuation index; The batch positioning and integration sub-module analyzes and integrates the event information and process parameters of each batch based on the abnormal fluctuation index, judges the batch association when the abnormal fluctuation occurs, locates the abnormal batch and process node, and obtains the batch abnormal characteristic positioning data.

Images