Efficient multi-station injection molding circulation production optimization system

Abstract

The invention relates to the technical field of injection molding production optimization, and discloses an efficient multi-station injection molding circulation production optimization system which comprises a state acquisition module used for acquiring real-time operation state data and preset production target data; the beat coordination module is used for carrying out beat deviation analysis to obtain station coordination parameters; the anomaly identification module is used for marking potential anomaly links when the parameters exceed the range; the resource allocation module is used for carrying out resource dynamic allocation on the abnormal link; the mode switching module is used for marking a normal operation mode when the parameters are normal; and the result feedback module is used for outputting an optimization result. In addition, the system also comprises a data storage module and an early warning prompt module. According to the system, real-time monitoring, rhythm coordination, abnormity identification and processing, resource allocation and the like of multi-station injection molding production are achieved through multi-module cooperation, the production efficiency, the product quality and the system stability are improved, and the system is suitable for a multi-station injection molding circulation production scene.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of injection molding production optimization, specifically to a high-efficiency multi-station injection molding cycle production optimization system. BACKGROUND

[0002] In modern industrial production, injection molding as an important processing technology is widely used in many fields such as automobiles, electronics, medical devices, etc. With the continuous growth of market demand and the increasing requirements of product quality, multi-station injection molding cycle production systems are becoming more and more common. Through the coordinated operation of multiple stations, batch production can be realized, and production efficiency can be improved.

[0003] There are many problems in the current multi-station injection molding cycle production process. On the one hand, the production rhythm between stations is difficult to accurately coordinate. In actual production, injection molding machine temperature, mold closing pressure, mold opening and closing action, raw material supply flow, and cycle period parameters will be affected by factors such as equipment performance, raw material characteristics, production environment, etc. Fluctuations occur. For example, when the temperature of the injection molding machine at a certain station fails to reach the preset target value, it may lead to poor melting state of the plastic raw material, thereby affecting the molding quality and production efficiency of the product, and also disrupting the rhythm of the entire production system.

[0004] When an abnormality occurs in the production process, the traditional production system often fails to accurately identify the abnormal link in a timely manner, and cannot realize the dynamic allocation of resources. Once an abnormality occurs at a certain station, such as unstable raw material supply flow, it will not only affect the production of that station, but also may have a chain effect on the production of other stations through the correlation between stations, leading to a decrease in the efficiency of the entire production system, and even a large number of defective products.

[0005] The existing multi-station injection molding cycle production system also has deficiencies in data processing and utilization. A large amount of real-time running state data and historical production data generated during production cannot be effectively collected, analyzed and utilized. It is difficult to build an effective model based on these data to predict potential abnormalities in the production process, and it is also difficult to optimize and improve the production system.

[0006] Different product models have different characteristics and requirements for injection molding production. The traditional production system lacks a flexible adjustment mechanism for different product models. When switching to produce different models of products, a lot of time and effort is needed to reset and debug the production parameters, which seriously affects the production efficiency and flexibility.

[0007] In the production process, the early warning and treatment of abnormal situations are not timely and effective enough. The traditional early warning mechanism is often based on simple threshold judgment and cannot fully consider the correlation between various parameters and complex production environment factors, which is prone to false positives or false negatives, resulting in production abnormalities that cannot be discovered and treated in time, increasing production losses. SUMMARY

[0008] The purpose of the present application is to provide an efficient multi-station injection molding cycle production optimization system to solve the problems raised in the above background.

[0009] To achieve the above purpose, the present application provides the following technical solution: an efficient multi-station injection molding cycle production optimization system, the system comprising:

[0010] A state acquisition module for acquiring real-time running state data and preset production target data in a multi-station injection molding production process;

[0011] A beat coordination module for analyzing the real-time running state data and the preset production target data for beat deviation through a basic coordination component to obtain a station coordination parameter;

[0012] An abnormality identification module for marking a potential abnormal link in the current injection molding production link when the station coordination parameter exceeds the allowable range of the coordination parameter;

[0013] A resource allocation module for dynamically allocating resources to the injection molding production link with the potential abnormal link mark through a deep adjustment device to obtain a first optimization result;

[0014] A mode switching module for marking a normal operation mode for the current injection molding production link when the station coordination parameter is within the allowable range of the coordination parameter to obtain a second optimization result;

[0015] A result feedback module for outputting the first optimization result or the second optimization result to a control terminal.

[0016] Preferably, the execution process of the beat coordination module comprises:

[0017] The injection molding machine temperature monitoring sequence, mold closing pressure monitoring value, mold opening and closing action frequency, raw material supply flow value, cycle period length value, and temperature target sequence, pressure target value, opening and closing frequency target value, flow target value, and cycle length target value are compared to obtain temperature deviation index, pressure deviation index, opening and closing frequency deviation index, flow deviation index, and cycle length deviation index;

[0018] According to the temperature deviation index, the pressure deviation index, the opening and closing frequency deviation index, the flow deviation index and the cycle length deviation index, a production rhythm deviation dataset is constructed;

[0019] The production rhythm deviation dataset is input into the basic coordination component, and the station coordination parameter is output.

[0020] Preferably, the execution flow of the state acquisition module comprises:

[0021] A communication connection is established with a sensor group distributed in each injection molding station, and injection molding machine temperature monitoring sequences, mold clamping pressure monitoring values, mold opening and closing action frequencies, raw material supply flow values and cycle period length values in the multi-station injection molding production process are received;

[0022] A communication connection is established with a production control instruction issuing end, and temperature target sequences, pressure target values, opening and closing frequency target values, flow target values and cycle length target values of the multi-station injection molding production are received;

[0023] The injection molding machine temperature monitoring sequences, the mold clamping pressure monitoring values, the mold opening and closing action frequencies, the raw material supply flow values and the cycle period length values are classified into the real-time running state data;

[0024] The temperature target sequences, the pressure target values, the opening and closing frequency target values, the flow target values and the cycle length target values are classified into the preset production target data.

[0025] Preferably, the execution flow of the rhythm coordination module further comprises:

[0026] A deviation evaluation rule is set based on the production characteristics of each station, and the deviation evaluation rule is used to quantify the difference degree of the injection molding machine temperature monitoring sequences and the temperature target sequences, the mold clamping pressure monitoring values and the pressure target values, the mold opening and closing action frequencies and the opening and closing frequency target values, the raw material supply flow values and the flow target values, and the cycle period length values and the cycle length target values;

[0027] According to the deviation evaluation rule, the injection molding machine temperature monitoring sequences, the mold clamping pressure monitoring values, the mold opening and closing action frequencies, the raw material supply flow values and the cycle period length values are compared with the temperature target sequences, the pressure target values, the opening and closing frequency target values, the flow target values and the cycle length target values, to obtain the temperature deviation index, the pressure deviation index, the opening and closing frequency deviation index, the flow deviation index and the cycle length deviation index.

[0028] Preferably, the execution process of the beat coordination module further comprises:

[0029] According to the current injection molding product model, the corresponding basic coordination component is called to process the production beat deviation data set to obtain the workstation collaborative parameter;

[0030] The construction process of the basic coordination component comprises:

[0031] Collect historical injection molding production record data, wherein the historical injection molding production record data comprises historical running state data and historical target data;

[0032] According to the historical running state data and the historical target data, a historical beat deviation data set is constructed;

[0033] With the historical beat deviation data set as a reference, historical production optimization result data is collected, and the proportion of abnormal optimization record data in the historical production optimization result data is calculated as a collaborative abnormal probability identifier value;

[0034] With the collaborative abnormal probability identifier value as the training basis and the historical beat deviation data set as the input sample, the basic coordination component is trained and generated.

[0035] Preferably, the execution process of the resource allocation module comprises:

[0036] The first historical optimization result data whose temperature deviation index exceeds the deviation allowed range and whose pressure deviation index, opening and closing frequency deviation index, flow deviation index and cycle time length deviation index all do not exceed the deviation allowed range are screened out;

[0037] The production abnormal type whose trigger frequency exceeds the frequency allowed range in the first historical optimization result data is counted as the temperature deviation high-frequency abnormal type.

[0038] Preferably, the execution process of the resource allocation module further comprises:

[0039] The temperature deviation index, the pressure deviation index, the opening and closing frequency deviation index, the flow deviation index and the cycle time length deviation index are iterated to perform abnormal type correlation matching to obtain temperature deviation correlation abnormal type, pressure deviation correlation abnormal type, opening and closing frequency deviation correlation abnormal type, flow deviation correlation abnormal type and cycle time length deviation correlation abnormal type;

[0040] According to the temperature deviation index, the pressure deviation index, the opening and closing frequency deviation index, the flow deviation index and the cycle length deviation index from high to low, the temperature deviation associated abnormal type, the pressure deviation associated abnormal type, the opening and closing frequency deviation associated abnormal type, the flow deviation associated abnormal type and the cycle length deviation associated abnormal type are sorted to obtain an abnormal type sorting result;

[0041] The injection molding production link with the potential abnormal link label is dynamically allocated with resources according to the abnormal type sorting result through the depth adjustment device, and the first optimization result is obtained.

[0042] Preferably, the execution process of the mode switching module comprises:

[0043] When the work station coordination parameter is in the coordination parameter allowable range, the preset normal operation mode parameter is called;

[0044] According to the normal operation mode parameter, the temperature adjustment component, the pressure control component, the mold driving component, the raw material supply component and the cycle timing component of each injection molding work station are parameter set, and the second optimization result is generated.

[0045] Preferably, the data storage module is used for:

[0046] The real-time running state data and the preset production target data obtained by the state acquisition module are received;

[0047] The first optimization result and the second optimization result output by the result feedback module are received;

[0048] The real-time running state data, the preset production target data, the first optimization result and the second optimization result are classified and stored in different data partitions to form a production process record database.

[0049] Preferably, the execution process of the early warning prompt module comprises:

[0050] When the abnormal identification module labels the injection molding production link as the potential abnormal link, the preset early warning threshold range is called;

[0051] The work station coordination parameter is compared with the early warning threshold range, and if the threshold is exceeded, an early warning signal is generated;

[0052] The early warning signal is sent to the sound and light prompt device of the control terminal to trigger an early warning response.

[0053] Compared with the prior art, the beneficial effects of the present application are:

[0054] The system obtains running state data and preset production target data in a multi-station injection molding production process in real time through a state acquisition module, thereby providing an accurate data basis for the entire optimization process. A beat coordination module performs beat deviation analysis based on the data, can accurately calculate station coordination parameters, realizes accurate coordination of production beats of various stations, effectively solves the problem that station beats are difficult to synchronize in a traditional system, and greatly improves the smoothness of production.

[0055] When the station coordination parameters exceed the allowable range, an abnormality identification module timely marks potential abnormal links, generates a warning signal in combination with a warning prompt module, and sends the warning signal to a control terminal, so that workers can quickly find abnormal conditions in production and avoid expansion of the abnormal conditions. A resource allocation module dynamically allocates resources through a depth adjustment device for the marked abnormal links, sorts the abnormal types according to relevance and severity, and allocates resources in a targeted manner, thereby improving the utilization efficiency of resources, quickly solving production abnormalities, and reducing production losses.

[0056] When the station coordination parameters are within the allowable range, a mode switching module marks the production links as being in a normal operation mode, calls conventional operation mode parameters to set parameters of various station components, and ensures the stability and continuity of the production process. A data storage module stores various types of data in a classified manner, forms a production process record database, provides rich data support for subsequent production analysis, optimization, and tracing, and facilitates the summary of production experience and the improvement of production processes.

[0057] The construction process of the basic coordination component is trained using historical production data, so that the system can call corresponding components according to different product models, improve the adaptability of the system to different product models, reduce the debugging time when switching between product models, and improve the production efficiency. The filtering, statistics, and relevance matching of abnormal types in the resource allocation module can deeply analyze the root cause and influence range of the abnormality, and realize more accurate abnormality processing.

[0058] The entire system realizes comprehensive monitoring, real-time analysis, timely warning, and accurate optimization of the multi-station injection molding cyclic production process through the cooperative work of various modules, greatly improves the automation level and intelligent degree of the production system, reduces the demand for manual intervention, reduces the influence of human factors on production, thereby improves the stability and consistency of product quality, and brings significant economic benefits and competitive advantages to enterprises. BRIEF DESCRIPTION OF DRAWINGS

[0059] Figure 1 A working principle diagram of the efficient multi-station injection molding cyclic production optimization system described in the present application;

[0060] Figure 2 A flowchart executed by the state acquisition module;

[0061] Figure 3 Flow chart for building a base coordination component;

[0062] Figure 4 Flow chart for associating a matching for an exception type;

[0063] Figure 5 Flow chart for performing by a mode switching module. DETAILED DESCRIPTION

[0064] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0065] Please refer to Figures 1-5 The present application relates to an efficient multi-station injection molding cycle production optimization system, which comprises a state acquisition module for acquiring real-time running state data and preset production target data in a multi-station injection molding production process. The specific implementation is as follows:

[0066] The state acquisition module is used to acquire real-time running state data and preset production target data in a multi-station injection molding production process.

[0067] The beat coordination module is used to perform beat deviation analysis on the real-time running state data and the preset production target data through a base coordination component to obtain a station coordination parameter.

[0068] The exception identification module is used to mark a potential abnormal link of the current injection molding production link when the station coordination parameter exceeds a coordination parameter allowable range.

[0069] The resource allocation module is used to perform resource dynamic allocation on the injection molding production link with the potential abnormal link mark through a deep adjustment device to obtain a first optimization result.

[0070] The mode switching module is used to mark a normal operation mode of the current injection molding production link when the station coordination parameter is within the coordination parameter allowable range to obtain a second optimization result.

[0071] The result feedback module is used to output the first optimization result or the second optimization result to a control terminal.

[0072] Embodiment 1

[0073] In this embodiment, the state acquisition module is the data acquisition core unit of the efficient multi-station injection molding cycle production optimization system, and its implementation is as follows:

[0074] The state acquisition module first needs to establish a communication connection with the sensor group distributed in each injection molding station. The sensor group includes various types of sensors, among which temperature sensors are deployed at key positions such as barrels, nozzles and molds of injection molding machines to collect real-time injection molding machine temperature monitoring sequences. These temperature sensors use high-precision thermocouples or thermistors to obtain temperature data at a sampling frequency of milliseconds, ensuring that the time resolution of the temperature monitoring sequence meets the real-time monitoring needs of the production process. The clamping pressure monitoring value is collected by a pressure sensor installed on the clamping mechanism. The range of the pressure sensor is selected according to the clamping force of the injection molding machine, and the accuracy can reach ±0.5% of the full scale, which can accurately capture the subtle changes in pressure during the clamping process. The mold opening and closing action frequency is counted by proximity switches or encoders installed on the mold driving mechanism. Each mold opening and closing action can be accurately recorded to obtain the mold opening and closing action frequency. The raw material supply flow value is collected by a flow meter installed on the raw material conveying pipeline. The type of flow meter is selected according to the physical properties of the raw material, such as volumetric flow meters for granular raw materials and electromagnetic flow meters for molten raw materials to ensure the accuracy of flow measurement. The cycle period length value is obtained by setting a time trigger point in the production process and using a high-precision timer to record the time interval from the start of one cycle to the start of the next cycle.

[0075] After establishing a communication connection with the sensor group, the state acquisition module continuously receives real-time data sent by each sensor. For the injection molding machine temperature monitoring sequence, the state acquisition module sorts the data of each temperature sensor according to the timestamp to form a continuous monitoring sequence with time as the horizontal axis and temperature as the vertical axis. For example, for the barrel temperature of a certain station, 10 data points are collected per second to form a temperature monitoring sequence. The mold clamping pressure monitoring value is sent by the pressure sensor to the state acquisition module after each mold clamping action is completed. The state acquisition module filters multiple pressure data within the same cycle and retains the effective pressure value after removing the interference signal. The mold opening and closing action frequency is sent by the sensor to the state acquisition module when each action occurs. The state acquisition module counts the pulse signals to obtain the mold opening and closing action frequency per unit time. The raw material supply flow value is calculated by the flowmeter in real time, and the flow data is sent to the state acquisition module in a standard communication protocol. The state acquisition module smoothes the flow data to avoid sudden changes in flow data caused by pressure fluctuations in the pipeline. The cycle length value is sent by the timer to the state acquisition module at the end of each production cycle. The state acquisition module verifies the validity of the cycle length data and removes obviously abnormal cycle length data.

[0076] The state acquisition module also needs to establish a communication connection with the production control instruction issuing end. The production control instruction issuing end can be a factory production management system, an upper computer control system, or other devices with instruction sending function. The state acquisition module interacts with the production control instruction issuing end through standard industrial communication protocols such as OPCUA, Modbus, etc. The preset production target data received from the production control instruction issuing end includes temperature target sequence, pressure target value, opening and closing frequency target value, flow target value, and cycle length target value. The temperature target sequence is set according to the process requirements of the injection molding product. For example, for a certain product, the barrel temperature needs to reach different target temperatures in different production stages to form a temperature target sequence that changes with time. The pressure target value is determined according to the structural strength of the product and the design requirements of the mold to ensure that the mold clamping pressure can meet the needs of product forming. The opening and closing frequency target value is determined by production efficiency and product quality requirements. Reasonable opening and closing frequency can improve production efficiency while avoiding excessive mold wear caused by frequent action. The flow target value is set according to the characteristics of the raw material and the weight requirements of the product to ensure that the raw material supply can meet the needs of product production. The cycle length target value considers production efficiency and time requirements of each process to set a reasonable production cycle length.

[0077] After obtaining the real-time running state data and the preset production target data, the state acquisition module needs to classify, arrange and store these data. For the real-time running state data, the state acquisition module stores the injection molding machine temperature monitoring sequence, the mold closing pressure monitoring value, the mold opening and closing action frequency, the raw material supply flow value, and the cycle period length value according to the station number and time sequence respectively. For example, a data folder is created for each station, and sub-folders are created according to the time and date in the folder. The temperature monitoring sequence, pressure value and other data of the station on the same day are stored in the corresponding sub-folder. For the preset production target data, the state acquisition module classifies and stores the temperature target sequence, the pressure target value, the opening and closing frequency target value, the flow target value, and the cycle length target value according to the product model. Each product model corresponds to a target data file, which facilitates quick access to the corresponding target data when producing different products.

[0078] The state acquisition module also needs to preprocess the obtained data to improve the reliability and usability of the data. The preprocessing process includes data filtering, outlier detection and data normalization. Data filtering uses digital filtering algorithms such as Kalman filtering or median filtering to remove random noise in sensor collected data. Outlier detection sets a reasonable threshold range, and marks and processes data that exceeds the threshold, for example, for temperature data, if the temperature value at a certain time exceeds the normal range of ±20%, it is determined as an outlier, and the temperature value at the adjacent time can be used for interpolation replacement. Data normalization converts data of different types and different ranges into a unified value range, which facilitates subsequent data analysis and processing by the module.

[0079] The state acquisition module also has data transmission and synchronization functions. Through industrial Ethernet or other high-speed communication networks, the processed real-time running state data and preset production target data are transmitted in real time to other modules of the system, such as the beat coordination module, the abnormality identification module, etc. In order to ensure the data consistency between modules, the state acquisition module uses a clock synchronization mechanism to synchronize with the system clock source through the Network Time Protocol (NTP), ensuring that the time stamps of the data received by each module are accurate and consistent.

[0080] In terms of hardware design, the state acquisition module uses a high-performance industrial controller as the core processing unit. This controller has powerful data processing capabilities and rich communication interfaces, allowing it to communicate with multiple sensor groups and production control instruction sending ends simultaneously. The memory and storage capacity of the controller are configured according to the data acquisition frequency and duration to ensure that historical data can be stored for a long enough time. In order to improve the reliability of the system, the state acquisition module also has redundant design, such as power supply redundancy and communication link redundancy. When a hardware component fails, the redundant component can automatically switch to ensure the continuity of data acquisition.

[0081] In terms of software, the program of the state acquisition module adopts modular design, including a communication module, a data acquisition module, a data processing module, a data storage module, and a synchronization module. The modules interact with each other through standard interfaces, facilitating the maintenance and upgrading of the system. The communication module is responsible for establishing a communication connection and data transmission with the sensor group and the production control instruction issuing end. The data acquisition module is responsible for receiving and analyzing the data sent by the sensors. The data processing module pre-processes and classifies the collected data. The data storage module stores the processed data in the designated storage medium. The synchronization module is responsible for synchronizing with the system clock source to ensure the time consistency of the data.

[0082] The state acquisition module also has human-computer interaction function. Through the touch screen or the upper computer interface, the operator can view the real-time collected data, set the data acquisition parameters, query the historical data, etc. The interface design follows the principle of intuitiveness and ease of use, and the key data is displayed in the form of charts, curves, etc., so that the operator can master the running state in the production process in real time.

[0083] Example 2:

[0084] In this embodiment, the beat coordination module is the core processing unit of the efficient multi-station injection molding cycle production optimization system, and its implementation mode is as follows:

[0085] The primary task of the beat coordination module is to analyze the beat deviation between the real-time running state data and the preset production target data in the multi-station injection molding production process, and the basis of this process is to build a scientific and reasonable deviation evaluation rule. Based on the production characteristics of each station, such as the differences in the types of injection products produced by different stations, the materials used, and the structure of the molds, the corresponding deviation evaluation rules are set. Taking the material as an example, when the product produced by a certain station uses high-temperature molten raw materials, the allowable range of temperature deviation is relatively narrow, while the allowable range of temperature deviation for the station using ordinary plastic raw materials can be appropriately relaxed; for the precision mold station, the evaluation standard of mold pressure deviation will be more stringent to ensure the dimensional accuracy of the product, while the pressure deviation evaluation standard of the ordinary mold station can be appropriately reduced.

[0086] After the bias evaluation rule is constructed, the beat coordination module compares and analyzes various production parameters according to the rule. The temperature monitoring sequence of the injection molding machine is compared with the temperature target sequence point by point. The temperature target sequence contains specific requirements for temperature at different production stages, such as the target temperature at the raw material melting stage and the target temperature at the pressure maintaining stage. By calculating the difference between the actual temperature and the target temperature at each time point, and combining the quantitative standard for temperature deviation in the bias evaluation rule, such as using absolute difference or relative difference, the temperature deviation index is obtained. For example, the target temperature of a certain station at the raw material melting stage is 220°C, and the real-time monitored temperature is 215°C. According to the bias evaluation rule, the temperature is allowed to deviate ±8°C at this stage, and the temperature deviation index can be calculated as 5°C.

[0087] Similarly, the mold clamping pressure monitoring value is compared with the pressure target value. The pressure target value is determined according to the structural strength of the product and the load capacity of the mold, such as a product requiring a mold clamping pressure of 80 MPa. The beat coordination module obtains the real-time pressure value transmitted by the pressure sensor during mold clamping, filters the pressure data in the same cycle to remove interference signals caused by equipment vibration and other factors, retains the effective pressure value, and then compares it with the pressure target value. According to the quantitative method for pressure deviation in the bias evaluation rule, such as taking the percentage of full scale as the deviation index, the pressure deviation index is obtained.

[0088] For the comparison of mold opening and closing action frequency and opening and closing frequency target value, the opening and closing frequency target value is set based on production efficiency and mold life, such as a station that needs to complete 10 mold opening and closing actions per minute. The beat coordination module obtains the actual frequency of mold opening and closing action through a counter, compares it with the target value, calculates the absolute value or relative value of the frequency deviation, and obtains the opening and closing frequency deviation index by combining the quantitative standard for frequency deviation in the bias evaluation rule.

[0089] In the comparison process of raw material supply flow value and flow target value, the flow target value is determined according to the product material consumption and production cycle, such as a station that needs to supply 50g of raw material per second. The beat coordination module receives the real-time flow data transmitted by the flow meter, smooths the data to eliminate the influence of pipeline pressure fluctuations, and then compares it with the flow target value. According to the quantitative method for flow deviation in the bias evaluation rule, such as taking the percentage of target flow as the deviation index, the flow deviation index is obtained.

[0090] The cycle time value is compared with the cycle time target value, which takes into account the time requirements and production efficiency of each process. For example, the production cycle target of a certain product is 30 seconds. The beat coordination module obtains the actual cycle time through the timer, compares it with the target value, calculates the absolute value of the time deviation, and obtains the cycle time deviation index according to the quantification standard of the deviation evaluation rule.

[0091] After obtaining the temperature deviation index, pressure deviation index, opening and closing frequency deviation index, flow deviation index and cycle time deviation index, the beat coordination module integrates these deviation indexes to construct a production beat deviation data set. This data set is dimensioned by the station and contains the deviation indexes of each parameter of each station and the corresponding time stamp, forming a multi-dimensional deviation data set that can fully reflect the beat deviation in the production process.

[0092] Next, the beat coordination module needs to call the corresponding basic coordination component to process the production beat deviation data set according to the current injection molding product model. The construction of the basic coordination component is a training process based on historical data. First, collect historical injection molding production record data, which includes historical running state data and historical target data, covering complete production data of different product models and different production batches. Then, according to the historical running state data and historical target data, construct the historical beat deviation data set in the same way as the production beat deviation data set.

[0093] Referring to the historical beat deviation data set, collect historical production optimization result data, which records the optimization measures taken in the past production process for different beat deviation situations and the results after optimization. Calculate the proportion of abnormal optimization record data in the historical production optimization result data, that is, the ratio of the number of abnormal optimization record data to the total number of optimization record data. Set this ratio as the collaborative anomaly probability identifier value, which reflects the probability of abnormal situations in the historical production process.

[0094] Using the collaborative anomaly probability identifier value as the training basis and the historical beat deviation data set as the input sample, the basic coordination component is trained using a machine learning algorithm. During the training process, the algorithm learns the mapping relationship between the historical beat deviation data and the corresponding optimization measures, so that the basic coordination component can output reasonable station coordination parameters based on the input beat deviation data. After training, the basic coordination component is stored according to product model to facilitate quick access to the corresponding component when producing different products.

[0095] When a current production cycle deviation dataset needs to be processed, the cycle coordination module first determines the product model of the current production, then retrieves the corresponding component from the stored basic coordination component, and inputs the production cycle deviation dataset into the component. The basic coordination component analyzes and processes the input data through an internal algorithm model, considers the weights of various deviation indicators and their correlations, and outputs a workstation coordination parameter. The workstation coordination parameter is used to indicate the cooperative working state between workstations, such as the production rhythm adjustment amplitude of each workstation, parameter matching relationship, etc., providing a basis for subsequent anomaly identification and production optimization.

[0096] During the entire processing process, the cycle coordination module also has the functions of data updating and model optimization. As production continues, new production data will be continuously generated, and the cycle coordination module will periodically add new historical production record data to the training data to retrain and optimize the basic coordination component to adapt to changes in process improvement, equipment aging, etc. during the production process, ensuring the accuracy and effectiveness of the basic coordination component. The cycle coordination module uses parallel computing technology when processing data, which can simultaneously process production cycle deviation data of multiple workstations, improving the efficiency of data processing and meeting the real-time optimization needs of multi-station injection molding production. At the same time, the module also has data visualization function, which displays the production cycle deviation dataset and the output workstation coordination parameter in the form of charts, curves, etc., making it easy for operators to intuitively understand the cycle deviation and workstation coordination state during production.

[0097] Example 3:

[0098] In this embodiment, the resource allocation module is the execution core unit of the efficient multi-station injection molding cycle production optimization system, and its implementation is as follows:

[0099] When the anomaly identification module marks a potential abnormal link in the injection molding production link, the resource allocation module starts the deep adjustment mechanism. Taking an injection molding workshop of an automobile parts as an example, assuming that the No. 3 workstation is producing an insurance shell, and the temperature deviation index of the workstation coordination parameter exceeds the allowed range, while the pressure, opening and closing frequency, etc. indicators are within the normal range, at this time the resource allocation module selects the first historical optimization result data that meets the condition of "temperature deviation exceeds the range but other indicators are normal" from the historical optimization data. These data come from the production records of the workshop in the past half year, containing abnormal handling records under different shifts and different raw material batches, such as the relevant records of the barrel temperature continuously higher than the target value by 5-8℃ on October 15, 2024, and the corresponding equipment adjustment measures.

[0100] After the first historical optimization result data is screened out, the module performs frequency statistics on the production abnormality types therein. Taking 200 pieces of historical data meeting the conditions as an example, 156 records show that the abnormality type is “heating ring power attenuation”, 32 records show that the abnormality type is “raw material water content exceeds the standard”, and 12 records show that the abnormality type is “temperature sensor failure”. The module sets the frequency allowable range as 10% of the total data amount, that is, 20, at this time, the triggering frequency of “heating ring power attenuation” is 78%, which obviously exceeds the threshold, and therefore it is marked as a temperature deviation high-frequency abnormality type. This statistical process is realized through a database query statement, which counts according to the abnormality type field grouping and compares with the preset frequency threshold.

[0101] After the high-frequency abnormality type identification is completed, the module enters the abnormality type association matching stage. Taking the temperature deviation index of the current No. 3 station as the core, the pressure deviation index (the actual value differs from the target value by 2 MPa, which is within the allowable range), the opening and closing frequency deviation index (the actual frequency is 1 time / minute less than the target value, which is within the allowable range), and other data of the station are called. The system matches through a preset association rule base, for example, the association probability of temperature deviation and heating ring power attenuation is 0.85, the association probability of temperature deviation and raw material water content exceeding the standard is 0.12, the association probability of temperature deviation and mold heat dissipation is 0.03; the association probability of pressure deviation and hydraulic system leakage is 0.7, the association probability of pressure deviation and mold wear is 0.2, and so on. Thus, the temperature deviation associated abnormality types (heating ring power attenuation, raw material water content exceeding the standard), the pressure deviation associated abnormality types (hydraulic system leakage, mold wear), and other association results are obtained.

[0102] The module sorts according to the numerical size of each deviation index. Assuming that the current temperature deviation index is +8°C (target value 220°C, actual average 228°C), the pressure deviation index is +2 MPa (target value 80 MPa, actual average 82 MPa), the opening and closing frequency deviation index is -1 time / minute (target value 10 times / minute, actual 9 times / minute), the flow deviation index is +5% (target value 50 g / s, actual 52.5 g / s), and the cycle length deviation index is +1 second (target value 30 seconds, actual 31 seconds). These deviation indexes are sorted in descending order of absolute value, temperature deviation (8°C) > pressure deviation (2 MPa) > cycle length deviation (1 second) > flow deviation (5%) > opening and closing frequency deviation (1 time / minute), and accordingly, the sorting results of the associated abnormality types are: heating ring power attenuation (temperature association), hydraulic system leakage (pressure association), mold heat dissipation (cycle length association), raw material supply pump wear (flow association), and drive motor speed abnormality (opening and closing frequency association).

[0103] After the sorting is completed, the module performs resource dynamic allocation through the depth adjustment device. For the "heating ring power attenuation" anomaly ranked first, the system first triggers the device diagnosis program, calls the historical current data of the heating ring of the No. 3 work station (the normal working current should be 15-18 A, and the current measured current is 12 A), confirms the power attenuation, automatically adjusts the heating ring grouping control parameter from "full group operation" to "grouped alternating intensive heating", and adjusts the PID parameter of the heating ring temperature controller from P=2.5, I=1.2, D=0.5 to P=3.0, I=1.5, D=0.8, and sends a warning work order to the device maintenance terminal to replace the heating ring.

[0104] For the "hydraulic system leakage" pressure correlation anomaly ranked second, although the current pressure deviation is within the allowable range, in order to prevent the anomaly from expanding, the system starts the hydraulic system pressure maintenance test program, continuously monitors the pressure decay rate during the pressure maintenance stage through the pressure sensor (the normal decay rate should be <0.5 MPa / 10 s, and the current measured value is 0.8 MPa / 10 s), confirms the existence of slight leakage, automatically adjusts the oil supplement frequency of the hydraulic station from "1 time every 30 minutes" to "1 time every 15 minutes", and pushes the hydraulic oil pipeline inspection prompt to the operator terminal.

[0105]

[0106] For the "mold poor heat dissipation" period length correlation anomaly ranked third, the system calls the mold temperature monitoring sequence (mold cavity temperature target value 45-50℃, actual average value 58℃), confirms the heat dissipation anomaly, automatically adjusts the flow of the mold cooling waterway from 20L / min to 25L / min, checks the cooling water temperature (inlet water temperature target value 25℃, actual 28℃), starts the standby cooler, reduces the inlet water temperature to 24℃, and records the adjusted period length trend.

[0107] In the resource allocation process, the depth adjustment device communicates with the PLC control system of each work station through industrial Ethernet, and all parameter adjustments need to pass three verifications: first, verify whether the adjusted parameter is within the safe operation range of the device (such as the heating ring power adjustment amplitude does not exceed 15% of the rated power), second, compare the effective adjustment range in the historical optimization case (such as the PID parameter adjustment needs to refer to the successful case of the same type device), and finally, through the simulation module, the production state after adjustment is previewed (such as the temperature change curve after the heating ring parameter adjustment is simulated through the thermodynamic model).

[0108] ​After the adjustment is completed, the module collects real-time parameter data: the temperature is reduced from 228°C to 222°C after 3 cycles, the pressure is stabilized at 80 MPa, and the cycle time is shortened from 31 seconds to 30.5 seconds. These data will be written into the production process record database in real time to form a new optimization case for updating the training data set of the basic coordination component. At the same time, the module feeds back the adjustment progress to the operator through the status indicator light (yellow flashing indicates adjustment, green constant indicates adjustment completion) and the operation interface pop-up window. The pop-up window content includes abnormal type, adjustment measure, and expected impact duration, etc. For example, "the temperature control parameter has been adjusted for the power attenuation of the heating ring. The temperature will return to normal in about 5 minutes. During this period, the product needs to be sampled and tested."

[0109] In addition, the resource allocation module has a multi-level permission management function. For operations involving device hardware replacement (such as heating ring replacement work orders), engineer-level permission confirmation is required; for process parameter adjustment (such as PID parameter modification), operator-level permission can be executed. This permission setting not only ensures the timeliness of production adjustment, but also avoids the safety risks caused by misoperation. The module also has an anti-misoperation mechanism, and all parameter adjustment instructions need to be confirmed twice (the first time the instruction is sent, and the second time it is confirmed within 5 seconds) to prevent errors caused by system interference or misoperation.

[0110] At the hardware level, the deep adjustment device adopts a redundant design, with the main controller and the standby controller synchronizing data in real time. When the main controller fails, the standby controller automatically takes over control, with a switching time of <50ms, ensuring that the resource allocation process is not interrupted. The industrial-grade relays and solid-state relays provided by the device are UL certified and can withstand frequent on-off operations, suitable for the high-load working environment of injection molding production.

[0111] At the software level, the algorithm core of the resource allocation module is based on the Bayesian network model, which continuously optimizes the association probability of abnormal types and deviation indicators through historical data training. For example, when a new optimization case shows that the association probability of "raw material water content exceeding standard" and temperature deviation rises to 0.15, the system will automatically update the association rule library. The module also supports custom abnormal type extension. When an abnormal type not recorded in the historical data appears, the operator can manually enter the abnormal description, associated parameters, and processing measures through the interface to enrich the system's abnormal handling knowledge base.

[0112] Example 4:

[0113] In this embodiment, the mode switching module is the state control core unit of the efficient multi-station injection molding cycle production optimization system, and its implementation is as follows:

[0114] With the production of mobile phone shell in an electronic accessory injection molding workshop as an example, when the system calculates that the coordination parameters of each station are all within the preset coordination parameter allowable range (such as the temperature deviation is within ±5℃, the pressure deviation is within ±3MPa) through the beat coordination module, the mode switching module determines that the current production link is in a normal running state, and then starts the parameter setting process of the normal running mode. At this time, the module first retrieves the normal running mode parameters corresponding to the mobile phone shell model from the system database. The parameter set is pre-set according to the product process requirements and the equipment characteristics, and contains the standard values of the key parameters such as the temperature, pressure and action frequency of each station.

[0115] Taking the No. 1 injection molding station as an example, the target parameters of the temperature adjusting component in the normal running mode parameters are: the barrel three-section temperature is set to 200℃, 220℃ and 230℃ respectively, and the mold temperature is set to 45℃. The mode switching module sends instructions to the temperature control unit of the No. 1 station through the industrial communication network. The instructions contain the target values of each temperature control point and the control accuracy requirements. After receiving the instructions, the temperature control unit first checks the current actual temperature (such as the actual temperature of the first section of the barrel is 198℃, the second section is 217℃, the third section is 228℃, and the mold temperature is 43℃), and then starts the PID adjustment program to gradually adjust the temperature of each section to the target value. During the adjustment process, the temperature control unit will collect temperature sensor data in real time to form a closed loop control to ensure that the temperature fluctuation range is not more than ±2℃.

[0116] For the pressure control component, the target value of the clamping pressure in the normal running mode parameters is set to 70MPa, and the target value of the injection pressure is set to 90MPa. After the mode switching module sends the pressure setting instructions to the pressure control unit, the pressure control unit first detects the pressure state of the current hydraulic system (such as the actual value of the clamping pressure is 68MPa, and the actual value of the injection pressure is 88MPa), and then adjusts the hydraulic oil flow through the proportional valve to gradually increase the pressure to the target value. In order to avoid the impact of pressure mutation on the equipment and mold, the pressure adjustment process adopts a segmented pressure increasing mode, and the pressure increasing amplitude of each stage is not more than 10% of the target value, and the interval between adjacent stages is 30 seconds, to ensure the smooth rise of the pressure.

[0117] In the conventional operation mode of the mold driving assembly, the mold opening and closing frequency target value is set to 12 times per minute, and the opening and closing speed is divided into three sections: the fast mold opening speed is set to 100 mm / s, the slow mold opening speed is set to 50 mm / s, and the mold closing speed is set to 80 mm / s. After the mode switching module sends the parameter setting instruction to the mold driving control unit, the control unit adjusts the speed and acceleration of the servo motor according to the current mold position and action state. For example, when the mold is in the mold opening state, the control unit will first increase the mold opening speed from the current 80 mm / s to 100 mm / s, and then switch to the slow speed of 50 mm / s when the mold is opened to 80% of the set distance, to ensure that the mold stops smoothly; when the mold is closing, it first closes quickly at a speed of 80 mm / s, and when the mold approaches the closed position, it switches to slow closing to avoid hitting the mold.

[0118] In the conventional operation mode of the raw material supply assembly, the raw material supply flow target value is set to 40 g / s, and the screw rotation speed is set to 120 r / min. After the mode switching module sends the instruction to the raw material supply control unit, the control unit first checks the material level of the raw material hopper (such as the material level display being full), then adjusts the rotation speed of the screw driving motor to 120 r / min, and controls the raw material supply amount by adjusting the opening degree of the feed gate. At the same time, the control unit will monitor the feedback data of the flowmeter in real time (such as the current flow being 38 g / s), and adjust the screw rotation speed through the PID adjustment algorithm to ensure that the flow is stable within the range of 40 g / s ± 1 g / s.

[0119] In the conventional operation mode of the cycle timing assembly, the production cycle target value is set to 25 seconds, including 5 seconds of injection time, 8 seconds of holding pressure time, 10 seconds of cooling time, and 2 seconds of mold opening and part removal time. After the mode switching module sends the parameter setting instruction to the cycle timing control unit, the control unit re-plans the time distribution of each process. For example, in the current production cycle, the injection time is actually 5.5 seconds, the holding pressure time is 7.5 seconds, the cooling time is 10.5 seconds, and the mold opening and part removal time is 1.5 seconds. The control unit will gradually adjust the cycle time to 25 seconds by adjusting the execution speed and sequence of each action. During the adjustment process, the control unit will prioritize ensuring the sufficiency of the cooling time to avoid product deformation due to insufficient cooling, and will shorten the auxiliary time by optimizing the connection of the mold opening and part removal actions.

[0120] During the parameter setting process, the mode switching module monitors the response state of each component in real time. For example, if the temperature adjustment component is set to increase the temperature of the second section of the barrel from 217°C to 220°C, at the first minute after the adjustment starts, the temperature rises to 219°C, and at the second minute, it rises to 220°C and stabilizes, and the module confirms that the temperature adjustment is complete. If the temperature rise rate is found to be too slow during the adjustment process (e.g., only rises to 218°C after 2 minutes), the module will automatically issue a warning signal, indicating that there may be a heating coil failure or a temperature controller anomaly, and suggesting that the operator check it.

[0121] The mode switching module also has a parameter linkage adjustment function. When the parameter adjustment of one component affects other components, the module will automatically trigger the linkage adjustment of related parameters. For example, when the raw material supply flow needs to be increased to 42g / s due to changes in raw material characteristics, the module will simultaneously adjust the screw speed to 130r / min and the injection pressure to 92MPa accordingly to ensure that the raw material can be fully plasticized and injected, avoiding short shots caused by insufficient injection pressure due to increased flow.

[0122] At the software level, the program of the mode switching module uses a state machine design, dividing the parameter setting process of the regular running mode into five stages: initialization, parameter retrieval, step-by-step execution, state confirmation, and completion feedback. Each stage has clear input conditions and output actions, ensuring the orderly progress of the parameter setting process. For example, in the step-by-step execution stage, the module sends parameter setting instructions in the order of temperature, pressure, action frequency, flow, and cycle. After each component's parameter setting is complete, it moves on to the next component's setting, avoiding conflicts between multiple components adjusting simultaneously.

[0123] At the hardware level, the mode switching module connects to the control units of each station through an industrial-grade communication interface, with OPCUA communication protocol to ensure real-time and reliable data transmission. The module is equipped with a backup power supply that can maintain at least 10 minutes of working time in the event of a power outage, ensuring that the current parameter setting state can be saved in the event of a sudden power outage, and the unfinished parameter adjustment can continue after power is restored.

[0124] In addition, the mode switching module also has a historical parameter query and comparison function. The operator can query the regular running mode parameters of the mobile phone shell model at different times through the human-machine interface, such as comparing the temperature setting values of the last month and the current month to analyze whether the parameter adjustment is due to equipment aging or raw material changes. The module also supports batch import and export of parameters, making it easy to quickly synchronize parameters between different stations producing the same product, improving production preparation efficiency.

[0125] Taking mobile phone shell production as an example, when the mode switching module completes the parameter setting of the normal operation mode, the running state of the equipment at each station will be more coordinated. The temperature is stable around the target value, ensuring uniform plasticization of the raw materials; the pressure is accurately controlled, ensuring the dimensional accuracy of the product; the mold opening and closing action is smooth, improving production efficiency; the raw material supply amount is stable, avoiding product weight fluctuations; the production cycle is strictly controlled, ensuring that the production capacity meets the standard. The entire production process runs continuously and stably in the normal operation mode, laying a foundation for the protection of product quality and production efficiency.

[0126] Example 5:

[0127] In this embodiment, the data storage module and the early warning prompt module are the core units of data management and risk early warning of the efficient multi-station injection molding cycle production optimization system, and the implementation mode is as follows:

[0128] The hardware architecture of the data storage module adopts a distributed storage scheme, and at least three storage servers are deployed in the workshop server room. Data redundancy storage is achieved through RAID5 disk array technology. Taking an injection molding workshop of an automotive interior part as an example, when the state acquisition module obtains real-time running state data, such as a barrel temperature monitoring sequence of No. 1 station (10 sampling points per second, each point containing temperature value, time stamp, sensor ID), the data storage module will first structure the data, associate the temperature data with metadata such as station number, equipment model, and then store the data in batches to different data partitions of different servers through load balancing algorithm. For example, the temperature data is stored in the "real-time temperature" partition of server A, and the pressure data is stored in the "pressure monitoring" partition of server B, ensuring storage efficiency under large data volume.

[0129] For preset production target data, such as a temperature target sequence of a certain type of door panel (including raw material melting stage 230℃, pressure maintaining stage 210℃, etc.), the data storage module establishes an index directory according to product type. When the production task is assigned, the system automatically retrieves the target data of the corresponding product and stores it in the "target parameter" partition, while generating a data verification code (such as MD5 value) to ensure that the data is not tampered with during transmission and storage. When storing, an incremental storage method is used, only the difference part from the historical version is recorded, for example, when the pressure target value of a certain product is adjusted from 80MPa to 82MPa, the module only stores the change record of the parameter and the change time, saving storage resources.

[0130] The storage of the first and second optimization results follows the production flow timing logic. Taking the triggering of resource allocation at Station No. 3 due to temperature deviation as an example, the module records the optimization start time, parameter adjustment details of the deep adjustment device (such as adjusting the heating ring PID parameter from P = 2.5 to P = 3.0), the change curve of the temperature data after adjustment (sampling every 5 minutes), and other information, and stores them in the "optimization case" partition. For the second optimization result in normal operation mode, the module records the regular parameter setting value, the response time of each component (such as the time taken by the temperature adjustment component to adjust from the current value to the target value), and other information, and stores them in the "normal operation record" partition.

[0131] The data partitioning strategy adopts a three-dimensional classification method: according to data type (real-time data, target data, optimization result), station number (Stations No. 1-20), and time period (day / week / month) to establish a three-level directory. For example, the temperature data storage path for Station No. 1 on June 24, 2025 is: / data type / real-time data / station number / Station No. 1 / time period / 2025 / 06 / 24 / temperature monitoring.dat. This structured storage method facilitates subsequent keyword search (such as "Station No. 3 temperature optimization on June 3, 2025") to quickly locate data.

[0132] The hardware of the early warning prompt module includes audible and visual prompt devices (LED alarm lights and buzzers installed in each area of the workshop) and control terminals (early warning display interfaces built into the operation panels of each station). When the anomaly identification module marks a station as a potential abnormal link, such as when the temperature deviation index in the station coordination parameters of Station No. 5 reaches +10°C (exceeding the allowed range of +8°C), the early warning prompt module first retrieves the pre-set early warning threshold range (the temperature deviation early warning threshold is +8°C), compares it through the logic operation unit, and confirms that it exceeds the threshold, immediately generating an early warning signal.

[0133] The transmission of the early warning signal adopts a dual-line redundancy mechanism: it is sent to the control terminal through the workshop industrial Ethernet at the same time, and it is sent to the audible and visual prompt devices through an independent RS485 bus. Taking the LED alarm light as an example, after receiving the early warning signal, it will flash yellow light at a frequency of 3 times per second, and the buzzer will emit a "beep" sound with an interval of 2 seconds; the early warning interface on the operation panel of the control terminal will pop up a red warning box displaying "Station No. 5 temperature anomaly, deviation +10°C", and highlight the abnormal parameter curve (the deviation part of the real-time temperature curve and the target curve).

[0134] The early warning level is divided into three levels: first-level warning (the parameter exceeds the threshold within 10%), second-level warning (exceeds 10%-30%), and third-level warning (exceeds 30% or more). Different levels correspond to different early warning response methods: first-level warning only triggers sound and light prompts and interface warnings; second-level warning, in addition to sound and light prompts, automatically reduces the production speed of the station by 20%; third-level warning triggers the device safety shutdown program, and sends a short message warning to the workshop manager's mobile phone (the content includes the station number, abnormal type, and timestamp). For example, a temperature deviation of +10°C belongs to second-level warning (threshold +8°C, exceeding 25%), and the system will reduce the injection speed of station No. 5 from 100 mm / s to 80 mm / s while triggering sound and light prompts.

[0135] The setting of the early warning threshold range is based on historical data statistics. Taking the temperature deviation threshold as an example, the module analyzes the temperature data of the station for the past year, calculates that the average temperature deviation during normal production is +2°C, and the standard deviation is 1.5°C, so the early warning threshold is set to the average value +4 times the standard deviation (+2°C +4×1.5°C = +8°C), ensuring that the threshold can timely capture abnormalities and avoid false positives. The threshold supports manual fine-tuning, and when the mold or raw material is replaced, the process engineer can temporarily adjust the temperature threshold to +10°C through the management interface, and the adjustment record will be automatically saved to the "Threshold Change Log".

[0136] The cooperation between the data storage module and the early warning prompt module is reflected in that when the early warning signal is generated, the module will automatically retrieve the historical data of the station for the past 1 hour (such as temperature trend, pressure change, raw material flow fluctuation, etc.) from the data storage module, generate an abnormality analysis report, and push it to the operator. For example, when the temperature of station No. 5 is abnormal, the report will show "the temperature has been rising continuously for the past 30 minutes, from 220°C to 230°C, during which the raw material flow increased by 5% and the clamping pressure decreased by 3MPa", providing data support for quickly locating the cause of the abnormality.

[0137] In terms of data security, the data storage module adopts multi-level permission control: the operator can only view the current station data, the process engineer can modify the target parameters, and the system administrator has all data management permissions. All data access records (such as access time, access account, operation type) are written into the audit log in real time, ensuring that the data is traceable. The storage server is configured with a firewall and an intrusion detection system to prevent unauthorized IP access and prevent data leakage.

[0138] The early warning prompt module also has a pre-warning fatigue avoidance mechanism, which automatically switches the early warning method (such as from sound warning to vibration warning) when the same type of warning lasts for more than 30 minutes, avoiding the operator's paralysis due to long-term exposure to the same type of warning. At the same time, the module will record the time spent on handling the warning, such as if the operator does not respond to the second-level warning within 10 minutes, the system will automatically upgrade to third-level warning and trigger the shutdown program.

[0139] Taking the injection molding production of automobile door panel as an example, the data storage module stores about 20 GB of production data every day, including various monitoring sequences of 10 stations, target parameters of 5 products, and average 30 times of optimization result records. These data are backed up to the cloud storage center regularly, with a retention period of 5 years, facilitating long-term production data analysis and process optimization. The early warning prompt module triggers 5-8 first-level warnings and 1-2 second-level warnings on average every day, effectively preventing batch quality problems caused by gradual equipment failure (such as heating ring power attenuation).

[0140] It should be noted that, in this text, relational terms such as first and second are used merely to distinguish one entity or action from another, without necessarily requiring or implying any actual such relationship or order between or among the entities or actions. Also, the terms "comprises", "comprising", or any other variations thereof, are intended to cover non-exclusive inclusions, so that a process, method, article, or apparatus that comprises a list of elements does not only include those elements, but also includes other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0141] Although embodiments of the present application have been shown and described, it is to be understood that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present application, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A high-efficiency multi-station injection molding cycle production optimization system, characterized in that, include: The status acquisition module is used to acquire real-time operating status data and preset production target data during the multi-station injection molding production process; The cycle time coordination module is used to perform cycle time deviation analysis on the real-time operating status data and the preset production target data through the basic coordination components to obtain workstation coordination parameters. An anomaly identification module is used to mark potential anomalies in the current injection molding production process when the workstation coordination parameters exceed the allowable range of coordination parameters. The resource allocation module is used to dynamically allocate resources in the injection molding production process marked with the potential abnormal process through the depth adjustment device to obtain a first optimization result; The mode switching module is used to mark the current injection molding production process as a normal operation mode when the workstation coordination parameters are within the allowable range of coordination parameters, and to obtain a second optimization result. The result feedback module is used to output the first optimization result or the second optimization result to the control terminal.

2. The high-efficiency multi-station injection molding cycle production optimization system as described in claim 1, characterized in that, The execution flow of the rhythm coordination module includes: The temperature monitoring sequence, mold closing pressure monitoring value, mold opening and closing frequency, raw material supply flow rate, and cycle duration value of the injection molding machine are compared with the target sequence, pressure target value, opening and closing frequency target value, flow rate target value, and cycle duration target value to obtain temperature deviation index, pressure deviation index, opening and closing frequency deviation index, flow rate deviation index, and cycle duration deviation index. Based on the temperature deviation index, the pressure deviation index, the opening and closing frequency deviation index, the flow rate deviation index, and the cycle duration deviation index, a production cycle deviation dataset is constructed. The production cycle deviation dataset is input into the basic coordination component, and the workstation coordination parameters are output.

3. The high-efficiency multi-station injection molding cycle production optimization system as described in claim 2, characterized in that, The execution flow of the status acquisition module includes: Establish a communication connection with the sensor group distributed in each injection station and receive the injection machine temperature monitoring sequence, mold closing pressure monitoring value, mold opening and closing frequency, raw material supply flow rate value, and cycle duration value in the multi-station injection molding production process. Establish a communication connection with the production control command issuing end and receive the target temperature sequence, target pressure value, target opening and closing frequency value, target flow rate value, and target cycle duration value of the multi-station injection molding production; The injection molding machine temperature monitoring sequence, the mold closing pressure monitoring value, the mold opening and closing frequency, the raw material supply flow rate, and the cycle duration value are included in the real-time operating status data. The target temperature sequence, the target pressure value, the target opening and closing frequency value, the target flow rate value, and the target cycle duration value are incorporated into the preset production target data.

4. The high-efficiency multi-station injection molding cycle production optimization system as described in claim 3, characterized in that, The execution flow of the rhythm coordination module also includes: Based on the production characteristics of each workstation, deviation evaluation rules are set. These rules are used to quantify the differences between the injection molding machine temperature monitoring sequence and the temperature target sequence, the mold closing pressure monitoring value and the pressure target value, the mold opening and closing frequency and the opening and closing frequency target value, the raw material supply flow rate value and the flow rate target value, and the cycle duration value and the cycle duration target value. According to the deviation evaluation rules, the injection molding machine temperature monitoring sequence, the mold closing pressure monitoring value, the mold opening and closing frequency, the raw material supply flow rate, and the cycle duration value are compared with the temperature target sequence, the pressure target value, the opening and closing frequency target value, the flow rate target value, and the cycle duration target value to obtain the temperature deviation index, the pressure deviation index, the opening and closing frequency deviation index, the flow rate deviation index, and the cycle duration deviation index.

5. The high-efficiency multi-station injection molding cycle production optimization system as described in claim 4, characterized in that, The execution flow of the rhythm coordination module also includes: Based on the current injection molding product model, the corresponding basic coordination component is invoked to process the production cycle deviation dataset and obtain the workstation coordination parameters; The basic coordination component construction process includes: Collect historical injection molding production record data, wherein the historical injection molding production record data includes historical operating status data and historical target data; Based on the historical operating status data and the historical target data, a historical beat deviation dataset is constructed; Using the historical beat deviation dataset as a reference, collect historical production optimization result data, and calculate the proportion of abnormal optimization record data in the historical production optimization result data, which is set as the collaborative abnormality probability identifier value; The basic coordination component is trained using the cooperative anomaly probability identifier as the training basis and the historical beat deviation dataset as the input sample.

6. The high-efficiency multi-station injection molding cycle production optimization system as described in claim 3, characterized in that, The execution flow of the resource allocation module includes: The first historical optimization result data is selected, where the temperature deviation index exceeds the allowable deviation range, but the pressure deviation index, the opening and closing frequency deviation index, the flow rate deviation index, and the cycle duration deviation index do not exceed the allowable deviation range. The production anomaly types whose trigger frequency exceeds the allowed frequency range in the first historical optimization result data are statistically analyzed and designated as the high-frequency anomaly type of temperature deviation.

7. The high-efficiency multi-station injection molding cycle production optimization system as described in claim 6, characterized in that, The execution process of the resource allocation module also includes: The temperature deviation index, pressure deviation index, opening and closing frequency deviation index, flow rate deviation index, and cycle duration deviation index are traversed to perform anomaly type correlation matching to obtain the temperature deviation associated anomaly type, pressure deviation associated anomaly type, opening and closing frequency deviation associated anomaly type, flow rate deviation associated anomaly type, and cycle duration deviation associated anomaly type. Based on the temperature deviation index, pressure deviation index, opening and closing frequency deviation index, flow rate deviation index, and cycle duration deviation index, in descending order, the abnormality types associated with the temperature deviation, pressure deviation, opening and closing frequency deviation, flow rate deviation, and cycle duration deviation are sorted to obtain the abnormality type sorting result. Using the depth adjustment device, resources are dynamically allocated to the injection molding production process marked with the potential abnormal links according to the abnormality type sorting result to obtain the first optimization result.

8. The high-efficiency multi-station injection molding cycle production optimization system as described in claim 1, characterized in that, The execution flow of the mode switching module includes: When the workstation collaboration parameters are within the allowable range, the preset normal operation mode parameters are retrieved; Based on the parameters of the conventional operating mode, the parameters of the temperature regulation component, pressure control component, mold drive component, raw material supply component and cycle timing component of each injection molding station are set to generate the second optimization result.

9. The high-efficiency multi-station injection molding cycle production optimization system as described in claim 1, characterized in that, It also includes a data storage module, which is used for: Receive the real-time operating status data and the preset production target data acquired by the status acquisition module; Receive the first optimization result and the second optimization result output by the result feedback module; The real-time operating status data, the preset production target data, the first optimization result, and the second optimization result are classified and stored in different data partitions to form a production process record database.

10. The high-efficiency multi-station injection molding cycle production optimization system as described in claim 1, characterized in that, It also includes an early warning module, the execution flow of which includes: When the anomaly identification module marks the potential anomaly in the injection molding production process, it retrieves the preset warning threshold range. The workstation coordination parameters are compared with the warning threshold range; if the threshold is exceeded, a warning signal is generated. The warning signal is sent to the audio-visual prompt device of the control terminal to trigger the warning response.

Images