A production control method and device of an electronic device, equipment and storage medium

Abstract

The application belongs to the technical field of intelligent manufacturing, and discloses a production control method and device of an electronic device, a control device and a storage medium. A preset composite firmware package is burned into the mainboard of the electronic device by a burning tool during production. The composite firmware package includes production firmware and delivery firmware embedded in the form of independent partition images. Thus, hardware calibration and function testing of the electronic device can be performed in the running environment of the production firmware. After the whole machine of the electronic device is coupled, a start instruction is directly sent to the electronic device to enable the electronic device to upgrade the production firmware to the delivery firmware. Since the start instruction is sent instantaneously through the network, the connection can be disconnected after the sending, and there is no need to wait for the upgrading process of the electronic device online. Thus, simultaneous automatic upgrading of a large number of devices can be realized, the production efficiency is greatly improved, and the composite firmware package is burned at one time, so that there is no need to burn again, the burning process can be simplified, and the failure rate can be reduced.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of intelligent manufacturing, and particularly relates to a production control method and device of an electronic device, a control device and a storage medium. BACKGROUND

[0002] In the production and manufacturing process of electronic devices, especially original design manufacturer (ODM) devices, the production firmware needs to be built-in with software services strictly matched with the version of the production line test tool, while the delivery firmware is provided by the ODM customer, and the internal software service version may be incompatible with the production line tool, resulting in that the delivery firmware cannot be directly used for production test. Therefore, the production firmware containing specific test tools and drivers is usually used to complete the hardware calibration and function test of the device. After all production procedures are completed, the customer-specified delivery firmware is burned into the device through a burning tool to replace the production firmware.

[0003] At present, the process commonly used in the industry is: first, in the download station of the production line, the production firmware is batch burned into the device mainboard using a multi-machine download tool (usually through a USB interface); second, the device mainboard completes all production test processes on the subsequent stations (such as calibration, single board test); and finally, a station is added at the end of the process, and the customer-specified delivery firmware is burned into the device again using the multi-machine download tool to overwrite the original production firmware.

[0004] The traditional technical solution adopts a twice-burning process, but the multi-machine download tool itself has a certain failure probability (for example, 1%) in burning. This means that each device will experience two failure risks, which theoretically doubles the whole machine failure rate caused by burning, increasing the rework cost and production uncertainty. Moreover, the multi-machine download tool based on USB usually has a quantity limit (such as one-to-eight), and the operator must wait for the entire burning process to end before processing the next batch of devices, which becomes a bottleneck of production efficiency, resulting in a very low production line automation efficiency. SUMMARY

[0005] The present application aims to provide a production control method and device of an electronic device, a device and a storage medium, which can simplify the burning process, reduce the failure rate, and greatly improve the production efficiency.

[0006] The present application discloses a production control method of an electronic device, comprising:

[0007] In the production process, a preset composite firmware package is burned into a mainboard of an electronic device by a burning tool; wherein the composite firmware package comprises a production firmware and a delivery firmware embedded in the form of independent partition images; the production firmware is a firmware on a production line, and the delivery firmware is a firmware at the time of delivery;

[0008] The electronic device is controlled to start and run the production firmware, and hardware calibration and function test are performed on the electronic device in the running environment of the production firmware;

[0009] After the whole machine of the electronic device is coupled, a start instruction is sent to the electronic device, so that the electronic device upgrades the production firmware to the delivery firmware.

[0010] In some embodiments, after the start instruction is sent to the electronic device to make the electronic device upgrade the production firmware to the delivery firmware, the method further comprises:

[0011] determining whether the electronic device normally restarts and runs the delivery firmware;

[0012] if the electronic device cannot normally restart or run the delivery firmware, determining that the electronic device is burned badly;

[0013] collecting current environmental parameters on the production line, and calculating an environmental index value according to the current environmental parameters;

[0014] determining a target adjustment model corresponding to the environmental index value from a plurality of adjustment models;

[0015] determining a target feature vector according to current burning data on the production line, inputting the target feature vector into the target adjustment model, and obtaining a target control parameter on the production line;

[0016] adjusting the current control parameter of the production line to the target control parameter.

[0017] In some embodiments, after determining that the electronic device is burned badly, the method further comprises:

[0018] obtaining a plurality of sensing images collected by different image sensing devices on the production line for the electronic device;

[0019] fusing a plurality of the sensing images to obtain a target image, and identifying the target image to obtain a product code of the electronic device;

[0020] obtaining a process parameter associated with the product code of the electronic device;

[0021] extracting production feature data of each burner according to the process parameter, and predicting a target failure probability of each burner according to the production feature data.

[0022] controlling the burners to automatically lock when the target failure probability reaches a specified probability, and controlling subsequent distribution of the mainboards on the production line to the burners with a target failure probability lower than the specified probability.

[0023] In some embodiments, the target failure probability of each burner is predicted according to the production feature data, including:

[0024] inputting the production feature data of each burner into a pre-trained prediction model to obtain a first failure probability of each burner;

[0025] determining a target failure probability according to the first failure probability.

[0026] In some embodiments, the target failure probability is determined according to the first failure probability, including:

[0027] predicting a health index of each burner according to the production feature data;

[0028] calculating a second failure probability according to the health index;

[0029] determining an average value of the first failure probability and the second failure probability as the target failure probability.

[0030] In some embodiments, the current environmental parameters at least include air temperature, average radiant temperature, air flow rate, relative humidity, pollutant concentration in the air, and limit deviation that the device can withstand; and the environmental index value is calculated according to the current environmental parameters, including:

[0031] calculating an air thermal comfort index according to the air temperature, the average radiant temperature, the air flow rate, and the relative humidity;

[0032] calculating an air quality health index according to the pollutant concentration in the air;

[0033] calculating a device operating environment comprehensive index according to the measured values of all current environmental parameters and the limit deviation that the device can withstand;

[0034] calculating the environmental index value according to the air thermal comfort index, the air quality health index, and the device operating environment comprehensive index.

[0035] The second aspect of the present application discloses a production control device of an electronic device, including:

[0036] A burning unit is configured to burn a preset composite firmware package into a mainboard of an electronic device through a burning tool during production, wherein the composite firmware package comprises a production firmware and a delivery firmware embedded in the form of an independent partition image; the production firmware is a firmware on a production line, and the delivery firmware is a firmware when the electronic device is delivered;

[0037] A running unit is configured to control the electronic device to start and run the production firmware, and perform hardware calibration and function test on the electronic device in a running environment of the production firmware;

[0038] An upgrading unit is configured to send a starting instruction to the electronic device after the electronic device is completely coupled, so that the electronic device upgrades the production firmware to the delivery firmware.

[0039] In some embodiments, the device further comprises:

[0040] A judging unit is configured to judge whether the electronic device is restarted normally and runs the delivery firmware after the upgrading unit sends the starting instruction to the electronic device, so that the electronic device upgrades the production firmware to the delivery firmware;

[0041] A determining unit is configured to determine that the electronic device is burned abnormally when the judging unit judges that the electronic device cannot be restarted normally or run the delivery firmware.

[0042] A collecting unit is configured to collect current environmental parameters on a production line;

[0043] An environmental calculating unit is configured to calculate an environmental index value according to the current environmental parameters;

[0044] A calling unit is configured to determine a target adjustment model corresponding to the environmental index value from a plurality of adjustment models;

[0045] A feature extracting unit is configured to determine a target feature vector according to current burning data on the production line;

[0046] A parameter optimizing unit is configured to input the target feature vector into the target adjustment model to obtain a target control parameter on the production line;

[0047] A parameter adjusting unit is configured to adjust a current control parameter of the production line to the target control parameter.

[0048] A third aspect of the present application discloses a control device comprising a memory storing executable program codes and a processor coupled with the memory; the processor invokes the executable program codes stored in the memory, and is configured to execute the production control method of the electronic device disclosed in the first aspect.

[0049] The fourth aspect of the present application discloses a computer readable storage medium storing a computer program, wherein the computer program causes a computer to execute the production control method of the electronic device disclosed in the first aspect.

[0050] The present application burns the preset composite firmware package to the mainboard of the electronic device in the production process by the burning tool, the composite firmware package includes the production firmware and the delivery firmware embedded in the form of independent partition image, so that the hardware calibration and the function test of the electronic device can be carried out in the running environment of the production firmware, and after the whole machine coupling of the electronic device is completed, the start instruction is directly sent to the electronic device, so that the electronic device upgrades the production firmware to the delivery firmware. Its beneficial effect lies in that the start instruction is sent instantaneously through the network, and the connection is disconnected after the instruction is sent, without online waiting for the upgrading process of the electronic device, so that the simultaneous automatic upgrading of a large number of devices can be realized, thereby greatly improving the production efficiency, and the composite firmware package is burned at one time, without re-burning, which can simplify the burning process and reduce the failure rate. BRIEF DESCRIPTION OF DRAWINGS

[0051] The drawings herein show the specific examples of the technical solutions of the present application, and constitute a part of the specification together with the specific embodiments, for explaining the technical solutions, principles and effects of the present application.

[0052] Unless specifically stated or defined otherwise, the same reference signs in different drawings represent the same or similar technical features, and different reference signs may also be used to represent the same or similar technical features.

[0053] Figure 1 is a flow chart of the production control method of the electronic device disclosed by the embodiment of the present application;

[0054] Figure 2 is a structural schematic diagram of the production control device of the electronic device disclosed by the embodiment of the present application;

[0055] Figure 3 is a structural schematic diagram of the control device disclosed by the embodiment of the present application.

[0056] Explanation of reference signs:

[0057] 201, burning unit; 202, running unit; 203, upgrading unit; 301, memory; 302, processor. DETAILED DESCRIPTION

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. In the case of conflict between the present description and the technical and scientific terms as understood by those skilled in the art, the present description will control. All the technical and scientific terms used herein can have the same meaning as the purpose of implementing the technical solutions of the present application. The terms "first, second" used herein are only used for distinguishing the names and do not represent the specific quantity or order. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0059] It should be noted that when an element is considered to be "fixed" to another element, it can be directly fixed to the other element or a middle element can exist; when an element is considered to be "connected" to another element, it can be directly connected to the other element or a middle element can exist; when an element is considered to be "mounted" to another element, it can be directly mounted to the other element or a middle element can exist. When an element is considered to be "provided" to another element, it can be directly provided to the other element or a middle element can exist.

[0060] Unless otherwise specified or defined, "the", "this" used herein refers to the technical features or technical contents mentioned or described before the corresponding position, which can be the same as or similar to the technical features or technical contents mentioned. In addition, the terms "include" and "have" used herein and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units not listed, or optionally includes other steps or units inherent to the process, method, product or device.

[0061] The embodiment of the present application discloses a production control method of an electronic device, which can be realized by computer programming. The execution subject of the method is a production line control host, which can be configured as a control device such as a computer, a notebook computer, a tablet computer, or a production control device embedded in the production line control host, and the present application does not make any limitation thereon. In order to facilitate the understanding of the present application, the specific embodiments of the present application will be described in more detail below with reference to the accompanying drawings.

[0062] As shown in Figure 1 The method comprises the following steps 110-130:

[0063] 110. In the production process, the production line control host burns the preset composite firmware package to the mainboard of the electronic device through a burning tool; the composite firmware package comprises production firmware and delivery firmware embedded in the form of independent partition images.

[0064] In the present application, the electronic device produced can be a smart phone watch, a smart earphone or a smart phone, etc. It should be noted that firmware refers to the device "driver" saved in the device. Through the firmware, the operating system can implement specific running actions according to the standard device driver, such as an optical drive, a CD recorder, etc. The firmware is a software that performs the most basic and bottom layer work of a system.

[0065] In the present application, the "production firmware" is defined as the firmware on the production line, which is used to drive the electronic device to complete the testing and calibration in all production processes; and the "delivery firmware" is defined as the firmware at the time of shipment, that is, the commercial version of the firmware finally delivered to the user.

[0066] In the embodiment of the present application, a composite firmware package is constructed in advance, which physically contains the production firmware and embeds the final delivery firmware in the form of an independent partition image.

[0067] The specific implementation of constructing the composite firmware package includes: when compiling the production firmware, checking whether the binary file of the delivery firmware (such as sysupgrade.bin) exists in the user-specified path through the compilation script (such as Makefile), if it exists, encapsulating it into one or more independent partition image (such as user_data.img) files, and then integrating it into the production firmware to generate the composite firmware package.

[0068] As an optional implementation, the partition strategy of the device flash memory can also be defined, and the device flash memory is divided into at least three independent areas: a system partition (rootfs) for running the system, a preset partition (user_data) for storing the delivery firmware image file, and a calibration data partition (such as factory data) for storing the calibration data. Ensure that the calibration data partition is independent of the system partition (rootfs) and the preset partition (user_data). Since the firmware self-upgrade process only covers the system partition, the integrity of the calibration data partition can be ensured, so that the calibration data can be inherited without loss.

[0069] In step 110, the composite firmware package prepared above can be burned into the mainboard of the electronic device at one time by using a burning tool (such as a USB multi-machine download tool) at the download station of the production line.

[0070] 120. The production line control host controls the electronic device to start and run the production firmware, and performs hardware calibration and function test on the electronic device in the running environment of the production firmware.

[0071] After the production line control host controls the electronic device to start, the production firmware system is run.

[0072] In the subsequent "calibration station" and "single board test station", the electronic device completes all hardware calibration and function test under the running environment of the production firmware. The key data generated in the process of hardware calibration and function test is written into an independent calibration data partition.

[0073] 130、After the electronic device is completely coupled, the production line control host sends a start instruction to the electronic device to make the electronic device upgrade the production firmware to the delivery firmware.

[0074] Specifically, in the whole machine test link after the whole machine coupling assembly into a complete device, the production line control host remotely logs in the electronic device through a network (such as Ethernet) in the form of Telnet or SSH, and issues a start instruction (such as the sysupgrade command of OpenWrt) to the electronic device. After the electronic device receives the start instruction, it executes a preset self-upgrade script (such as custom_FW_selfUpgrade.sh) to complete the self-upgrade operation of upgrading the production firmware to the delivery firmware. The core function of the self-upgrade script is to call the built-in upgrade instruction of the system and specify the upgrade source as the binary file of the delivery firmware pre-stored in the delivery partition.

[0075] Further, in the process of executing the firmware self-upgrade, the electronic device covers the content of the delivery firmware to the system partition (rootfs). Since the calibration data partition is independent, this upgrade process will not affect any calibration data stored therein, realizing lossless inheritance of the calibration data. After the upgrade is completed, the electronic device automatically restarts, and the final "delivery firmware" system is run after the restart, and all calibration data generated in the production process is retained, becoming a qualified product to be delivered.

[0076] In summary, by implementing the embodiment of the present application, the traditional two-time physical burning is reduced to one time, and the production test and the deployment of the final delivery firmware can be completed through only one physical burning, thereby fundamentally reducing the production failure rate caused by burning failure by 50%, significantly reducing the rework cost, and greatly reducing the production failure rate.

[0077] In addition, the second burning firmware upgrade operation is changed into an efficient trigger mechanism that can issue offline instructions (i.e. start instructions) remotely, in parallel and in batches through the network. Compared with the USB burning method which must be online and has port number limitation, the efficiency of the present method is higher, greatly releases the host computer resources, improves the automation level and flow speed of the production line, and thus greatly improves the production efficiency.

[0078] In addition, the production firmware and delivery firmware are decoupled. The customer does not need to care whether the delivery firmware provided by it is compatible with the test tool on the production line, but only needs to provide the final product function. This reduces the development and maintenance burden of the customer, and also greatly reduces the firmware acceptance workload of our side, without the need for complex compatibility traversal testing, thereby simplifying the firmware management and acceptance process.

[0079] Furthermore, through reasonable partition design, it is ensured that the key production data (i.e. calibration data) generated on the production line during the firmware version switching process is completely preserved, thereby ensuring the consistency and quality of the product.

[0080] Further, considering that the control in the production process of the electronic device in the prior art usually adopts fixed control parameters, lacking intelligent and adaptive adjustment capability, the production process is difficult to adapt to dynamic changes, affecting the production efficiency and product quality. Optionally, after step 130 is performed, the following non-illustrated steps 140-190 can also be performed in some possible embodiments:

[0081] 140, judge whether the electronic device is normally restarted and runs the delivery firmware.

[0082] 150, if the electronic device cannot be normally restarted or run the delivery firmware, it is determined that the electronic device is burned in bad.

[0083] Specifically, a check code (such as CRC, MD5 or SHA verification code) can be embedded in the delivery firmware in advance. If the electronic device cannot be normally restarted or run the delivery firmware after being burned in, the integrity of the check code is automatically verified. When it is verified that the embedded check code is incomplete, it is determined that the electronic device is burned in bad.

[0084] Optionally, after it is determined that the electronic device is burned in bad, the number of times of burning in bad of the burner for the electronic device is increased by one, and the number of times of burning in bad of the same burner is monitored. If the number of times of burning in bad of the same burner reaches a preset number within a specified time period (such as 15 minutes), the production line control host controls the burner to be automatically locked and stop burning in. The production line control host can also send a notification message to the user terminal to remind the engineer to repair, and the subsequent product is automatically routed to the standby burning station. In this way, by detecting and recording the number of times of burning in bad, an abnormal alarm can be triggered, for example, the burning in is automatically stopped within 15 minutes. 3 times of burning in bad.

[0085] Further, after determining that the electronic device is burned in improperly, and before adding one to the number of times of improper burning of the burner for the electronic device, it can be determined whether the electronic device is improperly burned for the first time. If the electronic device is improperly burned for the first time, the production line control host sends a retry instruction to the electronic device to make the electronic device automatically retry the specified number of times of self-upgrade operation. For example, if the electronic device is improperly burned for the first time, the electronic device automatically retries the self-upgrade operation for two times. After the electronic device automatically retries the specified number of times of self-upgrade operation, if it is determined again that the electronic device is improperly burned, one is added to the number of times of improper burning of the burner for the electronic device.

[0086] In this way, it can be determined that the burner is faulty only after the electronic device retries multiple times of improper burning, thereby excluding the event of simply improper burning for the first time, and improving the identification accuracy of the burner fault.

[0087] As an optional implementation, after determining that the electronic device is burned in improperly, the following steps 151-155 not shown in the figure can also be performed.

[0088] 151. Obtain multiple sensing images of the electronic device collected by different image sensing devices on the production line.

[0089] Multiple different sensing devices can be provided on the production line, such as a visible light camera, an infrared thermal imager, a multispectral scanner, a radar, and the like.

[0090] 152. Fuse the multiple sensing images to obtain a target image, and identify the target image to obtain the product code of the electronic device.

[0091] Fusing the multiple sensing images can improve the comprehensive information of multiple images captured in the same scene, and generate a target image (or a fused image) with richer, more comprehensive, and more reliable information. Different sensors have their own advantages and disadvantages, and the fused image can overcome the limitations of a single sensor. Through cross-validation of multiple sources of information, uncertainty is reduced, and the confidence of interpreting the scene or target is improved. Specifically, fusing the multiple sensing images to obtain a target image includes:

[0092] Aligning the multiple sensing images to the same coordinate system through affine transformation; performing multi-layer discrete wavelet transformation on each aligned image to obtain high-frequency coefficients and low-frequency coefficients of each sensing image; weighting and fusing the high-frequency coefficients of the multiple sensing images to obtain fused high-frequency coefficients, and weighting and fusing the low-frequency coefficients of the multiple sensing images to obtain fused low-frequency coefficients; and performing inverse discrete wavelet transformation on the fused high-frequency coefficients and low-frequency coefficients to obtain a final fused image as the target image.

[0093] In the weighted fusion process, different weight coefficients can be assigned to different sensor images. These weight coefficients are allocated based on the local variance or information entropy of the image. The higher the local variance or information entropy, the higher the assigned weight coefficient. Alternatively, the weight coefficients for different sensor images can be determined based on the factory precision of the different image sensors. For example, a sensor with ±1% precision has a higher weight coefficient than one with ±5%. In other words, the higher the precision, the higher the weight coefficient.

[0094] Optionally, after obtaining the product code of the electronic device in step 152, the chip batch number can also be identified based on the product code. The defect rate of the chip batch number is then calculated. If the defect rate rises to a specified threshold within a specified time period, the batch of materials is determined to be abnormal, and the production line control host issues an alarm message. This alarm message is used to notify the materials department to check the batch of materials. In this way, by triggering an alarm when the defect rate rises rapidly in a short period of time, strict monitoring of materials can be achieved.

[0095] 153. Obtain process parameters associated with the product code of the electronic device.

[0096] Process parameters include, but are not limited to, programmer number, workstation number, operator ID, programming time, programming duration, software version, firmware version, programming ambient temperature, and number of programming failures of the programmer.

[0097] 154. Extract production characteristic data of each programmer based on process parameters, and predict the target failure probability of each programmer based on the production characteristic data.

[0098] Extract production characteristic data for each programmer, such as: recent defect rate, average programming time, frequency of specific error codes, and continuous production time.

[0099] Optionally, in step 154, the specific implementation of predicting the target failure probability of each programmer based on production characteristic data may include:

[0100] The production characteristic data of each programmer is input into a pre-trained prediction model to obtain the first failure probability of each programmer. The target failure probability is then determined based on the first failure probability. The target failure probability refers to the probability that the programmer will fail within the next 24 hours.

[0101] The prediction model can predict the probability of a programmer failure based on the input features. This prediction model can be trained based on a machine learning model, such as a tree model like XGBoost or LightGBM.

[0102] In training the prediction model, the historical feature data X of each burner at each time point (including normal and pre-failure data) is obtained, such as [defect rate, average duration, error code A number, error code B number, running cycle number, …], and the corresponding label y is configured, which is used to define the time point of “failure”. For example, the data within N hours (such as 24 hours) before the failure is marked as 1 (failure), and the stable running data far earlier than the failure is marked as 0 (no failure). The data of the device without failure is always marked as 0. Then the historical feature data X is input into the tree model, so that the model learns to output the probability of being labeled 1 (failure), and a binary classification cross-entropy loss function (Log Loss) is used to iteratively optimize the model.

[0103] Further preferably, the health index of each burner can be predicted according to the production feature data, and the second failure probability is calculated according to the health index, and the average of the first failure probability and the second failure probability is determined as the target failure probability. Compared with directly taking the first failure probability as the target failure probability, the correction according to the health index can further improve the failure prediction accuracy.

[0104] Among them, the implementation of predicting the health index of each burner according to the production feature data can include:

[0105] The production feature data of each burner is input into a pre-trained anomaly detection model to obtain an anomaly score of each burner; and the health index of each burner is calculated according to the anomaly score of each burner. The anomaly detection model is a model trained only using the data of all burners during the normal stable running period, such as an isolation forest (Isolation Forest) or a one-classifier (One-Class SVM) machine learning model. By learning the data pattern of the device in the normal state, the running state deviating from the pattern is regarded as “abnormal”, and the greater the deviation, the lower the health index.

[0106] Specifically, the health index of each burner is calculated as follows:

[0107] After normalizing the anomaly score, subtract 100 to obtain the health index HI:

[0108] HI = max(0, 100 - (Anomaly_Score - Score_min) / (Score_max - Score_min) * 100); wherein Anomaly Score is the anomaly score, Score_min is the minimum value of the anomaly score of all burners, and Score_max is the maximum value of the anomaly score of all burners.

[0109] It should be noted that the second failure probability is negatively correlated with the health index, the higher the health index, the lower the corresponding second failure probability, and the sum of the two is 1. For example, the health index is 0.3, and the corresponding second failure probability is 70%.

[0110] 155、The production line control host controls the target failure probability of the burner to reach the specified probability, and controls the subsequent distribution of the mainboard on the production line to the burner with a target failure probability lower than the specified probability.

[0111] In this way, the subsequent mainboard to be burned can be distributed to the burner with a high health index, and the device with a low health index can be suspended or reduced in production control, and a maintenance work order can be automatically generated. By no longer regarding each burning failure event as an independent accidental event, but associating it with specific device codes and production process data, through calculation and analysis, the change from "after-the-fact remediation" to "before-the-fact prediction and during-the-process intervention" is achieved, so that a data-driven intelligent optimization system can be realized, and the intelligent degree of electronic device production control is improved.

[0112] 160、Collect the current environmental parameters on the production line, and calculate the environmental index value according to the current environmental parameters.

[0113] The current environmental parameters on the production line include but are not limited to environmental data such as temperature, humidity, light intensity, air quality index, oxygen content, carbon dioxide content, particle size distribution, and wind speed in the workshop, as well as various machine running parameters, sensor collection frequency or accuracy on the production line.

[0114] Specifically, in step 160, the current environmental parameters at least include air temperature, average radiant temperature, air flow rate, relative humidity, air pollutant concentration, and device tolerable limit deviation; then according to the current environmental parameters, the environmental index value can be calculated, which can include the following steps 161~164 not shown in the figure:

[0115] 161、According to the air temperature, average radiant temperature, air flow rate and relative humidity in the current environmental parameters, calculate the air thermal comfort index.

[0116] Among them, the core input variables when calculating the thermal comfort index (Predicted Mean Vote, PMV) are four environmental parameters: air temperature (°C); average radiant temperature (°C), which is usually approximately equal to air temperature; air flow rate (m / s); relative humidity (%). The PMV value is between -3 and +3, representing 7 feelings from "cold" to "hot". PMV=0 indicates thermal neutrality, which is the most comfortable.

[0117] 162、According to the air pollutant concentration in the current environmental parameters, calculate the air quality health index.

[0118] First, for each pollutant in the air (such as CO2, PM2.5) 2.5 Total Volatile Organic Compounds (TVOC) are calculated separately as a sub-index of the IAQI. sub :

[0119] IAQI sub = (IAQI high - IAQI low ) / (C high - C low ) * (C - C low ) + IAQI low ;

[0120] Where C represents the measured value of pollutant concentration; C low C high The IAQI is divided into the lower and upper limits of the pollutant concentration range; low IAQI high Corresponding to C respectively low and C high The lower and upper limits of the index value.

[0121] Then, combining IAQI sub Value: The maximum value among all pollutant sub-indices in the air is taken as the current Indoor Air Quality Index (IAQI).

[0122] 163. Calculate the comprehensive index of the equipment's operating environment based on the measured values ​​of all current environmental parameters and the limit deviations that the equipment can withstand.

[0123] First, obtain the ideal range for each measured value in the current environmental parameters, for example, the temperature requirement T. ideal ±ΔT, humidity requirement RH ideal ±ΔRH. Next, the deviation of each measurement value is calculated based on the ideal range, and the deviation of each measurement value is mapped to the interval [0, 1], where 0 represents the ideal and 1 represents the deviation from the tolerance range.

[0124] Deviation T = max(0, min(1, (|T) current - T ideal | -ΔT) / (T tolerance -ΔT) ));where, T current T is the measured value. ideal The ideal value is T, where ΔT is the deviation threshold. tolerance This refers to the maximum tolerance that the equipment can withstand.

[0125] Finally, the deviation degrees of all the measurement values are weightedly fused to obtain a device running environment comprehensive index, which is used to represent the "gap" between the current environment parameters and the ideal environment parameters of the device. The closer the device running environment comprehensive index is to 0, the more suitable the environment is for the device running. The closer the device running environment comprehensive index is to 1, the higher the early warning risk is, and the device may need to be stopped for protection. The weight coefficients of each measurement value are determined according to the importance of the influence of the measurement value on the device, and the weight coefficients of all the measurement values are summed to 1.

[0126] 164、According to the air thermal comfort index, the air quality health index and the device running environment comprehensive index, an environment index value is calculated.

[0127] Specifically, a fuzzy set (such as "comfortable", "uncomfortable"; "good air", "bad air") can be defined for each sub-index, and then the numerical value of each sub-index is converted into a fuzzy concept such as "good", "medium" and "bad". Then, the inference result is converted back to an accurate numerical value through a pre-set rule base, which is the environment index value.

[0128] 170、From a plurality of adjustment models, a target adjustment model corresponding to the environment index value is determined.

[0129] Considering that the requirements for the production line control parameters are different under different production environments, for example, in the case of too high humidity in the workshop, the data transmission rate during burning should be appropriately accelerated to prevent the device components from being affected by humidity and thus affecting the final yield. Therefore, in the embodiments of the present application, different adjustment models corresponding to different environment index values are configured, which are equivalent to different optimization systems. Thus, different adjustment models can be adaptively called to optimize the control parameters under different environments.

[0130] Specifically, the current environment level can be determined according to the environment index value, and then one adjustment model corresponding to the current environment level is selected from a plurality of pre-trained adjustment models as a target adjustment model. For example, when the environment index value is 15, it is determined that the environment level is in the range [0, 30], and the corresponding environment level is level one. When the environment index value is 40, it is determined that the environment level is in the range [30, 60], and the corresponding environment level is level two. Similarly, one or more adjustment models can be stored for each environment level. When there are multiple corresponding adjustment models, one of them is randomly selected or selected according to the user's demand. Optionally, when there are multiple corresponding adjustment models, the production line control host can pop up multiple options on the user interface, and the multiple options correspond to the multiple adjustment models one by one. Then, a selection instruction input by the user is received, and the target adjustment model selected by the user is determined according to the selection instruction.

[0131] Different adjustment models can be obtained in advance based on different machine learning models, such as deep learning, linear regression, support vector machine, decision tree, neural network, etc. Specifically, the training of the adjustment model of the production line control parameter can include the following steps S1-S3 which are not shown in the figure:

[0132] S1, obtain historical burning data on the electronic device production line, and obtain sample feature vectors at multiple sampling time points through feature extraction based on the historical burning data.

[0133] The historical burning data can be burning data in a historical period (such as the past week or the past half month), and the sample feature vector is the same as the target feature vector, including a vector composed of multiple feature values such as burning parameters, cumulative defect rate, and verification failure rate. Interval sampling refers to determining multiple discrete sampling time points from the historical period at a preset time interval, and obtaining sample feature vectors corresponding to each sampling time point.

[0134] According to the historical burning data, the sample feature vectors at the multiple sampling time points can be obtained through feature extraction, which can include:

[0135] Calculate the variance of each feature in the current burning data; retain the feature column with a variance greater than a preset threshold as a candidate feature; calculate the importance of each candidate feature in descending order, and select the top N features in descending order as principal components; feature extraction is performed on the historical burning data according to the principal components to obtain sample feature vectors at multiple sampling time points.

[0136] Wherein, for a single feature X j = [x1, x2, …, x n ], n is the number of samples, and the variance is calculated as:

[0137] ;

[0138] Wherein, is the value of the i-th sample on the feature, is the mean value of all samples of the feature. The greater the variance, the more obvious the fluctuation of the feature value between different samples, and the more useful information it may contain; the variance close to zero indicates that the feature is almost a constant.

[0139] Wherein, the principal component represents the main and key feature, and by selecting representative features, the dimensionality of the data can be reduced, and the reliability, accuracy and interpretability of the prediction result can be improved.

[0140] S2, obtain the corresponding optimization control parameters at each sampling time point as label data.

[0141] The burning parameters on the production line directly affect the yield of the electronic devices produced. At each sampling time, the ideal optimization control parameters can be calculated as label data for model training.

[0142] S3. According to the sample feature vectors at each sampling time and the corresponding label data, the constructed machine learning model is trained to obtain an adjustment model of the production line control parameters.

[0143] Specifically, during training, the sample feature vectors are divided into a training set and a validation set. First, the sample feature vectors in the training set are input into the constructed machine learning model, and the predicted control parameters corresponding to each sample feature vector output by the machine learning model are obtained. Then, the loss value between the predicted control parameters and the label data is calculated, and the weight parameters of the machine learning model are iterated according to the loss value until the performance index of the machine learning model on the validation set reaches a specified performance threshold, and the training is completed to obtain the adjustment model of the production line control parameters.

[0144] 180. Determine a target feature vector according to the current burning data on the production line, input the target feature vector into the target adjustment model, and obtain the target control parameters on the production line.

[0145] 190. Adjust the current control parameters of the production line to the target control parameters.

[0146] The current burning data refers to the burning data at the current time on the production line. The target feature vector includes the feature values of multiple specified features, such as the values of the specified features of the burning parameters, the cumulative defective rate, and the verification failure rate, which can be determined according to the current burning data. The cumulative defective rate and the verification failure rate can be calculated according to the number of defective products of the electronic device burning. The burning parameters include but are not limited to the clock frequency, the timing (such as the SWD clock delay of STMicro), the burning voltage (the power supply voltage of the burning interface (such as UART, SWD, JTAG), the burning voltage fluctuation, the threshold of high and low levels (such as the matching of TTL and CMOS levels), the data transmission rate (such as the baud rate), the storage path of the composite firmware package, the burning address, the erasing mode (full chip erasing, sector erasing, or retaining part of the data (such as Bootloader)), the burning mode (full automatic, differential burning (only writing the changed part), or forced burning), and the like.

[0147] The target control parameters include not only the optimized burning parameters after the adjustment model, but also various machine running parameters on the production line, the collection frequency or accuracy of the sensors, and the like.

[0148] Through the above steps 140-190, the target feature vector can be calculated according to the current burning parameter when it is judged that the electronic device is burned badly in the production process, and the optimized burning parameter is predicted through the machine learning model, so as to realize real-time dynamic adjustment of the burning parameter. Compared with the fixed control parameter, the intelligent control ability of the production line can be improved, and dynamic adaptation to the production process is realized.

[0149] As shown in Figure 2 The embodiment of the application discloses a production control device of an electronic device, which comprises a burning unit 201, a running unit 202, and an upgrading unit 203.

[0150] The burning unit 201 is used for burning a preset composite firmware package to the mainboard of the electronic device through a burning tool in the production process; wherein the composite firmware package comprises a production firmware and a delivery firmware embedded in the form of an independent partition image; the production firmware is a firmware on the production line, and the delivery firmware is a firmware when leaving the factory;

[0151] The running unit 202 is used for controlling the electronic device to start and run the production firmware, and performing hardware calibration and function test on the electronic device in the running environment of the production firmware;

[0152] The upgrading unit 203 is used for sending a starting instruction to the electronic device after the whole machine coupling of the electronic device is completed, so as to make the electronic device upgrade the production firmware to the delivery firmware.

[0153] As an optional implementation, the production control device further comprises the following units not shown in the figure:

[0154] The judging unit is used for judging whether the electronic device normally restarts and runs the delivery firmware after the upgrading unit sends the starting instruction to the electronic device, so as to make the electronic device upgrade the production firmware to the delivery firmware;

[0155] The determining unit is used for determining that the electronic device is burned badly when the judging unit judges that the electronic device cannot normally restart or run the delivery firmware;

[0156] The collecting unit is used for collecting current environmental parameters on the production line;

[0157] The environmental calculation unit is used for calculating an environmental index value according to the current environmental parameters;

[0158] The calling unit is used for determining a target adjustment model corresponding to the environmental index value from a plurality of adjustment models;

[0159] The feature extraction unit is used for determining a target feature vector according to current burning data on the production line;

[0160] The parameter optimization unit is used for inputting the target feature vector into the target adjustment model to obtain a target control parameter on the production line.

[0161] a parameter adjusting unit configured to adjust a current control parameter of the production line to a target control parameter.

[0162] As an optional implementation, the production control device further comprises the following units not shown in the figure:

[0163] an acquisition unit configured to acquire a plurality of sensing images collected by different image sensing devices on the production line for the electronic device after the determination unit determines that the electronic device is burned in poorly;

[0164] a fusion unit configured to fuse the plurality of sensing images to obtain a target image;

[0165] an identification unit configured to identify the target image to obtain a product code of the electronic device;

[0166] a correlation unit configured to acquire a process parameter associated with the product code of the electronic device;

[0167] an extraction unit configured to extract production characteristic data of each burner according to the process parameter;

[0168] a prediction unit configured to predict a target failure probability of each burner according to the production characteristic data;

[0169] a control unit configured to control the burners whose target failure probability reaches a specified probability to be automatically locked, and control subsequent motherboards on the production line to be distributed to the burners whose target failure probability is lower than the specified probability.

[0170] As an optional implementation, the prediction unit described above comprises the following sub-units not shown in the figure:

[0171] a prediction sub-unit configured to input the production characteristic data of each burner into a pre-trained prediction model to obtain a first failure probability of each burner;

[0172] a determination sub-unit configured to determine the target failure probability according to the first failure probability.

[0173] Further optionally, the determination sub-unit described above comprises the following modules not shown in the figure:

[0174] a prediction module configured to predict a health index of each burner according to the production characteristic data;

[0175] a calculation module configured to calculate a second failure probability according to the health index;

[0176] a correction module configured to determine an average value of the first failure probability and the second failure probability as the target failure probability.

[0177] As an optional implementation, the prediction unit described above comprises the following sub-units not shown in the figure: Figure 3As shown, the embodiment of the present application discloses a control device, comprising a memory 301 storing executable program codes and a processor 302 coupled with the memory 301;

[0178] The processor 302 calls the executable program codes stored in the memory 301 to execute the production control method of the electronic device described in each of the above embodiments.

[0179] The embodiment of the present application also discloses a computer readable storage medium storing a computer program, wherein the computer program enables the computer to execute the production control method of the electronic device described in each of the above embodiments.

[0180] The above embodiments are intended to exemplarily reproduce and deduce the technical solutions of the present application, and to completely describe the technical solutions, objects and effects of the present application, so as to make the public more thoroughly and comprehensively understand the disclosed content of the present application, and not to limit the protection scope of the present application.

[0181] The above embodiments are not based on the exhaustive enumeration of the present application, and there can be a plurality of other embodiments not listed. Any replacement and improvement made without violating the concept of the present application is within the protection scope of the present application.

Claims

1. A production control method of an electronic device, characterized by, The method comprises the following steps: In the production process, a preset composite firmware package is burned into the mainboard of the electronic device by a burning tool; the composite firmware package comprises a production firmware and a delivery firmware embedded in the form of independent partition images; the production firmware is a firmware on the production line, and the delivery firmware is a firmware at the time of delivery; the device flash memory of the mainboard of the electronic device comprises a system partition for running a system, a preset partition for storing a delivery firmware image file, and a calibration data partition for storing calibration data, which are independent of each other; the production firmware is burned into the system partition, and the delivery firmware is burned into the preset partition; The electronic device is controlled to start and run the production firmware, and hardware calibration and function test are performed on the electronic device in the running environment of the production firmware; In the whole machine test link after the whole machine of the electronic device is coupled and assembled into a complete device, the electronic device is remotely logged in through a network and a start instruction is sent to the electronic device, so that after the electronic device receives the start instruction, a preset self-upgrade script is executed to complete a self-upgrade operation of upgrading the production firmware to the delivery firmware; in the process of executing the firmware self-upgrade, the content of the delivery firmware is overwritten to the system partition; It is judged whether the electronic device normally restarts and runs the delivery firmware; If the electronic device cannot normally restart or run the delivery firmware, it is determined that the electronic device is burned badly; Current environmental parameters on the production line are collected, and an environmental index value is calculated according to the current environmental parameters; A target adjustment model corresponding to the environmental index value is determined from a plurality of adjustment models; A target feature vector is determined according to current burning data on the production line, the target feature vector is input into the target adjustment model, and a target control parameter on the production line is obtained; The current control parameter of the production line is adjusted to the target control parameter; The current environmental parameters at least include air temperature, average radiant temperature, air flow rate, relative humidity, pollutant concentration in air, and limit deviation that the device can withstand; the environmental index value is calculated according to the current environmental parameters, which comprises: An air thermal comfort index is calculated according to the air temperature, the average radiant temperature, the air flow rate, and the relative humidity; An air quality health index is calculated according to the pollutant concentration in air; A device running environment comprehensive index is calculated according to the measurement values of all current environmental parameters and the limit deviation that the device can withstand; An environmental index value is calculated according to the air thermal comfort index, the air quality health index, and the device running environment comprehensive index; The device running environment comprehensive index is calculated according to the measurement values of all current environmental parameters and the limit deviation that the device can withstand, which comprises: An ideal range corresponding to each measurement value in the current environmental parameters is obtained, and the deviation degree of each measurement value is calculated according to the ideal range; Each measurement value is mapped to the [0, 1] interval; The deviation degrees of all mapped measurement values are weighted and fused to obtain the device running environment comprehensive index.

2. The production control method of an electronic device according to claim 1, characterized by, After it is determined that the electronic device is burned badly, the method further comprises: Acquiring a plurality of sensing images collected by different image sensing devices on a production line for the electronic device; Fusing the plurality of sensing images to obtain a target image, and identifying the target image to obtain a product code of the electronic device; Acquiring process parameters associated with the product code of the electronic device; Extracting production feature data of each burner according to the process parameters, and predicting a target failure probability of each burner according to the production feature data; Controlling burners with a target failure probability reaching a specified probability to be automatically locked, and controlling subsequent mainboards on the production line to be distributed to burners with a target failure probability lower than the specified probability.

3. The production control method of an electronic device according to claim 2, wherein The method comprises the following steps: Inputting the production feature data of each burner into a pre-trained prediction model to obtain a first failure probability of each burner; Determining a target failure probability according to the first failure probability.

4. The production control method of an electronic device according to claim 3, characterized by, The method comprises the following steps: Predicting a health index of each burner according to the production feature data; Calculating a second failure probability according to the health index; Determining an average value of the first failure probability and the second failure probability as the target failure probability.

5. An apparatus for production control of an electronic device, characterized by comprising: The method comprises the following steps: A burning unit is configured to burn a preset composite firmware package to an electronic device mainboard through a burning tool during a production process; the composite firmware package comprises a production firmware and a delivery firmware embedded in the form of an independent partition image; the production firmware is a firmware on a production line, and the delivery firmware is a firmware at the time of delivery; a device flash memory of the electronic device mainboard comprises a system partition for running a system, a preset partition for storing a delivery firmware image file, and a calibration data partition for storing calibration data; the production firmware is burned to the system partition, and the delivery firmware is burned to the preset partition; A running unit is configured to control the electronic device to start and run the production firmware, and perform hardware calibration and function test on the electronic device in the running environment of the production firmware; An upgrading unit is configured to remotely log in the electronic device through a network and send a start instruction to the electronic device in a whole device test link after the electronic device is completely coupled and assembled into a complete device, so that the electronic device executes a preset self-upgrading script to complete a self-upgrading operation of upgrading the production firmware to the delivery firmware after receiving the start instruction; the electronic device covers the content of the delivery firmware to the system partition in the process of executing the firmware self-upgrading; A judging unit is configured to judge whether the electronic device is normally restarted and runs the delivery firmware after the upgrading unit sends the start instruction to the electronic device to make the electronic device upgrade the production firmware to the delivery firmware; A determining unit is configured to determine that the electronic device is burned badly when the judging unit judges that the electronic device cannot be normally restarted or run the delivery firmware; An acquisition unit is configured to acquire a current environment parameter on a production line; An environment calculation unit is configured to calculate an environment index value according to the current environment parameter; The calling unit is configured to determine a target adjustment model corresponding to the environment index value from a plurality of adjustment models; The feature extraction unit is configured to determine a target feature vector according to current burning data on the production line; The parameter optimization unit is configured to input the target feature vector into the target adjustment model to obtain a target control parameter on the production line; The parameter adjustment unit is configured to adjust a current control parameter of the production line to the target control parameter; The current environment parameters at least include air temperature, average radiation temperature, air flow rate, relative humidity, pollutant concentration in air, and limit deviation that can be borne by the equipment; the environment calculation unit is specifically configured to calculate an air thermal comfort index according to the air temperature, the average radiation temperature, the air flow rate, and the relative humidity; calculate an air quality health index according to the pollutant concentration in air; calculate an equipment operation environment comprehensive index according to the measured values of all the current environment parameters and the limit deviation that can be borne by the equipment; and calculate an environment index value according to the air thermal comfort index, the air quality health index, and the equipment operation environment comprehensive index. The environment calculation unit is configured to calculate an equipment operation environment comprehensive index according to the measured values of all the current environment parameters and the limit deviation that can be borne by the equipment, and the manner is specifically as follows: an ideal range corresponding to each measured value in the current environment parameters is obtained, the deviation degree of each measured value is calculated according to the ideal range; the deviation degree of each measured value is mapped into the [0, 1] interval; and the deviation degrees of all the mapped measured values are weighted and fused to calculate and obtain the equipment operation environment comprehensive index.

6. A control device characterized by comprising: The computer readable storage medium stores a computer program, and the computer program causes the computer to execute the production control method of the electronic device.

7. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program causes the computer to execute the production control method of the electronic device.

Images