A belt scale metering and control linkage method, system, device and storage medium

Abstract

The present application discloses a metering and interlocking control method, system, device and storage medium for a belt scale. The method includes: receiving a job task in real time and starting a job process matching the job task; determining a job target quantity according to the received job task; determining a job target lead quantity according to the received job task and the job process matching the job task; after the job process is started, controlling the loading and unloading equipment at the starting end to perform loading and unloading operations, starting the belt, the bifurcated hopper, the belt scale at the starting end and the belt scale at the stopping end for metering according to the job process; monitoring in real time whether the metering of the belt scale at the starting end reaches the job target lead quantity. If the job target lead quantity is reached, a signal instruction to stop the loading and unloading operation is generated; or monitoring in real time whether the metering of the belt scale at the stopping end reaches the job target lead quantity. If the job target lead quantity is reached, a signal instruction to stop feeding the bifurcated hopper is generated. The present application can achieve efficient and accurate loading and unloading operations in a process-based operation.

Description

Technical Field

[0001] This application relates to the technical field of belt scale optimization control, and specifically relates to a belt scale metering and interlocking control method, system, device, and storage medium. Background Art

[0002] In the bulk cargo loading and unloading operations, such as the cargo loading and unloading at ports, highly streamlined operations have become the key technical means to improve the loading and unloading efficiency and reduce costs. By reasonably arranging the operation process, the continuity and stability of the loading and unloading operations have been improved. However, due to the relatively single traditional operation process management method, it is difficult to accurately control the material supply and operation process. Therefore, in the process of automated bulk cargo loading and unloading operations, how to improve the accuracy and stability of the operations has always been a technical difficulty.

[0003] Currently, the common methods include manually adjusting the material supply volume and making manual interventions according to the actual situation, as well as using fixed operation process parameters for automated control. Although the manual adjustment method can better adapt to the changes at the operation site, due to the need for manual operation, the operation efficiency is low and the labor cost is high. The automated control with fixed parameters reduces the manual intervention to a certain extent, but due to the complexity and variability of the operation environment, the fixed parameters are difficult to meet the requirements of different scenarios, so there are great limitations in practical applications.

[0004] Although the above common methods can meet the basic needs of bulk cargo loading and unloading operations to a certain extent, there are problems of interrupting the material supply multiple times or starting and stopping the operation process multiple times when achieving the accurate control of the operation target volume, which increases the difficulty of realizing the unmanned operation mode and also increases the operation energy consumption, thus affecting the overall operation efficiency. Therefore, how to achieve efficient and accurate material supply control in the streamlined operations is a technical problem to be solved urgently. Summary of the Invention

[0005] In order to achieve efficient and accurate loading and unloading operations in the streamlined operations, this application provides a belt scale metering and interlocking control method, system, device, and storage medium.

[0006] In the first aspect, this application provides a belt scale metering and interlocking control method, including:

[0007] Receiving the operation task in real time and starting the operation process matching the operation task; wherein, different operation tasks are all pre-set with the operation processes matching them;

[0008] Determining the operation target volume according to the received operation task;

[0009] Determine the operation target lead based on the received operation task and the operation process matching the operation task, including: constructing a first neural network using a deep learning algorithm, inputting the received operation task and the operation process matching the operation task into the first neural network, and obtaining the operation target lead; the first neural network is trained and generated by historical operation tasks, operation processes matching historical operation tasks, and expert-recommended operation target leads under historical corresponding conditions;

[0010] After the operation process is started, control the loading and unloading equipment at the starting end to perform loading and unloading operations, start the belt and the bifurcated hopper, and measure the weights using the belt scale at the starting end and the belt scale at the stopping end according to the corresponding control of the operation process;

[0011] Monitor in real time whether the measurement of the belt scale at the starting end reaches the operation target lead. If it reaches the operation target lead, generate a signal instruction to stop the loading and unloading operation to control the loading and unloading equipment at the starting end to stop the loading and unloading operation; or monitor in real time whether the measurement of the belt scale at the stopping end reaches the operation target lead. If it reaches the operation target lead, generate a signal instruction to stop feeding the bifurcated hopper to control the bifurcated hopper to stop feeding.

[0012] By adopting the above solution, a deep learning algorithm is used to dynamically obtain the operation target lead matching the operation task. When the measurement at the starting end reaches the operation target lead, the loading and unloading equipment at the starting end is enabled to stop the operation in a timely manner, or when the measurement at the stopping end reaches the operation target lead, the bifurcated hopper is enabled to stop the operation in a timely manner, reducing the situation of starting and stopping the operation process multiple times, achieving precise control of the operation process, and ensuring a high degree of matching between the material weight and the target quantity.

[0013] Preferably, the operation process is divided into a first classification operation process in which only the main process participates in the operation and a second classification operation process in which sub-processes participate in the operation;

[0014] When the matching operation process is the first classification operation process, directly compare whether the measurement of the belt scale at the starting end reaches the operation target lead. If it reaches the operation target lead, generate a signal instruction to stop the loading and unloading operation to control the loading and unloading equipment at the starting end to stop the loading and unloading operation;

[0015] When the matching operation process is the second classification operation process, respectively judge whether the measurement of the belt scale at the stopping end corresponding to each sub-process of the second classification operation process reaches the target lead corresponding to each sub-process. When the measurement of the belt scale at the stopping end corresponding to each sub-process reaches the operation target lead, generate a signal instruction to stop feeding the bifurcated hopper to control the bifurcated hopper to stop feeding the material transfer path corresponding to the sub-process.

[0016] By adopting the above solution, the first classification operation process and the second classification operation process are intelligently distinguished according to different operation tasks. For the first classification operation process, it is directly compared whether the operation target lead is reached to determine whether to stop the loading and unloading equipment at the starting end, ensuring the precise control of the target quantity to be completed at one time. For the second classification operation process, it is monitored whether the metering of the belt scale at the stopping end corresponding to each sub-process reaches the target lead corresponding to each sub-process, effectively realizing the precise operation control of multiple processes in synchronization.

[0017] Preferably, it further includes:

[0018] Receiving the operation environment in real time; the operation environment includes temperature, humidity and vibration conditions;

[0019] The determination of the operation target lead according to the received operation task and the operation process matching the operation task further includes: constructing a second neural network using a deep learning algorithm, inputting the received operation task and the operation process matching the operation task into the second neural network to replace the input into the first neural network, and obtaining the operation target lead; the second neural network is trained and generated by historical operation tasks, operation processes matching historical operation tasks, historical operation environments and expert-recommended operation target leads under historical corresponding conditions.

[0020] By adopting the above solution, considering the influence of different operation environments on material transmission, the operation target lead is dynamically adjusted comprehensively considering the operation environment, operation task and the operation process corresponding to the operation task, improving the accuracy and adaptability of the operation process, and ensuring precise control can be achieved under various operation environments.

[0021] Preferably, it further includes:

[0022] Monitoring the metering of the belt scale at the stopping end in real time. If it is detected that the metering value of the belt scale at the stopping end is lower than the minimum metering value within the first preset time period or the change amount continuously remains lower than the preset change amount within the second preset time period, it is determined that the process is running empty, and a process stop instruction is generated.

[0023] By adopting the above solution, considering the situation of the process running empty, the situation of the process running empty is judged in time according to the metering result and the operation is interrupted in time, avoiding ineffective operation and reducing energy consumption.

[0024] Preferably, it further includes:

[0025] Monitoring the operation data of the loading and unloading equipment, belt and bifurcated bucket at the starting end in real time;

[0026] Construct a third neural network using deep learning algorithms, and input the job tasks, job processes, operation data, metering values of the starting belt scale, and metering values of the stopping belt scale into the third neural network in real time to output the prediction result of whether the belt scale metering is abnormal; the third neural network is trained and generated by using the historical job tasks, job processes, operation data, metering values of the starting belt scale, and metering values of the stopping belt scale with abnormal belt scale metering

[0027] When the prediction result of whether the belt scale metering is abnormal is that there is an abnormal risk, generate a process stop instruction and at the same time generate a belt scale metering abnormal prompt message

[0028] By adopting the above solution, comprehensively considering the operation conditions of the job equipment and the metering values of the belt scale to predict the possible occurrence of abnormal belt scale metering and pre-stop the relevant operations in advance, reducing the operation losses caused by metering abnormalities and improving the overall operation efficiency

[0029] Preferably, it further includes:

[0030] Before generating a signal instruction to stop the loading and unloading operation after determining that the metering of the starting belt scale reaches the job target lead in real-time monitoring, continue to determine whether the difference between the material weight between the starting loading end of the belt and the starting belt scale and the difference between the job target amount and the job lead amount is not greater than a preset difference. When it is not greater than the preset difference, then execute the generation of a signal instruction to stop the loading and unloading operation; among them, the obtaining steps of the material weight between the starting loading end of the belt and the starting belt scale include:

[0031] Use the sensor installed between the starting loading end of the belt and the starting belt scale to obtain the first material weight; use the imaging device to collect the images between the starting loading end of the belt and the starting belt scale, use image recognition technology to identify the material type and material size, and calculate the second material weight according to the material type and material size

[0032] Compare whether the difference between the first material weight and the second material weight is greater than the second preset difference. If it is greater, then re-obtain the first material weight using the spare sensor installed between the starting loading end of the belt and the starting belt scale or re-calculate and obtain the second material weight using image recognition technology, and then re-compare whether the difference between the first material weight and the second material weight is greater than the second preset difference. Repeat the steps of re-obtaining the first material weight and the second material weight and comparing them until the difference between the first material weight and the second material weight is not greater than the second preset difference; perform weighted calculation according to the first material weight and the second material weight to obtain the material weight between the starting loading end of the belt and the starting belt scale

[0033] By adopting the above solution, the accuracy and reliability of material weight measurement are ensured, the problem of inaccurate metering caused by single sensor failure or measurement error is avoided, and the accuracy and reliability of the overall operation process are improved.

[0034] Preferably, it further includes:

[0035] Design a visual interaction interface setting to display the metering values of the starting-end belt scale and the stopping-end belt scale in real time during the operation process.

[0036] By adopting the above solution, it helps the operator to monitor the progress of the operation process in real time, ensure timely grasp of the metering status of the belt scale, and thus improve the operation efficiency and accuracy.

[0037] In a second aspect, the present application provides a belt scale metering interlocking control system, including:

[0038] An operation process acquisition module, configured to receive operation tasks in real time and start an operation process matching the operation task; wherein, different operation tasks are each preset with an operation process matching it;

[0039] An operation target quantity acquisition module, configured to determine the operation target quantity according to the received operation task;

[0040] An operation target advance quantity acquisition module, configured to determine the operation target advance quantity according to the received operation task and the operation process matching the operation task, including: constructing a first neural network using a deep learning algorithm, inputting the received operation task and the operation process matching the operation task into the first neural network to obtain the operation target advance quantity; the first neural network is trained and generated by historical operation tasks, operation processes matching historical operation tasks, and expert-recommended operation target advance quantities under historical corresponding conditions;

[0041] An operation running module, configured to, after the operation process is started, control the starting-end loading and unloading equipment to perform loading and unloading operations, start the belt, the bifurcated hopper, the starting-end belt scale and the stopping-end belt scale for metering respectively according to the operation process;

[0042] An operation running monitoring module, configured to monitor in real time whether the metering of the starting-end belt scale reaches the operation target advance quantity. If the operation target advance quantity is reached, a signal instruction to stop the loading and unloading operation is generated to control the starting-end loading and unloading equipment to stop the loading and unloading operation; or monitor in real time whether the metering of the stopping-end belt scale reaches the operation target advance quantity. If the operation target advance quantity is reached, a signal instruction to stop feeding of the bifurcated hopper is generated to control the bifurcated hopper to stop feeding.

[0043] By adopting the above solution, efficient and accurate loading and unloading operations are realized in the process-based operation.

[0044] In a third aspect, the present application provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the method as described above.

[0045] In a fourth aspect, the present application provides a computer device, which includes a memory, a processor, and a program stored and executable on the memory. When the program is executed by the processor, it implements the steps of the method as described above.

[0046] In summary, the present application has the following beneficial effects:

[0047] 1. By receiving job tasks in real time and starting the job processes that match them, using deep learning algorithms to more accurately determine the lead of job targets, it is realized that the loading and unloading equipment at the starting end automatically stops loading materials when reaching the lead of the target, ensuring accurate loading and unloading in one go.

[0048] 2. Using deep learning algorithms to construct neural networks, automatically adjusting the lead of job targets according to different job environments, job tasks, and job processes, significantly improving the accuracy and stability of jobs.

[0049] 3. After the job process is started, the metering value of the belt scale is monitored in real time and the loading and unloading equipment at the starting end is automatically controlled to stop working according to preset conditions, significantly improving job efficiency and reducing job energy consumption and costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a flowchart of a method for joint control of belt scale metering in a specific embodiment;

[0051] Figure 2 It is a flowchart under specific different job tasks in a method for joint control of belt scale metering in a specific embodiment;

[0052] Figure 3 It is a schematic structural diagram of a system for joint control of belt scale metering in a specific embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] In order to make the objectives, technical solutions, and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0054] As Figure 1 shown, the embodiments of the present application disclose a method for joint control of belt scale metering, and the specific steps are as follows:

[0055] S1. Receive job tasks in real time and start the job processes that match the job tasks.

[0056] Specifically, taking the cargo handling operation at a port as an example, different operation tasks are set according to the handling requirements, and corresponding operation processes are also preset for different operation tasks and stored in the database.

[0057] Among them, the operation tasks include: operation objects, that is, operation requirement contents such as specific types of cargo to be handled, operation duration, operation target quantity, etc. The operation process can be drawn and matched by humans according to the operation tasks, and can also be divided according to whether the operation tasks need to be diverted. The main divisions include: the first classification operation process with only the main process participating in the operation, and the second classification operation process with sub-processes participating in the operation. For example, if the ratio of the operation target quantity to the operation duration is greater than the preset ratio value, then multi-process synchronous handling operations are required accordingly. Otherwise, a single main process can directly complete the operation.

[0058] Receive the operation tasks uploaded by the user in real time, match the operation processes matching the operation tasks, and automatically start the corresponding operation processes.

[0059] S2. Determine the operation target quantity according to the received operation tasks.

[0060] Query and obtain the operation target quantity in the operation tasks based on the received operation tasks. Specifically, the query method can be to traverse and query in the operation tasks using the unique identifier preset for the operation target quantity.

[0061] S3. Determine the operation target advance according to the received operation tasks and the operation processes matching the operation tasks.

[0062] Specifically, considering that when the loading and unloading equipment or the bifurcated bucket at the starting end stops, the goods or materials remaining on the conveyor belt have not been weighed by the end belt scale. In order to more accurately achieve precise loading and unloading, an operation target advance is set, and when this operation target advance is reached, the operation of the loading and unloading equipment or the bifurcated bucket at the starting end is stopped in a timely manner. Therefore, the operation target advance is determined in advance.

[0063] Considering that the operation target advance can be obtained by users or experts based on experience or by analyzing conveyor belt speed, conveyor belt width, density of goods or materials, and time, etc. In order to obtain the corresponding operation target advance for different operations, a first neural network is constructed using a deep learning algorithm. The input of the first neural network model is the operation tasks and the operation processes matching the operation tasks, and the output is the operation target advance. Specifically, it is trained and generated through historical operation tasks, operation processes matching historical operation tasks, and expert-recommended operation target advance under historical corresponding conditions. The received operation tasks and the operation processes matching the operation tasks are input into the first neural network to obtain the operation target advance under the corresponding conditions.

[0064] Among them, since there is also a second classification operation process in the operation process matching the historical operation task, there is an operation target lead corresponding to each sub-process set by experts under the historical corresponding conditions for this classification operation process. Therefore, the input is the operation task, the second classification operation process is matched with the operation task, and the output is the operation target lead corresponding to each sub-process.

[0065] S4. After the operation process is started, perform operations according to the operation process.

[0066] Specifically, control the loading and unloading equipment at the starting end to perform loading and unloading operations according to the operation process, that is, the loading and unloading equipment at the starting end starts to load the process, and the loading and unloading operation officially starts; while performing the loading and unloading operation, control the starting belt and the bifurcated hopper according to the operation process, that is, start the belt to run, and if there is a sub-process, start the bifurcated hopper correspondingly; according to the operation process, while starting the belt, start the belt scale at the starting end and the belt scale at the stopping end simultaneously to measure the weight of the goods or materials.

[0067] S5. During the process of performing operations according to the operation process, monitor the measurement value of the belt scale at the starting end or the belt scale at the stopping end in real time, and control the operation or stop of the operation based on the detection result.

[0068] During the process of performing operations according to the operation process, monitor in real time whether the measurement of the belt scale at the starting end reaches the operation target lead. If it reaches the operation target lead, generate a signal instruction to stop the loading and unloading operation to control the loading and unloading equipment at the starting end to stop the loading and unloading operation; or monitor in real time whether the measurement of the belt scale at the stopping end reaches the operation target lead. If it reaches the operation target lead, generate a signal instruction to stop feeding the bifurcated hopper to control the bifurcated hopper to stop feeding.

[0069] Specifically, as Figure 2 shown, when the matched operation process is the first classification operation process, due to the simple process, it is possible to directly compare whether the measurement of the belt scale at the starting end reaches the operation target lead. If it reaches the operation target lead, generate a signal instruction to stop the loading and unloading operation to control the loading and unloading equipment at the starting end to stop the loading and unloading operation, ensuring one-time loading and unloading in place.

[0070] As Figure 2As shown, when the matching operation process is the second classification operation process, since the process is relatively complex, metering only starts from the belt start-up. Subsequently, due to reasons such as diversion after the diversion, there may be situations such as cargo loss. It is more accurate to confirm whether the metering of the belt scale at the stop end corresponding to each sub-process in the end reaches the operation target lead. Therefore, it is determined separately whether the metering of the belt scale at the stop end corresponding to each sub-process of the second classification operation process reaches the target lead corresponding to each sub-process. If the metering of the belt scale at the stop end corresponding to each sub-process reaches the operation target lead, a signal instruction to stop the bifurcated bucket from feeding the material to this sub-process is generated to control the bifurcated bucket to stop feeding the material to the material transmission path corresponding to this sub-process.

[0071] In a specific embodiment, considering that different operating environments will affect the execution of operating tasks. For example, different temperatures and humidities will affect the metering of goods or materials on the belt, resulting in different actual weights from the required weights. Or due to the problem of the service life of the belt, different belt transmission vibrations or other environmental vibrations will affect the metering of the belt scale for the goods or materials on the belt. Therefore, in order to further achieve precise loading and unloading, the method further includes:

[0072] Receiving the operating environment in real time; the operating environment includes temperature, humidity, vibration conditions, and the service life of the belt, etc. Specifically, vibration sensors installed on the belt can be used to collect the operating environment data of the current operation.

[0073] The determining the operation target lead according to the received operation task and the operation process matching the operation task further includes:

[0074] Constructing a second neural network using a deep learning algorithm. The input of the second neural network is the operating environment, the operation task, and the operation process matching the operation task, and the output is the operation target lead, which is generated by training with historical operation tasks, the operation processes matching the historical operation tasks, historical operating environments, and the expert-recommended operation target leads under historical corresponding conditions.

[0075] Inputting the received operation task and the operation process matching the operation task into the second neural network to replace the input into the first neural network, and obtaining the operation target lead.

[0076] In addition, to ensure accuracy while reducing the amount of calculation, it can be set that there is an environmental data mutation in the operation environment received in real time compared with the operation environment received at the previous moment, that is, the difference of at least one environmental data is greater than the preset difference of the corresponding environmental data or the similarity of at least one environmental data is less than the preset similarity of the corresponding environmental data. For example, the temperature difference is greater than the preset temperature difference, and the similarity of the vibration signal is less than the preset similarity of the vibration signal; then the received operation task and the operation process matching the operation task are input into the second neural network to replace the input into the first neural network. Otherwise, the first neural network is continued to be used to obtain the operation target lead.

[0077] In a specific embodiment, considering that there may be situations where goods or materials are not transferred in time or there are belt failures, etc., resulting in an empty process, in order to avoid ineffective operations, interrupt the current operation in time, and improve the overall efficiency; the method further includes:

[0078] Real-time monitor the metering of the belt scale at the outage end; if it is detected that the metering value of the belt scale at the outage end is lower than the minimum metering value within the first preset time period, it indicates that no goods or materials are detected currently, or if the change amount is continuously lower than the preset change amount within the second preset time period, it indicates that the weight of any goods or materials detected currently has not changed, then it is determined that the process is empty, a process stop instruction is generated, and the operation ends.

[0079] Specifically, as Figure 2 shown, when the matching operation process is the first classification operation process, after the belt scale metering at the outage end detects that the process is empty, a process stop instruction is automatically generated, and the main process automatically stops running completely, and the operation ends.

[0080] When the matching operation process is the second classification operation process, after the belt scale metering corresponding to the sub-process detects that the process is empty, a process stop instruction for the corresponding sub-process is automatically generated, and the sub-process automatically stops running, and the operation of this operation line ends.

[0081] In a specific embodiment, considering that abnormal belt scale metering may occur when the operating equipment fails or the metering equipment fails, in order to achieve accurate loading and unloading operations, predict abnormal situations and stop operations in time, and avoid ineffective operations, the method includes:

[0082] Real-time monitor the operation data of the loading and unloading equipment, belt, and bifurcation hopper at the starting end;

[0083] To comprehensively predict abnormal situations, a third neural network is constructed using deep learning algorithms. The inputs of the third neural network are the operation tasks, operation processes, operation data of the loading equipment at the starting end, the belt, the bifurcated hopper, the metering value of the belt scale at the starting end, and the metering value of the belt scale at the stopping end. The output is whether there is an abnormality in the belt scale metering, which is specifically generated through training with the historical operation tasks, operation processes, operation data, metering value of the belt scale at the starting end, and metering value of the belt scale at the stopping end where the belt scale metering is marked as abnormal.

[0084] The operation tasks, operation processes, operation data, metering value of the belt scale at the starting end, and metering value of the belt scale at the stopping end are input into the third neural network in real time, and the prediction result of whether there is an abnormality in the belt scale metering is output.

[0085] When the prediction result of whether there is an abnormality in the belt scale metering indicates a risk of abnormality, a process stop instruction is generated, and at the same time, a belt scale metering abnormality prompt message is generated.

[0086] In a specific embodiment, in order to further achieve efficient and accurate loading and unloading operations, it is determined that the material weight between the starting loading end of the belt and the belt scale at the starting end can compensate for the difference between the target operation volume and the target advance amount before stopping the loading and unloading; the method further includes:

[0087] Before generating a signal instruction to stop the loading and unloading operation after determining that the metering of the belt scale at the starting end monitored in real time reaches the target advance amount of the operation, it is continuously determined whether the difference between the material weight between the starting loading end of the belt and the belt scale at the starting end and the difference between the target operation volume and the operation advance amount is not greater than a preset difference. When it is not greater than the preset difference, the signal instruction to stop the loading and unloading operation is then executed; the preset difference can be set manually.

[0088] Among them, the steps for obtaining the material weight between the starting loading end of the belt and the belt scale at the starting end include:

[0089] The first material weight is obtained by using a sensor installed between the starting loading end and the belt scale at the starting end; an image of the area between the starting loading end and the belt scale at the starting end is collected by using a camera device, the material type and material size are identified by using image recognition technology, the material density is obtained according to the material type, and the second material weight is calculated according to the material density and the material size.

[0090] Compare whether the difference between the weight of the first material and the weight of the second material is greater than the second preset difference. If it is greater, re-obtain the weight of the first material using the spare sensor installed between the starting loading end and the starting belt scale, or re-calculate and obtain the weight of the second material using the (optimized by incremental training) image recognition technology. Then, compare again whether the difference between the weight of the first material and the weight of the second material is greater than the second preset difference. Repeat the steps of re-obtaining and comparing the weight of the first material and the weight of the second material until the difference between the weight of the first material and the weight of the second material is not greater than the second preset difference;

[0091] Perform weighted calculation based on the weight of the first material and the weight of the second material to obtain the material weight between the starting loading end and the starting belt scale of the belt; among them, the specific weights can be dynamically updated according to the operating environment. When the operating environment data is within the preset environment data range, different proportions of weights are correspondingly matched. Each preset environment data range is set with a matched preset proportion of weights; for example: the first preset environment data range includes: the first temperature range, the first humidity range, and the first vibration signal amplitude range, corresponding to the first proportion of weights, that is, 1:1.

[0092] In a specific embodiment, in order to facilitate the user to view the measurement values and prompt information in real time, and facilitate analysis and adjustment, the method includes:

[0093] Design a visual interaction interface setting to display the measurement values of the starting belt scale and the stopping belt scale in real time during the operation process.

[0094] In addition, the method further includes: receiving the target lead value uploaded by the user on the visual interaction interface, comparing the currently submitted target lead value by the user with the obtained target lead. If the difference between the two is less than the third preset difference, generate a confirmation message for determining the setting of the target lead value, and modify the target lead to the target lead value when receiving the confirmation message.

[0095] As Figure 3 shown, the embodiment of the present application discloses a belt scale metering and control system, including:

[0096] An operation process acquisition module 101, configured to receive an operation task in real time and start an operation process matching the operation task; among them, different operation tasks are all pre-set with operation processes matching them;

[0097] An operation target quantity acquisition module 102, configured to determine the operation target quantity according to the received operation task;

[0098] The operation target lead acquisition module 103 is used to determine the operation target lead according to the received operation task and the operation process matching the operation task, including: constructing a first neural network using a deep learning algorithm, inputting the received operation task and the operation process matching the operation task into the first neural network to obtain the operation target lead; the first neural network is trained and generated by historical operation tasks, operation processes matching historical operation tasks, and expert-recommended operation target leads under historical corresponding conditions;

[0099] The operation execution module 104 is used to, after the operation process is started, control the loading and unloading equipment at the starting end to perform loading and unloading operations, start the belt and the bifurcated hopper, and measure the weights using the belt scale at the starting end and the belt scale at the stopping end according to the operation process;

[0100] The operation execution monitoring module 105 is used to monitor in real time whether the measurement of the belt scale at the starting end reaches the operation target lead. If the operation target lead is reached, a signal instruction to stop the loading and unloading operation is generated to control the loading and unloading equipment at the starting end to stop the loading and unloading operation; or monitor in real time whether the measurement of the belt scale at the stopping end reaches the operation target lead. If the operation target lead is reached, a signal instruction to stop feeding the bifurcated hopper is generated to control the bifurcated hopper to stop feeding.

[0101] In a specific embodiment, the system further includes:

[0102] The operation execution display module 106 is used to design a visual interaction interface setting and display in real time the measurement values of the belt scale at the starting end and the belt scale at the stopping end during the operation process;

[0103] The operation environment acquisition module 107 is used to receive the operation environment in real time; the operation environment includes temperature, humidity, and vibration conditions;

[0104] The operation target lead acquisition module 103 is further used to construct a second neural network using a deep learning algorithm, input the received operation task and the operation process matching the operation task into the second neural network to replace the input into the first neural network, and obtain the operation target lead; the second neural network is trained and generated by historical operation tasks, operation processes matching historical operation tasks, historical operation environments, and expert-recommended operation target leads under historical corresponding conditions.

[0105] In a specific embodiment, the operation execution monitoring module 105 is further used to monitor in real time the measurement of the belt scale at the stopping end. If it is detected that the measurement value of the belt scale at the stopping end is lower than the minimum measurement value within the first preset time period or the change amount remains lower than the preset change amount within the second preset time period, it is determined that the process is running empty, and a process stop instruction is generated.

[0106] A specific embodiment, the operation monitoring module 105 is further configured to: monitor in real time the operation data of the loading and unloading equipment, belt, and bifurcated hopper at the starting end; construct a third neural network using a deep learning algorithm, and input the operation task, operation process, operation data, the metering value of the belt scale at the starting end, and the metering value of the belt scale at the stopping end into the third neural network in real time, and output a prediction result on whether the belt scale metering is abnormal; the third neural network is trained and generated by using the historical operation tasks, operation processes, operation data, the metering value of the belt scale at the starting end, and the metering value of the belt scale at the stopping end with abnormal belt scale metering; when the prediction result on whether the belt scale metering is abnormal indicates an abnormal risk, generate a process stop instruction and simultaneously generate a belt scale metering abnormal prompt message.

[0107] A specific embodiment, the operation monitoring module 105 is further configured to: after determining that the metering of the belt scale at the starting end reaches the operation target lead in real-time monitoring, and before generating a signal instruction to stop the loading and unloading operation, continue to determine whether the difference between the material weight between the starting loading end of the belt and the belt scale at the starting end and the difference between the operation target amount and the operation lead amount is not greater than a preset difference, and when it is not greater than the preset difference, then execute generating a signal instruction to stop the loading and unloading operation.

[0108] The embodiment of the present application also discloses a computer-readable storage medium.

[0109] Specifically, the computer-readable storage medium stores a computer program that can be loaded and executed by a processor for the above belt scale metering control method. The computer-readable storage medium includes, for example: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0110] The embodiment of the present application also discloses a computer device.

[0111] Specifically, the computer device includes a memory and a processor, and the memory stores a computer program that can be loaded and executed by the processor for the above belt scale metering control method.

[0112] The above are all the preferred embodiments of the present application. The protection scope of the present application is not limited by this. Any feature disclosed in this specification (including the abstract and drawings), unless specifically described, can be replaced by other equivalent or similar-purpose alternative features. That is, unless specifically described, each feature is only an example in a series of equivalent or similar features.

Claims

1. A belt scale metering joint control method, characterized in that: include: Receive work tasks in real time and start work processes that match the work tasks; different work tasks are pre-set with work processes that match them; Determine the target amount of work according to the received work tasks; Determining the advance amount of the operation target according to the received operation task and the operation process matching the operation task, including: using a deep learning algorithm to construct a first neural network, inputting the received operation task and the operation process matching the operation task into the first neural network, and obtaining the advance amount of the operation target; the first neural network is trained and generated by historical operation tasks, operation processes matching the historical operation tasks, and expert recommended advance amounts of the operation targets under historical corresponding conditions; After the operation process is started, the loading and unloading equipment at the departure end is controlled to perform loading and unloading operations, the belt and fork bucket are started, and the belt scale at the departure end and the belt scale at the stop end are measured according to the operation process; Real-time monitoring of whether the measurement of the belt scale at the departure end reaches the operation target in advance. If the operation target is reached in advance, a signal instruction to stop the loading and unloading operation is generated to control the loading and unloading equipment at the departure end to stop the loading and unloading operation; or real-time monitoring of whether the measurement of the belt scale at the stop end reaches the operation target in advance. If the operation target is reached in advance, a signal instruction to stop the feeding of the fork bucket is generated to control the fork bucket to stop feeding; the operation process is divided into a first classification operation process in which only the main process participates in the operation, and a second classification operation process in which the sub-process participates in the operation; When the matching operation process is the first classification operation process, directly compare whether the measurement of the conveyor belt scale at the departure end reaches the operation target advance amount. If the operation target advance amount is reached, a signal instruction to stop the loading and unloading operation is generated to control the loading and unloading equipment at the departure end to stop the loading and unloading operation; When the matched operation process is the second classification operation process, it is judged whether the measurement of the belt scale at the stop end corresponding to each sub-process of the second classification operation process reaches the target advance amount corresponding to each sub-process. If the measurement of the belt scale at the stop end corresponding to each sub-process reaches the operation target advance amount, a signal instruction for the fork bucket to stop feeding to the sub-process is generated to control the fork bucket to stop feeding to the material transmission path corresponding to the sub-process; Also includes: After determining that the measurement of the conveyor belt scale at the departure end reaches the operation target advance amount through real-time monitoring, before generating a signal instruction to stop the loading and unloading operation, continue to determine whether the difference between the material weight between the conveyor belt loading end and the conveyor belt scale at the departure end and the difference between the operation target amount and the operation advance amount is not greater than a preset difference. If it is not greater than the preset difference, generate a signal instruction to stop the loading and unloading operation; wherein, the step of obtaining the material weight between the conveyor belt loading end and the conveyor belt scale at the departure end includes: The weight of the first material is obtained by using a sensor installed between the starting loading end and the starting end belt scale; an image between the starting loading end and the starting end belt scale is collected by using a camera device, the material type and material size are identified by using image recognition technology, and the weight of the second material is calculated according to the material type and material size; Compare whether the difference between the weight of the first material and the weight of the second material is greater than the second preset difference. If so, re-adopt the spare sensor installed between the belt scale from the departure loading end to the departure end to obtain the weight of the first material or re-use the image recognition technology to calculate and obtain the weight of the second material. Re-compare whether the difference between the weight of the first material and the weight of the second material is greater than the second preset difference. Repeat the steps of re-obtaining and comparing the weight of the first material and the weight of the second material until the difference between the weight of the first material and the weight of the second material is not greater than the second preset difference. Perform weighted calculation based on the weight of the first material and the weight of the second material to obtain the material weight between the belt scale from the departure loading end to the departure end of the belt.

2. The belt scale metering and joint control method according to claim 1, characterized in that: Also includes: Receive the working environment in real time; the working environment includes temperature, humidity and vibration conditions; The method of determining the advance amount of the operation target based on the received operation task and the operation process matching the operation task also includes: using a deep learning algorithm to construct a second neural network, inputting the received operation task and the operation process matching the operation task into the second neural network instead of inputting the first neural network to obtain the advance amount of the operation target; the second neural network is trained and generated through historical operation tasks, operation processes matching historical operation tasks, historical operation environments and expert-recommended operation target advance amounts under historical corresponding conditions.

3. The belt scale metering and joint control method according to claim 1, characterized in that: Also includes: Real-time monitoring of the belt scale measurement at the shutdown end. If it is detected that the measurement value of the belt scale at the shutdown end is lower than the minimum measurement value within the first preset time period or the change amount is continuously lower than the preset change amount within the second preset time period, the process is deemed to be empty and a process stop instruction is generated.

4. The belt scale metering and joint control method according to claim 1, characterized in that: Also includes: Real-time monitoring of the operating data of loading and unloading equipment, belts, and fork buckets at the departure end; A third neural network is constructed by using a deep learning algorithm, and the operation tasks, operation processes, operation data, measurement values ​​of the belt scale at the departure end, and measurement values ​​of the belt scale at the stop end are input into the third neural network in real time, and a prediction result of whether the belt scale measurement is abnormal or not is output; the third neural network is trained and generated by annotating the operation tasks, operation processes, operation data, measurement values ​​of the belt scale at the departure end, and measurement values ​​of the belt scale at the stop end with the history of abnormal belt scale measurement; If the prediction result of whether the belt scale measurement is abnormal or not is that there is an abnormal risk, a process stop instruction is generated, and a belt scale measurement abnormality prompt message is generated at the same time.

5. The belt scale metering and joint control method according to claim 1, characterized in that: Also includes: Design a visual interactive interface setting to display the measurement values ​​of the belt scale at the starting end and the belt scale at the stopping end during the operation process in real time.

6. A belt scale metering joint control system, characterized in that: include: The operation process acquisition module is used to receive the operation task in real time and start the operation process matching the operation task; wherein different operation tasks are pre-set with the operation process matching them; the operation process is divided into a first-class operation process in which only the main process participates in the operation and a second-class operation process in which the sub-process participates in the operation; The operation target quantity acquisition module is used to determine the operation target quantity according to the received operation task; The operation target lead time acquisition module is used to determine the operation target lead time according to the received operation task and the operation process matching the operation task, including: using a deep learning algorithm to construct a first neural network, inputting the received operation task and the operation process matching the operation task into the first neural network, and obtaining the operation target lead time; the first neural network is trained and generated by historical operation tasks, operation processes matching the historical operation tasks, and expert recommended operation target lead times under historical corresponding conditions; The operation operation module is used to control the loading and unloading equipment at the departure end to perform loading and unloading operations, start the belt and fork bucket, and measure the belt scale at the departure end and the belt scale at the stop end according to the operation process after the operation process is started; The operation monitoring module is used to monitor in real time whether the measurement of the belt scale at the departure end reaches the operation target in advance. If the operation target is reached in advance, a signal instruction to stop the loading and unloading operation is generated to control the loading and unloading equipment at the departure end to stop the loading and unloading operation; or to monitor in real time whether the measurement of the belt scale at the stop end reaches the operation target in advance. If the operation target is reached in advance, a signal instruction to stop feeding the fork bucket is generated to control the fork bucket to stop feeding; It is also used to directly compare whether the measurement of the belt scale at the departure end reaches the operation target advance amount when the matched operation process is the first classification operation process. If the operation target advance amount is reached, a signal instruction to stop the loading and unloading operation is generated to control the loading and unloading equipment at the departure end to stop the loading and unloading operation; when the matched operation process is the second classification operation process, it is judged whether the measurement of the belt scale at the stop end corresponding to each sub-process of the second classification operation process reaches the target advance amount corresponding to each sub-process. If the measurement of the belt scale at the stop end corresponding to each sub-process reaches the operation target advance amount, a signal instruction is generated for the fork bucket to stop feeding to the sub-process to control the fork bucket to stop feeding to the corresponding material transmission path of the sub-process; It is also used to continue to judge whether the difference between the material weight between the starting loading end of the belt and the starting end belt scale and the difference between the operation target and the operation advance amount is not greater than a preset difference before generating a signal instruction to stop the loading and unloading operation after judging that the measurement of the starting end belt scale reaches the operation target in advance through real-time monitoring, and if it is not greater than the preset difference, then generate a signal instruction to stop the loading and unloading operation; wherein, the acquisition of the material weight between the starting loading end of the belt and the starting end belt scale includes: acquiring the first material weight by using a sensor installed between the starting loading end and the starting end belt scale; acquiring an image between the starting loading end and the starting end belt scale by using a camera device, identifying the material type and material size by using image recognition technology, and The second material weight is calculated based on the material type and material size; the difference between the first material weight and the second material weight is compared to see whether it is greater than the second preset difference. If so, the spare sensor installed between the belt scale from the departure loading end to the departure end is used again to obtain the first material weight or the image recognition technology is used again to calculate the second material weight, and then the difference between the first material weight and the second material weight is compared again to see whether it is greater than the second preset difference. The steps of re-obtaining the first material weight and the second material weight and comparing them are repeated until the difference between the first material weight and the second material weight is not greater than the second preset difference; a weighted calculation is performed based on the first material weight and the second material weight to obtain the material weight between the belt scale from the departure loading end to the departure end.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 5.

8. A computer device, characterized in that: The computer device comprises a memory, a processor and a program stored and executable on the memory, and the program implements the steps of the method according to any one of claims 1 to 5 when executed by the processor.

Images