CN-121979145-A - Production line control method and system for coconut products

CN121979145ACN 121979145 ACN121979145 ACN 121979145ACN-121979145-A

Abstract

The invention relates to the technical field of food processing automation, in particular to a production line control method and system for coconut products. The method comprises the steps of firstly obtaining production plan data issued by a manufacturing execution system, inputting the data into a pre-trained energy consumption prediction model to generate a predicted energy consumption sequence of each production line in a planned period, then aggregating all the sequences to form a total energy demand load curve of the production system in a future period, then generating an active scheduling instruction comprising a high energy consumption process time sequence optimization scheme based on the load curve and a real-time energy supply state, and finally generating and issuing a time sequence control instruction to each production line according to the instruction, and dynamically adjusting the actual starting time of the high energy consumption process to enable the real-time energy consumption load of the system to be matched with the optimization scheme. The invention realizes the deep coordination of the production plan and the energy management, and solves the problems of energy consumption prediction missing and scheduling passivity caused by the disconnection of the production plan and the energy management, thereby improving the execution flexibility of the energy efficiency and the production plan.

Inventors

ZHENG XIKAI
Zheng Xichu
HU WENJUN
Zhuo Xiaomei

Assignees

海南大好麦食品有限公司

Dates

Publication Date: 20260505
Application Date: 20260130

Claims (10)

1. A process line control method for coconut products, applied to a production system comprising at least two independent production lines, comprising: Acquiring production plan data issued by a manufacturing execution system; Inputting the production plan data into a pre-trained energy consumption prediction model, and generating a predicted energy consumption sequence of each production line in a corresponding planned production period by the energy consumption prediction model; Aggregating all the predicted energy consumption sequences to generate a total energy demand load curve of the production system in a preset future period; based on the total energy demand load curve and the real-time energy supply state, feeding back an active scheduling instruction, wherein the active scheduling instruction comprises an optimization scheme for starting time sequences of high-energy-consumption working procedures in each production line; and generating and issuing corresponding time sequence control instructions to each production line control system according to the active scheduling instructions so as to dynamically adjust the actual starting time of the high-energy-consumption working procedure in each production line and enable the real-time energy consumption load of the production system to be matched with the optimization scheme.
2. The method according to claim 1, wherein the energy consumption prediction model is trained in advance based on historical production data of the production system, wherein the historical production data at least comprises time-series power data, raw material input amount and output amount data of each process under different product categories.
3. The method of claim 1, wherein the predicted energy consumption sequence comprises an energy consumption sub-sequence for a target energy consumption process, and wherein the target high energy consumption process comprises at least one of an instant sterilization process, a high temperature sterilization process, a homogenization process, and an evaporative concentration process.
4. A method of line control of coconut products as claimed in claim 3 wherein said step of aggregating all of said predicted energy consumption sequences to generate a total energy demand load profile for said production system over a predetermined future period comprises: Setting an initial reference time axis having a uniform time interval based on a preset future period; Mapping the predicted energy consumption sequence corresponding to each production line onto the initial reference time axis according to a corresponding planned production period to generate a target reference time axis, wherein for the empty period outside the planned production period, the energy consumption value of the empty period on the target reference time axis is filled with zero; accumulating all the energy consumption predicted values corresponding to each time point on the target reference time axis respectively, and calculating to obtain a system total load predicted value corresponding to the time point; And connecting the system total load predicted values of all the time points on the target reference time axis to generate a total energy demand load curve corresponding to the production system.
5. The method of claim 1, wherein the step of feeding back the active scheduling command based on the total energy demand load profile and the real-time energy supply status comprises: acquiring an externally input energy constraint condition and a production optimization target, wherein the energy constraint condition comprises an upper limit of contract capacitance or a total energy consumption limit in a future set period; Comparing the total energy demand load curve with the energy constraint condition to determine a load conflict period; Determining one or more target energy consuming processes with the largest load contribution in the load conflict period based on traceable load composition information in the total energy demand load curve; for each target high energy consumption procedure, calculating an adjustable time amount which can be started in a delayed or advanced way by the target high energy consumption procedure within a time elastic window allowed by the target high energy consumption procedure process; When a plurality of target high-energy-consumption working procedures are of the same kind and the planned time periods thereof are overlapped in the load conflict time periods, constructing an execution sequence table corresponding to the production system on the premise of ensuring the continuity of the core production batches of each production line; when the conflict can not be completely solved only through time sequence adjustment, constructing a priority list corresponding to the production system according to a preset product class priority, wherein the preset product class priority is set to be that a coconut water production line is higher than a raw coconut milk production line, and the raw coconut milk production line is higher than a frozen coconut milk production line; Combining and conflict checking the adjustable time amount, the execution sequence table and the priority list to generate a scheduling instruction candidate scheme; and evaluating the effect of the scheduling instruction candidate scheme on relieving the load conflict and the disturbance on the production plan, selecting an optimal scheme according to the production optimization target, and formatting the optimal scheme into an active scheduling instruction for output.
6. The method of claim 5, wherein the step of generating and issuing corresponding timing control instructions to each line control system based on the active scheduling instructions comprises: analyzing the active scheduling instruction, extracting an adjustable time amount, an execution sequence list and a priority list which are associated with each production line, and distributing the adjustable time amount according to the production line identification according to the execution sequence list and the priority list to generate independent control tasks corresponding to each production line; Respectively checking whether the independent control tasks accord with preset constraints of corresponding production lines to generate check data, wherein the preset constraints comprise that the material waiting time caused by procedure adjustment does not exceed the maximum allowable shelf life of the material waiting time, and the production lines which are listed in the priority list and subsequently degraded are in a safe load-reducing state; When the verification data is verification passing, calculating a planned starting time stamp of a corresponding high-energy-consumption process of the production line based on the adjustment time amount of an independent control task corresponding to the verification data and the sequencing position in an execution sequence table, and generating a time sequence control instruction containing the planned starting time stamp; issuing time sequence control instructions corresponding to the production lines to corresponding production line control systems, and monitoring actual starting time of high-energy-consumption working procedures; When the deviation between the actual starting time and the corresponding planned starting time stamp exceeds a preset threshold value, triggering automatic fine adjustment of the beat of the subsequent process.
7. A production line control system for coconut products, for use in a production system comprising at least two independent production lines, the system comprising: The production plan data acquisition module is used for acquiring production plan data issued by the manufacturing execution system; The energy consumption prediction module is used for inputting the production plan data into a pre-trained energy consumption prediction model, and generating a predicted energy consumption sequence of each production line in a corresponding planned production period by the energy consumption prediction model; The load curve aggregation module is used for aggregating all the predicted energy consumption sequences and generating a total energy demand load curve of the production system in a preset future period; the active scheduling instruction generation module is used for feeding back an active scheduling instruction based on the total energy demand load curve and the real-time energy supply state, wherein the active scheduling instruction comprises an optimization scheme for starting time sequences of high-energy-consumption working procedures in each production line; the time sequence control instruction execution module is used for generating and sending corresponding time sequence control instructions to each production line control system according to the active scheduling instructions so as to dynamically adjust the actual starting time of the high-energy-consumption working procedure in each production line and enable the real-time energy consumption load of the production system to be matched with the optimization scheme.
8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the method of controlling the production line of coconut products as recited in any one of claims 1-6.
9. A computer readable storage medium having a computer program stored thereon, wherein the computer program when executed implements the method of line control of coconut products as recited in any one of claims 1-6.
10. A computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, wherein the program instructions, when executed by a computer, cause the computer to perform the line control method of coconut products as recited in any one of claims 1-6.

Description

Production line control method and system for coconut products Technical Field The invention relates to the technical field of food processing automation, in particular to a production line control method and system for coconut products. Background In the field of large-scale coconut product processing, a plurality of special production lines are usually arranged in parallel to ensure the process independence of different products such as frozen coconut milk, raw coconut milk and coconut water. Each production line is provided with an independent production control system which is responsible for managing the process logic and process parameters inside the production line. At present, a manufacturing execution system is generally arranged on a production management layer of a factory for making a detailed production plan, and an energy management system is also arranged on an energy management layer for monitoring real-time energy consumption. However, these two systems are typically independent of each other at the functional and data level. The production control system only executes instructions from the manufacturing execution system, while the energy management system only passively collects historical and real-time energy consumption data. This architecture results in a critical technical breakpoint where the energy management center cannot acquire the predictable energy demand load profile based on the specific production plan of three production lines in advance and accurately for a period of time in the future. Due to the lack of this predictive information, energy scheduling is in a passive and hysteresis state. On one hand, the method can not actively coordinate the start-stop time sequence of high-energy-consumption equipment such as a sterilizing kettle and a concentrating device to realize peak clipping and valley filling, which may cause high energy consumption cost, and on the other hand, when the total energy limit is faced, the method is difficult to dynamically and finely adjust the production sequence and progress of each production line based on the principle of optimal global benefit so as to ensure the delivery of key orders. Disclosure of Invention The invention provides a production line control method and a production line control system for coconut products, which solve the technical problems that energy efficiency is low and production planning execution is inflexible because energy demand prediction and active scheduling based on a plan cannot be realized due to production control and energy management disjoint in the prior art. The invention provides a production line control method of coconut products, which is applied to a production system comprising at least two independent production lines, and comprises the following steps: Acquiring production plan data issued by a manufacturing execution system; Inputting the production plan data into a pre-trained energy consumption prediction model, and generating a predicted energy consumption sequence of each production line in a corresponding planned production period by the energy consumption prediction model; Aggregating all the predicted energy consumption sequences to generate a total energy demand load curve of the production system in a preset future period; based on the total energy demand load curve and the real-time energy supply state, feeding back an active scheduling instruction, wherein the active scheduling instruction comprises an optimization scheme for starting time sequences of high-energy-consumption working procedures in each production line; and generating and issuing corresponding time sequence control instructions to each production line control system according to the active scheduling instructions so as to dynamically adjust the actual starting time of the high-energy-consumption working procedure in each production line and enable the real-time energy consumption load of the production system to be matched with the optimization scheme. Optionally, the energy consumption prediction model is trained in advance based on historical production data of the production system, wherein the historical production data at least comprises time sequence power data, raw material input amount and output amount data of each process under different product categories. Optionally, the predicted energy consumption sequence comprises an energy consumption sub-sequence for a target energy consumption process, and the target high energy consumption process comprises at least one of an instantaneous sterilization process, a high temperature sterilization process, a homogenization process and an evaporation concentration process. Optionally, the step of aggregating all the predicted energy consumption sequences to generate a total energy demand load curve of the production system in a preset future period includes: Setting an initial reference time axis having a uniform time interval based on a preset future period; Mapping the pr