A predictable maintenance method and system for semiconductor wastewater quality

Abstract

This disclosure relates to the field of wastewater treatment, and more particularly to a method and system for predictive maintenance of semiconductor wastewater quality. The method includes: acquiring water quality conditions, filter consumable usage, and reagent usage before and after treatment by a semiconductor wastewater filtration device; determining maintenance work orders based on the water quality conditions, filter consumable usage, and reagent usage, wherein the maintenance work orders include equipment maintenance items, online inventory of filter consumables and reagents, and acquisition of on-site water quality sampling and measurement data, and updating the data involved in the content to obtain updated data; predicting future consumption of filter consumables and reagents based on the updated data from the maintenance work orders and the expected volume of semiconductor wastewater to be treated, thereby performing online inventory and inspection management to achieve predictive maintenance. This solves the problems of redundant equipment or consumables requiring additional storage space and management costs in existing technologies.

Description

Technical Field

[0001] This disclosure relates to the field of wastewater treatment, and in particular to a method and system for predictive maintenance of semiconductor wastewater quality. Background Technology

[0002] Semiconductor manufacturing processes generate a significant amount of wastewater, and the total wastewater must be discharged with the concentration of harmful pollutants reduced to a certain level. Existing production lines typically require the detection of the type and concentration of pollutants generated at each stage, necessitating the installation of sensors in the corresponding discharge pipes. Similarly, relevant purification processes are required to remove or reduce these pollutants. For example, US20220365058A1 discloses pollutant analysis devices 100A, 100B, and 100C for semiconductor production lines to detect the ionic composition of pollutants contained in effluent; it also includes a pretreatment sampler 110 to achieve multiple filtration (including a first filter 114 and a second filter 116).

[0003] However, the production capacity and pollutant emissions of semiconductor production lines are not constant, and the lifespan of monitoring sensors and the usage of consumables for filtering and purifying pollutants are also not fixed. While, with sufficient funds, wastewater treatment suppliers or consumable providers can be required to provide redundant equipment or consumables, in reality, such redundant equipment or consumables require additional storage space and management costs. Most semiconductor manufacturers will not pay for this redundancy, and suppliers or consumable providers cannot ascertain the required redundancy. Therefore, it is necessary to cooperate with semiconductor manufacturers to achieve predictable maintenance of semiconductor wastewater quality, that is, to predict the equipment that needs replacement or maintenance based on usage. Furthermore, since the needs of semiconductor manufacturers are constantly changing, the system needs to be able to update maintenance methods in real time, thereby reducing additional management, procurement, and maintenance costs. Summary of the Invention

[0004] This disclosure provides a method and system for predictable maintenance of semiconductor wastewater quality to address existing problems in related technologies. The technical solution is as follows:

[0005] In a first aspect, embodiments of this disclosure provide a method for predictable maintenance of semiconductor wastewater quality, comprising the following steps:

[0006] Obtain information on water quality, filtration consumables usage, and chemical usage before and after treatment by the semiconductor wastewater filtration equipment;

[0007] Maintenance work orders are determined based on water quality, usage of filter consumables, and usage of chemicals. The content of the maintenance work order includes equipment maintenance items, online inventory of filter consumables and chemicals, and acquisition of on-site water quality sampling and measurement data. Updated data is obtained by updating the data involved in the content.

[0008] Based on the updated data from maintenance work orders and the expected volume of semiconductor wastewater to be treated, the consumption of future filtration consumables and chemicals is predicted, enabling online inventory and inspection management to achieve predictable maintenance.

[0009] Optionally, based on updated data from maintenance work orders and the expected volume of semiconductor wastewater to be treated, the future consumption of filtration consumables and chemicals is predicted, including:

[0010] Collect historical maintenance work order data, including usage records of consumables and medicines;

[0011] Collect historical on-site water quality sampling and measurement data;

[0012] The historical maintenance work order data and historical on-site water quality sampling and measurement data are cleaned to remove missing values ​​and outliers.

[0013] Based on historical on-site water quality sampling and measurement data, on-site water quality data, historical expected water quality data, and water quantity data, the characteristics of changes in water quality and quantity before and after treatment are extracted, and a relationship model between the changes and the consumption of consumables and reagents is constructed. The relationship model can be trained by a machine learning model of a decision tree neural network model. The decision tree is used as the input layer of the neural network model, the changes are extracted using the decision tree, and the extracted changes are used to train the neural network model to adjust the model parameters in the neural network model.

[0014] Collect data on the volume of semiconductor wastewater to be treated;

[0015] When using a trained neural network model to predict future consumption of consumables and medicines, maintenance work orders and inspection management should be assigned to the same or a few staff members.

[0016] Optionally, the water quality before and after treatment by the semiconductor wastewater filtration equipment, the usage of filtration consumables, and the usage of chemicals are obtained, including:

[0017] The water quality information is obtained by periodically sampling and chemically analyzing the wastewater before and after treatment, and then feeding back the results.

[0018] The usage of filtration consumables and chemicals is obtained through the consumables usage records and chemical usage records.

[0019] Optionally, maintenance work orders can be determined based on water quality, usage of filtration consumables, and chemical usage, including:

[0020] The filtration efficiency of the semiconductor wastewater filtration equipment is determined based on past water quality conditions, usage of filtration consumables, and use of chemicals. Based on the filtration efficiency, the required equipment maintenance items for the semiconductor wastewater filtration equipment are determined.

[0021] Maintenance work orders are generated based on the local inventory of equipment maintenance projects, filter consumables, and chemicals to update the aforementioned data.

[0022] Optionally, the filtration efficiency of the semiconductor wastewater filtration equipment is determined based on past water quality conditions, usage of filtration consumables, and usage of chemicals, including:

[0023] The filtration efficiency is determined based on the past water quality of the semiconductor wastewater filtration equipment, the volume of wastewater treated, and the usage of filtration consumables and chemicals, as shown below:

[0024] in, For filtration efficiency, Based on past consumable usage costs, Based on past drug usage costs, This indicates the difference in water quality before and after wastewater treatment. The wastewater quality before wastewater treatment A represents the quality of the wastewater before treatment, and A represents the amount of wastewater treated.

[0025] Optionally, based on updated data from maintenance work orders and the expected volume of semiconductor wastewater to be treated, the future consumption of filtration consumables and chemicals is predicted, including:

[0026] Based on the filtration efficiency, the on-site water quality sampling measurement data in the updated data, and the expected volume of semiconductor wastewater to be treated, the expected filtration consumables and reagents to be used are calculated, as shown below:

[0027]

[0028] in, For future filtration consumable consumption, For future drug consumption, For filtration efficiency, For on-site water quality sampling and measurement data, For the expected water quality data, This represents the expected volume of semiconductor wastewater to be treated.

[0029] Optionally, online inventory and inspection management can be implemented to achieve predictable maintenance, including: developing online inventory management based on the expected use of filter consumables and chemicals and the online inventory of filter consumables and chemicals, and developing inspection plans for the actual consumption and operation of filter consumables and chemicals of the semiconductor wastewater filtration equipment.

[0030] As another aspect of this disclosure, a predictive maintenance system for semiconductor wastewater quality is provided, comprising:

[0031] The historical data acquisition unit acquires information on water quality before and after treatment by the semiconductor wastewater filtration equipment, as well as the usage of filtration consumables and chemicals.

[0032] The maintenance work order generation and data update unit determines maintenance work orders based on water quality, usage of filter consumables, and usage of chemicals. The maintenance work order includes equipment maintenance items, online inventory of filter consumables and chemicals, and acquisition of on-site water quality sampling and measurement data. The unit then updates the data involved in the content to obtain updated data.

[0033] The predictive maintenance unit predicts the future consumption of filtration consumables and chemicals based on updated data from maintenance work orders and the expected volume of semiconductor wastewater to be treated. This enables online inventory and inspection management, thus achieving predictive maintenance.

[0034] As another aspect of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the predictable maintenance method for semiconductor wastewater quality.

[0035] As another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the aforementioned method for predictable maintenance of semiconductor wastewater quality.

[0036] The advantages or beneficial effects of the above technical solutions include at least the following:

[0037] Based on the operation status, inventory status and expected volume of semiconductor wastewater to be treated, predictable maintenance of filtration consumables and agents can be achieved. This solves the problem of redundant equipment or consumables requiring additional storage space and management costs in the existing technology. It also reduces maintenance costs while ensuring that wastewater treatment meets standards and that the equipment operates normally and healthily. Furthermore, the system operation data and online inventory status can be updated regularly based on the feedback data from the maintenance work orders. The use of a neural network model combined with a decision tree can make the system more adaptable to changes and can be used to update the maintenance plan in real time [1], making the entire system more adaptable.

[0038] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of this disclosure will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0039] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in this disclosure and should not be construed as limiting the scope of this disclosure.

[0040] Figure 1 This is a flowchart of the predictable maintenance method for semiconductor wastewater quality according to Embodiment 1 of this disclosure;

[0041] Figure 2 This is a schematic diagram of the predictable maintenance method in Embodiment 1 of this disclosure;

[0042] Figure 3 This is a schematic diagram of a predictive maintenance system for semiconductor wastewater quality. Detailed Implementation

[0043] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0044] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0045] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0046] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0047] It is understood that the various method embodiments mentioned above in this disclosure can be combined with each other to form combined embodiments without violating the principle and logic. Due to space limitations, this disclosure will not elaborate further.

[0048] In addition, this disclosure also provides a predictable maintenance system for semiconductor wastewater quality, electronic equipment, computer-readable storage medium, and program, all of which can be used to implement any of the predictable maintenance methods for semiconductor wastewater quality provided in this disclosure. The corresponding technical solutions and descriptions are described in the corresponding section of the method and will not be repeated here.

[0049] The implementer of the predictive maintenance method for semiconductor wastewater quality can be a computer or other device capable of achieving predictive maintenance of semiconductor wastewater quality. For example, the method can be executed by a terminal device, server, or other processing device. The terminal device can be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, vehicle-mounted device, wearable device, etc. In some possible implementations, this predictive maintenance method for semiconductor wastewater quality can be implemented by a processor calling computer-readable instructions stored in memory.

[0050] Example 1

[0051] This embodiment provides a method for predictable maintenance of semiconductor wastewater quality, such as... Figure 1 As shown, it includes the following steps:

[0052] S10. Obtain the water quality, filtration consumables usage, and reagent usage of the semiconductor wastewater filtration equipment before and after treatment;

[0053] S20. Based on water quality, usage of filter consumables and chemicals, determine the maintenance work order. The maintenance work order includes equipment maintenance items, online inventory of filter consumables and chemicals, and acquisition of on-site water quality sampling and measurement data. Update the data involved in the content to obtain updated data.

[0054] S30: Based on the updated data from maintenance work orders and the expected volume of semiconductor wastewater to be treated, the system predicts the future consumption of filtration consumables and chemicals, and then conducts online inventory and inspection management to achieve predictable maintenance.

[0055] Based on the above configuration, this disclosure proposes a predictable maintenance method that can predictively maintain the filtration consumables and reagents according to the operating status, inventory status, and expected volume of semiconductor wastewater to be treated of the semiconductor wastewater filtration equipment. This solves the problem of redundant equipment or consumables requiring additional storage space and management costs in the prior art, and reduces maintenance costs while ensuring that wastewater treatment meets standards and the equipment operates normally and healthily.

[0056] The steps of each embodiment of this disclosure will be described in detail below.

[0057] S10. Obtain the water quality, filtration consumables usage, and reagent usage of the semiconductor wastewater filtration equipment before and after treatment;

[0058] The water quality is obtained by periodically sampling and chemically analyzing the wastewater before and after treatment and feeding back the results; optionally, the wastewater can also be monitored online for substances such as fluoride, nitrogen, phosphate, turbidity, and organic compounds.

[0059] Information on the usage of filtration consumables and chemicals is obtained through consumables usage records and chemical usage records, respectively. Records should include information on consumables used in filtration equipment, such as ultrafiltration (UF) membranes and reverse osmosis (RO) membranes, as well as their replacement cycles and usage status; records should also be kept of chemical agents used in wastewater treatment, including pH adjusters, coagulants, and flocculants. Records should include the amount used, frequency of use, and type of agent to facilitate process optimization and cost control.

[0060] S20. Based on water quality, usage of filter consumables, and usage of chemicals, determine the maintenance work order. The maintenance work order includes equipment maintenance items, online inventory of filter consumables and chemicals, and acquisition of on-site water quality sampling and measurement data. Update the data involved in the content to obtain updated data.

[0061] In some embodiments, maintenance work orders are determined based on water quality, usage of filtration consumables, and usage of chemicals, including:

[0062] The filtration efficiency of the semiconductor wastewater filtration equipment is determined based on past water quality conditions, usage of filtration consumables, and use of chemicals. Based on the filtration efficiency, the required equipment maintenance items for the semiconductor wastewater filtration equipment are determined.

[0063] Based on the equipment maintenance project, maintenance work orders are generated using the local inventory of filtration consumables and chemicals to update the aforementioned data.

[0064] The equipment maintenance items can be scheduled according to the filtration efficiency. The maintenance items include the inspection and maintenance of wastewater treatment equipment to ensure that all equipment components are in normal operation, such as pumps, pipes, valves, and agitators; it also includes the replacement of filter consumables, such as ultrafiltration (UF) membranes and reverse osmosis (RO) membranes, to ensure filtration effect and water quality compliance; in addition, it also includes sludge treatment systems and automated control systems, such as sludge collection, storage and disposal, and PLC program control.

[0065] In some embodiments, the filtration efficiency of the semiconductor wastewater filtration equipment is determined based on past water quality conditions, usage of filtration consumables, and usage of chemicals, including:

[0066] The filtration efficiency is determined based on the past water quality of the semiconductor wastewater filtration equipment, the volume of wastewater treated, and the usage of filtration consumables and chemicals, as shown below:

[0067] in, For filtration efficiency, Based on past consumable usage costs, Based on past drug usage costs, This indicates the difference in water quality before and after wastewater treatment. The wastewater quality before wastewater treatment A represents the wastewater quality before treatment, and A represents the volume of wastewater treated. The usage of consumables and chemicals is directly represented by past costs. Since the entire maintenance plan requires collaboration across multiple departments, this approach allows for data integration with purchasing and finance departments, linking usage volume and unit price, thus facilitating the implementation of the entire maintenance plan. Furthermore, the wastewater volume and the difference in water quality before and after treatment are inversely proportional to the amount of consumables and chemicals used. Using this as the basis for calculating filtration efficiency provides a more accurate reflection of the overall filtration system efficiency compared to the filtration efficiency of a single wastewater treatment unit, directly reflecting the cost of filtering a certain volume of wastewater.

[0068] S30: Based on the updated data from maintenance work orders and the expected volume of semiconductor wastewater to be treated, the system predicts the future consumption of filtration consumables and chemicals, and then conducts online inventory and inspection management to achieve predictable maintenance.

[0069] In some embodiments, based on updated data from maintenance work orders and the expected volume of semiconductor wastewater to be treated, the future consumption of filtration consumables and chemicals is predicted, including:

[0070] Based on the filtration efficiency, the on-site water quality sampling measurement data in the updated data, and the expected volume of semiconductor wastewater to be treated, the expected filtration consumables and reagents to be used are calculated, as shown below:

[0071]

[0072] in, For future filtration consumable consumption, For future drug consumption, For filtration efficiency, For on-site water quality sampling and measurement data, For the expected water quality data, The expected volume of semiconductor wastewater to be treated is given. The consumption of filter consumables and future reagents calculated using the above method is a holistic parameter. Further individual determinations of these consumptions are needed based on the actual wastewater quality and volume. For example, the specific reagents and dosages to be used may vary depending on the chemical pollutants present in the wastewater, as well as the presence of organic flocculation or particulate matter. The specific determination method is as follows, based on the actual filtration equipment used by those skilled in the art.

[0073] Preferably, when determining maintenance work orders and inspection management, maintenance work orders and inspection management should be assigned to the same or several staff members, so that the staff members are more familiar with the same type of procedures to be performed.

[0074] In one embodiment, online inventory and inspection management are performed to achieve predictable maintenance, including: developing online inventory management based on the expected use of filter consumables and chemicals and the online inventory of filter consumables and chemicals, and developing an inspection plan for the actual consumption and operation of filter consumables and chemicals of the semiconductor wastewater filtration equipment.

[0075] In another embodiment, based on updated data from maintenance work orders and the expected volume of semiconductor wastewater to be treated, the future consumption of filtration consumables and chemicals is predicted, including:

[0076] Collect historical maintenance work order data, including usage records of consumables and medicines;

[0077] Collect historical on-site water quality sampling and measurement data, including indicators such as chemical pollutants, organic matter, and particulate matter;

[0078] The historical maintenance work order data and historical on-site water quality sampling and measurement data are cleaned to remove missing values ​​and outliers. The missing values ​​can be removed by interpolation.

[0079] Based on historical on-site water quality sampling and measurement data, on-site water quality data, historical expected water quality data, and water quantity data, the changes in water quality and quantity before and after treatment, such as pollutant types and concentrations, are extracted. A relationship model between these changes and the consumption of consumables and reagents is constructed. This relationship model can be trained using a machine learning model of a decision tree neural network model. The decision tree is used as the input layer of the neural network model to extract the changes, providing better interpretation. The extracted changes are then used to train the neural network model to adjust the model parameters. Optionally, Keras can be used to build the neural network model, and DecisionTreeClassifier or DecisionTreeRegressor can be used for changes feature extraction.

[0080] Collect data on the volume of semiconductor wastewater to be treated;

[0081] A trained neural network model is used to predict future consumption of consumables and medicines.

[0082] Based on the specific water quality of the wastewater, the prediction results are further refined to determine the specific types and dosages of reagents.

[0083] Based on the model prediction results and maintenance work order feedback, maintenance work orders and inspection plans are formulated.

[0084] Optionally, ensure that tasks are assigned to staff familiar with the same type of process. Dynamically adjust inventory based on forecasts and real-time inventory data to ensure the supply of consumables and pharmaceuticals.

[0085] Furthermore, the accuracy and efficiency of the neural network model can be evaluated periodically, and the model can be optimized based on feedback. Additionally, as new data is continuously collected, the neural network model can learn and update itself to adapt to changing environments and conditions. Using a neural network model combined with decision trees enhances the system's adaptability to change, enabling real-time updates to maintenance plans and improving the overall system's overall resilience.

[0086] The specific means of achieving predictable maintenance include developing predictable maintenance plans. These plans encompass processes such as plan creation, maintenance work orders, consumable consumption statistics, and work order closure. Plan creation includes creating online inventory management plans and inspection plans, followed by work order allocation. Maintenance work orders include routine maintenance and emergency fault handling to ensure the system can achieve stable wastewater treatment, meeting water quality and treatment volume requirements. Consumable consumption during maintenance is statistically recorded in the system, and work orders are closed only after data feedback is completed. Furthermore, online inventory management includes procurement plans and inventory receipt dates to ensure sufficient inventory to meet demand and provide contingency reserves.

[0087] Among them, such as Figure 2 As shown, routine maintenance includes regular maintenance such as system inspection, system full inspection, and system annual inspection. Emergency fault handling in this embodiment includes emergency repair and anticipated maintenance in the foreseeable maintenance plan. For example, when the filtration efficiency changes significantly after considering price adjustments for consumables, emergency fault handling is required. After on-site investigation, expert diagnosis, professional operation, and effect verification, the foreseeable maintenance method implemented in this embodiment can predictively maintain filtration consumables and reagents based on the operating status, inventory status, and expected volume of semiconductor wastewater to be treated. This solves the problem of redundant equipment or consumables requiring additional storage space and management costs in existing technologies. It reduces maintenance costs while ensuring wastewater treatment meets standards and the equipment operates normally and healthily. Furthermore, it can regularly update system operating data and online inventory based on feedback data from maintenance work orders, thereby updating the maintenance plan and making the entire system more adaptable.

[0088] Example 2

[0089] This embodiment provides a predictive water quality maintenance system 100 for semiconductor wastewater, such as... Figure 3 As shown, it includes:

[0090] Historical data acquisition unit 1 acquires the water quality, filter consumables usage, and reagent usage of the semiconductor wastewater filtration equipment before and after treatment.

[0091] The maintenance work order generation and data update unit 2 determines maintenance work orders based on water quality, filter consumable usage, and chemical usage. The maintenance work order includes equipment maintenance items, online inventory of filter consumables and chemicals, and acquisition of on-site water quality sampling and measurement data. The updated data is obtained by updating the data involved in the content.

[0092] The predictive maintenance unit 3 predicts the future consumption of filtration consumables and chemicals based on updated data from maintenance work orders and the expected volume of semiconductor wastewater to be treated, thereby enabling online inventory and inspection management to achieve predictive maintenance.

[0093] In the historical data acquisition unit 1, the water quality is obtained by periodically sampling and chemically analyzing the wastewater before and after treatment and feeding back the results; optionally, the wastewater can also be monitored online, such as for fluoride, nitrogen, phosphate, turbidity and organic compounds.

[0094] Information on the usage of filtration consumables and chemicals is obtained through consumables usage records and chemical usage records, respectively. Records should include information on consumables used in filtration equipment, such as ultrafiltration (UF) membranes and reverse osmosis (RO) membranes, as well as their replacement cycles and usage status; records should also be kept of chemical agents used in wastewater treatment, including pH adjusters, coagulants, and flocculants. Records should include the amount used, frequency of use, and type of agent to facilitate process optimization and cost control.

[0095] In the maintenance work order generation and data update unit 2, maintenance work orders are determined based on water quality, filtration consumable usage, and chemical usage, including:

[0096] The filtration efficiency of the semiconductor wastewater filtration equipment is determined based on past water quality conditions, usage of filtration consumables, and use of chemicals. Based on the filtration efficiency, the required equipment maintenance items for the semiconductor wastewater filtration equipment are determined.

[0097] Based on the equipment maintenance project, maintenance work orders are generated using the local inventory of filtration consumables and chemicals to update the aforementioned data.

[0098] The equipment maintenance items can be scheduled according to the filtration efficiency. The maintenance items include the inspection and maintenance of wastewater treatment equipment to ensure that all equipment components are in normal operation, such as pumps, pipes, valves, and agitators; it also includes the replacement of filter consumables, such as ultrafiltration (UF) membranes and reverse osmosis (RO) membranes, to ensure filtration effect and water quality compliance; in addition, it also includes sludge treatment systems and automated control systems, such as sludge collection, storage and disposal, and PLC program control.

[0099] In some embodiments, the filtration efficiency of the semiconductor wastewater filtration equipment is determined based on past water quality conditions, usage of filtration consumables, and usage of chemicals, including:

[0100] The filtration efficiency is determined based on the past water quality of the semiconductor wastewater filtration equipment, the volume of wastewater treated, and the usage of filtration consumables and chemicals, as shown below:

[0101] in, For filtration efficiency, Based on past consumable usage costs, Based on past drug usage costs, This indicates the difference in water quality before and after wastewater treatment. The wastewater quality before wastewater treatment A represents the wastewater quality before treatment, and A represents the volume of wastewater treated. The usage of consumables and chemicals is directly represented by past costs. Since the entire maintenance plan requires collaboration across multiple departments, this approach allows for data integration with purchasing and finance departments, linking usage volume and unit price, thus facilitating the implementation of the entire maintenance plan. Furthermore, the wastewater volume and the difference in water quality before and after treatment are inversely proportional to the amount of consumables and chemicals used. Using this as the basis for calculating filtration efficiency provides a more accurate reflection of the overall filtration system efficiency compared to the filtration efficiency of a single wastewater treatment unit, directly reflecting the cost of filtering a certain volume of wastewater.

[0102] In the predictable maintenance unit 3, based on updated data from maintenance work orders and the expected volume of semiconductor wastewater to be treated, the future consumption of filtration consumables and chemicals is predicted, including:

[0103] Based on the filtration efficiency, the on-site water quality sampling measurement data in the updated data, and the expected volume of semiconductor wastewater to be treated, the expected filtration consumables and reagents to be used are calculated, as shown below:

[0104]

[0105] in, For future filtration consumable consumption, For future drug consumption, For filtration efficiency, For on-site water quality sampling and measurement data, For the expected water quality data, The expected volume of semiconductor wastewater to be treated is given. The consumption of filter consumables and future reagents calculated using the above method is a holistic parameter. Further individual determinations of these consumptions are needed based on the actual wastewater quality and volume. For example, the specific reagents and dosages to be used may vary depending on the chemical pollutants present in the wastewater, as well as the presence of organic flocculation or particulate matter. The specific determination method is as follows, based on the actual filtration equipment used by those skilled in the art.

[0106] In one embodiment, online inventory and inspection management are performed to achieve predictable maintenance, including: developing online inventory management based on the expected use of filter consumables and chemicals and the online inventory of filter consumables and chemicals, and developing an inspection plan for the actual consumption and operation of filter consumables and chemicals of the semiconductor wastewater filtration equipment.

[0107] The specific means of achieving predictable maintenance include developing predictable maintenance plans. These plans encompass processes such as plan creation, maintenance work orders, consumable consumption statistics, and work order closure. Plan creation includes creating online inventory management plans and inspection plans, followed by work order allocation. Maintenance work orders include routine maintenance and emergency fault handling to ensure the system can achieve stable wastewater treatment, meeting water quality and treatment volume requirements. Consumable consumption during maintenance is statistically recorded in the system, and work orders are closed only after data feedback is completed. Furthermore, online inventory management includes procurement plans and inventory receipt dates to ensure sufficient inventory to meet demand and provide contingency reserves.

[0108] Routine maintenance includes regular maintenance such as system inspections, full system inspections, and annual system inspections. Emergency fault handling in this embodiment includes emergency repairs and anticipated maintenance within the predictable maintenance plan. For example, if the filtration efficiency changes significantly after considering price adjustments for consumables, emergency fault handling is required. After on-site investigation, expert diagnosis, professional operation, and effect verification, the predictable maintenance method implemented in this embodiment can predictively maintain filtration consumables and reagents based on the operating status, inventory status, and expected volume of semiconductor wastewater to be treated. This solves the problem of redundant equipment or consumables requiring additional storage space and management costs in existing technologies. It reduces maintenance costs while ensuring wastewater treatment meets standards and the equipment operates normally and healthily. Furthermore, it can periodically update system operating data and online inventory based on feedback data from maintenance work orders, thereby updating the maintenance plan and making the entire system more adaptable.

[0109] Example 3

[0110] This disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the predictable maintenance method for semiconductor wastewater quality in Embodiment 1.

[0111] Embodiment 3 of this disclosure is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this disclosure.

[0112] Electronic devices can take the form of general-purpose computing devices, such as server devices. Components of an electronic device may include, but are not limited to: at least one processor, at least one memory, and buses connecting different system components (including memory and processor).

[0113] The bus includes a data bus, an address bus, and a control bus.

[0114] The memory may include volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0115] The memory may also include program tools having a set (at least one) of program modules, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0116] The processor performs various functional applications and data processing by running computer programs stored in memory.

[0117] Electronic devices can also communicate with one or more external devices (such as keyboards, pointing devices, etc.). This communication can be achieved through input / output (I / O) interfaces. Furthermore, electronic devices can communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapters. The network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems.

[0118] It should be noted that although several units / modules or sub-units / modules of the electronic device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0119] Example 4

[0120] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the predictable maintenance method for semiconductor wastewater quality in Embodiment 1.

[0121] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0122] In a possible implementation, this disclosure can also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of implementing the predictable maintenance method for semiconductor wastewater quality described in Embodiment 1.

[0123] The program code for executing this disclosure can be written in any combination of one or more programming languages, and the program code can be executed entirely on a user device, partially on a user device, as a stand-alone software package, partially on a user device and partially on a remote device, or entirely on a remote device.

[0124] The above are merely specific embodiments of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in this disclosure, and these should all be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A method for predictable maintenance of semiconductor wastewater quality, characterized in that, Includes the following steps: Obtain information on water quality, filtration consumables usage, and chemical usage before and after treatment by the semiconductor wastewater filtration equipment; Maintenance work orders are determined based on water quality, usage of filter consumables, and usage of chemicals. The content of the maintenance work order includes equipment maintenance items, online inventory of filter consumables and chemicals, and acquisition of on-site water quality sampling and measurement data. Updated data is obtained by updating the data involved in the content. Based on the updated data from maintenance work orders and the expected volume of semiconductor wastewater to be treated, the consumption of future filtration consumables and chemicals is predicted, thereby enabling online inventory and inspection management to achieve predictable maintenance. Based on updated data from maintenance work orders and the expected volume of semiconductor wastewater to be treated, the future consumption of filtration consumables and chemicals is predicted, including: Collect historical maintenance work order data, including usage records of consumables and medicines; Collect historical on-site water quality sampling and measurement data; The historical maintenance work order data and historical on-site water quality sampling and measurement data are cleaned to remove missing values ​​and outliers. Based on historical on-site water quality sampling and measurement data, on-site water quality data, historical expected water quality data, and water quantity data, the characteristics of changes in water quality and quantity before and after treatment are extracted, and a relationship model between the changes and the consumption of consumables and reagents is constructed. The relationship model can be trained by a machine learning model of a decision tree neural network model. The decision tree is used as the input layer of the neural network model, the changes are extracted using the decision tree, and the extracted changes are used to train the neural network model to adjust the model parameters in the neural network model. Collect data on the volume of semiconductor wastewater to be treated; A trained neural network model is used to predict future consumption of consumables and pharmaceuticals.

2. The method for predictable maintenance of semiconductor wastewater quality as described in claim 1, characterized in that, Obtain information on water quality before and after treatment by the semiconductor wastewater filtration equipment, as well as the usage of filtration consumables and chemicals, including: The water quality information is obtained by periodically sampling and chemically analyzing the wastewater before and after treatment, and then feeding back the results. The usage of filtration consumables and chemicals is obtained through the consumables usage records and chemical usage records.

3. The method for predictable maintenance of semiconductor wastewater quality as described in claim 2, characterized in that, Maintenance work orders are determined based on water quality, filtration consumable usage, and chemical usage, including: The filtration efficiency of the semiconductor wastewater filtration equipment is determined based on past water quality conditions, usage of filtration consumables, and use of chemicals. Based on the filtration efficiency, the required equipment maintenance items for the semiconductor wastewater filtration equipment are determined. Maintenance work orders are generated based on the local inventory of equipment maintenance projects, filter consumables, and chemicals to update the aforementioned data.

4. A predictive water quality maintenance system for semiconductor wastewater, characterized in that, include: The historical data acquisition unit acquires information on water quality before and after treatment by the semiconductor wastewater filtration equipment, as well as the usage of filtration consumables and chemicals. The maintenance work order generation and data update unit determines maintenance work orders based on water quality, usage of filter consumables, and usage of chemicals. The maintenance work order includes equipment maintenance items, online inventory of filter consumables and chemicals, and acquisition of on-site water quality sampling and measurement data. The unit then updates the data involved in the content to obtain updated data. The predictive maintenance unit, based on updated data from maintenance work orders and the expected volume of semiconductor wastewater to be treated, predicts the future consumption of filtration consumables and chemicals, and then performs online inventory and inspection management to achieve predictive maintenance. Based on updated data from maintenance work orders and the expected volume of semiconductor wastewater to be treated, the future consumption of filtration consumables and chemicals is predicted, including: Collect historical maintenance work order data, including usage records of consumables and medicines; Collect historical on-site water quality sampling and measurement data; The historical maintenance work order data and historical on-site water quality sampling and measurement data are cleaned to remove missing values ​​and outliers. Based on historical on-site water quality sampling and measurement data, on-site water quality data, historical expected water quality data, and water quantity data, the characteristics of changes in water quality and quantity before and after treatment are extracted, and a relationship model between the changes and the consumption of consumables and reagents is constructed. The relationship model can be trained by a machine learning model of a decision tree neural network model. The decision tree is used as the input layer of the neural network model, the changes are extracted using the decision tree, and the extracted changes are used to train the neural network model to adjust the model parameters in the neural network model. Collect data on the volume of semiconductor wastewater to be treated; A trained neural network model is used to predict future consumption of consumables and pharmaceuticals.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the predictable maintenance method for semiconductor wastewater quality as described in any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the predictable maintenance method for semiconductor wastewater quality as described in any one of claims 1 to 3.

Images