Share
Embed
プロセス制御x 自然言語処理の現在地と展望 / Current State and Future Outlook for Process Control and Natural Language Processing
2026年1月23日「AI制御ワーキング第1回研究会」発表資料
URL: https://www.psec.jp/ai%E5%88%B6%E5%BE%A1wg%E7%AC%AC1%E5%9B%9E%E7%A0%94%E7%A9%B6%E4%BC%9A/
Shota Kato
February 03, 2026
Transcript
30 slides
-
ࣗݾհɿՃ౻ↅଠ 1 ژେӃֶݚڀՊ Խֶֶઐ߈मྃ ಉେֶӃใֶݚڀՊ γεςϜՊֶઐ߈मྃ r ಉॿڭ rϚϯνΣελʔେֶ ٬һݚڀһ
r ࢈૯ݚটᡈݚڀһ ઐɿԽֶֶYσʔλαΠΤϯεYࣗવݴޠॲཧ ݚڀ༰ • ϓϩηεͷϞσϦϯάɺ੍ޚ • ཧϞσϧߏஙͷޮԽ 9 5XJUUFS !T@LBU झຯΧϝϥɼαΠΫϦϯάɼΰϧϑɼ ΞΠϦογϡΠεΩʔʢ#VTINJMMTʣɼήʔϜ -
• ݴޠϞσϧʢ-.ʣ୯ޠྻͷ֬𝑝(𝑥! , ⋯ , 𝑥" ) Λ༧ଌ͢Δɽ • -.Λ༻͍Δ͜ͱͰɼ୯ޠྻʹଓ͘୯ޠΛ༧ଌͰ͖Δɽ
• େنݴޠϞσϧͱɼେنͳσʔλͰֶश͞Εͨύϥϝʔλͷଟ͍-.ɽ -BSHFMBOHVBHFNPEFM--. • جຊతʹੑೳ㲍ύϥϝʔλɽ࠷ۙ#Λ͑ΔPQFOXFJHIU--.૿͖͑ͯͨɽ ݴޠϞσϧʢ-BOHVBHF.PEFM-.ʣ 3 𝑝 京都, の, 名物, は, 納豆 = 0.00000082 𝑝 京都, の, 名物, は, ラーメン = 0.00000197 𝑝 京都, の, 名物, は, 寿司 = 0.00000019 ɾɾɾ ژͷ໊ʁʁʁ / 𝑥" = argmax 𝑝 𝑥! , ⋯ , 𝑥"#! , 𝑥" 𝑥" ʙԯʢ#ʣݸ -
• ೖྗʢϓϩϯϓτʣΛ͢Δ͚ͩͰ༷ʑͳλεΫΛղ͚Δɽ • େنݴޠϞσϧͰߴ͍ੑೳΛୡ͢ΔͨΊʹɼ ଟ͘ͷϓϩϯϓτઃܭํ๏͕ఏҊ͞Ε͍ͯΔ [Liu+, ACM Comput. Surv., 2023]ɽ
• จ຺ֶशʢJODPOUFYUMFBSOJOH*$-ʣ ʢGFXTIPUֶशͱݺͿʣ[Brown+, NeurIPS, 2020] • ࢥߟ࿈ܕϓϩϯϓτ $IBJOPG5IPVHIUQSPNQUJOH$P5 [Wei+, NeurIPS, 2022] • 4FMGDPOTJTUFODZʢଟܾʣ [Wang+, ICLR, 2023] • LLMʹΑΔߴੑೳୡͷͨΊʹɼ Ϟσϧʢֶशσʔλύϥϝʔλɼreasoningͷ༗ແͳͲʣͷબఆɼ λεΫʹಛԽͨ͠ϫʔΫϑϩʔͷఆٛͳͲ͕ߦΘΕͯΔɽ --.Կ͕Ͱ͖Δ͔ʁ 5 -
• --.ʹɼ࣮తΛೖྗͨ͠Β࣮ίʔυͱ݁Ռ͕ಘΒΕΔɽ ͕ɼΑ͕͘ى͜Δɽ • --.͕ೖྗͷઐ༻ޠΛཧղͰ͖ͳ͍ɽ • --.ͷग़ྗܗ͕ࣜࢦࣔ௨ΓͱҟͳΔɽ • ίʔυಘΒΕ͕ͨɼಈ͔ͳ͍ɽ •
ҙਤ௨Γͷ࣮Λͤͣɼྫ֎ॲཧͷΈΛ࣮͢Δɽ • ʜ ྫɿ--.ʹΑΔ৽੍ޚख๏ͷ࣮ίʔσΟϯά 7 ʻೖྗʼख๏"ΑΓߴੑೳͳख๏ ΛఏҊ͢Δɽରܥɼϓϩηε9 ͱ͠ɼγϛϡϨʔγϣϯͰ༗༻ੑ Λࣔ͢ɽ --. ʻग़ྗʼϓϩηε9Λରͱͨ͠ ࣮ݧʹ͓͍ͯɼఏҊख๏͕ख๏" ΑΓ༏Ε͍ͯΔ͜ͱΛ࣮ূ͠· ͨ͠ɽίʔυɼʜ -
• --.ʹɼ࣮తΛೖྗͨ͠Β࣮ίʔυͱ݁Ռ͕ಘΒΕΔɽ ͕ɼΑ͕͘ى͜Δɽ • --.͕ೖྗͷઐ༻ޠΛཧղͰ͖ͳ͍ɽˠ3"(ʹΑΔ֦ࣝॆ • --.ͷग़ྗܗ͕ࣜࢦࣔ௨ΓͱҟͳΔɽ • ίʔυಘΒΕ͕ͨɼಈ͔ͳ͍ɽ •
ҙਤ௨Γͷ࣮Λͤͣɼྫ֎ॲཧͷΈΛ࣮͢Δɽ • ʜ ྫɿ--.ʹΑΔ৽੍ޚख๏ͷ࣮ίʔσΟϯά 8 ʻೖྗʼख๏"ΑΓߴੑೳͳख๏ ΛఏҊ͢Δɽରܥɼϓϩηε9 ͱ͠ɼγϛϡϨʔγϣϯͰ༗༻ੑ Λࣔ͢ɽ --. ʻग़ྗʼϓϩηε9Λରͱͨ͠ ࣮ݧʹ͓͍ͯɼఏҊख๏͕ख๏" ΑΓ༏Ε͍ͯΔ͜ͱΛ࣮ূ͠· ͨ͠ɽίʔυɼʜ -
• --.ʹɼ࣮తΛೖྗͨ͠Β࣮ίʔυͱ݁Ռ͕ಘΒΕΔɽ ͕ɼΑ͕͘ى͜Δɽ • --.͕ೖྗͷઐ༻ޠΛཧղͰ͖ͳ͍ɽˠ3"(ʹΑΔ֦ࣝॆ • --.ͷग़ྗܗ͕ࣜࢦࣔ௨ΓͱҟͳΔɽˠߏԽग़ྗʹΑΔܗ੍ࣜݶ • ίʔυಘΒΕ͕ͨɼಈ͔ͳ͍ɽ •
ҙਤ௨Γͷ࣮Λͤͣɼྫ֎ॲཧͷΈΛ࣮͢Δɽ • ʜ ྫɿ--.ʹΑΔ৽੍ޚख๏ͷ࣮ίʔσΟϯά 10 ʻೖྗʼख๏"ΑΓߴੑೳͳख๏ ΛఏҊ͢Δɽରܥɼϓϩηε9 ͱ͠ɼγϛϡϨʔγϣϯͰ༗༻ੑ Λࣔ͢ɽ --. ʻग़ྗʼϓϩηε9Λରͱͨ͠ ࣮ݧʹ͓͍ͯɼఏҊख๏͕ख๏" ΑΓ༏Ε͍ͯΔ͜ͱΛ࣮ূ͠· ͨ͠ɽίʔυɼʜ -
• --.ͷग़ྗܗࣜΛݻఆ͢Δɽ • ࣗ༝จݕূ͕ࠔͰͰ͋ΔͨΊɼεΩʔϚΛఆٛ͢Δɽ • ߏͱ༰ΛΘ͚ͯධՁ͢Δ͜ͱͰอकɾվળ͘͢͢͠Δɽ • +40/ܗࣜͷग़ྗ͕Α͘༻͍ΒΕ͍ͯΔɽ [Geng+, arXiv,
2025] • ߏԽ͢Δ͜ͱͰɼطଘͷϧʔϧνΣοΫ ׆༻Ͱ͖Δɽ ݕূՄೳʹ͢ΔͨΊͷඞਢٕज़ɿߏԽग़ྗ 11 ߏԽͳ͠ ʻೖྗʼख๏"ΑΓߴੑೳͳख๏ ΛఏҊ͢Δɽରܥɼϓϩηε9 ͱ͠ɼγϛϡϨʔγϣϯͰ༗༻ੑ Λࣔ͢ɽ --. ʻग़ྗʼϓϩηε9Λରͱͨ͠ ࣮ݧʹ͓͍ͯɼఏҊख๏͕ख๏" ΑΓ༏Ε͍ͯΔ͜ͱΛ࣮ূ͠· ͨ͠ɽίʔυɼʜ ߏԽ͋Γ ରϓϩηεɿϓϩηε9 มɿ<7 U ʜ> طଘख๏ʹΑΔੑೳɿʜ ʜ -
• --.ʹɼ࣮తΛೖྗͨ͠Β࣮ίʔυͱ݁Ռ͕ಘΒΕΔɽ ͕ɼΑ͕͘ى͜Δɽ • --.͕ೖྗͷઐ༻ޠΛཧղͰ͖ͳ͍ɽˠ3"(ʹΑΔ֦ࣝॆ • --.ͷग़ྗܗ͕ࣜࢦࣔ௨ΓͱҟͳΔɽˠߏԽग़ྗʹΑΔܗ੍ࣜݶ • ίʔυಘΒΕ͕ͨɼಈ͔ͳ͍ɽˠ--.ʹΑΔπʔϧ༻ •
ҙਤ௨Γͷ࣮Λͤͣɼྫ֎ॲཧͷΈΛ࣮͢Δɽ • ʜ ྫɿ--.ʹΑΔ৽੍ޚख๏ͷ࣮ίʔσΟϯά 12 ʻೖྗʼख๏"ΑΓߴੑೳͳख๏ ΛఏҊ͢Δɽରܥɼϓϩηε9 ͱ͠ɼγϛϡϨʔγϣϯͰ༗༻ੑ Λࣔ͢ɽ --. ʻग़ྗʼϓϩηε9Λରͱͨ͠ ࣮ݧʹ͓͍ͯɼఏҊख๏͕ख๏" ΑΓ༏Ε͍ͯΔ͜ͱΛ࣮ূ͠· ͨ͠ɽίʔυɼʜ -
• --.ʹɼ࣮తΛೖྗͨ͠Β࣮ίʔυͱ݁Ռ͕ಘΒΕΔɽ ͕ɼΑ͕͘ى͜Δɽ • --.͕ೖྗͷઐ༻ޠΛཧղͰ͖ͳ͍ɽˠ3"(ʹΑΔ֦ࣝॆ • --.ͷग़ྗܗ͕ࣜࢦࣔ௨ΓͱҟͳΔɽˠߏԽग़ྗʹΑΔܗ੍ࣜݶ • ίʔυಘΒΕ͕ͨɼಈ͔ͳ͍ɽˠ--.ʹΑΔπʔϧ༻ •
ҙਤ௨Γͷ࣮Λͤͣɼྫ֎ॲཧͷΈΛ࣮͢ΔɽˠΤʔδΣϯτʹΑΔ֬ೝ • ʜ ྫɿ--.ʹΑΔ৽੍ޚख๏ͷ࣮ίʔσΟϯά 14 ʻೖྗʼख๏"ΑΓߴੑೳͳख๏ ΛఏҊ͢Δɽରܥɼϓϩηε9 ͱ͠ɼγϛϡϨʔγϣϯͰ༗༻ੑ Λࣔ͢ɽ --. ʻग़ྗʼϓϩηε9Λରͱͨ͠ ࣮ݧʹ͓͍ͯɼఏҊख๏͕ख๏" ΑΓ༏Ε͍ͯΔ͜ͱΛ࣮ূ͠· ͨ͠ɽίʔυɼʜ -
• --.ʹɼ࣮తΛೖྗͨ͠Β࣮ίʔυͱ݁Ռ͕ಘΒΕΔɽ • ྑ͍݁ՌΛಘΔʹɼ͕ඞཁɽ • --.͕ೖྗͷઐ༻ޠΛཧղͰ͖ͳ͍ɽˠ3"(ʹΑΔ֦ࣝॆ • --.ͷग़ྗܗ͕ࣜࢦࣔ௨ΓͱҟͳΔɽˠߏԽग़ྗʹΑΔܗ੍ࣜݶ • ίʔυಘΒΕ͕ͨɼಈ͔ͳ͍ɽˠ--.ʹΑΔπʔϧ༻
• ҙਤ௨Γͷ࣮Λͤͣɼྫ֎ॲཧͷΈΛ࣮͢ΔɽˠΤʔδΣϯτʹΑΔ֬ೝ • ʜ --.ʹΑΔ৽੍ޚख๏ͷ࣮ίʔσΟϯάΛ࣮ݱ͢Δʹ 16 ʻೖྗʼख๏"ΑΓߴੑೳͳख๏ ΛఏҊ͢Δɽରܥɼϓϩηε9 ͱ͠ɼγϛϡϨʔγϣϯͰ༗༻ੑ Λࣔ͢ɽ --. ʻग़ྗʼϓϩηε9Λରͱͨ͠ ࣮ݧʹ͓͍ͯɼఏҊख๏͕ख๏" ΑΓ༏Ε͍ͯΔ͜ͱΛ࣮ূ͠· ͨ͠ɽίʔυɼʜ -
ୈճ৽ϓϩηε੍ޚݚڀձࢿྉΑΓ ϓϩϯϓτΤϯδχΞϦϯάࡐྉ։ൃͳͲͷݚڀ͕͋Δ͕ɼ "*ؔ࿈ͷֶձ΄ͲΓ্͕͍ͬͯͳ͍ɽ • ͷ "*$I&"OOVBM.FFUJOHʹ͓͍ͯɼMBSHFMBOHVBHFNPEFMʢ--.ʣ ΛλΠτϧʹؚΉൃද݅ɽҎԼͦͷҰ෦ɽ • 1SPNQU&OHJOFFSJOH%JSFDUFEJO$POUFYU-FBSOJOHPGBO--. XJUI*OUFHSBUFE
"VUPNBUFE4JNVMBUJPOGPS(FOFSBUJWF$IFNJDBM1SPDFTT • "-BSHF-BOHVBHF.PEFMGPS$IFNJDBM1SPDFTT&OHJOFFSJOH1*-05 • *OUFHSBUJOH$IFNJTUSZ,OPXMFEHFJO-BSHF-BOHVBHF.PEFMT7JB1SPNQU&OHJOFFSJOH • *OUFSQSFUBCMF'BVMU%FUFDUJPOJO$IFNJDBM1SPDFTTFT6TJOH-BSHF-BOHVBHF.PEFMT • -BSHF-BOHVBHF.PEFMT GPS%JTDPWFSJOH&RVBUJPOT • -BSHF-BOHVBHF.PEFM BOE.VMUJNPEBM-FBSOJOH'SBNFXPSLGPS$BUBMZTU%JTDPWFSZ Խֶֶʹ͓͚Δ--.ͷར༻ 17 -
• --.͕ೖྗͷઐ༻ޠΛཧղͰ͖ͳ͍ɽˠ3"(ʹΑΔ֦ࣝॆ • Φϯτϩδʔʢ0OUP$"1& [Morbach+, Eng. Appl. Artif. Intell., 2007]ʣͷ׆༻
• 14&ಛԽܕݴޠϞσϧ [Kato+, IFAC-PapersOnLine, 2022] ͷར༻ • --.ͷग़ྗܗ͕ࣜࢦࣔ௨ΓͱҟͳΔɽˠߏԽग़ྗʹΑΔܗ੍ࣜݶ • Խֶֶతࣝʹج੍ͮ͘ɿ ୯Ґɼ࣍ݩɼऩࢧɼਤͱͷ߹ੑʜ • ίʔυಘΒΕ͕ͨɼಈ͔ͳ͍ɽˠ--.ʹΑΔπʔϧ༻ • 14&ಛԽͷ࣮ߦڥʢྫ͑ɼϓϩηεγϛϡϨʔλʣͱͷଓ • ҙਤ௨Γͷ࣮Λͤͣɼྫ֎ॲཧͷΈΛ࣮͢ΔɽˠΤʔδΣϯτʹΑΔ֬ೝ • ্هͷٕज़Λूͨ͠ϚϧνΤʔδΣϯτγεςϜ 14&Ͱ--.Λ͏ࡍͷͱղܾࡦ 18 -
• Խֶϓϩηε҆શͷࣝάϥϑʴ (SBQI3"(Ͱ--.Λ֦ுɽ ԽֶۀஂࣄނͷۓٸରԠखॱΛ ࣗಈੜɾධՁͨ͠ɽ • $IFNJDBMQSPDFTTTBGFUZ LOPXMFEHFHSBQI $14,( ʴ(SBQI
3"(ʴ--. • ରͷΦϯτϩδʹج͖ͮɼ ࢹσʔλɾࣄނใࠂɾ๏نɾܭըॻ ͔Β$14,(Λߏங͠ɼ(SBQI3"( Ͱؔ࿈αϒάϥϑΛऔಘͯ͠--.ʹ ༩͑ɺۓٸରԠखॱΛੜ͢Δɽ 14&Ͱͷ--.׆༻ྫ̎ 20 [Zheng+, Can. J. Chem. Eng., 2025] -
• ϓϩηε੍ޚͱࣗવݴޠॲཧΛΈ߹Θͤͨݚڀݶఆతͳ͕Βଘࡏ • ओʹʮӡసࢧԉʯʮҟৗରԠʯʮઃܭࢧԉʯʮ҆શࢧԉʯͷΧςΰϦʹྨՄೳ • ٕज़ͷओ࣠ɺྨɾநग़ɾཁɾੜͱ͍ͬͨ/-1ͷجຊٕज़ͱͦͷ--.ల։ ϓϩηε੍ޚ Yࣗવݴޠॲཧͷطଘݚڀ 21 ӡసࢧԉ
ҟৗରԠ ੍ޚઃܭࢧԉ ҆શղੳ ϓϩηε੍ޚ º ࣗવݴޠॲཧʢ/-1جຊٕज़ͱ--.ʣ ྨ நग़ ཁ ੜ -
• 3VMFCBTFEͷεϖΠϯޠૢ࡞໋ྩΛ੍ޚ৴߸ʹม [Romano, IFAC Proc. Vol., 1992] • --.ʢ$IBU(-. --B."ʣͱ#&35ΛΈ߹Θͤͨ࢈ۀ2"γεςϜ
<-JV &OHJOFFSJOH > • "7&7"1SPDFTT4JNVMBUJPOͱ--.ΤʔδΣϯτΛ.$1Ͱͭͳ͗ɼରతɾ ࣗతʹϓϩηεγϛϡϨʔγϣϯΛߦ͏ΈͷఏҊ <-JBOH BS9JW > ӡసࢧԉɿࣗવݴޠʹΑΔૢ࡞ɾ࣭Ԡ 22 [Romano+, IFAC Proc. Vol., 1992] [Liang+, arXiv, 2026] -
• ϓϥϯτͷେͳΞϥʔϜΛରʹɼϚϧνϥϕϧނোྨϑϨʔϜϫʔΫΛߏங [Shatewakasi+, IECON, 2024] • อશϩά͔Βͷஅࢧԉʹ--.Λར༻ [Jose+, Expert Syst.
Appl., 2024] ҟৗରԠɿΞϥʔϜղੳͱஅࢧԉ 23 [Jose+, Expert Syst. Appl., 2024] [Shatewakasi+, IECON, 2024] -
• 1'%ΛςΩετԽ͠ɺ੍ޚߏΛ--.Ͱࣗಈੜ [Hirtreiter+, AIChE J. 2024] • ཁ༷͔݅Βߏཁૉநग़͠ɼ1-$ 1SPHSBNNBCMF-PHJD$POUSPMMFS1-$ ίʔυΛੜ
[Boudribila+, Ing. Syst. D. Inf., 2025] ઃܭࢧԉɿ1'%ˠ੍ޚߏɼςΩετˠ1-$ 24 [Hirtreiter+, AIChE J. 2024] -
• )";01จॻͷྨɾใநग़ [Feng+, Process Saf. Environ. Prot., 2021] • ࣝάϥϑΛ--.ͷࠜڌͱͯ͠׆༻
[Zheng+, Can. J. Chem. Eng., 2025] ҆શɾࣝཧɿ)";01ղੳͱจॻφϨοδͷ׆༻ 25 [Zheng+, Can. J. Chem. Eng., 2025] [Feng+, Process Saf. Environ. Prot., 2021] -
• Ԡ༻ྖҬͭɺ/-1ٕज़ྨɾநग़ɾੜɾର͕͍ͬͯΔ • ݱঢ়ͷ੍σʔλʢٕज़จॻɾϩάʣͷඋͱ࣮ͷݕূίετ • ࠓޙɺ--.ʴݕূʢ੍ɾ)*5-ʣʹΑΔࢧԉ͕ظ͞ΕΔʁ ૯ׅɿ1SPDFTT$POUSPMº /-1ͷలͱ՝ 26 ӡసࢧԉ
ҟৗରԠ ੍ޚઃܭࢧԉ ҆શղੳ ϓϩηε੍ޚ º ࣗવݴޠॲཧʢ/-1جຊٕज़ͱ--.ʣ º "*ٕज़ ྨ நग़ ཁ ੜ σʔλඋ ʢ࣮σʔλɾΦϯτϩδʣ υϝΠϯಛԽܕLLM ڧԽֶश ࿈߹ֶश ʢFederated learningʣ -
[Zhao+, arXiv, 2024] W. X. Zhao et al., “A Survey
of Large Language Models.” arXiv, 2024. [Liu+, ACM Comput. Surv., 2023]: P. Liu et al., “Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing.” ACM Comput. Surv. 55, 9, 2023. [Brown+, NeurIPS, 2020] T. B. Brown et al., “Language Models are Few-Shot Learners.” NeurIPS, 1877–1901, 2020. [Wei+, NeurIPS, 2022] J. Wei et al., “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.” NeurIPS, 24824–24837, 2022. [Wang+, ICLR, 2023] X. Wang et al., “Self-Consistency Improves Chain of Thought Reasoning in Language Models.” ICLR, 2023. [Lu+, arXiv, 2024] C. Lu et al., “The AI ScientistɿTowards Fully Automated Open-Ended Scientific Discovery.” arXiv, 2024. [Lewis+, NeurIPS, 2020] P. Lewis et al. “Retrieval-augmented generation for knowledge-intensive NLP tasks.” NeurIPS, 2020. [Geng+, arXiv, 2025] S. Geng et al. “JSONSchemaBench: A rigorous benchmark of structured outputs for language models." arXiv, 2025. [Guo+, ACL, 2024] Z. Guo et al., "StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Model." ACL, 2024. [Yao+, ICLR, 2023] S. Yao et al., "ReAct: Synergizing Reasoning and Acting in Language Models." ICLR, 2023. ࢀߟจݙ 27 -
[Morbach+, Eng. Appl. Artif. Intell., 2007] J. Morbach et al.,
"OntoCAPE-A large-scale ontology for chemical process engineering." Eng. Appl. Artif. Intell., 20, 2, 2007. [Kato+, IFAC-PapersOnLine, 2022] S. Kato et al., "ProcessBERT: A Pre-trained Language Model for Judging Equivalence of Variable Definitions in Process Models." IFAC-PapersOnLine, 55, 7, 2022. [Tao+, Comput. Chem. Eng., 2025] X. Tao et al., "From prompt design to iterative generation: Leveraging LLMs in PSE applications." Comput. Chem. Eng., 202, 2025. [Zheng+, Can. J. Che. Eng., 2025] C. Zheng et al., “Chemical process safety domain knowledge graph-enhanced LLM for efficient emergency response decision support.” Can. J. Che. Eng., 103, 10, 2025. [Romano+, IFAC Proc. Vol., 1992] J.M.G. Romano et al., “Natural language interface in control application to a pilot plant.” IFAC Proc. Vol, 25, 6, 1992. [Liu+, Engineering, 2025] R. Liu et al. “Knowledge enhanced industrial question-answering using large language models.” Engineering (Beijing, China), 2025. [Liang+, arXiv, 2026] J. Liang et al., “Large language model agent for user-friendly chemical process simulations.” arXiv, 2025. [Shatewakasi+, IECON, 2024] Y. Shatewakasi et al., “Towards NLP-driven online-classification of industrial alarm messages.” IECON, 2024. [Jose+, Expert Syst. Appl., 2024] S. Jose et al., “Advancing multimodal diagnostics: Integrating industrial textual data and domain knowledge with large language models.” Expert Syst. Appl., 255, 2024. ࢀߟจݙ 28 -
[Hirtreiter+, AIChE J. 2024] E. Hirtreiter et al., “Toward automatic
generation of control structures for process flow diagrams with large language models.” AIChE J. 70, 1, 2024. [Boudribila+, Ing. Syst. D. Inf., 2025] A. Boudribila et al., “Automatic generation of PLC control code from natural language requirement specifications.” Ing. Syst. D. Inf., 30, 6, 2025. [Feng+, Process Saf. Environ. Prot., 2021] X. Feng et al., “Application of natural language processing in HAZOP reports.” Process Saf. Environ. Prot., 155, 2021. ࢀߟจݙ 29